From 4ab4fa1032170b6ec50ffff0767096b3200dde8b Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Tue, 20 Aug 2019 15:33:23 -0700
Subject: drm/i915/psr: Make PSR registers relative to transcoders
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PSR registers are a mess, some have the full address while others just
have the additional offset from psr_mmio_base.

For BDW+ psr_mmio_base is nothing more than TRANSCODER_EDP_OFFSET +
0x800 and using it makes more difficult for people with an PSR
register address or PSR register name from from BSpec as i915 also
don't match the BSpec names.
For HSW psr_mmio_base is _DDI_BUF_CTL_A + 0x800 and PSR registers are
only available in DDIA.

Other reason to make relative to transcoder is that since BDW every
transcoder have PSR registers, so in theory it should be possible to
have PSR enabled in a non-eDP transcoder.

So for BDW+ we can use _TRANS2() to get the register offset of any
PSR register in any transcoder while for HSW we have _HSW_PSR_ADJ
that will calculate the register offset for the single PSR instance,
noting that we are already guarded about trying to enable PSR in other
port than DDIA on HSW by the 'if (dig_port->base.port != PORT_A)' in
intel_psr_compute_config(), this check should only be valid for HSW
and will be changed in future.
PSR2 registers and PSR_EVENT was added after Haswell so that is why
_PSR_ADJ() is not used in some macros.

The only registers that can not be relative to transcoder are
PSR_IMR and PSR_IIR that are not relative to anything, so keeping it
hardcoded. That changed for TGL but it will be handled in another
patch.

Also removing BDW_EDP_PSR_BASE from GVT because it is not used as it
is the only PSR register that GVT have.

v5:
- Macros changed to be more explicit about HSW (Dhinakaran)
- Squashed with the patch that added the tran parameter to the
macros (Dhinakaran)

v6:
- Checking for interruption errors after module reload in the
transcoder that will be used (Dhinakaran)
- Using lowercase to the registers offsets

v7:
- Removing IS_HASWELL() from registers macros(Jani)

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190820223325.27490-1-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 104 ++++++++++++++++++-------------
 drivers/gpu/drm/i915/gvt/handlers.c      |   2 +-
 drivers/gpu/drm/i915/i915_debugfs.c      |  18 +++---
 drivers/gpu/drm/i915/i915_drv.h          |   5 +-
 drivers/gpu/drm/i915/i915_reg.h          |  57 +++++++++++------
 5 files changed, 113 insertions(+), 73 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 3bfb720560c2..77232f6bca17 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -390,7 +390,7 @@ static void hsw_psr_setup_aux(struct intel_dp *intel_dp)
 
 	BUILD_BUG_ON(sizeof(aux_msg) > 20);
 	for (i = 0; i < sizeof(aux_msg); i += 4)
-		I915_WRITE(EDP_PSR_AUX_DATA(i >> 2),
+		I915_WRITE(EDP_PSR_AUX_DATA(dev_priv->psr.transcoder, i >> 2),
 			   intel_dp_pack_aux(&aux_msg[i], sizeof(aux_msg) - i));
 
 	aux_clock_divider = intel_dp->get_aux_clock_divider(intel_dp, 0);
@@ -401,7 +401,7 @@ static void hsw_psr_setup_aux(struct intel_dp *intel_dp)
 
 	/* Select only valid bits for SRD_AUX_CTL */
 	aux_ctl &= psr_aux_mask;
-	I915_WRITE(EDP_PSR_AUX_CTL, aux_ctl);
+	I915_WRITE(EDP_PSR_AUX_CTL(dev_priv->psr.transcoder), aux_ctl);
 }
 
 static void intel_psr_enable_sink(struct intel_dp *intel_dp)
@@ -491,8 +491,9 @@ static void hsw_activate_psr1(struct intel_dp *intel_dp)
 	if (INTEL_GEN(dev_priv) >= 8)
 		val |= EDP_PSR_CRC_ENABLE;
 
-	val |= I915_READ(EDP_PSR_CTL) & EDP_PSR_RESTORE_PSR_ACTIVE_CTX_MASK;
-	I915_WRITE(EDP_PSR_CTL, val);
+	val |= (I915_READ(EDP_PSR_CTL(dev_priv->psr.transcoder)) &
+		EDP_PSR_RESTORE_PSR_ACTIVE_CTX_MASK);
+	I915_WRITE(EDP_PSR_CTL(dev_priv->psr.transcoder), val);
 }
 
 static void hsw_activate_psr2(struct intel_dp *intel_dp)
@@ -528,9 +529,9 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 	 * PSR2 HW is incorrectly using EDP_PSR_TP1_TP3_SEL and BSpec is
 	 * recommending keep this bit unset while PSR2 is enabled.
 	 */
-	I915_WRITE(EDP_PSR_CTL, 0);
+	I915_WRITE(EDP_PSR_CTL(dev_priv->psr.transcoder), 0);
 
-	I915_WRITE(EDP_PSR2_CTL, val);
+	I915_WRITE(EDP_PSR2_CTL(dev_priv->psr.transcoder), val);
 }
 
 static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
@@ -606,10 +607,9 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 
 	/*
 	 * HSW spec explicitly says PSR is tied to port A.
-	 * BDW+ platforms with DDI implementation of PSR have different
-	 * PSR registers per transcoder and we only implement transcoder EDP
-	 * ones. Since by Display design transcoder EDP is tied to port A
-	 * we can safely escape based on the port A.
+	 * BDW+ platforms have a instance of PSR registers per transcoder but
+	 * for now it only supports one instance of PSR, so lets keep it
+	 * hardcoded to PORT_A
 	 */
 	if (dig_port->base.port != PORT_A) {
 		DRM_DEBUG_KMS("PSR condition failed: Port not supported\n");
@@ -649,8 +649,8 @@ static void intel_psr_activate(struct intel_dp *intel_dp)
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 
 	if (INTEL_GEN(dev_priv) >= 9)
-		WARN_ON(I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE);
-	WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
+		WARN_ON(I915_READ(EDP_PSR2_CTL(dev_priv->psr.transcoder)) & EDP_PSR2_ENABLE);
+	WARN_ON(I915_READ(EDP_PSR_CTL(dev_priv->psr.transcoder)) & EDP_PSR_ENABLE);
 	WARN_ON(dev_priv->psr.active);
 	lockdep_assert_held(&dev_priv->psr.lock);
 
@@ -720,19 +720,37 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp,
 	if (INTEL_GEN(dev_priv) < 11)
 		mask |= EDP_PSR_DEBUG_MASK_DISP_REG_WRITE;
 
-	I915_WRITE(EDP_PSR_DEBUG, mask);
+	I915_WRITE(EDP_PSR_DEBUG(dev_priv->psr.transcoder), mask);
 }
 
 static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
 				    const struct intel_crtc_state *crtc_state)
 {
 	struct intel_dp *intel_dp = dev_priv->psr.dp;
+	u32 val;
 
 	WARN_ON(dev_priv->psr.enabled);
 
 	dev_priv->psr.psr2_enabled = intel_psr2_enabled(dev_priv, crtc_state);
 	dev_priv->psr.busy_frontbuffer_bits = 0;
 	dev_priv->psr.pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	dev_priv->psr.transcoder = crtc_state->cpu_transcoder;
+
+	/*
+	 * If a PSR error happened and the driver is reloaded, the EDP_PSR_IIR
+	 * will still keep the error set even after the reset done in the
+	 * irq_preinstall and irq_uninstall hooks.
+	 * And enabling in this situation cause the screen to freeze in the
+	 * first time that PSR HW tries to activate so lets keep PSR disabled
+	 * to avoid any rendering problems.
+	 */
+	val = I915_READ(EDP_PSR_IIR);
+	val &= EDP_PSR_ERROR(edp_psr_shift(dev_priv->psr.transcoder));
+	if (val) {
+		dev_priv->psr.sink_not_reliable = true;
+		DRM_DEBUG_KMS("PSR interruption error set, not enabling PSR\n");
+		return;
+	}
 
 	DRM_DEBUG_KMS("Enabling PSR%s\n",
 		      dev_priv->psr.psr2_enabled ? "2" : "1");
@@ -782,20 +800,27 @@ static void intel_psr_exit(struct drm_i915_private *dev_priv)
 	u32 val;
 
 	if (!dev_priv->psr.active) {
-		if (INTEL_GEN(dev_priv) >= 9)
-			WARN_ON(I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE);
-		WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
+		if (INTEL_GEN(dev_priv) >= 9) {
+			val = I915_READ(EDP_PSR2_CTL(dev_priv->psr.transcoder));
+			WARN_ON(val & EDP_PSR2_ENABLE);
+		}
+
+		val = I915_READ(EDP_PSR_CTL(dev_priv->psr.transcoder));
+		WARN_ON(val & EDP_PSR_ENABLE);
+
 		return;
 	}
 
 	if (dev_priv->psr.psr2_enabled) {
-		val = I915_READ(EDP_PSR2_CTL);
+		val = I915_READ(EDP_PSR2_CTL(dev_priv->psr.transcoder));
 		WARN_ON(!(val & EDP_PSR2_ENABLE));
-		I915_WRITE(EDP_PSR2_CTL, val & ~EDP_PSR2_ENABLE);
+		val &= ~EDP_PSR2_ENABLE;
+		I915_WRITE(EDP_PSR2_CTL(dev_priv->psr.transcoder), val);
 	} else {
-		val = I915_READ(EDP_PSR_CTL);
+		val = I915_READ(EDP_PSR_CTL(dev_priv->psr.transcoder));
 		WARN_ON(!(val & EDP_PSR_ENABLE));
-		I915_WRITE(EDP_PSR_CTL, val & ~EDP_PSR_ENABLE);
+		val &= ~EDP_PSR_ENABLE;
+		I915_WRITE(EDP_PSR_CTL(dev_priv->psr.transcoder), val);
 	}
 	dev_priv->psr.active = false;
 }
@@ -817,10 +842,10 @@ static void intel_psr_disable_locked(struct intel_dp *intel_dp)
 	intel_psr_exit(dev_priv);
 
 	if (dev_priv->psr.psr2_enabled) {
-		psr_status = EDP_PSR2_STATUS;
+		psr_status = EDP_PSR2_STATUS(dev_priv->psr.transcoder);
 		psr_status_mask = EDP_PSR2_STATUS_STATE_MASK;
 	} else {
-		psr_status = EDP_PSR_STATUS;
+		psr_status = EDP_PSR_STATUS(dev_priv->psr.transcoder);
 		psr_status_mask = EDP_PSR_STATUS_STATE_MASK;
 	}
 
@@ -963,7 +988,8 @@ int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state,
 	 * defensive enough to cover everything.
 	 */
 
-	return __intel_wait_for_register(&dev_priv->uncore, EDP_PSR_STATUS,
+	return __intel_wait_for_register(&dev_priv->uncore,
+					 EDP_PSR_STATUS(dev_priv->psr.transcoder),
 					 EDP_PSR_STATUS_STATE_MASK,
 					 EDP_PSR_STATUS_STATE_IDLE, 2, 50,
 					 out_value);
@@ -979,10 +1005,10 @@ static bool __psr_wait_for_idle_locked(struct drm_i915_private *dev_priv)
 		return false;
 
 	if (dev_priv->psr.psr2_enabled) {
-		reg = EDP_PSR2_STATUS;
+		reg = EDP_PSR2_STATUS(dev_priv->psr.transcoder);
 		mask = EDP_PSR2_STATUS_STATE_MASK;
 	} else {
-		reg = EDP_PSR_STATUS;
+		reg = EDP_PSR_STATUS(dev_priv->psr.transcoder);
 		mask = EDP_PSR_STATUS_STATE_MASK;
 	}
 
@@ -1208,36 +1234,24 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
  */
 void intel_psr_init(struct drm_i915_private *dev_priv)
 {
-	u32 val;
-
 	if (!HAS_PSR(dev_priv))
 		return;
 
-	dev_priv->psr_mmio_base = IS_HASWELL(dev_priv) ?
-		HSW_EDP_PSR_BASE : BDW_EDP_PSR_BASE;
-
 	if (!dev_priv->psr.sink_support)
 		return;
 
+	if (IS_HASWELL(dev_priv))
+		/*
+		 * HSW don't have PSR registers on the same space as transcoder
+		 * so set this to a value that when subtract to the register
+		 * in transcoder space results in the right offset for HSW
+		 */
+		dev_priv->hsw_psr_mmio_adjust = _SRD_CTL_EDP - _HSW_EDP_PSR_BASE;
+
 	if (i915_modparams.enable_psr == -1)
 		if (INTEL_GEN(dev_priv) < 9 || !dev_priv->vbt.psr.enable)
 			i915_modparams.enable_psr = 0;
 
-	/*
-	 * If a PSR error happened and the driver is reloaded, the EDP_PSR_IIR
-	 * will still keep the error set even after the reset done in the
-	 * irq_preinstall and irq_uninstall hooks.
-	 * And enabling in this situation cause the screen to freeze in the
-	 * first time that PSR HW tries to activate so lets keep PSR disabled
-	 * to avoid any rendering problems.
-	 */
-	val = I915_READ(EDP_PSR_IIR);
-	val &= EDP_PSR_ERROR(edp_psr_shift(TRANSCODER_EDP));
-	if (val) {
-		DRM_DEBUG_KMS("PSR interruption error set\n");
-		dev_priv->psr.sink_not_reliable = true;
-	}
-
 	/* Set link_standby x link_off defaults */
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		/* HSW and BDW require workarounds that we don't implement. */
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 25f78196b964..45a9124e53b6 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -2796,7 +2796,7 @@ static int init_broadwell_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(CHICKEN_PIPESL_1(PIPE_C), D_BDW_PLUS);
 
 	MMIO_D(WM_MISC, D_BDW);
-	MMIO_D(_MMIO(BDW_EDP_PSR_BASE), D_BDW);
+	MMIO_D(_MMIO(_SRD_CTL_EDP), D_BDW);
 
 	MMIO_D(_MMIO(0x6671c), D_BDW_PLUS);
 	MMIO_D(_MMIO(0x66c00), D_BDW_PLUS);
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index b0f51591f2e4..e103fcba6435 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2133,7 +2133,7 @@ psr_source_status(struct drm_i915_private *dev_priv, struct seq_file *m)
 			"BUF_ON",
 			"TG_ON"
 		};
-		val = I915_READ(EDP_PSR2_STATUS);
+		val = I915_READ(EDP_PSR2_STATUS(dev_priv->psr.transcoder));
 		status_val = (val & EDP_PSR2_STATUS_STATE_MASK) >>
 			      EDP_PSR2_STATUS_STATE_SHIFT;
 		if (status_val < ARRAY_SIZE(live_status))
@@ -2149,7 +2149,7 @@ psr_source_status(struct drm_i915_private *dev_priv, struct seq_file *m)
 			"SRDOFFACK",
 			"SRDENT_ON",
 		};
-		val = I915_READ(EDP_PSR_STATUS);
+		val = I915_READ(EDP_PSR_STATUS(dev_priv->psr.transcoder));
 		status_val = (val & EDP_PSR_STATUS_STATE_MASK) >>
 			      EDP_PSR_STATUS_STATE_SHIFT;
 		if (status_val < ARRAY_SIZE(live_status))
@@ -2192,10 +2192,10 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 		goto unlock;
 
 	if (psr->psr2_enabled) {
-		val = I915_READ(EDP_PSR2_CTL);
+		val = I915_READ(EDP_PSR2_CTL(dev_priv->psr.transcoder));
 		enabled = val & EDP_PSR2_ENABLE;
 	} else {
-		val = I915_READ(EDP_PSR_CTL);
+		val = I915_READ(EDP_PSR_CTL(dev_priv->psr.transcoder));
 		enabled = val & EDP_PSR_ENABLE;
 	}
 	seq_printf(m, "Source PSR ctl: %s [0x%08x]\n",
@@ -2208,7 +2208,8 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 	 * SKL+ Perf counter is reset to 0 everytime DC state is entered
 	 */
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
-		val = I915_READ(EDP_PSR_PERF_CNT) & EDP_PSR_PERF_CNT_MASK;
+		val = I915_READ(EDP_PSR_PERF_CNT(dev_priv->psr.transcoder));
+		val &= EDP_PSR_PERF_CNT_MASK;
 		seq_printf(m, "Performance counter: %u\n", val);
 	}
 
@@ -2226,8 +2227,11 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 		 * Reading all 3 registers before hand to minimize crossing a
 		 * frame boundary between register reads
 		 */
-		for (frame = 0; frame < PSR2_SU_STATUS_FRAMES; frame += 3)
-			su_frames_val[frame / 3] = I915_READ(PSR2_SU_STATUS(frame));
+		for (frame = 0; frame < PSR2_SU_STATUS_FRAMES; frame += 3) {
+			val = I915_READ(PSR2_SU_STATUS(dev_priv->psr.transcoder,
+						       frame));
+			su_frames_val[frame / 3] = val;
+		}
 
 		seq_puts(m, "Frame:\tPSR2 SU blocks:\n");
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 1d725e0bba40..048896b1348b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -479,6 +479,7 @@ struct i915_psr {
 	bool enabled;
 	struct intel_dp *dp;
 	enum pipe pipe;
+	enum transcoder transcoder;
 	bool active;
 	struct work_struct work;
 	unsigned busy_frontbuffer_bits;
@@ -1330,11 +1331,11 @@ struct drm_i915_private {
 	 */
 	u32 gpio_mmio_base;
 
+	u32 hsw_psr_mmio_adjust;
+
 	/* MMIO base address for MIPI regs */
 	u32 mipi_mmio_base;
 
-	u32 psr_mmio_base;
-
 	u32 pps_mmio_base;
 
 	wait_queue_head_t gmbus_wait_queue;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 2abd199093c5..a092b34c269d 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4186,10 +4186,17 @@ enum {
 #define PIPESRC(trans)		_MMIO_TRANS2(trans, _PIPEASRC)
 #define PIPE_MULT(trans)	_MMIO_TRANS2(trans, _PIPE_MULT_A)
 
-/* HSW+ eDP PSR registers */
-#define HSW_EDP_PSR_BASE	0x64800
-#define BDW_EDP_PSR_BASE	0x6f800
-#define EDP_PSR_CTL				_MMIO(dev_priv->psr_mmio_base + 0)
+/*
+ * HSW+ eDP PSR registers
+ *
+ * HSW PSR registers are relative to DDIA(_DDI_BUF_CTL_A + 0x800) with just one
+ * instance of it
+ */
+#define _HSW_EDP_PSR_BASE			0x64800
+#define _SRD_CTL_A				0x60800
+#define _SRD_CTL_EDP				0x6f800
+#define _PSR_ADJ(tran, reg)			(_TRANS2(tran, reg) - dev_priv->hsw_psr_mmio_adjust)
+#define EDP_PSR_CTL(tran)			_MMIO(_PSR_ADJ(tran, _SRD_CTL_A))
 #define   EDP_PSR_ENABLE			(1 << 31)
 #define   BDW_PSR_SINGLE_FRAME			(1 << 30)
 #define   EDP_PSR_RESTORE_PSR_ACTIVE_CTX_MASK	(1 << 29) /* SW can't modify */
@@ -4226,16 +4233,22 @@ enum {
 #define   EDP_PSR_TRANSCODER_A_SHIFT		8
 #define   EDP_PSR_TRANSCODER_EDP_SHIFT		0
 
-#define EDP_PSR_AUX_CTL				_MMIO(dev_priv->psr_mmio_base + 0x10)
+#define _SRD_AUX_CTL_A				0x60810
+#define _SRD_AUX_CTL_EDP			0x6f810
+#define EDP_PSR_AUX_CTL(tran)			_MMIO(_PSR_ADJ(tran, _SRD_AUX_CTL_A))
 #define   EDP_PSR_AUX_CTL_TIME_OUT_MASK		(3 << 26)
 #define   EDP_PSR_AUX_CTL_MESSAGE_SIZE_MASK	(0x1f << 20)
 #define   EDP_PSR_AUX_CTL_PRECHARGE_2US_MASK	(0xf << 16)
 #define   EDP_PSR_AUX_CTL_ERROR_INTERRUPT	(1 << 11)
 #define   EDP_PSR_AUX_CTL_BIT_CLOCK_2X_MASK	(0x7ff)
 
-#define EDP_PSR_AUX_DATA(i)			_MMIO(dev_priv->psr_mmio_base + 0x14 + (i) * 4) /* 5 registers */
+#define _SRD_AUX_DATA_A				0x60814
+#define _SRD_AUX_DATA_EDP			0x6f814
+#define EDP_PSR_AUX_DATA(tran, i)		_MMIO(_PSR_ADJ(tran, _SRD_AUX_DATA_A) + (i) + 4) /* 5 registers */
 
-#define EDP_PSR_STATUS				_MMIO(dev_priv->psr_mmio_base + 0x40)
+#define _SRD_STATUS_A				0x60840
+#define _SRD_STATUS_EDP				0x6f840
+#define EDP_PSR_STATUS(tran)			_MMIO(_PSR_ADJ(tran, _SRD_STATUS_A))
 #define   EDP_PSR_STATUS_STATE_MASK		(7 << 29)
 #define   EDP_PSR_STATUS_STATE_SHIFT		29
 #define   EDP_PSR_STATUS_STATE_IDLE		(0 << 29)
@@ -4260,10 +4273,15 @@ enum {
 #define   EDP_PSR_STATUS_SENDING_TP1		(1 << 4)
 #define   EDP_PSR_STATUS_IDLE_MASK		0xf
 
-#define EDP_PSR_PERF_CNT		_MMIO(dev_priv->psr_mmio_base + 0x44)
+#define _SRD_PERF_CNT_A			0x60844
+#define _SRD_PERF_CNT_EDP		0x6f844
+#define EDP_PSR_PERF_CNT(tran)		_MMIO(_PSR_ADJ(tran, _SRD_PERF_CNT_A))
 #define   EDP_PSR_PERF_CNT_MASK		0xffffff
 
-#define EDP_PSR_DEBUG				_MMIO(dev_priv->psr_mmio_base + 0x60) /* PSR_MASK on SKL+ */
+/* PSR_MASK on SKL+ */
+#define _SRD_DEBUG_A				0x60860
+#define _SRD_DEBUG_EDP				0x6f860
+#define EDP_PSR_DEBUG(tran)			_MMIO(_PSR_ADJ(tran, _SRD_DEBUG_A))
 #define   EDP_PSR_DEBUG_MASK_MAX_SLEEP         (1 << 28)
 #define   EDP_PSR_DEBUG_MASK_LPSP              (1 << 27)
 #define   EDP_PSR_DEBUG_MASK_MEMUP             (1 << 26)
@@ -4271,7 +4289,9 @@ enum {
 #define   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE    (1 << 16) /* Reserved in ICL+ */
 #define   EDP_PSR_DEBUG_EXIT_ON_PIXEL_UNDERRUN (1 << 15) /* SKL+ */
 
-#define EDP_PSR2_CTL			_MMIO(0x6f900)
+#define _PSR2_CTL_A			0x60900
+#define _PSR2_CTL_EDP			0x6f900
+#define EDP_PSR2_CTL(tran)		_MMIO_TRANS2(tran, _PSR2_CTL_A)
 #define   EDP_PSR2_ENABLE		(1 << 31)
 #define   EDP_SU_TRACK_ENABLE		(1 << 30)
 #define   EDP_Y_COORDINATE_VALID	(1 << 26) /* GLK and CNL+ */
@@ -4293,8 +4313,8 @@ enum {
 #define _PSR_EVENT_TRANS_B			0x61848
 #define _PSR_EVENT_TRANS_C			0x62848
 #define _PSR_EVENT_TRANS_D			0x63848
-#define _PSR_EVENT_TRANS_EDP			0x6F848
-#define PSR_EVENT(trans)			_MMIO_TRANS2(trans, _PSR_EVENT_TRANS_A)
+#define _PSR_EVENT_TRANS_EDP			0x6f848
+#define PSR_EVENT(tran)				_MMIO_TRANS2(tran, _PSR_EVENT_TRANS_A)
 #define  PSR_EVENT_PSR2_WD_TIMER_EXPIRE		(1 << 17)
 #define  PSR_EVENT_PSR2_DISABLED		(1 << 16)
 #define  PSR_EVENT_SU_DIRTY_FIFO_UNDERRUN	(1 << 15)
@@ -4312,15 +4332,16 @@ enum {
 #define  PSR_EVENT_LPSP_MODE_EXIT		(1 << 1)
 #define  PSR_EVENT_PSR_DISABLE			(1 << 0)
 
-#define EDP_PSR2_STATUS			_MMIO(0x6f940)
+#define _PSR2_STATUS_A			0x60940
+#define _PSR2_STATUS_EDP		0x6f940
+#define EDP_PSR2_STATUS(tran)		_MMIO_TRANS2(tran, _PSR2_STATUS_A)
 #define EDP_PSR2_STATUS_STATE_MASK     (0xf << 28)
 #define EDP_PSR2_STATUS_STATE_SHIFT    28
 
-#define _PSR2_SU_STATUS_0		0x6F914
-#define _PSR2_SU_STATUS_1		0x6F918
-#define _PSR2_SU_STATUS_2		0x6F91C
-#define _PSR2_SU_STATUS(index)		_MMIO(_PICK_EVEN((index), _PSR2_SU_STATUS_0, _PSR2_SU_STATUS_1))
-#define PSR2_SU_STATUS(frame)		(_PSR2_SU_STATUS((frame) / 3))
+#define _PSR2_SU_STATUS_A		0x60914
+#define _PSR2_SU_STATUS_EDP		0x6f914
+#define _PSR2_SU_STATUS(tran, index)	_MMIO(_TRANS2(tran, _PSR2_SU_STATUS_A) + (index) * 4)
+#define PSR2_SU_STATUS(tran, frame)	(_PSR2_SU_STATUS(tran, (frame) / 3))
 #define PSR2_SU_STATUS_SHIFT(frame)	(((frame) % 3) * 10)
 #define PSR2_SU_STATUS_MASK(frame)	(0x3ff << PSR2_SU_STATUS_SHIFT(frame))
 #define PSR2_SU_STATUS_FRAMES		8
-- 
cgit v1.2.3


From 99fc38b12095cd0ca9fc5b8c8e27e827dff6ed34 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Tue, 20 Aug 2019 15:33:24 -0700
Subject: drm/i915: Add transcoder restriction to PSR2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

According to PSR2_CTL definition in BSpec there is only one instance
of PSR2_CTL. Platforms gen < 12 with EDP transcoder only support PSR2
on TRANSCODER_EDP while on TGL PSR2 is only supported by
TRANSCODER_A.

Since BDW PSR is allowed on any port, but we need to restrict by
transcoder.

v8: Renamed _psr2_supported_in_trans() to psr2_supported() (Lucas)

v9: Renamed psr2_supported() to transcoder_has_psr2() (Ville)

BSpec: 7713
BSpec: 20584
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Anshuman Gupta <anshuman.gupta@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190820223325.27490-2-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 77232f6bca17..771d9a40bf12 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -534,6 +534,15 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 	I915_WRITE(EDP_PSR2_CTL(dev_priv->psr.transcoder), val);
 }
 
+static bool
+transcoder_has_psr2(struct drm_i915_private *dev_priv, enum transcoder trans)
+{
+	if (INTEL_GEN(dev_priv) >= 12)
+		return trans == TRANSCODER_A;
+	else
+		return trans == TRANSCODER_EDP;
+}
+
 static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 				    struct intel_crtc_state *crtc_state)
 {
@@ -545,6 +554,12 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 	if (!dev_priv->psr.sink_psr2_support)
 		return false;
 
+	if (!transcoder_has_psr2(dev_priv, crtc_state->cpu_transcoder)) {
+		DRM_DEBUG_KMS("PSR2 not supported in transcoder %s\n",
+			      transcoder_name(crtc_state->cpu_transcoder));
+		return false;
+	}
+
 	/*
 	 * DSC and PSR2 cannot be enabled simultaneously. If a requested
 	 * resolution requires DSC to be enabled, priority is given to DSC
-- 
cgit v1.2.3


From df7415bfc06f8ee482a510aea39c12121e409dcc Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Tue, 20 Aug 2019 15:33:25 -0700
Subject: drm/i915: Do not unmask PSR interruption in IRQ postinstall
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

No need to unmask PSR interrutpion if PSR is not enabled, better move
the call to intel_psr_enable_source().

v2: Renamed intel_psr_irq_control() to psr_irq_control() (Lucas)

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190820223325.27490-3-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 6 ++++--
 drivers/gpu/drm/i915/display/intel_psr.h | 1 -
 drivers/gpu/drm/i915/i915_irq.c          | 2 --
 3 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 771d9a40bf12..28b62e587204 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -105,7 +105,7 @@ static int edp_psr_shift(enum transcoder cpu_transcoder)
 	}
 }
 
-void intel_psr_irq_control(struct drm_i915_private *dev_priv, u32 debug)
+static void psr_irq_control(struct drm_i915_private *dev_priv, u32 debug)
 {
 	u32 debug_mask, mask;
 	enum transcoder cpu_transcoder;
@@ -736,6 +736,8 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp,
 		mask |= EDP_PSR_DEBUG_MASK_DISP_REG_WRITE;
 
 	I915_WRITE(EDP_PSR_DEBUG(dev_priv->psr.transcoder), mask);
+
+	psr_irq_control(dev_priv, dev_priv->psr.debug);
 }
 
 static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
@@ -1108,7 +1110,7 @@ int intel_psr_debug_set(struct drm_i915_private *dev_priv, u64 val)
 
 	old_mode = dev_priv->psr.debug & I915_PSR_DEBUG_MODE_MASK;
 	dev_priv->psr.debug = val;
-	intel_psr_irq_control(dev_priv, dev_priv->psr.debug);
+	psr_irq_control(dev_priv, dev_priv->psr.debug);
 
 	mutex_unlock(&dev_priv->psr.lock);
 
diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h
index dc818826f36d..46e4de8b8cd5 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.h
+++ b/drivers/gpu/drm/i915/display/intel_psr.h
@@ -30,7 +30,6 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 void intel_psr_init(struct drm_i915_private *dev_priv);
 void intel_psr_compute_config(struct intel_dp *intel_dp,
 			      struct intel_crtc_state *crtc_state);
-void intel_psr_irq_control(struct drm_i915_private *dev_priv, u32 debug);
 void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir);
 void intel_psr_short_pulse(struct intel_dp *intel_dp);
 int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state,
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 37e3dd3c1a9d..77391d8325bf 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3684,7 +3684,6 @@ static void ironlake_irq_postinstall(struct drm_i915_private *dev_priv)
 
 	if (IS_HASWELL(dev_priv)) {
 		gen3_assert_iir_is_zero(uncore, EDP_PSR_IIR);
-		intel_psr_irq_control(dev_priv, dev_priv->psr.debug);
 		display_mask |= DE_EDP_PSR_INT_HSW;
 	}
 
@@ -3795,7 +3794,6 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 		de_port_enables |= GEN8_PORT_DP_A_HOTPLUG;
 
 	gen3_assert_iir_is_zero(uncore, EDP_PSR_IIR);
-	intel_psr_irq_control(dev_priv, dev_priv->psr.debug);
 
 	for_each_pipe(dev_priv, pipe) {
 		dev_priv->de_irq_mask[pipe] = ~de_pipe_masked;
-- 
cgit v1.2.3


From cee508a0bddba1627575de2e41fb8e321fa380a8 Mon Sep 17 00:00:00 2001
From: Anusha Srivatsa <anusha.srivatsa@intel.com>
Date: Tue, 20 Aug 2019 15:30:59 -0700
Subject: drm/dp/dsc: Add Support for all BPCs supported by TGL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DSC engine on ICL supports only 8 and 10 BPC as the input
BPC. But DSC engine in TGL supports 8, 10 and 12 BPC.
Add 12 BPC support for DSC while calculating compression
configuration.

v2: Remove the separate define TGL_DP_DSC_MAX_SUPPORTED_BPC
and use the value directly.(More such defines can be removed
as part of future patches). (Ville)

v3: Use values directly instead of accessing the defines
everytime for min and max DSC BPC.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190820223059.18052-1-anusha.srivatsa@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 921ad0a2f7ba..23908da1cd5d 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -70,8 +70,6 @@
 
 /* DP DSC small joiner has 2 FIFOs each of 640 x 6 bytes */
 #define DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER	61440
-#define DP_DSC_MIN_SUPPORTED_BPC		8
-#define DP_DSC_MAX_SUPPORTED_BPC		10
 
 /* DP DSC throughput values used for slice count calculations KPixels/s */
 #define DP_DSC_PEAK_PIXEL_RATE			2720000
@@ -1915,11 +1913,17 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 	if (!intel_dp_supports_dsc(intel_dp, pipe_config))
 		return -EINVAL;
 
-	dsc_max_bpc = min_t(u8, DP_DSC_MAX_SUPPORTED_BPC,
-			    conn_state->max_requested_bpc);
+	/* Max DSC Input BPC for ICL is 10 and for TGL+ is 12 */
+	if (INTEL_GEN(dev_priv) >= 12)
+		dsc_max_bpc = min_t(u8, 12, conn_state->max_requested_bpc);
+	else
+		dsc_max_bpc = min_t(u8, 10,
+				    conn_state->max_requested_bpc);
 
 	pipe_bpp = intel_dp_dsc_compute_bpp(intel_dp, dsc_max_bpc);
-	if (pipe_bpp < DP_DSC_MIN_SUPPORTED_BPC * 3) {
+
+	/* Min Input BPC for ICL+ is 8 */
+	if (pipe_bpp < 8 * 3) {
 		DRM_DEBUG_KMS("No DSC support for less than 8bpc\n");
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From d4c61c4a16decd8ace8660f22c81609a539fccba Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Wed, 21 Aug 2019 14:59:50 -0700
Subject: drm/i915/dp: Fix DSC enable code to use cpu_transcoder instead of
 encoder->type

This patch fixes the intel_configure_pps_for_dsc_encoder() function to use
cpu_transcoder instead of encoder->type to select the correct DSC registers
that was wrongly used in the original patch for one DSC register isntance.

Fixes: 7182414e2530 ("drm/i915/dp: Configure i915 Picture parameter Set registers during DSC enabling")
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.0+
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190821215950.24223-1-manasi.d.navare@intel.com
---
 drivers/gpu/drm/i915/display/intel_vdsc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c
index 598ddb60f9fb..d4fb7f16f9f6 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.c
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.c
@@ -547,7 +547,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 	pps_val |= DSC_PIC_HEIGHT(vdsc_cfg->pic_height) |
 		DSC_PIC_WIDTH(vdsc_cfg->pic_width / num_vdsc_instances);
 	DRM_INFO("PPS2 = 0x%08x\n", pps_val);
-	if (encoder->type == INTEL_OUTPUT_EDP) {
+	if (cpu_transcoder == TRANSCODER_EDP) {
 		I915_WRITE(DSCA_PICTURE_PARAMETER_SET_2, pps_val);
 		/*
 		 * If 2 VDSC instances are needed, configure PPS for second
-- 
cgit v1.2.3


From b3c0692f36a44bd02ee8ccc5bed972a36fbf2e99 Mon Sep 17 00:00:00 2001
From: Michel Thierry <michel.thierry@intel.com>
Date: Fri, 23 Aug 2019 01:20:33 -0700
Subject: drm/i915/tgl: Move GTCR register to cope with GAM MMIO address remap

GAM registers located in the 0x4xxx range have been relocated to 0xCxxx;
this is to make space for global MOCS registers.

v2: Rename register and bitfield to its new name (suggested by Mika)

HSD: 399379
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823082055.5992-2-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h | 3 +++
 drivers/gpu/drm/i915/i915_gem_gtt.c        | 8 +++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
index edf194d23c6b..1949346e714e 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_reg.h
@@ -83,6 +83,9 @@
 #define GEN8_GTCR			_MMIO(0x4274)
 #define   GEN8_GTCR_INVALIDATE		  (1<<0)
 
+#define GEN12_GUC_TLB_INV_CR		_MMIO(0xcee8)
+#define   GEN12_GUC_TLB_INV_CR_INVALIDATE	(1 << 0)
+
 #define GUC_ARAT_C6DIS			_MMIO(0xA178)
 
 #define GUC_SHIM_CONTROL		_MMIO(0xc064)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 0b81e0b64393..2a425db1cfd8 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -132,9 +132,15 @@ static void gen6_ggtt_invalidate(struct i915_ggtt *ggtt)
 static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
 {
 	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
+	struct drm_i915_private *i915 = ggtt->vm.i915;
 
 	gen6_ggtt_invalidate(ggtt);
-	intel_uncore_write_fw(uncore, GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+
+	if (INTEL_GEN(i915) >= 12)
+		intel_uncore_write_fw(uncore, GEN12_GUC_TLB_INV_CR,
+				      GEN12_GUC_TLB_INV_CR_INVALIDATE);
+	else
+		intel_uncore_write_fw(uncore, GEN8_GTCR, GEN8_GTCR_INVALIDATE);
 }
 
 static void gmch_ggtt_invalidate(struct i915_ggtt *ggtt)
-- 
cgit v1.2.3


From 5d86923060fce88a4dda8d8c9c5d5eb32f37c37b Mon Sep 17 00:00:00 2001
From: Michel Thierry <michel.thierry@intel.com>
Date: Fri, 23 Aug 2019 01:20:34 -0700
Subject: drm/i915/tgl: Enable VD HCP/MFX sub-pipe power gating

HCP/MFX power gating is disabled by default, turn it on for the vd units
available. User space will also issue a MI_FORCE_WAKEUP properly to
wake up proper subwell.

During driver load, init_clock_gating happens after device_info_init_mmio
read the vdbox disable fuse register, so only present vd units will have
these enabled.

BSpec: 14214
HSDES: 1209977827
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Tony Ye <tony.ye@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823082055.5992-3-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h |  4 ++++
 drivers/gpu/drm/i915/intel_pm.c | 18 +++++++++++++++++-
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index a092b34c269d..02e1ef10c47e 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -8615,6 +8615,10 @@ enum {
 #define   GEN9_PWRGT_MEDIA_STATUS_MASK		(1 << 0)
 #define   GEN9_PWRGT_RENDER_STATUS_MASK		(1 << 1)
 
+#define POWERGATE_ENABLE			_MMIO(0xa210)
+#define    VDN_HCP_POWERGATE_ENABLE(n)		BIT(((n) * 2) + 3)
+#define    VDN_MFX_POWERGATE_ENABLE(n)		BIT(((n) * 2) + 4)
+
 #define  GTFIFODBG				_MMIO(0x120000)
 #define    GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV	(0x1f << 20)
 #define    GT_FIFO_FREE_ENTRIES_CHV		(0x7f << 13)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 75ee027abb80..d3ea193cd093 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -9078,6 +9078,22 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv)
 		   _MASKED_BIT_ENABLE(GEN11_ENABLE_32_PLANE_MODE));
 }
 
+static void tgl_init_clock_gating(struct drm_i915_private *dev_priv)
+{
+	u32 vd_pg_enable = 0;
+	unsigned int i;
+
+	/* This is not a WA. Enable VD HCP & MFX_ENC powergate */
+	for (i = 0; i < I915_MAX_VCS; i++) {
+		if (HAS_ENGINE(dev_priv, _VCS(i)))
+			vd_pg_enable |= VDN_HCP_POWERGATE_ENABLE(i) |
+					VDN_MFX_POWERGATE_ENABLE(i);
+	}
+
+	I915_WRITE(POWERGATE_ENABLE,
+		   I915_READ(POWERGATE_ENABLE) | vd_pg_enable);
+}
+
 static void cnp_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	if (!HAS_PCH_CNP(dev_priv))
@@ -9598,7 +9614,7 @@ static void nop_init_clock_gating(struct drm_i915_private *dev_priv)
 void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv)
 {
 	if (IS_GEN(dev_priv, 12))
-		dev_priv->display.init_clock_gating = nop_init_clock_gating;
+		dev_priv->display.init_clock_gating = tgl_init_clock_gating;
 	else if (IS_GEN(dev_priv, 11))
 		dev_priv->display.init_clock_gating = icl_init_clock_gating;
 	else if (IS_CANNONLAKE(dev_priv))
-- 
cgit v1.2.3


From 4087f873df1fbf9d9590953119ea78dde6a759dd Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Fri, 23 Aug 2019 09:02:57 -0700
Subject: drm/i915: Use variable for debugfs device status

Use a local variable to find SSEU runtime information
in various debugfs functions.

v2: Remove extra line breaks per feedback from Chris

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823160307.180813-2-stuart.summers@intel.com
---
 drivers/gpu/drm/i915/i915_debugfs.c | 26 +++++++++++---------------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index e103fcba6435..806db87affb2 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3849,8 +3849,7 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
 		sseu->slice_mask |= BIT(s);
 
 		if (IS_GEN9_BC(dev_priv))
-			sseu->subslice_mask[s] =
-				RUNTIME_INFO(dev_priv)->sseu.subslice_mask[s];
+			sseu->subslice_mask[s] = info->sseu.subslice_mask[s];
 
 		for (ss = 0; ss < info->sseu.max_subslices; ss++) {
 			unsigned int eu_cnt;
@@ -3877,25 +3876,22 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
 static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv,
 					 struct sseu_dev_info *sseu)
 {
+	const struct intel_runtime_info *info = RUNTIME_INFO(dev_priv);
 	u32 slice_info = I915_READ(GEN8_GT_SLICE_INFO);
 	int s;
 
 	sseu->slice_mask = slice_info & GEN8_LSLICESTAT_MASK;
 
 	if (sseu->slice_mask) {
-		sseu->eu_per_subslice =
-			RUNTIME_INFO(dev_priv)->sseu.eu_per_subslice;
-		for (s = 0; s < fls(sseu->slice_mask); s++) {
-			sseu->subslice_mask[s] =
-				RUNTIME_INFO(dev_priv)->sseu.subslice_mask[s];
-		}
+		sseu->eu_per_subslice = info->sseu.eu_per_subslice;
+		for (s = 0; s < fls(sseu->slice_mask); s++)
+			sseu->subslice_mask[s] = info->sseu.subslice_mask[s];
 		sseu->eu_total = sseu->eu_per_subslice *
 				 intel_sseu_subslice_total(sseu);
 
 		/* subtract fused off EU(s) from enabled slice(s) */
 		for (s = 0; s < fls(sseu->slice_mask); s++) {
-			u8 subslice_7eu =
-				RUNTIME_INFO(dev_priv)->sseu.subslice_7eu[s];
+			u8 subslice_7eu = info->sseu.subslice_7eu[s];
 
 			sseu->eu_total -= hweight8(subslice_7eu);
 		}
@@ -3942,6 +3938,7 @@ static void i915_print_sseu_info(struct seq_file *m, bool is_available_info,
 static int i915_sseu_status(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	const struct intel_runtime_info *info = RUNTIME_INFO(dev_priv);
 	struct sseu_dev_info sseu;
 	intel_wakeref_t wakeref;
 
@@ -3949,14 +3946,13 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 		return -ENODEV;
 
 	seq_puts(m, "SSEU Device Info\n");
-	i915_print_sseu_info(m, true, &RUNTIME_INFO(dev_priv)->sseu);
+	i915_print_sseu_info(m, true, &info->sseu);
 
 	seq_puts(m, "SSEU Device Status\n");
 	memset(&sseu, 0, sizeof(sseu));
-	sseu.max_slices = RUNTIME_INFO(dev_priv)->sseu.max_slices;
-	sseu.max_subslices = RUNTIME_INFO(dev_priv)->sseu.max_subslices;
-	sseu.max_eus_per_subslice =
-		RUNTIME_INFO(dev_priv)->sseu.max_eus_per_subslice;
+	sseu.max_slices = info->sseu.max_slices;
+	sseu.max_subslices = info->sseu.max_subslices;
+	sseu.max_eus_per_subslice = info->sseu.max_eus_per_subslice;
 
 	with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) {
 		if (IS_CHERRYVIEW(dev_priv))
-- 
cgit v1.2.3


From 8b355db99cfbdaea848e05c288d6d80c391f0b13 Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Fri, 23 Aug 2019 09:02:58 -0700
Subject: drm/i915: Add function to set SSEU info per platform

Add a new function to allow each platform to set maximum
slice, subslice, and EU information to reduce code duplication.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823160307.180813-3-stuart.summers@intel.com
---
 drivers/gpu/drm/i915/gt/intel_sseu.c     |  8 +++++++
 drivers/gpu/drm/i915/gt/intel_sseu.h     |  3 +++
 drivers/gpu/drm/i915/i915_debugfs.c      |  6 ++---
 drivers/gpu/drm/i915/intel_device_info.c | 39 ++++++++++++--------------------
 4 files changed, 28 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index 6bf2d87da109..6727079eb9b6 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -8,6 +8,14 @@
 #include "intel_lrc_reg.h"
 #include "intel_sseu.h"
 
+void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
+			 u8 max_subslices, u8 max_eus_per_subslice)
+{
+	sseu->max_slices = max_slices;
+	sseu->max_subslices = max_subslices;
+	sseu->max_eus_per_subslice = max_eus_per_subslice;
+}
+
 unsigned int
 intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index b50d0401a4e2..64e47dad07be 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -63,6 +63,9 @@ intel_sseu_from_device_info(const struct sseu_dev_info *sseu)
 	return value;
 }
 
+void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
+			 u8 max_subslices, u8 max_eus_per_subslice);
+
 unsigned int
 intel_sseu_subslice_total(const struct sseu_dev_info *sseu);
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 806db87affb2..28713c9c98ea 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3950,9 +3950,9 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 
 	seq_puts(m, "SSEU Device Status\n");
 	memset(&sseu, 0, sizeof(sseu));
-	sseu.max_slices = info->sseu.max_slices;
-	sseu.max_subslices = info->sseu.max_subslices;
-	sseu.max_eus_per_subslice = info->sseu.max_eus_per_subslice;
+	intel_sseu_set_info(&sseu, info->sseu.max_slices,
+			    info->sseu.max_subslices,
+			    info->sseu.max_eus_per_subslice);
 
 	with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) {
 		if (IS_CHERRYVIEW(dev_priv))
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index d0ed44d33484..77d7bbaa49f3 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -191,15 +191,10 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
 	u8 eu_en;
 	int s;
 
-	if (IS_ELKHARTLAKE(dev_priv)) {
-		sseu->max_slices = 1;
-		sseu->max_subslices = 4;
-		sseu->max_eus_per_subslice = 8;
-	} else {
-		sseu->max_slices = 1;
-		sseu->max_subslices = 8;
-		sseu->max_eus_per_subslice = 8;
-	}
+	if (IS_ELKHARTLAKE(dev_priv))
+		intel_sseu_set_info(sseu, 1, 4, 8);
+	else
+		intel_sseu_set_info(sseu, 1, 8, 8);
 
 	s_en = I915_READ(GEN11_GT_SLICE_ENABLE) & GEN11_GT_S_ENA_MASK;
 	ss_en = ~I915_READ(GEN11_GT_SUBSLICE_DISABLE);
@@ -236,11 +231,10 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
 	const int eu_mask = 0xff;
 	u32 subslice_mask, eu_en;
 
+	intel_sseu_set_info(sseu, 6, 4, 8);
+
 	sseu->slice_mask = (fuse2 & GEN10_F2_S_ENA_MASK) >>
 			    GEN10_F2_S_ENA_SHIFT;
-	sseu->max_slices = 6;
-	sseu->max_subslices = 4;
-	sseu->max_eus_per_subslice = 8;
 
 	subslice_mask = (1 << 4) - 1;
 	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
@@ -314,9 +308,7 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 	fuse = I915_READ(CHV_FUSE_GT);
 
 	sseu->slice_mask = BIT(0);
-	sseu->max_slices = 1;
-	sseu->max_subslices = 2;
-	sseu->max_eus_per_subslice = 8;
+	intel_sseu_set_info(sseu, 1, 2, 8);
 
 	if (!(fuse & CHV_FGT_DISABLE_SS0)) {
 		u8 disabled_mask =
@@ -372,9 +364,8 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
 
 	/* BXT has a single slice and at most 3 subslices. */
-	sseu->max_slices = IS_GEN9_LP(dev_priv) ? 1 : 3;
-	sseu->max_subslices = IS_GEN9_LP(dev_priv) ? 3 : 4;
-	sseu->max_eus_per_subslice = 8;
+	intel_sseu_set_info(sseu, IS_GEN9_LP(dev_priv) ? 1 : 3,
+			    IS_GEN9_LP(dev_priv) ? 3 : 4, 8);
 
 	/*
 	 * The subslice disable field is global, i.e. it applies
@@ -473,9 +464,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 
 	fuse2 = I915_READ(GEN8_FUSE2);
 	sseu->slice_mask = (fuse2 & GEN8_F2_S_ENA_MASK) >> GEN8_F2_S_ENA_SHIFT;
-	sseu->max_slices = 3;
-	sseu->max_subslices = 3;
-	sseu->max_eus_per_subslice = 8;
+	intel_sseu_set_info(sseu, 3, 3, 8);
 
 	/*
 	 * The subslice disable field is global, i.e. it applies
@@ -577,9 +566,6 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 		break;
 	}
 
-	sseu->max_slices = hweight8(sseu->slice_mask);
-	sseu->max_subslices = hweight8(sseu->subslice_mask[0]);
-
 	fuse1 = I915_READ(HSW_PAVP_FUSE1);
 	switch ((fuse1 & HSW_F1_EU_DIS_MASK) >> HSW_F1_EU_DIS_SHIFT) {
 	default:
@@ -596,7 +582,10 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 		sseu->eu_per_subslice = 6;
 		break;
 	}
-	sseu->max_eus_per_subslice = sseu->eu_per_subslice;
+
+	intel_sseu_set_info(sseu, hweight8(sseu->slice_mask),
+			    hweight8(sseu->subslice_mask[0]),
+			    sseu->eu_per_subslice);
 
 	for (s = 0; s < sseu->max_slices; s++) {
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
-- 
cgit v1.2.3


From 7a200aad1127e98cbf4da9685f652899598fe357 Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Fri, 23 Aug 2019 09:02:59 -0700
Subject: drm/i915: Add subslice stride runtime parameter

Add a new parameter, ss_stride, to the runtime info
structure. This is used to mirror the userspace concept
of subslice stride, which is a range of subslices per slice.

This patch simply adds the definition and updates usage
in the QUERY_TOPOLOGY_INFO handler.

v2: Add GEM_BUG_ON to make sure ss_stride is valid

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823160307.180813-4-stuart.summers@intel.com
---
 drivers/gpu/drm/i915/gt/intel_sseu.c | 3 +++
 drivers/gpu/drm/i915/gt/intel_sseu.h | 3 +++
 drivers/gpu/drm/i915/i915_query.c    | 5 ++---
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index 6727079eb9b6..edf39ae132c3 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -14,6 +14,9 @@ void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
 	sseu->max_slices = max_slices;
 	sseu->max_subslices = max_subslices;
 	sseu->max_eus_per_subslice = max_eus_per_subslice;
+
+	sseu->ss_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
+	GEM_BUG_ON(sseu->ss_stride > GEN_MAX_SUBSLICE_STRIDE);
 }
 
 unsigned int
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 64e47dad07be..8b8b562ff773 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -15,6 +15,7 @@ struct drm_i915_private;
 #define GEN_MAX_SLICES		(6) /* CNL upper bound */
 #define GEN_MAX_SUBSLICES	(8) /* ICL upper bound */
 #define GEN_SSEU_STRIDE(max_entries) DIV_ROUND_UP(max_entries, BITS_PER_BYTE)
+#define GEN_MAX_SUBSLICE_STRIDE GEN_SSEU_STRIDE(GEN_MAX_SUBSLICES)
 
 struct sseu_dev_info {
 	u8 slice_mask;
@@ -33,6 +34,8 @@ struct sseu_dev_info {
 	u8 max_subslices;
 	u8 max_eus_per_subslice;
 
+	u8 ss_stride;
+
 	/* We don't have more than 8 eus per subslice at the moment and as we
 	 * store eus enabled using bits, no need to multiply by eus per
 	 * subslice.
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index ad9240a0817a..d8e25dcf5f0b 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -37,7 +37,6 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
 	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	struct drm_i915_query_topology_info topo;
 	u32 slice_length, subslice_length, eu_length, total_length;
-	u8 subslice_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
 	u8 eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
 	int ret;
 
@@ -50,7 +49,7 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
 	BUILD_BUG_ON(sizeof(u8) != sizeof(sseu->slice_mask));
 
 	slice_length = sizeof(sseu->slice_mask);
-	subslice_length = sseu->max_slices * subslice_stride;
+	subslice_length = sseu->max_slices * sseu->ss_stride;
 	eu_length = sseu->max_slices * sseu->max_subslices * eu_stride;
 	total_length = sizeof(topo) + slice_length + subslice_length +
 		       eu_length;
@@ -69,7 +68,7 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
 	topo.max_eus_per_subslice = sseu->max_eus_per_subslice;
 
 	topo.subslice_offset = slice_length;
-	topo.subslice_stride = subslice_stride;
+	topo.subslice_stride = sseu->ss_stride;
 	topo.eu_offset = slice_length + subslice_length;
 	topo.eu_stride = eu_stride;
 
-- 
cgit v1.2.3


From 49610c377be7f32d948f0970705b4ad015923aa0 Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Fri, 23 Aug 2019 09:03:00 -0700
Subject: drm/i915: Add EU stride runtime parameter

Add a new SSEU runtime parameter, eu_stride, which is
used to mirror the userspace concept of a range of EUs
per subslice.

This patch simply adds the parameter and updates usage
in the QUERY_TOPOLOGY_INFO handler.

v2: Add GEM_BUG_ON to make sure eu_stride is valid

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823160307.180813-5-stuart.summers@intel.com
---
 drivers/gpu/drm/i915/gt/intel_sseu.c     | 2 ++
 drivers/gpu/drm/i915/gt/intel_sseu.h     | 3 +++
 drivers/gpu/drm/i915/i915_query.c        | 5 ++---
 drivers/gpu/drm/i915/intel_device_info.c | 9 ++++-----
 4 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index edf39ae132c3..d52686a1afdc 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -17,6 +17,8 @@ void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
 
 	sseu->ss_stride = GEN_SSEU_STRIDE(sseu->max_subslices);
 	GEM_BUG_ON(sseu->ss_stride > GEN_MAX_SUBSLICE_STRIDE);
+	sseu->eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
+	GEM_BUG_ON(sseu->eu_stride > GEN_MAX_EU_STRIDE);
 }
 
 unsigned int
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 8b8b562ff773..7f2355ce963d 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -16,6 +16,8 @@ struct drm_i915_private;
 #define GEN_MAX_SUBSLICES	(8) /* ICL upper bound */
 #define GEN_SSEU_STRIDE(max_entries) DIV_ROUND_UP(max_entries, BITS_PER_BYTE)
 #define GEN_MAX_SUBSLICE_STRIDE GEN_SSEU_STRIDE(GEN_MAX_SUBSLICES)
+#define GEN_MAX_EUS		(10) /* HSW upper bound */
+#define GEN_MAX_EU_STRIDE GEN_SSEU_STRIDE(GEN_MAX_EUS)
 
 struct sseu_dev_info {
 	u8 slice_mask;
@@ -35,6 +37,7 @@ struct sseu_dev_info {
 	u8 max_eus_per_subslice;
 
 	u8 ss_stride;
+	u8 eu_stride;
 
 	/* We don't have more than 8 eus per subslice at the moment and as we
 	 * store eus enabled using bits, no need to multiply by eus per
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index d8e25dcf5f0b..abac5042da2b 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -37,7 +37,6 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
 	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	struct drm_i915_query_topology_info topo;
 	u32 slice_length, subslice_length, eu_length, total_length;
-	u8 eu_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
 	int ret;
 
 	if (query_item->flags != 0)
@@ -50,7 +49,7 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
 
 	slice_length = sizeof(sseu->slice_mask);
 	subslice_length = sseu->max_slices * sseu->ss_stride;
-	eu_length = sseu->max_slices * sseu->max_subslices * eu_stride;
+	eu_length = sseu->max_slices * sseu->max_subslices * sseu->eu_stride;
 	total_length = sizeof(topo) + slice_length + subslice_length +
 		       eu_length;
 
@@ -70,7 +69,7 @@ static int query_topology_info(struct drm_i915_private *dev_priv,
 	topo.subslice_offset = slice_length;
 	topo.subslice_stride = sseu->ss_stride;
 	topo.eu_offset = slice_length + subslice_length;
-	topo.eu_stride = eu_stride;
+	topo.eu_stride = sseu->eu_stride;
 
 	if (__copy_to_user(u64_to_user_ptr(query_item->data_ptr),
 			   &topo, sizeof(topo)))
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 77d7bbaa49f3..b1a79ed408eb 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -118,10 +118,9 @@ void intel_device_info_dump_runtime(const struct intel_runtime_info *info,
 static int sseu_eu_idx(const struct sseu_dev_info *sseu, int slice,
 		       int subslice)
 {
-	int subslice_stride = GEN_SSEU_STRIDE(sseu->max_eus_per_subslice);
-	int slice_stride = sseu->max_subslices * subslice_stride;
+	int slice_stride = sseu->max_subslices * sseu->eu_stride;
 
-	return slice * slice_stride + subslice * subslice_stride;
+	return slice * slice_stride + subslice * sseu->eu_stride;
 }
 
 static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
@@ -130,7 +129,7 @@ static u16 sseu_get_eus(const struct sseu_dev_info *sseu, int slice,
 	int i, offset = sseu_eu_idx(sseu, slice, subslice);
 	u16 eu_mask = 0;
 
-	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
+	for (i = 0; i < sseu->eu_stride; i++) {
 		eu_mask |= ((u16)sseu->eu_mask[offset + i]) <<
 			(i * BITS_PER_BYTE);
 	}
@@ -143,7 +142,7 @@ static void sseu_set_eus(struct sseu_dev_info *sseu, int slice, int subslice,
 {
 	int i, offset = sseu_eu_idx(sseu, slice, subslice);
 
-	for (i = 0; i < GEN_SSEU_STRIDE(sseu->max_eus_per_subslice); i++) {
+	for (i = 0; i < sseu->eu_stride; i++) {
 		sseu->eu_mask[offset + i] =
 			(eu_mask >> (BITS_PER_BYTE * i)) & 0xff;
 	}
-- 
cgit v1.2.3


From 33ee9e8680963fbfa298fec08eed7b45db0a1ebb Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Fri, 23 Aug 2019 09:03:01 -0700
Subject: drm/i915: Use local variables for subslice_mask for device info

When setting up subslice_mask, instead of operating on the slice
array directly, use a local variable to start bits per slice, then
use this to set the per slice array in one step.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823160307.180813-6-stuart.summers@intel.com
---
 drivers/gpu/drm/i915/intel_device_info.c | 49 +++++++++++++++++---------------
 1 file changed, 26 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index b1a79ed408eb..52515efe9f4e 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -235,18 +235,6 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
 	sseu->slice_mask = (fuse2 & GEN10_F2_S_ENA_MASK) >>
 			    GEN10_F2_S_ENA_SHIFT;
 
-	subslice_mask = (1 << 4) - 1;
-	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
-			   GEN10_F2_SS_DIS_SHIFT);
-
-	/*
-	 * Slice0 can have up to 3 subslices, but there are only 2 in
-	 * slice1/2.
-	 */
-	sseu->subslice_mask[0] = subslice_mask;
-	for (s = 1; s < sseu->max_slices; s++)
-		sseu->subslice_mask[s] = subslice_mask & 0x3;
-
 	/* Slice0 */
 	eu_en = ~I915_READ(GEN8_EU_DISABLE0);
 	for (ss = 0; ss < sseu->max_subslices; ss++)
@@ -270,14 +258,24 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
 	eu_en = ~I915_READ(GEN10_EU_DISABLE3);
 	sseu_set_eus(sseu, 5, 1, eu_en & eu_mask);
 
-	/* Do a second pass where we mark the subslices disabled if all their
-	 * eus are off.
-	 */
+	subslice_mask = (1 << 4) - 1;
+	subslice_mask &= ~((fuse2 & GEN10_F2_SS_DIS_MASK) >>
+			   GEN10_F2_SS_DIS_SHIFT);
+
 	for (s = 0; s < sseu->max_slices; s++) {
+		u32 subslice_mask_with_eus = subslice_mask;
+
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			if (sseu_get_eus(sseu, s, ss) == 0)
-				sseu->subslice_mask[s] &= ~BIT(ss);
+				subslice_mask_with_eus &= ~BIT(ss);
 		}
+
+		/*
+		 * Slice0 can have up to 3 subslices, but there are only 2 in
+		 * slice1/2.
+		 */
+		sseu->subslice_mask[s] = s == 0 ? subslice_mask_with_eus :
+						  subslice_mask_with_eus & 0x3;
 	}
 
 	sseu->eu_total = compute_eu_total(sseu);
@@ -303,6 +301,7 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	u32 fuse;
+	u8 subslice_mask = 0;
 
 	fuse = I915_READ(CHV_FUSE_GT);
 
@@ -316,7 +315,7 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 			(((fuse & CHV_FGT_EU_DIS_SS0_R1_MASK) >>
 			  CHV_FGT_EU_DIS_SS0_R1_SHIFT) << 4);
 
-		sseu->subslice_mask[0] |= BIT(0);
+		subslice_mask |= BIT(0);
 		sseu_set_eus(sseu, 0, 0, ~disabled_mask);
 	}
 
@@ -327,10 +326,12 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 			(((fuse & CHV_FGT_EU_DIS_SS1_R1_MASK) >>
 			  CHV_FGT_EU_DIS_SS1_R1_SHIFT) << 4);
 
-		sseu->subslice_mask[0] |= BIT(1);
+		subslice_mask |= BIT(1);
 		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
 	}
 
+	sseu->subslice_mask[0] = subslice_mask;
+
 	sseu->eu_total = compute_eu_total(sseu);
 
 	/*
@@ -540,6 +541,7 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	u32 fuse1;
+	u8 subslice_mask = 0;
 	int s, ss;
 
 	/*
@@ -552,16 +554,15 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 		/* fall through */
 	case 1:
 		sseu->slice_mask = BIT(0);
-		sseu->subslice_mask[0] = BIT(0);
+		subslice_mask = BIT(0);
 		break;
 	case 2:
 		sseu->slice_mask = BIT(0);
-		sseu->subslice_mask[0] = BIT(0) | BIT(1);
+		subslice_mask = BIT(0) | BIT(1);
 		break;
 	case 3:
 		sseu->slice_mask = BIT(0) | BIT(1);
-		sseu->subslice_mask[0] = BIT(0) | BIT(1);
-		sseu->subslice_mask[1] = BIT(0) | BIT(1);
+		subslice_mask = BIT(0) | BIT(1);
 		break;
 	}
 
@@ -583,10 +584,12 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 	}
 
 	intel_sseu_set_info(sseu, hweight8(sseu->slice_mask),
-			    hweight8(sseu->subslice_mask[0]),
+			    hweight8(subslice_mask),
 			    sseu->eu_per_subslice);
 
 	for (s = 0; s < sseu->max_slices; s++) {
+		sseu->subslice_mask[s] = subslice_mask;
+
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			sseu_set_eus(sseu, s, ss,
 				     (1UL << sseu->eu_per_subslice) - 1);
-- 
cgit v1.2.3


From 9e8a135ed5a414ba4333cda22b01ae77291f6b9b Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Fri, 23 Aug 2019 09:03:02 -0700
Subject: drm/i915: Add function to set subslices

Add a new function to set a set of subslices for a given
slice.

v2: Fix typo in subslice_mask assignment

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823160307.180813-7-stuart.summers@intel.com
---
 drivers/gpu/drm/i915/gt/intel_sseu.c     |  6 ++++++
 drivers/gpu/drm/i915/gt/intel_sseu.h     |  3 +++
 drivers/gpu/drm/i915/intel_device_info.c | 18 +++++++++++-------
 3 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index d52686a1afdc..3a5db0dbac72 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -32,6 +32,12 @@ intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
 	return total;
 }
 
+void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
+			      u8 ss_mask)
+{
+	sseu->subslice_mask[slice] = ss_mask;
+}
+
 unsigned int
 intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 7f2355ce963d..7f600f50dedb 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -78,6 +78,9 @@ intel_sseu_subslice_total(const struct sseu_dev_info *sseu);
 unsigned int
 intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice);
 
+void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
+			      u8 ss_mask);
+
 u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
 			 const struct intel_sseu *req_sseu);
 
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 52515efe9f4e..1a45728ac712 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -206,7 +206,10 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
 			int ss;
 
 			sseu->slice_mask |= BIT(s);
-			sseu->subslice_mask[s] = (ss_en >> ss_idx) & ss_en_mask;
+
+			intel_sseu_set_subslices(sseu, s, (ss_en >> ss_idx) &
+							  ss_en_mask);
+
 			for (ss = 0; ss < sseu->max_subslices; ss++) {
 				if (sseu->subslice_mask[s] & BIT(ss))
 					sseu_set_eus(sseu, s, ss, eu_en);
@@ -274,8 +277,9 @@ static void gen10_sseu_info_init(struct drm_i915_private *dev_priv)
 		 * Slice0 can have up to 3 subslices, but there are only 2 in
 		 * slice1/2.
 		 */
-		sseu->subslice_mask[s] = s == 0 ? subslice_mask_with_eus :
-						  subslice_mask_with_eus & 0x3;
+		intel_sseu_set_subslices(sseu, s, s == 0 ?
+						  subslice_mask_with_eus :
+						  subslice_mask_with_eus & 0x3);
 	}
 
 	sseu->eu_total = compute_eu_total(sseu);
@@ -330,7 +334,7 @@ static void cherryview_sseu_info_init(struct drm_i915_private *dev_priv)
 		sseu_set_eus(sseu, 0, 1, ~disabled_mask);
 	}
 
-	sseu->subslice_mask[0] = subslice_mask;
+	intel_sseu_set_subslices(sseu, 0, subslice_mask);
 
 	sseu->eu_total = compute_eu_total(sseu);
 
@@ -384,7 +388,7 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 			/* skip disabled slice */
 			continue;
 
-		sseu->subslice_mask[s] = subslice_mask;
+		intel_sseu_set_subslices(sseu, s, subslice_mask);
 
 		eu_disable = I915_READ(GEN9_EU_DISABLE(s));
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
@@ -491,7 +495,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 			/* skip disabled slice */
 			continue;
 
-		sseu->subslice_mask[s] = subslice_mask;
+		intel_sseu_set_subslices(sseu, s, subslice_mask);
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			u8 eu_disabled_mask;
@@ -588,7 +592,7 @@ static void haswell_sseu_info_init(struct drm_i915_private *dev_priv)
 			    sseu->eu_per_subslice);
 
 	for (s = 0; s < sseu->max_slices; s++) {
-		sseu->subslice_mask[s] = subslice_mask;
+		intel_sseu_set_subslices(sseu, s, subslice_mask);
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			sseu_set_eus(sseu, s, ss,
-- 
cgit v1.2.3


From 6db40ec80f544e289fe836319b20fcc19a454e8d Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Fri, 23 Aug 2019 09:03:03 -0700
Subject: drm/i915: Use subslice stride to set subslices for a given slice

Add a subslice stride calculation when setting subslices. This
aligns more closely with the userspace expectation of the subslice
mask structure.

v2: Use local variable for subslice_mask on HSW and
    clean up a few other subslice_mask local variable
    changes
v3: Add GEM_BUG_ON for ss_stride to prevent array overflow (Chris)
    Split main set function and refactors in intel_device_info.c
    into separate patches (Chris)
v4: Reduce ss_stride size check when setting subslices per slice
    based on actual expected max stride (Chris)
    Move that GEM_BUG_ON check for the ss_stride out to the patch
    which adds the ss_stride
v5: Use memcpy instead of looping through each stride index

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823160307.180813-8-stuart.summers@intel.com
---
 drivers/gpu/drm/i915/gt/intel_sseu.c | 6 ++++--
 drivers/gpu/drm/i915/gt/intel_sseu.h | 2 +-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index 3a5db0dbac72..1505042d7b5d 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -33,9 +33,11 @@ intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
 }
 
 void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
-			      u8 ss_mask)
+			      u32 ss_mask)
 {
-	sseu->subslice_mask[slice] = ss_mask;
+	int offset = slice * sseu->ss_stride;
+
+	memcpy(&sseu->subslice_mask[offset], &ss_mask, sseu->ss_stride);
 }
 
 unsigned int
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 7f600f50dedb..73a9064291a2 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -79,7 +79,7 @@ unsigned int
 intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice);
 
 void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
-			      u8 ss_mask);
+			      u32 ss_mask);
 
 u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
 			 const struct intel_sseu *req_sseu);
-- 
cgit v1.2.3


From e1210bbfb1f8dc2865e8ebd6884afa895333b6e4 Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Fri, 23 Aug 2019 09:03:04 -0700
Subject: drm/i915: Add function to determine if a slice has a subslice

Add a new function to determine whether a particular slice
has a given subslice.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823160307.180813-9-stuart.summers@intel.com
---
 drivers/gpu/drm/i915/gt/intel_sseu.h     | 16 ++++++++++++++++
 drivers/gpu/drm/i915/intel_device_info.c |  9 ++++-----
 2 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 73a9064291a2..7703d75f2da3 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -10,6 +10,8 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 
+#include "i915_gem.h"
+
 struct drm_i915_private;
 
 #define GEN_MAX_SLICES		(6) /* CNL upper bound */
@@ -69,6 +71,20 @@ intel_sseu_from_device_info(const struct sseu_dev_info *sseu)
 	return value;
 }
 
+static inline bool
+intel_sseu_has_subslice(const struct sseu_dev_info *sseu, int slice,
+			int subslice)
+{
+	u8 mask;
+	int ss_idx = subslice / BITS_PER_BYTE;
+
+	GEM_BUG_ON(ss_idx >= sseu->ss_stride);
+
+	mask = sseu->subslice_mask[slice * sseu->ss_stride + ss_idx];
+
+	return mask & BIT(subslice % BITS_PER_BYTE);
+}
+
 void intel_sseu_set_info(struct sseu_dev_info *sseu, u8 max_slices,
 			 u8 max_subslices, u8 max_eus_per_subslice);
 
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 1a45728ac712..c20f74ee5f22 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -210,10 +210,9 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
 			intel_sseu_set_subslices(sseu, s, (ss_en >> ss_idx) &
 							  ss_en_mask);
 
-			for (ss = 0; ss < sseu->max_subslices; ss++) {
-				if (sseu->subslice_mask[s] & BIT(ss))
+			for (ss = 0; ss < sseu->max_subslices; ss++)
+				if (intel_sseu_has_subslice(sseu, s, ss))
 					sseu_set_eus(sseu, s, ss, eu_en);
-			}
 		}
 	}
 	sseu->eu_per_subslice = hweight8(eu_en);
@@ -395,7 +394,7 @@ static void gen9_sseu_info_init(struct drm_i915_private *dev_priv)
 			int eu_per_ss;
 			u8 eu_disabled_mask;
 
-			if (!(sseu->subslice_mask[s] & BIT(ss)))
+			if (!intel_sseu_has_subslice(sseu, s, ss))
 				/* skip disabled subslice */
 				continue;
 
@@ -501,7 +500,7 @@ static void broadwell_sseu_info_init(struct drm_i915_private *dev_priv)
 			u8 eu_disabled_mask;
 			u32 n_disabled;
 
-			if (!(sseu->subslice_mask[s] & BIT(ss)))
+			if (!intel_sseu_has_subslice(sseu, s, ss))
 				/* skip disabled subslice */
 				continue;
 
-- 
cgit v1.2.3


From eaef5b3c411337db73a205d0e009c72f7a39f3a3 Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Fri, 23 Aug 2019 09:03:05 -0700
Subject: drm/i915: Refactor instdone loops on new subslice functions

Refactor instdone loops to use the new intel_sseu_has_subslice
function.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823160307.180813-10-stuart.summers@intel.com
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c    |  3 ++-
 drivers/gpu/drm/i915/gt/intel_engine_types.h | 30 +++++++++++++---------------
 drivers/gpu/drm/i915/gt/intel_hangcheck.c    |  3 ++-
 drivers/gpu/drm/i915/i915_debugfs.c          |  5 +++--
 drivers/gpu/drm/i915/i915_gpu_error.c        |  5 +++--
 5 files changed, 24 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 82630db0394b..17006d50b63f 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -948,6 +948,7 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine,
 			       struct intel_instdone *instdone)
 {
 	struct drm_i915_private *i915 = engine->i915;
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(i915)->sseu;
 	struct intel_uncore *uncore = engine->uncore;
 	u32 mmio_base = engine->mmio_base;
 	int slice;
@@ -965,7 +966,7 @@ void intel_engine_get_instdone(struct intel_engine_cs *engine,
 
 		instdone->slice_common =
 			intel_uncore_read(uncore, GEN7_SC_INSTDONE);
-		for_each_instdone_slice_subslice(i915, slice, subslice) {
+		for_each_instdone_slice_subslice(i915, sseu, slice, subslice) {
 			instdone->sampler[slice][subslice] =
 				read_subslice_reg(engine, slice, subslice,
 						  GEN7_SAMPLER_INSTDONE);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index a82cea95c2f2..15e02cb58a67 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -576,20 +576,18 @@ intel_engine_is_virtual(const struct intel_engine_cs *engine)
 	return engine->flags & I915_ENGINE_IS_VIRTUAL;
 }
 
-#define instdone_slice_mask(dev_priv__) \
-	(IS_GEN(dev_priv__, 7) ? \
-	 1 : RUNTIME_INFO(dev_priv__)->sseu.slice_mask)
-
-#define instdone_subslice_mask(dev_priv__) \
-	(IS_GEN(dev_priv__, 7) ? \
-	 1 : RUNTIME_INFO(dev_priv__)->sseu.subslice_mask[0])
-
-#define for_each_instdone_slice_subslice(dev_priv__, slice__, subslice__) \
-	for ((slice__) = 0, (subslice__) = 0; \
-	     (slice__) < I915_MAX_SLICES; \
-	     (subslice__) = ((subslice__) + 1) < I915_MAX_SUBSLICES ? (subslice__) + 1 : 0, \
-	       (slice__) += ((subslice__) == 0)) \
-		for_each_if((BIT(slice__) & instdone_slice_mask(dev_priv__)) && \
-			    (BIT(subslice__) & instdone_subslice_mask(dev_priv__)))
-
+#define instdone_has_slice(dev_priv___, sseu___, slice___) \
+	((IS_GEN(dev_priv___, 7) ? 1 : ((sseu___)->slice_mask)) & BIT(slice___))
+
+#define instdone_has_subslice(dev_priv__, sseu__, slice__, subslice__) \
+	(IS_GEN(dev_priv__, 7) ? (1 & BIT(subslice__)) : \
+	 intel_sseu_has_subslice(sseu__, 0, subslice__))
+
+#define for_each_instdone_slice_subslice(dev_priv_, sseu_, slice_, subslice_) \
+	for ((slice_) = 0, (subslice_) = 0; (slice_) < I915_MAX_SLICES; \
+	     (subslice_) = ((subslice_) + 1) % I915_MAX_SUBSLICES, \
+	     (slice_) += ((subslice_) == 0)) \
+		for_each_if((instdone_has_slice(dev_priv_, sseu_, slice_)) && \
+			    (instdone_has_subslice(dev_priv_, sseu_, slice_, \
+						    subslice_)))
 #endif /* __INTEL_ENGINE_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_hangcheck.c b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
index 05d042cdefe2..40f62f780be5 100644
--- a/drivers/gpu/drm/i915/gt/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
@@ -53,6 +53,7 @@ static bool instdone_unchanged(u32 current_instdone, u32 *old_instdone)
 static bool subunits_stuck(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	struct intel_instdone instdone;
 	struct intel_instdone *accu_instdone = &engine->hangcheck.instdone;
 	bool stuck;
@@ -71,7 +72,7 @@ static bool subunits_stuck(struct intel_engine_cs *engine)
 	stuck &= instdone_unchanged(instdone.slice_common,
 				    &accu_instdone->slice_common);
 
-	for_each_instdone_slice_subslice(dev_priv, slice, subslice) {
+	for_each_instdone_slice_subslice(dev_priv, sseu, slice, subslice) {
 		stuck &= instdone_unchanged(instdone.sampler[slice][subslice],
 					    &accu_instdone->sampler[slice][subslice]);
 		stuck &= instdone_unchanged(instdone.row[slice][subslice],
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 28713c9c98ea..44797f8b7c50 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -996,6 +996,7 @@ static void i915_instdone_info(struct drm_i915_private *dev_priv,
 			       struct seq_file *m,
 			       struct intel_instdone *instdone)
 {
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	int slice;
 	int subslice;
 
@@ -1011,11 +1012,11 @@ static void i915_instdone_info(struct drm_i915_private *dev_priv,
 	if (INTEL_GEN(dev_priv) <= 6)
 		return;
 
-	for_each_instdone_slice_subslice(dev_priv, slice, subslice)
+	for_each_instdone_slice_subslice(dev_priv, sseu, slice, subslice)
 		seq_printf(m, "\t\tSAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
 			   slice, subslice, instdone->sampler[slice][subslice]);
 
-	for_each_instdone_slice_subslice(dev_priv, slice, subslice)
+	for_each_instdone_slice_subslice(dev_priv, sseu, slice, subslice)
 		seq_printf(m, "\t\tROW_INSTDONE[%d][%d]: 0x%08x\n",
 			   slice, subslice, instdone->row[slice][subslice]);
 }
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index e284bd76fa86..4aff342b8944 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -421,6 +421,7 @@ static void err_compression_marker(struct drm_i915_error_state_buf *m)
 static void error_print_instdone(struct drm_i915_error_state_buf *m,
 				 const struct drm_i915_error_engine *ee)
 {
+	const struct sseu_dev_info *sseu = &RUNTIME_INFO(m->i915)->sseu;
 	int slice;
 	int subslice;
 
@@ -436,12 +437,12 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m,
 	if (INTEL_GEN(m->i915) <= 6)
 		return;
 
-	for_each_instdone_slice_subslice(m->i915, slice, subslice)
+	for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
 		err_printf(m, "  SAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
 			   slice, subslice,
 			   ee->instdone.sampler[slice][subslice]);
 
-	for_each_instdone_slice_subslice(m->i915, slice, subslice)
+	for_each_instdone_slice_subslice(m->i915, sseu, slice, subslice)
 		err_printf(m, "  ROW_INSTDONE[%d][%d]: 0x%08x\n",
 			   slice, subslice,
 			   ee->instdone.row[slice][subslice]);
-- 
cgit v1.2.3


From 668df17f594d6f57e822ceee680ace3233e97f02 Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Fri, 23 Aug 2019 09:03:06 -0700
Subject: drm/i915: Add new function to copy subslices for a slice

Add a new function to copy subslices for a specified slice
between intel_sseu structures for the purpose of determining
power-gate status. Note that currently ss_stride has a max
of 1.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823160307.180813-11-stuart.summers@intel.com
---
 drivers/gpu/drm/i915/i915_debugfs.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 44797f8b7c50..6e8b40299939 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3726,6 +3726,15 @@ i915_cache_sharing_set(void *data, u64 val)
 	return 0;
 }
 
+static void
+intel_sseu_copy_subslices(const struct sseu_dev_info *sseu, int slice,
+			  u8 *to_mask)
+{
+	int offset = slice * sseu->ss_stride;
+
+	memcpy(&to_mask[offset], &sseu->subslice_mask[offset], sseu->ss_stride);
+}
+
 DEFINE_SIMPLE_ATTRIBUTE(i915_cache_sharing_fops,
 			i915_cache_sharing_get, i915_cache_sharing_set,
 			"%llu\n");
@@ -3799,7 +3808,7 @@ static void gen10_sseu_device_status(struct drm_i915_private *dev_priv,
 			continue;
 
 		sseu->slice_mask |= BIT(s);
-		sseu->subslice_mask[s] = info->sseu.subslice_mask[s];
+		intel_sseu_copy_subslices(&info->sseu, s, sseu->subslice_mask);
 
 		for (ss = 0; ss < info->sseu.max_subslices; ss++) {
 			unsigned int eu_cnt;
@@ -3850,7 +3859,8 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
 		sseu->slice_mask |= BIT(s);
 
 		if (IS_GEN9_BC(dev_priv))
-			sseu->subslice_mask[s] = info->sseu.subslice_mask[s];
+			intel_sseu_copy_subslices(&info->sseu, s,
+						  sseu->subslice_mask);
 
 		for (ss = 0; ss < info->sseu.max_subslices; ss++) {
 			unsigned int eu_cnt;
@@ -3886,7 +3896,8 @@ static void broadwell_sseu_device_status(struct drm_i915_private *dev_priv,
 	if (sseu->slice_mask) {
 		sseu->eu_per_subslice = info->sseu.eu_per_subslice;
 		for (s = 0; s < fls(sseu->slice_mask); s++)
-			sseu->subslice_mask[s] = info->sseu.subslice_mask[s];
+			intel_sseu_copy_subslices(&info->sseu, s,
+						  sseu->subslice_mask);
 		sseu->eu_total = sseu->eu_per_subslice *
 				 intel_sseu_subslice_total(sseu);
 
-- 
cgit v1.2.3


From 100f5f7fbc3e23f58511a11a3751dfacf1ccb5a7 Mon Sep 17 00:00:00 2001
From: Stuart Summers <stuart.summers@intel.com>
Date: Fri, 23 Aug 2019 09:03:07 -0700
Subject: drm/i915: Expand subslice mask

Currently, the subslice_mask runtime parameter is stored as an
array of subslices per slice. Expand the subslice mask array to
better match what is presented to userspace through the
I915_QUERY_TOPOLOGY_INFO ioctl. The index into this array is
then calculated:
  slice * subslice stride + subslice index / 8

v2: Fix 32-bit build
v3: Use new helper function in SSEU workaround warning message
v4: Use GEM_BUG_ON to force developers to use valid SSEU configurations
    per platform (Chris)

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823160307.180813-12-stuart.summers@intel.com
---
 drivers/gpu/drm/i915/gt/intel_sseu.c        | 16 +++++++++++++++-
 drivers/gpu/drm/i915/gt/intel_sseu.h        |  4 +++-
 drivers/gpu/drm/i915/gt/intel_workarounds.c |  5 ++---
 drivers/gpu/drm/i915/i915_debugfs.c         |  5 ++++-
 drivers/gpu/drm/i915/intel_device_info.c    |  8 ++++----
 5 files changed, 28 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c
index 1505042d7b5d..74f793423231 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.c
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.c
@@ -32,6 +32,20 @@ intel_sseu_subslice_total(const struct sseu_dev_info *sseu)
 	return total;
 }
 
+u32 intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice)
+{
+	int i, offset = slice * sseu->ss_stride;
+	u32 mask = 0;
+
+	GEM_BUG_ON(slice >= sseu->max_slices);
+
+	for (i = 0; i < sseu->ss_stride; i++)
+		mask |= (u32)sseu->subslice_mask[offset + i] <<
+			i * BITS_PER_BYTE;
+
+	return mask;
+}
+
 void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
 			      u32 ss_mask)
 {
@@ -43,7 +57,7 @@ void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
 unsigned int
 intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice)
 {
-	return hweight8(sseu->subslice_mask[slice]);
+	return hweight32(intel_sseu_get_subslices(sseu, slice));
 }
 
 u32 intel_sseu_make_rpcs(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 7703d75f2da3..4070f6ff1db6 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -23,7 +23,7 @@ struct drm_i915_private;
 
 struct sseu_dev_info {
 	u8 slice_mask;
-	u8 subslice_mask[GEN_MAX_SLICES];
+	u8 subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
 	u16 eu_total;
 	u8 eu_per_subslice;
 	u8 min_eu_in_pool;
@@ -94,6 +94,8 @@ intel_sseu_subslice_total(const struct sseu_dev_info *sseu);
 unsigned int
 intel_sseu_subslices_per_slice(const struct sseu_dev_info *sseu, u8 slice);
 
+u32  intel_sseu_get_subslices(const struct sseu_dev_info *sseu, u8 slice);
+
 void intel_sseu_set_subslices(struct sseu_dev_info *sseu, int slice,
 			      u32 ss_mask);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 126ab3667919..ad2261e0cba8 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -801,11 +801,10 @@ wa_init_mcr(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	}
 
 	slice = fls(sseu->slice_mask) - 1;
-	GEM_BUG_ON(slice >= ARRAY_SIZE(sseu->subslice_mask));
-	subslice = fls(l3_en & sseu->subslice_mask[slice]);
+	subslice = fls(l3_en & intel_sseu_get_subslices(sseu, slice));
 	if (!subslice) {
 		DRM_WARN("No common index found between subslice mask %x and L3 bank mask %x!\n",
-			 sseu->subslice_mask[slice], l3_en);
+			 intel_sseu_get_subslices(sseu, slice), l3_en);
 		subslice = fls(l3_en);
 		WARN_ON(!subslice);
 	}
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 6e8b40299939..8c1d70425424 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3864,13 +3864,16 @@ static void gen9_sseu_device_status(struct drm_i915_private *dev_priv,
 
 		for (ss = 0; ss < info->sseu.max_subslices; ss++) {
 			unsigned int eu_cnt;
+			u8 ss_idx = s * info->sseu.ss_stride +
+				    ss / BITS_PER_BYTE;
 
 			if (IS_GEN9_LP(dev_priv)) {
 				if (!(s_reg[s] & (GEN9_PGCTL_SS_ACK(ss))))
 					/* skip disabled subslice */
 					continue;
 
-				sseu->subslice_mask[s] |= BIT(ss);
+				sseu->subslice_mask[ss_idx] |=
+					BIT(ss % BITS_PER_BYTE);
 			}
 
 			eu_cnt = 2 * hweight32(eu_reg[2*s + ss/2] &
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index c20f74ee5f22..d9b5baaef5d0 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -93,9 +93,9 @@ static void sseu_dump(const struct sseu_dev_info *sseu, struct drm_printer *p)
 		   hweight8(sseu->slice_mask), sseu->slice_mask);
 	drm_printf(p, "subslice total: %u\n", intel_sseu_subslice_total(sseu));
 	for (s = 0; s < sseu->max_slices; s++) {
-		drm_printf(p, "slice%d: %u subslices, mask=%04x\n",
+		drm_printf(p, "slice%d: %u subslices, mask=%08x\n",
 			   s, intel_sseu_subslices_per_slice(sseu, s),
-			   sseu->subslice_mask[s]);
+			   intel_sseu_get_subslices(sseu, s));
 	}
 	drm_printf(p, "EU total: %u\n", sseu->eu_total);
 	drm_printf(p, "EU per subslice: %u\n", sseu->eu_per_subslice);
@@ -159,9 +159,9 @@ void intel_device_info_dump_topology(const struct sseu_dev_info *sseu,
 	}
 
 	for (s = 0; s < sseu->max_slices; s++) {
-		drm_printf(p, "slice%d: %u subslice(s) (0x%hhx):\n",
+		drm_printf(p, "slice%d: %u subslice(s) (0x%08x):\n",
 			   s, intel_sseu_subslices_per_slice(sseu, s),
-			   sseu->subslice_mask[s]);
+			   intel_sseu_get_subslices(sseu, s));
 
 		for (ss = 0; ss < sseu->max_subslices; ss++) {
 			u16 enabled_eus = sseu_get_eus(sseu, s, ss);
-- 
cgit v1.2.3


From d06a79d33e0f97373a29decb66791758a6d2e968 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 21 Aug 2019 20:30:29 +0300
Subject: drm/i915: Use enum pipe instead of crtc index to track active pipes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We may need to eliminate the crtc->index == pipe assumptions from
the code to support arbitrary pipes being fused off. Start that by
switching some bitmasks over to using pipe instead of the crtc index.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190821173033.24123-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_cdclk.c         | 12 ++++++------
 drivers/gpu/drm/i915/display/intel_display.c       | 20 ++++++++++----------
 drivers/gpu/drm/i915/display/intel_display_types.h |  4 ++--
 drivers/gpu/drm/i915/i915_drv.h                    |  2 +-
 drivers/gpu/drm/i915/intel_pm.c                    | 20 ++++++++++----------
 5 files changed, 29 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index d0bc42e5039c..939088c7d814 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -2369,7 +2369,7 @@ static int vlv_modeset_calc_cdclk(struct intel_atomic_state *state)
 	state->cdclk.logical.voltage_level =
 		vlv_calc_voltage_level(dev_priv, cdclk);
 
-	if (!state->active_crtcs) {
+	if (!state->active_pipes) {
 		cdclk = vlv_calc_cdclk(dev_priv, state->cdclk.force_min_cdclk);
 
 		state->cdclk.actual.cdclk = cdclk;
@@ -2400,7 +2400,7 @@ static int bdw_modeset_calc_cdclk(struct intel_atomic_state *state)
 	state->cdclk.logical.voltage_level =
 		bdw_calc_voltage_level(cdclk);
 
-	if (!state->active_crtcs) {
+	if (!state->active_pipes) {
 		cdclk = bdw_calc_cdclk(state->cdclk.force_min_cdclk);
 
 		state->cdclk.actual.cdclk = cdclk;
@@ -2470,7 +2470,7 @@ static int skl_modeset_calc_cdclk(struct intel_atomic_state *state)
 	state->cdclk.logical.voltage_level =
 		skl_calc_voltage_level(cdclk);
 
-	if (!state->active_crtcs) {
+	if (!state->active_pipes) {
 		cdclk = skl_calc_cdclk(state->cdclk.force_min_cdclk, vco);
 
 		state->cdclk.actual.vco = vco;
@@ -2506,7 +2506,7 @@ static int bxt_modeset_calc_cdclk(struct intel_atomic_state *state)
 	state->cdclk.logical.voltage_level =
 		bxt_calc_voltage_level(cdclk);
 
-	if (!state->active_crtcs) {
+	if (!state->active_pipes) {
 		if (IS_GEMINILAKE(dev_priv)) {
 			cdclk = glk_calc_cdclk(state->cdclk.force_min_cdclk);
 			vco = glk_de_pll_vco(dev_priv, cdclk);
@@ -2544,7 +2544,7 @@ static int cnl_modeset_calc_cdclk(struct intel_atomic_state *state)
 		max(cnl_calc_voltage_level(cdclk),
 		    cnl_compute_min_voltage_level(state));
 
-	if (!state->active_crtcs) {
+	if (!state->active_pipes) {
 		cdclk = cnl_calc_cdclk(state->cdclk.force_min_cdclk);
 		vco = cnl_cdclk_pll_vco(dev_priv, cdclk);
 
@@ -2578,7 +2578,7 @@ static int icl_modeset_calc_cdclk(struct intel_atomic_state *state)
 		max(icl_calc_voltage_level(dev_priv, cdclk),
 		    cnl_compute_min_voltage_level(state));
 
-	if (!state->active_crtcs) {
+	if (!state->active_pipes) {
 		cdclk = icl_calc_cdclk(state->cdclk.force_min_cdclk, ref);
 		vco = icl_calc_cdclk_pll_vco(dev_priv, cdclk);
 
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index b51d1ceb8739..7b74df03a1ef 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -7080,7 +7080,7 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc,
 		intel_display_power_put_unchecked(dev_priv, domain);
 	intel_crtc->enabled_power_domains = 0;
 
-	dev_priv->active_crtcs &= ~(1 << intel_crtc->pipe);
+	dev_priv->active_pipes &= ~BIT(intel_crtc->pipe);
 	dev_priv->min_cdclk[intel_crtc->pipe] = 0;
 	dev_priv->min_voltage_level[intel_crtc->pipe] = 0;
 
@@ -13452,7 +13452,7 @@ static int intel_modeset_checks(struct intel_atomic_state *state)
 		state->cdclk.force_min_cdclk = dev_priv->cdclk.force_min_cdclk;
 
 	state->modeset = true;
-	state->active_crtcs = dev_priv->active_crtcs;
+	state->active_pipes = dev_priv->active_pipes;
 	state->cdclk.logical = dev_priv->cdclk.logical;
 	state->cdclk.actual = dev_priv->cdclk.actual;
 	state->cdclk.pipe = INVALID_PIPE;
@@ -13460,12 +13460,12 @@ static int intel_modeset_checks(struct intel_atomic_state *state)
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
 		if (new_crtc_state->base.active)
-			state->active_crtcs |= 1 << i;
+			state->active_pipes |= BIT(crtc->pipe);
 		else
-			state->active_crtcs &= ~(1 << i);
+			state->active_pipes &= ~BIT(crtc->pipe);
 
 		if (old_crtc_state->base.active != new_crtc_state->base.active)
-			state->active_pipe_changes |= drm_crtc_mask(&crtc->base);
+			state->active_pipe_changes |= BIT(crtc->pipe);
 	}
 
 	/*
@@ -13494,11 +13494,11 @@ static int intel_modeset_checks(struct intel_atomic_state *state)
 				return ret;
 		}
 
-		if (is_power_of_2(state->active_crtcs)) {
+		if (is_power_of_2(state->active_pipes)) {
 			struct intel_crtc *crtc;
 			struct intel_crtc_state *crtc_state;
 
-			pipe = ilog2(state->active_crtcs);
+			pipe = ilog2(state->active_pipes);
 			crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
 			crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
 			if (crtc_state && needs_modeset(crtc_state))
@@ -14191,7 +14191,7 @@ static int intel_atomic_commit(struct drm_device *dev,
 		       sizeof(state->min_cdclk));
 		memcpy(dev_priv->min_voltage_level, state->min_voltage_level,
 		       sizeof(state->min_voltage_level));
-		dev_priv->active_crtcs = state->active_crtcs;
+		dev_priv->active_pipes = state->active_pipes;
 		dev_priv->cdclk.force_min_cdclk = state->cdclk.force_min_cdclk;
 
 		intel_cdclk_swap_state(state);
@@ -16640,7 +16640,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 	struct drm_connector_list_iter conn_iter;
 	int i;
 
-	dev_priv->active_crtcs = 0;
+	dev_priv->active_pipes = 0;
 
 	for_each_intel_crtc(dev, crtc) {
 		struct intel_crtc_state *crtc_state =
@@ -16657,7 +16657,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		crtc->active = crtc_state->base.active;
 
 		if (crtc_state->base.active)
-			dev_priv->active_crtcs |= 1 << crtc->pipe;
+			dev_priv->active_pipes |= BIT(crtc->pipe);
 
 		DRM_DEBUG_KMS("[CRTC:%d:%s] hw state readout: %s\n",
 			      crtc->base.base.id, crtc->base.name,
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 449abaea619f..12523456143f 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -481,9 +481,9 @@ struct intel_atomic_state {
 	 * but the converse is not necessarily true; simply changing a mode may
 	 * not flip the final active status of any CRTC's
 	 */
-	unsigned int active_pipe_changes;
+	u8 active_pipe_changes;
 
-	unsigned int active_crtcs;
+	u8 active_pipes;
 	/* minimum acceptable cdclk for each pipe */
 	int min_cdclk[I915_MAX_PIPES];
 	/* minimum acceptable voltage level for each pipe */
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 048896b1348b..ba3f6d82ef26 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1468,7 +1468,7 @@ struct drm_i915_private {
 	 */
 	struct mutex dpll_lock;
 
-	unsigned int active_crtcs;
+	u8 active_pipes;
 	/* minimum acceptable cdclk for each pipe */
 	int min_cdclk[I915_MAX_PIPES];
 	/* minimum acceptable voltage level for each pipe */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d3ea193cd093..09f29a337313 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3761,18 +3761,18 @@ bool intel_can_enable_sagv(struct intel_atomic_state *state)
 	/*
 	 * If there are no active CRTCs, no additional checks need be performed
 	 */
-	if (hweight32(state->active_crtcs) == 0)
+	if (hweight32(state->active_pipes) == 0)
 		return true;
 
 	/*
 	 * SKL+ workaround: bspec recommends we disable SAGV when we have
 	 * more then one pipe enabled
 	 */
-	if (hweight32(state->active_crtcs) > 1)
+	if (hweight32(state->active_pipes) > 1)
 		return false;
 
 	/* Since we're now guaranteed to only have one active CRTC... */
-	pipe = ffs(state->active_crtcs) - 1;
+	pipe = ffs(state->active_pipes) - 1;
 	crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
 	crtc_state = to_intel_crtc_state(crtc->base.state);
 
@@ -3867,14 +3867,14 @@ skl_ddb_get_pipe_allocation_limits(struct drm_i915_private *dev_priv,
 	if (WARN_ON(!state) || !crtc_state->base.active) {
 		alloc->start = 0;
 		alloc->end = 0;
-		*num_active = hweight32(dev_priv->active_crtcs);
+		*num_active = hweight32(dev_priv->active_pipes);
 		return;
 	}
 
 	if (intel_state->active_pipe_changes)
-		*num_active = hweight32(intel_state->active_crtcs);
+		*num_active = hweight32(intel_state->active_pipes);
 	else
-		*num_active = hweight32(dev_priv->active_crtcs);
+		*num_active = hweight32(dev_priv->active_pipes);
 
 	ddb_size = intel_get_ddb_size(dev_priv, crtc_state, total_data_rate,
 				      *num_active, ddb);
@@ -5464,7 +5464,7 @@ skl_ddb_add_affected_pipes(struct intel_atomic_state *state, bool *changed)
 	 * If this transaction isn't actually touching any CRTC's, don't
 	 * bother with watermark calculation.  Note that if we pass this
 	 * test, we're guaranteed to hold at least one CRTC state mutex,
-	 * which means we can safely use values like dev_priv->active_crtcs
+	 * which means we can safely use values like dev_priv->active_pipes
 	 * since any racing commits that want to update them would need to
 	 * hold _all_ CRTC state mutexes.
 	 */
@@ -5489,13 +5489,13 @@ skl_ddb_add_affected_pipes(struct intel_atomic_state *state, bool *changed)
 		state->active_pipe_changes = ~0;
 
 		/*
-		 * We usually only initialize state->active_crtcs if we
+		 * We usually only initialize state->active_pipes if we
 		 * we're doing a modeset; make sure this field is always
 		 * initialized during the sanitization process that happens
 		 * on the first commit too.
 		 */
 		if (!state->modeset)
-			state->active_crtcs = dev_priv->active_crtcs;
+			state->active_pipes = dev_priv->active_pipes;
 	}
 
 	/*
@@ -5811,7 +5811,7 @@ void skl_wm_get_hw_state(struct drm_i915_private *dev_priv)
 			hw->dirty_pipes |= drm_crtc_mask(&crtc->base);
 	}
 
-	if (dev_priv->active_crtcs) {
+	if (dev_priv->active_pipes) {
 		/* Fully recompute DDB on first atomic commit */
 		dev_priv->wm.distrust_bios_wm = true;
 	}
-- 
cgit v1.2.3


From e8edae54c593bc9aea949fbf6b2a59fe53cd5d83 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 21 Aug 2019 20:30:30 +0300
Subject: drm/i915: Unconfuse pipe vs. crtc->index in
 i915_get_crtc_scanoutpos()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The "pipe" argument passed in by the vblank code is in fact the crtc
index. Don't assume that is the same as the pipe.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190821173033.24123-2-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 77391d8325bf..8ac6f6849981 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -942,14 +942,14 @@ static int __intel_get_crtc_scanline(struct intel_crtc *crtc)
 	return (position + crtc->scanline_offset) % vtotal;
 }
 
-bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
+bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int index,
 			      bool in_vblank_irq, int *vpos, int *hpos,
 			      ktime_t *stime, ktime_t *etime,
 			      const struct drm_display_mode *mode)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = intel_get_crtc_for_pipe(dev_priv,
-								pipe);
+	struct intel_crtc *crtc = to_intel_crtc(drm_crtc_from_index(dev, index));
+	enum pipe pipe = crtc->pipe;
 	int position;
 	int vbl_start, vbl_end, hsync_start, htotal, vtotal;
 	unsigned long irqflags;
@@ -992,7 +992,7 @@ bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 		/* No obvious pixelcount register. Only query vertical
 		 * scanout position from Display scan line register.
 		 */
-		position = __intel_get_crtc_scanline(intel_crtc);
+		position = __intel_get_crtc_scanline(crtc);
 	} else {
 		/* Have access to pixelcount since start of frame.
 		 * We can split this into vertical and horizontal
-- 
cgit v1.2.3


From d048a2684a413b33a28be277a7e9cee960ec8bb2 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 21 Aug 2019 20:30:31 +0300
Subject: drm/i915: Use enum pipe consistently
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace all "int pipe"s with "enum pipe pipe"s to make it clear
what we're dealing with.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190821173033.24123-3-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c       | 42 +++++++++++-----------
 drivers/gpu/drm/i915/display/intel_display_types.h |  2 +-
 drivers/gpu/drm/i915/display/intel_dvo.c           |  2 +-
 drivers/gpu/drm/i915/display/intel_lvds.c          |  2 +-
 drivers/gpu/drm/i915/display/vlv_dsi.c             |  2 +-
 drivers/gpu/drm/i915/i915_debugfs.c                |  2 +-
 drivers/gpu/drm/i915/i915_irq.c                    | 11 +++---
 drivers/gpu/drm/i915/intel_pm.c                    |  2 +-
 8 files changed, 33 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 7b74df03a1ef..ea2915dde6ab 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -490,7 +490,7 @@ static const struct intel_limit intel_limits_bxt = {
 
 /* WA Display #0827: Gen9:all */
 static void
-skl_wa_827(struct drm_i915_private *dev_priv, int pipe, bool enable)
+skl_wa_827(struct drm_i915_private *dev_priv, enum pipe pipe, bool enable)
 {
 	if (enable)
 		I915_WRITE(CLKGATE_DIS_PSL(pipe),
@@ -4421,7 +4421,7 @@ static void intel_fdi_normal_train(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	int pipe = crtc->pipe;
+	enum pipe pipe = crtc->pipe;
 	i915_reg_t reg;
 	u32 temp;
 
@@ -4464,7 +4464,7 @@ static void ironlake_fdi_link_train(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	int pipe = crtc->pipe;
+	enum pipe pipe = crtc->pipe;
 	i915_reg_t reg;
 	u32 temp, tries;
 
@@ -4565,7 +4565,7 @@ static void gen6_fdi_link_train(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	int pipe = crtc->pipe;
+	enum pipe pipe = crtc->pipe;
 	i915_reg_t reg;
 	u32 temp, i, retry;
 
@@ -4698,7 +4698,7 @@ static void ivb_manual_fdi_link_train(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	int pipe = crtc->pipe;
+	enum pipe pipe = crtc->pipe;
 	i915_reg_t reg;
 	u32 temp, i, j;
 
@@ -4816,7 +4816,7 @@ static void ironlake_fdi_pll_enable(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
-	int pipe = intel_crtc->pipe;
+	enum pipe pipe = intel_crtc->pipe;
 	i915_reg_t reg;
 	u32 temp;
 
@@ -4853,7 +4853,7 @@ static void ironlake_fdi_pll_disable(struct intel_crtc *intel_crtc)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	int pipe = intel_crtc->pipe;
+	enum pipe pipe = intel_crtc->pipe;
 	i915_reg_t reg;
 	u32 temp;
 
@@ -4884,7 +4884,7 @@ static void ironlake_fdi_disable(struct drm_crtc *crtc)
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
+	enum pipe pipe = intel_crtc->pipe;
 	i915_reg_t reg;
 	u32 temp;
 
@@ -5199,7 +5199,7 @@ static void ironlake_pch_enable(const struct intel_atomic_state *state,
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	int pipe = crtc->pipe;
+	enum pipe pipe = crtc->pipe;
 	u32 temp;
 
 	assert_pch_transcoder_disabled(dev_priv, pipe);
@@ -5294,7 +5294,7 @@ static void lpt_pch_enable(const struct intel_atomic_state *state,
 	lpt_enable_pch_transcoder(dev_priv, cpu_transcoder);
 }
 
-static void cpt_verify_modeset(struct drm_device *dev, int pipe)
+static void cpt_verify_modeset(struct drm_device *dev, enum pipe pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	i915_reg_t dslreg = PIPEDSL(pipe);
@@ -5633,7 +5633,7 @@ static void ironlake_pfit_enable(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	int pipe = crtc->pipe;
+	enum pipe pipe = crtc->pipe;
 
 	if (crtc_state->pch_pfit.enabled) {
 		/* Force use of hard-coded filter coefficients
@@ -5746,7 +5746,7 @@ intel_post_enable_primary(struct drm_crtc *crtc,
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
+	enum pipe pipe = intel_crtc->pipe;
 
 	/*
 	 * Gen2 reports pipe underruns whenever all planes are disabled.
@@ -5770,7 +5770,7 @@ intel_pre_disable_primary_noatomic(struct drm_crtc *crtc)
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
+	enum pipe pipe = intel_crtc->pipe;
 
 	/*
 	 * Gen2 reports pipe underruns whenever all planes are disabled.
@@ -6293,7 +6293,7 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
+	enum pipe pipe = intel_crtc->pipe;
 
 	if (WARN_ON(intel_crtc->active))
 		return;
@@ -6426,7 +6426,7 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	struct drm_crtc *crtc = pipe_config->base.crtc;
 	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe, hsw_workaround_pipe;
+	enum pipe pipe = intel_crtc->pipe, hsw_workaround_pipe;
 	enum transcoder cpu_transcoder = pipe_config->cpu_transcoder;
 	bool psl_clkgate_wa;
 
@@ -6552,7 +6552,7 @@ static void ironlake_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
+	enum pipe pipe = intel_crtc->pipe;
 
 	/*
 	 * Sometimes spurious CPU pipe underruns happen when the
@@ -6839,7 +6839,7 @@ static void valleyview_crtc_enable(struct intel_crtc_state *pipe_config,
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
+	enum pipe pipe = intel_crtc->pipe;
 
 	if (WARN_ON(intel_crtc->active))
 		return;
@@ -6971,7 +6971,7 @@ static void i9xx_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
+	enum pipe pipe = intel_crtc->pipe;
 
 	/*
 	 * On gen2 planes are double buffered but the pipe isn't, so we must
@@ -8543,7 +8543,7 @@ static void vlv_crtc_clock_get(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	int pipe = pipe_config->cpu_transcoder;
+	enum pipe pipe = crtc->pipe;
 	struct dpll clock;
 	u32 mdiv;
 	int refclk = 100000;
@@ -8653,7 +8653,7 @@ static void chv_crtc_clock_get(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	int pipe = pipe_config->cpu_transcoder;
+	enum pipe pipe = crtc->pipe;
 	enum dpio_channel port = vlv_pipe_to_channel(pipe);
 	struct dpll clock;
 	u32 cmn_dw13, pll_dw0, pll_dw1, pll_dw2, pll_dw3;
@@ -11265,7 +11265,7 @@ static void i9xx_crtc_clock_get(struct intel_crtc *crtc,
 {
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	int pipe = pipe_config->cpu_transcoder;
+	enum pipe pipe = crtc->pipe;
 	u32 dpll = pipe_config->dpll_hw_state.dpll;
 	u32 fp;
 	struct dpll clock;
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 12523456143f..96514dcc7812 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1509,7 +1509,7 @@ intel_wait_for_vblank(struct drm_i915_private *dev_priv, enum pipe pipe)
 	drm_wait_one_vblank(&dev_priv->drm, pipe);
 }
 static inline void
-intel_wait_for_vblank_if_active(struct drm_i915_private *dev_priv, int pipe)
+intel_wait_for_vblank_if_active(struct drm_i915_private *dev_priv, enum pipe pipe)
 {
 	const struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
 
diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c
index 93baf366692e..34193d04597a 100644
--- a/drivers/gpu/drm/i915/display/intel_dvo.c
+++ b/drivers/gpu/drm/i915/display/intel_dvo.c
@@ -280,7 +280,7 @@ static void intel_dvo_pre_enable(struct intel_encoder *encoder,
 	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
 	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
-	int pipe = crtc->pipe;
+	enum pipe pipe = crtc->pipe;
 	u32 dvo_val;
 	i915_reg_t dvo_reg = intel_dvo->dev.dvo_reg;
 	i915_reg_t dvo_srcdim_reg = intel_dvo->dev.dvo_srcdim_reg;
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index b7c459a8931c..c786abdc3336 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -232,7 +232,7 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder,
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
 	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	int pipe = crtc->pipe;
+	enum pipe pipe = crtc->pipe;
 	u32 temp;
 
 	if (HAS_PCH_SPLIT(dev_priv)) {
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index a71b22bdd95b..50064cde0724 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -749,7 +749,7 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder,
 	struct drm_crtc *crtc = pipe_config->base.crtc;
 	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
+	enum pipe pipe = intel_crtc->pipe;
 	enum port port;
 	u32 val;
 	bool glk_cold_boot = false;
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 8c1d70425424..5c1a2b1e7d34 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -376,7 +376,7 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 static void gen8_display_interrupt_info(struct seq_file *m)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	int pipe;
+	enum pipe pipe;
 
 	for_each_pipe(dev_priv, pipe) {
 		enum intel_display_power_domain power_domain;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 8ac6f6849981..3f1b6ee157ba 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1716,7 +1716,7 @@ static void i9xx_pipestat_irq_reset(struct drm_i915_private *dev_priv)
 static void i9xx_pipestat_irq_ack(struct drm_i915_private *dev_priv,
 				  u32 iir, u32 pipe_stats[I915_MAX_PIPES])
 {
-	int pipe;
+	enum pipe pipe;
 
 	spin_lock(&dev_priv->irq_lock);
 
@@ -1741,6 +1741,7 @@ static void i9xx_pipestat_irq_ack(struct drm_i915_private *dev_priv,
 		status_mask = PIPE_FIFO_UNDERRUN_STATUS;
 
 		switch (pipe) {
+		default:
 		case PIPE_A:
 			iir_bit = I915_DISPLAY_PIPE_A_EVENT_INTERRUPT;
 			break;
@@ -2136,7 +2137,7 @@ static void ibx_hpd_irq_handler(struct drm_i915_private *dev_priv,
 
 static void ibx_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 {
-	int pipe;
+	enum pipe pipe;
 	u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK;
 
 	ibx_hpd_irq_handler(dev_priv, hotplug_trigger, hpd_ibx);
@@ -2222,7 +2223,7 @@ static void cpt_serr_int_handler(struct drm_i915_private *dev_priv)
 
 static void cpt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 {
-	int pipe;
+	enum pipe pipe;
 	u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_CPT;
 
 	ibx_hpd_irq_handler(dev_priv, hotplug_trigger, hpd_cpt);
@@ -3246,7 +3247,7 @@ static void valleyview_irq_reset(struct drm_i915_private *dev_priv)
 static void gen8_irq_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
-	int pipe;
+	enum pipe pipe;
 
 	gen8_master_intr_disable(dev_priv->uncore.regs);
 
@@ -3271,7 +3272,7 @@ static void gen8_irq_reset(struct drm_i915_private *dev_priv)
 static void gen11_irq_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
-	int pipe;
+	enum pipe pipe;
 
 	gen11_master_intr_disable(dev_priv->uncore.regs);
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 09f29a337313..437cd50e5d06 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -8858,7 +8858,7 @@ static void ilk_init_clock_gating(struct drm_i915_private *dev_priv)
 
 static void cpt_init_clock_gating(struct drm_i915_private *dev_priv)
 {
-	int pipe;
+	enum pipe pipe;
 	u32 val;
 
 	/*
-- 
cgit v1.2.3


From c08e91323920ec4b3a4d889af3988e300b1902f1 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 21 Aug 2019 20:30:32 +0300
Subject: drm/i915: s/num_active_crtcs/num_active_pipes/
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Set a good example and talk about pipes rather than crtcs.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190821173033.24123-4-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_pm.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 437cd50e5d06..b4b9609db092 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1490,7 +1490,7 @@ static void g4x_merge_wm(struct drm_i915_private *dev_priv,
 			 struct g4x_wm_values *wm)
 {
 	struct intel_crtc *crtc;
-	int num_active_crtcs = 0;
+	int num_active_pipes = 0;
 
 	wm->cxsr = true;
 	wm->hpll_en = true;
@@ -1509,10 +1509,10 @@ static void g4x_merge_wm(struct drm_i915_private *dev_priv,
 		if (!wm_state->fbc_en)
 			wm->fbc_en = false;
 
-		num_active_crtcs++;
+		num_active_pipes++;
 	}
 
-	if (num_active_crtcs != 1) {
+	if (num_active_pipes != 1) {
 		wm->cxsr = false;
 		wm->hpll_en = false;
 		wm->fbc_en = false;
@@ -2098,7 +2098,7 @@ static void vlv_merge_wm(struct drm_i915_private *dev_priv,
 			 struct vlv_wm_values *wm)
 {
 	struct intel_crtc *crtc;
-	int num_active_crtcs = 0;
+	int num_active_pipes = 0;
 
 	wm->level = dev_priv->wm.max_level;
 	wm->cxsr = true;
@@ -2112,14 +2112,14 @@ static void vlv_merge_wm(struct drm_i915_private *dev_priv,
 		if (!wm_state->cxsr)
 			wm->cxsr = false;
 
-		num_active_crtcs++;
+		num_active_pipes++;
 		wm->level = min_t(int, wm->level, wm_state->num_levels - 1);
 	}
 
-	if (num_active_crtcs != 1)
+	if (num_active_pipes != 1)
 		wm->cxsr = false;
 
-	if (num_active_crtcs > 1)
+	if (num_active_pipes > 1)
 		wm->level = VLV_WM_LEVEL_PM2;
 
 	for_each_intel_crtc(&dev_priv->drm, crtc) {
-- 
cgit v1.2.3


From 0b14d96820d1fd05ea610a0f5f952b34e5a24f2c Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 21 Aug 2019 20:30:33 +0300
Subject: drm/i915: Use hweight8() for 8bit masks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use hweight8() instead of hweight32() for 8bit masks. Doesn't actually
matter for us since the arch code will go for hweight32() anyway, but
maybe we stil want to do this for documentation purposes?

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190821173033.24123-5-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_pm.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index b4b9609db092..4fa9bc83c8b4 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1327,8 +1327,8 @@ static int g4x_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	struct intel_atomic_state *state =
 		to_intel_atomic_state(crtc_state->base.state);
 	struct g4x_wm_state *wm_state = &crtc_state->wm.g4x.optimal;
-	int num_active_planes = hweight32(crtc_state->active_planes &
-					  ~BIT(PLANE_CURSOR));
+	int num_active_planes = hweight8(crtc_state->active_planes &
+					 ~BIT(PLANE_CURSOR));
 	const struct g4x_pipe_wm *raw;
 	const struct intel_plane_state *old_plane_state;
 	const struct intel_plane_state *new_plane_state;
@@ -1659,7 +1659,7 @@ static int vlv_compute_fifo(struct intel_crtc_state *crtc_state)
 		&crtc_state->wm.vlv.raw[VLV_WM_LEVEL_PM2];
 	struct vlv_fifo_state *fifo_state = &crtc_state->wm.vlv.fifo_state;
 	unsigned int active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
-	int num_active_planes = hweight32(active_planes);
+	int num_active_planes = hweight8(active_planes);
 	const int fifo_size = 511;
 	int fifo_extra, fifo_left = fifo_size;
 	int sprite0_fifo_extra = 0;
@@ -1848,8 +1848,8 @@ static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	struct vlv_wm_state *wm_state = &crtc_state->wm.vlv.optimal;
 	const struct vlv_fifo_state *fifo_state =
 		&crtc_state->wm.vlv.fifo_state;
-	int num_active_planes = hweight32(crtc_state->active_planes &
-					  ~BIT(PLANE_CURSOR));
+	int num_active_planes = hweight8(crtc_state->active_planes &
+					 ~BIT(PLANE_CURSOR));
 	bool needs_modeset = drm_atomic_crtc_needs_modeset(&crtc_state->base);
 	const struct intel_plane_state *old_plane_state;
 	const struct intel_plane_state *new_plane_state;
@@ -3761,14 +3761,14 @@ bool intel_can_enable_sagv(struct intel_atomic_state *state)
 	/*
 	 * If there are no active CRTCs, no additional checks need be performed
 	 */
-	if (hweight32(state->active_pipes) == 0)
+	if (hweight8(state->active_pipes) == 0)
 		return true;
 
 	/*
 	 * SKL+ workaround: bspec recommends we disable SAGV when we have
 	 * more then one pipe enabled
 	 */
-	if (hweight32(state->active_pipes) > 1)
+	if (hweight8(state->active_pipes) > 1)
 		return false;
 
 	/* Since we're now guaranteed to only have one active CRTC... */
@@ -3867,14 +3867,14 @@ skl_ddb_get_pipe_allocation_limits(struct drm_i915_private *dev_priv,
 	if (WARN_ON(!state) || !crtc_state->base.active) {
 		alloc->start = 0;
 		alloc->end = 0;
-		*num_active = hweight32(dev_priv->active_pipes);
+		*num_active = hweight8(dev_priv->active_pipes);
 		return;
 	}
 
 	if (intel_state->active_pipe_changes)
-		*num_active = hweight32(intel_state->active_pipes);
+		*num_active = hweight8(intel_state->active_pipes);
 	else
-		*num_active = hweight32(dev_priv->active_pipes);
+		*num_active = hweight8(dev_priv->active_pipes);
 
 	ddb_size = intel_get_ddb_size(dev_priv, crtc_state, total_data_rate,
 				      *num_active, ddb);
-- 
cgit v1.2.3


From 6dcb85a0ad990455ae7c596e3fc966ad9c1ba9c5 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 23 Aug 2019 14:26:46 +0100
Subject: drm/i915: Hold irq-off for the entire fake lock period

Sadly lockdep records when the irqs are re-enabled and then marks up the
fake lock as being irq-unsafe. Our hand is forced and so we must mark up
the entire fake lock critical section as irq-off.

Hopefully this is the last tweak required!

v2: Not quite, we need to mark the timeline spinlock as irqsafe. That
was a genuine bug being hidden by the earlier lockdep splat.

Fixes: d67739268cf0 ("drm/i915/gt: Mark up the nested engine-pm timeline lock as irqsafe")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823132700.25286-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_engine_pm.c | 28 ++++++++++++++++++----------
 drivers/gpu/drm/i915/gt/intel_reset.c     |  9 +++++----
 drivers/gpu/drm/i915/gt/intel_timeline.c  | 10 ++++++----
 drivers/gpu/drm/i915/i915_gem.c           | 15 ++++++++-------
 drivers/gpu/drm/i915/i915_request.c       |  9 +++++----
 5 files changed, 42 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index a372d4ea9370..65b5ca74b394 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -39,27 +39,32 @@ static int __engine_unpark(struct intel_wakeref *wf)
 
 #if IS_ENABLED(CONFIG_LOCKDEP)
 
-static inline void __timeline_mark_lock(struct intel_context *ce)
+static inline unsigned long __timeline_mark_lock(struct intel_context *ce)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
 	mutex_acquire(&ce->timeline->mutex.dep_map, 2, 0, _THIS_IP_);
-	local_irq_restore(flags);
+
+	return flags;
 }
 
-static inline void __timeline_mark_unlock(struct intel_context *ce)
+static inline void __timeline_mark_unlock(struct intel_context *ce,
+					  unsigned long flags)
 {
 	mutex_release(&ce->timeline->mutex.dep_map, 0, _THIS_IP_);
+	local_irq_restore(flags);
 }
 
 #else
 
-static inline void __timeline_mark_lock(struct intel_context *ce)
+static inline unsigned long __timeline_mark_lock(struct intel_context *ce)
 {
+	return 0;
 }
 
-static inline void __timeline_mark_unlock(struct intel_context *ce)
+static inline void __timeline_mark_unlock(struct intel_context *ce,
+					  unsigned long flags)
 {
 }
 
@@ -68,6 +73,8 @@ static inline void __timeline_mark_unlock(struct intel_context *ce)
 static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 {
 	struct i915_request *rq;
+	unsigned long flags;
+	bool result = true;
 
 	/* Already inside the kernel context, safe to power down. */
 	if (engine->wakeref_serial == engine->serial)
@@ -89,12 +96,12 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	 * retiring the last request, thus all rings should be empty and
 	 * all timelines idle.
 	 */
-	__timeline_mark_lock(engine->kernel_context);
+	flags = __timeline_mark_lock(engine->kernel_context);
 
 	rq = __i915_request_create(engine->kernel_context, GFP_NOWAIT);
 	if (IS_ERR(rq))
 		/* Context switch failed, hope for the best! Maybe reset? */
-		return true;
+		goto out_unlock;
 
 	intel_timeline_enter(rq->timeline);
 
@@ -110,9 +117,10 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	__intel_wakeref_defer_park(&engine->wakeref);
 	__i915_request_queue(rq, NULL);
 
-	__timeline_mark_unlock(engine->kernel_context);
-
-	return false;
+	result = false;
+out_unlock:
+	__timeline_mark_unlock(engine->kernel_context, flags);
+	return result;
 }
 
 static int __engine_park(struct intel_wakeref *wf)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 077716442c90..b9d84d52e986 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -792,6 +792,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
 	struct intel_timeline *tl;
+	unsigned long flags;
 
 	if (!test_bit(I915_WEDGED, &gt->reset.flags))
 		return true;
@@ -811,7 +812,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	 *
 	 * No more can be submitted until we reset the wedged bit.
 	 */
-	spin_lock(&timelines->lock);
+	spin_lock_irqsave(&timelines->lock, flags);
 	list_for_each_entry(tl, &timelines->active_list, link) {
 		struct i915_request *rq;
 
@@ -819,7 +820,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 		if (!rq)
 			continue;
 
-		spin_unlock(&timelines->lock);
+		spin_unlock_irqrestore(&timelines->lock, flags);
 
 		/*
 		 * All internal dependencies (i915_requests) will have
@@ -832,10 +833,10 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 		i915_request_put(rq);
 
 		/* Restart iteration after droping lock */
-		spin_lock(&timelines->lock);
+		spin_lock_irqsave(&timelines->lock, flags);
 		tl = list_entry(&timelines->active_list, typeof(*tl), link);
 	}
-	spin_unlock(&timelines->lock);
+	spin_unlock_irqrestore(&timelines->lock, flags);
 
 	intel_gt_sanitize(gt, false);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 02fbe11b671b..9cb01d9828f1 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -337,6 +337,7 @@ int intel_timeline_pin(struct intel_timeline *tl)
 void intel_timeline_enter(struct intel_timeline *tl)
 {
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
+	unsigned long flags;
 
 	lockdep_assert_held(&tl->mutex);
 
@@ -345,14 +346,15 @@ void intel_timeline_enter(struct intel_timeline *tl)
 		return;
 	GEM_BUG_ON(!tl->active_count); /* overflow? */
 
-	spin_lock(&timelines->lock);
+	spin_lock_irqsave(&timelines->lock, flags);
 	list_add(&tl->link, &timelines->active_list);
-	spin_unlock(&timelines->lock);
+	spin_unlock_irqrestore(&timelines->lock, flags);
 }
 
 void intel_timeline_exit(struct intel_timeline *tl)
 {
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
+	unsigned long flags;
 
 	lockdep_assert_held(&tl->mutex);
 
@@ -360,9 +362,9 @@ void intel_timeline_exit(struct intel_timeline *tl)
 	if (--tl->active_count)
 		return;
 
-	spin_lock(&timelines->lock);
+	spin_lock_irqsave(&timelines->lock, flags);
 	list_del(&tl->link);
-	spin_unlock(&timelines->lock);
+	spin_unlock_irqrestore(&timelines->lock, flags);
 
 	/*
 	 * Since this timeline is idle, all bariers upon which we were waiting
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index eb31b69a316a..ec9a46c276de 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -889,12 +889,13 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915)
 
 static long
 wait_for_timelines(struct drm_i915_private *i915,
-		   unsigned int flags, long timeout)
+		   unsigned int wait, long timeout)
 {
 	struct intel_gt_timelines *timelines = &i915->gt.timelines;
 	struct intel_timeline *tl;
+	unsigned long flags;
 
-	spin_lock(&timelines->lock);
+	spin_lock_irqsave(&timelines->lock, flags);
 	list_for_each_entry(tl, &timelines->active_list, link) {
 		struct i915_request *rq;
 
@@ -902,7 +903,7 @@ wait_for_timelines(struct drm_i915_private *i915,
 		if (!rq)
 			continue;
 
-		spin_unlock(&timelines->lock);
+		spin_unlock_irqrestore(&timelines->lock, flags);
 
 		/*
 		 * "Race-to-idle".
@@ -913,19 +914,19 @@ wait_for_timelines(struct drm_i915_private *i915,
 		 * want to complete as quickly as possible to avoid prolonged
 		 * stalls, so allow the gpu to boost to maximum clocks.
 		 */
-		if (flags & I915_WAIT_FOR_IDLE_BOOST)
+		if (wait & I915_WAIT_FOR_IDLE_BOOST)
 			gen6_rps_boost(rq);
 
-		timeout = i915_request_wait(rq, flags, timeout);
+		timeout = i915_request_wait(rq, wait, timeout);
 		i915_request_put(rq);
 		if (timeout < 0)
 			return timeout;
 
 		/* restart after reacquiring the lock */
-		spin_lock(&timelines->lock);
+		spin_lock_irqsave(&timelines->lock, flags);
 		tl = list_entry(&timelines->active_list, typeof(*tl), link);
 	}
-	spin_unlock(&timelines->lock);
+	spin_unlock_irqrestore(&timelines->lock, flags);
 
 	return timeout;
 }
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index f1a0a57fc6fc..a53777dd371c 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1465,9 +1465,10 @@ bool i915_retire_requests(struct drm_i915_private *i915)
 {
 	struct intel_gt_timelines *timelines = &i915->gt.timelines;
 	struct intel_timeline *tl, *tn;
+	unsigned long flags;
 	LIST_HEAD(free);
 
-	spin_lock(&timelines->lock);
+	spin_lock_irqsave(&timelines->lock, flags);
 	list_for_each_entry_safe(tl, tn, &timelines->active_list, link) {
 		if (!mutex_trylock(&tl->mutex))
 			continue;
@@ -1475,11 +1476,11 @@ bool i915_retire_requests(struct drm_i915_private *i915)
 		intel_timeline_get(tl);
 		GEM_BUG_ON(!tl->active_count);
 		tl->active_count++; /* pin the list element */
-		spin_unlock(&timelines->lock);
+		spin_unlock_irqrestore(&timelines->lock, flags);
 
 		retire_requests(tl);
 
-		spin_lock(&timelines->lock);
+		spin_lock_irqsave(&timelines->lock, flags);
 
 		/* Resume iteration after dropping lock */
 		list_safe_reset_next(tl, tn, link);
@@ -1494,7 +1495,7 @@ bool i915_retire_requests(struct drm_i915_private *i915)
 			list_add(&tl->link, &free);
 		}
 	}
-	spin_unlock(&timelines->lock);
+	spin_unlock_irqrestore(&timelines->lock, flags);
 
 	list_for_each_entry_safe(tl, tn, &free, link)
 		__intel_timeline_free(&tl->kref);
-- 
cgit v1.2.3


From 191797a892c91aec6cdffc4e05696b722d779fe3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 23 Aug 2019 15:14:21 +0100
Subject: drm/i915/gtt: Preallocate Braswell top-level page directory

In order for the Braswell top-level PD to remain the same from the time
of request construction to its submission onto HW, as we may be
asynchronously rewriting the page tables (thus changing the expected
register state after having already stored the old addresses in the
request), the top level PD must be preallocated.

So wave goodbye to our lazy allocation of those 4x2 pages.

v2: A little bit of write-flushing required (presumably it always has
been required, but now we are more susceptible and it is showing up!)

v3: Put back the forced-PD-reload on every batch, we can't survive
without it and explicitly marking the context for PD reload makes
Braswell turn nasty.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823141421.2398-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c |  8 +++++++-
 drivers/gpu/drm/i915/i915_gem_gtt.c         | 10 +++++-----
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 1cdfe05514c3..1f735ca9b173 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1003,12 +1003,18 @@ static int emit_ppgtt_update(struct i915_request *rq, void *data)
 		intel_ring_advance(rq, cs);
 	} else if (HAS_LOGICAL_RING_CONTEXTS(engine->i915)) {
 		struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
+		int err;
+
+		/* Magic required to prevent forcewake errors! */
+		err = engine->emit_flush(rq, EMIT_INVALIDATE);
+		if (err)
+			return err;
 
 		cs = intel_ring_begin(rq, 4 * GEN8_3LVL_PDPES + 2);
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
-		*cs++ = MI_LOAD_REGISTER_IMM(2 * GEN8_3LVL_PDPES);
+		*cs++ = MI_LOAD_REGISTER_IMM(2 * GEN8_3LVL_PDPES) | MI_LRI_FORCE_POSTED;
 		for (i = GEN8_3LVL_PDPES; i--; ) {
 			const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 2a425db1cfd8..e0e9b9b52544 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -168,6 +168,7 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
 		pte_flags |= PTE_READ_ONLY;
 
 	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
+	wmb();
 
 	return 0;
 }
@@ -1426,6 +1427,7 @@ static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt)
 		set_pd_entry(pd, idx, pde);
 		atomic_inc(px_used(pde)); /* keep pinned */
 	}
+	wmb();
 
 	return 0;
 }
@@ -1513,11 +1515,9 @@ static struct i915_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 	}
 
 	if (!i915_vm_is_4lvl(&ppgtt->vm)) {
-		if (intel_vgpu_active(i915)) {
-			err = gen8_preallocate_top_level_pdp(ppgtt);
-			if (err)
-				goto err_free_pd;
-		}
+		err = gen8_preallocate_top_level_pdp(ppgtt);
+		if (err)
+			goto err_free_pd;
 	}
 
 	ppgtt->vm.insert_entries = gen8_ppgtt_insert;
-- 
cgit v1.2.3


From 636e83f2f208555c3d19d8b454ebdd8d8f4652cc Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 23 Aug 2019 16:39:44 +0100
Subject: drm/i915: Flush the existing fence before GGTT read/write

Our fence management is lazy, very lazy. If the user marks an object as
untiled, we do not immediately flush the fence but merely mark it as
dirty. On the next use we have to remember to check and remove the fence,
by which time we hope it is idle and we do not have to wait.

v2: Throw away the old fence on the next ggtt_pin.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111468
Fixes: 1f7fd484fff1 ("drm/i915: Replace i915_vma_put_fence()")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823153944.20630-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ec9a46c276de..95e7c52cf8ed 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1027,6 +1027,14 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			return ERR_PTR(ret);
 	}
 
+	if (vma->fence && !i915_gem_object_is_tiled(obj)) {
+		mutex_lock(&vma->vm->mutex);
+		ret = i915_vma_revoke_fence(vma);
+		mutex_unlock(&vma->vm->mutex);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
 	ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
 	if (ret)
 		return ERR_PTR(ret);
-- 
cgit v1.2.3


From 936ad29de8129747bbfeec8a85e38c8a830bd5da Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Mon, 19 Aug 2019 18:23:27 -0700
Subject: drm/i915/uc: define GuC and HuC FWs for EHL

First uc firmware release for EHL.

Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Tested-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190820012327.36443-1-daniele.ceraolospurio@intel.com
---
 drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index bd22bf11adad..296a82603be0 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -39,12 +39,13 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
  * Must be ordered based on platform + revid, from newer to older.
  */
 #define INTEL_UC_FIRMWARE_DEFS(fw_def, guc_def, huc_def) \
-	fw_def(ICELAKE,    0, guc_def(icl, 33, 0, 0), huc_def(icl,  8,  4, 3238)) \
-	fw_def(COFFEELAKE, 0, guc_def(kbl, 33, 0, 0), huc_def(kbl, 02, 00, 1810)) \
-	fw_def(GEMINILAKE, 0, guc_def(glk, 33, 0, 0), huc_def(glk, 03, 01, 2893)) \
-	fw_def(KABYLAKE,   0, guc_def(kbl, 33, 0, 0), huc_def(kbl, 02, 00, 1810)) \
-	fw_def(BROXTON,    0, guc_def(bxt, 33, 0, 0), huc_def(bxt, 01,  8, 2893)) \
-	fw_def(SKYLAKE,    0, guc_def(skl, 33, 0, 0), huc_def(skl, 01, 07, 1398))
+	fw_def(ELKHARTLAKE, 0, guc_def(ehl, 33, 0, 4), huc_def(ehl,  9,  0,    0)) \
+	fw_def(ICELAKE,     0, guc_def(icl, 33, 0, 0), huc_def(icl,  8,  4, 3238)) \
+	fw_def(COFFEELAKE,  0, guc_def(kbl, 33, 0, 0), huc_def(kbl, 02, 00, 1810)) \
+	fw_def(GEMINILAKE,  0, guc_def(glk, 33, 0, 0), huc_def(glk, 03, 01, 2893)) \
+	fw_def(KABYLAKE,    0, guc_def(kbl, 33, 0, 0), huc_def(kbl, 02, 00, 1810)) \
+	fw_def(BROXTON,     0, guc_def(bxt, 33, 0, 0), huc_def(bxt, 01,  8, 2893)) \
+	fw_def(SKYLAKE,     0, guc_def(skl, 33, 0, 0), huc_def(skl, 01, 07, 1398))
 
 #define __MAKE_UC_FW_PATH(prefix_, name_, separator_, major_, minor_, patch_) \
 	"i915/" \
-- 
cgit v1.2.3


From 77715906921251bd9f75bcf4825f176df3f91208 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 23 Aug 2019 19:14:55 +0100
Subject: drm/i915: Keep drm_i915_file_private around under RCU

Ensure that the drm_i915_file_private continues to exist as we attempt
to remove a request from its list, which may race with the destruction
of the file.

<6> [38.380714] [IGT] gem_ctx_create: starting subtest basic-files
<0> [42.201329] BUG: spinlock bad magic on CPU#0, kworker/u16:0/7
<4> [42.201356] general protection fault: 0000 [#1] PREEMPT SMP PTI
<4> [42.201371] CPU: 0 PID: 7 Comm: kworker/u16:0 Tainted: G     U            5.3.0-rc5-CI-Patchwork_14169+ #1
<4> [42.201391] Hardware name: Dell Inc.                 OptiPlex 745                 /0GW726, BIOS 2.3.1  05/21/2007
<4> [42.201594] Workqueue: i915 retire_work_handler [i915]
<4> [42.201614] RIP: 0010:spin_dump+0x5a/0x90
<4> [42.201625] Code: 00 48 8d 88 c0 06 00 00 48 c7 c7 00 71 09 82 e8 35 ef 00 00 48 85 db 44 8b 4d 08 41 b8 ff ff ff ff 48 c7 c1 0b cd 0f 82 74 0e <44> 8b 83 e0 04 00 00 48 8d 8b c0 06 00 00 8b 55 04 48 89 ee 48 c7
<4> [42.201660] RSP: 0018:ffffc9000004bd80 EFLAGS: 00010202
<4> [42.201673] RAX: 0000000000000031 RBX: 6b6b6b6b6b6b6b6b RCX: ffffffff820fcd0b
<4> [42.201688] RDX: 0000000000000000 RSI: ffff88803de266f8 RDI: 00000000ffffffff
<4> [42.201703] RBP: ffff888038381ff8 R08: 00000000ffffffff R09: 000000006b6b6b6b
<4> [42.201718] R10: 0000000041cb0b89 R11: 646162206b636f6c R12: ffff88802a618500
<4> [42.201733] R13: ffff88802b32c288 R14: ffff888038381ff8 R15: ffff88802b32c250
<4> [42.201748] FS:  0000000000000000(0000) GS:ffff88803de00000(0000) knlGS:0000000000000000
<4> [42.201765] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
<4> [42.201778] CR2: 00007f2cefc6d180 CR3: 00000000381ee000 CR4: 00000000000006f0
<4> [42.201793] Call Trace:
<4> [42.201805]  do_raw_spin_lock+0x66/0xb0
<4> [42.201898]  i915_request_retire+0x548/0x7c0 [i915]
<4> [42.201989]  retire_requests+0x4d/0x60 [i915]
<4> [42.202078]  i915_retire_requests+0x144/0x2e0 [i915]
<4> [42.202169]  retire_work_handler+0x10/0x40 [i915]

Recently, in commit 44c22f3f1a0a ("drm/i915: Serialize insertion into the
file->mm.request_list"), we fixed a race on insertion. Now, it appears
we also have a race with destruction!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823181455.31910-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_throttle.c |  4 +---
 drivers/gpu/drm/i915/i915_drv.c              |  2 +-
 drivers/gpu/drm/i915/i915_drv.h              |  6 +++++-
 drivers/gpu/drm/i915/i915_request.c          | 13 +++++++------
 4 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_throttle.c b/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
index 1e372420771b..540ef0551789 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
@@ -50,10 +50,8 @@ i915_gem_throttle_ioctl(struct drm_device *dev, void *data,
 		if (time_after_eq(request->emitted_jiffies, recent_enough))
 			break;
 
-		if (target) {
+		if (target && xchg(&target->file_priv, NULL))
 			list_del(&target->client_link);
-			target->file_priv = NULL;
-		}
 
 		target = request;
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index b5b2a64753e6..723b9b7202b0 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1730,7 +1730,7 @@ static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
 	i915_gem_release(dev, file);
 	mutex_unlock(&dev->struct_mutex);
 
-	kfree(file_priv);
+	kfree_rcu(file_priv, rcu);
 
 	/* Catch up with all the deferred frees from "this" client */
 	i915_gem_flush_free_objects(to_i915(dev));
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ba3f6d82ef26..f5e39a3bfff6 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -185,7 +185,11 @@ struct i915_mmu_object;
 
 struct drm_i915_file_private {
 	struct drm_i915_private *dev_priv;
-	struct drm_file *file;
+
+	union {
+		struct drm_file *file;
+		struct rcu_head rcu;
+	};
 
 	struct {
 		spinlock_t lock;
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index a53777dd371c..18865ce04e13 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -169,16 +169,17 @@ remove_from_client(struct i915_request *request)
 {
 	struct drm_i915_file_private *file_priv;
 
-	file_priv = READ_ONCE(request->file_priv);
-	if (!file_priv)
+	if (!READ_ONCE(request->file_priv))
 		return;
 
-	spin_lock(&file_priv->mm.lock);
-	if (request->file_priv) {
+	rcu_read_lock();
+	file_priv = xchg(&request->file_priv, NULL);
+	if (file_priv) {
+		spin_lock(&file_priv->mm.lock);
 		list_del(&request->client_link);
-		request->file_priv = NULL;
+		spin_unlock(&file_priv->mm.lock);
 	}
-	spin_unlock(&file_priv->mm.lock);
+	rcu_read_unlock();
 }
 
 static void free_capture_list(struct i915_request *request)
-- 
cgit v1.2.3


From 75b974a859e5d9a3ceaa3aa03bbc27d404b32231 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 24 Aug 2019 00:51:41 +0100
Subject: drm/i915/selftests: Teach igt_gpu_fill_dw() to take intel_context

Avoid having to pass around (ctx, engine) everywhere by passing the
actual intel_context we intend to use. Today we preach this lesson to
igt_gpu_fill_dw and its callers' callers.

The immediate benefit for the GEM selftests is that we aim to use the
GEM context as the control, the source of the engines on which to test
the GEM context.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823235141.31799-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/selftests/huge_pages.c    | 103 +++++++++++----------
 .../gpu/drm/i915/gem/selftests/i915_gem_context.c  |  70 ++++++++------
 drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c |  26 +++---
 drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h |  13 ++-
 4 files changed, 116 insertions(+), 96 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 8de83c6d81f5..c5cea4379216 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -879,9 +879,8 @@ out_object_put:
 	return err;
 }
 
-static int gpu_write(struct i915_vma *vma,
-		     struct i915_gem_context *ctx,
-		     struct intel_engine_cs *engine,
+static int gpu_write(struct intel_context *ce,
+		     struct i915_vma *vma,
 		     u32 dw,
 		     u32 val)
 {
@@ -893,7 +892,7 @@ static int gpu_write(struct i915_vma *vma,
 	if (err)
 		return err;
 
-	return igt_gpu_fill_dw(vma, ctx, engine, dw * sizeof(u32),
+	return igt_gpu_fill_dw(ce, vma, dw * sizeof(u32),
 			       vma->size >> PAGE_SHIFT, val);
 }
 
@@ -929,18 +928,16 @@ static int cpu_check(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 	return err;
 }
 
-static int __igt_write_huge(struct i915_gem_context *ctx,
-			    struct intel_engine_cs *engine,
+static int __igt_write_huge(struct intel_context *ce,
 			    struct drm_i915_gem_object *obj,
 			    u64 size, u64 offset,
 			    u32 dword, u32 val)
 {
-	struct i915_address_space *vm = ctx->vm ?: &engine->gt->ggtt->vm;
 	unsigned int flags = PIN_USER | PIN_OFFSET_FIXED;
 	struct i915_vma *vma;
 	int err;
 
-	vma = i915_vma_instance(obj, vm, NULL);
+	vma = i915_vma_instance(obj, ce->vm, NULL);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
@@ -954,7 +951,7 @@ static int __igt_write_huge(struct i915_gem_context *ctx,
 		 * The ggtt may have some pages reserved so
 		 * refrain from erroring out.
 		 */
-		if (err == -ENOSPC && i915_is_ggtt(vm))
+		if (err == -ENOSPC && i915_is_ggtt(ce->vm))
 			err = 0;
 
 		goto out_vma_close;
@@ -964,7 +961,7 @@ static int __igt_write_huge(struct i915_gem_context *ctx,
 	if (err)
 		goto out_vma_unpin;
 
-	err = gpu_write(vma, ctx, engine, dword, val);
+	err = gpu_write(ce, vma, dword, val);
 	if (err) {
 		pr_err("gpu-write failed at offset=%llx\n", offset);
 		goto out_vma_unpin;
@@ -987,14 +984,13 @@ out_vma_close:
 static int igt_write_huge(struct i915_gem_context *ctx,
 			  struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	struct i915_address_space *vm = ctx->vm ?: &i915->ggtt.vm;
-	static struct intel_engine_cs *engines[I915_NUM_ENGINES];
-	struct intel_engine_cs *engine;
+	struct i915_gem_engines *engines;
+	struct i915_gem_engines_iter it;
+	struct intel_context *ce;
 	I915_RND_STATE(prng);
 	IGT_TIMEOUT(end_time);
 	unsigned int max_page_size;
-	unsigned int id;
+	unsigned int count;
 	u64 max;
 	u64 num;
 	u64 size;
@@ -1008,19 +1004,18 @@ static int igt_write_huge(struct i915_gem_context *ctx,
 	if (obj->mm.page_sizes.sg & I915_GTT_PAGE_SIZE_64K)
 		size = round_up(size, I915_GTT_PAGE_SIZE_2M);
 
-	max_page_size = rounddown_pow_of_two(obj->mm.page_sizes.sg);
-	max = div_u64((vm->total - size), max_page_size);
-
 	n = 0;
-	for_each_engine(engine, i915, id) {
-		if (!intel_engine_can_store_dword(engine)) {
-			pr_info("store-dword-imm not supported on engine=%u\n",
-				id);
+	count = 0;
+	max = U64_MAX;
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+		count++;
+		if (!intel_engine_can_store_dword(ce->engine))
 			continue;
-		}
-		engines[n++] = engine;
-	}
 
+		max = min(max, ce->vm->total);
+		n++;
+	}
+	i915_gem_context_unlock_engines(ctx);
 	if (!n)
 		return 0;
 
@@ -1029,23 +1024,30 @@ static int igt_write_huge(struct i915_gem_context *ctx,
 	 * randomized order, lets also make feeding to the same engine a few
 	 * times in succession a possibility by enlarging the permutation array.
 	 */
-	order = i915_random_order(n * I915_NUM_ENGINES, &prng);
+	order = i915_random_order(count * count, &prng);
 	if (!order)
 		return -ENOMEM;
 
+	max_page_size = rounddown_pow_of_two(obj->mm.page_sizes.sg);
+	max = div_u64(max - size, max_page_size);
+
 	/*
 	 * Try various offsets in an ascending/descending fashion until we
 	 * timeout -- we want to avoid issues hidden by effectively always using
 	 * offset = 0.
 	 */
 	i = 0;
+	engines = i915_gem_context_lock_engines(ctx);
 	for_each_prime_number_from(num, 0, max) {
 		u64 offset_low = num * max_page_size;
 		u64 offset_high = (max - num) * max_page_size;
 		u32 dword = offset_in_page(num) / 4;
+		struct intel_context *ce;
 
-		engine = engines[order[i] % n];
-		i = (i + 1) % (n * I915_NUM_ENGINES);
+		ce = engines->engines[order[i] % engines->num_engines];
+		i = (i + 1) % (count * count);
+		if (!ce || !intel_engine_can_store_dword(ce->engine))
+			continue;
 
 		/*
 		 * In order to utilize 64K pages we need to both pad the vma
@@ -1057,22 +1059,23 @@ static int igt_write_huge(struct i915_gem_context *ctx,
 			offset_low = round_down(offset_low,
 						I915_GTT_PAGE_SIZE_2M);
 
-		err = __igt_write_huge(ctx, engine, obj, size, offset_low,
+		err = __igt_write_huge(ce, obj, size, offset_low,
 				       dword, num + 1);
 		if (err)
 			break;
 
-		err = __igt_write_huge(ctx, engine, obj, size, offset_high,
+		err = __igt_write_huge(ce, obj, size, offset_high,
 				       dword, num + 1);
 		if (err)
 			break;
 
 		if (igt_timeout(end_time,
-				"%s timed out on engine=%u, offset_low=%llx offset_high=%llx, max_page_size=%x\n",
-				__func__, engine->id, offset_low, offset_high,
+				"%s timed out on %s, offset_low=%llx offset_high=%llx, max_page_size=%x\n",
+				__func__, ce->engine->name, offset_low, offset_high,
 				max_page_size))
 			break;
 	}
+	i915_gem_context_unlock_engines(ctx);
 
 	kfree(order);
 
@@ -1316,10 +1319,10 @@ static int igt_ppgtt_pin_update(void *arg)
 	unsigned long supported = INTEL_INFO(dev_priv)->page_sizes;
 	struct i915_address_space *vm = ctx->vm;
 	struct drm_i915_gem_object *obj;
+	struct i915_gem_engines_iter it;
+	struct intel_context *ce;
 	struct i915_vma *vma;
 	unsigned int flags = PIN_USER | PIN_OFFSET_FIXED;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
 	unsigned int n;
 	int first, last;
 	int err;
@@ -1419,14 +1422,18 @@ static int igt_ppgtt_pin_update(void *arg)
 	 */
 
 	n = 0;
-	for_each_engine(engine, dev_priv, id) {
-		if (!intel_engine_can_store_dword(engine))
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+		if (!intel_engine_can_store_dword(ce->engine))
 			continue;
 
-		err = gpu_write(vma, ctx, engine, n++, 0xdeadbeaf);
+		err = gpu_write(ce, vma, n++, 0xdeadbeaf);
 		if (err)
-			goto out_unpin;
+			break;
 	}
+	i915_gem_context_unlock_engines(ctx);
+	if (err)
+		goto out_unpin;
+
 	while (n--) {
 		err = cpu_check(obj, n, 0xdeadbeaf);
 		if (err)
@@ -1507,8 +1514,8 @@ static int igt_shrink_thp(void *arg)
 	struct drm_i915_private *i915 = ctx->i915;
 	struct i915_address_space *vm = ctx->vm ?: &i915->ggtt.vm;
 	struct drm_i915_gem_object *obj;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
+	struct i915_gem_engines_iter it;
+	struct intel_context *ce;
 	struct i915_vma *vma;
 	unsigned int flags = PIN_USER;
 	unsigned int n;
@@ -1548,16 +1555,19 @@ static int igt_shrink_thp(void *arg)
 		goto out_unpin;
 
 	n = 0;
-	for_each_engine(engine, i915, id) {
-		if (!intel_engine_can_store_dword(engine))
+
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+		if (!intel_engine_can_store_dword(ce->engine))
 			continue;
 
-		err = gpu_write(vma, ctx, engine, n++, 0xdeadbeaf);
+		err = gpu_write(ce, vma, n++, 0xdeadbeaf);
 		if (err)
-			goto out_unpin;
+			break;
 	}
-
+	i915_gem_context_unlock_engines(ctx);
 	i915_vma_unpin(vma);
+	if (err)
+		goto out_close;
 
 	/*
 	 * Now that the pages are *unpinned* shrink-all should invoke
@@ -1583,10 +1593,9 @@ static int igt_shrink_thp(void *arg)
 	while (n--) {
 		err = cpu_check(obj, n, 0xdeadbeaf);
 		if (err)
-			goto out_unpin;
+			break;
 	}
 
-
 out_unpin:
 	i915_vma_unpin(vma);
 out_close:
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 3e6f4a65d356..3adb60c2fd1f 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -166,19 +166,17 @@ static unsigned long fake_page_count(struct drm_i915_gem_object *obj)
 	return huge_gem_object_dma_size(obj) >> PAGE_SHIFT;
 }
 
-static int gpu_fill(struct drm_i915_gem_object *obj,
-		    struct i915_gem_context *ctx,
-		    struct intel_engine_cs *engine,
+static int gpu_fill(struct intel_context *ce,
+		    struct drm_i915_gem_object *obj,
 		    unsigned int dw)
 {
-	struct i915_address_space *vm = ctx->vm ?: &engine->gt->ggtt->vm;
 	struct i915_vma *vma;
 	int err;
 
-	GEM_BUG_ON(obj->base.size > vm->total);
-	GEM_BUG_ON(!intel_engine_can_store_dword(engine));
+	GEM_BUG_ON(obj->base.size > ce->vm->total);
+	GEM_BUG_ON(!intel_engine_can_store_dword(ce->engine));
 
-	vma = i915_vma_instance(obj, vm, NULL);
+	vma = i915_vma_instance(obj, ce->vm, NULL);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
@@ -200,9 +198,7 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
 	 * whilst checking that each context provides a unique view
 	 * into the object.
 	 */
-	err = igt_gpu_fill_dw(vma,
-			      ctx,
-			      engine,
+	err = igt_gpu_fill_dw(ce, vma,
 			      (dw * real_page_count(obj)) << PAGE_SHIFT |
 			      (dw * sizeof(u32)),
 			      real_page_count(obj),
@@ -305,22 +301,21 @@ static int file_add_object(struct drm_file *file,
 }
 
 static struct drm_i915_gem_object *
-create_test_object(struct i915_gem_context *ctx,
+create_test_object(struct i915_address_space *vm,
 		   struct drm_file *file,
 		   struct list_head *objects)
 {
 	struct drm_i915_gem_object *obj;
-	struct i915_address_space *vm = ctx->vm ?: &ctx->i915->ggtt.vm;
 	u64 size;
 	int err;
 
 	/* Keep in GEM's good graces */
-	i915_retire_requests(ctx->i915);
+	i915_retire_requests(vm->i915);
 
 	size = min(vm->total / 2, 1024ull * DW_PER_PAGE * PAGE_SIZE);
 	size = round_down(size, DW_PER_PAGE * PAGE_SIZE);
 
-	obj = huge_gem_object(ctx->i915, DW_PER_PAGE * PAGE_SIZE, size);
+	obj = huge_gem_object(vm->i915, DW_PER_PAGE * PAGE_SIZE, size);
 	if (IS_ERR(obj))
 		return obj;
 
@@ -393,6 +388,7 @@ static int igt_ctx_exec(void *arg)
 		dw = 0;
 		while (!time_after(jiffies, end_time)) {
 			struct i915_gem_context *ctx;
+			struct intel_context *ce;
 
 			ctx = live_context(i915, file);
 			if (IS_ERR(ctx)) {
@@ -400,15 +396,20 @@ static int igt_ctx_exec(void *arg)
 				goto out_unlock;
 			}
 
+			ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
+
 			if (!obj) {
-				obj = create_test_object(ctx, file, &objects);
+				obj = create_test_object(ce->vm, file, &objects);
 				if (IS_ERR(obj)) {
 					err = PTR_ERR(obj);
+					intel_context_put(ce);
 					goto out_unlock;
 				}
 			}
 
-			err = gpu_fill(obj, ctx, engine, dw);
+			err = gpu_fill(ce, obj, dw);
+			intel_context_put(ce);
+
 			if (err) {
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
@@ -509,6 +510,7 @@ static int igt_shared_ctx_exec(void *arg)
 		ncontexts = 0;
 		while (!time_after(jiffies, end_time)) {
 			struct i915_gem_context *ctx;
+			struct intel_context *ce;
 
 			ctx = kernel_context(i915);
 			if (IS_ERR(ctx)) {
@@ -518,22 +520,26 @@ static int igt_shared_ctx_exec(void *arg)
 
 			__assign_ppgtt(ctx, parent->vm);
 
+			ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
 			if (!obj) {
-				obj = create_test_object(parent, file, &objects);
+				obj = create_test_object(parent->vm, file, &objects);
 				if (IS_ERR(obj)) {
 					err = PTR_ERR(obj);
+					intel_context_put(ce);
 					kernel_context_close(ctx);
 					goto out_test;
 				}
 			}
 
-			err = gpu_fill(obj, ctx, engine, dw);
+			err = gpu_fill(ce, obj, dw);
+			intel_context_put(ce);
+			kernel_context_close(ctx);
+
 			if (err) {
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
 				       engine->name, ctx->hw_id,
 				       yesno(!!ctx->vm), err);
-				kernel_context_close(ctx);
 				goto out_test;
 			}
 
@@ -544,8 +550,6 @@ static int igt_shared_ctx_exec(void *arg)
 
 			ndwords++;
 			ncontexts++;
-
-			kernel_context_close(ctx);
 		}
 		pr_info("Submitted %lu contexts to %s, filling %lu dwords\n",
 			ncontexts, engine->name, ndwords);
@@ -604,6 +608,8 @@ static struct i915_vma *rpcs_query_batch(struct i915_vma *vma)
 	__i915_gem_object_flush_map(obj, 0, 64);
 	i915_gem_object_unpin_map(obj);
 
+	intel_gt_chipset_flush(vma->vm->gt);
+
 	vma = i915_vma_instance(obj, vma->vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
@@ -1082,17 +1088,19 @@ static int igt_ctx_readonly(void *arg)
 	ndwords = 0;
 	dw = 0;
 	while (!time_after(jiffies, end_time)) {
-		struct intel_engine_cs *engine;
-		unsigned int id;
+		struct i915_gem_engines_iter it;
+		struct intel_context *ce;
 
-		for_each_engine(engine, i915, id) {
-			if (!intel_engine_can_store_dword(engine))
+		for_each_gem_engine(ce,
+				    i915_gem_context_lock_engines(ctx), it) {
+			if (!intel_engine_can_store_dword(ce->engine))
 				continue;
 
 			if (!obj) {
-				obj = create_test_object(ctx, file, &objects);
+				obj = create_test_object(ce->vm, file, &objects);
 				if (IS_ERR(obj)) {
 					err = PTR_ERR(obj);
+					i915_gem_context_unlock_engines(ctx);
 					goto out_unlock;
 				}
 
@@ -1100,12 +1108,13 @@ static int igt_ctx_readonly(void *arg)
 					i915_gem_object_set_readonly(obj);
 			}
 
-			err = gpu_fill(obj, ctx, engine, dw);
+			err = gpu_fill(ce, obj, dw);
 			if (err) {
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
-				       engine->name, ctx->hw_id,
+				       ce->engine->name, ctx->hw_id,
 				       yesno(!!ctx->vm), err);
+				i915_gem_context_unlock_engines(ctx);
 				goto out_unlock;
 			}
 
@@ -1115,6 +1124,7 @@ static int igt_ctx_readonly(void *arg)
 			}
 			ndwords++;
 		}
+		i915_gem_context_unlock_engines(ctx);
 	}
 	pr_info("Submitted %lu dwords (across %u engines)\n",
 		ndwords, RUNTIME_INFO(i915)->num_engines);
@@ -1197,6 +1207,8 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 	__i915_gem_object_flush_map(obj, 0, 64);
 	i915_gem_object_unpin_map(obj);
 
+	intel_gt_chipset_flush(engine->gt);
+
 	vma = i915_vma_instance(obj, ctx->vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
@@ -1296,6 +1308,8 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 	i915_gem_object_flush_map(obj);
 	i915_gem_object_unpin_map(obj);
 
+	intel_gt_chipset_flush(engine->gt);
+
 	vma = i915_vma_instance(obj, ctx->vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
diff --git a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
index 57ece53c1075..ee5dc13a30b3 100644
--- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
+++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
@@ -9,6 +9,7 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_pm.h"
 #include "gt/intel_context.h"
+#include "gt/intel_gt.h"
 #include "i915_vma.h"
 #include "i915_drv.h"
 
@@ -84,6 +85,8 @@ igt_emit_store_dw(struct i915_vma *vma,
 	*cmd = MI_BATCH_BUFFER_END;
 	i915_gem_object_unpin_map(obj);
 
+	intel_gt_chipset_flush(vma->vm->gt);
+
 	vma = i915_vma_instance(obj, vma->vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
@@ -101,40 +104,35 @@ err:
 	return ERR_PTR(err);
 }
 
-int igt_gpu_fill_dw(struct i915_vma *vma,
-		    struct i915_gem_context *ctx,
-		    struct intel_engine_cs *engine,
-		    u64 offset,
-		    unsigned long count,
-		    u32 val)
+int igt_gpu_fill_dw(struct intel_context *ce,
+		    struct i915_vma *vma, u64 offset,
+		    unsigned long count, u32 val)
 {
-	struct i915_address_space *vm = ctx->vm ?: &engine->gt->ggtt->vm;
 	struct i915_request *rq;
 	struct i915_vma *batch;
 	unsigned int flags;
 	int err;
 
-	GEM_BUG_ON(vma->size > vm->total);
-	GEM_BUG_ON(!intel_engine_can_store_dword(engine));
+	GEM_BUG_ON(!intel_engine_can_store_dword(ce->engine));
 	GEM_BUG_ON(!i915_vma_is_pinned(vma));
 
 	batch = igt_emit_store_dw(vma, offset, count, val);
 	if (IS_ERR(batch))
 		return PTR_ERR(batch);
 
-	rq = igt_request_alloc(ctx, engine);
+	rq = intel_context_create_request(ce);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_batch;
 	}
 
 	flags = 0;
-	if (INTEL_GEN(vm->i915) <= 5)
+	if (INTEL_GEN(ce->vm->i915) <= 5)
 		flags |= I915_DISPATCH_SECURE;
 
-	err = engine->emit_bb_start(rq,
-				    batch->node.start, batch->node.size,
-				    flags);
+	err = rq->engine->emit_bb_start(rq,
+					batch->node.start, batch->node.size,
+					flags);
 	if (err)
 		goto err_request;
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h
index 361a7ef866b0..4221cf84d175 100644
--- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h
+++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.h
@@ -11,9 +11,11 @@
 
 struct i915_request;
 struct i915_gem_context;
-struct intel_engine_cs;
 struct i915_vma;
 
+struct intel_context;
+struct intel_engine_cs;
+
 struct i915_request *
 igt_request_alloc(struct i915_gem_context *ctx, struct intel_engine_cs *engine);
 
@@ -23,11 +25,8 @@ igt_emit_store_dw(struct i915_vma *vma,
 		  unsigned long count,
 		  u32 val);
 
-int igt_gpu_fill_dw(struct i915_vma *vma,
-		    struct i915_gem_context *ctx,
-		    struct intel_engine_cs *engine,
-		    u64 offset,
-		    unsigned long count,
-		    u32 val);
+int igt_gpu_fill_dw(struct intel_context *ce,
+		    struct i915_vma *vma, u64 offset,
+		    unsigned long count, u32 val);
 
 #endif /* __IGT_GEM_UTILS_H__ */
-- 
cgit v1.2.3


From 52988009843160c5b366b4082ed6df48041c655c Mon Sep 17 00:00:00 2001
From: Xiaolin Zhang <xiaolin.zhang@intel.com>
Date: Fri, 23 Aug 2019 14:57:31 +0800
Subject: drm/i915: to make vgpu ppgtt notificaiton as atomic operation

vgpu ppgtt notification was split into 2 steps, the first step is to
update PVINFO's pdp register and then write PVINFO's g2v_notify register
with action code to tirgger ppgtt notification to GVT side.

currently these steps were not atomic operations due to no any protection,
so it is easy to enter race condition state during the MTBF, stress and
IGT test to cause GPU hang.

the solution is to add a lock to make vgpu ppgtt notication as atomic
operation.

Cc: stable@vger.kernel.org
Signed-off-by: Xiaolin Zhang <xiaolin.zhang@intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/1566543451-13955-1-git-send-email-xiaolin.zhang@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h     |  1 +
 drivers/gpu/drm/i915/i915_gem_gtt.c | 12 +++++++-----
 drivers/gpu/drm/i915/i915_vgpu.c    |  1 +
 3 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f5e39a3bfff6..b42651a387d9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -966,6 +966,7 @@ struct i915_frontbuffer_tracking {
 };
 
 struct i915_virtual_gpu {
+	struct mutex lock; /* serialises sending of g2v_notify command pkts */
 	bool active;
 	u32 caps;
 };
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index e0e9b9b52544..0db82921fb38 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -834,10 +834,9 @@ static void mark_tlbs_dirty(struct i915_ppgtt *ppgtt)
 	ppgtt->pd_dirty_engines = ALL_ENGINES;
 }
 
-static int gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
+static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
 {
-	struct i915_address_space *vm = &ppgtt->vm;
-	struct drm_i915_private *dev_priv = vm->i915;
+	struct drm_i915_private *dev_priv = ppgtt->vm.i915;
 	enum vgt_g2v_type msg;
 	int i;
 
@@ -846,7 +845,9 @@ static int gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
 	else
 		atomic_dec(px_used(ppgtt->pd));
 
-	if (i915_vm_is_4lvl(vm)) {
+	mutex_lock(&dev_priv->vgpu.lock);
+
+	if (i915_vm_is_4lvl(&ppgtt->vm)) {
 		const u64 daddr = px_dma(ppgtt->pd);
 
 		I915_WRITE(vgtif_reg(pdp[0].lo), lower_32_bits(daddr));
@@ -866,9 +867,10 @@ static int gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
 				VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY);
 	}
 
+	/* g2v_notify atomically (via hv trap) consumes the message packet. */
 	I915_WRITE(vgtif_reg(g2v_notify), msg);
 
-	return 0;
+	mutex_unlock(&dev_priv->vgpu.lock);
 }
 
 /* Index shifts into the pagetable are offset by GEN8_PTE_SHIFT [12] */
diff --git a/drivers/gpu/drm/i915/i915_vgpu.c b/drivers/gpu/drm/i915/i915_vgpu.c
index 39bebf16edbe..968be26735c5 100644
--- a/drivers/gpu/drm/i915/i915_vgpu.c
+++ b/drivers/gpu/drm/i915/i915_vgpu.c
@@ -94,6 +94,7 @@ void i915_detect_vgpu(struct drm_i915_private *dev_priv)
 	dev_priv->vgpu.caps = readl(shared_area + vgtif_offset(vgt_caps));
 
 	dev_priv->vgpu.active = true;
+	mutex_init(&dev_priv->vgpu.lock);
 	DRM_INFO("Virtual GPU for Intel GVT-g detected.\n");
 
 out:
-- 
cgit v1.2.3


From acd674af95d3f627062007429b9c195c6b32361d Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Fri, 23 Aug 2019 16:52:51 -0400
Subject: drm/i915: Call dma_set_max_seg_size() in i915_driver_hw_probe()

Currently, we don't call dma_set_max_seg_size() for i915 because we
intentionally do not limit the segment length that the device supports.
However, this results in a warning being emitted if we try to map
anything larger than SZ_64K on a kernel with CONFIG_DMA_API_DEBUG_SG
enabled:

[    7.751926] DMA-API: i915 0000:00:02.0: mapping sg segment longer
than device claims to support [len=98304] [max=65536]
[    7.751934] WARNING: CPU: 5 PID: 474 at kernel/dma/debug.c:1220
debug_dma_map_sg+0x20f/0x340

This was originally brought up on
https://bugs.freedesktop.org/show_bug.cgi?id=108517 , and the consensus
there was it wasn't really useful to set a limit (and that dma-debug
isn't really all that useful for i915 in the first place). Unfortunately
though, CONFIG_DMA_API_DEBUG_SG is enabled in the debug configs for
various distro kernels. Since a WARN_ON() will disable automatic problem
reporting (and cause any CI with said option enabled to start
complaining), we really should just fix the problem.

Note that as me and Chris Wilson discussed, the other solution for this
would be to make DMA-API not make such assumptions when a driver hasn't
explicitly set a maximum segment size. But, taking a look at the commit
which originally introduced this behavior, commit 78c47830a5cb
("dma-debug: check scatterlist segments"), there is an explicit mention
of this assumption and how it applies to devices with no segment size:

	Conversely, devices which are less limited than the rather
	conservative defaults, or indeed have no limitations at all
	(e.g. GPUs with their own internal MMU), should be encouraged to
	set appropriate dma_parms, as they may get more efficient DMA
	mapping performance out of it.

So unless there's any concerns (I'm open to discussion!), let's just
follow suite and call dma_set_max_seg_size() with UINT_MAX as our limit
to silence any warnings.

Changes since v3:
* Drop patch for enabling CONFIG_DMA_API_DEBUG_SG in CI. It looks like
  just turning it on causes the kernel to spit out bogus WARN_ONs()
  during some igt tests which would otherwise require teaching igt to
  disable the various DMA-API debugging options causing this. This is
  too much work to be worth it, since DMA-API debugging is useless for
  us. So, we'll just settle with this single patch to squelch WARN_ONs()
  during driver load for users that have CONFIG_DMA_API_DEBUG_SG turned
  on for some reason.
* Move dma_set_max_seg_size() call into i915_driver_hw_probe() - Chris
  Wilson

Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: <stable@vger.kernel.org> # v4.18+
Link: https://patchwork.freedesktop.org/patch/msgid/20190823205251.14298-1-lyude@redhat.com
---
 drivers/gpu/drm/i915/i915_drv.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 723b9b7202b0..9478f704a315 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1279,6 +1279,12 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 
 	pci_set_master(pdev);
 
+	/*
+	 * We don't have a max segment size, so set it to the max so sg's
+	 * debugging layer doesn't complain
+	 */
+	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
+
 	/* overlay on gen2 is broken and can't address above 1G */
 	if (IS_GEN(dev_priv, 2)) {
 		ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(30));
-- 
cgit v1.2.3


From 1d5b7773314994d23f2fc4acfa4278929b03ffd5 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 26 Aug 2019 08:21:22 +0100
Subject: drm/i915/selftests: Add the usual batch vma managements to
 st_workarounds

To properly handle asynchronous migration of batch objects, we need to
couple the fences on the incoming batch into the request and should not
assume that they always start idle.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190826072149.9447-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/selftest_workarounds.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index d06d68ac2a3b..999a98f00494 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -565,6 +565,14 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 				goto err_request;
 		}
 
+		i915_vma_lock(batch);
+		err = i915_request_await_object(rq, batch->obj, false);
+		if (err == 0)
+			err = i915_vma_move_to_active(batch, rq, 0);
+		i915_vma_unlock(batch);
+		if (err)
+			goto err_request;
+
 		err = engine->emit_bb_start(rq,
 					    batch->node.start, PAGE_SIZE,
 					    0);
@@ -850,6 +858,14 @@ static int scrub_whitelisted_registers(struct i915_gem_context *ctx,
 			goto err_request;
 	}
 
+	i915_vma_lock(batch);
+	err = i915_request_await_object(rq, batch->obj, false);
+	if (err == 0)
+		err = i915_vma_move_to_active(batch, rq, 0);
+	i915_vma_unlock(batch);
+	if (err)
+		goto err_request;
+
 	/* Perform the writes from an unprivileged "user" batch */
 	err = engine->emit_bb_start(rq, batch->node.start, 0, 0);
 
-- 
cgit v1.2.3


From ebfdf5cd806b3bbf1ff79e69bce6a28df8bbe39d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 26 Aug 2019 14:07:50 +0100
Subject: drm/i915: Use NOEVICT for first pass on attemping to pin a GGTT mmap

The intention is that we first try to pin the current vma into the
mappable aperture only if it is already in use or it fits in the free
space and will not cause contention. The first attempt was meant to be
using PIN_NOEVICT to reuse the current vma if possible, following up
with different eviction strategies.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111485
Fixes: 6846895fde05 ("drm/i915: Replace PIN_NONFAULT with calls to PIN_NOEVICT")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190826130750.17272-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_mman.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 595539a09e38..261c9bd83f51 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -265,7 +265,7 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
 				       PIN_MAPPABLE |
 				       PIN_NONBLOCK /* NOWARN */ |
-				       PIN_NOSEARCH);
+				       PIN_NOEVICT);
 	if (IS_ERR(vma)) {
 		/* Use a partial view if it is bigger than available space */
 		struct i915_ggtt_view view =
-- 
cgit v1.2.3


From 21b0c32bdaba7c2e365d9faca0536fc40dd056d4 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 27 Aug 2019 10:49:33 +0100
Subject: drm/i915/selftests: Markup impossible error pointers

If we create a new live_context() we should have a mapping for each
engine. Document that assumption with an assertion.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190827094933.13778-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 3adb60c2fd1f..37a177e37665 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -397,6 +397,7 @@ static int igt_ctx_exec(void *arg)
 			}
 
 			ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
+			GEM_BUG_ON(IS_ERR(ce));
 
 			if (!obj) {
 				obj = create_test_object(ce->vm, file, &objects);
@@ -521,6 +522,8 @@ static int igt_shared_ctx_exec(void *arg)
 			__assign_ppgtt(ctx, parent->vm);
 
 			ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
+			GEM_BUG_ON(IS_ERR(ce));
+
 			if (!obj) {
 				obj = create_test_object(parent->vm, file, &objects);
 				if (IS_ERR(obj)) {
-- 
cgit v1.2.3


From f52c6d0df6909a0412c347c8e442acc22ce94747 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 27 Aug 2019 14:26:31 +0100
Subject: drm/i915: Only activate i915_active debugobject once

The point of debug_object_activate is to mark the first, and only the
first, acquisition. The object then remains active until the last
release.  However, we marked up all successful first acquires even though
we allowed concurrent parties to try and acquire the i915_active
simultaneously (serialised by the i915_active.mutex).

Testcase: igt/gem_mmap_gtt/fault-concurrent
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190827132631.18627-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_active.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 48e16ad93bbd..6a447f1d0110 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -92,12 +92,16 @@ static void debug_active_init(struct i915_active *ref)
 
 static void debug_active_activate(struct i915_active *ref)
 {
-	debug_object_activate(ref, &active_debug_desc);
+	lockdep_assert_held(&ref->mutex);
+	if (!atomic_read(&ref->count)) /* before the first inc */
+		debug_object_activate(ref, &active_debug_desc);
 }
 
 static void debug_active_deactivate(struct i915_active *ref)
 {
-	debug_object_deactivate(ref, &active_debug_desc);
+	lockdep_assert_held(&ref->mutex);
+	if (!atomic_read(&ref->count)) /* after the last dec */
+		debug_object_deactivate(ref, &active_debug_desc);
 }
 
 static void debug_active_fini(struct i915_active *ref)
-- 
cgit v1.2.3


From cccdce1dd061c0b8ae156f026a3ee2c9d58613d3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 27 Aug 2019 14:59:35 +0100
Subject: drm/i915: Make engine's batch pool safe for use with virtual engines

A virtual engine itself does not have a batch pool, but we can gleefully
use any of its siblings instead.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190827135935.3831-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c |  4 ++--
 drivers/gpu/drm/i915/gem/i915_gem_object_blt.c |  4 ++--
 drivers/gpu/drm/i915/gt/intel_engine_pool.c    | 12 +++++++++++-
 drivers/gpu/drm/i915/gt/intel_engine_pool.h    |  2 +-
 drivers/gpu/drm/i915/gt/intel_lrc.c            | 12 ++++++++++++
 drivers/gpu/drm/i915/gt/intel_lrc.h            |  4 ++++
 6 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index f813fcb8ceb6..5a2238d44423 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -1145,7 +1145,7 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	u32 *cmd;
 	int err;
 
-	pool = intel_engine_pool_get(&eb->engine->pool, PAGE_SIZE);
+	pool = intel_engine_get_pool(eb->engine, PAGE_SIZE);
 	if (IS_ERR(pool))
 		return PTR_ERR(pool);
 
@@ -1963,7 +1963,7 @@ static struct i915_vma *eb_parse(struct i915_execbuffer *eb, bool is_master)
 	struct i915_vma *vma;
 	int err;
 
-	pool = intel_engine_pool_get(&eb->engine->pool, eb->batch_len);
+	pool = intel_engine_get_pool(eb->engine, eb->batch_len);
 	if (IS_ERR(pool))
 		return ERR_CAST(pool);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
index 6415f9a17e2d..5bd8de124d74 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
@@ -32,7 +32,7 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 	count = div_u64(vma->size, block_size);
 	size = (1 + 8 * count) * sizeof(u32);
 	size = round_up(size, PAGE_SIZE);
-	pool = intel_engine_pool_get(&ce->engine->pool, size);
+	pool = intel_engine_get_pool(ce->engine, size);
 	if (IS_ERR(pool)) {
 		err = PTR_ERR(pool);
 		goto out_pm;
@@ -216,7 +216,7 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
 	count = div_u64(dst->size, block_size);
 	size = (1 + 11 * count) * sizeof(u32);
 	size = round_up(size, PAGE_SIZE);
-	pool = intel_engine_pool_get(&ce->engine->pool, size);
+	pool = intel_engine_get_pool(ce->engine, size);
 	if (IS_ERR(pool)) {
 		err = PTR_ERR(pool);
 		goto out_pm;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pool.c b/drivers/gpu/drm/i915/gt/intel_engine_pool.c
index 4cd54c569911..97d36cca8ded 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pool.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pool.c
@@ -107,9 +107,19 @@ node_create(struct intel_engine_pool *pool, size_t sz)
 	return node;
 }
 
+static struct intel_engine_pool *lookup_pool(struct intel_engine_cs *engine)
+{
+	if (intel_engine_is_virtual(engine))
+		engine = intel_virtual_engine_get_sibling(engine, 0);
+
+	GEM_BUG_ON(!engine);
+	return &engine->pool;
+}
+
 struct intel_engine_pool_node *
-intel_engine_pool_get(struct intel_engine_pool *pool, size_t size)
+intel_engine_get_pool(struct intel_engine_cs *engine, size_t size)
 {
+	struct intel_engine_pool *pool = lookup_pool(engine);
 	struct intel_engine_pool_node *node;
 	struct list_head *list;
 	unsigned long flags;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pool.h b/drivers/gpu/drm/i915/gt/intel_engine_pool.h
index 8d069efd9457..7e2123b33594 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pool.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pool.h
@@ -12,7 +12,7 @@
 #include "i915_request.h"
 
 struct intel_engine_pool_node *
-intel_engine_pool_get(struct intel_engine_pool *pool, size_t size);
+intel_engine_get_pool(struct intel_engine_cs *engine, size_t size);
 
 static inline int
 intel_engine_pool_mark_active(struct intel_engine_pool_node *node,
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index d42584439f51..cfbdcca76ff0 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -3851,6 +3851,18 @@ int intel_virtual_engine_attach_bond(struct intel_engine_cs *engine,
 	return 0;
 }
 
+struct intel_engine_cs *
+intel_virtual_engine_get_sibling(struct intel_engine_cs *engine,
+				 unsigned int sibling)
+{
+	struct virtual_engine *ve = to_virtual_engine(engine);
+
+	if (sibling >= ve->num_siblings)
+		return NULL;
+
+	return ve->siblings[sibling];
+}
+
 void intel_execlists_show_requests(struct intel_engine_cs *engine,
 				   struct drm_printer *m,
 				   void (*show_request)(struct drm_printer *m,
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index c2bba82bcc16..dc0252e0589e 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -131,4 +131,8 @@ int intel_virtual_engine_attach_bond(struct intel_engine_cs *engine,
 				     const struct intel_engine_cs *master,
 				     const struct intel_engine_cs *sibling);
 
+struct intel_engine_cs *
+intel_virtual_engine_get_sibling(struct intel_engine_cs *engine,
+				 unsigned int sibling);
+
 #endif /* _INTEL_LRC_H_ */
-- 
cgit v1.2.3


From 6056517ab8c30fb239b08c06ef577677cbcd409c Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Fri, 23 Aug 2019 01:20:37 -0700
Subject: drm/i915/tgl: Guard and warn if more than one eDP panel is present
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On TGL+ it's possible to have PSR1 enabled in other ports besides DDIA.
PSR2 is still limited to DDIA. However currently we handle only one
instance of PSR struct. Lets guard intel_psr_init_dpcd() against
multiple eDP panels and warn about it.

v2: Reword commit message to be TGL+ only and with the info where
PSR1/PSR2 are supported (Lucas)

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Anshuman Gupta <anshuman.gupta@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823082055.5992-6-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 28b62e587204..78e920015a00 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -283,6 +283,11 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 	struct drm_i915_private *dev_priv =
 		to_i915(dp_to_dig_port(intel_dp)->base.base.dev);
 
+	if (dev_priv->psr.dp) {
+		DRM_WARN("More than one eDP panel found, PSR support should be extended\n");
+		return;
+	}
+
 	drm_dp_dpcd_read(&intel_dp->aux, DP_PSR_SUPPORT, intel_dp->psr_dpcd,
 			 sizeof(intel_dp->psr_dpcd));
 
@@ -305,7 +310,6 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 	dev_priv->psr.sink_sync_latency =
 		intel_dp_get_sink_sync_latency(intel_dp);
 
-	WARN_ON(dev_priv->psr.dp);
 	dev_priv->psr.dp = intel_dp;
 
 	if (INTEL_GEN(dev_priv) >= 9 &&
-- 
cgit v1.2.3


From 0f81e645eb1ed224af43bb7b347806cc74d189f6 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Sat, 17 Aug 2019 02:38:33 -0700
Subject: drm/i915: Do not read PSR2 register in transcoders without PSR2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fix unclaimed access warnings:

[  245.525788] ------------[ cut here ]------------
[  245.525884] Unclaimed read from register 0x62900
[  245.526154] WARNING: CPU: 0 PID: 1234 at drivers/gpu/drm/i915/intel_uncore.c:1100 __unclaimed_reg_debug+0x40/0x50 [i915]
[  245.526160] Modules linked in: i915 x86_pkg_temp_thermal ax88179_178a coretemp usbnet crct10dif_pclmul mii crc32_pclmul ghash_clmulni_intel e1000e [last unloaded: i915]
[  245.526191] CPU: 0 PID: 1234 Comm: kms_fullmodeset Not tainted 5.1.0-rc6+ #915
[  245.526197] Hardware name: Intel Corporation Tiger Lake Client Platform/TigerLake U DDR4 SODIMM RVP, BIOS TGLSFWR1.D00.2081.A10.1904182155 04/18/2019
[  245.526273] RIP: 0010:__unclaimed_reg_debug+0x40/0x50 [i915]
[  245.526281] Code: 74 05 5b 5d 41 5c c3 45 84 e4 48 c7 c0 76 97 21 a0 48 c7 c6 6c 97 21 a0 89 ea 48 0f 44 f0 48 c7 c7 7f 97 21 a0 e8 4f 1e fe e0 <0f> 0b 83 2d 6f d9 1c 00 01 5b 5d 41 5c c3 66 90 41 57 41 56 41 55
[  245.526288] RSP: 0018:ffffc900006bf7d8 EFLAGS: 00010086
[  245.526297] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
[  245.526304] RDX: 0000000000000007 RSI: 0000000000000000 RDI: 00000000ffffffff
[  245.526310] RBP: 0000000000061900 R08: 0000000000000000 R09: 0000000000000001
[  245.526317] R10: 0000000000000006 R11: 0000000000000000 R12: 0000000000000001
[  245.526324] R13: 0000000000000000 R14: ffff8882914f0d58 R15: 0000000000000206
[  245.526332] FS:  00007fed2a3c39c0(0000) GS:ffff8882a8600000(0000) knlGS:0000000000000000
[  245.526340] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  245.526347] CR2: 00007fed28dff000 CR3: 00000002a086c006 CR4: 0000000000760ef0
[  245.526354] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  245.526361] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  245.526367] PKRU: 55555554
[  245.526373] Call Trace:
[  245.526454]  gen11_fwtable_read32+0x219/0x250 [i915]
[  245.526576]  intel_psr_activate+0x57/0x400 [i915]
[  245.526697]  intel_psr_enable_locked+0x367/0x4b0 [i915]
[  245.526828]  intel_psr_enable+0xa4/0xd0 [i915]
[  245.526946]  intel_enable_ddi+0x127/0x2f0 [i915]
[  245.527075]  intel_encoders_enable.isra.79+0x62/0x90 [i915]
[  245.527202]  haswell_crtc_enable+0x2a2/0x850 [i915]
[  245.527337]  intel_update_crtc+0x51/0x360 [i915]
[  245.527466]  skl_update_crtcs+0x26c/0x300 [i915]
[  245.527603]  intel_atomic_commit_tail+0x3e5/0x13c0 [i915]
[  245.527757]  intel_atomic_commit+0x24d/0x2d0 [i915]
[  245.527782]  drm_atomic_helper_set_config+0x7b/0x90
[  245.527799]  drm_mode_setcrtc+0x1b4/0x6f0
[  245.527856]  ? drm_mode_getcrtc+0x180/0x180
[  245.527867]  drm_ioctl_kernel+0xad/0xf0
[  245.527886]  drm_ioctl+0x2f4/0x3b0
[  245.527902]  ? drm_mode_getcrtc+0x180/0x180
[  245.527935]  ? rcu_read_lock_sched_held+0x6f/0x80
[  245.527956]  do_vfs_ioctl+0xa0/0x6d0
[  245.527970]  ? __task_pid_nr_ns+0xb6/0x200
[  245.527991]  ksys_ioctl+0x35/0x70
[  245.528009]  __x64_sys_ioctl+0x11/0x20
[  245.528020]  do_syscall_64+0x55/0x180
[  245.528034]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  245.528042] RIP: 0033:0x7fed2cc7c3c7
[  245.528050] Code: 00 00 90 48 8b 05 c9 3a 0d 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 99 3a 0d 00 f7 d8 64 89 01 48
[  245.528057] RSP: 002b:00007ffe36944378 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[  245.528067] RAX: ffffffffffffffda RBX: 00007ffe369443b0 RCX: 00007fed2cc7c3c7
[  245.528074] RDX: 00007ffe369443b0 RSI: 00000000c06864a2 RDI: 0000000000000003
[  245.528081] RBP: 00007ffe369443b0 R08: 0000000000000000 R09: 0000564c0173ae98
[  245.528088] R10: 0000564c0173aeb8 R11: 0000000000000246 R12: 00000000c06864a2
[  245.528095] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000000
[  245.528128] irq event stamp: 140866
[  245.528138] hardirqs last  enabled at (140865): [<ffffffff819a63dc>] _raw_spin_unlock_irqrestore+0x4c/0x60
[  245.528148] hardirqs last disabled at (140866): [<ffffffff819a624d>] _raw_spin_lock_irqsave+0xd/0x50
[  245.528158] softirqs last  enabled at (140860): [<ffffffff81c0038c>] __do_softirq+0x38c/0x499
[  245.528170] softirqs last disabled at (140853): [<ffffffff810b4a09>] irq_exit+0xa9/0xc0
[  245.528247] WARNING: CPU: 0 PID: 1234 at drivers/gpu/drm/i915/intel_uncore.c:1100 __unclaimed_reg_debug+0x40/0x50 [i915]
[  245.528254] ---[ end trace 366069676e98a410 ]---

Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823082055.5992-7-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 78e920015a00..dafd3737cc5a 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -541,7 +541,9 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 static bool
 transcoder_has_psr2(struct drm_i915_private *dev_priv, enum transcoder trans)
 {
-	if (INTEL_GEN(dev_priv) >= 12)
+	if (INTEL_GEN(dev_priv) < 9)
+		return false;
+	else if (INTEL_GEN(dev_priv) >= 12)
 		return trans == TRANSCODER_A;
 	else
 		return trans == TRANSCODER_EDP;
@@ -667,8 +669,9 @@ static void intel_psr_activate(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 
-	if (INTEL_GEN(dev_priv) >= 9)
+	if (transcoder_has_psr2(dev_priv, dev_priv->psr.transcoder))
 		WARN_ON(I915_READ(EDP_PSR2_CTL(dev_priv->psr.transcoder)) & EDP_PSR2_ENABLE);
+
 	WARN_ON(I915_READ(EDP_PSR_CTL(dev_priv->psr.transcoder)) & EDP_PSR_ENABLE);
 	WARN_ON(dev_priv->psr.active);
 	lockdep_assert_held(&dev_priv->psr.lock);
@@ -821,7 +824,7 @@ static void intel_psr_exit(struct drm_i915_private *dev_priv)
 	u32 val;
 
 	if (!dev_priv->psr.active) {
-		if (INTEL_GEN(dev_priv) >= 9) {
+		if (transcoder_has_psr2(dev_priv, dev_priv->psr.transcoder)) {
 			val = I915_READ(EDP_PSR2_CTL(dev_priv->psr.transcoder));
 			WARN_ON(val & EDP_PSR2_ENABLE);
 		}
-- 
cgit v1.2.3


From f7b3c22619a44ce7599fc9fa1df5df6281a26217 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Fri, 23 Aug 2019 01:20:41 -0700
Subject: drm/i915/tgl: Add maximum resolution supported by PSR2 HW
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

TGL PSR2 HW supports a bigger resolution, so lets add it

BSpec: 50422, 49199
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Anshuman Gupta <anshuman.gupta@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823082055.5992-10-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index dafd3737cc5a..2af3826121fa 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -576,7 +576,10 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 		return false;
 	}
 
-	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 12) {
+		psr_max_h = 5120;
+		psr_max_v = 3200;
+	} else if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
 		psr_max_h = 4096;
 		psr_max_v = 2304;
 	} else if (IS_GEN(dev_priv, 9)) {
-- 
cgit v1.2.3


From 0456417ef680aab9a2aa93b950443e25104101b9 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Fri, 23 Aug 2019 01:20:43 -0700
Subject: drm: Add for_each_oldnew_intel_crtc_in_state_reverse()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Same as for_each_oldnew_intel_crtc_in_state() but iterates in reverse
order.

v2: Fix additional blank line
v3: Rebase

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823082055.5992-12-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index e57e6969051d..03321fb4a703 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -411,6 +411,15 @@ enum phy_fia {
 	     (__i)++) \
 		for_each_if(crtc)
 
+#define for_each_oldnew_intel_crtc_in_state_reverse(__state, crtc, old_crtc_state, new_crtc_state, __i) \
+	for ((__i) = (__state)->base.dev->mode_config.num_crtc - 1; \
+	     (__i) >= 0  && \
+	     ((crtc) = to_intel_crtc((__state)->base.crtcs[__i].ptr), \
+	      (old_crtc_state) = to_intel_crtc_state((__state)->base.crtcs[__i].old_state), \
+	      (new_crtc_state) = to_intel_crtc_state((__state)->base.crtcs[__i].new_state), 1); \
+	     (__i)--) \
+		for_each_if(crtc)
+
 void intel_link_compute_m_n(u16 bpp, int nlanes,
 			    int pixel_clock, int link_clock,
 			    struct intel_link_m_n *m_n,
-- 
cgit v1.2.3


From 9c722e17c1b91d7dc5ec77cb4fcaaa6b30653fe3 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Fri, 23 Aug 2019 01:20:44 -0700
Subject: drm/i915: Disable pipes in reverse order
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Disable CRTC/pipes in reverse order because some features (MST in
TGL+) requires master and slave relationship between pipes, so it
should always pick the lowest pipe as master as it will be enabled
first and disable in the reverse order so the master will be the last
one to be disabled.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823082055.5992-13-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index ea2915dde6ab..a9f8be2cd364 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -13908,7 +13908,15 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	if (state->modeset)
 		wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_MODESET);
 
-	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+	/*
+	 * Disable CRTC/pipes in reverse order because some features(MST in
+	 * TGL+) requires master and slave relationship between pipes, so it
+	 * should always pick the lowest pipe as master as it will be enabled
+	 * first and disable in the reverse order so the master will be the
+	 * last one to be disabled.
+	 */
+	for_each_oldnew_intel_crtc_in_state_reverse(state, crtc, old_crtc_state,
+						    new_crtc_state, i) {
 		if (needs_modeset(new_crtc_state) ||
 		    new_crtc_state->update_pipe) {
 
-- 
cgit v1.2.3


From 99389390fef50c880d2ca0b6667c12423b3d5260 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Fri, 23 Aug 2019 01:20:47 -0700
Subject: drm/i915/tgl: Implement TGL DisplayPort training sequence
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On TGL some registers moved from DDI to transcoder and the
DisplayPort training sequence has a separate BSpec page.

I started adding 'ifs' to the original intel_ddi_pre_enable_dp() but
it was becoming really hard to follow, so a new and cleaner function
for TGL was added with comments of all steps. It's similar to ICL,
but different enough to deserve a new function.

The rest of DisplayPort enable and the whole disable sequences
remained the same.

v2: FEC and DSC should be enabled on sink side before start link
training(Maarten reported and Manasi confirmed the DSC part)

v3: Add call to enable FEC on step 7.l(Manasi)

BSpec: 49190
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823082055.5992-16-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 140 ++++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/display/intel_dp.c  |   8 +-
 2 files changed, 140 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 8eb2b3ec01ed..3180dacb5be4 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -1761,7 +1761,14 @@ void intel_ddi_set_vc_payload_alloc(const struct intel_crtc_state *crtc_state,
 	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
 }
 
-void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
+/*
+ * Returns the TRANS_DDI_FUNC_CTL value based on CRTC state.
+ *
+ * Only intended to be used by intel_ddi_enable_transcoder_func() and
+ * intel_ddi_config_transcoder_func().
+ */
+static u32
+intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct intel_encoder *encoder = intel_ddi_get_crtc_encoder(crtc);
@@ -1845,6 +1852,34 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
 		temp |= DDI_PORT_WIDTH(crtc_state->lane_count);
 	}
 
+	return temp;
+}
+
+void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
+	u32 temp;
+
+	temp = intel_ddi_transcoder_func_reg_val_get(crtc_state);
+	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
+}
+
+/*
+ * Same as intel_ddi_enable_transcoder_func(), but it does not set the enable
+ * bit.
+ */
+static void
+intel_ddi_config_transcoder_func(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
+	u32 temp;
+
+	temp = intel_ddi_transcoder_func_reg_val_get(crtc_state);
+	temp &= ~TRANS_DDI_FUNC_ENABLE;
 	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
 }
 
@@ -3160,9 +3195,94 @@ static void intel_ddi_disable_fec_state(struct intel_encoder *encoder,
 	POSTING_READ(DP_TP_CTL(port));
 }
 
-static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
-				    const struct intel_crtc_state *crtc_state,
-				    const struct drm_connector_state *conn_state)
+static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
+				  const struct intel_crtc_state *crtc_state,
+				  const struct drm_connector_state *conn_state)
+{
+	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
+	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
+	bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
+	int level = intel_ddi_dp_level(intel_dp);
+
+	intel_dp_set_link_params(intel_dp, crtc_state->port_clock,
+				 crtc_state->lane_count, is_mst);
+
+	/* 1.a got on intel_atomic_commit_tail() */
+
+	/* 2. */
+	intel_edp_panel_on(intel_dp);
+
+	/*
+	 * 1.b, 3. and 4. is done before tgl_ddi_pre_enable_dp() by:
+	 * haswell_crtc_enable()->intel_encoders_pre_pll_enable() and
+	 * haswell_crtc_enable()->intel_enable_shared_dpll()
+	 */
+
+	/* 5. */
+	if (!intel_phy_is_tc(dev_priv, phy) ||
+	    dig_port->tc_mode != TC_PORT_TBT_ALT)
+		intel_display_power_get(dev_priv,
+					dig_port->ddi_io_power_domain);
+
+	/* 6. */
+	icl_program_mg_dp_mode(dig_port);
+
+	/*
+	 * 7.a - Steps in this function should only be executed over MST
+	 * master, what will be taken in care by MST hook
+	 * intel_mst_pre_enable_dp()
+	 */
+	intel_ddi_enable_pipe_clock(crtc_state);
+
+	/* 7.b */
+	intel_ddi_config_transcoder_func(crtc_state);
+
+	/* 7.d */
+	icl_disable_phy_clock_gating(dig_port);
+
+	/* 7.e */
+	icl_ddi_vswing_sequence(encoder, crtc_state->port_clock, level,
+				encoder->type);
+
+	/* 7.f */
+	if (intel_phy_is_combo(dev_priv, phy)) {
+		bool lane_reversal =
+			dig_port->saved_port_bits & DDI_BUF_PORT_REVERSAL;
+
+		intel_combo_phy_power_up_lanes(dev_priv, phy, false,
+					       crtc_state->lane_count,
+					       lane_reversal);
+	}
+
+	/* 7.g */
+	intel_ddi_init_dp_buf_reg(encoder);
+
+	if (!is_mst)
+		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
+
+	intel_dp_sink_set_decompression_state(intel_dp, crtc_state, true);
+	/*
+	 * DDI FEC: "anticipates enabling FEC encoding sets the FEC_READY bit
+	 * in the FEC_CONFIGURATION register to 1 before initiating link
+	 * training
+	 */
+	intel_dp_sink_set_fec_ready(intel_dp, crtc_state);
+	/* 7.c, 7.h, 7.i, 7.j */
+	intel_dp_start_link_train(intel_dp);
+
+	/* 7.k */
+	intel_dp_stop_link_train(intel_dp);
+
+	/* 7.l */
+	intel_ddi_enable_fec(encoder, crtc_state);
+	intel_dsc_enable(encoder, crtc_state);
+}
+
+static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
+				  const struct intel_crtc_state *crtc_state,
+				  const struct drm_connector_state *conn_state)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
@@ -3228,6 +3348,18 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	intel_dsc_enable(encoder, crtc_state);
 }
 
+static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
+				    const struct intel_crtc_state *crtc_state,
+				    const struct drm_connector_state *conn_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (INTEL_GEN(dev_priv) >= 12)
+		tgl_ddi_pre_enable_dp(encoder, crtc_state, conn_state);
+	else
+		hsw_ddi_pre_enable_dp(encoder, crtc_state, conn_state);
+}
+
 static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 				      const struct intel_crtc_state *crtc_state,
 				      const struct drm_connector_state *conn_state)
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 23908da1cd5d..f74594d8d9df 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -3954,13 +3954,13 @@ void intel_dp_set_idle_link_train(struct intel_dp *intel_dp)
 	I915_WRITE(DP_TP_CTL(port), val);
 
 	/*
-	 * On PORT_A we can have only eDP in SST mode. There the only reason
-	 * we need to set idle transmission mode is to work around a HW issue
-	 * where we enable the pipe while not in idle link-training mode.
+	 * Until TGL on PORT_A we can have only eDP in SST mode. There the only
+	 * reason we need to set idle transmission mode is to work around a HW
+	 * issue where we enable the pipe while not in idle link-training mode.
 	 * In this case there is requirement to wait for a minimum number of
 	 * idle patterns to be sent.
 	 */
-	if (port == PORT_A)
+	if (port == PORT_A && INTEL_GEN(dev_priv) < 12)
 		return;
 
 	if (intel_de_wait_for_set(dev_priv, DP_TP_STATUS(port),
-- 
cgit v1.2.3


From a8ff5d405e90e7044ab45f315f2dbcbe6aebf5f8 Mon Sep 17 00:00:00 2001
From: Michel Thierry <michel.thierry@intel.com>
Date: Fri, 23 Aug 2019 01:20:48 -0700
Subject: drm/i915/tgl: Do not apply WaIncreaseDefaultTLBEntries from GEN12
 onwards

Workaround no longer needed (plus L3_LRA_1_GPGPU doesn't exist).

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823082055.5992-17-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 0db82921fb38..c94dfa562247 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2029,7 +2029,7 @@ static void gtt_write_workarounds(struct intel_gt *gt)
 		intel_uncore_write(uncore,
 				   GEN8_L3_LRA_1_GPGPU,
 				   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_BXT);
-	else if (INTEL_GEN(i915) >= 9)
+	else if (INTEL_GEN(i915) >= 9 && INTEL_GEN(i915) <= 11)
 		intel_uncore_write(uncore,
 				   GEN8_L3_LRA_1_GPGPU,
 				   GEN9_L3_LRA_1_GPGPU_DEFAULT_VALUE_SKL);
-- 
cgit v1.2.3


From 45e9c829ebeaa13b3b999f76963b9920d2147128 Mon Sep 17 00:00:00 2001
From: Michel Thierry <michel.thierry@intel.com>
Date: Fri, 23 Aug 2019 01:20:50 -0700
Subject: drm/i915/tgl/perf: use the same oa ctx_id format as icl

Compared to Icelake, Tigerlake's MAX_CONTEXT_HW_ID is smaller by one, but
since we just use the upper 32 bits of the lrc_desc, it's guaranteed OA
will use the correct one.

Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823082055.5992-19-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/i915_perf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index e42b86827d6b..2c9f46e12622 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1299,7 +1299,8 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		}
 		break;
 
-	case 11: {
+	case 11:
+	case 12: {
 		stream->specific_ctx_id_mask =
 			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32) |
 			((1U << GEN11_ENGINE_INSTANCE_WIDTH) - 1) << (GEN11_ENGINE_INSTANCE_SHIFT - 32) |
-- 
cgit v1.2.3


From 8a9a982767b7c89b2f23290e4f0f21f194b79dfe Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Tue, 27 Aug 2019 11:58:05 -0700
Subject: drm/i915: use a separate context for gpu relocs

The CS pre-parser can pre-fetch commands across memory sync points and
starting from gen12 it is able to pre-fetch across BB_START and BB_END
boundaries as well, so when we emit gpu relocs the pre-parser might
fetch the target location of the reloc before the memory write lands.

The parser can't pre-fetch across the ctx switch, so we use a separate
context to guarantee that the memory is synchronized before the parser
can get to it.

Note that there is no risk of the CS doing a lite restore from the reloc
context to the user context, even if the two have the same hw_id,
because since gen11 the CS also checks the LRCA when deciding if it can
lite-restore.

v2: limit new context to gen12+, release in eb_destroy, add a comment
    in emit_fini_breadcrumb (Chris).

Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190827185805.21799-1-daniele.ceraolospurio@intel.com
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 30 +++++++++++++++++++++++++-
 drivers/gpu/drm/i915/gt/intel_lrc.c            | 18 ++++++++++++++++
 2 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 5a2238d44423..8fbb454cfd6b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -252,6 +252,7 @@ struct i915_execbuffer {
 		bool has_fence : 1;
 		bool needs_unfenced : 1;
 
+		struct intel_context *ce;
 		struct i915_request *rq;
 		u32 *rq_cmd;
 		unsigned int rq_size;
@@ -880,6 +881,9 @@ static void eb_destroy(const struct i915_execbuffer *eb)
 {
 	GEM_BUG_ON(eb->reloc_cache.rq);
 
+	if (eb->reloc_cache.ce)
+		intel_context_put(eb->reloc_cache.ce);
+
 	if (eb->lut_size > 0)
 		kfree(eb->buckets);
 }
@@ -903,6 +907,7 @@ static void reloc_cache_init(struct reloc_cache *cache,
 	cache->has_fence = cache->gen < 4;
 	cache->needs_unfenced = INTEL_INFO(i915)->unfenced_needs_alignment;
 	cache->node.allocated = false;
+	cache->ce = NULL;
 	cache->rq = NULL;
 	cache->rq_size = 0;
 }
@@ -1168,7 +1173,7 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	if (err)
 		goto err_unmap;
 
-	rq = i915_request_create(eb->context);
+	rq = intel_context_create_request(cache->ce);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto err_unpin;
@@ -1239,6 +1244,29 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
 		if (!intel_engine_can_store_dword(eb->engine))
 			return ERR_PTR(-ENODEV);
 
+		if (!cache->ce) {
+			struct intel_context *ce;
+
+			/*
+			 * The CS pre-parser can pre-fetch commands across
+			 * memory sync points and starting gen12 it is able to
+			 * pre-fetch across BB_START and BB_END boundaries
+			 * (within the same context). We therefore use a
+			 * separate context gen12+ to guarantee that the reloc
+			 * writes land before the parser gets to the target
+			 * memory location.
+			 */
+			if (cache->gen >= 12)
+				ce = intel_context_create(eb->context->gem_context,
+							  eb->engine);
+			else
+				ce = intel_context_get(eb->context);
+			if (IS_ERR(ce))
+				return ERR_CAST(ce);
+
+			cache->ce = ce;
+		}
+
 		err = __reloc_gpu_alloc(eb, vma, len);
 		if (unlikely(err))
 			return ERR_PTR(err);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index cfbdcca76ff0..a141e9e37bf7 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2931,6 +2931,24 @@ static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 	return gen8_emit_fini_breadcrumb_footer(request, cs);
 }
 
+/*
+ * Note that the CS instruction pre-parser will not stall on the breadcrumb
+ * flush and will continue pre-fetching the instructions after it before the
+ * memory sync is completed. On pre-gen12 HW, the pre-parser will stop at
+ * BB_START/END instructions, so, even though we might pre-fetch the pre-amble
+ * of the next request before the memory has been flushed, we're guaranteed that
+ * we won't access the batch itself too early.
+ * However, on gen12+ the parser can pre-fetch across the BB_START/END commands,
+ * so, if the current request is modifying an instruction in the next request on
+ * the same intel_context, we might pre-fetch and then execute the pre-update
+ * instruction. To avoid this, the users of self-modifying code should either
+ * disable the parser around the code emitting the memory writes, via a new flag
+ * added to MI_ARB_CHECK, or emit the writes from a different intel_context. For
+ * the in-kernel use-cases we've opted to use a separate context, see
+ * reloc_gpu() as an example.
+ * All the above applies only to the instructions themselves. Non-inline data
+ * used by the instructions is not pre-fetched.
+ */
 static u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *request,
 					   u32 *cs)
 {
-- 
cgit v1.2.3


From f2085c8e950d536c7982182b0c9c015804011dd2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 27 Aug 2019 17:17:25 +0100
Subject: drm/i915/selftests: Remove accidental serialization between gpu_fill

Upon object creation for live_gem_contexts, we fill the object with
known scratch and flush it out of the CPU cache. Before performing the
GPU fill, we don't need to flush it again and so avoid serialising with
previous fills.

However, we do need some throttling on the internal interfaces if we do
not want to run out of memory!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190827161726.3640-1-chris@chris-wilson.co.uk
---
 .../gpu/drm/i915/gem/selftests/i915_gem_context.c  | 83 +++++++++++++++++++---
 1 file changed, 72 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 37a177e37665..63116c4fa8ba 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -180,12 +180,6 @@ static int gpu_fill(struct intel_context *ce,
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	i915_gem_object_lock(obj);
-	err = i915_gem_object_set_to_gtt_domain(obj, true);
-	i915_gem_object_unlock(obj);
-	if (err)
-		return err;
-
 	err = i915_vma_pin(vma, 0, 0, PIN_HIGH | PIN_USER);
 	if (err)
 		return err;
@@ -343,6 +337,45 @@ static unsigned long max_dwords(struct drm_i915_gem_object *obj)
 	return npages / DW_PER_PAGE;
 }
 
+static void throttle_release(struct i915_request **q, int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		if (IS_ERR_OR_NULL(q[i]))
+			continue;
+
+		i915_request_put(fetch_and_zero(&q[i]));
+	}
+}
+
+static int throttle(struct intel_context *ce,
+		    struct i915_request **q, int count)
+{
+	int i;
+
+	if (!IS_ERR_OR_NULL(q[0])) {
+		if (i915_request_wait(q[0],
+				      I915_WAIT_INTERRUPTIBLE,
+				      MAX_SCHEDULE_TIMEOUT) < 0)
+			return -EINTR;
+
+		i915_request_put(q[0]);
+	}
+
+	for (i = 0; i < count - 1; i++)
+		q[i] = q[i + 1];
+
+	q[i] = intel_context_create_request(ce);
+	if (IS_ERR(q[i]))
+		return PTR_ERR(q[i]);
+
+	i915_request_get(q[i]);
+	i915_request_add(q[i]);
+
+	return 0;
+}
+
 static int igt_ctx_exec(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -362,6 +395,7 @@ static int igt_ctx_exec(void *arg)
 	for_each_engine(engine, i915, id) {
 		struct drm_i915_gem_object *obj = NULL;
 		unsigned long ncontexts, ndwords, dw;
+		struct i915_request *tq[5] = {};
 		struct igt_live_test t;
 		struct drm_file *file;
 		IGT_TIMEOUT(end_time);
@@ -409,13 +443,18 @@ static int igt_ctx_exec(void *arg)
 			}
 
 			err = gpu_fill(ce, obj, dw);
-			intel_context_put(ce);
-
 			if (err) {
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
 				       engine->name, ctx->hw_id,
 				       yesno(!!ctx->vm), err);
+				intel_context_put(ce);
+				goto out_unlock;
+			}
+
+			err = throttle(ce, tq, ARRAY_SIZE(tq));
+			if (err) {
+				intel_context_put(ce);
 				goto out_unlock;
 			}
 
@@ -426,6 +465,8 @@ static int igt_ctx_exec(void *arg)
 
 			ndwords++;
 			ncontexts++;
+
+			intel_context_put(ce);
 		}
 
 		pr_info("Submitted %lu contexts to %s, filling %lu dwords\n",
@@ -444,6 +485,7 @@ static int igt_ctx_exec(void *arg)
 		}
 
 out_unlock:
+		throttle_release(tq, ARRAY_SIZE(tq));
 		if (igt_live_test_end(&t))
 			err = -EIO;
 		mutex_unlock(&i915->drm.struct_mutex);
@@ -461,6 +503,7 @@ out_unlock:
 static int igt_shared_ctx_exec(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
+	struct i915_request *tq[5] = {};
 	struct i915_gem_context *parent;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -535,14 +578,20 @@ static int igt_shared_ctx_exec(void *arg)
 			}
 
 			err = gpu_fill(ce, obj, dw);
-			intel_context_put(ce);
-			kernel_context_close(ctx);
-
 			if (err) {
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
 				       engine->name, ctx->hw_id,
 				       yesno(!!ctx->vm), err);
+				intel_context_put(ce);
+				kernel_context_close(ctx);
+				goto out_test;
+			}
+
+			err = throttle(ce, tq, ARRAY_SIZE(tq));
+			if (err) {
+				intel_context_put(ce);
+				kernel_context_close(ctx);
 				goto out_test;
 			}
 
@@ -553,6 +602,9 @@ static int igt_shared_ctx_exec(void *arg)
 
 			ndwords++;
 			ncontexts++;
+
+			intel_context_put(ce);
+			kernel_context_close(ctx);
 		}
 		pr_info("Submitted %lu contexts to %s, filling %lu dwords\n",
 			ncontexts, engine->name, ndwords);
@@ -574,6 +626,7 @@ static int igt_shared_ctx_exec(void *arg)
 		mutex_lock(&i915->drm.struct_mutex);
 	}
 out_test:
+	throttle_release(tq, ARRAY_SIZE(tq));
 	if (igt_live_test_end(&t))
 		err = -EIO;
 out_unlock:
@@ -1050,6 +1103,7 @@ static int igt_ctx_readonly(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct drm_i915_gem_object *obj = NULL;
+	struct i915_request *tq[5] = {};
 	struct i915_address_space *vm;
 	struct i915_gem_context *ctx;
 	unsigned long idx, ndwords, dw;
@@ -1121,6 +1175,12 @@ static int igt_ctx_readonly(void *arg)
 				goto out_unlock;
 			}
 
+			err = throttle(ce, tq, ARRAY_SIZE(tq));
+			if (err) {
+				i915_gem_context_unlock_engines(ctx);
+				goto out_unlock;
+			}
+
 			if (++dw == max_dwords(obj)) {
 				obj = NULL;
 				dw = 0;
@@ -1151,6 +1211,7 @@ static int igt_ctx_readonly(void *arg)
 	}
 
 out_unlock:
+	throttle_release(tq, ARRAY_SIZE(tq));
 	if (igt_live_test_end(&t))
 		err = -EIO;
 	mutex_unlock(&i915->drm.struct_mutex);
-- 
cgit v1.2.3


From c4e6488120e9ef1ceced8fb0caf134c5242ddaf4 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 27 Aug 2019 17:17:26 +0100
Subject: drm/i915/selftests: Try to recycle context allocations

igt_ctx_exec allocates a new context for each iteration, keeping them
all allocated until the end. Instead, release the local ctx reference at
the end of each iteration, allowing ourselves to reap those if under
mempressure.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190827161726.3640-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 63116c4fa8ba..da54a718c712 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -424,7 +424,7 @@ static int igt_ctx_exec(void *arg)
 			struct i915_gem_context *ctx;
 			struct intel_context *ce;
 
-			ctx = live_context(i915, file);
+			ctx = kernel_context(i915);
 			if (IS_ERR(ctx)) {
 				err = PTR_ERR(ctx);
 				goto out_unlock;
@@ -438,6 +438,7 @@ static int igt_ctx_exec(void *arg)
 				if (IS_ERR(obj)) {
 					err = PTR_ERR(obj);
 					intel_context_put(ce);
+					kernel_context_close(ctx);
 					goto out_unlock;
 				}
 			}
@@ -449,12 +450,14 @@ static int igt_ctx_exec(void *arg)
 				       engine->name, ctx->hw_id,
 				       yesno(!!ctx->vm), err);
 				intel_context_put(ce);
+				kernel_context_close(ctx);
 				goto out_unlock;
 			}
 
 			err = throttle(ce, tq, ARRAY_SIZE(tq));
 			if (err) {
 				intel_context_put(ce);
+				kernel_context_close(ctx);
 				goto out_unlock;
 			}
 
@@ -467,6 +470,7 @@ static int igt_ctx_exec(void *arg)
 			ncontexts++;
 
 			intel_context_put(ce);
+			kernel_context_close(ctx);
 		}
 
 		pr_info("Submitted %lu contexts to %s, filling %lu dwords\n",
-- 
cgit v1.2.3


From e8f6b4952ec54a9d7e43f908d39dc168b0310599 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 27 Aug 2019 13:06:15 +0100
Subject: drm/i915/execlists: Flush the post-sync breadcrumb write harder

Quite rarely we see that the CS completion event fires before the
breadcrumb is coherent, which presumably is a result of the CS_STALL not
waiting for the post-sync operation. Try throwing in a DC_FLUSH into
the following pipecontrol to see if that makes any difference.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190827120615.31390-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index a141e9e37bf7..171d5205962c 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2923,8 +2923,10 @@ static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 				      PIPE_CONTROL_DC_FLUSH_ENABLE);
 
 	/* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */
+	/* XXX DC_FLUSH for post-sync write? (cf early context-switch bug) */
 	cs = gen8_emit_pipe_control(cs,
 				    PIPE_CONTROL_FLUSH_ENABLE |
+				    PIPE_CONTROL_DC_FLUSH_ENABLE |
 				    PIPE_CONTROL_CS_STALL,
 				    0);
 
-- 
cgit v1.2.3


From 592a7c5e082e237c7508f37b2c3494a731acad88 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Fri, 9 Aug 2019 17:56:53 +0300
Subject: drm/i915: Extend non readable mcr range

Our current avoidance of non readable mcr range was not
inclusive enough. Extend the start and end.

References: HSDES#1405586840
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190809145653.2279-1-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index ad2261e0cba8..8639fcccdb42 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1453,7 +1453,7 @@ static bool mcr_range(struct drm_i915_private *i915, u32 offset)
 	 * which only controls CPU initiated MMIO. Routing does not
 	 * work for CS access so we cannot verify them on this path.
 	 */
-	if (INTEL_GEN(i915) >= 8 && (offset >= 0xb100 && offset <= 0xb3ff))
+	if (INTEL_GEN(i915) >= 8 && (offset >= 0xb000 && offset <= 0xb4ff))
 		return true;
 
 	return false;
-- 
cgit v1.2.3


From 325b916a9e1b11d28c40b02e24734750946a1785 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 26 Aug 2019 14:38:37 +0100
Subject: drm/i915/selftests: Ignore coherency failures on Broadwater

We've been ignoring similar coherency issues in IGT for Broadwater, and
specifically Broadwater (original gen4) and not, for example, Crestline
(same generation as Broadwater, but the mobile variant). Without any
means to reproduce locally (I have a 965GM but alas no 965G), fixing will
be slow, so tell CI to ignore any failure until we are ready with a fix.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190826133837.6784-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 17006d50b63f..a8014c59b388 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1119,6 +1119,8 @@ bool intel_engine_can_store_dword(struct intel_engine_cs *engine)
 	case 3:
 		/* maybe only uses physical not virtual addresses */
 		return !(IS_I915G(engine->i915) || IS_I915GM(engine->i915));
+	case 4:
+		return !IS_I965G(engine->i915); /* who knows! */
 	case 6:
 		return engine->class != VIDEO_DECODE_CLASS; /* b0rked */
 	default:
-- 
cgit v1.2.3


From 8a84bacba19c154bdcb278657d0b7594ce2d939c Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Fri, 23 Aug 2019 13:07:11 +0300
Subject: drm/i915: Align power domain names with port names
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a difference in BSpec's and the driver's designation of DDI
ports. BSpec uses the following names:
- before GEN11:
  BSpec/driver:
  	port A/B/C/D etc
- GEN11:
  BSpec/driver:
	port A-F
- GEN12:
  BSpec:
  	port A/B/C for combo PHY ports
	port TC1-6 for Type C PHY ports
  driver:
	port A-I.
  The driver's port D name matches BSpec's TC1 port name.

So far power domains were named according to the BSpec designation, to
make it easier to match the code against the specification. That however
can be confusing when a power domain needs to be matched to a port on
GEN12+. To resolve that use the driver's port A-I designation for power
domain names too and rename the corresponding power wells so that they
reflect the mapping from the driver's to BSpec's port name.

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823100711.27833-1-imre.deak@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c       |  10 +-
 drivers/gpu/drm/i915/display/intel_display_power.c | 361 ++++++++++-----------
 drivers/gpu/drm/i915/display/intel_display_power.h |  40 +--
 drivers/gpu/drm/i915/i915_debugfs.c                |   3 +-
 4 files changed, 198 insertions(+), 216 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index a9f8be2cd364..4773832b0f49 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -6737,16 +6737,16 @@ intel_aux_power_domain(struct intel_digital_port *dig_port)
 	    dig_port->tc_mode == TC_PORT_TBT_ALT) {
 		switch (dig_port->aux_ch) {
 		case AUX_CH_C:
-			return POWER_DOMAIN_AUX_TBT1;
+			return POWER_DOMAIN_AUX_C_TBT;
 		case AUX_CH_D:
-			return POWER_DOMAIN_AUX_TBT2;
+			return POWER_DOMAIN_AUX_D_TBT;
 		case AUX_CH_E:
-			return POWER_DOMAIN_AUX_TBT3;
+			return POWER_DOMAIN_AUX_E_TBT;
 		case AUX_CH_F:
-			return POWER_DOMAIN_AUX_TBT4;
+			return POWER_DOMAIN_AUX_F_TBT;
 		default:
 			MISSING_CASE(dig_port->aux_ch);
-			return POWER_DOMAIN_AUX_TBT1;
+			return POWER_DOMAIN_AUX_C_TBT;
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 12099760d99e..ce88a27229ef 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -24,11 +24,8 @@ bool intel_display_power_well_is_enabled(struct drm_i915_private *dev_priv,
 					 enum i915_power_well_id power_well_id);
 
 const char *
-intel_display_power_domain_str(struct drm_i915_private *i915,
-			       enum intel_display_power_domain domain)
+intel_display_power_domain_str(enum intel_display_power_domain domain)
 {
-	bool ddi_tc_ports = IS_GEN(i915, 12);
-
 	switch (domain) {
 	case POWER_DOMAIN_DISPLAY_CORE:
 		return "DISPLAY_CORE";
@@ -71,23 +68,17 @@ intel_display_power_domain_str(struct drm_i915_private *i915,
 	case POWER_DOMAIN_PORT_DDI_C_LANES:
 		return "PORT_DDI_C_LANES";
 	case POWER_DOMAIN_PORT_DDI_D_LANES:
-		BUILD_BUG_ON(POWER_DOMAIN_PORT_DDI_D_LANES !=
-			     POWER_DOMAIN_PORT_DDI_TC1_LANES);
-		return ddi_tc_ports ? "PORT_DDI_TC1_LANES" : "PORT_DDI_D_LANES";
+		return "PORT_DDI_D_LANES";
 	case POWER_DOMAIN_PORT_DDI_E_LANES:
-		BUILD_BUG_ON(POWER_DOMAIN_PORT_DDI_E_LANES !=
-			     POWER_DOMAIN_PORT_DDI_TC2_LANES);
-		return ddi_tc_ports ? "PORT_DDI_TC2_LANES" : "PORT_DDI_E_LANES";
+		return "PORT_DDI_E_LANES";
 	case POWER_DOMAIN_PORT_DDI_F_LANES:
-		BUILD_BUG_ON(POWER_DOMAIN_PORT_DDI_F_LANES !=
-			     POWER_DOMAIN_PORT_DDI_TC3_LANES);
-		return ddi_tc_ports ? "PORT_DDI_TC3_LANES" : "PORT_DDI_F_LANES";
-	case POWER_DOMAIN_PORT_DDI_TC4_LANES:
-		return "PORT_DDI_TC4_LANES";
-	case POWER_DOMAIN_PORT_DDI_TC5_LANES:
-		return "PORT_DDI_TC5_LANES";
-	case POWER_DOMAIN_PORT_DDI_TC6_LANES:
-		return "PORT_DDI_TC6_LANES";
+		return "PORT_DDI_F_LANES";
+	case POWER_DOMAIN_PORT_DDI_G_LANES:
+		return "PORT_DDI_G_LANES";
+	case POWER_DOMAIN_PORT_DDI_H_LANES:
+		return "PORT_DDI_H_LANES";
+	case POWER_DOMAIN_PORT_DDI_I_LANES:
+		return "PORT_DDI_I_LANES";
 	case POWER_DOMAIN_PORT_DDI_A_IO:
 		return "PORT_DDI_A_IO";
 	case POWER_DOMAIN_PORT_DDI_B_IO:
@@ -95,23 +86,17 @@ intel_display_power_domain_str(struct drm_i915_private *i915,
 	case POWER_DOMAIN_PORT_DDI_C_IO:
 		return "PORT_DDI_C_IO";
 	case POWER_DOMAIN_PORT_DDI_D_IO:
-		BUILD_BUG_ON(POWER_DOMAIN_PORT_DDI_D_IO !=
-			     POWER_DOMAIN_PORT_DDI_TC1_IO);
-		return ddi_tc_ports ? "PORT_DDI_TC1_IO" : "PORT_DDI_D_IO";
+		return "PORT_DDI_D_IO";
 	case POWER_DOMAIN_PORT_DDI_E_IO:
-		BUILD_BUG_ON(POWER_DOMAIN_PORT_DDI_E_IO !=
-			     POWER_DOMAIN_PORT_DDI_TC2_IO);
-		return ddi_tc_ports ? "PORT_DDI_TC2_IO" : "PORT_DDI_E_IO";
+		return "PORT_DDI_E_IO";
 	case POWER_DOMAIN_PORT_DDI_F_IO:
-		BUILD_BUG_ON(POWER_DOMAIN_PORT_DDI_F_IO !=
-			     POWER_DOMAIN_PORT_DDI_TC3_IO);
-		return ddi_tc_ports ? "PORT_DDI_TC3_IO" : "PORT_DDI_F_IO";
-	case POWER_DOMAIN_PORT_DDI_TC4_IO:
-		return "PORT_DDI_TC4_IO";
-	case POWER_DOMAIN_PORT_DDI_TC5_IO:
-		return "PORT_DDI_TC5_IO";
-	case POWER_DOMAIN_PORT_DDI_TC6_IO:
-		return "PORT_DDI_TC6_IO";
+		return "PORT_DDI_F_IO";
+	case POWER_DOMAIN_PORT_DDI_G_IO:
+		return "PORT_DDI_G_IO";
+	case POWER_DOMAIN_PORT_DDI_H_IO:
+		return "PORT_DDI_H_IO";
+	case POWER_DOMAIN_PORT_DDI_I_IO:
+		return "PORT_DDI_I_IO";
 	case POWER_DOMAIN_PORT_DSI:
 		return "PORT_DSI";
 	case POWER_DOMAIN_PORT_CRT:
@@ -129,34 +114,33 @@ intel_display_power_domain_str(struct drm_i915_private *i915,
 	case POWER_DOMAIN_AUX_C:
 		return "AUX_C";
 	case POWER_DOMAIN_AUX_D:
-		BUILD_BUG_ON(POWER_DOMAIN_AUX_D != POWER_DOMAIN_AUX_TC1);
-		return ddi_tc_ports ? "AUX_TC1" : "AUX_D";
+		return "AUX_D";
 	case POWER_DOMAIN_AUX_E:
-		BUILD_BUG_ON(POWER_DOMAIN_AUX_E != POWER_DOMAIN_AUX_TC2);
-		return ddi_tc_ports ? "AUX_TC2" : "AUX_E";
+		return "AUX_E";
 	case POWER_DOMAIN_AUX_F:
-		BUILD_BUG_ON(POWER_DOMAIN_AUX_F != POWER_DOMAIN_AUX_TC3);
-		return ddi_tc_ports ? "AUX_TC3" : "AUX_F";
-	case POWER_DOMAIN_AUX_TC4:
-		return "AUX_TC4";
-	case POWER_DOMAIN_AUX_TC5:
-		return "AUX_TC5";
-	case POWER_DOMAIN_AUX_TC6:
-		return "AUX_TC6";
+		return "AUX_F";
+	case POWER_DOMAIN_AUX_G:
+		return "AUX_G";
+	case POWER_DOMAIN_AUX_H:
+		return "AUX_H";
+	case POWER_DOMAIN_AUX_I:
+		return "AUX_I";
 	case POWER_DOMAIN_AUX_IO_A:
 		return "AUX_IO_A";
-	case POWER_DOMAIN_AUX_TBT1:
-		return "AUX_TBT1";
-	case POWER_DOMAIN_AUX_TBT2:
-		return "AUX_TBT2";
-	case POWER_DOMAIN_AUX_TBT3:
-		return "AUX_TBT3";
-	case POWER_DOMAIN_AUX_TBT4:
-		return "AUX_TBT4";
-	case POWER_DOMAIN_AUX_TBT5:
-		return "AUX_TBT5";
-	case POWER_DOMAIN_AUX_TBT6:
-		return "AUX_TBT6";
+	case POWER_DOMAIN_AUX_C_TBT:
+		return "AUX_C_TBT";
+	case POWER_DOMAIN_AUX_D_TBT:
+		return "AUX_D_TBT";
+	case POWER_DOMAIN_AUX_E_TBT:
+		return "AUX_E_TBT";
+	case POWER_DOMAIN_AUX_F_TBT:
+		return "AUX_F_TBT";
+	case POWER_DOMAIN_AUX_G_TBT:
+		return "AUX_G_TBT";
+	case POWER_DOMAIN_AUX_H_TBT:
+		return "AUX_H_TBT";
+	case POWER_DOMAIN_AUX_I_TBT:
+		return "AUX_I_TBT";
 	case POWER_DOMAIN_GMBUS:
 		return "GMBUS";
 	case POWER_DOMAIN_INIT:
@@ -1718,15 +1702,12 @@ __async_put_domains_state_ok(struct i915_power_domains *power_domains)
 static void print_power_domains(struct i915_power_domains *power_domains,
 				const char *prefix, u64 mask)
 {
-	struct drm_i915_private *i915 =
-		container_of(power_domains, struct drm_i915_private,
-			     power_domains);
 	enum intel_display_power_domain domain;
 
 	DRM_DEBUG_DRIVER("%s (%lu):\n", prefix, hweight64(mask));
 	for_each_power_domain(domain, mask)
 		DRM_DEBUG_DRIVER("%s use_count %d\n",
-				 intel_display_power_domain_str(i915, domain),
+				 intel_display_power_domain_str(domain),
 				 power_domains->domain_use_count[domain]);
 }
 
@@ -1896,7 +1877,7 @@ __intel_display_power_put_domain(struct drm_i915_private *dev_priv,
 {
 	struct i915_power_domains *power_domains;
 	struct i915_power_well *power_well;
-	const char *name = intel_display_power_domain_str(dev_priv, domain);
+	const char *name = intel_display_power_domain_str(domain);
 
 	power_domains = &dev_priv->power_domains;
 
@@ -2487,10 +2468,10 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	BIT_ULL(POWER_DOMAIN_AUX_D) |			\
 	BIT_ULL(POWER_DOMAIN_AUX_E) |			\
 	BIT_ULL(POWER_DOMAIN_AUX_F) |			\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT1) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT2) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT3) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT4) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_C_TBT) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_D_TBT) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_E_TBT) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_F_TBT) |		\
 	BIT_ULL(POWER_DOMAIN_VGA) |			\
 	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
@@ -2530,22 +2511,22 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	BIT_ULL(POWER_DOMAIN_AUX_A))
 #define ICL_AUX_B_IO_POWER_DOMAINS (			\
 	BIT_ULL(POWER_DOMAIN_AUX_B))
-#define ICL_AUX_C_IO_POWER_DOMAINS (			\
+#define ICL_AUX_C_TC1_IO_POWER_DOMAINS (		\
 	BIT_ULL(POWER_DOMAIN_AUX_C))
-#define ICL_AUX_D_IO_POWER_DOMAINS (			\
+#define ICL_AUX_D_TC2_IO_POWER_DOMAINS (		\
 	BIT_ULL(POWER_DOMAIN_AUX_D))
-#define ICL_AUX_E_IO_POWER_DOMAINS (			\
+#define ICL_AUX_E_TC3_IO_POWER_DOMAINS (		\
 	BIT_ULL(POWER_DOMAIN_AUX_E))
-#define ICL_AUX_F_IO_POWER_DOMAINS (			\
+#define ICL_AUX_F_TC4_IO_POWER_DOMAINS (		\
 	BIT_ULL(POWER_DOMAIN_AUX_F))
-#define ICL_AUX_TBT1_IO_POWER_DOMAINS (			\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT1))
-#define ICL_AUX_TBT2_IO_POWER_DOMAINS (			\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT2))
-#define ICL_AUX_TBT3_IO_POWER_DOMAINS (			\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT3))
-#define ICL_AUX_TBT4_IO_POWER_DOMAINS (			\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT4))
+#define ICL_AUX_C_TBT1_IO_POWER_DOMAINS (		\
+	BIT_ULL(POWER_DOMAIN_AUX_C_TBT))
+#define ICL_AUX_D_TBT2_IO_POWER_DOMAINS (		\
+	BIT_ULL(POWER_DOMAIN_AUX_D_TBT))
+#define ICL_AUX_E_TBT3_IO_POWER_DOMAINS (		\
+	BIT_ULL(POWER_DOMAIN_AUX_E_TBT))
+#define ICL_AUX_F_TBT4_IO_POWER_DOMAINS (		\
+	BIT_ULL(POWER_DOMAIN_AUX_F_TBT))
 
 #define TGL_PW_5_POWER_DOMAINS (			\
 	BIT_ULL(POWER_DOMAIN_PIPE_D) |			\
@@ -2565,24 +2546,24 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	BIT_ULL(POWER_DOMAIN_PIPE_B) |			\
 	BIT_ULL(POWER_DOMAIN_TRANSCODER_B) |		\
 	BIT_ULL(POWER_DOMAIN_PIPE_B_PANEL_FITTER) |	\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_TC1_LANES) |	\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_TC2_LANES) |	\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_TC3_LANES) |	\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_TC4_LANES) |	\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_TC5_LANES) |	\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_TC6_LANES) |	\
-	BIT_ULL(POWER_DOMAIN_AUX_TC1) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TC2) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TC3) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TC4) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TC5) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TC6) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT1) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT2) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT3) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT4) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT5) |		\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT6) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_E_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_G_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_H_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_I_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_AUX_D) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_E) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_F) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_G) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_H) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_I) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_D_TBT) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_E_TBT) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_F_TBT) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_G_TBT) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_H_TBT) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_I_TBT) |		\
 	BIT_ULL(POWER_DOMAIN_VGA) |			\
 	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
@@ -2598,35 +2579,50 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
 
-#define TGL_DDI_IO_TC1_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_TC1_IO))
-#define TGL_DDI_IO_TC2_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_TC2_IO))
-#define TGL_DDI_IO_TC3_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_TC3_IO))
-#define TGL_DDI_IO_TC4_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_TC4_IO))
-#define TGL_DDI_IO_TC5_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_TC5_IO))
-#define TGL_DDI_IO_TC6_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_PORT_DDI_TC6_IO))
-
-#define TGL_AUX_TC1_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_TC1))
-#define TGL_AUX_TC2_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_TC2))
-#define TGL_AUX_TC3_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_TC3))
-#define TGL_AUX_TC4_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_TC4))
-#define TGL_AUX_TC5_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_TC5))
-#define TGL_AUX_TC6_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_TC6))
-#define TGL_AUX_TBT5_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT5))
-#define TGL_AUX_TBT6_IO_POWER_DOMAINS (		\
-	BIT_ULL(POWER_DOMAIN_AUX_TBT6))
+#define TGL_DDI_IO_D_TC1_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_IO))
+#define TGL_DDI_IO_E_TC2_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_E_IO))
+#define TGL_DDI_IO_F_TC3_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_IO))
+#define TGL_DDI_IO_G_TC4_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_G_IO))
+#define TGL_DDI_IO_H_TC5_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_H_IO))
+#define TGL_DDI_IO_I_TC6_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_I_IO))
+
+#define TGL_AUX_A_IO_POWER_DOMAINS (		\
+	BIT_ULL(POWER_DOMAIN_AUX_IO_A) |	\
+	BIT_ULL(POWER_DOMAIN_AUX_A))
+#define TGL_AUX_B_IO_POWER_DOMAINS (		\
+	BIT_ULL(POWER_DOMAIN_AUX_B))
+#define TGL_AUX_C_IO_POWER_DOMAINS (		\
+	BIT_ULL(POWER_DOMAIN_AUX_C))
+#define TGL_AUX_D_TC1_IO_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_AUX_D))
+#define TGL_AUX_E_TC2_IO_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_AUX_E))
+#define TGL_AUX_F_TC3_IO_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_AUX_F))
+#define TGL_AUX_G_TC4_IO_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_AUX_G))
+#define TGL_AUX_H_TC5_IO_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_AUX_H))
+#define TGL_AUX_I_TC6_IO_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_AUX_I))
+#define TGL_AUX_D_TBT1_IO_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_AUX_D_TBT))
+#define TGL_AUX_E_TBT2_IO_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_AUX_E_TBT))
+#define TGL_AUX_F_TBT3_IO_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_AUX_F_TBT))
+#define TGL_AUX_G_TBT4_IO_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_AUX_G_TBT))
+#define TGL_AUX_H_TBT5_IO_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_AUX_H_TBT))
+#define TGL_AUX_I_TBT6_IO_POWER_DOMAINS (	\
+	BIT_ULL(POWER_DOMAIN_AUX_I_TBT))
 
 static const struct i915_power_well_ops i9xx_always_on_power_well_ops = {
 	.sync_hw = i9xx_power_well_sync_hw_noop,
@@ -3484,8 +3480,8 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX C",
-		.domains = ICL_AUX_C_IO_POWER_DOMAINS,
+		.name = "AUX C TC1",
+		.domains = ICL_AUX_C_TC1_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3495,8 +3491,8 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX D",
-		.domains = ICL_AUX_D_IO_POWER_DOMAINS,
+		.name = "AUX D TC2",
+		.domains = ICL_AUX_D_TC2_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3506,8 +3502,8 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX E",
-		.domains = ICL_AUX_E_IO_POWER_DOMAINS,
+		.name = "AUX E TC3",
+		.domains = ICL_AUX_E_TC3_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3517,8 +3513,8 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX F",
-		.domains = ICL_AUX_F_IO_POWER_DOMAINS,
+		.name = "AUX F TC4",
+		.domains = ICL_AUX_F_TC4_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3528,8 +3524,8 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TBT1",
-		.domains = ICL_AUX_TBT1_IO_POWER_DOMAINS,
+		.name = "AUX C TBT1",
+		.domains = ICL_AUX_C_TBT1_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3539,8 +3535,8 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TBT2",
-		.domains = ICL_AUX_TBT2_IO_POWER_DOMAINS,
+		.name = "AUX D TBT2",
+		.domains = ICL_AUX_D_TBT2_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3550,8 +3546,8 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TBT3",
-		.domains = ICL_AUX_TBT3_IO_POWER_DOMAINS,
+		.name = "AUX E TBT3",
+		.domains = ICL_AUX_E_TBT3_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3561,8 +3557,8 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TBT4",
-		.domains = ICL_AUX_TBT4_IO_POWER_DOMAINS,
+		.name = "AUX F TBT4",
+		.domains = ICL_AUX_F_TBT4_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3667,8 +3663,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		}
 	},
 	{
-		.name = "DDI TC1 IO",
-		.domains = TGL_DDI_IO_TC1_POWER_DOMAINS,
+		.name = "DDI D TC1 IO",
+		.domains = TGL_DDI_IO_D_TC1_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3677,8 +3673,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "DDI TC2 IO",
-		.domains = TGL_DDI_IO_TC2_POWER_DOMAINS,
+		.name = "DDI E TC2 IO",
+		.domains = TGL_DDI_IO_E_TC2_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3687,8 +3683,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "DDI TC3 IO",
-		.domains = TGL_DDI_IO_TC3_POWER_DOMAINS,
+		.name = "DDI F TC3 IO",
+		.domains = TGL_DDI_IO_F_TC3_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3697,8 +3693,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "DDI TC4 IO",
-		.domains = TGL_DDI_IO_TC4_POWER_DOMAINS,
+		.name = "DDI G TC4 IO",
+		.domains = TGL_DDI_IO_G_TC4_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3707,8 +3703,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "DDI TC5 IO",
-		.domains = TGL_DDI_IO_TC5_POWER_DOMAINS,
+		.name = "DDI H TC5 IO",
+		.domains = TGL_DDI_IO_H_TC5_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3717,8 +3713,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "DDI TC6 IO",
-		.domains = TGL_DDI_IO_TC6_POWER_DOMAINS,
+		.name = "DDI I TC6 IO",
+		.domains = TGL_DDI_IO_I_TC6_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3728,7 +3724,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	},
 	{
 		.name = "AUX A",
-		.domains = ICL_AUX_A_IO_POWER_DOMAINS,
+		.domains = TGL_AUX_A_IO_POWER_DOMAINS,
 		.ops = &icl_combo_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3738,7 +3734,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	},
 	{
 		.name = "AUX B",
-		.domains = ICL_AUX_B_IO_POWER_DOMAINS,
+		.domains = TGL_AUX_B_IO_POWER_DOMAINS,
 		.ops = &icl_combo_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3748,7 +3744,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 	},
 	{
 		.name = "AUX C",
-		.domains = ICL_AUX_C_IO_POWER_DOMAINS,
+		.domains = TGL_AUX_C_IO_POWER_DOMAINS,
 		.ops = &icl_combo_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3757,8 +3753,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TC1",
-		.domains = TGL_AUX_TC1_IO_POWER_DOMAINS,
+		.name = "AUX D TC1",
+		.domains = TGL_AUX_D_TC1_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3768,8 +3764,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TC2",
-		.domains = TGL_AUX_TC2_IO_POWER_DOMAINS,
+		.name = "AUX E TC2",
+		.domains = TGL_AUX_E_TC2_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3779,8 +3775,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TC3",
-		.domains = TGL_AUX_TC3_IO_POWER_DOMAINS,
+		.name = "AUX F TC3",
+		.domains = TGL_AUX_F_TC3_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3790,8 +3786,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TC4",
-		.domains = TGL_AUX_TC4_IO_POWER_DOMAINS,
+		.name = "AUX G TC4",
+		.domains = TGL_AUX_G_TC4_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3801,8 +3797,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TC5",
-		.domains = TGL_AUX_TC5_IO_POWER_DOMAINS,
+		.name = "AUX H TC5",
+		.domains = TGL_AUX_H_TC5_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3812,8 +3808,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TC6",
-		.domains = TGL_AUX_TC6_IO_POWER_DOMAINS,
+		.name = "AUX I TC6",
+		.domains = TGL_AUX_I_TC6_IO_POWER_DOMAINS,
 		.ops = &icl_tc_phy_aux_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3823,8 +3819,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TBT1",
-		.domains = ICL_AUX_TBT1_IO_POWER_DOMAINS,
+		.name = "AUX D TBT1",
+		.domains = TGL_AUX_D_TBT1_IO_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3834,8 +3830,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TBT2",
-		.domains = ICL_AUX_TBT2_IO_POWER_DOMAINS,
+		.name = "AUX E TBT2",
+		.domains = TGL_AUX_E_TBT2_IO_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3845,8 +3841,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TBT3",
-		.domains = ICL_AUX_TBT3_IO_POWER_DOMAINS,
+		.name = "AUX F TBT3",
+		.domains = TGL_AUX_F_TBT3_IO_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3856,8 +3852,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TBT4",
-		.domains = ICL_AUX_TBT4_IO_POWER_DOMAINS,
+		.name = "AUX G TBT4",
+		.domains = TGL_AUX_G_TBT4_IO_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3867,8 +3863,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TBT5",
-		.domains = TGL_AUX_TBT5_IO_POWER_DOMAINS,
+		.name = "AUX H TBT5",
+		.domains = TGL_AUX_H_TBT5_IO_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -3878,8 +3874,8 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		},
 	},
 	{
-		.name = "AUX TBT6",
-		.domains = TGL_AUX_TBT6_IO_POWER_DOMAINS,
+		.name = "AUX I TBT6",
+		.domains = TGL_AUX_I_TBT6_IO_POWER_DOMAINS,
 		.ops = &hsw_power_well_ops,
 		.id = DISP_PW_ID_NONE,
 		{
@@ -5104,8 +5100,7 @@ static void intel_power_domains_dump_info(struct drm_i915_private *i915)
 
 		for_each_power_domain(domain, power_well->desc->domains)
 			DRM_DEBUG_DRIVER("  %-23s %d\n",
-					 intel_display_power_domain_str(i915,
-									domain),
+					 intel_display_power_domain_str(domain),
 					 power_domains->domain_use_count[domain]);
 	}
 }
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.h b/drivers/gpu/drm/i915/display/intel_display_power.h
index a50605b8b1ad..737b5def7fc6 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.h
+++ b/drivers/gpu/drm/i915/display/intel_display_power.h
@@ -36,29 +36,20 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_PORT_DDI_B_LANES,
 	POWER_DOMAIN_PORT_DDI_C_LANES,
 	POWER_DOMAIN_PORT_DDI_D_LANES,
-	POWER_DOMAIN_PORT_DDI_TC1_LANES = POWER_DOMAIN_PORT_DDI_D_LANES,
 	POWER_DOMAIN_PORT_DDI_E_LANES,
-	POWER_DOMAIN_PORT_DDI_TC2_LANES = POWER_DOMAIN_PORT_DDI_E_LANES,
 	POWER_DOMAIN_PORT_DDI_F_LANES,
-	POWER_DOMAIN_PORT_DDI_TC3_LANES = POWER_DOMAIN_PORT_DDI_F_LANES,
-	POWER_DOMAIN_PORT_DDI_TC4_LANES,
-	POWER_DOMAIN_PORT_DDI_TC5_LANES,
-	POWER_DOMAIN_PORT_DDI_TC6_LANES,
+	POWER_DOMAIN_PORT_DDI_G_LANES,
+	POWER_DOMAIN_PORT_DDI_H_LANES,
+	POWER_DOMAIN_PORT_DDI_I_LANES,
 	POWER_DOMAIN_PORT_DDI_A_IO,
 	POWER_DOMAIN_PORT_DDI_B_IO,
 	POWER_DOMAIN_PORT_DDI_C_IO,
 	POWER_DOMAIN_PORT_DDI_D_IO,
-	POWER_DOMAIN_PORT_DDI_TC1_IO = POWER_DOMAIN_PORT_DDI_D_IO,
 	POWER_DOMAIN_PORT_DDI_E_IO,
-	POWER_DOMAIN_PORT_DDI_TC2_IO = POWER_DOMAIN_PORT_DDI_E_IO,
 	POWER_DOMAIN_PORT_DDI_F_IO,
-	POWER_DOMAIN_PORT_DDI_TC3_IO = POWER_DOMAIN_PORT_DDI_F_IO,
 	POWER_DOMAIN_PORT_DDI_G_IO,
-	POWER_DOMAIN_PORT_DDI_TC4_IO = POWER_DOMAIN_PORT_DDI_G_IO,
 	POWER_DOMAIN_PORT_DDI_H_IO,
-	POWER_DOMAIN_PORT_DDI_TC5_IO = POWER_DOMAIN_PORT_DDI_H_IO,
 	POWER_DOMAIN_PORT_DDI_I_IO,
-	POWER_DOMAIN_PORT_DDI_TC6_IO = POWER_DOMAIN_PORT_DDI_I_IO,
 	POWER_DOMAIN_PORT_DSI,
 	POWER_DOMAIN_PORT_CRT,
 	POWER_DOMAIN_PORT_OTHER,
@@ -68,21 +59,19 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_AUX_B,
 	POWER_DOMAIN_AUX_C,
 	POWER_DOMAIN_AUX_D,
-	POWER_DOMAIN_AUX_TC1 = POWER_DOMAIN_AUX_D,
 	POWER_DOMAIN_AUX_E,
-	POWER_DOMAIN_AUX_TC2 = POWER_DOMAIN_AUX_E,
 	POWER_DOMAIN_AUX_F,
-	POWER_DOMAIN_AUX_TC3 = POWER_DOMAIN_AUX_F,
-	POWER_DOMAIN_AUX_TC4,
-	POWER_DOMAIN_AUX_TC5,
-	POWER_DOMAIN_AUX_TC6,
+	POWER_DOMAIN_AUX_G,
+	POWER_DOMAIN_AUX_H,
+	POWER_DOMAIN_AUX_I,
 	POWER_DOMAIN_AUX_IO_A,
-	POWER_DOMAIN_AUX_TBT1,
-	POWER_DOMAIN_AUX_TBT2,
-	POWER_DOMAIN_AUX_TBT3,
-	POWER_DOMAIN_AUX_TBT4,
-	POWER_DOMAIN_AUX_TBT5,
-	POWER_DOMAIN_AUX_TBT6,
+	POWER_DOMAIN_AUX_C_TBT,
+	POWER_DOMAIN_AUX_D_TBT,
+	POWER_DOMAIN_AUX_E_TBT,
+	POWER_DOMAIN_AUX_F_TBT,
+	POWER_DOMAIN_AUX_G_TBT,
+	POWER_DOMAIN_AUX_H_TBT,
+	POWER_DOMAIN_AUX_I_TBT,
 	POWER_DOMAIN_GMBUS,
 	POWER_DOMAIN_MODESET,
 	POWER_DOMAIN_GT_IRQ,
@@ -269,8 +258,7 @@ void intel_display_power_suspend(struct drm_i915_private *i915);
 void intel_display_power_resume(struct drm_i915_private *i915);
 
 const char *
-intel_display_power_domain_str(struct drm_i915_private *i915,
-			       enum intel_display_power_domain domain);
+intel_display_power_domain_str(enum intel_display_power_domain domain);
 
 bool intel_display_power_is_enabled(struct drm_i915_private *dev_priv,
 				    enum intel_display_power_domain domain);
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 5c1a2b1e7d34..5e81c4fc13ae 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2365,8 +2365,7 @@ static int i915_power_domain_info(struct seq_file *m, void *unused)
 
 		for_each_power_domain(power_domain, power_well->desc->domains)
 			seq_printf(m, "  %-23s %d\n",
-				 intel_display_power_domain_str(dev_priv,
-								power_domain),
+				 intel_display_power_domain_str(power_domain),
 				 power_domains->domain_use_count[power_domain]);
 	}
 
-- 
cgit v1.2.3


From 0f7dc62068bb2b929e213e759dba1eb038448a5c Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 26 Aug 2019 08:21:27 +0100
Subject: drm/i915: Protect our local workers against I915_FENCE_TIMEOUT

Trust our own workers to not cause unnecessary delays and disable the
automatic timeout on their asynchronous fence waits. (Along the same
lines that we trust our own requests to complete eventually, if
necessary by force.)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190826072149.9447-6-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_request.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 18865ce04e13..754a78364a63 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -924,7 +924,7 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 			ret = i915_request_await_request(rq, to_request(fence));
 		else
 			ret = i915_sw_fence_await_dma_fence(&rq->submit, fence,
-							    I915_FENCE_TIMEOUT,
+							    fence->context ? I915_FENCE_TIMEOUT : 0,
 							    I915_FENCE_GFP);
 		if (ret < 0)
 			return ret;
-- 
cgit v1.2.3


From 9770f22077981cac2bd2f4dd6caa6269892cd3f7 Mon Sep 17 00:00:00 2001
From: Madhumitha Tolakanahalli Pradeep
 <madhumitha.tolakanahalli.pradeep@intel.com>
Date: Thu, 22 Aug 2019 17:46:55 -0700
Subject: drm/i915/tgl: Enabling DSC on Pipe A for TGL

DSC was not supported on Pipe A for previous platforms. Tigerlake onwards,
all the pipes support DSC. Hence, the DSC and FEC restriction on
Pipe A needs to be removed.

v2: Changes in the logic around removing the restriction around
    Pipe A (Manasi, Lucas)

Cc: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Madhumitha Tolakanahalli Pradeep <madhumitha.tolakanahalli.pradeep@intel.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823004655.28905-1-madhumitha.tolakanahalli.pradeep@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index f74594d8d9df..c9986c7a3f5b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1737,8 +1737,14 @@ static bool intel_dp_source_supports_fec(struct intel_dp *intel_dp,
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 
-	return INTEL_GEN(dev_priv) >= 11 &&
-		pipe_config->cpu_transcoder != TRANSCODER_A;
+	/* On TGL, FEC is supported on all Pipes */
+	if (INTEL_GEN(dev_priv) >= 12)
+		return true;
+
+	if (IS_GEN(dev_priv, 11) && pipe_config->cpu_transcoder != TRANSCODER_A)
+		return true;
+
+	return false;
 }
 
 static bool intel_dp_supports_fec(struct intel_dp *intel_dp,
@@ -1753,8 +1759,15 @@ static bool intel_dp_source_supports_dsc(struct intel_dp *intel_dp,
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 
-	return INTEL_GEN(dev_priv) >= 10 &&
-		pipe_config->cpu_transcoder != TRANSCODER_A;
+	/* On TGL, DSC is supported on all Pipes */
+	if (INTEL_GEN(dev_priv) >= 12)
+		return true;
+
+	if (INTEL_GEN(dev_priv) >= 10 &&
+	    pipe_config->cpu_transcoder != TRANSCODER_A)
+		return true;
+
+	return false;
 }
 
 static bool intel_dp_supports_dsc(struct intel_dp *intel_dp,
-- 
cgit v1.2.3


From 074c77e3ec636fa5e2664e3c79aba397ec569761 Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Tue, 27 Aug 2019 01:45:16 -0700
Subject: drm/i915/tgl: Gen-12 display loses Yf tiling and legacy CCS support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Yf tiling was removed in gen-12, so do not expose Yf modifiers to user
space. Gen-12 display also is incompatible with pre-gen12 Y-tiled
CCS, so do not expose I915_FORMAT_MOD_Y_TILED_CCS.

v2: Rebase to carry forward recently added gen11 formats.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190827084516.6748-1-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/display/intel_sprite.c | 86 +++++++++++++++++++++++++++--
 1 file changed, 80 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index dea63be1964f..8ca2fbc2af1d 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -2157,6 +2157,13 @@ static const u64 skl_plane_format_modifiers_ccs[] = {
 	DRM_FORMAT_MOD_INVALID
 };
 
+static const u64 gen12_plane_format_modifiers_noccs[] = {
+	I915_FORMAT_MOD_Y_TILED,
+	I915_FORMAT_MOD_X_TILED,
+	DRM_FORMAT_MOD_LINEAR,
+	DRM_FORMAT_MOD_INVALID
+};
+
 static bool g4x_sprite_format_mod_supported(struct drm_plane *_plane,
 					    u32 format, u64 modifier)
 {
@@ -2305,6 +2312,55 @@ static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
 	}
 }
 
+static bool gen12_plane_format_mod_supported(struct drm_plane *_plane,
+					     u32 format, u64 modifier)
+{
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+	case I915_FORMAT_MOD_Y_TILED:
+		break;
+	default:
+		return false;
+	}
+
+	switch (format) {
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_ABGR8888:
+	case DRM_FORMAT_RGB565:
+	case DRM_FORMAT_XRGB2101010:
+	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_YUYV:
+	case DRM_FORMAT_YVYU:
+	case DRM_FORMAT_UYVY:
+	case DRM_FORMAT_VYUY:
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_P010:
+	case DRM_FORMAT_P012:
+	case DRM_FORMAT_P016:
+	case DRM_FORMAT_XVYU2101010:
+	case DRM_FORMAT_C8:
+	case DRM_FORMAT_XBGR16161616F:
+	case DRM_FORMAT_ABGR16161616F:
+	case DRM_FORMAT_XRGB16161616F:
+	case DRM_FORMAT_ARGB16161616F:
+	case DRM_FORMAT_Y210:
+	case DRM_FORMAT_Y212:
+	case DRM_FORMAT_Y216:
+	case DRM_FORMAT_XVYU12_16161616:
+	case DRM_FORMAT_XVYU16161616:
+		if (modifier == DRM_FORMAT_MOD_LINEAR ||
+		    modifier == I915_FORMAT_MOD_X_TILED ||
+		    modifier == I915_FORMAT_MOD_Y_TILED)
+			return true;
+		/* fall through */
+	default:
+		return false;
+	}
+}
+
 static const struct drm_plane_funcs g4x_sprite_funcs = {
 	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
@@ -2341,6 +2397,15 @@ static const struct drm_plane_funcs skl_plane_funcs = {
 	.format_mod_supported = skl_plane_format_mod_supported,
 };
 
+static const struct drm_plane_funcs gen12_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = gen12_plane_format_mod_supported,
+};
+
 static bool skl_plane_has_fbc(struct drm_i915_private *dev_priv,
 			      enum pipe pipe, enum plane_id plane_id)
 {
@@ -2429,6 +2494,7 @@ struct intel_plane *
 skl_universal_plane_create(struct drm_i915_private *dev_priv,
 			   enum pipe pipe, enum plane_id plane_id)
 {
+	static const struct drm_plane_funcs *plane_funcs;
 	struct intel_plane *plane;
 	enum drm_plane_type plane_type;
 	unsigned int supported_rotations;
@@ -2471,11 +2537,19 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv,
 		formats = skl_get_plane_formats(dev_priv, pipe,
 						plane_id, &num_formats);
 
-	plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe, plane_id);
-	if (plane->has_ccs)
-		modifiers = skl_plane_format_modifiers_ccs;
-	else
-		modifiers = skl_plane_format_modifiers_noccs;
+	if (INTEL_GEN(dev_priv) >= 12) {
+		/* TODO: Implement support for gen-12 CCS modifiers */
+		plane->has_ccs = false;
+		modifiers = gen12_plane_format_modifiers_noccs;
+		plane_funcs = &gen12_plane_funcs;
+	} else {
+		plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe, plane_id);
+		if (plane->has_ccs)
+			modifiers = skl_plane_format_modifiers_ccs;
+		else
+			modifiers = skl_plane_format_modifiers_noccs;
+		plane_funcs = &skl_plane_funcs;
+	}
 
 	if (plane_id == PLANE_PRIMARY)
 		plane_type = DRM_PLANE_TYPE_PRIMARY;
@@ -2485,7 +2559,7 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv,
 	possible_crtcs = BIT(pipe);
 
 	ret = drm_universal_plane_init(&dev_priv->drm, &plane->base,
-				       possible_crtcs, &skl_plane_funcs,
+				       possible_crtcs, plane_funcs,
 				       formats, num_formats, modifiers,
 				       plane_type,
 				       "plane %d%c", plane_id + 1,
-- 
cgit v1.2.3


From 99d7a74110ef4c97f921b90fa8d897c6d71610a9 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Fri, 23 Aug 2019 01:20:39 -0700
Subject: drm/i915/tgl: PSR link standby is not supported anymore
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

According to BSpc if link standby is set on TGL+, PSR will not be
enabled. Vendors should not use panels that requires link standby and
even if they do, panel should assert a PSR error that will cause PSR to
be disabled.

BSpec: 50434
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Anshuman Gupta <anshuman.gupta@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190823082055.5992-8-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 2af3826121fa..629b8b98a97f 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1283,8 +1283,8 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		/* HSW and BDW require workarounds that we don't implement. */
 		dev_priv->psr.link_standby = false;
-	else
-		/* For new platforms let's respect VBT back again */
+	else if (INTEL_GEN(dev_priv) < 12)
+		/* For new platforms up to TGL let's respect VBT back again */
 		dev_priv->psr.link_standby = dev_priv->vbt.psr.full_link;
 
 	INIT_WORK(&dev_priv->psr.work, intel_psr_work);
-- 
cgit v1.2.3


From e7b6affd0baef7b3c5e2acd94236093dcf437105 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 29 Aug 2019 18:08:48 +0100
Subject: drm/i915/selftests: cond_resched() within the longer buddy tests

Let the scheduler have a breather in between passes of the longer buddy
tests. Important if we are running under kasan etc and this takes far
longer than usual!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190829170848.969-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_buddy.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_buddy.c b/drivers/gpu/drm/i915/selftests/i915_buddy.c
index 23f784eae1e7..1b856bae67b5 100644
--- a/drivers/gpu/drm/i915/selftests/i915_buddy.c
+++ b/drivers/gpu/drm/i915/selftests/i915_buddy.c
@@ -375,6 +375,8 @@ retry:
 
 		if (err)
 			break;
+
+		cond_resched();
 	}
 
 	if (err == -ENOMEM)
@@ -687,6 +689,8 @@ static int igt_buddy_alloc_range(void *arg)
 		rem -= size;
 		if (!rem)
 			break;
+
+		cond_resched();
 	}
 
 	if (err == -ENOMEM)
-- 
cgit v1.2.3


From 9be02fde93e5b564663f10a48f19159fba718e3d Mon Sep 17 00:00:00 2001
From: Fernando Pacheco <fernando.pacheco@intel.com>
Date: Thu, 29 Aug 2019 10:41:53 -0700
Subject: drm/i915/uc: Extract common code from GuC stop/disable comm

During normal driver unload we attempt to disable GuC communication
while it is currently stopped. This results in a nop'd call to
intel_guc_ct_disable within guc_disable_communication because
stop/disable rely on the same flag to prevent further comms with CT.

We can avoid the call to disable and still leave communication in a
satisfactory state by extracting a set of shared steps from stop/disable.
This set can include guc_disable_interrupts as we do not require the
single caller of guc_stop_communication to be atomic:
"drm/i915/selftests: Fixup atomic reset checking".

This situation (stop -> disable) only occurs during intel_uc_fini_hw,
so during fini, call guc_disable_communication only if currently enabled.
The symmetric calls to enable/disable remain unmodified for all other
scenarios.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=110943
Signed-off-by: Fernando Pacheco <fernando.pacheco@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190829174154.14675-1-fernando.pacheco@intel.com
---
 drivers/gpu/drm/i915/gt/uc/intel_uc.c | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 71ee7ab035cc..29a9eec60d2e 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -224,17 +224,7 @@ static int guc_enable_communication(struct intel_guc *guc)
 	return 0;
 }
 
-static void guc_stop_communication(struct intel_guc *guc)
-{
-	intel_guc_ct_stop(&guc->ct);
-
-	guc->send = intel_guc_send_nop;
-	guc->handler = intel_guc_to_host_event_handler_nop;
-
-	guc_clear_mmio_msg(guc);
-}
-
-static void guc_disable_communication(struct intel_guc *guc)
+static void __guc_stop_communication(struct intel_guc *guc)
 {
 	/*
 	 * Events generated during or after CT disable are logged by guc in
@@ -247,6 +237,20 @@ static void guc_disable_communication(struct intel_guc *guc)
 
 	guc->send = intel_guc_send_nop;
 	guc->handler = intel_guc_to_host_event_handler_nop;
+}
+
+static void guc_stop_communication(struct intel_guc *guc)
+{
+	intel_guc_ct_stop(&guc->ct);
+
+	__guc_stop_communication(guc);
+
+	DRM_INFO("GuC communication stopped\n");
+}
+
+static void guc_disable_communication(struct intel_guc *guc)
+{
+	__guc_stop_communication(guc);
 
 	intel_guc_ct_disable(&guc->ct);
 
@@ -537,7 +541,9 @@ void intel_uc_fini_hw(struct intel_uc *uc)
 	if (intel_uc_supports_guc_submission(uc))
 		intel_guc_submission_disable(guc);
 
-	guc_disable_communication(guc);
+	if (guc_communication_enabled(guc))
+		guc_disable_communication(guc);
+
 	__uc_sanitize(uc);
 }
 
-- 
cgit v1.2.3


From 31444afb460ee627cb7800acee46548449c52368 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Thu, 29 Aug 2019 21:19:19 +0100
Subject: drm/i915: s/for_each_sgt_dma/for_each_sgt_daddr/

The sg_table for our backing store might contain addresses from
stolen-memory or in the future local-memory, at which point this is no
longer a dma-iterator. As a consequence we should now break on NULL
iter.sgp, instead of dmap == 0 which is considered an invalid dma
address.

As a bonus, gcc much prefers this construct,

  Function                                     old     new   delta
  gen8_ggtt_insert_entries                     211     192     -19
  gen6_ggtt_insert_entries                     292     262     -30
  i915_error_object_create                     996     954     -42

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190829201919.21493-1-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/i915_gem_gtt.c       | 4 ++--
 drivers/gpu/drm/i915/i915_gem_gtt.h       | 4 ++--
 drivers/gpu/drm/i915/i915_gpu_error.c     | 2 +-
 drivers/gpu/drm/i915/i915_scatterlist.h   | 8 ++++----
 drivers/gpu/drm/i915/selftests/i915_vma.c | 2 +-
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index c94dfa562247..3c50cea76dc5 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2208,7 +2208,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 
 	gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm;
 	gtt_entries += vma->node.start / I915_GTT_PAGE_SIZE;
-	for_each_sgt_dma(addr, sgt_iter, vma->pages)
+	for_each_sgt_daddr(addr, sgt_iter, vma->pages)
 		gen8_set_pte(gtt_entries++, pte_encode | addr);
 
 	/*
@@ -2249,7 +2249,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 	unsigned int i = vma->node.start / I915_GTT_PAGE_SIZE;
 	struct sgt_iter iter;
 	dma_addr_t addr;
-	for_each_sgt_dma(addr, iter, vma->pages)
+	for_each_sgt_daddr(addr, iter, vma->pages)
 		iowrite32(vm->pte_encode(addr, level, flags), &entries[i++]);
 
 	/*
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index b97a47fc7a68..576f6fb95d13 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -148,8 +148,8 @@ typedef u64 gen8_pte_t;
 #define GEN8_PDE_IPS_64K BIT(11)
 #define GEN8_PDE_PS_2M   BIT(7)
 
-#define for_each_sgt_dma(__dmap, __iter, __sgt) \
-	__for_each_sgt_dma(__dmap, __iter, __sgt, I915_GTT_PAGE_SIZE)
+#define for_each_sgt_daddr(__dp, __iter, __sgt) \
+	__for_each_sgt_daddr(__dp, __iter, __sgt, I915_GTT_PAGE_SIZE)
 
 struct intel_remapped_plane_info {
 	/* in gtt pages */
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 4aff342b8944..3ccf7fd9307f 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -990,7 +990,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 	dst->unused = 0;
 
 	ret = -EINVAL;
-	for_each_sgt_dma(dma, iter, vma->pages) {
+	for_each_sgt_daddr(dma, iter, vma->pages) {
 		void __iomem *s;
 
 		ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0);
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h
index 6617963df9ed..b7b59328cb76 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.h
+++ b/drivers/gpu/drm/i915/i915_scatterlist.h
@@ -67,15 +67,15 @@ static inline struct scatterlist *__sg_next(struct scatterlist *sg)
 }
 
 /**
- * __for_each_sgt_dma - iterate over the DMA addresses of the given sg_table
- * @__dmap:	DMA address (output)
+ * __for_each_sgt_daddr - iterate over the device addresses of the given sg_table
+ * @__dp:	Device address (output)
  * @__iter:	'struct sgt_iter' (iterator state, internal)
  * @__sgt:	sg_table to iterate over (input)
  * @__step:	step size
  */
-#define __for_each_sgt_dma(__dmap, __iter, __sgt, __step)		\
+#define __for_each_sgt_daddr(__dp, __iter, __sgt, __step)		\
 	for ((__iter) = __sgt_iter((__sgt)->sgl, true);			\
-	     ((__dmap) = (__iter).dma + (__iter).curr);			\
+	     ((__dp) = (__iter).dma + (__iter).curr), (__iter).sgp;	\
 	     (((__iter).curr += (__step)) >= (__iter).max) ?		\
 	     (__iter) = __sgt_iter(__sg_next((__iter).sgp), true), 0 : 0)
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index a5bec0a4cdcc..97752deecccb 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -623,7 +623,7 @@ static bool assert_partial(struct drm_i915_gem_object *obj,
 	struct sgt_iter sgt;
 	dma_addr_t dma;
 
-	for_each_sgt_dma(dma, sgt, vma->pages) {
+	for_each_sgt_daddr(dma, sgt, vma->pages) {
 		dma_addr_t src;
 
 		if (!size) {
-- 
cgit v1.2.3


From 0c84127102ee240e3039d6e78a3dba0afff2f810 Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Tue, 27 Aug 2019 15:17:34 -0700
Subject: drm/i915/display: Rename update_crtcs() to commit_modeset_enables()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch has no functional changes. This just renames the update_crtcs()
hooks to commit_modeset_enables() to match the drm_atomic helper naming
conventions.

v2:
* Rebase on drm-tip

Suggested-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190827221735.29351-2-manasi.d.navare@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 10 +++++-----
 drivers/gpu/drm/i915/i915_drv.h              |  2 +-
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 4773832b0f49..85183ef80c97 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -13743,7 +13743,7 @@ static void intel_update_crtc(struct intel_crtc *crtc,
 	intel_finish_crtc_commit(state, crtc);
 }
 
-static void intel_update_crtcs(struct intel_atomic_state *state)
+static void intel_commit_modeset_enables(struct intel_atomic_state *state)
 {
 	struct intel_crtc *crtc;
 	struct intel_crtc_state *old_crtc_state, *new_crtc_state;
@@ -13758,7 +13758,7 @@ static void intel_update_crtcs(struct intel_atomic_state *state)
 	}
 }
 
-static void skl_update_crtcs(struct intel_atomic_state *state)
+static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	struct intel_crtc *crtc;
@@ -13999,7 +13999,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 		intel_encoders_update_prepare(state);
 
 	/* Now enable the clocks, plane, pipe, and connectors that we set up. */
-	dev_priv->display.update_crtcs(state);
+	dev_priv->display.commit_modeset_enables(state);
 
 	if (state->modeset) {
 		intel_encoders_update_complete(state);
@@ -15906,9 +15906,9 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
 	}
 
 	if (INTEL_GEN(dev_priv) >= 9)
-		dev_priv->display.update_crtcs = skl_update_crtcs;
+		dev_priv->display.commit_modeset_enables = skl_commit_modeset_enables;
 	else
-		dev_priv->display.update_crtcs = intel_update_crtcs;
+		dev_priv->display.commit_modeset_enables = intel_commit_modeset_enables;
 }
 
 static i915_reg_t i915_vgacntrl_reg(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b42651a387d9..75a42e8df67e 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -288,7 +288,7 @@ struct drm_i915_display_funcs {
 			    struct intel_atomic_state *old_state);
 	void (*crtc_disable)(struct intel_crtc_state *old_crtc_state,
 			     struct intel_atomic_state *old_state);
-	void (*update_crtcs)(struct intel_atomic_state *state);
+	void (*commit_modeset_enables)(struct intel_atomic_state *state);
 	void (*audio_codec_enable)(struct intel_encoder *encoder,
 				   const struct intel_crtc_state *crtc_state,
 				   const struct drm_connector_state *conn_state);
-- 
cgit v1.2.3


From 66d9cec8a6c9f3eb1d81507d5f045e28272359fb Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Wed, 28 Aug 2019 15:47:01 -0700
Subject: drm/i915/display: Move the commit_tail() disable sequence to separate
 function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Create a new function intel_commit_modeset_disables() consistent
with the naming in drm atomic helpers and similar to the enable function.
This helps better organize the disable sequence in atomic_commit_tail()

No functional change

v4:
* Do not create a function pointer, just a function (Maarten)
v3:
* Rebase (Manasi)
v2:
* Create a helper for old_crtc_state disables (Lucas)

Suggested-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190828224701.422-1-manasi.d.navare@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 92 ++++++++++++++++++----------
 drivers/gpu/drm/i915/i915_drv.h              |  1 +
 2 files changed, 59 insertions(+), 34 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 85183ef80c97..b38d842ff6ec 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -13743,6 +13743,61 @@ static void intel_update_crtc(struct intel_crtc *crtc,
 	intel_finish_crtc_commit(state, crtc);
 }
 
+static void intel_old_crtc_state_disables(struct intel_atomic_state *state,
+					  struct intel_crtc_state *old_crtc_state,
+					  struct intel_crtc_state *new_crtc_state,
+					  struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+
+	intel_crtc_disable_planes(state, crtc);
+
+	/*
+	 * We need to disable pipe CRC before disabling the pipe,
+	 * or we race against vblank off.
+	 */
+	intel_crtc_disable_pipe_crc(crtc);
+
+	dev_priv->display.crtc_disable(old_crtc_state, state);
+	crtc->active = false;
+	intel_fbc_disable(crtc);
+	intel_disable_shared_dpll(old_crtc_state);
+
+	/*
+	 * Underruns don't always raise interrupts,
+	 * so check manually.
+	 */
+	intel_check_cpu_fifo_underruns(dev_priv);
+	intel_check_pch_fifo_underruns(dev_priv);
+
+	/* FIXME unify this for all platforms */
+	if (!new_crtc_state->base.active &&
+	    !HAS_GMCH(dev_priv) &&
+	    dev_priv->display.initial_watermarks)
+		dev_priv->display.initial_watermarks(state,
+						     new_crtc_state);
+}
+
+static void intel_commit_modeset_disables(struct intel_atomic_state *state)
+{
+	struct intel_crtc_state *new_crtc_state, *old_crtc_state;
+	struct intel_crtc *crtc;
+	int i;
+
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+		if (!needs_modeset(new_crtc_state))
+			continue;
+
+		intel_pre_plane_update(old_crtc_state, new_crtc_state);
+
+		if (old_crtc_state->base.active)
+			intel_old_crtc_state_disables(state,
+						      old_crtc_state,
+						      new_crtc_state,
+						      crtc);
+	}
+}
+
 static void intel_commit_modeset_enables(struct intel_atomic_state *state)
 {
 	struct intel_crtc *crtc;
@@ -13923,42 +13978,10 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 			put_domains[crtc->pipe] =
 				modeset_get_crtc_power_domains(new_crtc_state);
 		}
-
-		if (!needs_modeset(new_crtc_state))
-			continue;
-
-		intel_pre_plane_update(old_crtc_state, new_crtc_state);
-
-		if (old_crtc_state->base.active) {
-			intel_crtc_disable_planes(state, crtc);
-
-			/*
-			 * We need to disable pipe CRC before disabling the pipe,
-			 * or we race against vblank off.
-			 */
-			intel_crtc_disable_pipe_crc(crtc);
-
-			dev_priv->display.crtc_disable(old_crtc_state, state);
-			crtc->active = false;
-			intel_fbc_disable(crtc);
-			intel_disable_shared_dpll(old_crtc_state);
-
-			/*
-			 * Underruns don't always raise
-			 * interrupts, so check manually.
-			 */
-			intel_check_cpu_fifo_underruns(dev_priv);
-			intel_check_pch_fifo_underruns(dev_priv);
-
-			/* FIXME unify this for all platforms */
-			if (!new_crtc_state->base.active &&
-			    !HAS_GMCH(dev_priv) &&
-			    dev_priv->display.initial_watermarks)
-				dev_priv->display.initial_watermarks(state,
-								     new_crtc_state);
-		}
 	}
 
+	intel_commit_modeset_disables(state);
+
 	/* FIXME: Eventually get rid of our crtc->config pointer */
 	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i)
 		crtc->config = new_crtc_state;
@@ -15909,6 +15932,7 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
 		dev_priv->display.commit_modeset_enables = skl_commit_modeset_enables;
 	else
 		dev_priv->display.commit_modeset_enables = intel_commit_modeset_enables;
+
 }
 
 static i915_reg_t i915_vgacntrl_reg(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 75a42e8df67e..db7480831e52 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -289,6 +289,7 @@ struct drm_i915_display_funcs {
 	void (*crtc_disable)(struct intel_crtc_state *old_crtc_state,
 			     struct intel_atomic_state *old_state);
 	void (*commit_modeset_enables)(struct intel_atomic_state *state);
+	void (*commit_modeset_disables)(struct intel_atomic_state *state);
 	void (*audio_codec_enable)(struct intel_encoder *encoder,
 				   const struct intel_crtc_state *crtc_state,
 				   const struct drm_connector_state *conn_state);
-- 
cgit v1.2.3


From 11988e393813f520974f69bf0e55c367a1cbac48 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 29 Aug 2019 09:11:15 +0100
Subject: drm/i915/execlists: Try rearranging breadcrumb flush

The addition of the DC_FLUSH failed to ensure sanctity of the post-sync
write as CI immediately got a completion CS-event before the breadcrumb
was coherent. So let's try the other idea of moving the post-sync write
into the CS_STALL.

References: https://bugs.freedesktop.org/show_bug.cgi?id=111514
References: e8f6b4952ec5 ("drm/i915/execlists: Flush the post-sync breadcrumb write harder")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190829081150.10271-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 171d5205962c..7d460b1842dd 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2915,20 +2915,18 @@ static u32 *gen8_emit_fini_breadcrumb(struct i915_request *request, u32 *cs)
 
 static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 {
+	cs = gen8_emit_pipe_control(cs,
+				    PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+				    PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+				    PIPE_CONTROL_DC_FLUSH_ENABLE,
+				    0);
+
+	/* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */
 	cs = gen8_emit_ggtt_write_rcs(cs,
 				      request->fence.seqno,
 				      request->timeline->hwsp_offset,
-				      PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
-				      PIPE_CONTROL_DEPTH_CACHE_FLUSH |
-				      PIPE_CONTROL_DC_FLUSH_ENABLE);
-
-	/* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */
-	/* XXX DC_FLUSH for post-sync write? (cf early context-switch bug) */
-	cs = gen8_emit_pipe_control(cs,
-				    PIPE_CONTROL_FLUSH_ENABLE |
-				    PIPE_CONTROL_DC_FLUSH_ENABLE |
-				    PIPE_CONTROL_CS_STALL,
-				    0);
+				      PIPE_CONTROL_FLUSH_ENABLE |
+				      PIPE_CONTROL_CS_STALL);
 
 	return gen8_emit_fini_breadcrumb_footer(request, cs);
 }
-- 
cgit v1.2.3


From 0dcceb35a13de07d8c28305b69a33b339c7eba0a Mon Sep 17 00:00:00 2001
From: Ramalingam C <ramalingam.c@intel.com>
Date: Wed, 28 Aug 2019 22:12:11 +0530
Subject: drm/i915: mei_hdcp: I915 sends ddi index as per ME FW

I915 converts it's port value into ddi index defiend by ME FW
and pass it as a member of hdcp_port_data structure.

Hence expose the enum mei_fw_ddi to I915 through
i915_mei_interface.h.

v2:
  Copyright years are bumped [Tomas]

Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Acked-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Uma Shankar <uma.shankar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190828164216.405-2-ramalingam.c@intel.com
---
 drivers/gpu/drm/i915/display/intel_hdcp.c | 17 +++++++++++++++-
 drivers/misc/mei/hdcp/mei_hdcp.c          | 34 ++++++++++---------------------
 drivers/misc/mei/hdcp/mei_hdcp.h          | 12 -----------
 include/drm/i915_mei_hdcp_interface.h     | 18 +++++++++++++---
 4 files changed, 42 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index 6ec5ceeab601..e8b04cc8fcb1 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -1,9 +1,11 @@
 /* SPDX-License-Identifier: MIT */
 /*
  * Copyright (C) 2017 Google, Inc.
+ * Copyright _ 2017-2019, Intel Corporation.
  *
  * Authors:
  * Sean Paul <seanpaul@chromium.org>
+ * Ramalingam C <ramalingam.c@intel.com>
  */
 
 #include <linux/component.h>
@@ -1749,13 +1751,26 @@ static const struct component_ops i915_hdcp_component_ops = {
 	.unbind = i915_hdcp_component_unbind,
 };
 
+static inline
+enum mei_fw_ddi intel_get_mei_fw_ddi_index(enum port port)
+{
+	switch (port) {
+	case PORT_A:
+		return MEI_DDI_A;
+	case PORT_B ... PORT_F:
+		return (enum mei_fw_ddi)port;
+	default:
+		return MEI_DDI_INVALID_PORT;
+	}
+}
+
 static inline int initialize_hdcp_port_data(struct intel_connector *connector,
 					    const struct intel_hdcp_shim *shim)
 {
 	struct intel_hdcp *hdcp = &connector->hdcp;
 	struct hdcp_port_data *data = &hdcp->port_data;
 
-	data->port = connector->encoder->port;
+	data->fw_ddi = intel_get_mei_fw_ddi_index(connector->encoder->port);
 	data->port_type = (u8)HDCP_PORT_TYPE_INTEGRATED;
 	data->protocol = (u8)shim->protocol;
 
diff --git a/drivers/misc/mei/hdcp/mei_hdcp.c b/drivers/misc/mei/hdcp/mei_hdcp.c
index c681f6fab342..3638c77eba26 100644
--- a/drivers/misc/mei/hdcp/mei_hdcp.c
+++ b/drivers/misc/mei/hdcp/mei_hdcp.c
@@ -27,18 +27,6 @@
 
 #include "mei_hdcp.h"
 
-static inline u8 mei_get_ddi_index(enum port port)
-{
-	switch (port) {
-	case PORT_A:
-		return MEI_DDI_A;
-	case PORT_B ... PORT_F:
-		return (u8)port;
-	default:
-		return MEI_DDI_INVALID_PORT;
-	}
-}
-
 /**
  * mei_hdcp_initiate_session() - Initiate a Wired HDCP2.2 Tx Session in ME FW
  * @dev: device corresponding to the mei_cl_device
@@ -69,7 +57,7 @@ mei_hdcp_initiate_session(struct device *dev, struct hdcp_port_data *data,
 				WIRED_CMD_BUF_LEN_INITIATE_HDCP2_SESSION_IN;
 
 	session_init_in.port.integrated_port_type = data->port_type;
-	session_init_in.port.physical_port = mei_get_ddi_index(data->port);
+	session_init_in.port.physical_port = (u8)data->fw_ddi;
 	session_init_in.protocol = data->protocol;
 
 	byte = mei_cldev_send(cldev, (u8 *)&session_init_in,
@@ -138,7 +126,7 @@ mei_hdcp_verify_receiver_cert_prepare_km(struct device *dev,
 				WIRED_CMD_BUF_LEN_VERIFY_RECEIVER_CERT_IN;
 
 	verify_rxcert_in.port.integrated_port_type = data->port_type;
-	verify_rxcert_in.port.physical_port = mei_get_ddi_index(data->port);
+	verify_rxcert_in.port.physical_port = (u8)data->fw_ddi;
 
 	verify_rxcert_in.cert_rx = rx_cert->cert_rx;
 	memcpy(verify_rxcert_in.r_rx, &rx_cert->r_rx, HDCP_2_2_RRX_LEN);
@@ -208,7 +196,7 @@ mei_hdcp_verify_hprime(struct device *dev, struct hdcp_port_data *data,
 	send_hprime_in.header.buffer_len = WIRED_CMD_BUF_LEN_AKE_SEND_HPRIME_IN;
 
 	send_hprime_in.port.integrated_port_type = data->port_type;
-	send_hprime_in.port.physical_port = mei_get_ddi_index(data->port);
+	send_hprime_in.port.physical_port = (u8)data->fw_ddi;
 
 	memcpy(send_hprime_in.h_prime, rx_hprime->h_prime,
 	       HDCP_2_2_H_PRIME_LEN);
@@ -265,7 +253,7 @@ mei_hdcp_store_pairing_info(struct device *dev, struct hdcp_port_data *data,
 					WIRED_CMD_BUF_LEN_SEND_PAIRING_INFO_IN;
 
 	pairing_info_in.port.integrated_port_type = data->port_type;
-	pairing_info_in.port.physical_port = mei_get_ddi_index(data->port);
+	pairing_info_in.port.physical_port = (u8)data->fw_ddi;
 
 	memcpy(pairing_info_in.e_kh_km, pairing_info->e_kh_km,
 	       HDCP_2_2_E_KH_KM_LEN);
@@ -323,7 +311,7 @@ mei_hdcp_initiate_locality_check(struct device *dev,
 	lc_init_in.header.buffer_len = WIRED_CMD_BUF_LEN_INIT_LOCALITY_CHECK_IN;
 
 	lc_init_in.port.integrated_port_type = data->port_type;
-	lc_init_in.port.physical_port = mei_get_ddi_index(data->port);
+	lc_init_in.port.physical_port = (u8)data->fw_ddi;
 
 	byte = mei_cldev_send(cldev, (u8 *)&lc_init_in, sizeof(lc_init_in));
 	if (byte < 0) {
@@ -378,7 +366,7 @@ mei_hdcp_verify_lprime(struct device *dev, struct hdcp_port_data *data,
 					WIRED_CMD_BUF_LEN_VALIDATE_LOCALITY_IN;
 
 	verify_lprime_in.port.integrated_port_type = data->port_type;
-	verify_lprime_in.port.physical_port = mei_get_ddi_index(data->port);
+	verify_lprime_in.port.physical_port = (u8)data->fw_ddi;
 
 	memcpy(verify_lprime_in.l_prime, rx_lprime->l_prime,
 	       HDCP_2_2_L_PRIME_LEN);
@@ -435,7 +423,7 @@ static int mei_hdcp_get_session_key(struct device *dev,
 	get_skey_in.header.buffer_len = WIRED_CMD_BUF_LEN_GET_SESSION_KEY_IN;
 
 	get_skey_in.port.integrated_port_type = data->port_type;
-	get_skey_in.port.physical_port = mei_get_ddi_index(data->port);
+	get_skey_in.port.physical_port = (u8)data->fw_ddi;
 
 	byte = mei_cldev_send(cldev, (u8 *)&get_skey_in, sizeof(get_skey_in));
 	if (byte < 0) {
@@ -499,7 +487,7 @@ mei_hdcp_repeater_check_flow_prepare_ack(struct device *dev,
 					WIRED_CMD_BUF_LEN_VERIFY_REPEATER_IN;
 
 	verify_repeater_in.port.integrated_port_type = data->port_type;
-	verify_repeater_in.port.physical_port = mei_get_ddi_index(data->port);
+	verify_repeater_in.port.physical_port = (u8)data->fw_ddi;
 
 	memcpy(verify_repeater_in.rx_info, rep_topology->rx_info,
 	       HDCP_2_2_RXINFO_LEN);
@@ -569,7 +557,7 @@ static int mei_hdcp_verify_mprime(struct device *dev,
 			WIRED_CMD_BUF_LEN_REPEATER_AUTH_STREAM_REQ_MIN_IN;
 
 	verify_mprime_in.port.integrated_port_type = data->port_type;
-	verify_mprime_in.port.physical_port = mei_get_ddi_index(data->port);
+	verify_mprime_in.port.physical_port = (u8)data->fw_ddi;
 
 	memcpy(verify_mprime_in.m_prime, stream_ready->m_prime,
 	       HDCP_2_2_MPRIME_LEN);
@@ -630,7 +618,7 @@ static int mei_hdcp_enable_authentication(struct device *dev,
 	enable_auth_in.header.buffer_len = WIRED_CMD_BUF_LEN_ENABLE_AUTH_IN;
 
 	enable_auth_in.port.integrated_port_type = data->port_type;
-	enable_auth_in.port.physical_port = mei_get_ddi_index(data->port);
+	enable_auth_in.port.physical_port = (u8)data->fw_ddi;
 	enable_auth_in.stream_type = data->streams[0].stream_type;
 
 	byte = mei_cldev_send(cldev, (u8 *)&enable_auth_in,
@@ -684,7 +672,7 @@ mei_hdcp_close_session(struct device *dev, struct hdcp_port_data *data)
 				WIRED_CMD_BUF_LEN_CLOSE_SESSION_IN;
 
 	session_close_in.port.integrated_port_type = data->port_type;
-	session_close_in.port.physical_port = mei_get_ddi_index(data->port);
+	session_close_in.port.physical_port = (u8)data->fw_ddi;
 
 	byte = mei_cldev_send(cldev, (u8 *)&session_close_in,
 			      sizeof(session_close_in));
diff --git a/drivers/misc/mei/hdcp/mei_hdcp.h b/drivers/misc/mei/hdcp/mei_hdcp.h
index e4b1cd54c853..e60282eb2d48 100644
--- a/drivers/misc/mei/hdcp/mei_hdcp.h
+++ b/drivers/misc/mei/hdcp/mei_hdcp.h
@@ -362,16 +362,4 @@ struct wired_cmd_repeater_auth_stream_req_out {
 	struct hdcp_cmd_header	header;
 	struct hdcp_port_id	port;
 } __packed;
-
-enum mei_fw_ddi {
-	MEI_DDI_INVALID_PORT = 0x0,
-
-	MEI_DDI_B = 1,
-	MEI_DDI_C,
-	MEI_DDI_D,
-	MEI_DDI_E,
-	MEI_DDI_F,
-	MEI_DDI_A = 7,
-	MEI_DDI_RANGE_END = MEI_DDI_A,
-};
 #endif /* __MEI_HDCP_H__ */
diff --git a/include/drm/i915_mei_hdcp_interface.h b/include/drm/i915_mei_hdcp_interface.h
index 8c344255146a..08670aa650d4 100644
--- a/include/drm/i915_mei_hdcp_interface.h
+++ b/include/drm/i915_mei_hdcp_interface.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: (GPL-2.0+) */
 /*
- * Copyright © 2017-2018 Intel Corporation
+ * Copyright © 2017-2019 Intel Corporation
  *
  * Authors:
  * Ramalingam C <ramalingam.c@intel.com>
@@ -42,9 +42,21 @@ enum hdcp_wired_protocol {
 	HDCP_PROTOCOL_DP
 };
 
+enum mei_fw_ddi {
+	MEI_DDI_INVALID_PORT = 0x0,
+
+	MEI_DDI_B = 1,
+	MEI_DDI_C,
+	MEI_DDI_D,
+	MEI_DDI_E,
+	MEI_DDI_F,
+	MEI_DDI_A = 7,
+	MEI_DDI_RANGE_END = MEI_DDI_A,
+};
+
 /**
  * struct hdcp_port_data - intel specific HDCP port data
- * @port: port index as per I915
+ * @fw_ddi: ddi index as per ME FW
  * @port_type: HDCP port type as per ME FW classification
  * @protocol: HDCP adaptation as per ME FW
  * @k: No of streams transmitted on a port. Only on DP MST this is != 1
@@ -56,7 +68,7 @@ enum hdcp_wired_protocol {
  *	     streams
  */
 struct hdcp_port_data {
-	enum port port;
+	enum mei_fw_ddi fw_ddi;
 	u8 port_type;
 	u8 protocol;
 	u16 k;
-- 
cgit v1.2.3


From 5b6030da28cd6d6f5d129d7039ea0db83bcee6cf Mon Sep 17 00:00:00 2001
From: Ramalingam C <ramalingam.c@intel.com>
Date: Wed, 28 Aug 2019 22:12:12 +0530
Subject: drm: Move port definition back to i915 header

We dont need the definition of the enum port outside I915, anymore.
Hence move enum port definition into I915 driver itself.

v2:
  intel_display.h is included in intel_hdcp.h
v3:
  enum port is declared in headers.
v4:
  commit msg is rephrased.
v5:
  copyright year is updated [Tomas]

Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Reviewed-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Uma Shankar <uma.shankar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190828164216.405-3-ramalingam.c@intel.com
---
 drivers/gpu/drm/i915/display/intel_bios.h    |  3 ++-
 drivers/gpu/drm/i915/display/intel_display.h | 20 +++++++++++++++++++-
 drivers/gpu/drm/i915/display/intel_dp.h      |  1 +
 drivers/gpu/drm/i915/display/intel_hdcp.h    |  1 +
 drivers/gpu/drm/i915/display/intel_hdmi.h    |  1 +
 drivers/gpu/drm/i915/display/intel_hotplug.h |  1 +
 drivers/gpu/drm/i915/display/intel_sdvo.h    |  1 +
 include/drm/i915_drm.h                       | 18 ------------------
 8 files changed, 26 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bios.h b/drivers/gpu/drm/i915/display/intel_bios.h
index 4969189e620f..98f064828a57 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.h
+++ b/drivers/gpu/drm/i915/display/intel_bios.h
@@ -1,5 +1,5 @@
 /*
- * Copyright © 2016 Intel Corporation
+ * Copyright © 2016-2019 Intel Corporation
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -35,6 +35,7 @@
 #include <drm/i915_drm.h>
 
 struct drm_i915_private;
+enum port;
 
 enum intel_backlight_type {
 	INTEL_BACKLIGHT_PMIC,
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 03321fb4a703..33fd523c4622 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -1,5 +1,5 @@
 /*
- * Copyright © 2006-2017 Intel Corporation
+ * Copyright © 2006-2019 Intel Corporation
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
@@ -182,6 +182,24 @@ enum plane_id {
 	for ((__p) = PLANE_PRIMARY; (__p) < I915_MAX_PLANES; (__p)++) \
 		for_each_if((__crtc)->plane_ids_mask & BIT(__p))
 
+enum port {
+	PORT_NONE = -1,
+
+	PORT_A = 0,
+	PORT_B,
+	PORT_C,
+	PORT_D,
+	PORT_E,
+	PORT_F,
+	PORT_G,
+	PORT_H,
+	PORT_I,
+
+	I915_MAX_PORTS
+};
+
+#define port_name(p) ((p) + 'A')
+
 /*
  * Ports identifier referenced from other drivers.
  * Expected to remain stable over time
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index 657bbb1f5ed0..e01d1f89409d 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -13,6 +13,7 @@
 #include "i915_reg.h"
 
 enum pipe;
+enum port;
 struct drm_connector_state;
 struct drm_encoder;
 struct drm_i915_private;
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.h b/drivers/gpu/drm/i915/display/intel_hdcp.h
index 13555b054930..59a2b40405cc 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.h
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.h
@@ -15,6 +15,7 @@ struct drm_connector_state;
 struct drm_i915_private;
 struct intel_connector;
 struct intel_hdcp_shim;
+enum port;
 
 void intel_hdcp_atomic_check(struct drm_connector *connector,
 			     struct drm_connector_state *old_state,
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.h b/drivers/gpu/drm/i915/display/intel_hdmi.h
index 106c2e0bc3c9..cf1ea5427639 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.h
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.h
@@ -23,6 +23,7 @@ struct intel_crtc_state;
 struct intel_hdmi;
 struct drm_connector_state;
 union hdmi_infoframe;
+enum port;
 
 void intel_hdmi_init(struct drm_i915_private *dev_priv, i915_reg_t hdmi_reg,
 		     enum port port);
diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.h b/drivers/gpu/drm/i915/display/intel_hotplug.h
index b0cd447b7fbc..087b5f57b321 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug.h
+++ b/drivers/gpu/drm/i915/display/intel_hotplug.h
@@ -13,6 +13,7 @@
 struct drm_i915_private;
 struct intel_connector;
 struct intel_encoder;
+enum port;
 
 void intel_hpd_poll_init(struct drm_i915_private *dev_priv);
 enum intel_hotplug_state intel_encoder_hotplug(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.h b/drivers/gpu/drm/i915/display/intel_sdvo.h
index c9e05bcdd141..a66f224aa17d 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.h
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.h
@@ -14,6 +14,7 @@
 
 struct drm_i915_private;
 enum pipe;
+enum port;
 
 bool intel_sdvo_port_enabled(struct drm_i915_private *dev_priv,
 			     i915_reg_t sdvo_reg, enum pipe *pipe);
diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index 23274cf92712..6722005884db 100644
--- a/include/drm/i915_drm.h
+++ b/include/drm/i915_drm.h
@@ -100,22 +100,4 @@ extern struct resource intel_graphics_stolen_res;
 #define INTEL_GEN11_BSM_DW1	0xc4
 #define   INTEL_BSM_MASK	(-(1u << 20))
 
-enum port {
-	PORT_NONE = -1,
-
-	PORT_A = 0,
-	PORT_B,
-	PORT_C,
-	PORT_D,
-	PORT_E,
-	PORT_F,
-	PORT_G,
-	PORT_H,
-	PORT_I,
-
-	I915_MAX_PORTS
-};
-
-#define port_name(p) ((p) + 'A')
-
 #endif				/* _I915_DRM_H_ */
-- 
cgit v1.2.3


From 807c71d59a1063badc8bf60ee71470c2ff4be1cc Mon Sep 17 00:00:00 2001
From: Ramalingam C <ramalingam.c@intel.com>
Date: Wed, 28 Aug 2019 22:12:13 +0530
Subject: drm: Extend I915 mei interface for transcoder info

I915 needs to send the index of the transcoder as per ME FW.

To support this, define enum mei_fw_tc and add as a member into
the struct hdcp_port_data.

v2:
  Typo in commit msg is fixed [Shashank]
v3:
  kdoc is added for mei_fw_tc [Tomas]
  s/MEI_TC_x/MEI_TRANSCODER_x

Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Tomas Winkler <tomas.winkler@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Signed-off-by: Uma Shankar <uma.shankar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190828164216.405-4-ramalingam.c@intel.com
---
 include/drm/i915_mei_hdcp_interface.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/include/drm/i915_mei_hdcp_interface.h b/include/drm/i915_mei_hdcp_interface.h
index 08670aa650d4..4d48de8890ca 100644
--- a/include/drm/i915_mei_hdcp_interface.h
+++ b/include/drm/i915_mei_hdcp_interface.h
@@ -54,9 +54,32 @@ enum mei_fw_ddi {
 	MEI_DDI_RANGE_END = MEI_DDI_A,
 };
 
+/**
+ * enum mei_fw_tc - ME Firmware defined index for transcoders
+ * @MEI_INVALID_TRANSCODER: Index for Invalid transcoder
+ * @MEI_TRANSCODER_EDP: Index for EDP Transcoder
+ * @MEI_TRANSCODER_DSI0: Index for DSI0 Transcoder
+ * @MEI_TRANSCODER_DSI1: Index for DSI1 Transcoder
+ * @MEI_TRANSCODER_A: Index for Transcoder A
+ * @MEI_TRANSCODER_B: Index for Transcoder B
+ * @MEI_TRANSCODER_C: Index for Transcoder C
+ * @MEI_TRANSCODER_D: Index for Transcoder D
+ */
+enum mei_fw_tc {
+	MEI_INVALID_TRANSCODER = 0x00,
+	MEI_TRANSCODER_EDP,
+	MEI_TRANSCODER_DSI0,
+	MEI_TRANSCODER_DSI1,
+	MEI_TRANSCODER_A = 0x10,
+	MEI_TRANSCODER_B,
+	MEI_TRANSCODER_C,
+	MEI_TRANSCODER_D
+};
+
 /**
  * struct hdcp_port_data - intel specific HDCP port data
  * @fw_ddi: ddi index as per ME FW
+ * @fw_tc: transcoder index as per ME FW
  * @port_type: HDCP port type as per ME FW classification
  * @protocol: HDCP adaptation as per ME FW
  * @k: No of streams transmitted on a port. Only on DP MST this is != 1
@@ -69,6 +92,7 @@ enum mei_fw_ddi {
  */
 struct hdcp_port_data {
 	enum mei_fw_ddi fw_ddi;
+	enum mei_fw_tc fw_tc;
 	u8 port_type;
 	u8 protocol;
 	u16 k;
-- 
cgit v1.2.3


From 2d15cf1b9ae4c623b1a05838317f4c18fd534c9a Mon Sep 17 00:00:00 2001
From: Ramalingam C <ramalingam.c@intel.com>
Date: Wed, 28 Aug 2019 22:12:14 +0530
Subject: misc/mei/hdcp: Fill transcoder index in port info

For gen12+ platform we need to pass the transcoder info
as part of the port info into ME FW.

This change fills the payload for ME FW from hdcp_port_data.

v2:
  Doc is enhanced for physical_port and attached_transcoder [Tomas]

Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Acked-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Uma Shankar <uma.shankar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190828164216.405-5-ramalingam.c@intel.com
---
 drivers/misc/mei/hdcp/mei_hdcp.c | 11 +++++++++++
 drivers/misc/mei/hdcp/mei_hdcp.h |  5 ++++-
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/misc/mei/hdcp/mei_hdcp.c b/drivers/misc/mei/hdcp/mei_hdcp.c
index 3638c77eba26..93027fd96c71 100644
--- a/drivers/misc/mei/hdcp/mei_hdcp.c
+++ b/drivers/misc/mei/hdcp/mei_hdcp.c
@@ -58,6 +58,7 @@ mei_hdcp_initiate_session(struct device *dev, struct hdcp_port_data *data,
 
 	session_init_in.port.integrated_port_type = data->port_type;
 	session_init_in.port.physical_port = (u8)data->fw_ddi;
+	session_init_in.port.attached_transcoder = (u8)data->fw_tc;
 	session_init_in.protocol = data->protocol;
 
 	byte = mei_cldev_send(cldev, (u8 *)&session_init_in,
@@ -127,6 +128,7 @@ mei_hdcp_verify_receiver_cert_prepare_km(struct device *dev,
 
 	verify_rxcert_in.port.integrated_port_type = data->port_type;
 	verify_rxcert_in.port.physical_port = (u8)data->fw_ddi;
+	verify_rxcert_in.port.attached_transcoder = (u8)data->fw_tc;
 
 	verify_rxcert_in.cert_rx = rx_cert->cert_rx;
 	memcpy(verify_rxcert_in.r_rx, &rx_cert->r_rx, HDCP_2_2_RRX_LEN);
@@ -197,6 +199,7 @@ mei_hdcp_verify_hprime(struct device *dev, struct hdcp_port_data *data,
 
 	send_hprime_in.port.integrated_port_type = data->port_type;
 	send_hprime_in.port.physical_port = (u8)data->fw_ddi;
+	send_hprime_in.port.attached_transcoder = (u8)data->fw_tc;
 
 	memcpy(send_hprime_in.h_prime, rx_hprime->h_prime,
 	       HDCP_2_2_H_PRIME_LEN);
@@ -254,6 +257,7 @@ mei_hdcp_store_pairing_info(struct device *dev, struct hdcp_port_data *data,
 
 	pairing_info_in.port.integrated_port_type = data->port_type;
 	pairing_info_in.port.physical_port = (u8)data->fw_ddi;
+	pairing_info_in.port.attached_transcoder = (u8)data->fw_tc;
 
 	memcpy(pairing_info_in.e_kh_km, pairing_info->e_kh_km,
 	       HDCP_2_2_E_KH_KM_LEN);
@@ -312,6 +316,7 @@ mei_hdcp_initiate_locality_check(struct device *dev,
 
 	lc_init_in.port.integrated_port_type = data->port_type;
 	lc_init_in.port.physical_port = (u8)data->fw_ddi;
+	lc_init_in.port.attached_transcoder = (u8)data->fw_tc;
 
 	byte = mei_cldev_send(cldev, (u8 *)&lc_init_in, sizeof(lc_init_in));
 	if (byte < 0) {
@@ -367,6 +372,7 @@ mei_hdcp_verify_lprime(struct device *dev, struct hdcp_port_data *data,
 
 	verify_lprime_in.port.integrated_port_type = data->port_type;
 	verify_lprime_in.port.physical_port = (u8)data->fw_ddi;
+	verify_lprime_in.port.attached_transcoder = (u8)data->fw_tc;
 
 	memcpy(verify_lprime_in.l_prime, rx_lprime->l_prime,
 	       HDCP_2_2_L_PRIME_LEN);
@@ -424,6 +430,7 @@ static int mei_hdcp_get_session_key(struct device *dev,
 
 	get_skey_in.port.integrated_port_type = data->port_type;
 	get_skey_in.port.physical_port = (u8)data->fw_ddi;
+	get_skey_in.port.attached_transcoder = (u8)data->fw_tc;
 
 	byte = mei_cldev_send(cldev, (u8 *)&get_skey_in, sizeof(get_skey_in));
 	if (byte < 0) {
@@ -488,6 +495,7 @@ mei_hdcp_repeater_check_flow_prepare_ack(struct device *dev,
 
 	verify_repeater_in.port.integrated_port_type = data->port_type;
 	verify_repeater_in.port.physical_port = (u8)data->fw_ddi;
+	verify_repeater_in.port.attached_transcoder = (u8)data->fw_tc;
 
 	memcpy(verify_repeater_in.rx_info, rep_topology->rx_info,
 	       HDCP_2_2_RXINFO_LEN);
@@ -558,6 +566,7 @@ static int mei_hdcp_verify_mprime(struct device *dev,
 
 	verify_mprime_in.port.integrated_port_type = data->port_type;
 	verify_mprime_in.port.physical_port = (u8)data->fw_ddi;
+	verify_mprime_in.port.attached_transcoder = (u8)data->fw_tc;
 
 	memcpy(verify_mprime_in.m_prime, stream_ready->m_prime,
 	       HDCP_2_2_MPRIME_LEN);
@@ -619,6 +628,7 @@ static int mei_hdcp_enable_authentication(struct device *dev,
 
 	enable_auth_in.port.integrated_port_type = data->port_type;
 	enable_auth_in.port.physical_port = (u8)data->fw_ddi;
+	enable_auth_in.port.attached_transcoder = (u8)data->fw_tc;
 	enable_auth_in.stream_type = data->streams[0].stream_type;
 
 	byte = mei_cldev_send(cldev, (u8 *)&enable_auth_in,
@@ -673,6 +683,7 @@ mei_hdcp_close_session(struct device *dev, struct hdcp_port_data *data)
 
 	session_close_in.port.integrated_port_type = data->port_type;
 	session_close_in.port.physical_port = (u8)data->fw_ddi;
+	session_close_in.port.attached_transcoder = (u8)data->fw_tc;
 
 	byte = mei_cldev_send(cldev, (u8 *)&session_close_in,
 			      sizeof(session_close_in));
diff --git a/drivers/misc/mei/hdcp/mei_hdcp.h b/drivers/misc/mei/hdcp/mei_hdcp.h
index e60282eb2d48..18ffc773fa18 100644
--- a/drivers/misc/mei/hdcp/mei_hdcp.h
+++ b/drivers/misc/mei/hdcp/mei_hdcp.h
@@ -184,8 +184,11 @@ struct hdcp_cmd_no_data {
 /* Uniquely identifies the hdcp port being addressed for a given command. */
 struct hdcp_port_id {
 	u8	integrated_port_type;
+	/* physical_port is used until Gen11.5. Must be zero for Gen11.5+ */
 	u8	physical_port;
-	u16	reserved;
+	/* attached_transcoder is for Gen11.5+. Set to zero for <Gen11.5 */
+	u8	attached_transcoder;
+	u8	reserved;
 } __packed;
 
 /*
-- 
cgit v1.2.3


From 39e2df090c3cdce23a064929333b3be119111765 Mon Sep 17 00:00:00 2001
From: Ramalingam C <ramalingam.c@intel.com>
Date: Wed, 28 Aug 2019 22:12:15 +0530
Subject: drm/i915/hdcp: update current transcoder into intel_hdcp

On gen12+ platforms, HDCP HW is associated to the transcoder.
Hence on every modeset update associated transcoder into the
intel_hdcp of the port.

v2:
  s/trans/cpu_transcoder [Jani]
v3:
  comment is added for fw_ddi init for gen12+ [Shashank]
  only hdcp capable transcoder is translated into fw_tc [Shashank]
v4:
  fw_tc initialization is kept for modeset. [Tomas]
  few extra doc is added at port_data init [Tomas]
v5:
  Few comments are improvised [Tomas]

Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Signed-off-by: Uma Shankar <uma.shankar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190828164216.405-6-ramalingam.c@intel.com
---
 drivers/gpu/drm/i915/display/intel_display_types.h |  7 ++++
 drivers/gpu/drm/i915/display/intel_dp.c            |  3 ++
 drivers/gpu/drm/i915/display/intel_hdcp.c          | 47 +++++++++++++++++++++-
 drivers/gpu/drm/i915/display/intel_hdcp.h          |  3 ++
 drivers/gpu/drm/i915/display/intel_hdmi.c          |  3 ++
 5 files changed, 62 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 96514dcc7812..61277a87dbe7 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -388,6 +388,13 @@ struct intel_hdcp {
 	wait_queue_head_t cp_irq_queue;
 	atomic_t cp_irq_count;
 	int cp_irq_count_cached;
+
+	/*
+	 * HDCP register access for gen12+ need the transcoder associated.
+	 * Transcoder attached to the connector could be changed at modeset.
+	 * Hence caching the transcoder here.
+	 */
+	enum transcoder cpu_transcoder;
 };
 
 struct intel_connector {
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index c9986c7a3f5b..aaa90992a7f0 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2261,6 +2261,9 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 
 	intel_psr_compute_config(intel_dp, pipe_config);
 
+	intel_hdcp_transcoder_config(intel_connector,
+				     pipe_config->cpu_transcoder);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index e8b04cc8fcb1..edcec64a2c11 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -1764,13 +1764,58 @@ enum mei_fw_ddi intel_get_mei_fw_ddi_index(enum port port)
 	}
 }
 
+static inline
+enum mei_fw_tc intel_get_mei_fw_tc(enum transcoder cpu_transcoder)
+{
+	switch (cpu_transcoder) {
+	case TRANSCODER_A ... TRANSCODER_D:
+		return (enum mei_fw_tc)(cpu_transcoder | 0x10);
+	default: /* eDP, DSI TRANSCODERS are non HDCP capable */
+		return MEI_INVALID_TRANSCODER;
+	}
+}
+
+void intel_hdcp_transcoder_config(struct intel_connector *connector,
+				  enum transcoder cpu_transcoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	struct intel_hdcp *hdcp = &connector->hdcp;
+
+	if (!hdcp->shim)
+		return;
+
+	if (INTEL_GEN(dev_priv) >= 12) {
+		mutex_lock(&hdcp->mutex);
+		hdcp->cpu_transcoder = cpu_transcoder;
+		hdcp->port_data.fw_tc = intel_get_mei_fw_tc(cpu_transcoder);
+		mutex_unlock(&hdcp->mutex);
+	}
+}
+
 static inline int initialize_hdcp_port_data(struct intel_connector *connector,
 					    const struct intel_hdcp_shim *shim)
 {
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	struct intel_hdcp *hdcp = &connector->hdcp;
 	struct hdcp_port_data *data = &hdcp->port_data;
 
-	data->fw_ddi = intel_get_mei_fw_ddi_index(connector->encoder->port);
+	if (INTEL_GEN(dev_priv) < 12)
+		data->fw_ddi =
+			intel_get_mei_fw_ddi_index(connector->encoder->port);
+	else
+		/*
+		 * As per ME FW API expectation, for GEN 12+, fw_ddi is filled
+		 * with zero(INVALID PORT index).
+		 */
+		data->fw_ddi = MEI_DDI_INVALID_PORT;
+
+	/*
+	 * As associated transcoder is set and modified at modeset, here fw_tc
+	 * is initialized to zero (invalid transcoder index). This will be
+	 * retained for <Gen12 forever.
+	 */
+	data->fw_tc = MEI_INVALID_TRANSCODER;
+
 	data->port_type = (u8)HDCP_PORT_TYPE_INTEGRATED;
 	data->protocol = (u8)shim->protocol;
 
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.h b/drivers/gpu/drm/i915/display/intel_hdcp.h
index 59a2b40405cc..41c1053d9e38 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.h
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.h
@@ -16,10 +16,13 @@ struct drm_i915_private;
 struct intel_connector;
 struct intel_hdcp_shim;
 enum port;
+enum transcoder;
 
 void intel_hdcp_atomic_check(struct drm_connector *connector,
 			     struct drm_connector_state *old_state,
 			     struct drm_connector_state *new_state);
+void intel_hdcp_transcoder_config(struct intel_connector *connector,
+				  enum transcoder cpu_transcoder);
 int intel_hdcp_init(struct intel_connector *connector,
 		    const struct intel_hdcp_shim *hdcp_shim);
 int intel_hdcp_enable(struct intel_connector *connector, u8 content_type);
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index e02f0faecf02..6e9bb6bd1ee2 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2431,6 +2431,9 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 		return -EINVAL;
 	}
 
+	intel_hdcp_transcoder_config(intel_hdmi->attached_connector,
+				     pipe_config->cpu_transcoder);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 692059318c0fc6c3584b861adc67abbb0c1598f0 Mon Sep 17 00:00:00 2001
From: Ramalingam C <ramalingam.c@intel.com>
Date: Wed, 28 Aug 2019 22:12:16 +0530
Subject: drm/i915/hdcp: Enable HDCP 1.4 and 2.2 on Gen12+

>From Gen12 onwards, HDCP HW block is implemented within transcoders.
Till Gen11 HDCP HW block was part of DDI.

Hence required changes in HW programming is handled here.

As ME FW needs the transcoder detail on which HDCP is enabled
on Gen12+ platform, we are populating the detail in hdcp_port_data.

v2:
  _MMIO_TRANS is used [Lucas and Daniel]
  platform check is moved into the caller [Lucas]
v3:
  platform check is moved into a macro [Shashank]
v4:
  Few optimizations in the coding [Shashank]
v5:
  Fixed alignment in macro definition in i915_reg.h [Shashank]
  unused variables "reg" is removed.
v6:
  Configuring the transcoder at compute_config.
  transcoder is used instead of pipe in macros.
  Rebased.
v7:
  transcoder is cached at intel_hdcp
  hdcp_port_data is configured with transcoder index asper ME FW.
v8:
  s/trans/cpu_transcoder
  s/tc/cpu_transcoder
v9:
  rep_ctl is prepared for TCD too.
  return moved into deault of rep_ctl prepare function [Shashank]

Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Uma Shankar <uma.shankar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190828164216.405-7-ramalingam.c@intel.com
---
 drivers/gpu/drm/i915/display/intel_hdcp.c | 152 +++++++++++++++++++-----------
 drivers/gpu/drm/i915/display/intel_hdmi.c |  10 +-
 drivers/gpu/drm/i915/i915_reg.h           | 124 ++++++++++++++++++++++--
 3 files changed, 221 insertions(+), 65 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index edcec64a2c11..e69fa34528df 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -20,6 +20,7 @@
 #include "intel_display_types.h"
 #include "intel_hdcp.h"
 #include "intel_sideband.h"
+#include "intel_connector.h"
 
 #define KEY_LOAD_TRIES	5
 #define ENCRYPT_STATUS_CHANGE_TIMEOUT_MS	50
@@ -107,24 +108,20 @@ bool intel_hdcp2_capable(struct intel_connector *connector)
 	return capable;
 }
 
-static inline bool intel_hdcp_in_use(struct intel_connector *connector)
+static inline
+bool intel_hdcp_in_use(struct drm_i915_private *dev_priv,
+		       enum transcoder cpu_transcoder, enum port port)
 {
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	enum port port = connector->encoder->port;
-	u32 reg;
-
-	reg = I915_READ(PORT_HDCP_STATUS(port));
-	return reg & HDCP_STATUS_ENC;
+	return I915_READ(HDCP_STATUS(dev_priv, cpu_transcoder, port)) &
+	       HDCP_STATUS_ENC;
 }
 
-static inline bool intel_hdcp2_in_use(struct intel_connector *connector)
+static inline
+bool intel_hdcp2_in_use(struct drm_i915_private *dev_priv,
+			enum transcoder cpu_transcoder, enum port port)
 {
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	enum port port = connector->encoder->port;
-	u32 reg;
-
-	reg = I915_READ(HDCP2_STATUS_DDI(port));
-	return reg & LINK_ENCRYPTION_STATUS;
+	return I915_READ(HDCP2_STATUS(dev_priv, cpu_transcoder, port)) &
+	       LINK_ENCRYPTION_STATUS;
 }
 
 static int intel_hdcp_poll_ksv_fifo(struct intel_digital_port *intel_dig_port,
@@ -255,9 +252,29 @@ static int intel_write_sha_text(struct drm_i915_private *dev_priv, u32 sha_text)
 }
 
 static
-u32 intel_hdcp_get_repeater_ctl(struct intel_digital_port *intel_dig_port)
+u32 intel_hdcp_get_repeater_ctl(struct drm_i915_private *dev_priv,
+				enum transcoder cpu_transcoder, enum port port)
 {
-	enum port port = intel_dig_port->base.port;
+	if (INTEL_GEN(dev_priv) >= 12) {
+		switch (cpu_transcoder) {
+		case TRANSCODER_A:
+			return HDCP_TRANSA_REP_PRESENT |
+			       HDCP_TRANSA_SHA1_M0;
+		case TRANSCODER_B:
+			return HDCP_TRANSB_REP_PRESENT |
+			       HDCP_TRANSB_SHA1_M0;
+		case TRANSCODER_C:
+			return HDCP_TRANSC_REP_PRESENT |
+			       HDCP_TRANSC_SHA1_M0;
+		case TRANSCODER_D:
+			return HDCP_TRANSD_REP_PRESENT |
+			       HDCP_TRANSD_SHA1_M0;
+		default:
+			DRM_ERROR("Unknown transcoder %d\n", cpu_transcoder);
+			return -EINVAL;
+		}
+	}
+
 	switch (port) {
 	case PORT_A:
 		return HDCP_DDIA_REP_PRESENT | HDCP_DDIA_SHA1_M0;
@@ -270,18 +287,20 @@ u32 intel_hdcp_get_repeater_ctl(struct intel_digital_port *intel_dig_port)
 	case PORT_E:
 		return HDCP_DDIE_REP_PRESENT | HDCP_DDIE_SHA1_M0;
 	default:
-		break;
+		DRM_ERROR("Unknown port %d\n", port);
+		return -EINVAL;
 	}
-	DRM_ERROR("Unknown port %d\n", port);
-	return -EINVAL;
 }
 
 static
-int intel_hdcp_validate_v_prime(struct intel_digital_port *intel_dig_port,
+int intel_hdcp_validate_v_prime(struct intel_connector *connector,
 				const struct intel_hdcp_shim *shim,
 				u8 *ksv_fifo, u8 num_downstream, u8 *bstatus)
 {
+	struct intel_digital_port *intel_dig_port = conn_to_dig_port(connector);
 	struct drm_i915_private *dev_priv;
+	enum transcoder cpu_transcoder = connector->hdcp.cpu_transcoder;
+	enum port port = intel_dig_port->base.port;
 	u32 vprime, sha_text, sha_leftovers, rep_ctl;
 	int ret, i, j, sha_idx;
 
@@ -308,7 +327,7 @@ int intel_hdcp_validate_v_prime(struct intel_digital_port *intel_dig_port,
 	sha_idx = 0;
 	sha_text = 0;
 	sha_leftovers = 0;
-	rep_ctl = intel_hdcp_get_repeater_ctl(intel_dig_port);
+	rep_ctl = intel_hdcp_get_repeater_ctl(dev_priv, cpu_transcoder, port);
 	I915_WRITE(HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_32);
 	for (i = 0; i < num_downstream; i++) {
 		unsigned int sha_empty;
@@ -550,7 +569,7 @@ int intel_hdcp_auth_downstream(struct intel_connector *connector)
 	 * V prime atleast twice.
 	 */
 	for (i = 0; i < tries; i++) {
-		ret = intel_hdcp_validate_v_prime(intel_dig_port, shim,
+		ret = intel_hdcp_validate_v_prime(connector, shim,
 						  ksv_fifo, num_downstream,
 						  bstatus);
 		if (!ret)
@@ -578,6 +597,7 @@ static int intel_hdcp_auth(struct intel_connector *connector)
 	struct drm_device *dev = connector->base.dev;
 	const struct intel_hdcp_shim *shim = hdcp->shim;
 	struct drm_i915_private *dev_priv;
+	enum transcoder cpu_transcoder = connector->hdcp.cpu_transcoder;
 	enum port port;
 	unsigned long r0_prime_gen_start;
 	int ret, i, tries = 2;
@@ -617,18 +637,21 @@ static int intel_hdcp_auth(struct intel_connector *connector)
 
 	/* Initialize An with 2 random values and acquire it */
 	for (i = 0; i < 2; i++)
-		I915_WRITE(PORT_HDCP_ANINIT(port), get_random_u32());
-	I915_WRITE(PORT_HDCP_CONF(port), HDCP_CONF_CAPTURE_AN);
+		I915_WRITE(HDCP_ANINIT(dev_priv, cpu_transcoder, port),
+			   get_random_u32());
+	I915_WRITE(HDCP_CONF(dev_priv, cpu_transcoder, port),
+		   HDCP_CONF_CAPTURE_AN);
 
 	/* Wait for An to be acquired */
-	if (intel_de_wait_for_set(dev_priv, PORT_HDCP_STATUS(port),
+	if (intel_de_wait_for_set(dev_priv,
+				  HDCP_STATUS(dev_priv, cpu_transcoder, port),
 				  HDCP_STATUS_AN_READY, 1)) {
 		DRM_ERROR("Timed out waiting for An\n");
 		return -ETIMEDOUT;
 	}
 
-	an.reg[0] = I915_READ(PORT_HDCP_ANLO(port));
-	an.reg[1] = I915_READ(PORT_HDCP_ANHI(port));
+	an.reg[0] = I915_READ(HDCP_ANLO(dev_priv, cpu_transcoder, port));
+	an.reg[1] = I915_READ(HDCP_ANHI(dev_priv, cpu_transcoder, port));
 	ret = shim->write_an_aksv(intel_dig_port, an.shim);
 	if (ret)
 		return ret;
@@ -646,24 +669,26 @@ static int intel_hdcp_auth(struct intel_connector *connector)
 		return -EPERM;
 	}
 
-	I915_WRITE(PORT_HDCP_BKSVLO(port), bksv.reg[0]);
-	I915_WRITE(PORT_HDCP_BKSVHI(port), bksv.reg[1]);
+	I915_WRITE(HDCP_BKSVLO(dev_priv, cpu_transcoder, port), bksv.reg[0]);
+	I915_WRITE(HDCP_BKSVHI(dev_priv, cpu_transcoder, port), bksv.reg[1]);
 
 	ret = shim->repeater_present(intel_dig_port, &repeater_present);
 	if (ret)
 		return ret;
 	if (repeater_present)
 		I915_WRITE(HDCP_REP_CTL,
-			   intel_hdcp_get_repeater_ctl(intel_dig_port));
+			   intel_hdcp_get_repeater_ctl(dev_priv, cpu_transcoder,
+						       port));
 
 	ret = shim->toggle_signalling(intel_dig_port, true);
 	if (ret)
 		return ret;
 
-	I915_WRITE(PORT_HDCP_CONF(port), HDCP_CONF_AUTH_AND_ENC);
+	I915_WRITE(HDCP_CONF(dev_priv, cpu_transcoder, port),
+		   HDCP_CONF_AUTH_AND_ENC);
 
 	/* Wait for R0 ready */
-	if (wait_for(I915_READ(PORT_HDCP_STATUS(port)) &
+	if (wait_for(I915_READ(HDCP_STATUS(dev_priv, cpu_transcoder, port)) &
 		     (HDCP_STATUS_R0_READY | HDCP_STATUS_ENC), 1)) {
 		DRM_ERROR("Timed out waiting for R0 ready\n");
 		return -ETIMEDOUT;
@@ -691,22 +716,25 @@ static int intel_hdcp_auth(struct intel_connector *connector)
 		ret = shim->read_ri_prime(intel_dig_port, ri.shim);
 		if (ret)
 			return ret;
-		I915_WRITE(PORT_HDCP_RPRIME(port), ri.reg);
+		I915_WRITE(HDCP_RPRIME(dev_priv, cpu_transcoder, port), ri.reg);
 
 		/* Wait for Ri prime match */
-		if (!wait_for(I915_READ(PORT_HDCP_STATUS(port)) &
+		if (!wait_for(I915_READ(HDCP_STATUS(dev_priv, cpu_transcoder,
+						    port)) &
 		    (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC), 1))
 			break;
 	}
 
 	if (i == tries) {
 		DRM_DEBUG_KMS("Timed out waiting for Ri prime match (%x)\n",
-			      I915_READ(PORT_HDCP_STATUS(port)));
+			      I915_READ(HDCP_STATUS(dev_priv, cpu_transcoder,
+						    port)));
 		return -ETIMEDOUT;
 	}
 
 	/* Wait for encryption confirmation */
-	if (intel_de_wait_for_set(dev_priv, PORT_HDCP_STATUS(port),
+	if (intel_de_wait_for_set(dev_priv,
+				  HDCP_STATUS(dev_priv, cpu_transcoder, port),
 				  HDCP_STATUS_ENC,
 				  ENCRYPT_STATUS_CHANGE_TIMEOUT_MS)) {
 		DRM_ERROR("Timed out waiting for encryption\n");
@@ -731,15 +759,17 @@ static int _intel_hdcp_disable(struct intel_connector *connector)
 	struct drm_i915_private *dev_priv = connector->base.dev->dev_private;
 	struct intel_digital_port *intel_dig_port = conn_to_dig_port(connector);
 	enum port port = intel_dig_port->base.port;
+	enum transcoder cpu_transcoder = hdcp->cpu_transcoder;
 	int ret;
 
 	DRM_DEBUG_KMS("[%s:%d] HDCP is being disabled...\n",
 		      connector->base.name, connector->base.base.id);
 
 	hdcp->hdcp_encrypted = false;
-	I915_WRITE(PORT_HDCP_CONF(port), 0);
-	if (intel_de_wait_for_clear(dev_priv, PORT_HDCP_STATUS(port), ~0,
-				    ENCRYPT_STATUS_CHANGE_TIMEOUT_MS)) {
+	I915_WRITE(HDCP_CONF(dev_priv, cpu_transcoder, port), 0);
+	if (intel_de_wait_for_clear(dev_priv,
+				    HDCP_STATUS(dev_priv, cpu_transcoder, port),
+				    ~0, ENCRYPT_STATUS_CHANGE_TIMEOUT_MS)) {
 		DRM_ERROR("Failed to disable HDCP, timeout clearing status\n");
 		return -ETIMEDOUT;
 	}
@@ -810,9 +840,11 @@ static int intel_hdcp_check_link(struct intel_connector *connector)
 	struct drm_i915_private *dev_priv = connector->base.dev->dev_private;
 	struct intel_digital_port *intel_dig_port = conn_to_dig_port(connector);
 	enum port port = intel_dig_port->base.port;
+	enum transcoder cpu_transcoder;
 	int ret = 0;
 
 	mutex_lock(&hdcp->mutex);
+	cpu_transcoder = hdcp->cpu_transcoder;
 
 	/* Check_link valid only when HDCP1.4 is enabled */
 	if (hdcp->value != DRM_MODE_CONTENT_PROTECTION_ENABLED ||
@@ -821,10 +853,11 @@ static int intel_hdcp_check_link(struct intel_connector *connector)
 		goto out;
 	}
 
-	if (WARN_ON(!intel_hdcp_in_use(connector))) {
+	if (WARN_ON(!intel_hdcp_in_use(dev_priv, cpu_transcoder, port))) {
 		DRM_ERROR("%s:%d HDCP link stopped encryption,%x\n",
 			  connector->base.name, connector->base.base.id,
-			  I915_READ(PORT_HDCP_STATUS(port)));
+			  I915_READ(HDCP_STATUS(dev_priv, cpu_transcoder,
+						port)));
 		ret = -ENXIO;
 		hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED;
 		schedule_work(&hdcp->prop_work);
@@ -1495,10 +1528,11 @@ static int hdcp2_enable_encryption(struct intel_connector *connector)
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	struct intel_hdcp *hdcp = &connector->hdcp;
 	enum port port = connector->encoder->port;
+	enum transcoder cpu_transcoder = hdcp->cpu_transcoder;
 	int ret;
 
-	WARN_ON(I915_READ(HDCP2_STATUS_DDI(port)) & LINK_ENCRYPTION_STATUS);
-
+	WARN_ON(I915_READ(HDCP2_STATUS(dev_priv, cpu_transcoder, port)) &
+		LINK_ENCRYPTION_STATUS);
 	if (hdcp->shim->toggle_signalling) {
 		ret = hdcp->shim->toggle_signalling(intel_dig_port, true);
 		if (ret) {
@@ -1508,14 +1542,18 @@ static int hdcp2_enable_encryption(struct intel_connector *connector)
 		}
 	}
 
-	if (I915_READ(HDCP2_STATUS_DDI(port)) & LINK_AUTH_STATUS) {
+	if (I915_READ(HDCP2_STATUS(dev_priv, cpu_transcoder, port)) &
+	    LINK_AUTH_STATUS) {
 		/* Link is Authenticated. Now set for Encryption */
-		I915_WRITE(HDCP2_CTL_DDI(port),
-			   I915_READ(HDCP2_CTL_DDI(port)) |
+		I915_WRITE(HDCP2_CTL(dev_priv, cpu_transcoder, port),
+			   I915_READ(HDCP2_CTL(dev_priv, cpu_transcoder,
+					       port)) |
 			   CTL_LINK_ENCRYPTION_REQ);
 	}
 
-	ret = intel_de_wait_for_set(dev_priv, HDCP2_STATUS_DDI(port),
+	ret = intel_de_wait_for_set(dev_priv,
+				    HDCP2_STATUS(dev_priv, cpu_transcoder,
+						 port),
 				    LINK_ENCRYPTION_STATUS,
 				    ENCRYPT_STATUS_CHANGE_TIMEOUT_MS);
 
@@ -1528,14 +1566,19 @@ static int hdcp2_disable_encryption(struct intel_connector *connector)
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	struct intel_hdcp *hdcp = &connector->hdcp;
 	enum port port = connector->encoder->port;
+	enum transcoder cpu_transcoder = hdcp->cpu_transcoder;
 	int ret;
 
-	WARN_ON(!(I915_READ(HDCP2_STATUS_DDI(port)) & LINK_ENCRYPTION_STATUS));
+	WARN_ON(!(I915_READ(HDCP2_STATUS(dev_priv, cpu_transcoder, port)) &
+			    LINK_ENCRYPTION_STATUS));
 
-	I915_WRITE(HDCP2_CTL_DDI(port),
-		   I915_READ(HDCP2_CTL_DDI(port)) & ~CTL_LINK_ENCRYPTION_REQ);
+	I915_WRITE(HDCP2_CTL(dev_priv, cpu_transcoder, port),
+		   I915_READ(HDCP2_CTL(dev_priv, cpu_transcoder, port)) &
+		   ~CTL_LINK_ENCRYPTION_REQ);
 
-	ret = intel_de_wait_for_clear(dev_priv, HDCP2_STATUS_DDI(port),
+	ret = intel_de_wait_for_clear(dev_priv,
+				      HDCP2_STATUS(dev_priv, cpu_transcoder,
+						   port),
 				      LINK_ENCRYPTION_STATUS,
 				      ENCRYPT_STATUS_CHANGE_TIMEOUT_MS);
 	if (ret == -ETIMEDOUT)
@@ -1634,9 +1677,11 @@ static int intel_hdcp2_check_link(struct intel_connector *connector)
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	struct intel_hdcp *hdcp = &connector->hdcp;
 	enum port port = connector->encoder->port;
+	enum transcoder cpu_transcoder;
 	int ret = 0;
 
 	mutex_lock(&hdcp->mutex);
+	cpu_transcoder = hdcp->cpu_transcoder;
 
 	/* hdcp2_check_link is expected only when HDCP2.2 is Enabled */
 	if (hdcp->value != DRM_MODE_CONTENT_PROTECTION_ENABLED ||
@@ -1645,9 +1690,10 @@ static int intel_hdcp2_check_link(struct intel_connector *connector)
 		goto out;
 	}
 
-	if (WARN_ON(!intel_hdcp2_in_use(connector))) {
+	if (WARN_ON(!intel_hdcp2_in_use(dev_priv, cpu_transcoder, port))) {
 		DRM_ERROR("HDCP2.2 link stopped the encryption, %x\n",
-			  I915_READ(HDCP2_STATUS_DDI(port)));
+			  I915_READ(HDCP2_STATUS(dev_priv, cpu_transcoder,
+						 port)));
 		ret = -ENXIO;
 		hdcp->value = DRM_MODE_CONTENT_PROTECTION_DESIRED;
 		schedule_work(&hdcp->prop_work);
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 6e9bb6bd1ee2..f6bb77fd0930 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -1491,7 +1491,10 @@ bool intel_hdmi_hdcp_check_link(struct intel_digital_port *intel_dig_port)
 {
 	struct drm_i915_private *dev_priv =
 		intel_dig_port->base.base.dev->dev_private;
+	struct intel_connector *connector =
+		intel_dig_port->hdmi.attached_connector;
 	enum port port = intel_dig_port->base.port;
+	enum transcoder cpu_transcoder = connector->hdcp.cpu_transcoder;
 	int ret;
 	union {
 		u32 reg;
@@ -1502,13 +1505,14 @@ bool intel_hdmi_hdcp_check_link(struct intel_digital_port *intel_dig_port)
 	if (ret)
 		return false;
 
-	I915_WRITE(PORT_HDCP_RPRIME(port), ri.reg);
+	I915_WRITE(HDCP_RPRIME(dev_priv, cpu_transcoder, port), ri.reg);
 
 	/* Wait for Ri prime match */
-	if (wait_for(I915_READ(PORT_HDCP_STATUS(port)) &
+	if (wait_for(I915_READ(HDCP_STATUS(dev_priv, cpu_transcoder, port)) &
 		     (HDCP_STATUS_RI_MATCH | HDCP_STATUS_ENC), 1)) {
 		DRM_ERROR("Ri' mismatch detected, link check failed (%x)\n",
-			  I915_READ(PORT_HDCP_STATUS(port)));
+			  I915_READ(HDCP_STATUS(dev_priv, cpu_transcoder,
+						port)));
 		return false;
 	}
 	return true;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 02e1ef10c47e..3cfdab18c0cf 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -9281,12 +9281,20 @@ enum skl_power_gate {
 
 /* HDCP Repeater Registers */
 #define HDCP_REP_CTL			_MMIO(0x66d00)
+#define  HDCP_TRANSA_REP_PRESENT	BIT(31)
+#define  HDCP_TRANSB_REP_PRESENT	BIT(30)
+#define  HDCP_TRANSC_REP_PRESENT	BIT(29)
+#define  HDCP_TRANSD_REP_PRESENT	BIT(28)
 #define  HDCP_DDIB_REP_PRESENT		BIT(30)
 #define  HDCP_DDIA_REP_PRESENT		BIT(29)
 #define  HDCP_DDIC_REP_PRESENT		BIT(28)
 #define  HDCP_DDID_REP_PRESENT		BIT(27)
 #define  HDCP_DDIF_REP_PRESENT		BIT(26)
 #define  HDCP_DDIE_REP_PRESENT		BIT(25)
+#define  HDCP_TRANSA_SHA1_M0		(1 << 20)
+#define  HDCP_TRANSB_SHA1_M0		(2 << 20)
+#define  HDCP_TRANSC_SHA1_M0		(3 << 20)
+#define  HDCP_TRANSD_SHA1_M0		(4 << 20)
 #define  HDCP_DDIB_SHA1_M0		(1 << 20)
 #define  HDCP_DDIA_SHA1_M0		(2 << 20)
 #define  HDCP_DDIC_SHA1_M0		(3 << 20)
@@ -9326,15 +9334,92 @@ enum skl_power_gate {
 					  _PORTE_HDCP_AUTHENC, \
 					  _PORTF_HDCP_AUTHENC) + (x))
 #define PORT_HDCP_CONF(port)		_PORT_HDCP_AUTHENC(port, 0x0)
+#define _TRANSA_HDCP_CONF		0x66400
+#define _TRANSB_HDCP_CONF		0x66500
+#define TRANS_HDCP_CONF(trans)		_MMIO_TRANS(trans, _TRANSA_HDCP_CONF, \
+						    _TRANSB_HDCP_CONF)
+#define HDCP_CONF(dev_priv, trans, port) \
+					(INTEL_GEN(dev_priv) >= 12 ? \
+					 TRANS_HDCP_CONF(trans) : \
+					 PORT_HDCP_CONF(port))
+
 #define  HDCP_CONF_CAPTURE_AN		BIT(0)
 #define  HDCP_CONF_AUTH_AND_ENC		(BIT(1) | BIT(0))
 #define PORT_HDCP_ANINIT(port)		_PORT_HDCP_AUTHENC(port, 0x4)
+#define _TRANSA_HDCP_ANINIT		0x66404
+#define _TRANSB_HDCP_ANINIT		0x66504
+#define TRANS_HDCP_ANINIT(trans)	_MMIO_TRANS(trans, \
+						    _TRANSA_HDCP_ANINIT, \
+						    _TRANSB_HDCP_ANINIT)
+#define HDCP_ANINIT(dev_priv, trans, port) \
+					(INTEL_GEN(dev_priv) >= 12 ? \
+					 TRANS_HDCP_ANINIT(trans) : \
+					 PORT_HDCP_ANINIT(port))
+
 #define PORT_HDCP_ANLO(port)		_PORT_HDCP_AUTHENC(port, 0x8)
+#define _TRANSA_HDCP_ANLO		0x66408
+#define _TRANSB_HDCP_ANLO		0x66508
+#define TRANS_HDCP_ANLO(trans)		_MMIO_TRANS(trans, _TRANSA_HDCP_ANLO, \
+						    _TRANSB_HDCP_ANLO)
+#define HDCP_ANLO(dev_priv, trans, port) \
+					(INTEL_GEN(dev_priv) >= 12 ? \
+					 TRANS_HDCP_ANLO(trans) : \
+					 PORT_HDCP_ANLO(port))
+
 #define PORT_HDCP_ANHI(port)		_PORT_HDCP_AUTHENC(port, 0xC)
+#define _TRANSA_HDCP_ANHI		0x6640C
+#define _TRANSB_HDCP_ANHI		0x6650C
+#define TRANS_HDCP_ANHI(trans)		_MMIO_TRANS(trans, _TRANSA_HDCP_ANHI, \
+						    _TRANSB_HDCP_ANHI)
+#define HDCP_ANHI(dev_priv, trans, port) \
+					(INTEL_GEN(dev_priv) >= 12 ? \
+					 TRANS_HDCP_ANHI(trans) : \
+					 PORT_HDCP_ANHI(port))
+
 #define PORT_HDCP_BKSVLO(port)		_PORT_HDCP_AUTHENC(port, 0x10)
+#define _TRANSA_HDCP_BKSVLO		0x66410
+#define _TRANSB_HDCP_BKSVLO		0x66510
+#define TRANS_HDCP_BKSVLO(trans)	_MMIO_TRANS(trans, \
+						    _TRANSA_HDCP_BKSVLO, \
+						    _TRANSB_HDCP_BKSVLO)
+#define HDCP_BKSVLO(dev_priv, trans, port) \
+					(INTEL_GEN(dev_priv) >= 12 ? \
+					 TRANS_HDCP_BKSVLO(trans) : \
+					 PORT_HDCP_BKSVLO(port))
+
 #define PORT_HDCP_BKSVHI(port)		_PORT_HDCP_AUTHENC(port, 0x14)
+#define _TRANSA_HDCP_BKSVHI		0x66414
+#define _TRANSB_HDCP_BKSVHI		0x66514
+#define TRANS_HDCP_BKSVHI(trans)	_MMIO_TRANS(trans, \
+						    _TRANSA_HDCP_BKSVHI, \
+						    _TRANSB_HDCP_BKSVHI)
+#define HDCP_BKSVHI(dev_priv, trans, port) \
+					(INTEL_GEN(dev_priv) >= 12 ? \
+					 TRANS_HDCP_BKSVHI(trans) : \
+					 PORT_HDCP_BKSVHI(port))
+
 #define PORT_HDCP_RPRIME(port)		_PORT_HDCP_AUTHENC(port, 0x18)
+#define _TRANSA_HDCP_RPRIME		0x66418
+#define _TRANSB_HDCP_RPRIME		0x66518
+#define TRANS_HDCP_RPRIME(trans)	_MMIO_TRANS(trans, \
+						    _TRANSA_HDCP_RPRIME, \
+						    _TRANSB_HDCP_RPRIME)
+#define HDCP_RPRIME(dev_priv, trans, port) \
+					(INTEL_GEN(dev_priv) >= 12 ? \
+					 TRANS_HDCP_RPRIME(trans) : \
+					 PORT_HDCP_RPRIME(port))
+
 #define PORT_HDCP_STATUS(port)		_PORT_HDCP_AUTHENC(port, 0x1C)
+#define _TRANSA_HDCP_STATUS		0x6641C
+#define _TRANSB_HDCP_STATUS		0x6651C
+#define TRANS_HDCP_STATUS(trans)	_MMIO_TRANS(trans, \
+						    _TRANSA_HDCP_STATUS, \
+						    _TRANSB_HDCP_STATUS)
+#define HDCP_STATUS(dev_priv, trans, port) \
+					(INTEL_GEN(dev_priv) >= 12 ? \
+					 TRANS_HDCP_STATUS(trans) : \
+					 PORT_HDCP_STATUS(port))
+
 #define  HDCP_STATUS_STREAM_A_ENC	BIT(31)
 #define  HDCP_STATUS_STREAM_B_ENC	BIT(30)
 #define  HDCP_STATUS_STREAM_C_ENC	BIT(29)
@@ -9361,23 +9446,44 @@ enum skl_power_gate {
 					  _PORTD_HDCP2_BASE, \
 					  _PORTE_HDCP2_BASE, \
 					  _PORTF_HDCP2_BASE) + (x))
-
-#define HDCP2_AUTH_DDI(port)		_PORT_HDCP2_BASE(port, 0x98)
+#define PORT_HDCP2_AUTH(port)		_PORT_HDCP2_BASE(port, 0x98)
+#define _TRANSA_HDCP2_AUTH		0x66498
+#define _TRANSB_HDCP2_AUTH		0x66598
+#define TRANS_HDCP2_AUTH(trans)		_MMIO_TRANS(trans, _TRANSA_HDCP2_AUTH, \
+						    _TRANSB_HDCP2_AUTH)
 #define   AUTH_LINK_AUTHENTICATED	BIT(31)
 #define   AUTH_LINK_TYPE		BIT(30)
 #define   AUTH_FORCE_CLR_INPUTCTR	BIT(19)
 #define   AUTH_CLR_KEYS			BIT(18)
-
-#define HDCP2_CTL_DDI(port)		_PORT_HDCP2_BASE(port, 0xB0)
+#define HDCP2_AUTH(dev_priv, trans, port) \
+					(INTEL_GEN(dev_priv) >= 12 ? \
+					 TRANS_HDCP2_AUTH(trans) : \
+					 PORT_HDCP2_AUTH(port))
+
+#define PORT_HDCP2_CTL(port)		_PORT_HDCP2_BASE(port, 0xB0)
+#define _TRANSA_HDCP2_CTL		0x664B0
+#define _TRANSB_HDCP2_CTL		0x665B0
+#define TRANS_HDCP2_CTL(trans)		_MMIO_TRANS(trans, _TRANSA_HDCP2_CTL, \
+						    _TRANSB_HDCP2_CTL)
 #define   CTL_LINK_ENCRYPTION_REQ	BIT(31)
-
-#define HDCP2_STATUS_DDI(port)		_PORT_HDCP2_BASE(port, 0xB4)
-#define   STREAM_ENCRYPTION_STATUS_A	BIT(31)
-#define   STREAM_ENCRYPTION_STATUS_B	BIT(30)
-#define   STREAM_ENCRYPTION_STATUS_C	BIT(29)
+#define HDCP2_CTL(dev_priv, trans, port) \
+					(INTEL_GEN(dev_priv) >= 12 ? \
+					 TRANS_HDCP2_CTL(trans) : \
+					 PORT_HDCP2_CTL(port))
+
+#define PORT_HDCP2_STATUS(port)		_PORT_HDCP2_BASE(port, 0xB4)
+#define _TRANSA_HDCP2_STATUS		0x664B4
+#define _TRANSB_HDCP2_STATUS		0x665B4
+#define TRANS_HDCP2_STATUS(trans)	_MMIO_TRANS(trans, \
+						    _TRANSA_HDCP2_STATUS, \
+						    _TRANSB_HDCP2_STATUS)
 #define   LINK_TYPE_STATUS		BIT(22)
 #define   LINK_AUTH_STATUS		BIT(21)
 #define   LINK_ENCRYPTION_STATUS	BIT(20)
+#define HDCP2_STATUS(dev_priv, trans, port) \
+					(INTEL_GEN(dev_priv) >= 12 ? \
+					 TRANS_HDCP2_STATUS(trans) : \
+					 PORT_HDCP2_STATUS(port))
 
 /* Per-pipe DDI Function Control */
 #define _TRANS_DDI_FUNC_CTL_A		0x60400
-- 
cgit v1.2.3


From b047463c852272ef9956ad3a4c706f78f8b06c17 Mon Sep 17 00:00:00 2001
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Date: Fri, 30 Aug 2019 11:58:48 +0300
Subject: drm/i915: Remove link to missing "Batchbuffer Pools" documentation

The referenced documentation section has been removed. Remove the
link to avoid warning when building the documentation.

Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190830085849.12519-1-joonas.lahtinen@linux.intel.com
---
 Documentation/gpu/i915.rst | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 3415255ad3dc..7d1f65612856 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -358,15 +358,6 @@ Batchbuffer Parsing
 .. kernel-doc:: drivers/gpu/drm/i915/i915_cmd_parser.c
    :internal:
 
-Batchbuffer Pools
------------------
-
-.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_batch_pool.c
-   :doc: batch pool
-
-.. kernel-doc:: drivers/gpu/drm/i915/i915_gem_batch_pool.c
-   :internal:
-
 User Batchbuffer Execution
 --------------------------
 
-- 
cgit v1.2.3


From 4072761b981c630acbc6195391e5a22bae114e39 Mon Sep 17 00:00:00 2001
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Date: Fri, 30 Aug 2019 11:58:49 +0300
Subject: drm/i915: Indent GuC/WOPCM documentation sections

Indent GuC/WOPCM documentation correctly to reside under
"Memory Management and Command Submission" section to avoid
it escaping to the upper level navigation.

Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190830085849.12519-2-joonas.lahtinen@linux.intel.com
---
 Documentation/gpu/i915.rst | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 7d1f65612856..e249ea7b0ec7 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -407,31 +407,31 @@ Object Tiling IOCTLs
    :doc: buffer object tiling
 
 WOPCM
-=====
+-----
 
 WOPCM Layout
-------------
+~~~~~~~~~~~~
 
 .. kernel-doc:: drivers/gpu/drm/i915/intel_wopcm.c
    :doc: WOPCM Layout
 
 GuC
-===
+---
 
 Firmware Layout
--------------------
+~~~~~~~~~~~~~~~
 
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h
    :doc: Firmware Layout
 
 GuC-specific firmware loader
-----------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c
    :internal:
 
 GuC-based command submission
-----------------------------
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
    :doc: GuC-based command submission
@@ -440,7 +440,7 @@ GuC-based command submission
    :internal:
 
 GuC Address Space
------------------
+~~~~~~~~~~~~~~~~~
 
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.c
    :doc: GuC Address Space
-- 
cgit v1.2.3


From ed3126fa0d393825f2f134668b31363581035825 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 29 Aug 2019 14:15:23 -0700
Subject: drm/i915: parameterize south hpd macros
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

South, follow the north.

Instead of defining separate macros for each port, make them take port
as parameter as done for TC ports and for north engine. This will allow
us to easily extend this as needed.

tgp_ddi_port_hotplug_long_detect() is also removed as after the EHL
introduction the tgp variant is an exact copy of icp.

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190829211526.30525-1-jose.souza@intel.com
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c | 22 ++++------------------
 drivers/gpu/drm/i915/i915_reg.h | 36 ++++++++++++------------------------
 2 files changed, 16 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 3f1b6ee157ba..084e322ec15b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1401,11 +1401,11 @@ static bool icp_ddi_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
 	switch (pin) {
 	case HPD_PORT_A:
-		return val & ICP_DDIA_HPD_LONG_DETECT;
+		return val & SHOTPLUG_CTL_DDI_HPD_LONG_DETECT(PORT_A);
 	case HPD_PORT_B:
-		return val & ICP_DDIB_HPD_LONG_DETECT;
+		return val & SHOTPLUG_CTL_DDI_HPD_LONG_DETECT(PORT_B);
 	case HPD_PORT_C:
-		return val & TGP_DDIC_HPD_LONG_DETECT;
+		return val & SHOTPLUG_CTL_DDI_HPD_LONG_DETECT(PORT_C);
 	default:
 		return false;
 	}
@@ -1427,20 +1427,6 @@ static bool icp_tc_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 	}
 }
 
-static bool tgp_ddi_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
-{
-	switch (pin) {
-	case HPD_PORT_A:
-		return val & ICP_DDIA_HPD_LONG_DETECT;
-	case HPD_PORT_B:
-		return val & ICP_DDIB_HPD_LONG_DETECT;
-	case HPD_PORT_C:
-		return val & TGP_DDIC_HPD_LONG_DETECT;
-	default:
-		return false;
-	}
-}
-
 static bool tgp_tc_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
 	switch (pin) {
@@ -2318,7 +2304,7 @@ static void tgp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
 				   ddi_hotplug_trigger,
 				   dig_hotplug_reg, hpd_tgp,
-				   tgp_ddi_port_hotplug_long_detect);
+				   icp_ddi_port_hotplug_long_detect);
 	}
 
 	if (tc_hotplug_trigger) {
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 3cfdab18c0cf..946beb9e295e 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7928,26 +7928,13 @@ enum {
  * SHOTPLUG_CTL_DDI and SHOTPLUG_CTL_TC.
  */
 
-#define SHOTPLUG_CTL_DDI			_MMIO(0xc4030)
-#define   TGP_DDIC_HPD_ENABLE			(1 << 11)
-#define   TGP_DDIC_HPD_STATUS_MASK		(3 << 8)
-#define   TGP_DDIC_HPD_NO_DETECT		(0 << 8)
-#define   TGP_DDIC_HPD_SHORT_DETECT		(1 << 8)
-#define   TGP_DDIC_HPD_LONG_DETECT		(2 << 8)
-#define   TGP_DDIC_HPD_SHORT_LONG_DETECT	(3 << 8)
-#define   ICP_DDIB_HPD_ENABLE			(1 << 7)
-#define   ICP_DDIB_HPD_STATUS_MASK		(3 << 4)
-#define   ICP_DDIB_HPD_NO_DETECT		(0 << 4)
-#define   ICP_DDIB_HPD_SHORT_DETECT		(1 << 4)
-#define   ICP_DDIB_HPD_LONG_DETECT		(2 << 4)
-#define   ICP_DDIB_HPD_SHORT_LONG_DETECT	(3 << 4)
-#define   ICP_DDIA_HPD_ENABLE			(1 << 3)
-#define   ICP_DDIA_HPD_OP_DRIVE_1		(1 << 2)
-#define   ICP_DDIA_HPD_STATUS_MASK		(3 << 0)
-#define   ICP_DDIA_HPD_NO_DETECT		(0 << 0)
-#define   ICP_DDIA_HPD_SHORT_DETECT		(1 << 0)
-#define   ICP_DDIA_HPD_LONG_DETECT		(2 << 0)
-#define   ICP_DDIA_HPD_SHORT_LONG_DETECT	(3 << 0)
+#define SHOTPLUG_CTL_DDI				_MMIO(0xc4030)
+#define   SHOTPLUG_CTL_DDI_HPD_ENABLE(port)		(0x8 << (4 * (port)))
+#define   SHOTPLUG_CTL_DDI_HPD_STATUS_MASK(port)	(0x3 << (4 * (port)))
+#define   SHOTPLUG_CTL_DDI_HPD_NO_DETECT(port)		(0x0 << (4 * (port)))
+#define   SHOTPLUG_CTL_DDI_HPD_SHORT_DETECT(port)	(0x1 << (4 * (port)))
+#define   SHOTPLUG_CTL_DDI_HPD_LONG_DETECT(port)	(0x2 << (4 * (port)))
+#define   SHOTPLUG_CTL_DDI_HPD_SHORT_LONG_DETECT(port)	(0x3 << (4 * (port)))
 
 #define SHOTPLUG_CTL_TC				_MMIO(0xc4034)
 #define   ICP_TC_HPD_ENABLE(tc_port)		(8 << (tc_port) * 4)
@@ -8058,14 +8045,15 @@ enum {
 #define   ICP_TC_HPD_LONG_DETECT(tc_port)	(2 << (tc_port) * 4)
 #define   ICP_TC_HPD_SHORT_DETECT(tc_port)	(1 << (tc_port) * 4)
 
-#define ICP_DDI_HPD_ENABLE_MASK		(ICP_DDIB_HPD_ENABLE |	\
-					 ICP_DDIA_HPD_ENABLE)
+#define ICP_DDI_HPD_ENABLE_MASK		(SHOTPLUG_CTL_DDI_HPD_ENABLE(PORT_B) | \
+					 SHOTPLUG_CTL_DDI_HPD_ENABLE(PORT_A))
 #define ICP_TC_HPD_ENABLE_MASK		(ICP_TC_HPD_ENABLE(PORT_TC4) | \
 					 ICP_TC_HPD_ENABLE(PORT_TC3) | \
 					 ICP_TC_HPD_ENABLE(PORT_TC2) | \
 					 ICP_TC_HPD_ENABLE(PORT_TC1))
-#define TGP_DDI_HPD_ENABLE_MASK		(TGP_DDIC_HPD_ENABLE |	\
-					 ICP_DDI_HPD_ENABLE_MASK)
+#define TGP_DDI_HPD_ENABLE_MASK		(SHOTPLUG_CTL_DDI_HPD_ENABLE(PORT_C) | \
+					 SHOTPLUG_CTL_DDI_HPD_ENABLE(PORT_B) | \
+					 SHOTPLUG_CTL_DDI_HPD_ENABLE(PORT_A))
 #define TGP_TC_HPD_ENABLE_MASK		(ICP_TC_HPD_ENABLE(PORT_TC6) | \
 					 ICP_TC_HPD_ENABLE(PORT_TC5) | \
 					 ICP_TC_HPD_ENABLE_MASK)
-- 
cgit v1.2.3


From 58676af69c2eb1e0202215fcfc1d421f186226ed Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 29 Aug 2019 14:15:24 -0700
Subject: drm/i915: unify icp, tgp and mcc irq handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The differences are only on the pins, trigger and long_detect function.
The MCC handling is already partially merged, so merge TGP as well.
Remove the pins argument from icp_irq_handler() so we have all the
differences between the 3 set in a common if ladder.

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190829211526.30525-2-jose.souza@intel.com
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c | 65 ++++++++++-------------------------------
 1 file changed, 16 insertions(+), 49 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 084e322ec15b..5f590987dcd5 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2243,19 +2243,27 @@ static void cpt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		cpt_serr_int_handler(dev_priv);
 }
 
-static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir,
-			    const u32 *pins)
+static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 {
-	u32 ddi_hotplug_trigger;
-	u32 tc_hotplug_trigger;
+	u32 ddi_hotplug_trigger, tc_hotplug_trigger;
 	u32 pin_mask = 0, long_mask = 0;
+	bool (*tc_port_hotplug_long_detect)(enum hpd_pin pin, u32 val);
+	const u32 *pins;
 
-	if (HAS_PCH_MCC(dev_priv)) {
+	if (HAS_PCH_TGP(dev_priv)) {
+		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_TGP;
+		tc_hotplug_trigger = pch_iir & SDE_TC_MASK_TGP;
+		tc_port_hotplug_long_detect = tgp_tc_port_hotplug_long_detect;
+		pins = hpd_tgp;
+	} else if (HAS_PCH_MCC(dev_priv)) {
 		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_TGP;
 		tc_hotplug_trigger = 0;
+		pins = hpd_mcc;
 	} else {
 		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP;
 		tc_hotplug_trigger = pch_iir & SDE_TC_MASK_ICP;
+		tc_port_hotplug_long_detect = icp_tc_port_hotplug_long_detect;
+		pins = hpd_icp;
 	}
 
 	if (ddi_hotplug_trigger) {
@@ -2279,44 +2287,7 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir,
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
 				   tc_hotplug_trigger,
 				   dig_hotplug_reg, pins,
-				   icp_tc_port_hotplug_long_detect);
-	}
-
-	if (pin_mask)
-		intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
-
-	if (pch_iir & SDE_GMBUS_ICP)
-		gmbus_irq_handler(dev_priv);
-}
-
-static void tgp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
-{
-	u32 ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_TGP;
-	u32 tc_hotplug_trigger = pch_iir & SDE_TC_MASK_TGP;
-	u32 pin_mask = 0, long_mask = 0;
-
-	if (ddi_hotplug_trigger) {
-		u32 dig_hotplug_reg;
-
-		dig_hotplug_reg = I915_READ(SHOTPLUG_CTL_DDI);
-		I915_WRITE(SHOTPLUG_CTL_DDI, dig_hotplug_reg);
-
-		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
-				   ddi_hotplug_trigger,
-				   dig_hotplug_reg, hpd_tgp,
-				   icp_ddi_port_hotplug_long_detect);
-	}
-
-	if (tc_hotplug_trigger) {
-		u32 dig_hotplug_reg;
-
-		dig_hotplug_reg = I915_READ(SHOTPLUG_CTL_TC);
-		I915_WRITE(SHOTPLUG_CTL_TC, dig_hotplug_reg);
-
-		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
-				   tc_hotplug_trigger,
-				   dig_hotplug_reg, hpd_tgp,
-				   tgp_tc_port_hotplug_long_detect);
+				   tc_port_hotplug_long_detect);
 	}
 
 	if (pin_mask)
@@ -2767,12 +2738,8 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 			I915_WRITE(SDEIIR, iir);
 			ret = IRQ_HANDLED;
 
-			if (INTEL_PCH_TYPE(dev_priv) >= PCH_TGP)
-				tgp_irq_handler(dev_priv, iir);
-			else if (INTEL_PCH_TYPE(dev_priv) >= PCH_MCC)
-				icp_irq_handler(dev_priv, iir, hpd_mcc);
-			else if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
-				icp_irq_handler(dev_priv, iir, hpd_icp);
+			if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
+				icp_irq_handler(dev_priv, iir);
 			else if (INTEL_PCH_TYPE(dev_priv) >= PCH_SPT)
 				spt_irq_handler(dev_priv, iir);
 			else
-- 
cgit v1.2.3


From b32821c036310c49cdc45639b1d451b21fc3f17b Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 29 Aug 2019 14:15:25 -0700
Subject: drm/i915: parameterize SDE hotplug registers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Ice Lake, Tiger Lake and Elkhart Lake all have different port
configurations and all of them can be parameterized the same way to form
the SDE hotplug bitmask. Avoid making them a special case an just use
the parameterized macros.

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190829211526.30525-3-jose.souza@intel.com
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c | 36 ++++++++++++++++++------------------
 drivers/gpu/drm/i915/i915_reg.h | 35 +++++++++++++++--------------------
 2 files changed, 33 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 5f590987dcd5..541382832126 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -149,30 +149,30 @@ static const u32 hpd_gen12[HPD_NUM_PINS] = {
 };
 
 static const u32 hpd_icp[HPD_NUM_PINS] = {
-	[HPD_PORT_A] = SDE_DDIA_HOTPLUG_ICP,
-	[HPD_PORT_B] = SDE_DDIB_HOTPLUG_ICP,
-	[HPD_PORT_C] = SDE_TC1_HOTPLUG_ICP,
-	[HPD_PORT_D] = SDE_TC2_HOTPLUG_ICP,
-	[HPD_PORT_E] = SDE_TC3_HOTPLUG_ICP,
-	[HPD_PORT_F] = SDE_TC4_HOTPLUG_ICP
+	[HPD_PORT_A] = SDE_DDI_HOTPLUG_ICP(PORT_A),
+	[HPD_PORT_B] = SDE_DDI_HOTPLUG_ICP(PORT_B),
+	[HPD_PORT_C] = SDE_TC_HOTPLUG_ICP(PORT_TC1),
+	[HPD_PORT_D] = SDE_TC_HOTPLUG_ICP(PORT_TC2),
+	[HPD_PORT_E] = SDE_TC_HOTPLUG_ICP(PORT_TC3),
+	[HPD_PORT_F] = SDE_TC_HOTPLUG_ICP(PORT_TC4),
 };
 
 static const u32 hpd_mcc[HPD_NUM_PINS] = {
-	[HPD_PORT_A] = SDE_DDIA_HOTPLUG_ICP,
-	[HPD_PORT_B] = SDE_DDIB_HOTPLUG_ICP,
-	[HPD_PORT_C] = SDE_TC1_HOTPLUG_ICP
+	[HPD_PORT_A] = SDE_DDI_HOTPLUG_ICP(PORT_A),
+	[HPD_PORT_B] = SDE_DDI_HOTPLUG_ICP(PORT_B),
+	[HPD_PORT_C] = SDE_TC_HOTPLUG_ICP(PORT_TC1),
 };
 
 static const u32 hpd_tgp[HPD_NUM_PINS] = {
-	[HPD_PORT_A] = SDE_DDIA_HOTPLUG_ICP,
-	[HPD_PORT_B] = SDE_DDIB_HOTPLUG_ICP,
-	[HPD_PORT_C] = SDE_DDIC_HOTPLUG_TGP,
-	[HPD_PORT_D] = SDE_TC1_HOTPLUG_ICP,
-	[HPD_PORT_E] = SDE_TC2_HOTPLUG_ICP,
-	[HPD_PORT_F] = SDE_TC3_HOTPLUG_ICP,
-	[HPD_PORT_G] = SDE_TC4_HOTPLUG_ICP,
-	[HPD_PORT_H] = SDE_TC5_HOTPLUG_TGP,
-	[HPD_PORT_I] = SDE_TC6_HOTPLUG_TGP,
+	[HPD_PORT_A] = SDE_DDI_HOTPLUG_ICP(PORT_A),
+	[HPD_PORT_B] = SDE_DDI_HOTPLUG_ICP(PORT_B),
+	[HPD_PORT_C] = SDE_DDI_HOTPLUG_ICP(PORT_C),
+	[HPD_PORT_D] = SDE_TC_HOTPLUG_ICP(PORT_TC1),
+	[HPD_PORT_E] = SDE_TC_HOTPLUG_ICP(PORT_TC2),
+	[HPD_PORT_F] = SDE_TC_HOTPLUG_ICP(PORT_TC3),
+	[HPD_PORT_G] = SDE_TC_HOTPLUG_ICP(PORT_TC4),
+	[HPD_PORT_H] = SDE_TC_HOTPLUG_ICP(PORT_TC5),
+	[HPD_PORT_I] = SDE_TC_HOTPLUG_ICP(PORT_TC6),
 };
 
 void gen3_irq_reset(struct intel_uncore *uncore, i915_reg_t imr,
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 946beb9e295e..53735433fe20 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7839,29 +7839,24 @@ enum {
 				 SDE_FDI_RXA_CPT)
 
 /* south display engine interrupt: ICP/TGP */
-#define SDE_TC6_HOTPLUG_TGP		(1 << 29)
-#define SDE_TC5_HOTPLUG_TGP		(1 << 28)
-#define SDE_TC4_HOTPLUG_ICP		(1 << 27)
-#define SDE_TC3_HOTPLUG_ICP		(1 << 26)
-#define SDE_TC2_HOTPLUG_ICP		(1 << 25)
-#define SDE_TC1_HOTPLUG_ICP		(1 << 24)
 #define SDE_GMBUS_ICP			(1 << 23)
-#define SDE_DDIC_HOTPLUG_TGP		(1 << 18)
-#define SDE_DDIB_HOTPLUG_ICP		(1 << 17)
-#define SDE_DDIA_HOTPLUG_ICP		(1 << 16)
 #define SDE_TC_HOTPLUG_ICP(tc_port)	(1 << ((tc_port) + 24))
 #define SDE_DDI_HOTPLUG_ICP(port)	(1 << ((port) + 16))
-#define SDE_DDI_MASK_ICP		(SDE_DDIB_HOTPLUG_ICP |	\
-					 SDE_DDIA_HOTPLUG_ICP)
-#define SDE_TC_MASK_ICP			(SDE_TC4_HOTPLUG_ICP |	\
-					 SDE_TC3_HOTPLUG_ICP |	\
-					 SDE_TC2_HOTPLUG_ICP |	\
-					 SDE_TC1_HOTPLUG_ICP)
-#define SDE_DDI_MASK_TGP		(SDE_DDIC_HOTPLUG_TGP | \
-					 SDE_DDI_MASK_ICP)
-#define SDE_TC_MASK_TGP			(SDE_TC6_HOTPLUG_TGP |	\
-					 SDE_TC5_HOTPLUG_TGP |	\
-					 SDE_TC_MASK_ICP)
+#define SDE_DDI_MASK_ICP		(SDE_DDI_HOTPLUG_ICP(PORT_B) | \
+					 SDE_DDI_HOTPLUG_ICP(PORT_A))
+#define SDE_TC_MASK_ICP			(SDE_TC_HOTPLUG_ICP(PORT_TC4) | \
+					 SDE_TC_HOTPLUG_ICP(PORT_TC3) | \
+					 SDE_TC_HOTPLUG_ICP(PORT_TC2) | \
+					 SDE_TC_HOTPLUG_ICP(PORT_TC1))
+#define SDE_DDI_MASK_TGP		(SDE_DDI_HOTPLUG_ICP(PORT_C) | \
+					 SDE_DDI_HOTPLUG_ICP(PORT_B) | \
+					 SDE_DDI_HOTPLUG_ICP(PORT_A))
+#define SDE_TC_MASK_TGP			(SDE_TC_HOTPLUG_ICP(PORT_TC6) | \
+					 SDE_TC_HOTPLUG_ICP(PORT_TC5) | \
+					 SDE_TC_HOTPLUG_ICP(PORT_TC4) | \
+					 SDE_TC_HOTPLUG_ICP(PORT_TC3) | \
+					 SDE_TC_HOTPLUG_ICP(PORT_TC2) | \
+					 SDE_TC_HOTPLUG_ICP(PORT_TC1))
 
 #define SDEISR  _MMIO(0xc4000)
 #define SDEIMR  _MMIO(0xc4004)
-- 
cgit v1.2.3


From 40e98130c32889e4ed128d129b824107b90501fe Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 29 Aug 2019 14:15:26 -0700
Subject: drm/i915: unify icp, tgp and mcc irq setup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use a single function to setup the SDE irq and make MCC, ICP and TGP use
it, just like was done for the irq handler.

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190829211526.30525-4-jose.souza@intel.com
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c | 50 +++++++++++++++++------------------------
 1 file changed, 21 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 541382832126..135c9ee55e07 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3385,42 +3385,31 @@ static void icp_hpd_detection_setup(struct drm_i915_private *dev_priv,
 	}
 }
 
-static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv)
+static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv,
+			      u32 sde_ddi_mask, u32 sde_tc_mask,
+			      u32 ddi_enable_mask, u32 tc_enable_mask,
+			      const u32 *pins)
 {
 	u32 hotplug_irqs, enabled_irqs;
 
-	hotplug_irqs = SDE_DDI_MASK_ICP | SDE_TC_MASK_ICP;
-	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_icp);
+	hotplug_irqs = sde_ddi_mask | sde_tc_mask;
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, pins);
 
 	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
 
-	icp_hpd_detection_setup(dev_priv, ICP_DDI_HPD_ENABLE_MASK,
-				ICP_TC_HPD_ENABLE_MASK);
+	icp_hpd_detection_setup(dev_priv, ddi_enable_mask, tc_enable_mask);
 }
 
+/*
+ * EHL doesn't need most of gen11_hpd_irq_setup, it's handling only the
+ * equivalent of SDE.
+ */
 static void mcc_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
-	u32 hotplug_irqs, enabled_irqs;
-
-	hotplug_irqs = SDE_DDI_MASK_TGP;
-	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_mcc);
-
-	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
-
-	icp_hpd_detection_setup(dev_priv, TGP_DDI_HPD_ENABLE_MASK, 0);
-}
-
-static void tgp_hpd_irq_setup(struct drm_i915_private *dev_priv)
-{
-	u32 hotplug_irqs, enabled_irqs;
-
-	hotplug_irqs = SDE_DDI_MASK_TGP | SDE_TC_MASK_TGP;
-	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_tgp);
-
-	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
-
-	icp_hpd_detection_setup(dev_priv, TGP_DDI_HPD_ENABLE_MASK,
-				TGP_TC_HPD_ENABLE_MASK);
+	icp_hpd_irq_setup(dev_priv,
+			  SDE_DDI_MASK_TGP, 0,
+			  TGP_DDI_HPD_ENABLE_MASK, 0,
+			  hpd_mcc);
 }
 
 static void gen11_hpd_detection_setup(struct drm_i915_private *dev_priv)
@@ -3460,9 +3449,13 @@ static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
 	gen11_hpd_detection_setup(dev_priv);
 
 	if (INTEL_PCH_TYPE(dev_priv) >= PCH_TGP)
-		tgp_hpd_irq_setup(dev_priv);
+		icp_hpd_irq_setup(dev_priv, SDE_DDI_MASK_TGP, SDE_TC_MASK_TGP,
+				  TGP_DDI_HPD_ENABLE_MASK,
+				  TGP_TC_HPD_ENABLE_MASK, hpd_tgp);
 	else if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
-		icp_hpd_irq_setup(dev_priv);
+		icp_hpd_irq_setup(dev_priv, SDE_DDI_MASK_ICP, SDE_TC_MASK_ICP,
+				  ICP_DDI_HPD_ENABLE_MASK,
+				  ICP_TC_HPD_ENABLE_MASK, hpd_icp);
 }
 
 static void spt_hpd_detection_setup(struct drm_i915_private *dev_priv)
@@ -4340,7 +4333,6 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 			dev_priv->display.hpd_irq_setup = i915_hpd_irq_setup;
 	} else {
 		if (HAS_PCH_MCC(dev_priv))
-			/* EHL doesn't need most of gen11_hpd_irq_setup */
 			dev_priv->display.hpd_irq_setup = mcc_hpd_irq_setup;
 		else if (INTEL_GEN(dev_priv) >= 11)
 			dev_priv->display.hpd_irq_setup = gen11_hpd_irq_setup;
-- 
cgit v1.2.3


From 3dc007fe9b2b256d2779bb9e9a0d372eb1d90643 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 30 Aug 2019 18:59:58 +0100
Subject: drm/i915/gtt: Downgrade gen7 (ivb, byt, hsw) back to aliasing-ppgtt

With the upcoming change in timing (dramatically reducing the latency
between manipulating the ppGTT and execution), no amount of tweaking
could save Baytrail, it would always fail to invalidate its TLB. Ville
was right, Baytrail is beyond hope.

v2: Rollback on all gen7; same timing instability on TLB invalidation.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190830180000.24608-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 63 +++++++++---------------------
 drivers/gpu/drm/i915/i915_pci.c            |  4 +-
 2 files changed, 20 insertions(+), 47 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index 601c16239fdf..ac55a0d054bd 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -1741,46 +1741,22 @@ static int remap_l3(struct i915_request *rq)
 
 static int switch_context(struct i915_request *rq)
 {
-	struct intel_engine_cs *engine = rq->engine;
-	struct i915_address_space *vm = vm_alias(rq->hw_context);
-	unsigned int unwind_mm = 0;
-	u32 hw_flags = 0;
+	struct intel_context *ce = rq->hw_context;
+	struct i915_address_space *vm = vm_alias(ce);
 	int ret;
 
 	GEM_BUG_ON(HAS_EXECLISTS(rq->i915));
 
 	if (vm) {
-		struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
-		int loops;
-
-		/*
-		 * Baytail takes a little more convincing that it really needs
-		 * to reload the PD between contexts. It is not just a little
-		 * longer, as adding more stalls after the load_pd_dir (i.e.
-		 * adding a long loop around flush_pd_dir) is not as effective
-		 * as reloading the PD umpteen times. 32 is derived from
-		 * experimentation (gem_exec_parallel/fds) and has no good
-		 * explanation.
-		 */
-		loops = 1;
-		if (engine->id == BCS0 && IS_VALLEYVIEW(engine->i915))
-			loops = 32;
-
-		do {
-			ret = load_pd_dir(rq, ppgtt);
-			if (ret)
-				goto err;
-		} while (--loops);
-
-		if (ppgtt->pd_dirty_engines & engine->mask) {
-			unwind_mm = engine->mask;
-			ppgtt->pd_dirty_engines &= ~unwind_mm;
-			hw_flags = MI_FORCE_RESTORE;
-		}
+		ret = load_pd_dir(rq, i915_vm_to_ppgtt(vm));
+		if (ret)
+			return ret;
 	}
 
-	if (rq->hw_context->state) {
-		GEM_BUG_ON(engine->id != RCS0);
+	if (ce->state) {
+		u32 hw_flags;
+
+		GEM_BUG_ON(rq->engine->id != RCS0);
 
 		/*
 		 * The kernel context(s) is treated as pure scratch and is not
@@ -1789,22 +1765,25 @@ static int switch_context(struct i915_request *rq)
 		 * as nothing actually executes using the kernel context; it
 		 * is purely used for flushing user contexts.
 		 */
+		hw_flags = 0;
 		if (i915_gem_context_is_kernel(rq->gem_context))
 			hw_flags = MI_RESTORE_INHIBIT;
 
 		ret = mi_set_context(rq, hw_flags);
 		if (ret)
-			goto err_mm;
+			return ret;
 	}
 
 	if (vm) {
+		struct intel_engine_cs *engine = rq->engine;
+
 		ret = engine->emit_flush(rq, EMIT_INVALIDATE);
 		if (ret)
-			goto err_mm;
+			return ret;
 
 		ret = flush_pd_dir(rq);
 		if (ret)
-			goto err_mm;
+			return ret;
 
 		/*
 		 * Not only do we need a full barrier (post-sync write) after
@@ -1816,24 +1795,18 @@ static int switch_context(struct i915_request *rq)
 		 */
 		ret = engine->emit_flush(rq, EMIT_INVALIDATE);
 		if (ret)
-			goto err_mm;
+			return ret;
 
 		ret = engine->emit_flush(rq, EMIT_FLUSH);
 		if (ret)
-			goto err_mm;
+			return ret;
 	}
 
 	ret = remap_l3(rq);
 	if (ret)
-		goto err_mm;
+		return ret;
 
 	return 0;
-
-err_mm:
-	if (unwind_mm)
-		i915_vm_to_ppgtt(vm)->pd_dirty_engines |= unwind_mm;
-err:
-	return ret;
 }
 
 static int ring_request_alloc(struct i915_request *request)
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 1974e4c78a43..18212c39a9ba 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -420,7 +420,7 @@ static const struct intel_device_info intel_sandybridge_m_gt2_info = {
 	.has_rc6 = 1, \
 	.has_rc6p = 1, \
 	.has_rps = true, \
-	.ppgtt_type = INTEL_PPGTT_FULL, \
+	.ppgtt_type = INTEL_PPGTT_ALIASING, \
 	.ppgtt_size = 31, \
 	IVB_PIPE_OFFSETS, \
 	IVB_CURSOR_OFFSETS, \
@@ -476,7 +476,7 @@ static const struct intel_device_info intel_valleyview_info = {
 	.has_rps = true,
 	.display.has_gmch = 1,
 	.display.has_hotplug = 1,
-	.ppgtt_type = INTEL_PPGTT_FULL,
+	.ppgtt_type = INTEL_PPGTT_ALIASING,
 	.ppgtt_size = 31,
 	.has_snoop = true,
 	.has_coherent_ggtt = false,
-- 
cgit v1.2.3


From 0b718ba1e884f64dce27c19311dd2859b87e56b9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 30 Aug 2019 18:59:59 +0100
Subject: drm/i915/gtt: Downgrade Cherryview back to aliasing-ppgtt

With the upcoming change in timing (dramatically reducing the latency
between manipulating the ppGTT and execution), no amount of tweaking
could save Cherryview, it would always fail to invalidate its TLB.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190830180000.24608-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 69 ++++++-------------------------------
 drivers/gpu/drm/i915/i915_pci.c     |  2 +-
 2 files changed, 11 insertions(+), 60 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 7d460b1842dd..0e28263c7b87 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1871,60 +1871,6 @@ static int gen8_emit_init_breadcrumb(struct i915_request *rq)
 	return 0;
 }
 
-static int emit_pdps(struct i915_request *rq)
-{
-	const struct intel_engine_cs * const engine = rq->engine;
-	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(rq->hw_context->vm);
-	int err, i;
-	u32 *cs;
-
-	GEM_BUG_ON(intel_vgpu_active(rq->i915));
-
-	/*
-	 * Beware ye of the dragons, this sequence is magic!
-	 *
-	 * Small changes to this sequence can cause anything from
-	 * GPU hangs to forcewake errors and machine lockups!
-	 */
-
-	/* Flush any residual operations from the context load */
-	err = engine->emit_flush(rq, EMIT_FLUSH);
-	if (err)
-		return err;
-
-	/* Magic required to prevent forcewake errors! */
-	err = engine->emit_flush(rq, EMIT_INVALIDATE);
-	if (err)
-		return err;
-
-	cs = intel_ring_begin(rq, 4 * GEN8_3LVL_PDPES + 2);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	/* Ensure the LRI have landed before we invalidate & continue */
-	*cs++ = MI_LOAD_REGISTER_IMM(2 * GEN8_3LVL_PDPES) | MI_LRI_FORCE_POSTED;
-	for (i = GEN8_3LVL_PDPES; i--; ) {
-		const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i);
-		u32 base = engine->mmio_base;
-
-		*cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, i));
-		*cs++ = upper_32_bits(pd_daddr);
-		*cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, i));
-		*cs++ = lower_32_bits(pd_daddr);
-	}
-	*cs++ = MI_NOOP;
-
-	intel_ring_advance(rq, cs);
-
-	/* Be doubly sure the LRI have landed before proceeding */
-	err = engine->emit_flush(rq, EMIT_FLUSH);
-	if (err)
-		return err;
-
-	/* Re-invalidate the TLB for luck */
-	return engine->emit_flush(rq, EMIT_INVALIDATE);
-}
-
 static int execlists_request_alloc(struct i915_request *request)
 {
 	int ret;
@@ -1947,10 +1893,7 @@ static int execlists_request_alloc(struct i915_request *request)
 	 */
 
 	/* Unconditionally invalidate GPU caches and TLBs. */
-	if (i915_vm_is_4lvl(request->hw_context->vm))
-		ret = request->engine->emit_flush(request, EMIT_INVALIDATE);
-	else
-		ret = emit_pdps(request);
+	ret = request->engine->emit_flush(request, EMIT_INVALIDATE);
 	if (ret)
 		return ret;
 
@@ -3167,12 +3110,20 @@ static u32 intel_lr_indirect_ctx_offset(struct intel_engine_cs *engine)
 	return indirect_ctx_offset;
 }
 
+static struct i915_ppgtt *vm_alias(struct i915_address_space *vm)
+{
+	if (i915_is_ggtt(vm))
+		return i915_vm_to_ggtt(vm)->alias;
+	else
+		return i915_vm_to_ppgtt(vm);
+}
+
 static void execlists_init_reg_state(u32 *regs,
 				     struct intel_context *ce,
 				     struct intel_engine_cs *engine,
 				     struct intel_ring *ring)
 {
-	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(ce->vm);
+	struct i915_ppgtt *ppgtt = vm_alias(ce->vm);
 	bool rcs = engine->class == RENDER_CLASS;
 	u32 base = engine->mmio_base;
 
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 18212c39a9ba..fbe98a2db88e 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -570,7 +570,7 @@ static const struct intel_device_info intel_cherryview_info = {
 	.has_rps = true,
 	.has_logical_ring_contexts = 1,
 	.display.has_gmch = 1,
-	.ppgtt_type = INTEL_PPGTT_FULL,
+	.ppgtt_type = INTEL_PPGTT_ALIASING,
 	.ppgtt_size = 32,
 	.has_reset_engine = 1,
 	.has_snoop = true,
-- 
cgit v1.2.3


From c1d143dd2ac8d481500fec4c0d715ff301d2766f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 30 Aug 2019 19:00:00 +0100
Subject: drm/i915: Remove ppgtt->dirty_engines

This is no longer used anywhere and so can be removed. However, tracking
the dirty status on the ppgtt doesn't work very well if the ppgtt is
shared, so perhaps for the best that it is no longer required.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190830180000.24608-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 16 +---------------
 drivers/gpu/drm/i915/i915_gem_gtt.h |  1 -
 2 files changed, 1 insertion(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 3c50cea76dc5..ee51fd1a6207 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -823,17 +823,6 @@ release_pd_entry(struct i915_page_directory * const pd,
 	return free;
 }
 
-/*
- * PDE TLBs are a pain to invalidate on GEN8+. When we modify
- * the page table structures, we mark them dirty so that
- * context switching/execlist queuing code takes extra steps
- * to ensure that tlbs are flushed.
- */
-static void mark_tlbs_dirty(struct i915_ppgtt *ppgtt)
-{
-	ppgtt->pd_dirty_engines = ALL_ENGINES;
-}
-
 static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
 {
 	struct drm_i915_private *dev_priv = ppgtt->vm.i915;
@@ -1735,10 +1724,8 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 	}
 	spin_unlock(&pd->lock);
 
-	if (flush) {
-		mark_tlbs_dirty(&ppgtt->base);
+	if (flush)
 		gen6_ggtt_invalidate(vm->gt->ggtt);
-	}
 
 	goto out;
 
@@ -1833,7 +1820,6 @@ static int pd_vma_bind(struct i915_vma *vma,
 	gen6_for_all_pdes(pt, ppgtt->base.pd, pde)
 		gen6_write_pde(ppgtt, pde, pt);
 
-	mark_tlbs_dirty(&ppgtt->base);
 	gen6_ggtt_invalidate(ggtt);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 576f6fb95d13..07c85c134d4c 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -422,7 +422,6 @@ struct i915_ggtt {
 struct i915_ppgtt {
 	struct i915_address_space vm;
 
-	intel_engine_mask_t pd_dirty_engines;
 	struct i915_page_directory *pd;
 };
 
-- 
cgit v1.2.3


From aabbe344dc3ca5f7d8263a02608ba6179e8a4499 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 30 Aug 2019 19:03:25 +0100
Subject: drm/i915: Use RCU for unlocked vm_idr lookup

Since i915_address_space is now RCU protected, we can do the vm_idr lookup
without taking the vm_idr_mutex, just with the rcu_read_lock() instead.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190830180325.7755-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 1f735ca9b173..b8969605f4e8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1057,14 +1057,11 @@ static int set_ppgtt(struct drm_i915_file_private *file_priv,
 	if (upper_32_bits(args->value))
 		return -ENOENT;
 
-	err = mutex_lock_interruptible(&file_priv->vm_idr_lock);
-	if (err)
-		return err;
-
+	rcu_read_lock();
 	vm = idr_find(&file_priv->vm_idr, args->value);
-	if (vm)
-		i915_vm_get(vm);
-	mutex_unlock(&file_priv->vm_idr_lock);
+	if (vm && !kref_get_unless_zero(&vm->ref))
+		vm = NULL;
+	rcu_read_unlock();
 	if (!vm)
 		return -ENOENT;
 
-- 
cgit v1.2.3


From 7bff9779d76917adfa7c67712aa6ae3b7e5098ba Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Fri, 30 Aug 2019 12:16:44 +0200
Subject: drm/i915: Fix regression with crtc disable ordering
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When we moved the code to disable crtc's to a separate patch,
we forgot to ensure that for_each_oldnew_intel_crtc_in_state_reverse()
was moved as well.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Fixes: 66d9cec8a6c9 ("drm/i915/display: Move the commit_tail() disable sequence to separate function")
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190830101644.8740-1-maarten.lankhorst@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index b38d842ff6ec..e661e2099118 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -13784,7 +13784,15 @@ static void intel_commit_modeset_disables(struct intel_atomic_state *state)
 	struct intel_crtc *crtc;
 	int i;
 
-	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+	/*
+	 * Disable CRTC/pipes in reverse order because some features(MST in
+	 * TGL+) requires master and slave relationship between pipes, so it
+	 * should always pick the lowest pipe as master as it will be enabled
+	 * first and disable in the reverse order so the master will be the
+	 * last one to be disabled.
+	 */
+	for_each_oldnew_intel_crtc_in_state_reverse(state, crtc, old_crtc_state,
+						    new_crtc_state, i) {
 		if (!needs_modeset(new_crtc_state))
 			continue;
 
@@ -13963,15 +13971,8 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	if (state->modeset)
 		wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_MODESET);
 
-	/*
-	 * Disable CRTC/pipes in reverse order because some features(MST in
-	 * TGL+) requires master and slave relationship between pipes, so it
-	 * should always pick the lowest pipe as master as it will be enabled
-	 * first and disable in the reverse order so the master will be the
-	 * last one to be disabled.
-	 */
-	for_each_oldnew_intel_crtc_in_state_reverse(state, crtc, old_crtc_state,
-						    new_crtc_state, i) {
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
 		if (needs_modeset(new_crtc_state) ||
 		    new_crtc_state->update_pipe) {
 
-- 
cgit v1.2.3


From 385ba629aa1cdca5373c1fdbf6693ade5062ad27 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Thu, 29 Aug 2019 17:48:28 -0700
Subject: drm/i915: Allow /2 CD2X divider on gen11+
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The bspec has just recently been updated with new cdclk values that
require the use of a /2 CD2X divider rather than a /1 divider.  Once we
add the divider selection logic to ICL+ cdclk programming, we have
pretty much the same logic we were already using on CNL, so it's simpler
to drop icl_set_cdclk() completely and reuse cnl_set_cdclk() on gen11+
platforms as well.

v2:
 - Using ICL_CDCLK_CD2X_PIPE_NONE + BXT_CDCLK_CD2X_PIPE(pipe) for TGL is
   correct, but looks really confusing.  Add some TGL_ macros that alias
   these to avoid confusion.  (Ville)
 - Use DIV_ROUND_CLOSEST rather than / when applying the divider. (Ville)

Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190830004828.19359-1-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 90 ++++++++++++------------------
 drivers/gpu/drm/i915/i915_reg.h            |  3 +
 2 files changed, 38 insertions(+), 55 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 939088c7d814..58ba42dcf23f 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1659,10 +1659,23 @@ static void cnl_set_cdclk(struct drm_i915_private *dev_priv,
 		cnl_cdclk_pll_enable(dev_priv, vco);
 
 	val = divider | skl_cdclk_decimal(cdclk);
-	if (pipe == INVALID_PIPE)
-		val |= BXT_CDCLK_CD2X_PIPE_NONE;
-	else
-		val |= BXT_CDCLK_CD2X_PIPE(pipe);
+
+	if (INTEL_GEN(dev_priv) >= 12) {
+		if (pipe == INVALID_PIPE)
+			val |= TGL_CDCLK_CD2X_PIPE_NONE;
+		else
+			val |= TGL_CDCLK_CD2X_PIPE(pipe);
+	} else if (INTEL_GEN(dev_priv) >= 11) {
+		if (pipe == INVALID_PIPE)
+			val |= ICL_CDCLK_CD2X_PIPE_NONE;
+		else
+			val |= ICL_CDCLK_CD2X_PIPE(pipe);
+	} else {
+		if (pipe == INVALID_PIPE)
+			val |= BXT_CDCLK_CD2X_PIPE_NONE;
+		else
+			val |= BXT_CDCLK_CD2X_PIPE(pipe);
+	}
 	I915_WRITE(CDCLK_CTL, val);
 
 	if (pipe != INVALID_PIPE)
@@ -1813,51 +1826,6 @@ static int icl_calc_cdclk_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 	return dev_priv->cdclk.hw.ref * ratio;
 }
 
-static void icl_set_cdclk(struct drm_i915_private *dev_priv,
-			  const struct intel_cdclk_state *cdclk_state,
-			  enum pipe pipe)
-{
-	unsigned int cdclk = cdclk_state->cdclk;
-	unsigned int vco = cdclk_state->vco;
-	int ret;
-
-	ret = skl_pcode_request(dev_priv, SKL_PCODE_CDCLK_CONTROL,
-				SKL_CDCLK_PREPARE_FOR_CHANGE,
-				SKL_CDCLK_READY_FOR_CHANGE,
-				SKL_CDCLK_READY_FOR_CHANGE, 3);
-	if (ret) {
-		DRM_ERROR("Failed to inform PCU about cdclk change (%d)\n",
-			  ret);
-		return;
-	}
-
-	if (dev_priv->cdclk.hw.vco != 0 &&
-	    dev_priv->cdclk.hw.vco != vco)
-		cnl_cdclk_pll_disable(dev_priv);
-
-	if (dev_priv->cdclk.hw.vco != vco)
-		cnl_cdclk_pll_enable(dev_priv, vco);
-
-	/*
-	 * On ICL CD2X_DIV can only be 1, so we'll never end up changing the
-	 * divider here synchronized to a pipe while CDCLK is on, nor will we
-	 * need the corresponding vblank wait.
-	 */
-	I915_WRITE(CDCLK_CTL, ICL_CDCLK_CD2X_PIPE_NONE |
-			      skl_cdclk_decimal(cdclk));
-
-	sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL,
-				cdclk_state->voltage_level);
-
-	intel_update_cdclk(dev_priv);
-
-	/*
-	 * Can't read out the voltage level :(
-	 * Let's just assume everything is as expected.
-	 */
-	dev_priv->cdclk.hw.voltage_level = cdclk_state->voltage_level;
-}
-
 static u8 icl_calc_voltage_level(struct drm_i915_private *dev_priv, int cdclk)
 {
 	if (IS_ELKHARTLAKE(dev_priv)) {
@@ -1881,6 +1849,7 @@ static void icl_get_cdclk(struct drm_i915_private *dev_priv,
 			  struct intel_cdclk_state *cdclk_state)
 {
 	u32 val;
+	int div;
 
 	cdclk_state->bypass = 50000;
 
@@ -1914,10 +1883,21 @@ static void icl_get_cdclk(struct drm_i915_private *dev_priv,
 
 	cdclk_state->vco = (val & BXT_DE_PLL_RATIO_MASK) * cdclk_state->ref;
 
-	val = I915_READ(CDCLK_CTL);
-	WARN_ON((val & BXT_CDCLK_CD2X_DIV_SEL_MASK) != 0);
+	val = I915_READ(CDCLK_CTL) & BXT_CDCLK_CD2X_DIV_SEL_MASK;
+	switch (val) {
+	case BXT_CDCLK_CD2X_DIV_SEL_1:
+		div = 2;
+		break;
+	case BXT_CDCLK_CD2X_DIV_SEL_2:
+		div = 4;
+		break;
+	default:
+		MISSING_CASE(val);
+		div = 2;
+		break;
+	}
 
-	cdclk_state->cdclk = cdclk_state->vco / 2;
+	cdclk_state->cdclk = DIV_ROUND_CLOSEST(cdclk_state->vco, div);
 
 out:
 	/*
@@ -1963,7 +1943,7 @@ sanitize:
 				icl_calc_voltage_level(dev_priv,
 						       sanitized_state.cdclk);
 
-	icl_set_cdclk(dev_priv, &sanitized_state, INVALID_PIPE);
+	cnl_set_cdclk(dev_priv, &sanitized_state, INVALID_PIPE);
 }
 
 static void icl_uninit_cdclk(struct drm_i915_private *dev_priv)
@@ -1975,7 +1955,7 @@ static void icl_uninit_cdclk(struct drm_i915_private *dev_priv)
 	cdclk_state.voltage_level = icl_calc_voltage_level(dev_priv,
 							   cdclk_state.cdclk);
 
-	icl_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
+	cnl_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
 
 static void cnl_init_cdclk(struct drm_i915_private *dev_priv)
@@ -2810,7 +2790,7 @@ void intel_update_rawclk(struct drm_i915_private *dev_priv)
 void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 {
 	if (INTEL_GEN(dev_priv) >= 11) {
-		dev_priv->display.set_cdclk = icl_set_cdclk;
+		dev_priv->display.set_cdclk = cnl_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = icl_modeset_calc_cdclk;
 	} else if (IS_CANNONLAKE(dev_priv)) {
 		dev_priv->display.set_cdclk = cnl_set_cdclk;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 53735433fe20..6c43b8c583bb 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -9759,7 +9759,10 @@ enum skl_power_gate {
 #define  BXT_CDCLK_CD2X_PIPE(pipe)	((pipe) << 20)
 #define  CDCLK_DIVMUX_CD_OVERRIDE	(1 << 19)
 #define  BXT_CDCLK_CD2X_PIPE_NONE	BXT_CDCLK_CD2X_PIPE(3)
+#define  ICL_CDCLK_CD2X_PIPE(pipe)	(_PICK(pipe, 0, 2, 6) << 19)
 #define  ICL_CDCLK_CD2X_PIPE_NONE	(7 << 19)
+#define  TGL_CDCLK_CD2X_PIPE(pipe)	BXT_CDCLK_CD2X_PIPE(pipe)
+#define  TGL_CDCLK_CD2X_PIPE_NONE	ICL_CDCLK_CD2X_PIPE_NONE
 #define  BXT_CDCLK_SSA_PRECHARGE_ENABLE	(1 << 16)
 #define  CDCLK_FREQ_DECIMAL_MASK	(0x7ff)
 
-- 
cgit v1.2.3


From 3d1da92baffe69cf847699ceccf4297356da58fa Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Mon, 26 Aug 2019 15:55:40 -0700
Subject: drm/i915: Add 324mhz and 326.4mhz cdclks for gen11+
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The bspec was recently updated with these new cdclk values for ICL, EHL,
and TGL.

Bspec: 20598
Bspec: 49201
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190826225540.11987-3-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 58ba42dcf23f..76f11d465e91 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1761,8 +1761,10 @@ sanitize:
 
 static int icl_calc_cdclk(int min_cdclk, unsigned int ref)
 {
-	static const int ranges_24[] = { 180000, 192000, 312000, 552000, 648000 };
-	static const int ranges_19_38[] = { 172800, 192000, 307200, 556800, 652800 };
+	static const int ranges_24[] = { 180000, 192000, 312000, 324000,
+					 552000, 648000 };
+	static const int ranges_19_38[] = { 172800, 192000, 307200, 326400,
+					    556800, 652800 };
 	const int *ranges;
 	int len, i;
 
@@ -1803,6 +1805,7 @@ static int icl_calc_cdclk_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 		/* fall through */
 	case 172800:
 	case 307200:
+	case 326400:
 	case 556800:
 	case 652800:
 		WARN_ON(dev_priv->cdclk.hw.ref != 19200 &&
@@ -1810,6 +1813,7 @@ static int icl_calc_cdclk_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 		break;
 	case 180000:
 	case 312000:
+	case 324000:
 	case 552000:
 	case 648000:
 		WARN_ON(dev_priv->cdclk.hw.ref != 24000);
-- 
cgit v1.2.3


From dffa8feb308455f9b3ce0eeb55a4eac3afc0786b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 30 Aug 2019 19:19:29 +0100
Subject: drm/i915/perf: Assert locking for i915_init_oa_perf_state()

We use the context->pin_mutex to serialise updates to the OA config and
the registers values written into each new context. Document this
relationship and assert we do hold the context->pin_mutex as used by
gen8_configure_all_contexts() to serialise updates to the OA config
itself.

v2: Add a white-lie for when we call intel_gt_resume() from init.
v3: Lie while we have the context pinned inside atomic reset.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> #v1
Link: https://patchwork.freedesktop.org/patch/msgid/20190830181929.18663-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_gt_pm.c |  7 ++++++-
 drivers/gpu/drm/i915/gt/intel_lrc.c   | 10 ++++++++++
 drivers/gpu/drm/i915/i915_perf.c      |  3 +++
 3 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 1363e069ec83..aa6cf0152ce7 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -6,6 +6,7 @@
 
 #include "i915_drv.h"
 #include "i915_params.h"
+#include "intel_context.h"
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
@@ -142,8 +143,12 @@ int intel_gt_resume(struct intel_gt *gt)
 		intel_engine_pm_get(engine);
 
 		ce = engine->kernel_context;
-		if (ce)
+		if (ce) {
+			GEM_BUG_ON(!intel_context_is_pinned(ce));
+			mutex_acquire(&ce->pin_mutex.dep_map, 0, 0, _THIS_IP_);
 			ce->ops->reset(ce);
+			mutex_release(&ce->pin_mutex.dep_map, 0, _THIS_IP_);
+		}
 
 		engine->serial++; /* kernel context lost */
 		err = engine->resume(engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 0e28263c7b87..87b7473a6dfb 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2383,6 +2383,11 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	ce = rq->hw_context;
 	GEM_BUG_ON(i915_active_is_idle(&ce->active));
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
+
+	/* Proclaim we have exclusive access to the context image! */
+	GEM_BUG_ON(!intel_context_is_pinned(ce));
+	mutex_acquire(&ce->pin_mutex.dep_map, 2, 0, _THIS_IP_);
+
 	rq = active_request(rq);
 	if (!rq) {
 		ce->ring->head = ce->ring->tail;
@@ -2442,6 +2447,7 @@ out_replay:
 		  engine->name, ce->ring->head, ce->ring->tail);
 	intel_ring_update_space(ce->ring);
 	__execlists_update_reg_state(ce, engine);
+	mutex_release(&ce->pin_mutex.dep_map, 0, _THIS_IP_);
 
 unwind:
 	/* Push back any incomplete requests for replay after the reset. */
@@ -3920,6 +3926,9 @@ void intel_lr_context_reset(struct intel_engine_cs *engine,
 			    u32 head,
 			    bool scrub)
 {
+	GEM_BUG_ON(!intel_context_is_pinned(ce));
+	mutex_acquire(&ce->pin_mutex.dep_map, 2, 0, _THIS_IP_);
+
 	/*
 	 * We want a simple context + ring to execute the breadcrumb update.
 	 * We cannot rely on the context being intact across the GPU hang,
@@ -3944,6 +3953,7 @@ void intel_lr_context_reset(struct intel_engine_cs *engine,
 	intel_ring_update_space(ce->ring);
 
 	__execlists_update_reg_state(ce, engine);
+	mutex_release(&ce->pin_mutex.dep_map, 0, _THIS_IP_);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 2c9f46e12622..c1b764233761 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -2305,6 +2305,9 @@ void i915_oa_init_reg_state(struct intel_engine_cs *engine,
 {
 	struct i915_perf_stream *stream;
 
+	/* perf.exclusive_stream serialised by gen8_configure_all_contexts() */
+	lockdep_assert_held(&ce->pin_mutex);
+
 	if (engine->class != RENDER_CLASS)
 		return;
 
-- 
cgit v1.2.3


From 75427b2a2bffc083d51dec389c235722a9c69b05 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 28 Aug 2019 13:20:59 +0300
Subject: drm/i915: Limit MST to <= 8bpc once again
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

My attempt at allowing MST to use the higher color depths has
regressed some configurations. Apparently people have setups
where all MST streams will fit into the DP link with 8bpc but
won't fit with higher color depths.

What we really should be doing is reducing the bpc for all the
streams on the same link until they start to fit. But that requires
a bit more work, so in the meantime let's revert back closer to
the old behavior and limit MST to at most 8bpc.

Cc: stable@vger.kernel.org
Cc: Lyude Paul <lyude@redhat.com>
Tested-by: Geoffrey Bennett <gmux22@gmail.com>
Fixes: f1477219869c ("drm/i915: Remove the 8bpc shackles from DP MST")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111505
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190828102059.2512-1-ville.syrjala@linux.intel.com
Reviewed-by: Lyude Paul <lyude@redhat.com>
---
 drivers/gpu/drm/i915/display/intel_dp_mst.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 2c5ac3dd647f..6df240a01b8c 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -128,7 +128,15 @@ static int intel_dp_mst_compute_config(struct intel_encoder *encoder,
 	limits.max_lane_count = intel_dp_max_lane_count(intel_dp);
 
 	limits.min_bpp = intel_dp_min_bpp(pipe_config);
-	limits.max_bpp = pipe_config->pipe_bpp;
+	/*
+	 * FIXME: If all the streams can't fit into the link with
+	 * their current pipe_bpp we should reduce pipe_bpp across
+	 * the board until things start to fit. Until then we
+	 * limit to <= 8bpc since that's what was hardcoded for all
+	 * MST streams previously. This hack should be removed once
+	 * we have the proper retry logic in place.
+	 */
+	limits.max_bpp = min(pipe_config->pipe_bpp, 24);
 
 	intel_dp_adjust_compliance_config(intel_dp, pipe_config, &limits);
 
-- 
cgit v1.2.3


From 66a990dd0c49b534b2396934c1659b3fef34233d Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 30 Aug 2019 21:27:19 +0300
Subject: drm/i915: Prefer encoder->name over port_name()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

enum port is a mess now because it no longer matches the spec
at all. Let's start to dig ourselves out of this hole by
reducing our reliance on port_name(). This should at least make
a bunch of debug messages a bit more sensible while we think how
to fill the the hole properly.

Based on the following cocci script with a lot of manual cleanup
(all the format strings etc.):
@@
expression E;
@@
(
- port_name(E->port)
+ E->base.base.id, E->base.name
|
- port_name(E.port)
+ E.base.base.id, E.base.name
)

@@
enum port P;
expression E;
@@
  P = E->port
<...
- port_name(P)
+ E->base.base.id, E->base.name
...>

@@
enum port P;
expression E;
@@
  P = E.port
<...
- port_name(P)
+ E.base.base.id, E.base.name
...>

@@
expression E;
@@
{
- enum port P = E;
... when != P
}

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190830182719.32608-1-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/display/intel_audio.c    |  10 ++-
 drivers/gpu/drm/i915/display/intel_ddi.c      |  19 ++--
 drivers/gpu/drm/i915/display/intel_display.c  |   4 +-
 drivers/gpu/drm/i915/display/intel_dp.c       | 122 +++++++++++++++-----------
 drivers/gpu/drm/i915/display/intel_dpll_mgr.c |   4 +-
 drivers/gpu/drm/i915/display/intel_hdmi.c     |   9 +-
 drivers/gpu/drm/i915/display/intel_hotplug.c  |   3 +-
 drivers/gpu/drm/i915/i915_debugfs.c           |   5 +-
 8 files changed, 102 insertions(+), 74 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index ddcccf4408c3..aac089c79ceb 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -560,8 +560,9 @@ static void ilk_audio_codec_disable(struct intel_encoder *encoder,
 	u32 tmp, eldv;
 	i915_reg_t aud_config, aud_cntrl_st2;
 
-	DRM_DEBUG_KMS("Disable audio codec on port %c, pipe %c\n",
-		      port_name(port), pipe_name(pipe));
+	DRM_DEBUG_KMS("Disable audio codec on [ENCODER:%d:%s], pipe %c\n",
+		      encoder->base.base.id, encoder->base.name,
+		      pipe_name(pipe));
 
 	if (WARN_ON(port == PORT_A))
 		return;
@@ -609,8 +610,9 @@ static void ilk_audio_codec_enable(struct intel_encoder *encoder,
 	int len, i;
 	i915_reg_t hdmiw_hdmiedid, aud_config, aud_cntl_st, aud_cntrl_st2;
 
-	DRM_DEBUG_KMS("Enable audio codec on port %c, pipe %c, %u bytes ELD\n",
-		      port_name(port), pipe_name(pipe), drm_eld_size(eld));
+	DRM_DEBUG_KMS("Enable audio codec on [ENCODER:%d:%s], pipe %c, %u bytes ELD\n",
+		      encoder->base.base.id, encoder->base.name,
+		      pipe_name(pipe), drm_eld_size(eld));
 
 	if (WARN_ON(port == PORT_A))
 		return;
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 3180dacb5be4..1fe0bf01e580 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -2080,18 +2080,20 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
 	}
 
 	if (!*pipe_mask)
-		DRM_DEBUG_KMS("No pipe for ddi port %c found\n",
-			      port_name(port));
+		DRM_DEBUG_KMS("No pipe for [ENCODER:%d:%s] found\n",
+			      encoder->base.base.id, encoder->base.name);
 
 	if (!mst_pipe_mask && hweight8(*pipe_mask) > 1) {
-		DRM_DEBUG_KMS("Multiple pipes for non DP-MST port %c (pipe_mask %02x)\n",
-			      port_name(port), *pipe_mask);
+		DRM_DEBUG_KMS("Multiple pipes for [ENCODER:%d:%s] (pipe_mask %02x)\n",
+			      encoder->base.base.id, encoder->base.name,
+			      *pipe_mask);
 		*pipe_mask = BIT(ffs(*pipe_mask) - 1);
 	}
 
 	if (mst_pipe_mask && mst_pipe_mask != *pipe_mask)
-		DRM_DEBUG_KMS("Conflicting MST and non-MST encoders for port %c (pipe_mask %02x mst_pipe_mask %02x)\n",
-			      port_name(port), *pipe_mask, mst_pipe_mask);
+		DRM_DEBUG_KMS("Conflicting MST and non-MST state for [ENCODER:%d:%s] (pipe_mask %02x mst_pipe_mask %02x)\n",
+			      encoder->base.base.id, encoder->base.name,
+			      *pipe_mask, mst_pipe_mask);
 	else
 		*is_dp_mst = mst_pipe_mask;
 
@@ -2101,8 +2103,9 @@ out:
 		if ((tmp & (BXT_PHY_CMNLANE_POWERDOWN_ACK |
 			    BXT_PHY_LANE_POWERDOWN_ACK |
 			    BXT_PHY_LANE_ENABLED)) != BXT_PHY_LANE_ENABLED)
-			DRM_ERROR("Port %c enabled but PHY powered down? "
-				  "(PHY_CTL %08x)\n", port_name(port), tmp);
+			DRM_ERROR("[ENCODER:%d:%s] enabled but PHY powered down? "
+				  "(PHY_CTL %08x)\n", encoder->base.base.id,
+				  encoder->base.name, tmp);
 	}
 
 	intel_display_power_put(dev_priv, encoder->power_domain, wakeref);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index e661e2099118..a03dc6eb61f8 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -1612,8 +1612,8 @@ void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
 
 	if (intel_de_wait_for_register(dev_priv, dpll_reg,
 				       port_mask, expected_mask, 1000))
-		WARN(1, "timed out waiting for port %c ready: got 0x%x, expected 0x%x\n",
-		     port_name(dport->base.port),
+		WARN(1, "timed out waiting for [ENCODER:%d:%s] port ready: got 0x%x, expected 0x%x\n",
+		     dport->base.base.base.id, dport->base.base.name,
 		     I915_READ(dpll_reg) & port_mask, expected_mask);
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index aaa90992a7f0..4e3e696e7fc8 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -639,12 +639,14 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp)
 	u32 DP;
 
 	if (WARN(I915_READ(intel_dp->output_reg) & DP_PORT_EN,
-		 "skipping pipe %c power sequencer kick due to port %c being active\n",
-		 pipe_name(pipe), port_name(intel_dig_port->base.port)))
+		 "skipping pipe %c power sequencer kick due to [ENCODER:%d:%s] being active\n",
+		 pipe_name(pipe), intel_dig_port->base.base.base.id,
+		 intel_dig_port->base.base.name))
 		return;
 
-	DRM_DEBUG_KMS("kicking pipe %c power sequencer for port %c\n",
-		      pipe_name(pipe), port_name(intel_dig_port->base.port));
+	DRM_DEBUG_KMS("kicking pipe %c power sequencer for [ENCODER:%d:%s]\n",
+		      pipe_name(pipe), intel_dig_port->base.base.base.id,
+		      intel_dig_port->base.base.name);
 
 	/* Preserve the BIOS-computed detected bit. This is
 	 * supposed to be read-only.
@@ -762,9 +764,10 @@ vlv_power_sequencer_pipe(struct intel_dp *intel_dp)
 	vlv_steal_power_sequencer(dev_priv, pipe);
 	intel_dp->pps_pipe = pipe;
 
-	DRM_DEBUG_KMS("picked pipe %c power sequencer for port %c\n",
+	DRM_DEBUG_KMS("picked pipe %c power sequencer for [ENCODER:%d:%s]\n",
 		      pipe_name(intel_dp->pps_pipe),
-		      port_name(intel_dig_port->base.port));
+		      intel_dig_port->base.base.base.id,
+		      intel_dig_port->base.base.name);
 
 	/* init power sequencer on this pipe and port */
 	intel_dp_init_panel_power_sequencer(intel_dp);
@@ -872,13 +875,16 @@ vlv_initial_power_sequencer_setup(struct intel_dp *intel_dp)
 
 	/* didn't find one? just let vlv_power_sequencer_pipe() pick one when needed */
 	if (intel_dp->pps_pipe == INVALID_PIPE) {
-		DRM_DEBUG_KMS("no initial power sequencer for port %c\n",
-			      port_name(port));
+		DRM_DEBUG_KMS("no initial power sequencer for [ENCODER:%d:%s]\n",
+			      intel_dig_port->base.base.base.id,
+			      intel_dig_port->base.base.name);
 		return;
 	}
 
-	DRM_DEBUG_KMS("initial power sequencer for port %c: pipe %c\n",
-		      port_name(port), pipe_name(intel_dp->pps_pipe));
+	DRM_DEBUG_KMS("initial power sequencer for [ENCODER:%d:%s]: pipe %c\n",
+		      intel_dig_port->base.base.base.id,
+		      intel_dig_port->base.base.name,
+		      pipe_name(intel_dp->pps_pipe));
 
 	intel_dp_init_panel_power_sequencer(intel_dp);
 	intel_dp_init_panel_power_sequencer_registers(intel_dp, false);
@@ -2492,8 +2498,9 @@ static bool edp_panel_vdd_on(struct intel_dp *intel_dp)
 	intel_display_power_get(dev_priv,
 				intel_aux_power_domain(intel_dig_port));
 
-	DRM_DEBUG_KMS("Turning eDP port %c VDD on\n",
-		      port_name(intel_dig_port->base.port));
+	DRM_DEBUG_KMS("Turning [ENCODER:%d:%s] VDD on\n",
+		      intel_dig_port->base.base.base.id,
+		      intel_dig_port->base.base.name);
 
 	if (!edp_have_panel_power(intel_dp))
 		wait_panel_power_cycle(intel_dp);
@@ -2512,8 +2519,9 @@ static bool edp_panel_vdd_on(struct intel_dp *intel_dp)
 	 * If the panel wasn't on, delay before accessing aux channel
 	 */
 	if (!edp_have_panel_power(intel_dp)) {
-		DRM_DEBUG_KMS("eDP port %c panel power wasn't enabled\n",
-			      port_name(intel_dig_port->base.port));
+		DRM_DEBUG_KMS("[ENCODER:%d:%s] panel power wasn't enabled\n",
+			      intel_dig_port->base.base.base.id,
+			      intel_dig_port->base.base.name);
 		msleep(intel_dp->panel_power_up_delay);
 	}
 
@@ -2538,8 +2546,9 @@ void intel_edp_panel_vdd_on(struct intel_dp *intel_dp)
 	vdd = false;
 	with_pps_lock(intel_dp, wakeref)
 		vdd = edp_panel_vdd_on(intel_dp);
-	I915_STATE_WARN(!vdd, "eDP port %c VDD already requested on\n",
-	     port_name(dp_to_dig_port(intel_dp)->base.port));
+	I915_STATE_WARN(!vdd, "[ENCODER:%d:%s] VDD already requested on\n",
+			dp_to_dig_port(intel_dp)->base.base.base.id,
+			dp_to_dig_port(intel_dp)->base.base.name);
 }
 
 static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
@@ -2557,8 +2566,9 @@ static void edp_panel_vdd_off_sync(struct intel_dp *intel_dp)
 	if (!edp_have_panel_vdd(intel_dp))
 		return;
 
-	DRM_DEBUG_KMS("Turning eDP port %c VDD off\n",
-		      port_name(intel_dig_port->base.port));
+	DRM_DEBUG_KMS("Turning [ENCODER:%d:%s] VDD off\n",
+		      intel_dig_port->base.base.base.id,
+		      intel_dig_port->base.base.name);
 
 	pp = ironlake_get_pp_control(intel_dp);
 	pp &= ~EDP_FORCE_VDD;
@@ -2620,8 +2630,9 @@ static void edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
 	if (!intel_dp_is_edp(intel_dp))
 		return;
 
-	I915_STATE_WARN(!intel_dp->want_panel_vdd, "eDP port %c VDD not forced on",
-	     port_name(dp_to_dig_port(intel_dp)->base.port));
+	I915_STATE_WARN(!intel_dp->want_panel_vdd, "[ENCODER:%d:%s] VDD not forced on",
+			dp_to_dig_port(intel_dp)->base.base.base.id,
+			dp_to_dig_port(intel_dp)->base.base.name);
 
 	intel_dp->want_panel_vdd = false;
 
@@ -2642,12 +2653,14 @@ static void edp_panel_on(struct intel_dp *intel_dp)
 	if (!intel_dp_is_edp(intel_dp))
 		return;
 
-	DRM_DEBUG_KMS("Turn eDP port %c panel power on\n",
-		      port_name(dp_to_dig_port(intel_dp)->base.port));
+	DRM_DEBUG_KMS("Turn [ENCODER:%d:%s] panel power on\n",
+		      dp_to_dig_port(intel_dp)->base.base.base.id,
+		      dp_to_dig_port(intel_dp)->base.base.name);
 
 	if (WARN(edp_have_panel_power(intel_dp),
-		 "eDP port %c panel power already on\n",
-		 port_name(dp_to_dig_port(intel_dp)->base.port)))
+		 "[ENCODER:%d:%s] panel power already on\n",
+		 dp_to_dig_port(intel_dp)->base.base.base.id,
+		 dp_to_dig_port(intel_dp)->base.base.name))
 		return;
 
 	wait_panel_power_cycle(intel_dp);
@@ -2702,11 +2715,11 @@ static void edp_panel_off(struct intel_dp *intel_dp)
 	if (!intel_dp_is_edp(intel_dp))
 		return;
 
-	DRM_DEBUG_KMS("Turn eDP port %c panel power off\n",
-		      port_name(dig_port->base.port));
+	DRM_DEBUG_KMS("Turn [ENCODER:%d:%s] panel power off\n",
+		      dig_port->base.base.base.id, dig_port->base.base.name);
 
-	WARN(!intel_dp->want_panel_vdd, "Need eDP port %c VDD to turn off panel\n",
-	     port_name(dig_port->base.port));
+	WARN(!intel_dp->want_panel_vdd, "Need [ENCODER:%d:%s] VDD to turn off panel\n",
+	     dig_port->base.base.base.id, dig_port->base.base.name);
 
 	pp = ironlake_get_pp_control(intel_dp);
 	/* We need to switch off panel power _and_ force vdd, for otherwise some
@@ -2851,8 +2864,8 @@ static void assert_dp_port(struct intel_dp *intel_dp, bool state)
 	bool cur_state = I915_READ(intel_dp->output_reg) & DP_PORT_EN;
 
 	I915_STATE_WARN(cur_state != state,
-			"DP port %c state assertion failure (expected %s, current %s)\n",
-			port_name(dig_port->base.port),
+			"[ENCODER:%d:%s] state assertion failure (expected %s, current %s)\n",
+			dig_port->base.base.base.id, dig_port->base.base.name,
 			onoff(state), onoff(cur_state));
 }
 #define assert_dp_port_disabled(d) assert_dp_port((d), false)
@@ -3430,8 +3443,9 @@ static void vlv_detach_power_sequencer(struct intel_dp *intel_dp)
 	 * port select always when logically disconnecting a power sequencer
 	 * from a port.
 	 */
-	DRM_DEBUG_KMS("detaching pipe %c power sequencer from port %c\n",
-		      pipe_name(pipe), port_name(intel_dig_port->base.port));
+	DRM_DEBUG_KMS("detaching pipe %c power sequencer from [ENCODER:%d:%s]\n",
+		      pipe_name(pipe), intel_dig_port->base.base.base.id,
+		      intel_dig_port->base.base.name);
 	I915_WRITE(pp_on_reg, 0);
 	POSTING_READ(pp_on_reg);
 
@@ -3447,17 +3461,18 @@ static void vlv_steal_power_sequencer(struct drm_i915_private *dev_priv,
 
 	for_each_intel_dp(&dev_priv->drm, encoder) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-		enum port port = encoder->port;
 
 		WARN(intel_dp->active_pipe == pipe,
-		     "stealing pipe %c power sequencer from active (e)DP port %c\n",
-		     pipe_name(pipe), port_name(port));
+		     "stealing pipe %c power sequencer from active [ENCODER:%d:%s]\n",
+		     pipe_name(pipe), encoder->base.base.id,
+		     encoder->base.name);
 
 		if (intel_dp->pps_pipe != pipe)
 			continue;
 
-		DRM_DEBUG_KMS("stealing pipe %c power sequencer from port %c\n",
-			      pipe_name(pipe), port_name(port));
+		DRM_DEBUG_KMS("stealing pipe %c power sequencer from [ENCODER:%d:%s]\n",
+			      pipe_name(pipe), encoder->base.base.id,
+			      encoder->base.name);
 
 		/* make sure vdd is off before we steal it */
 		vlv_detach_power_sequencer(intel_dp);
@@ -3499,8 +3514,9 @@ static void vlv_init_panel_power_sequencer(struct intel_encoder *encoder,
 	/* now it's all ours */
 	intel_dp->pps_pipe = crtc->pipe;
 
-	DRM_DEBUG_KMS("initializing pipe %c power sequencer for port %c\n",
-		      pipe_name(intel_dp->pps_pipe), port_name(encoder->port));
+	DRM_DEBUG_KMS("initializing pipe %c power sequencer for [ENCODER:%d:%s]\n",
+		      pipe_name(intel_dp->pps_pipe), encoder->base.base.id,
+		      encoder->base.name);
 
 	/* init power sequencer on this pipe and port */
 	intel_dp_init_panel_power_sequencer(intel_dp);
@@ -4321,9 +4337,10 @@ intel_dp_configure_mst(struct intel_dp *intel_dp)
 		&dp_to_dig_port(intel_dp)->base;
 	bool sink_can_mst = intel_dp_sink_can_mst(intel_dp);
 
-	DRM_DEBUG_KMS("MST support? port %c: %s, sink: %s, modparam: %s\n",
-		      port_name(encoder->port), yesno(intel_dp->can_mst),
-		      yesno(sink_can_mst), yesno(i915_modparams.enable_dp_mst));
+	DRM_DEBUG_KMS("[ENCODER:%d:%s] MST support? port: %s, sink: %s, modparam: %s\n",
+		      encoder->base.base.id, encoder->base.name,
+		      yesno(intel_dp->can_mst), yesno(sink_can_mst),
+		      yesno(i915_modparams.enable_dp_mst));
 
 	if (!intel_dp->can_mst)
 		return;
@@ -6284,13 +6301,15 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd)
 		 * would end up in an endless cycle of
 		 * "vdd off -> long hpd -> vdd on -> detect -> vdd off -> ..."
 		 */
-		DRM_DEBUG_KMS("ignoring long hpd on eDP port %c\n",
-			      port_name(intel_dig_port->base.port));
+		DRM_DEBUG_KMS("ignoring long hpd on eDP [ENCODER:%d:%s]\n",
+			      intel_dig_port->base.base.base.id,
+			      intel_dig_port->base.base.name);
 		return IRQ_HANDLED;
 	}
 
-	DRM_DEBUG_KMS("got hpd irq on port %c - %s\n",
-		      port_name(intel_dig_port->base.port),
+	DRM_DEBUG_KMS("got hpd irq on [ENCODER:%d:%s] - %s\n",
+		      intel_dig_port->base.base.base.id,
+		      intel_dig_port->base.base.name,
 		      long_hpd ? "long" : "short");
 
 	if (long_hpd) {
@@ -7154,8 +7173,9 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 		  intel_dp_modeset_retry_work_fn);
 
 	if (WARN(intel_dig_port->max_lanes < 1,
-		 "Not enough lanes (%d) for DP on port %c\n",
-		 intel_dig_port->max_lanes, port_name(port)))
+		 "Not enough lanes (%d) for DP on [ENCODER:%d:%s]\n",
+		 intel_dig_port->max_lanes, intel_encoder->base.base.id,
+		 intel_encoder->base.name))
 		return false;
 
 	intel_dp_set_source_rates(intel_dp);
@@ -7196,9 +7216,9 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 		    port != PORT_B && port != PORT_C))
 		return false;
 
-	DRM_DEBUG_KMS("Adding %s connector on port %c\n",
-			type == DRM_MODE_CONNECTOR_eDP ? "eDP" : "DP",
-			port_name(port));
+	DRM_DEBUG_KMS("Adding %s connector on [ENCODER:%d:%s]\n",
+		      type == DRM_MODE_CONNECTOR_eDP ? "eDP" : "DP",
+		      intel_encoder->base.base.id, intel_encoder->base.name);
 
 	drm_connector_init(dev, connector, &intel_dp_connector_funcs, type);
 	drm_connector_helper_add(connector, &intel_dp_connector_helper_funcs);
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index b8148f838354..98288edf88f0 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -2910,8 +2910,8 @@ static bool icl_get_combo_phy_dpll(struct intel_atomic_state *state,
 						has_dpll4 ? DPLL_ID_EHL_DPLL4
 							  : DPLL_ID_ICL_DPLL1);
 	if (!port_dpll->pll) {
-		DRM_DEBUG_KMS("No combo PHY PLL found for port %c\n",
-			      port_name(encoder->port));
+		DRM_DEBUG_KMS("No combo PHY PLL found for [ENCODER:%d:%s]\n",
+			      encoder->base.base.id, encoder->base.name);
 		return false;
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index f6bb77fd0930..d1e26a00c642 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -3075,12 +3075,13 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum port port = intel_encoder->port;
 
-	DRM_DEBUG_KMS("Adding HDMI connector on port %c\n",
-		      port_name(port));
+	DRM_DEBUG_KMS("Adding HDMI connector on [ENCODER:%d:%s]\n",
+		      intel_encoder->base.base.id, intel_encoder->base.name);
 
 	if (WARN(intel_dig_port->max_lanes < 4,
-		 "Not enough lanes (%d) for HDMI on port %c\n",
-		 intel_dig_port->max_lanes, port_name(port)))
+		 "Not enough lanes (%d) for HDMI on [ENCODER:%d:%s]\n",
+		 intel_dig_port->max_lanes, intel_encoder->base.base.id,
+		 intel_encoder->base.name))
 		return;
 
 	drm_connector_init(dev, connector, &intel_hdmi_connector_funcs,
diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c
index 56be20f6f47e..fc29046d48ea 100644
--- a/drivers/gpu/drm/i915/display/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/display/intel_hotplug.c
@@ -481,7 +481,8 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 
 		long_hpd = long_mask & BIT(pin);
 
-		DRM_DEBUG_DRIVER("digital hpd port %c - %s\n", port_name(port),
+		DRM_DEBUG_DRIVER("digital hpd on [ENCODER:%d:%s] - %s\n",
+				 encoder->base.base.id, encoder->base.name,
 				 long_hpd ? "long" : "short");
 		queue_dig = true;
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 5e81c4fc13ae..974936917329 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3114,8 +3114,9 @@ static int i915_dp_mst_info(struct seq_file *m, void *unused)
 		if (!intel_dig_port->dp.can_mst)
 			continue;
 
-		seq_printf(m, "MST Source Port %c\n",
-			   port_name(intel_dig_port->base.port));
+		seq_printf(m, "MST Source Port [ENCODER:%d:%s]\n",
+			   intel_dig_port->base.base.base.id,
+			   intel_dig_port->base.base.name);
 		drm_dp_mst_dump_topology(m, &intel_dig_port->dp.mst_mgr);
 	}
 	drm_connector_list_iter_end(&conn_iter);
-- 
cgit v1.2.3


From 9e362992ff34cab695e669ef1e3f4f65463087e5 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 28 Aug 2019 21:34:24 +0300
Subject: drm/i915: Clean up HDMI deep color handling a bit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reogranize the HDMI deep color state computation to just
loop over possible bpc values. Avoids having to maintain
so many variants of the clock etc.

The current code also looks confused w.r.t. port_clock vs.
bw_constrained. It would happily update port_clock for
deep color but then not actually enable deep color due to
bw_constrained being set. The new logic handles that case
correctly.

v2: Pull stuff into separate funcs (Jani)

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190828183424.7856-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_hdmi.c | 134 +++++++++++++++++-------------
 1 file changed, 77 insertions(+), 57 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index d1e26a00c642..640254feef27 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2265,9 +2265,7 @@ static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state,
 
 static bool
 intel_hdmi_ycbcr420_config(struct drm_connector *connector,
-			   struct intel_crtc_state *config,
-			   int *clock_12bpc, int *clock_10bpc,
-			   int *clock_8bpc)
+			   struct intel_crtc_state *config)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(config->base.crtc);
 
@@ -2276,11 +2274,6 @@ intel_hdmi_ycbcr420_config(struct drm_connector *connector,
 		return false;
 	}
 
-	/* YCBCR420 TMDS rate requirement is half the pixel clock */
-	config->port_clock /= 2;
-	*clock_12bpc /= 2;
-	*clock_10bpc /= 2;
-	*clock_8bpc /= 2;
 	config->output_format = INTEL_OUTPUT_FORMAT_YCBCR420;
 
 	/* YCBCR 420 output conversion needs a scaler */
@@ -2295,6 +2288,76 @@ intel_hdmi_ycbcr420_config(struct drm_connector *connector,
 	return true;
 }
 
+static int intel_hdmi_port_clock(int clock, int bpc)
+{
+	/*
+	 * Need to adjust the port link by:
+	 *  1.5x for 12bpc
+	 *  1.25x for 10bpc
+	 */
+	return clock * bpc / 8;
+}
+
+static int intel_hdmi_compute_bpc(struct intel_encoder *encoder,
+				  struct intel_crtc_state *crtc_state,
+				  int clock, bool force_dvi)
+{
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	int bpc;
+
+	for (bpc = 12; bpc >= 10; bpc -= 2) {
+		if (hdmi_deep_color_possible(crtc_state, bpc) &&
+		    hdmi_port_clock_valid(intel_hdmi,
+					  intel_hdmi_port_clock(clock, bpc),
+					  true, force_dvi) == MODE_OK)
+			return bpc;
+	}
+
+	return 8;
+}
+
+static int intel_hdmi_compute_clock(struct intel_encoder *encoder,
+				    struct intel_crtc_state *crtc_state,
+				    bool force_dvi)
+{
+	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
+	const struct drm_display_mode *adjusted_mode =
+		&crtc_state->base.adjusted_mode;
+	int bpc, clock = adjusted_mode->crtc_clock;
+
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
+		clock *= 2;
+
+	/* YCBCR420 TMDS rate requirement is half the pixel clock */
+	if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420)
+		clock /= 2;
+
+	bpc = intel_hdmi_compute_bpc(encoder, crtc_state,
+				     clock, force_dvi);
+
+	crtc_state->port_clock = intel_hdmi_port_clock(clock, bpc);
+
+	/*
+	 * pipe_bpp could already be below 8bpc due to
+	 * FDI bandwidth constraints. We shouldn't bump it
+	 * back up to 8bpc in that case.
+	 */
+	if (crtc_state->pipe_bpp > bpc * 3)
+		crtc_state->pipe_bpp = bpc * 3;
+
+	DRM_DEBUG_KMS("picking %d bpc for HDMI output (pipe bpp: %d)\n",
+		      bpc, crtc_state->pipe_bpp);
+
+	if (hdmi_port_clock_valid(intel_hdmi, crtc_state->port_clock,
+				  false, force_dvi) != MODE_OK) {
+		DRM_DEBUG_KMS("unsupported HDMI clock (%d kHz), rejecting mode\n",
+			      crtc_state->port_clock);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 int intel_hdmi_compute_config(struct intel_encoder *encoder,
 			      struct intel_crtc_state *pipe_config,
 			      struct drm_connector_state *conn_state)
@@ -2306,11 +2369,8 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 	struct drm_scdc *scdc = &connector->display_info.hdmi.scdc;
 	struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
-	int clock_8bpc = pipe_config->base.adjusted_mode.crtc_clock;
-	int clock_10bpc = clock_8bpc * 5 / 4;
-	int clock_12bpc = clock_8bpc * 3 / 2;
-	int desired_bpp;
 	bool force_dvi = intel_conn_state->force_audio == HDMI_AUDIO_OFF_DVI;
+	int ret;
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return -EINVAL;
@@ -2332,17 +2392,11 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 			intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_LIMITED;
 	}
 
-	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) {
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
 		pipe_config->pixel_multiplier = 2;
-		clock_8bpc *= 2;
-		clock_10bpc *= 2;
-		clock_12bpc *= 2;
-	}
 
 	if (drm_mode_is_420_only(&connector->display_info, adjusted_mode)) {
-		if (!intel_hdmi_ycbcr420_config(connector, pipe_config,
-						&clock_12bpc, &clock_10bpc,
-						&clock_8bpc)) {
+		if (!intel_hdmi_ycbcr420_config(connector, pipe_config)) {
 			DRM_ERROR("Can't support YCBCR420 output\n");
 			return -EINVAL;
 		}
@@ -2359,43 +2413,9 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 				intel_conn_state->force_audio == HDMI_AUDIO_ON;
 	}
 
-	/*
-	 * Note that g4x/vlv don't support 12bpc hdmi outputs. We also need
-	 * to check that the higher clock still fits within limits.
-	 */
-	if (hdmi_deep_color_possible(pipe_config, 12) &&
-	    hdmi_port_clock_valid(intel_hdmi, clock_12bpc,
-				  true, force_dvi) == MODE_OK) {
-		DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n");
-		desired_bpp = 12*3;
-
-		/* Need to adjust the port link by 1.5x for 12bpc. */
-		pipe_config->port_clock = clock_12bpc;
-	} else if (hdmi_deep_color_possible(pipe_config, 10) &&
-		   hdmi_port_clock_valid(intel_hdmi, clock_10bpc,
-					 true, force_dvi) == MODE_OK) {
-		DRM_DEBUG_KMS("picking bpc to 10 for HDMI output\n");
-		desired_bpp = 10 * 3;
-
-		/* Need to adjust the port link by 1.25x for 10bpc. */
-		pipe_config->port_clock = clock_10bpc;
-	} else {
-		DRM_DEBUG_KMS("picking bpc to 8 for HDMI output\n");
-		desired_bpp = 8*3;
-
-		pipe_config->port_clock = clock_8bpc;
-	}
-
-	if (!pipe_config->bw_constrained) {
-		DRM_DEBUG_KMS("forcing pipe bpp to %i for HDMI\n", desired_bpp);
-		pipe_config->pipe_bpp = desired_bpp;
-	}
-
-	if (hdmi_port_clock_valid(intel_hdmi, pipe_config->port_clock,
-				  false, force_dvi) != MODE_OK) {
-		DRM_DEBUG_KMS("unsupported HDMI clock, rejecting mode\n");
-		return -EINVAL;
-	}
+	ret = intel_hdmi_compute_clock(encoder, pipe_config, force_dvi);
+	if (ret)
+		return ret;
 
 	/* Set user selected PAR to incoming mode's member */
 	adjusted_mode->picture_aspect_ratio = conn_state->picture_aspect_ratio;
-- 
cgit v1.2.3


From 8f5e2b306b4e26db0ec65e0a27b232b179c9122b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 2 Sep 2019 05:02:43 +0100
Subject: drm/i915: Restrict the aliasing-ppgtt to the size of the ggtt

The aliasing-ppgtt is not allowed to be smaller than the ggtt, nor
should we advertise it as being any bigger, or else we may get sued for
false advertisement.

Testcase: igt/gem_exec_big
Fixes: 0b718ba1e884 ("drm/i915/gtt: Downgrade Cherryview back to aliasing-ppgtt")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190902040303.14195-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index ee51fd1a6207..906dc6fff383 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2597,6 +2597,8 @@ static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
 	GEM_BUG_ON(ggtt->vm.vma_ops.unbind_vma != ggtt_unbind_vma);
 	ggtt->vm.vma_ops.unbind_vma = aliasing_gtt_unbind_vma;
 
+	ppgtt->vm.total = ggtt->vm.total;
+
 	return 0;
 
 err_ppgtt:
-- 
cgit v1.2.3


From 4f36ef2ee1876b2e145327f03f675a0577f258cb Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 2 Sep 2019 05:02:44 +0100
Subject: drm/i915: Report aliasing ppgtt size as ggtt size

The aliasing-ppgtt is constrained to be the same size as the Global GTT
since it aliases the same address space. Simplifying gtt size reporting
in this case.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190902040303.14195-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index b8969605f4e8..f1c0e5d958f3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -2231,8 +2231,6 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 		args->size = 0;
 		if (ctx->vm)
 			args->value = ctx->vm->total;
-		else if (to_i915(dev)->ggtt.alias)
-			args->value = to_i915(dev)->ggtt.alias->vm.total;
 		else
 			args->value = to_i915(dev)->ggtt.vm.total;
 		break;
-- 
cgit v1.2.3


From 5a90606df7cb73eceb46897a87154e94b31af93a Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 2 Sep 2019 05:02:47 +0100
Subject: drm/i915: Replace obj->pin_global with obj->frontbuffer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

obj->pin_global was originally used as a means to keep the shrinker off
the active scanout, but we use the vma->pin_count itself for that and
the obj->frontbuffer to delay shrinking active framebuffers. The other
role that obj->pin_global gained was for spotting display objects inside
GEM and working harder to keep those coherent; for which we can again
simply inspect obj->frontbuffer directly.

Coming up next, we will want to manipulate the pin_global counter
outside of the principle locks, so would need to make pin_global atomic.
However, since obj->frontbuffer is already managed atomically, it makes
sense to use that the primary key for display objects instead of having
pin_global.

Ville pointed out the principle difference is that obj->frontbuffer is
set for as long as an intel_framebuffer is attached to an object, but
obj->pin_global was only raised for as long as the object was active. In
practice, this means that we consider the object as being on the scanout
for longer than is strictly required, causing us to be more proactive in
flushing -- though it should be true that we would have flushed
eventually when the back became the front, except that on the flip path
that flush is async but when hit from another ioctl it will be
synchronous.

v2: i915_gem_object_is_framebuffer()

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190902040303.14195-5-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/display/intel_display.c     |  2 ++
 drivers/gpu/drm/i915/display/intel_frontbuffer.c | 13 ++++++---
 drivers/gpu/drm/i915/gem/i915_gem_domain.c       | 34 +++++++-----------------
 drivers/gpu/drm/i915/gem/i915_gem_object.h       |  3 ++-
 drivers/gpu/drm/i915/gem/i915_gem_object_types.h |  2 --
 drivers/gpu/drm/i915/gem/i915_gem_shrinker.c     | 15 +++--------
 drivers/gpu/drm/i915/i915_debugfs.c              | 12 +++------
 7 files changed, 31 insertions(+), 50 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index a03dc6eb61f8..12a94c6e3d51 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -2080,6 +2080,8 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	u32 alignment;
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+	if (WARN_ON(!i915_gem_object_is_framebuffer(obj)))
+		return ERR_PTR(-EINVAL);
 
 	alignment = intel_surf_alignment(fb, 0);
 
diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
index 719379774fa5..fc40dc1fdbcc 100644
--- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
@@ -220,11 +220,18 @@ static void frontbuffer_release(struct kref *ref)
 {
 	struct intel_frontbuffer *front =
 		container_of(ref, typeof(*front), ref);
+	struct drm_i915_gem_object *obj = front->obj;
+	struct i915_vma *vma;
 
-	front->obj->frontbuffer = NULL;
-	spin_unlock(&to_i915(front->obj->base.dev)->fb_tracking.lock);
+	spin_lock(&obj->vma.lock);
+	for_each_ggtt_vma(vma, obj)
+		vma->display_alignment = I915_GTT_MIN_ALIGNMENT;
+	spin_unlock(&obj->vma.lock);
 
-	i915_gem_object_put(front->obj);
+	obj->frontbuffer = NULL;
+	spin_unlock(&to_i915(obj->base.dev)->fb_tracking.lock);
+
+	i915_gem_object_put(obj);
 	kfree(front);
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 9c58e8fac1d9..6af740a5e3db 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -27,7 +27,7 @@ static void __i915_gem_object_flush_for_display(struct drm_i915_gem_object *obj)
 
 void i915_gem_object_flush_if_display(struct drm_i915_gem_object *obj)
 {
-	if (!READ_ONCE(obj->pin_global))
+	if (!i915_gem_object_is_framebuffer(obj))
 		return;
 
 	i915_gem_object_lock(obj);
@@ -422,12 +422,8 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 
 	assert_object_held(obj);
 
-	/* Mark the global pin early so that we account for the
-	 * display coherency whilst setting up the cache domains.
-	 */
-	obj->pin_global++;
-
-	/* The display engine is not coherent with the LLC cache on gen6.  As
+	/*
+	 * The display engine is not coherent with the LLC cache on gen6.  As
 	 * a result, we make sure that the pinning that is about to occur is
 	 * done with uncached PTEs. This is lowest common denominator for all
 	 * chipsets.
@@ -439,12 +435,11 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	ret = i915_gem_object_set_cache_level(obj,
 					      HAS_WT(to_i915(obj->base.dev)) ?
 					      I915_CACHE_WT : I915_CACHE_NONE);
-	if (ret) {
-		vma = ERR_PTR(ret);
-		goto err_unpin_global;
-	}
+	if (ret)
+		return ERR_PTR(ret);
 
-	/* As the user may map the buffer once pinned in the display plane
+	/*
+	 * As the user may map the buffer once pinned in the display plane
 	 * (e.g. libkms for the bootup splash), we have to ensure that we
 	 * always use map_and_fenceable for all scanout buffers. However,
 	 * it may simply be too big to fit into mappable, in which case
@@ -461,22 +456,19 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	if (IS_ERR(vma))
 		vma = i915_gem_object_ggtt_pin(obj, view, 0, alignment, flags);
 	if (IS_ERR(vma))
-		goto err_unpin_global;
+		return vma;
 
 	vma->display_alignment = max_t(u64, vma->display_alignment, alignment);
 
 	__i915_gem_object_flush_for_display(obj);
 
-	/* It should now be out of any other write domains, and we can update
+	/*
+	 * It should now be out of any other write domains, and we can update
 	 * the domain values for our changes.
 	 */
 	obj->read_domains |= I915_GEM_DOMAIN_GTT;
 
 	return vma;
-
-err_unpin_global:
-	obj->pin_global--;
-	return vma;
 }
 
 static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
@@ -514,12 +506,6 @@ i915_gem_object_unpin_from_display_plane(struct i915_vma *vma)
 
 	assert_object_held(obj);
 
-	if (WARN_ON(obj->pin_global == 0))
-		return;
-
-	if (--obj->pin_global == 0)
-		vma->display_alignment = I915_GTT_MIN_ALIGNMENT;
-
 	/* Bump the LRU to try and avoid premature eviction whilst flipping  */
 	i915_gem_object_bump_inactive_ggtt(obj);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 5efb9936e05b..29b9eddc4c7f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -406,7 +406,8 @@ static inline bool cpu_write_needs_clflush(struct drm_i915_gem_object *obj)
 	if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE))
 		return true;
 
-	return obj->pin_global; /* currently in use by HW, keep flushed */
+	/* Currently in use by HW (display engine)? Keep flushed. */
+	return i915_gem_object_is_framebuffer(obj);
 }
 
 static inline void __start_cpu_write(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index ede0eb4218a8..13b9dc0e1a89 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -152,8 +152,6 @@ struct drm_i915_gem_object {
 
 	/** Count of VMA actually bound by this object */
 	atomic_t bind_count;
-	/** Count of how many global VMA are currently pinned for use by HW */
-	unsigned int pin_global;
 
 	struct {
 		struct mutex lock; /* protects the pages and their use */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index edd21d14e64f..4e55cfc2b0dc 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -61,7 +61,8 @@ static bool can_release_pages(struct drm_i915_gem_object *obj)
 	if (!i915_gem_object_is_shrinkable(obj))
 		return false;
 
-	/* Only report true if by unbinding the object and putting its pages
+	/*
+	 * Only report true if by unbinding the object and putting its pages
 	 * we can actually make forward progress towards freeing physical
 	 * pages.
 	 *
@@ -72,16 +73,8 @@ static bool can_release_pages(struct drm_i915_gem_object *obj)
 	if (atomic_read(&obj->mm.pages_pin_count) > atomic_read(&obj->bind_count))
 		return false;
 
-	/* If any vma are "permanently" pinned, it will prevent us from
-	 * reclaiming the obj->mm.pages. We only allow scanout objects to claim
-	 * a permanent pin, along with a few others like the context objects.
-	 * To simplify the scan, and to avoid walking the list of vma under the
-	 * object, we just check the count of its permanently pinned.
-	 */
-	if (READ_ONCE(obj->pin_global))
-		return false;
-
-	/* We can only return physical pages to the system if we can either
+	/*
+	 * We can only return physical pages to the system if we can either
 	 * discard the contents (because the user has marked them as being
 	 * purgeable) or if we can move their contents out to swap.
 	 */
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 974936917329..9798f27a697a 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -77,11 +77,6 @@ static int i915_capabilities(struct seq_file *m, void *data)
 	return 0;
 }
 
-static char get_pin_flag(struct drm_i915_gem_object *obj)
-{
-	return obj->pin_global ? 'p' : ' ';
-}
-
 static char get_tiling_flag(struct drm_i915_gem_object *obj)
 {
 	switch (i915_gem_object_get_tiling(obj)) {
@@ -140,9 +135,8 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 	struct i915_vma *vma;
 	int pin_count = 0;
 
-	seq_printf(m, "%pK: %c%c%c%c %8zdKiB %02x %02x %s%s%s",
+	seq_printf(m, "%pK: %c%c%c %8zdKiB %02x %02x %s%s%s",
 		   &obj->base,
-		   get_pin_flag(obj),
 		   get_tiling_flag(obj),
 		   get_global_flag(obj),
 		   get_pin_mapped_flag(obj),
@@ -221,8 +215,8 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 	seq_printf(m, " (pinned x %d)", pin_count);
 	if (obj->stolen)
 		seq_printf(m, " (stolen: %08llx)", obj->stolen->start);
-	if (obj->pin_global)
-		seq_printf(m, " (global)");
+	if (i915_gem_object_is_framebuffer(obj))
+		seq_printf(m, " (fb)");
 
 	engine = i915_gem_object_last_write_engine(obj);
 	if (engine)
-- 
cgit v1.2.3


From f2690074462bdb99530179f41ae73b45e765b761 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sun, 1 Sep 2019 12:04:31 +0100
Subject: drm/i915/selftests: Remove unused __engines_name()

This function was never used and probably will never be used, so remove
it.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190901110431.12393-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index da54a718c712..dc25bcc3e372 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -1546,21 +1546,6 @@ out_unlock:
 	return err;
 }
 
-static __maybe_unused const char *
-__engine_name(struct drm_i915_private *i915, intel_engine_mask_t engines)
-{
-	struct intel_engine_cs *engine;
-	intel_engine_mask_t tmp;
-
-	if (engines == ALL_ENGINES)
-		return "all";
-
-	for_each_engine_masked(engine, i915, engines, tmp)
-		return engine->name;
-
-	return "none";
-}
-
 static bool skip_unused_engines(struct intel_context *ce, void *data)
 {
 	return !ce->state;
-- 
cgit v1.2.3


From 8f9fb61caed13e282e1e3387e64905b90cc65abd Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 2 Sep 2019 05:02:46 +0100
Subject: drm/i915: Refresh the errno to vmf_fault translations

It's been a long time since we accidentally reported -EIO upon wedging,
it can now only be generated by failure to swap in a page.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
Reviewed-by: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190902040303.14195-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_mman.c | 39 ++++++++++++--------------------
 1 file changed, 15 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 261c9bd83f51..82db2b783123 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -287,6 +287,9 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 			view.type = I915_GGTT_VIEW_PARTIAL;
 			vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
 		}
+
+		/* The entire mappable GGTT is pinned? Unexpected! */
+		GEM_BUG_ON(vma == ERR_PTR(-ENOSPC));
 	}
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
@@ -333,23 +336,19 @@ err_rpm:
 	i915_gem_object_unpin_pages(obj);
 err:
 	switch (ret) {
-	case -EIO:
-		/*
-		 * We eat errors when the gpu is terminally wedged to avoid
-		 * userspace unduly crashing (gl has no provisions for mmaps to
-		 * fail). But any other -EIO isn't ours (e.g. swap in failure)
-		 * and so needs to be reported.
-		 */
-		if (!intel_gt_is_wedged(ggtt->vm.gt))
-			return VM_FAULT_SIGBUS;
-		/* else, fall through */
-	case -EAGAIN:
-		/*
-		 * EAGAIN means the gpu is hung and we'll wait for the error
-		 * handler to reset everything when re-faulting in
-		 * i915_mutex_lock_interruptible.
-		 */
+	default:
+		WARN_ONCE(ret, "unhandled error in %s: %i\n", __func__, ret);
+		/* fallthrough */
+	case -EIO: /* shmemfs failure from swap device */
+	case -EFAULT: /* purged object */
+		return VM_FAULT_SIGBUS;
+
+	case -ENOSPC: /* shmemfs allocation failure */
+	case -ENOMEM: /* our allocation failure */
+		return VM_FAULT_OOM;
+
 	case 0:
+	case -EAGAIN:
 	case -ERESTARTSYS:
 	case -EINTR:
 	case -EBUSY:
@@ -358,14 +357,6 @@ err:
 		 * already did the job.
 		 */
 		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	case -ENOSPC:
-	case -EFAULT:
-		return VM_FAULT_SIGBUS;
-	default:
-		WARN_ONCE(ret, "unhandled error in %s: %i\n", __func__, ret);
-		return VM_FAULT_SIGBUS;
 	}
 }
 
-- 
cgit v1.2.3


From b1a4383d1e6e6003fceba9aae14bda77bfe03dc3 Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Wed, 4 Sep 2019 00:52:52 +0530
Subject: drm/i915/display: Add debug log for color parameters

Add debug log for color related parameters like gamma_mode, gamma_enable,
csc_enable, etc inside intel_dump_pipe_config().

v6: -Added debug log for color para in intel_dump_pipe_config [Jani]
v7: -Split patch 3 into 4 patches
v8: -Corrected alignment [Uma]

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1567538578-4489-3-git-send-email-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 12a94c6e3d51..540dffa0a601 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -12140,6 +12140,15 @@ static void intel_dump_pipe_config(const struct intel_crtc_state *pipe_config,
 
 	intel_dpll_dump_hw_state(dev_priv, &pipe_config->dpll_hw_state);
 
+	if (IS_CHERRYVIEW(dev_priv))
+		DRM_DEBUG_KMS("cgm_mode: 0x%x gamma_mode: 0x%x gamma_enable: %d csc_enable: %d\n",
+			      pipe_config->cgm_mode, pipe_config->gamma_mode,
+			      pipe_config->gamma_enable, pipe_config->csc_enable);
+	else
+		DRM_DEBUG_KMS("csc_mode: 0x%x gamma_mode: 0x%x gamma_enable: %d csc_enable: %d\n",
+			      pipe_config->csc_mode, pipe_config->gamma_mode,
+			      pipe_config->gamma_enable, pipe_config->csc_enable);
+
 dump_planes:
 	if (!state)
 		return;
-- 
cgit v1.2.3


From 145450f6a42df99523967a0da42bdb00dacb413b Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Wed, 4 Sep 2019 00:52:51 +0530
Subject: drm/i915/display: Add func to get gamma bit precision

Each platform supports different gamma modes and each gamma mode
has different bit precision. Here bit precision corresponds
to number of bits the hw LUT supports.

Add func per platform to return bit precision corresponding to gamma mode
which will be later used as a parameter in lut comparison function
intel_color_lut_equal().

This is done for legacy, ilk, glk and their variant platforms.

v6:  -Added func intel_color_get_bit_precision() to get bit precision for
      gamma and degamma lut readout depending upon platform and
      corresponding to load_luts() [Ankit]
     -Made patch11 as patch3 [Jani]
v7:  -Renamed func intel_color_get_bit_precision() to
      intel_color_get_gamma_bit_precision()
     -Added separate function/platform for gamma bit precision [Ville]
     -Corrected checkpatch warnings
v8:  -Split patch 3 into 4 separate patches
v9:  -Changed commit message, gave more info [Uma]
     -Added precision func for icl+ platform
v10: -Removed precision func for chv and icl+ platforms [Jani]
     -Added gamma_enable check once [Jani]

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1567538578-4489-2-git-send-email-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 60 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_color.h |  1 +
 2 files changed, 61 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 71a0201437a9..b5c0c6583568 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1371,6 +1371,66 @@ static int icl_color_check(struct intel_crtc_state *crtc_state)
 	return 0;
 }
 
+static int i9xx_gamma_precision(const struct intel_crtc_state *crtc_state)
+{
+	switch (crtc_state->gamma_mode) {
+	case GAMMA_MODE_MODE_8BIT:
+		return 8;
+	case GAMMA_MODE_MODE_10BIT:
+		return 16;
+	default:
+		MISSING_CASE(crtc_state->gamma_mode);
+		return 0;
+	}
+}
+
+static int ilk_gamma_precision(const struct intel_crtc_state *crtc_state)
+{
+	if ((crtc_state->csc_mode & CSC_POSITION_BEFORE_GAMMA) == 0)
+		return 0;
+
+	switch (crtc_state->gamma_mode) {
+	case GAMMA_MODE_MODE_8BIT:
+		return 8;
+	case GAMMA_MODE_MODE_10BIT:
+		return 10;
+	default:
+		MISSING_CASE(crtc_state->gamma_mode);
+		return 0;
+	}
+}
+
+static int glk_gamma_precision(const struct intel_crtc_state *crtc_state)
+{
+	switch (crtc_state->gamma_mode) {
+	case GAMMA_MODE_MODE_8BIT:
+		return 8;
+	case GAMMA_MODE_MODE_10BIT:
+		return 10;
+	default:
+		MISSING_CASE(crtc_state->gamma_mode);
+		return 0;
+	}
+}
+
+int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+
+	if (!crtc_state->gamma_enable)
+		return 0;
+
+	if (HAS_GMCH(dev_priv) && !IS_CHERRYVIEW(dev_priv))
+		return i9xx_gamma_precision(crtc_state);
+	else if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+		return glk_gamma_precision(crtc_state);
+	else if (IS_IRONLAKE(dev_priv))
+		return ilk_gamma_precision(crtc_state);
+
+	return 0;
+}
+
 void intel_color_init(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
diff --git a/drivers/gpu/drm/i915/display/intel_color.h b/drivers/gpu/drm/i915/display/intel_color.h
index 057e8ac63555..0226d3a784b6 100644
--- a/drivers/gpu/drm/i915/display/intel_color.h
+++ b/drivers/gpu/drm/i915/display/intel_color.h
@@ -14,5 +14,6 @@ int intel_color_check(struct intel_crtc_state *crtc_state);
 void intel_color_commit(const struct intel_crtc_state *crtc_state);
 void intel_color_load_luts(const struct intel_crtc_state *crtc_state);
 void intel_color_get_config(struct intel_crtc_state *crtc_state);
+int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_state);
 
 #endif /* __INTEL_COLOR_H__ */
-- 
cgit v1.2.3


From e9c8f591445d7b99883889caab3c5d1aafcee360 Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Wed, 4 Sep 2019 00:52:53 +0530
Subject: drm/i915/display: Add func to compare hw/sw gamma lut

Add func intel_color_lut_equal() to compare hw/sw gamma
lut values. Since hw/sw gamma lut sizes and lut entries comparison
will be different for different gamma modes, add gamma mode dependent
checks.

v3:  -Rebase
v4:  -Renamed intel_compare_color_lut() to intel_color_lut_equal() [Jani]
     -Added the default label above the correct label [Jani]
     -Corrected smatch warn "variable dereferenced before check"
      [Dan Carpenter]
v5:  -Added condition (!blob1 && !blob2) return true [Jani]
v6:  -Made patch11 as patch3 [Jani]
v8:  -Split patch 3 into 4 patches
     -Optimized blob check condition [Ville]
v9:  -Exclude spilt gamma mode (bdw and ivb platforms)
      as there is exception in way gamma values are written in
      hardware [Ville]
     -Added exception made in commit [Uma]
     -Dropped else, character limit and indentation [Uma]
     -Added multi segmented gama mode for icl+ platforms [Uma]
v10: -Dropped multi segmented mode for icl+ platforms [Jani]
     -Removed references of sw and hw state in compare code [Jani]
     -Dropped inline from func [Jani]

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1567538578-4489-4-git-send-email-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 72 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_color.h |  6 +++
 2 files changed, 78 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index b5c0c6583568..1ab561d79706 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1431,6 +1431,78 @@ int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_stat
 	return 0;
 }
 
+static bool err_check(struct drm_color_lut *lut1,
+		      struct drm_color_lut *lut2, u32 err)
+{
+	return ((abs((long)lut2->red - lut1->red)) <= err) &&
+		((abs((long)lut2->blue - lut1->blue)) <= err) &&
+		((abs((long)lut2->green - lut1->green)) <= err);
+}
+
+static bool intel_color_lut_entry_equal(struct drm_color_lut *lut1,
+					struct drm_color_lut *lut2,
+					int lut_size, u32 err)
+{
+	int i;
+
+	for (i = 0; i < lut_size; i++) {
+		if (!err_check(&lut1[i], &lut2[i], err))
+			return false;
+	}
+
+	return true;
+}
+
+bool intel_color_lut_equal(struct drm_property_blob *blob1,
+			   struct drm_property_blob *blob2,
+			   u32 gamma_mode, u32 bit_precision)
+{
+	struct drm_color_lut *lut1, *lut2;
+	int lut_size1, lut_size2;
+	u32 err;
+
+	if (!blob1 != !blob2)
+		return false;
+
+	if (!blob1)
+		return true;
+
+	lut_size1 = drm_color_lut_size(blob1);
+	lut_size2 = drm_color_lut_size(blob2);
+
+	/* check sw and hw lut size */
+	switch (gamma_mode) {
+	case GAMMA_MODE_MODE_8BIT:
+	case GAMMA_MODE_MODE_10BIT:
+		if (lut_size1 != lut_size2)
+			return false;
+		break;
+	default:
+		MISSING_CASE(gamma_mode);
+			return false;
+	}
+
+	lut1 = blob1->data;
+	lut2 = blob2->data;
+
+	err = 0xffff >> bit_precision;
+
+	/* check sw and hw lut entry to be equal */
+	switch (gamma_mode) {
+	case GAMMA_MODE_MODE_8BIT:
+	case GAMMA_MODE_MODE_10BIT:
+		if (!intel_color_lut_entry_equal(lut1, lut2,
+						 lut_size2, err))
+			return false;
+		break;
+	default:
+		MISSING_CASE(gamma_mode);
+			return false;
+	}
+
+	return true;
+}
+
 void intel_color_init(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
diff --git a/drivers/gpu/drm/i915/display/intel_color.h b/drivers/gpu/drm/i915/display/intel_color.h
index 0226d3a784b6..173727aaa24d 100644
--- a/drivers/gpu/drm/i915/display/intel_color.h
+++ b/drivers/gpu/drm/i915/display/intel_color.h
@@ -6,8 +6,11 @@
 #ifndef __INTEL_COLOR_H__
 #define __INTEL_COLOR_H__
 
+#include <linux/types.h>
+
 struct intel_crtc_state;
 struct intel_crtc;
+struct drm_property_blob;
 
 void intel_color_init(struct intel_crtc *crtc);
 int intel_color_check(struct intel_crtc_state *crtc_state);
@@ -15,5 +18,8 @@ void intel_color_commit(const struct intel_crtc_state *crtc_state);
 void intel_color_load_luts(const struct intel_crtc_state *crtc_state);
 void intel_color_get_config(struct intel_crtc_state *crtc_state);
 int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_state);
+bool intel_color_lut_equal(struct drm_property_blob *blob1,
+			   struct drm_property_blob *blob2,
+			   u32 gamma_mode, u32 bit_precision);
 
 #endif /* __INTEL_COLOR_H__ */
-- 
cgit v1.2.3


From 7e764059cf708f262aa3c406af91f9f8f79e7f52 Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Wed, 4 Sep 2019 00:52:54 +0530
Subject: drm/i915/display: Add macro to compare gamma hw/sw lut

Add macro to compare hw/sw gamma lut values. First need to
check whether hw/sw gamma mode matches or not. If not
no need to compare lut values, if matches then only compare
lut entries.

v5: -Called PIPE_CONF_CHECK_COLOR_LUT inside if (!adjust) [Jani]
    -Added #undef PIPE_CONF_CHECK_COLOR_LUT [Jani]
v8: -Added check for gamma mode before gamma lut entry comparison
     [Jani]
    -Split patch 3 into 4 patches

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1567538578-4489-5-git-send-email-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 540dffa0a601..06cf2171474d 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -12531,6 +12531,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 {
 	struct drm_i915_private *dev_priv = to_i915(current_config->base.crtc->dev);
 	bool ret = true;
+	u32 bp_gamma = 0;
 	bool fixup_inherited = fastset &&
 		(current_config->base.mode.private_flags & I915_MODE_FLAG_INHERITED) &&
 		!(pipe_config->base.mode.private_flags & I915_MODE_FLAG_INHERITED);
@@ -12682,6 +12683,24 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	} \
 } while (0)
 
+#define PIPE_CONF_CHECK_COLOR_LUT(name1, name2, bit_precision) do { \
+	if (current_config->name1 != pipe_config->name1) { \
+		pipe_config_mismatch(fastset, __stringify(name1), \
+				"(expected %i, found %i, won't compare lut values)\n", \
+				current_config->name1, \
+				pipe_config->name1); \
+		ret = false;\
+	} else { \
+		if (!intel_color_lut_equal(current_config->name2, \
+					pipe_config->name2, pipe_config->name1, \
+					bit_precision)) { \
+			pipe_config_mismatch(fastset, __stringify(name2), \
+					"hw_state doesn't match sw_state\n"); \
+			ret = false; \
+		} \
+	} \
+} while (0)
+
 #define PIPE_CONF_QUIRK(quirk) \
 	((current_config->quirks | pipe_config->quirks) & (quirk))
 
@@ -12777,6 +12796,11 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 			PIPE_CONF_CHECK_X(csc_mode);
 		PIPE_CONF_CHECK_BOOL(gamma_enable);
 		PIPE_CONF_CHECK_BOOL(csc_enable);
+
+		bp_gamma = intel_color_get_gamma_bit_precision(pipe_config);
+		if (bp_gamma)
+			PIPE_CONF_CHECK_COLOR_LUT(gamma_mode, base.gamma_lut, bp_gamma);
+
 	}
 
 	PIPE_CONF_CHECK_BOOL(double_wide);
@@ -12839,6 +12863,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 #undef PIPE_CONF_CHECK_P
 #undef PIPE_CONF_CHECK_FLAGS
 #undef PIPE_CONF_CHECK_CLOCK_FUZZY
+#undef PIPE_CONF_CHECK_COLOR_LUT
 #undef PIPE_CONF_QUIRK
 
 	return ret;
-- 
cgit v1.2.3


From 1af22383829864299102ca0c2eab458f755a9971 Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Wed, 4 Sep 2019 00:52:55 +0530
Subject: drm/i915/display: Extract i9xx_read_luts()

For the legacy(gen < 4) gamma, add hw read out to create hw blob of gamma
lut values. Also, add function intel_color_lut_pack to convert hw value
with given bit precision to lut property val.

v4:  -No need to initialize *blob [Jani]
     -Removed right shifts [Jani]
     -Dropped dev local var [Jani]
v5:  -Returned blob instead of assigning it internally within the
      function [Ville]
     -Renamed function i9xx_get_color_config() to i9xx_read_luts()
     -Renamed i9xx_get_config_internal() to i9xx_read_lut_8() [Ville]
v9:  -Change in commit message [Jani, Uma]
     -Wrap commit within 75 characters [Uma]
     -Use macro for 256 [Uma]
     -Made read func para as const [Ville, Uma]
v10: -Made i9xx_read_luts() static [Jani]

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1567538578-4489-6-git-send-email-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 54 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_reg.h            |  3 ++
 2 files changed, 57 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 1ab561d79706..55076def6a98 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1503,6 +1503,59 @@ bool intel_color_lut_equal(struct drm_property_blob *blob1,
 	return true;
 }
 
+/* convert hw value with given bit_precision to lut property val */
+static u32 intel_color_lut_pack(u32 val, u32 bit_precision)
+{
+	u32 max = 0xffff >> (16 - bit_precision);
+
+	val = clamp_val(val, 0, max);
+
+	if (bit_precision < 16)
+		val <<= 16 - bit_precision;
+
+	return val;
+}
+
+static struct drm_property_blob *
+i9xx_read_lut_8(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
+	struct drm_property_blob *blob;
+	struct drm_color_lut *blob_data;
+	u32 i, val;
+
+	blob = drm_property_create_blob(&dev_priv->drm,
+					sizeof(struct drm_color_lut) * LEGACY_LUT_LENGTH,
+					NULL);
+	if (IS_ERR(blob))
+		return NULL;
+
+	blob_data = blob->data;
+
+	for (i = 0; i < LEGACY_LUT_LENGTH; i++) {
+		if (HAS_GMCH(dev_priv))
+			val = I915_READ(PALETTE(pipe, i));
+		else
+			val = I915_READ(LGC_PALETTE(pipe, i));
+
+		blob_data[i].red = intel_color_lut_pack(REG_FIELD_GET(
+							LGC_PALETTE_RED_MASK, val), 8);
+		blob_data[i].green = intel_color_lut_pack(REG_FIELD_GET(
+							  LGC_PALETTE_GREEN_MASK, val), 8);
+		blob_data[i].blue = intel_color_lut_pack(REG_FIELD_GET(
+							 LGC_PALETTE_BLUE_MASK, val), 8);
+	}
+
+	return blob;
+}
+
+static void i9xx_read_luts(struct intel_crtc_state *crtc_state)
+{
+	crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+}
+
 void intel_color_init(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
@@ -1523,6 +1576,7 @@ void intel_color_init(struct intel_crtc *crtc)
 			dev_priv->display.color_check = i9xx_color_check;
 			dev_priv->display.color_commit = i9xx_color_commit;
 			dev_priv->display.load_luts = i9xx_load_luts;
+			dev_priv->display.read_luts = i9xx_read_luts;
 		}
 	} else {
 		if (INTEL_GEN(dev_priv) >= 11)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6c43b8c583bb..aac717fa4e25 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7192,6 +7192,9 @@ enum {
 /* legacy palette */
 #define _LGC_PALETTE_A           0x4a000
 #define _LGC_PALETTE_B           0x4a800
+#define LGC_PALETTE_RED_MASK     REG_GENMASK(23, 16)
+#define LGC_PALETTE_GREEN_MASK   REG_GENMASK(15, 8)
+#define LGC_PALETTE_BLUE_MASK    REG_GENMASK(7, 0)
 #define LGC_PALETTE(pipe, i) _MMIO(_PIPE(pipe, _LGC_PALETTE_A, _LGC_PALETTE_B) + (i) * 4)
 
 /* ilk/snb precision palette */
-- 
cgit v1.2.3


From 6b97b118d4d542c7bc25b725c6de3947fffb921b Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Wed, 4 Sep 2019 00:52:56 +0530
Subject: drm/i915/display: Extract ilk_read_luts()

For ilk, add hw read out to create hw blob of gamma
lut values.

v4:  -No need to initialize *blob [Jani]
     -Removed right shifts [Jani]
     -Dropped dev local var [Jani]
v5:  -Returned blob instead of assigning it internally within the
      function [Ville]
     -Renamed ilk_get_color_config() to ilk_read_luts() [Ville]
v9:  -80 character limit [Uma]
     -Made read func para as const [Ville, Uma]
     -Renamed ilk_read_gamma_lut() to ilk_read_lut_10() [Uma, Ville]
v10: -Made ilk_read_luts() static [Jani]
     -ilk_load_lut_10 has lut_size, not (lut_size - 1) [Jani]

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1567538578-4489-7-git-send-email-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 45 +++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/i915_reg.h            |  3 ++
 2 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 55076def6a98..80f82b2bd284 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1556,6 +1556,47 @@ static void i9xx_read_luts(struct intel_crtc_state *crtc_state)
 	crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
 }
 
+static struct drm_property_blob *
+ilk_read_lut_10(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	u32 lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
+	enum pipe pipe = crtc->pipe;
+	struct drm_property_blob *blob;
+	struct drm_color_lut *blob_data;
+	u32 i, val;
+
+	blob = drm_property_create_blob(&dev_priv->drm,
+					sizeof(struct drm_color_lut) * lut_size,
+					NULL);
+	if (IS_ERR(blob))
+		return NULL;
+
+	blob_data = blob->data;
+
+	for (i = 0; i < lut_size; i++) {
+		val = I915_READ(PREC_PALETTE(pipe, i));
+
+		blob_data[i].red = intel_color_lut_pack(REG_FIELD_GET(
+							PREC_PALETTE_RED_MASK, val), 10);
+		blob_data[i].green = intel_color_lut_pack(REG_FIELD_GET(
+							  PREC_PALETTE_GREEN_MASK, val), 10);
+		blob_data[i].blue = intel_color_lut_pack(REG_FIELD_GET(
+							 PREC_PALETTE_BLUE_MASK, val), 10);
+	}
+
+	return blob;
+}
+
+static void ilk_read_luts(struct intel_crtc_state *crtc_state)
+{
+	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
+		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+	else
+		crtc_state->base.gamma_lut = ilk_read_lut_10(crtc_state);
+}
+
 void intel_color_init(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
@@ -1603,8 +1644,10 @@ void intel_color_init(struct intel_crtc *crtc)
 			dev_priv->display.load_luts = bdw_load_luts;
 		else if (INTEL_GEN(dev_priv) >= 7)
 			dev_priv->display.load_luts = ivb_load_luts;
-		else
+		else {
 			dev_priv->display.load_luts = ilk_load_luts;
+			dev_priv->display.read_luts = ilk_read_luts;
+		}
 	}
 
 	drm_crtc_enable_color_mgmt(&crtc->base,
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index aac717fa4e25..6ebb76a430e4 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7200,6 +7200,9 @@ enum {
 /* ilk/snb precision palette */
 #define _PREC_PALETTE_A           0x4b000
 #define _PREC_PALETTE_B           0x4c000
+#define   PREC_PALETTE_RED_MASK   REG_GENMASK(29, 20)
+#define   PREC_PALETTE_GREEN_MASK REG_GENMASK(19, 10)
+#define   PREC_PALETTE_BLUE_MASK  REG_GENMASK(9, 0)
 #define PREC_PALETTE(pipe, i) _MMIO(_PIPE(pipe, _PREC_PALETTE_A, _PREC_PALETTE_B) + (i) * 4)
 
 #define  _PREC_PIPEAGCMAX              0x4d000
-- 
cgit v1.2.3


From 4bb6a9d5d9a8289673c4cb0786d44be8a63c21db Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Wed, 4 Sep 2019 00:52:57 +0530
Subject: drm/i915/display: Extract glk_read_luts()

For glk, add hw read out to create hw blob of gamma
lut values.

v4: -No need to initialize *blob [Jani]
    -Removed right shifts [Jani]
    -Dropped dev local var [Jani]
v5: -Returned blob instead of assigning it internally within the
     function [Ville]
    -Renamed glk_get_color_config() to glk_read_luts() [Ville]
    -Added degamma validation [Ville]
v9: -80 character limit [Uma]
    -Made read func para as const [Ville, Uma]

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1567538578-4489-8-git-send-email-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 51 ++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_reg.h            |  3 ++
 2 files changed, 52 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 80f82b2bd284..6d641e159899 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1597,6 +1597,52 @@ static void ilk_read_luts(struct intel_crtc_state *crtc_state)
 		crtc_state->base.gamma_lut = ilk_read_lut_10(crtc_state);
 }
 
+static struct drm_property_blob *
+glk_read_lut_10(const struct intel_crtc_state *crtc_state, u32 prec_index)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	int hw_lut_size = ivb_lut_10_size(prec_index);
+	enum pipe pipe = crtc->pipe;
+	struct drm_property_blob *blob;
+	struct drm_color_lut *blob_data;
+	u32 i, val;
+
+	I915_WRITE(PREC_PAL_INDEX(pipe), prec_index |
+		   PAL_PREC_AUTO_INCREMENT);
+
+	blob = drm_property_create_blob(&dev_priv->drm,
+					sizeof(struct drm_color_lut) * hw_lut_size,
+					NULL);
+	if (IS_ERR(blob))
+		return NULL;
+
+	blob_data = blob->data;
+
+	for (i = 0; i < hw_lut_size; i++) {
+		val = I915_READ(PREC_PAL_DATA(pipe));
+
+		blob_data[i].red = intel_color_lut_pack(REG_FIELD_GET(
+							PREC_PAL_DATA_RED_MASK, val), 10);
+		blob_data[i].green = intel_color_lut_pack(REG_FIELD_GET(
+							PREC_PAL_DATA_GREEN_MASK, val), 10);
+		blob_data[i].blue = intel_color_lut_pack(REG_FIELD_GET(
+							PREC_PAL_DATA_BLUE_MASK, val), 10);
+	}
+
+	I915_WRITE(PREC_PAL_INDEX(pipe), 0);
+
+	return blob;
+}
+
+static void glk_read_luts(struct intel_crtc_state *crtc_state)
+{
+	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
+		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+	else
+		crtc_state->base.gamma_lut = glk_read_lut_10(crtc_state, PAL_PREC_INDEX_VALUE(0));
+}
+
 void intel_color_init(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
@@ -1638,9 +1684,10 @@ void intel_color_init(struct intel_crtc *crtc)
 
 		if (INTEL_GEN(dev_priv) >= 11)
 			dev_priv->display.load_luts = icl_load_luts;
-		else if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+		else if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv)) {
 			dev_priv->display.load_luts = glk_load_luts;
-		else if (INTEL_GEN(dev_priv) >= 8)
+			dev_priv->display.read_luts = glk_read_luts;
+		} else if (INTEL_GEN(dev_priv) >= 8)
 			dev_priv->display.load_luts = bdw_load_luts;
 		else if (INTEL_GEN(dev_priv) >= 7)
 			dev_priv->display.load_luts = ivb_load_luts;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6ebb76a430e4..45ed96d7c599 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -10351,6 +10351,9 @@ enum skl_power_gate {
 #define _PAL_PREC_GC_MAX_A	0x4A410
 #define _PAL_PREC_GC_MAX_B	0x4AC10
 #define _PAL_PREC_GC_MAX_C	0x4B410
+#define   PREC_PAL_DATA_RED_MASK	REG_GENMASK(29, 20)
+#define   PREC_PAL_DATA_GREEN_MASK	REG_GENMASK(19, 10)
+#define   PREC_PAL_DATA_BLUE_MASK	REG_GENMASK(9, 0)
 #define _PAL_PREC_EXT_GC_MAX_A	0x4A420
 #define _PAL_PREC_EXT_GC_MAX_B	0x4AC20
 #define _PAL_PREC_EXT_GC_MAX_C	0x4B420
-- 
cgit v1.2.3


From 9d7b01e93526efe79dbf75b69cc5972b5a4f7b37 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 4 Sep 2019 11:07:07 +0100
Subject: drm/i915: Restore relaxed padding (OCL_OOB_SUPPRES_ENABLE) for skl+

This bit was fliped on for "syncing dependencies between camera and
graphics". BSpec has no recollection why, and it is causing
unrecoverable GPU hangs with Vulkan compute workloads.

From BSpec, setting bit5 to 0 enables relaxed padding requirements for
buffers, 1D and 2D non-array, non-MSAA, non-mip-mapped linear surfaces;
and *must* be set to 0h on skl+ to ensure "Out of Bounds" case is
suppressed.

Reported-by: Jason Ekstrand <jason@jlekstrand.net>
Suggested-by: Jason Ekstrand <jason@jlekstrand.net>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=110998
Fixes: 8424171e135c ("drm/i915/gen9: h/w w/a: syncing dependencies between camera and graphics")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: denys.kostin@globallogic.com
Cc: Jason Ekstrand <jason@jlekstrand.net>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: <stable@vger.kernel.org> # v4.1+
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190904100707.7377-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 8639fcccdb42..243d3f77be13 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -297,11 +297,6 @@ static void gen9_ctx_workarounds_init(struct intel_engine_cs *engine,
 			  FLOW_CONTROL_ENABLE |
 			  PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE);
 
-	/* Syncing dependencies between camera and graphics:skl,bxt,kbl */
-	if (!IS_COFFEELAKE(i915))
-		WA_SET_BIT_MASKED(HALF_SLICE_CHICKEN3,
-				  GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC);
-
 	/* WaEnableYV12BugFixInHalfSliceChicken7:skl,bxt,kbl,glk,cfl */
 	/* WaEnableSamplerGPGPUPreemptionSupport:skl,bxt,kbl,cfl */
 	WA_SET_BIT_MASKED(GEN9_HALF_SLICE_CHICKEN7,
-- 
cgit v1.2.3


From e838bfa8e170415fa3cc8e83ecb171e809c0c422 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 3 Sep 2019 18:40:18 +0300
Subject: Revert "drm/i915: Fix DP-MST crtc_mask"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 4eaceea3a00f8e936a7f48dcd0c975a57f88930f.

Several userspace clients (modesetting ddx and mutter+wayland at least)
handle encoder.possible_crtcs incorrectly. What they essentially do is
the following:

possible_crtcs = ~0;
for_each_possible_encoder(connector)
	possible_crtcs &= encoder->possible_crtcs;

Ie. they calculate the intersection of the possible_crtcs
for the connector when they really should be calculating the
union instead.

In our case each MST encoder now has just one unique bit set,
and so the intersection is always zero. The end result is that
MST connectors can't be lit up because no crtc can be found to
drive them.

I've submitted a fix for the modesetting ddx [1], and complained
on #wayland about mutter, so hopefully the situation will improve
in the future. In the meantime we have regression, and so must go
back to the old way of misconfiguring possible_crtcs in the kernel.

[1] https://gitlab.freedesktop.org/xorg/xserver/merge_requests/277

Cc: Jonas Ådahl <jadahl@gmail.com>
Cc: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111507
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190903154018.26357-1-ville.syrjala@linux.intel.com
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp_mst.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 6df240a01b8c..37366f81255b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -615,7 +615,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
 	intel_encoder->type = INTEL_OUTPUT_DP_MST;
 	intel_encoder->power_domain = intel_dig_port->base.power_domain;
 	intel_encoder->port = intel_dig_port->base.port;
-	intel_encoder->crtc_mask = BIT(pipe);
+	intel_encoder->crtc_mask = 0x7;
 	intel_encoder->cloneable = 0;
 
 	intel_encoder->compute_config = intel_dp_mst_compute_config;
-- 
cgit v1.2.3


From ab016914984e2a7405756dfc8a8e4cb54a4c1b48 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue, 20 Aug 2019 21:54:51 +0200
Subject: drm/i915: disable set/get_tiling ioctl on gen12+
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The cpu (de)tiler hw is gone, this stopped being useful. Plus it never
supported any of the fancy new tiling formats, which means userspace
also stopped using the magic side-channel this provides.

This would totally break a lot of the igts, but they're already broken
for the same reasons as userspace on gen12 would be.

v2: Look at ggtt->num_fences instead, that also avoids the need for a
comment (Chris). This also means that gen12 support really needs to
make sure num_fences is set to 0. There is a patch for that, but it
checks for HAS_MAPPABLE_APERTURE, which I'm not sure is the right
thing really. Adding relevant people.

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Kenneth Graunke <kenneth@whitecape.org>
Cc: Jason Ekstrand <jason@jlekstrand.net>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190820195451.15671-1-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/i915/gem/i915_gem_tiling.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
index ca0c2f451742..e5d1ae8d4dba 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
@@ -313,10 +313,14 @@ int
 i915_gem_set_tiling_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *file)
 {
+	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_set_tiling *args = data;
 	struct drm_i915_gem_object *obj;
 	int err;
 
+	if (!dev_priv->ggtt.num_fences)
+		return -EOPNOTSUPP;
+
 	obj = i915_gem_object_lookup(file, args->handle);
 	if (!obj)
 		return -ENOENT;
@@ -402,6 +406,9 @@ i915_gem_get_tiling_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_gem_object *obj;
 	int err = -ENOENT;
 
+	if (!dev_priv->ggtt.num_fences)
+		return -EOPNOTSUPP;
+
 	rcu_read_lock();
 	obj = i915_gem_object_lookup_rcu(file, args->handle);
 	if (obj) {
-- 
cgit v1.2.3


From 2f3b87124b9f08518b43abf2266035dd22fdbd3c Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Wed, 4 Sep 2019 14:34:14 -0700
Subject: drm/i915/psr: Only handle interruptions of the transcoder in use
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It was enabling and checking PSR interruptions in every transcoder
while it should keep the interruptions on the non-used transcoders
masked.

While doing this it gives us trouble on Tiger Lake if we are
reading/writing to registers of disabled transcoders since from gen12
onwards the registers are relative to the transcoder. Instead of forcing
them ON to access those registers, just avoid the accesses as they are
not needed.

v2 (Lucas):
  - Explain why we can't keep accessing all transcoders
  - Remove TODO about extending the irq handling to multiple instances:
    when/if implementing multiple instances it's pretty clear by the
    singleton psr that it needs to be extended
  - Fix intel_psr_debug_set() calling psr_irq_control() with
    psr.transcoder not set yet (from Imre). Now we only set the debug
    register right away if psr is already enabled. Otherwise we just
    record the value to be set when enabling the source.
  - Do not depend on the value of TRANSCODER_A. Just be relative to it
    (from Imre)
  - handle psr error last so we don't schedule the work before handling
    the other flags

v3:
  - Adding a warning about setting reserverd bits on EDP_PSR_IMR

Cc: Imre Deak <imre.deak@intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190904213419.27547-2-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 142 ++++++++++++-------------------
 drivers/gpu/drm/i915/i915_reg.h          |  13 ++-
 2 files changed, 60 insertions(+), 95 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 629b8b98a97f..1d99ffeaa36a 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -88,48 +88,20 @@ static bool intel_psr2_enabled(struct drm_i915_private *dev_priv,
 	}
 }
 
-static int edp_psr_shift(enum transcoder cpu_transcoder)
+static void psr_irq_control(struct drm_i915_private *dev_priv)
 {
-	switch (cpu_transcoder) {
-	case TRANSCODER_A:
-		return EDP_PSR_TRANSCODER_A_SHIFT;
-	case TRANSCODER_B:
-		return EDP_PSR_TRANSCODER_B_SHIFT;
-	case TRANSCODER_C:
-		return EDP_PSR_TRANSCODER_C_SHIFT;
-	default:
-		MISSING_CASE(cpu_transcoder);
-		/* fallthrough */
-	case TRANSCODER_EDP:
-		return EDP_PSR_TRANSCODER_EDP_SHIFT;
-	}
-}
-
-static void psr_irq_control(struct drm_i915_private *dev_priv, u32 debug)
-{
-	u32 debug_mask, mask;
-	enum transcoder cpu_transcoder;
-	u32 transcoders = BIT(TRANSCODER_EDP);
-
-	if (INTEL_GEN(dev_priv) >= 8)
-		transcoders |= BIT(TRANSCODER_A) |
-			       BIT(TRANSCODER_B) |
-			       BIT(TRANSCODER_C);
-
-	debug_mask = 0;
-	mask = 0;
-	for_each_cpu_transcoder_masked(dev_priv, cpu_transcoder, transcoders) {
-		int shift = edp_psr_shift(cpu_transcoder);
-
-		mask |= EDP_PSR_ERROR(shift);
-		debug_mask |= EDP_PSR_POST_EXIT(shift) |
-			      EDP_PSR_PRE_ENTRY(shift);
-	}
-
-	if (debug & I915_PSR_DEBUG_IRQ)
-		mask |= debug_mask;
-
-	I915_WRITE(EDP_PSR_IMR, ~mask);
+	enum transcoder trans = dev_priv->psr.transcoder;
+	u32 val, mask;
+
+	mask = EDP_PSR_ERROR(trans);
+	if (dev_priv->psr.debug & I915_PSR_DEBUG_IRQ)
+		mask |= EDP_PSR_POST_EXIT(trans) | EDP_PSR_PRE_ENTRY(trans);
+
+	/* Warning: it is masking/setting reserved bits too */
+	val = I915_READ(EDP_PSR_IMR);
+	val &= ~EDP_PSR_TRANS_MASK(trans);
+	val |= ~mask;
+	I915_WRITE(EDP_PSR_IMR, val);
 }
 
 static void psr_event_print(u32 val, bool psr2_enabled)
@@ -171,60 +143,48 @@ static void psr_event_print(u32 val, bool psr2_enabled)
 
 void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir)
 {
-	u32 transcoders = BIT(TRANSCODER_EDP);
-	enum transcoder cpu_transcoder;
+	enum transcoder cpu_transcoder = dev_priv->psr.transcoder;
 	ktime_t time_ns =  ktime_get();
-	u32 mask = 0;
-
-	if (INTEL_GEN(dev_priv) >= 8)
-		transcoders |= BIT(TRANSCODER_A) |
-			       BIT(TRANSCODER_B) |
-			       BIT(TRANSCODER_C);
-
-	for_each_cpu_transcoder_masked(dev_priv, cpu_transcoder, transcoders) {
-		int shift = edp_psr_shift(cpu_transcoder);
 
-		if (psr_iir & EDP_PSR_ERROR(shift)) {
-			DRM_WARN("[transcoder %s] PSR aux error\n",
-				 transcoder_name(cpu_transcoder));
+	if (psr_iir & EDP_PSR_PRE_ENTRY(cpu_transcoder)) {
+		dev_priv->psr.last_entry_attempt = time_ns;
+		DRM_DEBUG_KMS("[transcoder %s] PSR entry attempt in 2 vblanks\n",
+			      transcoder_name(cpu_transcoder));
+	}
 
-			dev_priv->psr.irq_aux_error = true;
+	if (psr_iir & EDP_PSR_POST_EXIT(cpu_transcoder)) {
+		dev_priv->psr.last_exit = time_ns;
+		DRM_DEBUG_KMS("[transcoder %s] PSR exit completed\n",
+			      transcoder_name(cpu_transcoder));
 
-			/*
-			 * If this interruption is not masked it will keep
-			 * interrupting so fast that it prevents the scheduled
-			 * work to run.
-			 * Also after a PSR error, we don't want to arm PSR
-			 * again so we don't care about unmask the interruption
-			 * or unset irq_aux_error.
-			 */
-			mask |= EDP_PSR_ERROR(shift);
-		}
+		if (INTEL_GEN(dev_priv) >= 9) {
+			u32 val = I915_READ(PSR_EVENT(cpu_transcoder));
+			bool psr2_enabled = dev_priv->psr.psr2_enabled;
 
-		if (psr_iir & EDP_PSR_PRE_ENTRY(shift)) {
-			dev_priv->psr.last_entry_attempt = time_ns;
-			DRM_DEBUG_KMS("[transcoder %s] PSR entry attempt in 2 vblanks\n",
-				      transcoder_name(cpu_transcoder));
+			I915_WRITE(PSR_EVENT(cpu_transcoder), val);
+			psr_event_print(val, psr2_enabled);
 		}
+	}
 
-		if (psr_iir & EDP_PSR_POST_EXIT(shift)) {
-			dev_priv->psr.last_exit = time_ns;
-			DRM_DEBUG_KMS("[transcoder %s] PSR exit completed\n",
-				      transcoder_name(cpu_transcoder));
+	if (psr_iir & EDP_PSR_ERROR(cpu_transcoder)) {
+		u32 val;
 
-			if (INTEL_GEN(dev_priv) >= 9) {
-				u32 val = I915_READ(PSR_EVENT(cpu_transcoder));
-				bool psr2_enabled = dev_priv->psr.psr2_enabled;
+		DRM_WARN("[transcoder %s] PSR aux error\n",
+			 transcoder_name(cpu_transcoder));
 
-				I915_WRITE(PSR_EVENT(cpu_transcoder), val);
-				psr_event_print(val, psr2_enabled);
-			}
-		}
-	}
+		dev_priv->psr.irq_aux_error = true;
 
-	if (mask) {
-		mask |= I915_READ(EDP_PSR_IMR);
-		I915_WRITE(EDP_PSR_IMR, mask);
+		/*
+		 * If this interruption is not masked it will keep
+		 * interrupting so fast that it prevents the scheduled
+		 * work to run.
+		 * Also after a PSR error, we don't want to arm PSR
+		 * again so we don't care about unmask the interruption
+		 * or unset irq_aux_error.
+		 */
+		val = I915_READ(EDP_PSR_IMR);
+		val |= EDP_PSR_ERROR(cpu_transcoder);
+		I915_WRITE(EDP_PSR_IMR, val);
 
 		schedule_work(&dev_priv->psr.work);
 	}
@@ -747,7 +707,7 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp,
 
 	I915_WRITE(EDP_PSR_DEBUG(dev_priv->psr.transcoder), mask);
 
-	psr_irq_control(dev_priv, dev_priv->psr.debug);
+	psr_irq_control(dev_priv);
 }
 
 static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
@@ -772,7 +732,7 @@ static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
 	 * to avoid any rendering problems.
 	 */
 	val = I915_READ(EDP_PSR_IIR);
-	val &= EDP_PSR_ERROR(edp_psr_shift(dev_priv->psr.transcoder));
+	val &= EDP_PSR_ERROR(dev_priv->psr.transcoder);
 	if (val) {
 		dev_priv->psr.sink_not_reliable = true;
 		DRM_DEBUG_KMS("PSR interruption error set, not enabling PSR\n");
@@ -1120,7 +1080,13 @@ int intel_psr_debug_set(struct drm_i915_private *dev_priv, u64 val)
 
 	old_mode = dev_priv->psr.debug & I915_PSR_DEBUG_MODE_MASK;
 	dev_priv->psr.debug = val;
-	psr_irq_control(dev_priv, dev_priv->psr.debug);
+
+	/*
+	 * Do it right away if it's already enabled, otherwise it will be done
+	 * when enabling the source.
+	 */
+	if (dev_priv->psr.enabled)
+		psr_irq_control(dev_priv);
 
 	mutex_unlock(&dev_priv->psr.lock);
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 45ed96d7c599..81f68455d492 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4225,13 +4225,12 @@ enum {
 /* Bspec claims those aren't shifted but stay at 0x64800 */
 #define EDP_PSR_IMR				_MMIO(0x64834)
 #define EDP_PSR_IIR				_MMIO(0x64838)
-#define   EDP_PSR_ERROR(shift)			(1 << ((shift) + 2))
-#define   EDP_PSR_POST_EXIT(shift)		(1 << ((shift) + 1))
-#define   EDP_PSR_PRE_ENTRY(shift)		(1 << (shift))
-#define   EDP_PSR_TRANSCODER_C_SHIFT		24
-#define   EDP_PSR_TRANSCODER_B_SHIFT		16
-#define   EDP_PSR_TRANSCODER_A_SHIFT		8
-#define   EDP_PSR_TRANSCODER_EDP_SHIFT		0
+#define   _EDP_PSR_TRANS_SHIFT(trans)		((trans) == TRANSCODER_EDP ? \
+						 0 : ((trans) - TRANSCODER_A + 1) * 8)
+#define   EDP_PSR_TRANS_MASK(trans)		(0x7 << _EDP_PSR_TRANS_SHIFT(trans))
+#define   EDP_PSR_ERROR(trans)			(0x4 << _EDP_PSR_TRANS_SHIFT(trans))
+#define   EDP_PSR_POST_EXIT(trans)		(0x2 << _EDP_PSR_TRANS_SHIFT(trans))
+#define   EDP_PSR_PRE_ENTRY(trans)		(0x1 << _EDP_PSR_TRANS_SHIFT(trans))
 
 #define _SRD_AUX_CTL_A				0x60810
 #define _SRD_AUX_CTL_EDP			0x6f810
-- 
cgit v1.2.3


From 8241cfbe67f4082eee5fc72e5a8025c5b58c2ddf Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Wed, 4 Sep 2019 14:34:15 -0700
Subject: drm/i915/tgl: Access the right register when handling PSR
 interruptions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For older gens PSR IIR and IMR have fixed addresses. From TGL onwards those
registers moved to each transcoder offset. The bits for the registers
are defined without an offset per transcoder as right now we have one
register per transcoder. So add a fake "trans_shift" when calculating
the bits offsets: it will be 0 for gen12+ and psr.transcoder otherwise.

v2 (Lucas): change the implementation to use trans_shift instead of
getting each bit value with a different macro

Cc: Imre Deak <imre.deak@intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190904213419.27547-3-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_psr.c | 60 ++++++++++++++++++++++++--------
 drivers/gpu/drm/i915/i915_irq.c          | 51 +++++++++++++++++++++++----
 drivers/gpu/drm/i915/i915_reg.h          | 10 +++++-
 3 files changed, 99 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 1d99ffeaa36a..b3c7eef53bf3 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -90,18 +90,33 @@ static bool intel_psr2_enabled(struct drm_i915_private *dev_priv,
 
 static void psr_irq_control(struct drm_i915_private *dev_priv)
 {
-	enum transcoder trans = dev_priv->psr.transcoder;
-	u32 val, mask;
+	enum transcoder trans_shift;
+	u32 mask, val;
+	i915_reg_t imr_reg;
 
-	mask = EDP_PSR_ERROR(trans);
+	/*
+	 * gen12+ has registers relative to transcoder and one per transcoder
+	 * using the same bit definition: handle it as TRANSCODER_EDP to force
+	 * 0 shift in bit definition
+	 */
+	if (INTEL_GEN(dev_priv) >= 12) {
+		trans_shift = 0;
+		imr_reg = TRANS_PSR_IMR(dev_priv->psr.transcoder);
+	} else {
+		trans_shift = dev_priv->psr.transcoder;
+		imr_reg = EDP_PSR_IMR;
+	}
+
+	mask = EDP_PSR_ERROR(trans_shift);
 	if (dev_priv->psr.debug & I915_PSR_DEBUG_IRQ)
-		mask |= EDP_PSR_POST_EXIT(trans) | EDP_PSR_PRE_ENTRY(trans);
+		mask |= EDP_PSR_POST_EXIT(trans_shift) |
+			EDP_PSR_PRE_ENTRY(trans_shift);
 
 	/* Warning: it is masking/setting reserved bits too */
-	val = I915_READ(EDP_PSR_IMR);
-	val &= ~EDP_PSR_TRANS_MASK(trans);
+	val = I915_READ(imr_reg);
+	val &= ~EDP_PSR_TRANS_MASK(trans_shift);
 	val |= ~mask;
-	I915_WRITE(EDP_PSR_IMR, val);
+	I915_WRITE(imr_reg, val);
 }
 
 static void psr_event_print(u32 val, bool psr2_enabled)
@@ -144,15 +159,25 @@ static void psr_event_print(u32 val, bool psr2_enabled)
 void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir)
 {
 	enum transcoder cpu_transcoder = dev_priv->psr.transcoder;
+	enum transcoder trans_shift;
+	i915_reg_t imr_reg;
 	ktime_t time_ns =  ktime_get();
 
-	if (psr_iir & EDP_PSR_PRE_ENTRY(cpu_transcoder)) {
+	if (INTEL_GEN(dev_priv) >= 12) {
+		trans_shift = 0;
+		imr_reg = TRANS_PSR_IMR(dev_priv->psr.transcoder);
+	} else {
+		trans_shift = dev_priv->psr.transcoder;
+		imr_reg = EDP_PSR_IMR;
+	}
+
+	if (psr_iir & EDP_PSR_PRE_ENTRY(trans_shift)) {
 		dev_priv->psr.last_entry_attempt = time_ns;
 		DRM_DEBUG_KMS("[transcoder %s] PSR entry attempt in 2 vblanks\n",
 			      transcoder_name(cpu_transcoder));
 	}
 
-	if (psr_iir & EDP_PSR_POST_EXIT(cpu_transcoder)) {
+	if (psr_iir & EDP_PSR_POST_EXIT(trans_shift)) {
 		dev_priv->psr.last_exit = time_ns;
 		DRM_DEBUG_KMS("[transcoder %s] PSR exit completed\n",
 			      transcoder_name(cpu_transcoder));
@@ -166,7 +191,7 @@ void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir)
 		}
 	}
 
-	if (psr_iir & EDP_PSR_ERROR(cpu_transcoder)) {
+	if (psr_iir & EDP_PSR_ERROR(trans_shift)) {
 		u32 val;
 
 		DRM_WARN("[transcoder %s] PSR aux error\n",
@@ -182,9 +207,9 @@ void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir)
 		 * again so we don't care about unmask the interruption
 		 * or unset irq_aux_error.
 		 */
-		val = I915_READ(EDP_PSR_IMR);
-		val |= EDP_PSR_ERROR(cpu_transcoder);
-		I915_WRITE(EDP_PSR_IMR, val);
+		val = I915_READ(imr_reg);
+		val |= EDP_PSR_ERROR(trans_shift);
+		I915_WRITE(imr_reg, val);
 
 		schedule_work(&dev_priv->psr.work);
 	}
@@ -731,8 +756,13 @@ static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
 	 * first time that PSR HW tries to activate so lets keep PSR disabled
 	 * to avoid any rendering problems.
 	 */
-	val = I915_READ(EDP_PSR_IIR);
-	val &= EDP_PSR_ERROR(dev_priv->psr.transcoder);
+	if (INTEL_GEN(dev_priv) >= 12) {
+		val = I915_READ(TRANS_PSR_IIR(dev_priv->psr.transcoder));
+		val &= EDP_PSR_ERROR(0);
+	} else {
+		val = I915_READ(EDP_PSR_IIR);
+		val &= EDP_PSR_ERROR(dev_priv->psr.transcoder);
+	}
 	if (val) {
 		dev_priv->psr.sink_not_reliable = true;
 		DRM_DEBUG_KMS("PSR interruption error set, not enabling PSR\n");
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 135c9ee55e07..ae7228032d2c 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2613,11 +2613,21 @@ gen8_de_misc_irq_handler(struct drm_i915_private *dev_priv, u32 iir)
 	}
 
 	if (iir & GEN8_DE_EDP_PSR) {
-		u32 psr_iir = I915_READ(EDP_PSR_IIR);
+		u32 psr_iir;
+		i915_reg_t iir_reg;
+
+		if (INTEL_GEN(dev_priv) >= 12)
+			iir_reg = TRANS_PSR_IIR(dev_priv->psr.transcoder);
+		else
+			iir_reg = EDP_PSR_IIR;
+
+		psr_iir = I915_READ(iir_reg);
+		I915_WRITE(iir_reg, psr_iir);
+
+		if (psr_iir)
+			found = true;
 
 		intel_psr_irq_handler(dev_priv, psr_iir);
-		I915_WRITE(EDP_PSR_IIR, psr_iir);
-		found = true;
 	}
 
 	if (!found)
@@ -3233,8 +3243,23 @@ static void gen11_irq_reset(struct drm_i915_private *dev_priv)
 
 	intel_uncore_write(uncore, GEN11_DISPLAY_INT_CTL, 0);
 
-	intel_uncore_write(uncore, EDP_PSR_IMR, 0xffffffff);
-	intel_uncore_write(uncore, EDP_PSR_IIR, 0xffffffff);
+	if (INTEL_GEN(dev_priv) >= 12) {
+		enum transcoder trans;
+
+		for (trans = TRANSCODER_A; trans <= TRANSCODER_D; trans++) {
+			enum intel_display_power_domain domain;
+
+			domain = POWER_DOMAIN_TRANSCODER(trans);
+			if (!intel_display_power_is_enabled(dev_priv, domain))
+				continue;
+
+			intel_uncore_write(uncore, TRANS_PSR_IMR(trans), 0xffffffff);
+			intel_uncore_write(uncore, TRANS_PSR_IIR(trans), 0xffffffff);
+		}
+	} else {
+		intel_uncore_write(uncore, EDP_PSR_IMR, 0xffffffff);
+		intel_uncore_write(uncore, EDP_PSR_IIR, 0xffffffff);
+	}
 
 	for_each_pipe(dev_priv, pipe)
 		if (intel_display_power_is_enabled(dev_priv,
@@ -3740,7 +3765,21 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	else if (IS_BROADWELL(dev_priv))
 		de_port_enables |= GEN8_PORT_DP_A_HOTPLUG;
 
-	gen3_assert_iir_is_zero(uncore, EDP_PSR_IIR);
+	if (INTEL_GEN(dev_priv) >= 12) {
+		enum transcoder trans;
+
+		for (trans = TRANSCODER_A; trans <= TRANSCODER_D; trans++) {
+			enum intel_display_power_domain domain;
+
+			domain = POWER_DOMAIN_TRANSCODER(trans);
+			if (!intel_display_power_is_enabled(dev_priv, domain))
+				continue;
+
+			gen3_assert_iir_is_zero(uncore, TRANS_PSR_IIR(trans));
+		}
+	} else {
+		gen3_assert_iir_is_zero(uncore, EDP_PSR_IIR);
+	}
 
 	for_each_pipe(dev_priv, pipe) {
 		dev_priv->de_irq_mask[pipe] = ~de_pipe_masked;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 81f68455d492..de9e679e90bb 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4222,9 +4222,17 @@ enum {
 #define   EDP_PSR_TP1_TIME_0us			(3 << 4)
 #define   EDP_PSR_IDLE_FRAME_SHIFT		0
 
-/* Bspec claims those aren't shifted but stay at 0x64800 */
+/*
+ * Until TGL, IMR/IIR are fixed at 0x648xx. On TGL+ those registers are relative
+ * to transcoder and bits defined for each one as if using no shift (i.e. as if
+ * it was for TRANSCODER_EDP)
+ */
 #define EDP_PSR_IMR				_MMIO(0x64834)
 #define EDP_PSR_IIR				_MMIO(0x64838)
+#define _PSR_IMR_A				0x60814
+#define _PSR_IIR_A				0x60818
+#define TRANS_PSR_IMR(tran)			_MMIO_TRANS2(tran, _PSR_IMR_A)
+#define TRANS_PSR_IIR(tran)			_MMIO_TRANS2(tran, _PSR_IIR_A)
 #define   _EDP_PSR_TRANS_SHIFT(trans)		((trans) == TRANSCODER_EDP ? \
 						 0 : ((trans) - TRANSCODER_A + 1) * 8)
 #define   EDP_PSR_TRANS_MASK(trans)		(0x7 << _EDP_PSR_TRANS_SHIFT(trans))
-- 
cgit v1.2.3


From e468ff06157a3bb1b70ac8ea807429446b8bf4b2 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 4 Sep 2019 14:34:16 -0700
Subject: drm/i915: protect access to DP_TP_* on non-dp
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DP_TP_{CTL,STATUS} should only be programmed when the encoder is intel_dp.
Checking its current usages intel_disable_ddi_buf() is the only
offender, with other places being protected by checks like
pipe_config->fec_enable that is only set by intel_dp.

v3 (José):
- Using intel_crtc_has_dp_encoder() instead of intel_encoder_is_dp()
(Ville)

Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190904213419.27547-4-jose.souza@intel.com
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 1fe0bf01e580..ec132cd6add8 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3465,10 +3465,12 @@ static void intel_disable_ddi_buf(struct intel_encoder *encoder,
 		wait = true;
 	}
 
-	val = I915_READ(DP_TP_CTL(port));
-	val &= ~(DP_TP_CTL_ENABLE | DP_TP_CTL_LINK_TRAIN_MASK);
-	val |= DP_TP_CTL_LINK_TRAIN_PAT1;
-	I915_WRITE(DP_TP_CTL(port), val);
+	if (intel_crtc_has_dp_encoder(crtc_state)) {
+		val = I915_READ(DP_TP_CTL(port));
+		val &= ~(DP_TP_CTL_ENABLE | DP_TP_CTL_LINK_TRAIN_MASK);
+		val |= DP_TP_CTL_LINK_TRAIN_PAT1;
+		I915_WRITE(DP_TP_CTL(port), val);
+	}
 
 	/* Disable FEC in DP Sink */
 	intel_ddi_disable_fec_state(encoder, crtc_state);
-- 
cgit v1.2.3


From 4444df6e205bc1dc16ba112588815defe3c5a724 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 4 Sep 2019 14:34:17 -0700
Subject: drm/i915/tgl: move DP_TP_* to transcoder
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Gen 12 onwards moves the DP_TP_* registers to be transcoder-based rather
than port-based. This adds the new register addresses and changes all
the callers to use the register saved in intel_dp->regs.*. This is
filled out when preparing to enable the port so we take into account if
we should use the transcoder or the port.

v2: reimplement by stashing the registers we want to access under
intel_dp->reg. Now they are initialized when enabling the port.
Ville suggested to store the transcoder to be used exclusively
by TGL+. After implementing I thought just storing the register directly
made it cleaner.

Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190904213419.27547-5-jose.souza@intel.com
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c           | 43 ++++++++++++++--------
 drivers/gpu/drm/i915/display/intel_display_types.h |  9 +++++
 drivers/gpu/drm/i915/display/intel_dp.c            | 13 ++++---
 drivers/gpu/drm/i915/display/intel_dp_mst.c        |  8 ++--
 drivers/gpu/drm/i915/i915_reg.h                    |  4 ++
 5 files changed, 51 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index ec132cd6add8..3e6394139964 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3167,17 +3167,18 @@ static void intel_ddi_enable_fec(struct intel_encoder *encoder,
 				 const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum port port = encoder->port;
+	struct intel_dp *intel_dp;
 	u32 val;
 
 	if (!crtc_state->fec_enable)
 		return;
 
-	val = I915_READ(DP_TP_CTL(port));
+	intel_dp = enc_to_intel_dp(&encoder->base);
+	val = I915_READ(intel_dp->regs.dp_tp_ctl);
 	val |= DP_TP_CTL_FEC_ENABLE;
-	I915_WRITE(DP_TP_CTL(port), val);
+	I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
 
-	if (intel_de_wait_for_set(dev_priv, DP_TP_STATUS(port),
+	if (intel_de_wait_for_set(dev_priv, intel_dp->regs.dp_tp_status,
 				  DP_TP_STATUS_FEC_ENABLE_LIVE, 1))
 		DRM_ERROR("Timed out waiting for FEC Enable Status\n");
 }
@@ -3186,16 +3187,17 @@ static void intel_ddi_disable_fec_state(struct intel_encoder *encoder,
 					const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum port port = encoder->port;
+	struct intel_dp *intel_dp;
 	u32 val;
 
 	if (!crtc_state->fec_enable)
 		return;
 
-	val = I915_READ(DP_TP_CTL(port));
+	intel_dp = enc_to_intel_dp(&encoder->base);
+	val = I915_READ(intel_dp->regs.dp_tp_ctl);
 	val &= ~DP_TP_CTL_FEC_ENABLE;
-	I915_WRITE(DP_TP_CTL(port), val);
-	POSTING_READ(DP_TP_CTL(port));
+	I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
+	POSTING_READ(intel_dp->regs.dp_tp_ctl);
 }
 
 static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
@@ -3208,10 +3210,14 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
 	bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
 	int level = intel_ddi_dp_level(intel_dp);
+	enum transcoder transcoder = crtc_state->cpu_transcoder;
 
 	intel_dp_set_link_params(intel_dp, crtc_state->port_clock,
 				 crtc_state->lane_count, is_mst);
 
+	intel_dp->regs.dp_tp_ctl = TGL_DP_TP_CTL(transcoder);
+	intel_dp->regs.dp_tp_status = TGL_DP_TP_STATUS(transcoder);
+
 	/* 1.a got on intel_atomic_commit_tail() */
 
 	/* 2. */
@@ -3300,6 +3306,9 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	intel_dp_set_link_params(intel_dp, crtc_state->port_clock,
 				 crtc_state->lane_count, is_mst);
 
+	intel_dp->regs.dp_tp_ctl = DP_TP_CTL(port);
+	intel_dp->regs.dp_tp_status = DP_TP_STATUS(port);
+
 	intel_edp_panel_on(intel_dp);
 
 	intel_ddi_clk_select(encoder, crtc_state);
@@ -3466,10 +3475,12 @@ static void intel_disable_ddi_buf(struct intel_encoder *encoder,
 	}
 
 	if (intel_crtc_has_dp_encoder(crtc_state)) {
-		val = I915_READ(DP_TP_CTL(port));
+		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+
+		val = I915_READ(intel_dp->regs.dp_tp_ctl);
 		val &= ~(DP_TP_CTL_ENABLE | DP_TP_CTL_LINK_TRAIN_MASK);
 		val |= DP_TP_CTL_LINK_TRAIN_PAT1;
-		I915_WRITE(DP_TP_CTL(port), val);
+		I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
 	}
 
 	/* Disable FEC in DP Sink */
@@ -3898,7 +3909,7 @@ static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
 	u32 val;
 	bool wait = false;
 
-	if (I915_READ(DP_TP_CTL(port)) & DP_TP_CTL_ENABLE) {
+	if (I915_READ(intel_dp->regs.dp_tp_ctl) & DP_TP_CTL_ENABLE) {
 		val = I915_READ(DDI_BUF_CTL(port));
 		if (val & DDI_BUF_CTL_ENABLE) {
 			val &= ~DDI_BUF_CTL_ENABLE;
@@ -3906,11 +3917,11 @@ static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
 			wait = true;
 		}
 
-		val = I915_READ(DP_TP_CTL(port));
+		val = I915_READ(intel_dp->regs.dp_tp_ctl);
 		val &= ~(DP_TP_CTL_ENABLE | DP_TP_CTL_LINK_TRAIN_MASK);
 		val |= DP_TP_CTL_LINK_TRAIN_PAT1;
-		I915_WRITE(DP_TP_CTL(port), val);
-		POSTING_READ(DP_TP_CTL(port));
+		I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
+		POSTING_READ(intel_dp->regs.dp_tp_ctl);
 
 		if (wait)
 			intel_wait_ddi_buf_idle(dev_priv, port);
@@ -3925,8 +3936,8 @@ static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp)
 		if (drm_dp_enhanced_frame_cap(intel_dp->dpcd))
 			val |= DP_TP_CTL_ENHANCED_FRAME_ENABLE;
 	}
-	I915_WRITE(DP_TP_CTL(port), val);
-	POSTING_READ(DP_TP_CTL(port));
+	I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
+	POSTING_READ(intel_dp->regs.dp_tp_ctl);
 
 	intel_dp->DP |= DDI_BUF_CTL_ENABLE;
 	I915_WRITE(DDI_BUF_CTL(port), intel_dp->DP);
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 61277a87dbe7..d5cc4b810d9e 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1218,6 +1218,15 @@ struct intel_dp {
 	bool can_mst; /* this port supports mst */
 	bool is_mst;
 	int active_mst_links;
+
+	/*
+	 * DP_TP_* registers may be either on port or transcoder register space.
+	 */
+	struct {
+		i915_reg_t dp_tp_ctl;
+		i915_reg_t dp_tp_status;
+	} regs;
+
 	/* connector directly attached - won't be use for modeset in mst world */
 	struct intel_connector *attached_connector;
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 4e3e696e7fc8..f06fbca5cb3e 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2297,6 +2297,9 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 				 intel_crtc_has_type(pipe_config,
 						     INTEL_OUTPUT_DP_MST));
 
+	intel_dp->regs.dp_tp_ctl = DP_TP_CTL(port);
+	intel_dp->regs.dp_tp_status = DP_TP_STATUS(port);
+
 	/*
 	 * There are four kinds of DP registers:
 	 *
@@ -3253,7 +3256,7 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 			      dp_train_pat & train_pat_mask);
 
 	if (HAS_DDI(dev_priv)) {
-		u32 temp = I915_READ(DP_TP_CTL(port));
+		u32 temp = I915_READ(intel_dp->regs.dp_tp_ctl);
 
 		if (dp_train_pat & DP_LINK_SCRAMBLING_DISABLE)
 			temp |= DP_TP_CTL_SCRAMBLE_DISABLE;
@@ -3279,7 +3282,7 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 			temp |= DP_TP_CTL_LINK_TRAIN_PAT4;
 			break;
 		}
-		I915_WRITE(DP_TP_CTL(port), temp);
+		I915_WRITE(intel_dp->regs.dp_tp_ctl, temp);
 
 	} else if ((IS_IVYBRIDGE(dev_priv) && port == PORT_A) ||
 		   (HAS_PCH_CPT(dev_priv) && port != PORT_A)) {
@@ -3980,10 +3983,10 @@ void intel_dp_set_idle_link_train(struct intel_dp *intel_dp)
 	if (!HAS_DDI(dev_priv))
 		return;
 
-	val = I915_READ(DP_TP_CTL(port));
+	val = I915_READ(intel_dp->regs.dp_tp_ctl);
 	val &= ~DP_TP_CTL_LINK_TRAIN_MASK;
 	val |= DP_TP_CTL_LINK_TRAIN_IDLE;
-	I915_WRITE(DP_TP_CTL(port), val);
+	I915_WRITE(intel_dp->regs.dp_tp_ctl, val);
 
 	/*
 	 * Until TGL on PORT_A we can have only eDP in SST mode. There the only
@@ -3995,7 +3998,7 @@ void intel_dp_set_idle_link_train(struct intel_dp *intel_dp)
 	if (port == PORT_A && INTEL_GEN(dev_priv) < 12)
 		return;
 
-	if (intel_de_wait_for_set(dev_priv, DP_TP_STATUS(port),
+	if (intel_de_wait_for_set(dev_priv, intel_dp->regs.dp_tp_status,
 				  DP_TP_STATUS_IDLE_DONE, 1))
 		DRM_ERROR("Timed out waiting for DP idle patterns\n");
 }
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 37366f81255b..3f9cdbaab95e 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -295,7 +295,6 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum port port = intel_dig_port->base.port;
 	struct intel_connector *connector =
 		to_intel_connector(conn_state->connector);
 	int ret;
@@ -326,8 +325,8 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 		DRM_ERROR("failed to allocate vcpi\n");
 
 	intel_dp->active_mst_links++;
-	temp = I915_READ(DP_TP_STATUS(port));
-	I915_WRITE(DP_TP_STATUS(port), temp);
+	temp = I915_READ(intel_dp->regs.dp_tp_status);
+	I915_WRITE(intel_dp->regs.dp_tp_status, temp);
 
 	ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr);
 
@@ -342,11 +341,10 @@ static void intel_mst_enable_dp(struct intel_encoder *encoder,
 	struct intel_digital_port *intel_dig_port = intel_mst->primary;
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum port port = intel_dig_port->base.port;
 
 	DRM_DEBUG_KMS("active links %d\n", intel_dp->active_mst_links);
 
-	if (intel_de_wait_for_set(dev_priv, DP_TP_STATUS(port),
+	if (intel_de_wait_for_set(dev_priv, intel_dp->regs.dp_tp_status,
 				  DP_TP_STATUS_ACT_SENT, 1))
 		DRM_ERROR("Timed out waiting for ACT sent\n");
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index de9e679e90bb..006cffd56be2 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -9546,7 +9546,9 @@ enum skl_power_gate {
 /* DisplayPort Transport Control */
 #define _DP_TP_CTL_A			0x64040
 #define _DP_TP_CTL_B			0x64140
+#define _TGL_DP_TP_CTL_A		0x60540
 #define DP_TP_CTL(port) _MMIO_PORT(port, _DP_TP_CTL_A, _DP_TP_CTL_B)
+#define TGL_DP_TP_CTL(tran) _MMIO_TRANS2((tran), _TGL_DP_TP_CTL_A)
 #define  DP_TP_CTL_ENABLE			(1 << 31)
 #define  DP_TP_CTL_FEC_ENABLE			(1 << 30)
 #define  DP_TP_CTL_MODE_SST			(0 << 27)
@@ -9566,7 +9568,9 @@ enum skl_power_gate {
 /* DisplayPort Transport Status */
 #define _DP_TP_STATUS_A			0x64044
 #define _DP_TP_STATUS_B			0x64144
+#define _TGL_DP_TP_STATUS_A		0x60544
 #define DP_TP_STATUS(port) _MMIO_PORT(port, _DP_TP_STATUS_A, _DP_TP_STATUS_B)
+#define TGL_DP_TP_STATUS(tran) _MMIO_TRANS2((tran), _TGL_DP_TP_STATUS_A)
 #define  DP_TP_STATUS_FEC_ENABLE_LIVE		(1 << 28)
 #define  DP_TP_STATUS_IDLE_DONE			(1 << 25)
 #define  DP_TP_STATUS_ACT_SENT			(1 << 24)
-- 
cgit v1.2.3


From 8ffa4392a32e27b3945b8c0585550d3dd831c68b Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 4 Sep 2019 14:34:18 -0700
Subject: drm/i915/tgl: disable SAGV temporarily
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

SAGV is not currently working for Tiger Lake. We better disable it until
the implementation is stabilized and we can enable it.

HSDES: 1409542895 2208191909

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190904213419.27547-6-jose.souza@intel.com
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/intel_pm.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 4fa9bc83c8b4..7294fcf05323 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3654,6 +3654,10 @@ static bool skl_needs_memory_bw_wa(struct drm_i915_private *dev_priv)
 static bool
 intel_has_sagv(struct drm_i915_private *dev_priv)
 {
+	/* HACK! */
+	if (IS_GEN(dev_priv, 12))
+		return false;
+
 	return (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) &&
 		dev_priv->sagv_status != I915_SAGV_NOT_CONTROLLED;
 }
-- 
cgit v1.2.3


From 5b548ae63d584c76d41926e9efd63b0d2d56127f Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 4 Sep 2019 14:34:19 -0700
Subject: drm/i915/tgl: add gen12 to stolen initialization
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add case for gen == 12 and add MISSING_CASE() for future gens. We were
already handling gen12 as the default, so this doesn't change the
current behavior.

BSpec: 19481 and 44980

Cc: CQ Tang <cq.tang@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190904213419.27547-7-jose.souza@intel.com
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_stolen.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index aa533b4ab5f5..7ce5259d73d6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -425,8 +425,11 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 			bdw_get_stolen_reserved(dev_priv,
 						&reserved_base, &reserved_size);
 		break;
-	case 11:
 	default:
+		MISSING_CASE(INTEL_GEN(dev_priv));
+		/* fall-through */
+	case 11:
+	case 12:
 		icl_get_stolen_reserved(dev_priv, &reserved_base,
 					&reserved_size);
 		break;
-- 
cgit v1.2.3


From d10e0cb7591ef88fa8edfb164327a30d323b9d3d Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Wed, 4 Sep 2019 16:02:40 -0700
Subject: drm/i915: Apply FBC WA for TGL too
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

WA 1409120013 is also valid for TGL, so lets check for ">= 11".

BSpec: 52890

Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Clinton Taylor <Clinton.A.Taylor@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190904230241.20638-1-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_fbc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 16ed44bfd734..dc34b23e2320 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -343,8 +343,8 @@ static void gen7_fbc_activate(struct drm_i915_private *dev_priv)
 			   HSW_FBCQ_DIS);
 	}
 
-	if (IS_GEN(dev_priv, 11))
-		/* Wa_1409120013:icl,ehl */
+	if (INTEL_GEN(dev_priv) >= 11)
+		/* Wa_1409120013:icl,ehl,tgl */
 		I915_WRITE(ILK_DPFC_CHICKEN, ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL);
 
 	I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
-- 
cgit v1.2.3


From aaef851083ed577a4a6094dec3caf7f00f1fd0db Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Wed, 4 Sep 2019 16:02:41 -0700
Subject: drm/i915/mst: Do not hardcoded the crtcs that encoder can connect
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Tiger Lake has up to 4 pipes so the mask would need to be 0xf instead of
0x7. Do not hardcode the mask so it allows the fake MST encoders to
connect to all pipes no matter how many the platform has.

Iterating over all pipes to keep consistent with intel_ddi_init().

Initialy this patch was replaced by commit 4eaceea3a00f ("drm/i915:
Fix DP-MST crtc_mask") but userspace it not correctly using
encoder.possible_crtcs and it was reverted by
commit e838bfa8e170 ("Revert "drm/i915: Fix DP-MST crtc_mask"")

Userspace should be fixed but it might take a while, so bringing this
patch back for now.

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190904230241.20638-2-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp_mst.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 3f9cdbaab95e..eeeb3f933aa4 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -597,6 +597,8 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
 	struct intel_dp_mst_encoder *intel_mst;
 	struct intel_encoder *intel_encoder;
 	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	enum pipe pipe_iter;
 
 	intel_mst = kzalloc(sizeof(*intel_mst), GFP_KERNEL);
 
@@ -613,8 +615,9 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
 	intel_encoder->type = INTEL_OUTPUT_DP_MST;
 	intel_encoder->power_domain = intel_dig_port->base.power_domain;
 	intel_encoder->port = intel_dig_port->base.port;
-	intel_encoder->crtc_mask = 0x7;
 	intel_encoder->cloneable = 0;
+	for_each_pipe(dev_priv, pipe_iter)
+		intel_encoder->crtc_mask |= BIT(pipe_iter);
 
 	intel_encoder->compute_config = intel_dp_mst_compute_config;
 	intel_encoder->disable = intel_mst_disable_dp;
-- 
cgit v1.2.3


From a8c15954d64ac7177559c9f5eeb6593e5883fd69 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 3 Sep 2019 07:21:33 +0100
Subject: drm/i915: Protect debugfs per_file_stats with RCU lock

If we make sure we grab a strong reference to each object as we dump it,
we can reduce the locks outside of our iterators to an rcu_read_lock.

This should prevent errors like:
[ 2138.371911] BUG: KASAN: use-after-free in per_file_stats+0x43/0x380 [i915]
[ 2138.371924] Read of size 8 at addr ffff888223651000 by task cat/8293

[ 2138.371947] CPU: 0 PID: 8293 Comm: cat Not tainted 5.3.0-rc6-CI-Custom_4352+ #1
[ 2138.371953] Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./J4205-ITX, BIOS P1.40 07/14/2017
[ 2138.371959] Call Trace:
[ 2138.371974]  dump_stack+0x7c/0xbb
[ 2138.372099]  ? per_file_stats+0x43/0x380 [i915]
[ 2138.372108]  print_address_description+0x73/0x3a0
[ 2138.372231]  ? per_file_stats+0x43/0x380 [i915]
[ 2138.372352]  ? per_file_stats+0x43/0x380 [i915]
[ 2138.372362]  __kasan_report+0x14e/0x192
[ 2138.372489]  ? per_file_stats+0x43/0x380 [i915]
[ 2138.372502]  kasan_report+0xe/0x20
[ 2138.372625]  per_file_stats+0x43/0x380 [i915]
[ 2138.372751]  ? i915_panel_show+0x110/0x110 [i915]
[ 2138.372761]  idr_for_each+0xa7/0x160
[ 2138.372773]  ? idr_get_next_ul+0x110/0x110
[ 2138.372782]  ? do_raw_spin_lock+0x10a/0x1d0
[ 2138.372923]  print_context_stats+0x264/0x510 [i915]

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: David Weinehall <david.weinehall@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190903062133.27360-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_debugfs.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 9798f27a697a..708855e051b5 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -237,6 +237,9 @@ static int per_file_stats(int id, void *ptr, void *data)
 	struct file_stats *stats = data;
 	struct i915_vma *vma;
 
+	if (!kref_get_unless_zero(&obj->base.refcount))
+		return 0;
+
 	stats->count++;
 	stats->total += obj->base.size;
 	if (!atomic_read(&obj->bind_count))
@@ -284,6 +287,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 	}
 	spin_unlock(&obj->vma.lock);
 
+	i915_gem_object_put(obj);
 	return 0;
 }
 
@@ -313,10 +317,12 @@ static void print_context_stats(struct seq_file *m,
 				    i915_gem_context_lock_engines(ctx), it) {
 			intel_context_lock_pinned(ce);
 			if (intel_context_is_pinned(ce)) {
+				rcu_read_lock();
 				if (ce->state)
 					per_file_stats(0,
 						       ce->state->obj, &kstats);
 				per_file_stats(0, ce->ring->vma->obj, &kstats);
+				rcu_read_unlock();
 			}
 			intel_context_unlock_pinned(ce);
 		}
@@ -328,9 +334,9 @@ static void print_context_stats(struct seq_file *m,
 			struct task_struct *task;
 			char name[80];
 
-			spin_lock(&file->table_lock);
+			rcu_read_lock();
 			idr_for_each(&file->object_idr, per_file_stats, &stats);
-			spin_unlock(&file->table_lock);
+			rcu_read_unlock();
 
 			rcu_read_lock();
 			task = pid_task(ctx->pid ?: file->pid, PIDTYPE_PID);
-- 
cgit v1.2.3


From ca9cab183449787058f700fd0a74a8c91b277268 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Sat, 13 Apr 2019 11:13:27 +0000
Subject: drm/i915: add immutable zpos plane properties
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds basic immutable support for the zpos property. The zpos increases
from bottom to top: primary, sprites, cursor.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
[contact@emersion.fr: adapted for latest drm-tip]
Signed-off-by: Simon Ser <contact@emersion.fr>
Link: https://patchwork.freedesktop.org/patch/msgid/YSH9PasoADJJdNJCSdI4m55ankIBsCaoSgkw-NQ5dlruCAxc8J-SQwVl5n3ddSAMDLTdbdyQvkONmtbjkUU-TQk5VIu1p-aZRO1OjjuSxjY=@emersion.fr
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 10 ++++++++--
 drivers/gpu/drm/i915/display/intel_sprite.c  |  7 ++++++-
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 06cf2171474d..3b5275ab66cf 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -14887,7 +14887,7 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 	const u64 *modifiers;
 	const u32 *formats;
 	int num_formats;
-	int ret;
+	int ret, zpos;
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		return skl_universal_plane_create(dev_priv, pipe,
@@ -14976,6 +14976,9 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 						   DRM_MODE_ROTATE_0,
 						   supported_rotations);
 
+	zpos = 0;
+	drm_plane_create_zpos_immutable_property(&plane->base, zpos);
+
 	drm_plane_helper_add(&plane->base, &intel_plane_helper_funcs);
 
 	return plane;
@@ -14992,7 +14995,7 @@ intel_cursor_plane_create(struct drm_i915_private *dev_priv,
 {
 	unsigned int possible_crtcs;
 	struct intel_plane *cursor;
-	int ret;
+	int ret, zpos;
 
 	cursor = intel_plane_alloc();
 	if (IS_ERR(cursor))
@@ -15041,6 +15044,9 @@ intel_cursor_plane_create(struct drm_i915_private *dev_priv,
 						   DRM_MODE_ROTATE_0 |
 						   DRM_MODE_ROTATE_180);
 
+	zpos = RUNTIME_INFO(dev_priv)->num_sprites[pipe] + 1;
+	drm_plane_create_zpos_immutable_property(&cursor->base, zpos);
+
 	drm_plane_helper_add(&cursor->base, &intel_plane_helper_funcs);
 
 	return cursor;
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index 8ca2fbc2af1d..e415b0ad4a42 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -2592,6 +2592,8 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv,
 					     BIT(DRM_MODE_BLEND_PREMULTI) |
 					     BIT(DRM_MODE_BLEND_COVERAGE));
 
+	drm_plane_create_zpos_immutable_property(&plane->base, plane_id);
+
 	drm_plane_helper_add(&plane->base, &intel_plane_helper_funcs);
 
 	return plane;
@@ -2613,7 +2615,7 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 	const u64 *modifiers;
 	const u32 *formats;
 	int num_formats;
-	int ret;
+	int ret, zpos;
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		return skl_universal_plane_create(dev_priv, pipe,
@@ -2703,6 +2705,9 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 					  DRM_COLOR_YCBCR_BT709,
 					  DRM_COLOR_YCBCR_LIMITED_RANGE);
 
+	zpos = sprite + 1;
+	drm_plane_create_zpos_immutable_property(&plane->base, zpos);
+
 	drm_plane_helper_add(&plane->base, &intel_plane_helper_funcs);
 
 	return plane;
-- 
cgit v1.2.3


From 71cd86cfaa12645ca39e5bbeceb2039af74fba2e Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Thu, 5 Sep 2019 11:13:37 -0700
Subject: drm/i915/tgl: Use refclk/2 as bypass frequency
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unlike gen11, which always ran at 50MHz when the cdclk PLL was disabled,
TGL runs at refclk/2.  The 50MHz croclk/2 is only used by hardware
during some power state transitions.

Bspec: 49201
Cc: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190905181337.23727-1-matthew.d.roper@intel.com
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 76f11d465e91..d3e56628af70 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1855,8 +1855,6 @@ static void icl_get_cdclk(struct drm_i915_private *dev_priv,
 	u32 val;
 	int div;
 
-	cdclk_state->bypass = 50000;
-
 	val = I915_READ(SKL_DSSM);
 	switch (val & ICL_DSSM_CDCLK_PLL_REFCLK_MASK) {
 	default:
@@ -1873,6 +1871,11 @@ static void icl_get_cdclk(struct drm_i915_private *dev_priv,
 		break;
 	}
 
+	if (INTEL_GEN(dev_priv) >= 12)
+		cdclk_state->bypass = cdclk_state->ref / 2;
+	else
+		cdclk_state->bypass = 50000;
+
 	val = I915_READ(BXT_DE_PLL_ENABLE);
 	if ((val & BXT_DE_PLL_PLL_ENABLE) == 0 ||
 	    (val & BXT_DE_PLL_LOCK) == 0) {
-- 
cgit v1.2.3


From cdb736fa8b8b65740030ba8f9dc87f0fc3313858 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Fri, 6 Sep 2019 16:49:57 +0300
Subject: drm/i915: Use engine relative LRIs on context setup

Daniele pointed out that relative mmio works differently in
on context restore. Instead of adding the engine mmio base to offset,
it masks out the base and adds bits [12:2] to current engine base.

This should allow us to construct context register state to be
applicable to all instances, including virtual. And avoid the trouble
of updating the registers on virtual instances when submitting work.

v2: only enable for gen12 for now (Mika)
v3: make enabling readable (Chris)

Bspec: 20206
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190906134957.25909-1-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_engine_types.h |  7 ++++++
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h |  2 ++
 drivers/gpu/drm/i915/gt/intel_lrc.c          | 32 ++++++++++++++++++++--------
 3 files changed, 32 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 15e02cb58a67..943f0663837e 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -481,6 +481,7 @@ struct intel_engine_cs {
 #define I915_ENGINE_HAS_SEMAPHORES   BIT(3)
 #define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4)
 #define I915_ENGINE_IS_VIRTUAL       BIT(5)
+#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6)
 	unsigned int flags;
 
 	/*
@@ -576,6 +577,12 @@ intel_engine_is_virtual(const struct intel_engine_cs *engine)
 	return engine->flags & I915_ENGINE_IS_VIRTUAL;
 }
 
+static inline bool
+intel_engine_has_relative_mmio(const struct intel_engine_cs * const engine)
+{
+	return engine->flags & I915_ENGINE_HAS_RELATIVE_MMIO;
+}
+
 #define instdone_has_slice(dev_priv___, sseu___, slice___) \
 	((IS_GEN(dev_priv___, 7) ? 1 : ((sseu___)->slice_mask)) & BIT(slice___))
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 86e00a2db8a4..fbad403ab7ac 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -132,6 +132,8 @@
  *   address/value pairs. Don't overdue it, though, x <= 2^4 must hold!
  */
 #define MI_LOAD_REGISTER_IMM(x)	MI_INSTR(0x22, 2*(x)-1)
+/* Gen11+. addr = base + (ctx_restore ? offset & GENMASK(12,2) : offset) */
+#define   MI_LRI_CS_MMIO		(1<<19)
 #define   MI_LRI_FORCE_POSTED		(1<<12)
 #define MI_STORE_REGISTER_MEM        MI_INSTR(0x24, 1)
 #define MI_STORE_REGISTER_MEM_GEN8   MI_INSTR(0x24, 2)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 87b7473a6dfb..de86ca6add09 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1214,7 +1214,10 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				unsigned int n;
 
 				GEM_BUG_ON(READ_ONCE(ve->context.inflight));
-				virtual_update_register_offsets(regs, engine);
+
+				if (!intel_engine_has_relative_mmio(engine))
+					virtual_update_register_offsets(regs,
+									engine);
 
 				if (!list_empty(&ve->context.signals))
 					virtual_xfer_breadcrumbs(ve, engine);
@@ -2939,6 +2942,9 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 		if (HAS_LOGICAL_RING_PREEMPTION(engine->i915))
 			engine->flags |= I915_ENGINE_HAS_PREEMPTION;
 	}
+
+	if (engine->class != COPY_ENGINE_CLASS && INTEL_GEN(engine->i915) >= 12)
+		engine->flags |= I915_ENGINE_HAS_RELATIVE_MMIO;
 }
 
 static void execlists_destroy(struct intel_engine_cs *engine)
@@ -3130,8 +3136,10 @@ static void execlists_init_reg_state(u32 *regs,
 				     struct intel_ring *ring)
 {
 	struct i915_ppgtt *ppgtt = vm_alias(ce->vm);
-	bool rcs = engine->class == RENDER_CLASS;
-	u32 base = engine->mmio_base;
+	const bool rcs = engine->class == RENDER_CLASS;
+	const u32 base = engine->mmio_base;
+	const u32 lri_base =
+		intel_engine_has_relative_mmio(engine) ? MI_LRI_CS_MMIO : 0;
 
 	/*
 	 * A context is actually a big batch buffer with several
@@ -3143,8 +3151,10 @@ static void execlists_init_reg_state(u32 *regs,
 	 *
 	 * Must keep consistent with virtual_update_register_offsets().
 	 */
-	regs[CTX_LRI_HEADER_0] = MI_LOAD_REGISTER_IMM(rcs ? 14 : 11) |
-				 MI_LRI_FORCE_POSTED;
+	regs[CTX_LRI_HEADER_0] =
+		MI_LOAD_REGISTER_IMM(rcs ? 14 : 11) |
+		MI_LRI_FORCE_POSTED |
+		lri_base;
 
 	CTX_REG(regs, CTX_CONTEXT_CONTROL, RING_CONTEXT_CONTROL(base),
 		_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) |
@@ -3191,7 +3201,10 @@ static void execlists_init_reg_state(u32 *regs,
 		}
 	}
 
-	regs[CTX_LRI_HEADER_1] = MI_LOAD_REGISTER_IMM(9) | MI_LRI_FORCE_POSTED;
+	regs[CTX_LRI_HEADER_1] =
+		MI_LOAD_REGISTER_IMM(9) |
+		MI_LRI_FORCE_POSTED |
+		lri_base;
 
 	CTX_REG(regs, CTX_CTX_TIMESTAMP, RING_CTX_TIMESTAMP(base), 0);
 	/* PDP values well be assigned later if needed */
@@ -3218,7 +3231,7 @@ static void execlists_init_reg_state(u32 *regs,
 	}
 
 	if (rcs) {
-		regs[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1);
+		regs[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1) | lri_base;
 		CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, 0);
 	}
 
@@ -3411,8 +3424,9 @@ static void virtual_engine_initial_hint(struct virtual_engine *ve)
 		return;
 
 	swap(ve->siblings[swp], ve->siblings[0]);
-	virtual_update_register_offsets(ve->context.lrc_reg_state,
-					ve->siblings[0]);
+	if (!intel_engine_has_relative_mmio(ve->siblings[0]))
+		virtual_update_register_offsets(ve->context.lrc_reg_state,
+						ve->siblings[0]);
 }
 
 static int virtual_context_pin(struct intel_context *ce)
-- 
cgit v1.2.3


From 5bf05dc58d65b215437df3013163a7eea78d5d4c Mon Sep 17 00:00:00 2001
From: Michel Thierry <michel.thierry@intel.com>
Date: Fri, 6 Sep 2019 15:23:14 +0300
Subject: drm/i915/tgl: Register state context definition for Gen12
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Gen12 has subtle changes in the reg state context offsets (some fields
are gone, some are in a different location), compared to previous Gens.

The simplest approach seems to be keeping Gen12 (and future platform)
changes apart from the previous gens, while keeping the registers that
are contiguous in functions we can reuse.

v2: alias, virtual engine, rpcs, prune unused regs
v3: use engine base (Daniele), take ctx_bb for all

Bspec: 46255
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Tested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
[ickle: Tweaked the GEM_WARN_ON after settling on a compromise with
Daniele]
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190906122314.2146-2-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_lrc.c     | 200 +++++++++++++++++++++++---------
 drivers/gpu/drm/i915/gt/intel_lrc_reg.h |   6 +-
 2 files changed, 147 insertions(+), 59 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index de86ca6add09..0ddfbebbcbbc 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -808,8 +808,12 @@ static void virtual_update_register_offsets(u32 *regs,
 {
 	u32 base = engine->mmio_base;
 
+	/* Refactor so that we only have one place that knows all the offsets! */
+	GEM_WARN_ON(INTEL_GEN(engine->i915) >= 12);
+
 	/* Must match execlists_init_reg_state()! */
 
+	/* Common part */
 	regs[CTX_CONTEXT_CONTROL] =
 		i915_mmio_reg_offset(RING_CONTEXT_CONTROL(base));
 	regs[CTX_RING_HEAD] = i915_mmio_reg_offset(RING_HEAD(base));
@@ -820,13 +824,16 @@ static void virtual_update_register_offsets(u32 *regs,
 	regs[CTX_BB_HEAD_U] = i915_mmio_reg_offset(RING_BBADDR_UDW(base));
 	regs[CTX_BB_HEAD_L] = i915_mmio_reg_offset(RING_BBADDR(base));
 	regs[CTX_BB_STATE] = i915_mmio_reg_offset(RING_BBSTATE(base));
+
 	regs[CTX_SECOND_BB_HEAD_U] =
 		i915_mmio_reg_offset(RING_SBBADDR_UDW(base));
 	regs[CTX_SECOND_BB_HEAD_L] = i915_mmio_reg_offset(RING_SBBADDR(base));
 	regs[CTX_SECOND_BB_STATE] = i915_mmio_reg_offset(RING_SBBSTATE(base));
 
+	/* PPGTT part */
 	regs[CTX_CTX_TIMESTAMP] =
 		i915_mmio_reg_offset(RING_CTX_TIMESTAMP(base));
+
 	regs[CTX_PDP3_UDW] = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 3));
 	regs[CTX_PDP3_LDW] = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, 3));
 	regs[CTX_PDP2_UDW] = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 2));
@@ -3122,39 +3129,13 @@ static u32 intel_lr_indirect_ctx_offset(struct intel_engine_cs *engine)
 	return indirect_ctx_offset;
 }
 
-static struct i915_ppgtt *vm_alias(struct i915_address_space *vm)
-{
-	if (i915_is_ggtt(vm))
-		return i915_vm_to_ggtt(vm)->alias;
-	else
-		return i915_vm_to_ppgtt(vm);
-}
 
-static void execlists_init_reg_state(u32 *regs,
-				     struct intel_context *ce,
-				     struct intel_engine_cs *engine,
-				     struct intel_ring *ring)
+static void init_common_reg_state(u32 * const regs,
+				  struct i915_ppgtt * const ppgtt,
+				  struct intel_engine_cs *engine,
+				  struct intel_ring *ring)
 {
-	struct i915_ppgtt *ppgtt = vm_alias(ce->vm);
-	const bool rcs = engine->class == RENDER_CLASS;
 	const u32 base = engine->mmio_base;
-	const u32 lri_base =
-		intel_engine_has_relative_mmio(engine) ? MI_LRI_CS_MMIO : 0;
-
-	/*
-	 * A context is actually a big batch buffer with several
-	 * MI_LOAD_REGISTER_IMM commands followed by (reg, value) pairs. The
-	 * values we are setting here are only for the first context restore:
-	 * on a subsequent save, the GPU will recreate this batchbuffer with new
-	 * values (including all the missing MI_LOAD_REGISTER_IMM commands that
-	 * we are not initializing here).
-	 *
-	 * Must keep consistent with virtual_update_register_offsets().
-	 */
-	regs[CTX_LRI_HEADER_0] =
-		MI_LOAD_REGISTER_IMM(rcs ? 14 : 11) |
-		MI_LRI_FORCE_POSTED |
-		lri_base;
 
 	CTX_REG(regs, CTX_CONTEXT_CONTROL, RING_CONTEXT_CONTROL(base),
 		_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) |
@@ -3172,41 +3153,43 @@ static void execlists_init_reg_state(u32 *regs,
 	CTX_REG(regs, CTX_BB_HEAD_U, RING_BBADDR_UDW(base), 0);
 	CTX_REG(regs, CTX_BB_HEAD_L, RING_BBADDR(base), 0);
 	CTX_REG(regs, CTX_BB_STATE, RING_BBSTATE(base), RING_BB_PPGTT);
-	CTX_REG(regs, CTX_SECOND_BB_HEAD_U, RING_SBBADDR_UDW(base), 0);
-	CTX_REG(regs, CTX_SECOND_BB_HEAD_L, RING_SBBADDR(base), 0);
-	CTX_REG(regs, CTX_SECOND_BB_STATE, RING_SBBSTATE(base), 0);
-	if (rcs) {
-		struct i915_ctx_workarounds *wa_ctx = &engine->wa_ctx;
-
-		CTX_REG(regs, CTX_RCS_INDIRECT_CTX, RING_INDIRECT_CTX(base), 0);
-		CTX_REG(regs, CTX_RCS_INDIRECT_CTX_OFFSET,
-			RING_INDIRECT_CTX_OFFSET(base), 0);
-		if (wa_ctx->indirect_ctx.size) {
-			u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
+}
 
-			regs[CTX_RCS_INDIRECT_CTX + 1] =
-				(ggtt_offset + wa_ctx->indirect_ctx.offset) |
-				(wa_ctx->indirect_ctx.size / CACHELINE_BYTES);
+static void init_wa_bb_reg_state(u32 * const regs,
+				 struct intel_engine_cs *engine,
+				 u32 pos_bb_per_ctx)
+{
+	struct i915_ctx_workarounds * const wa_ctx = &engine->wa_ctx;
+	const u32 base = engine->mmio_base;
+	const u32 pos_indirect_ctx = pos_bb_per_ctx + 2;
+	const u32 pos_indirect_ctx_offset = pos_indirect_ctx + 2;
 
-			regs[CTX_RCS_INDIRECT_CTX_OFFSET + 1] =
-				intel_lr_indirect_ctx_offset(engine) << 6;
-		}
+	CTX_REG(regs, pos_indirect_ctx, RING_INDIRECT_CTX(base), 0);
+	CTX_REG(regs, pos_indirect_ctx_offset,
+		RING_INDIRECT_CTX_OFFSET(base), 0);
+	if (wa_ctx->indirect_ctx.size) {
+		const u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
 
-		CTX_REG(regs, CTX_BB_PER_CTX_PTR, RING_BB_PER_CTX_PTR(base), 0);
-		if (wa_ctx->per_ctx.size) {
-			u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
+		regs[pos_indirect_ctx + 1] =
+			(ggtt_offset + wa_ctx->indirect_ctx.offset) |
+			(wa_ctx->indirect_ctx.size / CACHELINE_BYTES);
 
-			regs[CTX_BB_PER_CTX_PTR + 1] =
-				(ggtt_offset + wa_ctx->per_ctx.offset) | 0x01;
-		}
+		regs[pos_indirect_ctx_offset + 1] =
+			intel_lr_indirect_ctx_offset(engine) << 6;
 	}
 
-	regs[CTX_LRI_HEADER_1] =
-		MI_LOAD_REGISTER_IMM(9) |
-		MI_LRI_FORCE_POSTED |
-		lri_base;
+	CTX_REG(regs, pos_bb_per_ctx, RING_BB_PER_CTX_PTR(base), 0);
+	if (wa_ctx->per_ctx.size) {
+		const u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
 
-	CTX_REG(regs, CTX_CTX_TIMESTAMP, RING_CTX_TIMESTAMP(base), 0);
+		regs[pos_bb_per_ctx + 1] =
+			(ggtt_offset + wa_ctx->per_ctx.offset) | 0x01;
+	}
+}
+
+static void init_ppgtt_reg_state(u32 *regs, u32 base,
+				 struct i915_ppgtt *ppgtt)
+{
 	/* PDP values well be assigned later if needed */
 	CTX_REG(regs, CTX_PDP3_UDW, GEN8_RING_PDP_UDW(base, 3), 0);
 	CTX_REG(regs, CTX_PDP3_LDW, GEN8_RING_PDP_LDW(base, 3), 0);
@@ -3229,6 +3212,47 @@ static void execlists_init_reg_state(u32 *regs,
 		ASSIGN_CTX_PDP(ppgtt, regs, 1);
 		ASSIGN_CTX_PDP(ppgtt, regs, 0);
 	}
+}
+
+static struct i915_ppgtt *vm_alias(struct i915_address_space *vm)
+{
+	if (i915_is_ggtt(vm))
+		return i915_vm_to_ggtt(vm)->alias;
+	else
+		return i915_vm_to_ppgtt(vm);
+}
+
+static void gen8_init_reg_state(u32 * const regs,
+				struct intel_context *ce,
+				struct intel_engine_cs *engine,
+				struct intel_ring *ring)
+{
+	struct i915_ppgtt * const ppgtt = vm_alias(ce->vm);
+	const bool rcs = engine->class == RENDER_CLASS;
+	const u32 base = engine->mmio_base;
+	const u32 lri_base =
+		intel_engine_has_relative_mmio(engine) ? MI_LRI_CS_MMIO : 0;
+
+	regs[CTX_LRI_HEADER_0] =
+		MI_LOAD_REGISTER_IMM(rcs ? 14 : 11) |
+		MI_LRI_FORCE_POSTED |
+		lri_base;
+
+	init_common_reg_state(regs, ppgtt, engine, ring);
+	CTX_REG(regs, CTX_SECOND_BB_HEAD_U, RING_SBBADDR_UDW(base), 0);
+	CTX_REG(regs, CTX_SECOND_BB_HEAD_L, RING_SBBADDR(base), 0);
+	CTX_REG(regs, CTX_SECOND_BB_STATE, RING_SBBSTATE(base), 0);
+	if (rcs)
+		init_wa_bb_reg_state(regs, engine, CTX_BB_PER_CTX_PTR);
+
+	regs[CTX_LRI_HEADER_1] =
+		MI_LOAD_REGISTER_IMM(9) |
+		MI_LRI_FORCE_POSTED |
+		lri_base;
+
+	CTX_REG(regs, CTX_CTX_TIMESTAMP, RING_CTX_TIMESTAMP(base), 0);
+
+	init_ppgtt_reg_state(regs, base, ppgtt);
 
 	if (rcs) {
 		regs[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1) | lri_base;
@@ -3240,6 +3264,66 @@ static void execlists_init_reg_state(u32 *regs,
 		regs[CTX_END] |= BIT(0);
 }
 
+static void gen12_init_reg_state(u32 * const regs,
+				 struct intel_context *ce,
+				 struct intel_engine_cs *engine,
+				 struct intel_ring *ring)
+{
+	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(ce->vm);
+	const bool rcs = engine->class == RENDER_CLASS;
+	const u32 base = engine->mmio_base;
+	const u32 lri_base =
+		intel_engine_has_relative_mmio(engine) ? MI_LRI_CS_MMIO : 0;
+
+	regs[CTX_LRI_HEADER_0] =
+		MI_LOAD_REGISTER_IMM(rcs ? 11 : 9) |
+		MI_LRI_FORCE_POSTED |
+		lri_base;
+
+	init_common_reg_state(regs, ppgtt, engine, ring);
+
+	/* We want ctx_ptr for all engines to be set */
+	init_wa_bb_reg_state(regs, engine, GEN12_CTX_BB_PER_CTX_PTR);
+
+	regs[CTX_LRI_HEADER_1] =
+		MI_LOAD_REGISTER_IMM(9) |
+		MI_LRI_FORCE_POSTED |
+		lri_base;
+
+	CTX_REG(regs, CTX_CTX_TIMESTAMP, RING_CTX_TIMESTAMP(base), 0);
+
+	init_ppgtt_reg_state(regs, base, ppgtt);
+
+	if (rcs) {
+		regs[GEN12_CTX_LRI_HEADER_3] =
+			MI_LOAD_REGISTER_IMM(1) | lri_base;
+		CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, 0);
+
+		/* TODO: oa_init_reg_state ? */
+	}
+}
+
+static void execlists_init_reg_state(u32 *regs,
+				     struct intel_context *ce,
+				     struct intel_engine_cs *engine,
+				     struct intel_ring *ring)
+{
+	/*
+	 * A context is actually a big batch buffer with several
+	 * MI_LOAD_REGISTER_IMM commands followed by (reg, value) pairs. The
+	 * values we are setting here are only for the first context restore:
+	 * on a subsequent save, the GPU will recreate this batchbuffer with new
+	 * values (including all the missing MI_LOAD_REGISTER_IMM commands that
+	 * we are not initializing here).
+	 *
+	 * Must keep consistent with virtual_update_register_offsets().
+	 */
+	if (INTEL_GEN(engine->i915) >= 12)
+		gen12_init_reg_state(regs, ce, engine, ring);
+	else
+		gen8_init_reg_state(regs, ce, engine, ring);
+}
+
 static int
 populate_lr_context(struct intel_context *ce,
 		    struct drm_i915_gem_object *ctx_obj,
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
index b8f20ad71169..68caf8541866 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
@@ -9,7 +9,7 @@
 
 #include <linux/types.h>
 
-/* GEN8+ Reg State Context */
+/* GEN8 to GEN11 Reg State Context */
 #define CTX_LRI_HEADER_0		0x01
 #define CTX_CONTEXT_CONTROL		0x02
 #define CTX_RING_HEAD			0x04
@@ -39,6 +39,10 @@
 #define CTX_R_PWR_CLK_STATE		0x42
 #define CTX_END				0x44
 
+/* GEN12+ Reg State Context */
+#define GEN12_CTX_BB_PER_CTX_PTR		0x12
+#define GEN12_CTX_LRI_HEADER_3			0x41
+
 #define CTX_REG(reg_state, pos, reg, val) do { \
 	u32 *reg_state__ = (reg_state); \
 	const u32 pos__ = (pos); \
-- 
cgit v1.2.3


From 42014f69bb235f1123a6f8befb58b3e350a6f180 Mon Sep 17 00:00:00 2001
From: Andi Shyti <andi.shyti@intel.com>
Date: Thu, 5 Sep 2019 14:14:03 +0300
Subject: drm/i915: Hook up GT power management

Refactor the GT power management interface to work through the GT now
that it is under the control of gt/

Based on a patch by Chris Wilson.

Signed-off-by: Andi Shyti <andi.shyti@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190905111403.10071-1-andi.shyti@intel.com
---
 drivers/gpu/drm/i915/gem/i915_gem_pm.c           |  1 +
 drivers/gpu/drm/i915/gt/intel_gt.c               | 45 ++++++++++++++++++++++--
 drivers/gpu/drm/i915/gt/intel_gt.h               |  9 +++--
 drivers/gpu/drm/i915/gt/intel_gt_pm.c            | 36 +++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_gt_pm.h            |  2 ++
 drivers/gpu/drm/i915/i915_drv.c                  | 21 +++--------
 drivers/gpu/drm/i915/i915_gem.c                  | 30 +++-------------
 drivers/gpu/drm/i915/intel_pm.c                  |  4 ++-
 drivers/gpu/drm/i915/selftests/mock_gem_device.c |  2 +-
 9 files changed, 100 insertions(+), 50 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 92e53c25424c..b3993d24b83d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -137,6 +137,7 @@ static bool switch_to_kernel_context_sync(struct intel_gt *gt)
 
 bool i915_gem_load_power_context(struct drm_i915_private *i915)
 {
+	intel_gt_pm_enable(&i915->gt);
 	return switch_to_kernel_context_sync(&i915->gt);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index d48ec9a76ed1..e2cc697d27fb 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -7,6 +7,7 @@
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_uncore.h"
+#include "intel_pm.h"
 
 void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 {
@@ -27,6 +28,9 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 void intel_gt_init_hw(struct drm_i915_private *i915)
 {
 	i915->gt.ggtt = &i915->ggtt;
+
+	/* BIOS often leaves RC6 enabled, but disable it for hw init */
+	intel_gt_pm_disable(&i915->gt);
 }
 
 static void rmw_set(struct intel_uncore *uncore, i915_reg_t reg, u32 set)
@@ -222,7 +226,13 @@ void intel_gt_chipset_flush(struct intel_gt *gt)
 		intel_gtt_chipset_flush();
 }
 
-int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size)
+void intel_gt_driver_register(struct intel_gt *gt)
+{
+	if (IS_GEN(gt->i915, 5))
+		intel_gpu_ips_init(gt->i915);
+}
+
+static int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size)
 {
 	struct drm_i915_private *i915 = gt->i915;
 	struct drm_i915_gem_object *obj;
@@ -256,11 +266,42 @@ err_unref:
 	return ret;
 }
 
-void intel_gt_fini_scratch(struct intel_gt *gt)
+static void intel_gt_fini_scratch(struct intel_gt *gt)
 {
 	i915_vma_unpin_and_release(&gt->scratch, 0);
 }
 
+int intel_gt_init(struct intel_gt *gt)
+{
+	int err;
+
+	err = intel_gt_init_scratch(gt, IS_GEN(gt->i915, 2) ? SZ_256K : SZ_4K);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+void intel_gt_driver_remove(struct intel_gt *gt)
+{
+	GEM_BUG_ON(gt->awake);
+	intel_gt_pm_disable(gt);
+}
+
+void intel_gt_driver_unregister(struct intel_gt *gt)
+{
+	intel_gpu_ips_teardown();
+}
+
+void intel_gt_driver_release(struct intel_gt *gt)
+{
+	/* Paranoia: make sure we have disabled everything before we exit. */
+	intel_gt_pm_disable(gt);
+
+	intel_cleanup_gt_powersave(gt->i915);
+	intel_gt_fini_scratch(gt);
+}
+
 void intel_gt_driver_late_release(struct intel_gt *gt)
 {
 	intel_uc_driver_late_release(&gt->uc);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 4920cb351f10..17af21cb7ed3 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -29,6 +29,12 @@ static inline struct intel_gt *huc_to_gt(struct intel_huc *huc)
 
 void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915);
 void intel_gt_init_hw(struct drm_i915_private *i915);
+int intel_gt_init(struct intel_gt *gt);
+void intel_gt_driver_register(struct intel_gt *gt);
+
+void intel_gt_driver_unregister(struct intel_gt *gt);
+void intel_gt_driver_remove(struct intel_gt *gt);
+void intel_gt_driver_release(struct intel_gt *gt);
 
 void intel_gt_driver_late_release(struct intel_gt *gt);
 
@@ -41,9 +47,6 @@ void intel_gt_chipset_flush(struct intel_gt *gt);
 
 void intel_gt_init_hangcheck(struct intel_gt *gt);
 
-int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size);
-void intel_gt_fini_scratch(struct intel_gt *gt);
-
 static inline u32 intel_gt_scratch_offset(const struct intel_gt *gt,
 					  enum intel_gt_scratch_field field)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index aa6cf0152ce7..6ba0d2069f87 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -124,6 +124,42 @@ void intel_gt_sanitize(struct intel_gt *gt, bool force)
 		__intel_engine_reset(engine, false);
 }
 
+static bool is_mock_device(const struct intel_gt *gt)
+{
+	return I915_SELFTEST_ONLY(gt->awake == -1);
+}
+
+void intel_gt_pm_enable(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	/* Powersaving is controlled by the host when inside a VM */
+	if (intel_vgpu_active(gt->i915))
+		return;
+
+	if (is_mock_device(gt))
+		return;
+
+	intel_gt_pm_get(gt);
+
+	for_each_engine(engine, gt->i915, id) {
+		intel_engine_pm_get(engine);
+		engine->serial++; /* force kernel context reload */
+		intel_engine_pm_put(engine);
+	}
+
+	intel_gt_pm_put(gt);
+}
+
+void intel_gt_pm_disable(struct intel_gt *gt)
+{
+	if (is_mock_device(gt))
+		return;
+
+	intel_sanitize_gt_powersave(gt->i915);
+}
+
 int intel_gt_resume(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
index fb39d99cd6ee..d1f3e2e23937 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
@@ -43,6 +43,8 @@ static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt)
 }
 
 void intel_gt_pm_init_early(struct intel_gt *gt);
+void intel_gt_pm_enable(struct intel_gt *gt);
+void intel_gt_pm_disable(struct intel_gt *gt);
 
 void intel_gt_sanitize(struct intel_gt *gt, bool force);
 int intel_gt_resume(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 9478f704a315..63e52e153414 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1316,9 +1316,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 	pm_qos_add_request(&dev_priv->pm_qos, PM_QOS_CPU_DMA_LATENCY,
 			   PM_QOS_DEFAULT_VALUE);
 
-	/* BIOS often leaves RC6 enabled, but disable it for hw init */
-	intel_sanitize_gt_powersave(dev_priv);
-
 	intel_gt_init_workarounds(dev_priv);
 
 	/* On the 945G/GM, the chipset reports the MSI capability on the
@@ -1424,8 +1421,7 @@ static void i915_driver_register(struct drm_i915_private *dev_priv)
 		acpi_video_register();
 	}
 
-	if (IS_GEN(dev_priv, 5))
-		intel_gpu_ips_init(dev_priv);
+	intel_gt_driver_register(&dev_priv->gt);
 
 	intel_audio_init(dev_priv);
 
@@ -1468,7 +1464,7 @@ static void i915_driver_unregister(struct drm_i915_private *dev_priv)
 	 */
 	drm_kms_helper_poll_fini(&dev_priv->drm);
 
-	intel_gpu_ips_teardown();
+	intel_gt_driver_unregister(&dev_priv->gt);
 	acpi_video_unregister();
 	intel_opregion_unregister(dev_priv);
 
@@ -1612,9 +1608,6 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 out_cleanup_hw:
 	i915_driver_hw_remove(dev_priv);
 	i915_ggtt_driver_release(dev_priv);
-
-	/* Paranoia: make sure we have disabled everything before we exit. */
-	intel_sanitize_gt_powersave(dev_priv);
 out_cleanup_mmio:
 	i915_driver_mmio_release(dev_priv);
 out_runtime_pm_put:
@@ -1685,9 +1678,6 @@ static void i915_driver_release(struct drm_device *dev)
 
 	i915_ggtt_driver_release(dev_priv);
 
-	/* Paranoia: make sure we have disabled everything before we exit. */
-	intel_sanitize_gt_powersave(dev_priv);
-
 	i915_driver_mmio_release(dev_priv);
 
 	enable_rpm_wakeref_asserts(rpm);
@@ -1916,7 +1906,7 @@ static int i915_drm_resume(struct drm_device *dev)
 	int ret;
 
 	disable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
-	intel_sanitize_gt_powersave(dev_priv);
+	intel_gt_pm_disable(&dev_priv->gt);
 
 	i915_gem_sanitize(dev_priv);
 
@@ -2044,7 +2034,7 @@ static int i915_drm_resume_early(struct drm_device *dev)
 
 	intel_display_power_resume_early(dev_priv);
 
-	intel_sanitize_gt_powersave(dev_priv);
+	intel_gt_pm_disable(&dev_priv->gt);
 
 	intel_power_domains_resume(dev_priv);
 
@@ -2588,9 +2578,6 @@ static int intel_runtime_suspend(struct device *kdev)
 	struct intel_runtime_pm *rpm = &dev_priv->runtime_pm;
 	int ret = 0;
 
-	if (WARN_ON_ONCE(!(dev_priv->gt_pm.rc6.enabled && HAS_RC6(dev_priv))))
-		return -ENODEV;
-
 	if (WARN_ON_ONCE(!HAS_RUNTIME_PM(dev_priv)))
 		return -ENODEV;
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 95e7c52cf8ed..141024c66f36 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1375,17 +1375,6 @@ out:
 	return err;
 }
 
-static int
-i915_gem_init_scratch(struct drm_i915_private *i915, unsigned int size)
-{
-	return intel_gt_init_scratch(&i915->gt, size);
-}
-
-static void i915_gem_fini_scratch(struct drm_i915_private *i915)
-{
-	intel_gt_fini_scratch(&i915->gt);
-}
-
 static int intel_engines_verify_workarounds(struct drm_i915_private *i915)
 {
 	struct intel_engine_cs *engine;
@@ -1436,12 +1425,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 		goto err_unlock;
 	}
 
-	ret = i915_gem_init_scratch(dev_priv,
-				    IS_GEN(dev_priv, 2) ? SZ_256K : PAGE_SIZE);
-	if (ret) {
-		GEM_BUG_ON(ret == -EIO);
-		goto err_ggtt;
-	}
+	intel_gt_init(&dev_priv->gt);
 
 	ret = intel_engines_setup(dev_priv);
 	if (ret) {
@@ -1527,15 +1511,13 @@ err_init_hw:
 err_uc_init:
 	if (ret != -EIO) {
 		intel_uc_fini(&dev_priv->gt.uc);
-		intel_cleanup_gt_powersave(dev_priv);
 		intel_engines_cleanup(dev_priv);
 	}
 err_context:
 	if (ret != -EIO)
 		i915_gem_contexts_fini(dev_priv);
 err_scratch:
-	i915_gem_fini_scratch(dev_priv);
-err_ggtt:
+	intel_gt_driver_release(&dev_priv->gt);
 err_unlock:
 	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
@@ -1587,12 +1569,10 @@ void i915_gem_driver_unregister(struct drm_i915_private *i915)
 
 void i915_gem_driver_remove(struct drm_i915_private *dev_priv)
 {
-	GEM_BUG_ON(dev_priv->gt.awake);
-
 	intel_wakeref_auto_fini(&dev_priv->ggtt.userfault_wakeref);
 
 	i915_gem_suspend_late(dev_priv);
-	intel_disable_gt_powersave(dev_priv);
+	intel_gt_driver_remove(&dev_priv->gt);
 
 	/* Flush any outstanding unpin_work. */
 	i915_gem_drain_workqueue(dev_priv);
@@ -1610,13 +1590,11 @@ void i915_gem_driver_release(struct drm_i915_private *dev_priv)
 	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_engines_cleanup(dev_priv);
 	i915_gem_contexts_fini(dev_priv);
-	i915_gem_fini_scratch(dev_priv);
+	intel_gt_driver_release(&dev_priv->gt);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	intel_wa_list_free(&dev_priv->gt_wa_list);
 
-	intel_cleanup_gt_powersave(dev_priv);
-
 	intel_uc_cleanup_firmwares(&dev_priv->gt.uc);
 	i915_gem_cleanup_userptr(dev_priv);
 	intel_timelines_fini(dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 7294fcf05323..528e90ed5de4 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -8671,7 +8671,9 @@ void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
 {
 	mutex_lock(&dev_priv->gt_pm.rps.lock);
 
-	intel_disable_rc6(dev_priv);
+	if (HAS_RC6(dev_priv))
+		intel_disable_rc6(dev_priv);
+
 	intel_disable_rps(dev_priv);
 	if (HAS_LLC(dev_priv))
 		intel_disable_llc_pstate(dev_priv);
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 01a89c071bf5..91f15fa728cd 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -192,7 +192,7 @@ struct drm_i915_private *mock_gem_device(void)
 	INIT_DELAYED_WORK(&i915->gem.retire_work, mock_retire_work_handler);
 	INIT_WORK(&i915->gem.idle_work, mock_idle_work_handler);
 
-	i915->gt.awake = true;
+	i915->gt.awake = -1;
 
 	intel_timelines_init(i915);
 
-- 
cgit v1.2.3


From de10ac47597e7a3596b27631d0d5ce5f48d2c099 Mon Sep 17 00:00:00 2001
From: Remi Pommarel <repk@triplefau.lt>
Date: Sun, 1 Sep 2019 12:54:10 +0200
Subject: iio: adc: meson_saradc: Fix memory allocation order

meson_saradc's irq handler uses priv->regmap so make sure that it is
allocated before the irq get enabled.

This also fixes crash when CONFIG_DEBUG_SHIRQ is enabled, as device
managed resources are freed in the inverted order they had been
allocated, priv->regmap was freed before the spurious fake irq that
CONFIG_DEBUG_SHIRQ adds called the handler.

Fixes: 3af109131b7eb8 ("iio: adc: meson-saradc: switch from polling to interrupt mode")
Reported-by: Elie Roudninski <xademax@gmail.com>
Signed-off-by: Remi Pommarel <repk@triplefau.lt>
Reviewed-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Tested-by: Elie ROUDNINSKI <xademax@gmail.com>
Reviewed-by: Kevin Hilman <khilman@baylibre.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/meson_saradc.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c
index 7b28d045d271..7b27306330a3 100644
--- a/drivers/iio/adc/meson_saradc.c
+++ b/drivers/iio/adc/meson_saradc.c
@@ -1219,6 +1219,11 @@ static int meson_sar_adc_probe(struct platform_device *pdev)
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
+	priv->regmap = devm_regmap_init_mmio(&pdev->dev, base,
+					     priv->param->regmap_config);
+	if (IS_ERR(priv->regmap))
+		return PTR_ERR(priv->regmap);
+
 	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
 	if (!irq)
 		return -EINVAL;
@@ -1228,11 +1233,6 @@ static int meson_sar_adc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	priv->regmap = devm_regmap_init_mmio(&pdev->dev, base,
-					     priv->param->regmap_config);
-	if (IS_ERR(priv->regmap))
-		return PTR_ERR(priv->regmap);
-
 	priv->clkin = devm_clk_get(&pdev->dev, "clkin");
 	if (IS_ERR(priv->clkin)) {
 		dev_err(&pdev->dev, "failed to get clkin\n");
-- 
cgit v1.2.3


From 85ae3aeedeccb6febb0c6f9d5346d9c6419ad925 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 31 Aug 2019 13:18:22 +0200
Subject: iio: imu: st_lsm6dsx: forbid 0 sensor sensitivity

Do not allow configuring null sensor gain since it will force to 0
device outputs

Fixes: c8d4066c7246 ("iio: imu: st_lsm6dsx: remove invalid gain value for LSM9DS1")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h      |  2 ++
 drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c | 28 +++++++++++++++++++---------
 drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c | 11 ++++-------
 3 files changed, 25 insertions(+), 16 deletions(-)

diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h
index 80e42c7dbcbe..0fe6999b8257 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx.h
@@ -99,7 +99,9 @@ struct st_lsm6dsx_fs {
 #define ST_LSM6DSX_FS_LIST_SIZE		4
 struct st_lsm6dsx_fs_table_entry {
 	struct st_lsm6dsx_reg reg;
+
 	struct st_lsm6dsx_fs fs_avl[ST_LSM6DSX_FS_LIST_SIZE];
+	int fs_len;
 };
 
 /**
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
index 2d3495560136..fd5ebe1e1594 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c
@@ -145,6 +145,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_G_TO_M_S_2(122), 0x2 },
 				.fs_avl[2] = { IIO_G_TO_M_S_2(244), 0x3 },
 				.fs_avl[3] = { IIO_G_TO_M_S_2(732), 0x1 },
+				.fs_len = 4,
 			},
 			[ST_LSM6DSX_ID_GYRO] = {
 				.reg = {
@@ -154,6 +155,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[0] = {  IIO_DEGREE_TO_RAD(245), 0x0 },
 				.fs_avl[1] = {  IIO_DEGREE_TO_RAD(500), 0x1 },
 				.fs_avl[2] = { IIO_DEGREE_TO_RAD(2000), 0x3 },
+				.fs_len = 3,
 			},
 		},
 	},
@@ -215,6 +217,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_G_TO_M_S_2(122), 0x2 },
 				.fs_avl[2] = { IIO_G_TO_M_S_2(244), 0x3 },
 				.fs_avl[3] = { IIO_G_TO_M_S_2(488), 0x1 },
+				.fs_len = 4,
 			},
 			[ST_LSM6DSX_ID_GYRO] = {
 				.reg = {
@@ -225,6 +228,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_DEGREE_TO_RAD(17500), 0x1 },
 				.fs_avl[2] = { IIO_DEGREE_TO_RAD(35000), 0x2 },
 				.fs_avl[3] = { IIO_DEGREE_TO_RAD(70000), 0x3 },
+				.fs_len = 4,
 			},
 		},
 		.decimator = {
@@ -327,6 +331,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_G_TO_M_S_2(122), 0x2 },
 				.fs_avl[2] = { IIO_G_TO_M_S_2(244), 0x3 },
 				.fs_avl[3] = { IIO_G_TO_M_S_2(488), 0x1 },
+				.fs_len = 4,
 			},
 			[ST_LSM6DSX_ID_GYRO] = {
 				.reg = {
@@ -337,6 +342,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_DEGREE_TO_RAD(17500), 0x1 },
 				.fs_avl[2] = { IIO_DEGREE_TO_RAD(35000), 0x2 },
 				.fs_avl[3] = { IIO_DEGREE_TO_RAD(70000), 0x3 },
+				.fs_len = 4,
 			},
 		},
 		.decimator = {
@@ -448,6 +454,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_G_TO_M_S_2(122), 0x2 },
 				.fs_avl[2] = { IIO_G_TO_M_S_2(244), 0x3 },
 				.fs_avl[3] = { IIO_G_TO_M_S_2(488), 0x1 },
+				.fs_len = 4,
 			},
 			[ST_LSM6DSX_ID_GYRO] = {
 				.reg = {
@@ -458,6 +465,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_DEGREE_TO_RAD(17500), 0x1 },
 				.fs_avl[2] = { IIO_DEGREE_TO_RAD(35000), 0x2 },
 				.fs_avl[3] = { IIO_DEGREE_TO_RAD(70000), 0x3 },
+				.fs_len = 4,
 			},
 		},
 		.decimator = {
@@ -563,6 +571,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_G_TO_M_S_2(122), 0x2 },
 				.fs_avl[2] = { IIO_G_TO_M_S_2(244), 0x3 },
 				.fs_avl[3] = { IIO_G_TO_M_S_2(488), 0x1 },
+				.fs_len = 4,
 			},
 			[ST_LSM6DSX_ID_GYRO] = {
 				.reg = {
@@ -573,6 +582,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_DEGREE_TO_RAD(17500), 0x1 },
 				.fs_avl[2] = { IIO_DEGREE_TO_RAD(35000), 0x2 },
 				.fs_avl[3] = { IIO_DEGREE_TO_RAD(70000), 0x3 },
+				.fs_len = 4,
 			},
 		},
 		.batch = {
@@ -693,6 +703,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_G_TO_M_S_2(122), 0x2 },
 				.fs_avl[2] = { IIO_G_TO_M_S_2(244), 0x3 },
 				.fs_avl[3] = { IIO_G_TO_M_S_2(488), 0x1 },
+				.fs_len = 4,
 			},
 			[ST_LSM6DSX_ID_GYRO] = {
 				.reg = {
@@ -703,6 +714,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_DEGREE_TO_RAD(17500), 0x1 },
 				.fs_avl[2] = { IIO_DEGREE_TO_RAD(35000), 0x2 },
 				.fs_avl[3] = { IIO_DEGREE_TO_RAD(70000), 0x3 },
+				.fs_len = 4,
 			},
 		},
 		.batch = {
@@ -800,6 +812,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_G_TO_M_S_2(122), 0x2 },
 				.fs_avl[2] = { IIO_G_TO_M_S_2(244), 0x3 },
 				.fs_avl[3] = { IIO_G_TO_M_S_2(488), 0x1 },
+				.fs_len = 4,
 			},
 			[ST_LSM6DSX_ID_GYRO] = {
 				.reg = {
@@ -810,6 +823,7 @@ static const struct st_lsm6dsx_settings st_lsm6dsx_sensor_settings[] = {
 				.fs_avl[1] = { IIO_DEGREE_TO_RAD(17500), 0x1 },
 				.fs_avl[2] = { IIO_DEGREE_TO_RAD(35000), 0x2 },
 				.fs_avl[3] = { IIO_DEGREE_TO_RAD(70000), 0x3 },
+				.fs_len = 4,
 			},
 		},
 		.batch = {
@@ -933,11 +947,12 @@ static int st_lsm6dsx_set_full_scale(struct st_lsm6dsx_sensor *sensor,
 	int i, err;
 
 	fs_table = &sensor->hw->settings->fs_table[sensor->id];
-	for (i = 0; i < ST_LSM6DSX_FS_LIST_SIZE; i++)
+	for (i = 0; i < fs_table->fs_len; i++) {
 		if (fs_table->fs_avl[i].gain == gain)
 			break;
+	}
 
-	if (i == ST_LSM6DSX_FS_LIST_SIZE)
+	if (i == fs_table->fs_len)
 		return -EINVAL;
 
 	data = ST_LSM6DSX_SHIFT_VAL(fs_table->fs_avl[i].val,
@@ -1196,18 +1211,13 @@ static ssize_t st_lsm6dsx_sysfs_scale_avail(struct device *dev,
 {
 	struct st_lsm6dsx_sensor *sensor = iio_priv(dev_get_drvdata(dev));
 	const struct st_lsm6dsx_fs_table_entry *fs_table;
-	enum st_lsm6dsx_sensor_id id = sensor->id;
 	struct st_lsm6dsx_hw *hw = sensor->hw;
 	int i, len = 0;
 
-	fs_table = &hw->settings->fs_table[id];
-	for (i = 0; i < ST_LSM6DSX_FS_LIST_SIZE; i++) {
-		if (!fs_table->fs_avl[i].gain)
-			break;
-
+	fs_table = &hw->settings->fs_table[sensor->id];
+	for (i = 0; i < fs_table->fs_len; i++)
 		len += scnprintf(buf + len, PAGE_SIZE - len, "0.%06u ",
 				 fs_table->fs_avl[i].gain);
-	}
 	buf[len - 1] = '\n';
 
 	return len;
diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c
index 66fbcd94642d..f5fca2171954 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c
@@ -61,6 +61,7 @@ static const struct st_lsm6dsx_ext_dev_settings st_lsm6dsx_ext_dev_table[] = {
 				.gain = 1500,
 				.val = 0x0,
 			}, /* 1500 uG/LSB */
+			.fs_len = 1,
 		},
 		.temp_comp = {
 			.addr = 0x60,
@@ -555,13 +556,9 @@ static ssize_t st_lsm6dsx_shub_scale_avail(struct device *dev,
 	int i, len = 0;
 
 	settings = sensor->ext_info.settings;
-	for (i = 0; i < ST_LSM6DSX_FS_LIST_SIZE; i++) {
-		u16 val = settings->fs_table.fs_avl[i].gain;
-
-		if (val > 0)
-			len += scnprintf(buf + len, PAGE_SIZE - len, "0.%06u ",
-					 val);
-	}
+	for (i = 0; i < settings->fs_table.fs_len; i++)
+		len += scnprintf(buf + len, PAGE_SIZE - len, "0.%06u ",
+				 settings->fs_table.fs_avl[i].gain);
 	buf[len - 1] = '\n';
 
 	return len;
-- 
cgit v1.2.3


From 6c59a962e081df6d8fe43325bbfabec57e0d4751 Mon Sep 17 00:00:00 2001
From: Pascal Bouwmann <bouwmann@tau-tec.de>
Date: Thu, 29 Aug 2019 07:29:41 +0200
Subject: iio: fix center temperature of bmc150-accel-core

The center temperature of the supported devices stored in the constant
BMC150_ACCEL_TEMP_CENTER_VAL is not 24 degrees but 23 degrees.

It seems that some datasheets were inconsistent on this value leading
to the error.  For most usecases will only make minor difference so
not queued for stable.

Signed-off-by: Pascal Bouwmann <bouwmann@tau-tec.de>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/bmc150-accel-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c
index cf6c0e3a83d3..121b4e89f038 100644
--- a/drivers/iio/accel/bmc150-accel-core.c
+++ b/drivers/iio/accel/bmc150-accel-core.c
@@ -117,7 +117,7 @@
 #define BMC150_ACCEL_SLEEP_1_SEC		0x0F
 
 #define BMC150_ACCEL_REG_TEMP			0x08
-#define BMC150_ACCEL_TEMP_CENTER_VAL		24
+#define BMC150_ACCEL_TEMP_CENTER_VAL		23
 
 #define BMC150_ACCEL_AXIS_TO_REG(axis)	(BMC150_ACCEL_REG_XOUT_L + (axis * 2))
 #define BMC150_AUTO_SUSPEND_DELAY_MS		2000
-- 
cgit v1.2.3


From 5d7f965e5675ae0cbec5fe56af79da9039f723ed Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Thu, 5 Sep 2019 10:29:21 +0300
Subject: drm/i915/buddy: add missing call to i915_global_register

We are meant to register the kmem cache at init, such the supplied exit
and shrink hooks can be called.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190905072921.7979-1-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/i915_buddy.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/i915_buddy.c b/drivers/gpu/drm/i915/i915_buddy.c
index fe1871d7c126..e9d4200ce3bc 100644
--- a/drivers/gpu/drm/i915/i915_buddy.c
+++ b/drivers/gpu/drm/i915/i915_buddy.c
@@ -38,6 +38,7 @@ int __init i915_global_buddy_init(void)
 	if (!global.slab_blocks)
 		return -ENOMEM;
 
+	i915_global_register(&global.base);
 	return 0;
 }
 
-- 
cgit v1.2.3


From d810583fc2fcf139cc766eb2303500b2d9cf064d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 7 Sep 2019 11:50:46 +0100
Subject: drm/i915/execlists: Remove incorrect BUG_ON for schedule-out

As we may unwind incomplete requests (for preemption) prior to
processing the CSB and the schedule-out events, we may update rq->engine
(resetting it to point back to the parent virtual engine) prior to
calling execlists_schedule_out(), invalidating the assertion that the
request still points to the inflight engine. (The likelihood of this is
increased if the CSB interrupt processing is pushed to the ksoftirqd for
being too slow and direct submission overtakes it.)

Tvrtko summarised it as:
"So unwind from direct submission resets rq->engine and races with
process_csb from the tasklet which notices request has actually
completed."

Reported-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Fixes: df403069029d ("drm/i915/execlists: Lift process_csb() out of the irq-off spinlock")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190907105046.19934-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 0ddfbebbcbbc..f073aea6a1fe 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -631,7 +631,6 @@ execlists_schedule_out(struct i915_request *rq)
 	struct intel_engine_cs *cur, *old;
 
 	trace_i915_request_out(rq);
-	GEM_BUG_ON(intel_context_inflight(ce) != rq->engine);
 
 	old = READ_ONCE(ce->inflight);
 	do
-- 
cgit v1.2.3


From 9c426b770bd088f18899f836093d810a83b59b98 Mon Sep 17 00:00:00 2001
From: Talel Shenhar <talel@amazon.com>
Date: Mon, 9 Sep 2019 11:39:18 +0300
Subject: irqchip/al-fic: Add support for irq retrigger

Introduce interrupts retrigger support for Amazon's Annapurna Labs Fabric
Interrupt Controller.

Signed-off-by: Talel Shenhar <talel@amazon.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/1568018358-18985-1-git-send-email-talel@amazon.com
---
 drivers/irqchip/irq-al-fic.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/irqchip/irq-al-fic.c b/drivers/irqchip/irq-al-fic.c
index 1a57cee3efab..0b0a73739756 100644
--- a/drivers/irqchip/irq-al-fic.c
+++ b/drivers/irqchip/irq-al-fic.c
@@ -15,6 +15,7 @@
 
 /* FIC Registers */
 #define AL_FIC_CAUSE		0x00
+#define AL_FIC_SET_CAUSE	0x08
 #define AL_FIC_MASK		0x10
 #define AL_FIC_CONTROL		0x28
 
@@ -126,6 +127,16 @@ static void al_fic_irq_handler(struct irq_desc *desc)
 	chained_irq_exit(irqchip, desc);
 }
 
+static int al_fic_irq_retrigger(struct irq_data *data)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
+	struct al_fic *fic = gc->private;
+
+	writel_relaxed(BIT(data->hwirq), fic->base + AL_FIC_SET_CAUSE);
+
+	return 1;
+}
+
 static int al_fic_register(struct device_node *node,
 			   struct al_fic *fic)
 {
@@ -159,6 +170,7 @@ static int al_fic_register(struct device_node *node,
 	gc->chip_types->chip.irq_unmask = irq_gc_mask_clr_bit;
 	gc->chip_types->chip.irq_ack = irq_gc_ack_clr_bit;
 	gc->chip_types->chip.irq_set_type = al_fic_irq_set_type;
+	gc->chip_types->chip.irq_retrigger = al_fic_irq_retrigger;
 	gc->chip_types->chip.flags = IRQCHIP_SKIP_SET_WAKE;
 	gc->private = fic;
 
-- 
cgit v1.2.3


From 212fbf2c9e84ceb267cadd8342156b69b54b8135 Mon Sep 17 00:00:00 2001
From: Sandeep Sheriker Mallikarjun <sandeepsheriker.mallikarjun@microchip.com>
Date: Mon, 9 Sep 2019 14:00:35 +0300
Subject: irqchip/atmel-aic5: Add support for sam9x60 irqchip

Add support for SAM9X60 irqchip.

Signed-off-by: Sandeep Sheriker Mallikarjun <sandeepsheriker.mallikarjun@microchip.com>
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/1568026835-6646-1-git-send-email-claudiu.beznea@microchip.com

[claudiu.beznea@microchip.com: update aic5_irq_fixups[], update
 documentation]
---
 .../devicetree/bindings/interrupt-controller/atmel,aic.txt     |  7 +++++--
 drivers/irqchip/irq-atmel-aic5.c                               | 10 ++++++++++
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
index f4c5d34c4111..7079d44bf3ba 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
@@ -1,8 +1,11 @@
 * Advanced Interrupt Controller (AIC)
 
 Required properties:
-- compatible: Should be "atmel,<chip>-aic"
-  <chip> can be "at91rm9200", "sama5d2", "sama5d3" or "sama5d4"
+- compatible: Should be:
+    - "atmel,<chip>-aic" where  <chip> can be "at91rm9200", "sama5d2",
+      "sama5d3" or "sama5d4"
+    - "microchip,<chip>-aic" where <chip> can be "sam9x60"
+
 - interrupt-controller: Identifies the node as an interrupt controller.
 - #interrupt-cells: The number of cells to define the interrupts. It should be 3.
   The first cell is the IRQ number (aka "Peripheral IDentifier" on datasheet).
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index 6acad2ea0fb3..29333497ba10 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -313,6 +313,7 @@ static void __init sama5d3_aic_irq_fixup(void)
 static const struct of_device_id aic5_irq_fixups[] __initconst = {
 	{ .compatible = "atmel,sama5d3", .data = sama5d3_aic_irq_fixup },
 	{ .compatible = "atmel,sama5d4", .data = sama5d3_aic_irq_fixup },
+	{ .compatible = "microchip,sam9x60", .data = sama5d3_aic_irq_fixup },
 	{ /* sentinel */ },
 };
 
@@ -390,3 +391,12 @@ static int __init sama5d4_aic5_of_init(struct device_node *node,
 	return aic5_of_init(node, parent, NR_SAMA5D4_IRQS);
 }
 IRQCHIP_DECLARE(sama5d4_aic5, "atmel,sama5d4-aic", sama5d4_aic5_of_init);
+
+#define NR_SAM9X60_IRQS		50
+
+static int __init sam9x60_aic5_of_init(struct device_node *node,
+				       struct device_node *parent)
+{
+	return aic5_of_init(node, parent, NR_SAM9X60_IRQS);
+}
+IRQCHIP_DECLARE(sam9x60_aic5, "microchip,sam9x60-aic", sam9x60_aic5_of_init);
-- 
cgit v1.2.3


From b6749e20d5710c955fc6d4322f8fd98c915b2573 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 1 Sep 2019 22:12:35 +0100
Subject: arm64: KVM: Drop hyp_alternate_select for checking for
 ARM64_WORKAROUND_834220

There is no reason for using hyp_alternate_select when checking
for ARM64_WORKAROUND_834220, as each of the capabilities is
also backed by a static key. Just replace the KVM-specific
construct with cpus_have_const_cap(ARM64_WORKAROUND_834220).

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Christoffer Dall <christoffer.dall@arm.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
---
 arch/arm64/kvm/hyp/switch.c | 17 ++---------------
 1 file changed, 2 insertions(+), 15 deletions(-)

diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index adaf266d8de8..a15baca9aca0 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -229,20 +229,6 @@ static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
 	}
 }
 
-static bool __hyp_text __true_value(void)
-{
-	return true;
-}
-
-static bool __hyp_text __false_value(void)
-{
-	return false;
-}
-
-static hyp_alternate_select(__check_arm_834220,
-			    __false_value, __true_value,
-			    ARM64_WORKAROUND_834220);
-
 static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
 {
 	u64 par, tmp;
@@ -298,7 +284,8 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 	 * resolve the IPA using the AT instruction.
 	 */
 	if (!(esr & ESR_ELx_S1PTW) &&
-	    (__check_arm_834220()() || (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+	    (cpus_have_const_cap(ARM64_WORKAROUND_834220) ||
+	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
 		if (!__translate_far_to_hpfar(far, &hpfar))
 			return false;
 	} else {
-- 
cgit v1.2.3


From aa979fa899c5cf592e63ce7b34bc767224225c6a Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 1 Sep 2019 22:12:36 +0100
Subject: arm64: KVM: Replace hyp_alternate_select with has_vhe()

Given that the TLB invalidation path is pretty rarely used, there
was never any advantage to using hyp_alternate_select() here.
has_vhe(), being a glorified static key, is the right tool for
the job.

Off you go.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Christoffer Dall <christoffer.dall@arm.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
---
 arch/arm64/kvm/hyp/tlb.c | 36 ++++++++++++++++++++++--------------
 1 file changed, 22 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index c466060b76d6..eb0efc5557f3 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -67,10 +67,14 @@ static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
 	isb();
 }
 
-static hyp_alternate_select(__tlb_switch_to_guest,
-			    __tlb_switch_to_guest_nvhe,
-			    __tlb_switch_to_guest_vhe,
-			    ARM64_HAS_VIRT_HOST_EXTN);
+static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
+					     struct tlb_inv_context *cxt)
+{
+	if (has_vhe())
+		__tlb_switch_to_guest_vhe(kvm, cxt);
+	else
+		__tlb_switch_to_guest_nvhe(kvm, cxt);
+}
 
 static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
 						struct tlb_inv_context *cxt)
@@ -98,10 +102,14 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
 	write_sysreg(0, vttbr_el2);
 }
 
-static hyp_alternate_select(__tlb_switch_to_host,
-			    __tlb_switch_to_host_nvhe,
-			    __tlb_switch_to_host_vhe,
-			    ARM64_HAS_VIRT_HOST_EXTN);
+static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
+					    struct tlb_inv_context *cxt)
+{
+	if (has_vhe())
+		__tlb_switch_to_host_vhe(kvm, cxt);
+	else
+		__tlb_switch_to_host_nvhe(kvm, cxt);
+}
 
 void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
@@ -111,7 +119,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	__tlb_switch_to_guest()(kvm, &cxt);
+	__tlb_switch_to_guest(kvm, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -154,7 +162,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	if (!has_vhe() && icache_is_vpipt())
 		__flush_icache_all();
 
-	__tlb_switch_to_host()(kvm, &cxt);
+	__tlb_switch_to_host(kvm, &cxt);
 }
 
 void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
@@ -165,13 +173,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	__tlb_switch_to_guest()(kvm, &cxt);
+	__tlb_switch_to_guest(kvm, &cxt);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host()(kvm, &cxt);
+	__tlb_switch_to_host(kvm, &cxt);
 }
 
 void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
@@ -180,13 +188,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest()(kvm, &cxt);
+	__tlb_switch_to_guest(kvm, &cxt);
 
 	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host()(kvm, &cxt);
+	__tlb_switch_to_host(kvm, &cxt);
 }
 
 void __hyp_text __kvm_flush_vm_context(void)
-- 
cgit v1.2.3


From 084b5a80e87258997632dbd975ec3e5fda6bb943 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 1 Sep 2019 22:12:37 +0100
Subject: arm64: KVM: Kill hyp_alternate_select()

hyp_alternate_select() is now completely unused. Goodbye.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Christoffer Dall <christoffer.dall@arm.com>
Reviewed-by: Andrew Jones <drjones@redhat.com>
---
 arch/arm64/include/asm/kvm_hyp.h | 24 ------------------------
 1 file changed, 24 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 86825aa20852..97f21cc66657 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -47,30 +47,6 @@
 #define read_sysreg_el2(r)	read_sysreg_elx(r, _EL2, _EL1)
 #define write_sysreg_el2(v,r)	write_sysreg_elx(v, r, _EL2, _EL1)
 
-/**
- * hyp_alternate_select - Generates patchable code sequences that are
- * used to switch between two implementations of a function, depending
- * on the availability of a feature.
- *
- * @fname: a symbol name that will be defined as a function returning a
- * function pointer whose type will match @orig and @alt
- * @orig: A pointer to the default function, as returned by @fname when
- * @cond doesn't hold
- * @alt: A pointer to the alternate function, as returned by @fname
- * when @cond holds
- * @cond: a CPU feature (as described in asm/cpufeature.h)
- */
-#define hyp_alternate_select(fname, orig, alt, cond)			\
-typeof(orig) * __hyp_text fname(void)					\
-{									\
-	typeof(alt) *val = orig;					\
-	asm volatile(ALTERNATIVE("nop		\n",			\
-				 "mov	%0, %1	\n",			\
-				 cond)					\
-		     : "+r" (val) : "r" (alt));				\
-	return val;							\
-}
-
 int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu);
 
 void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
-- 
cgit v1.2.3


From 1e0a96e508827ad88229bff32ea2641c83fc52a8 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Mon, 9 Sep 2019 13:40:50 +0100
Subject: drm/i915: export color_differs

Export color_differs so that we can use it elsewhere.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190909124052.22900-1-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/i915_gem_gtt.c |  2 +-
 drivers/gpu/drm/i915/i915_vma.c     | 11 ++++-------
 drivers/gpu/drm/i915/i915_vma.h     |  6 ++++++
 3 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 906dc6fff383..095f5e358a58 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2552,7 +2552,7 @@ static void i915_gtt_color_adjust(const struct drm_mm_node *node,
 				  u64 *start,
 				  u64 *end)
 {
-	if (node->allocated && node->color != color)
+	if (i915_node_color_differs(node, color))
 		*start += I915_GTT_PAGE_SIZE;
 
 	/* Also leave a space between the unallocated reserved node after the
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index e0e677b2a3a9..a90bd2678353 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -477,11 +477,6 @@ void __i915_vma_set_map_and_fenceable(struct i915_vma *vma)
 		vma->flags &= ~I915_VMA_CAN_FENCE;
 }
 
-static bool color_differs(struct drm_mm_node *node, unsigned long color)
-{
-	return node->allocated && node->color != color;
-}
-
 bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long cache_level)
 {
 	struct drm_mm_node *node = &vma->node;
@@ -502,11 +497,13 @@ bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long cache_level)
 	GEM_BUG_ON(list_empty(&node->node_list));
 
 	other = list_prev_entry(node, node_list);
-	if (color_differs(other, cache_level) && !drm_mm_hole_follows(other))
+	if (i915_node_color_differs(other, cache_level) &&
+	    !drm_mm_hole_follows(other))
 		return false;
 
 	other = list_next_entry(node, node_list);
-	if (color_differs(other, cache_level) && !drm_mm_hole_follows(node))
+	if (i915_node_color_differs(other, cache_level) &&
+	    !drm_mm_hole_follows(node))
 		return false;
 
 	return true;
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 889fc7cb910a..5b1e0cf7669d 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -373,6 +373,12 @@ static inline bool i915_vma_is_bound(const struct i915_vma *vma,
 	return vma->flags & where;
 }
 
+static inline bool i915_node_color_differs(const struct drm_mm_node *node,
+					   unsigned long color)
+{
+	return node->allocated && node->color != color;
+}
+
 /**
  * i915_vma_pin_iomap - calls ioremap_wc to map the GGTT VMA via the aperture
  * @vma: VMA to iomap
-- 
cgit v1.2.3


From e9ceb751ad4ee69591bcd33b2a220738855395ea Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Mon, 9 Sep 2019 13:40:51 +0100
Subject: drm/i915: s/i915_gtt_color_adjust/i915_ggtt_color_adjust

Make it clear that the color adjust callback applies to the ggtt.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190909124052.22900-2-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/i915_gem_gtt.c             | 10 +++++-----
 drivers/gpu/drm/i915/selftests/i915_gem_evict.c |  2 +-
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 095f5e358a58..48688d683e95 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2547,10 +2547,10 @@ static int ggtt_set_pages(struct i915_vma *vma)
 	return 0;
 }
 
-static void i915_gtt_color_adjust(const struct drm_mm_node *node,
-				  unsigned long color,
-				  u64 *start,
-				  u64 *end)
+static void i915_ggtt_color_adjust(const struct drm_mm_node *node,
+				   unsigned long color,
+				   u64 *start,
+				   u64 *end)
 {
 	if (i915_node_color_differs(node, color))
 		*start += I915_GTT_PAGE_SIZE;
@@ -3206,7 +3206,7 @@ static int ggtt_init_hw(struct i915_ggtt *ggtt)
 	ggtt->vm.has_read_only = IS_VALLEYVIEW(i915);
 
 	if (!HAS_LLC(i915) && !HAS_PPGTT(i915))
-		ggtt->vm.mm.color_adjust = i915_gtt_color_adjust;
+		ggtt->vm.mm.color_adjust = i915_ggtt_color_adjust;
 
 	if (!io_mapping_init_wc(&ggtt->iomap,
 				ggtt->gmadr.start,
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index cb30c669b1b7..fca38167bdce 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -276,7 +276,7 @@ static int igt_evict_for_cache_color(void *arg)
 
 	/* Currently the use of color_adjust is limited to cache domains within
 	 * the ggtt, and so the presence of mm.color_adjust is assumed to be
-	 * i915_gtt_color_adjust throughout our driver, so using a mock color
+	 * i915_ggtt_color_adjust throughout our driver, so using a mock color
 	 * adjust will work just fine for our purposes.
 	 */
 	ggtt->vm.mm.color_adjust = mock_color_adjust;
-- 
cgit v1.2.3


From 33dd8899231372a438bf7d96afa1dbe13a5e17c7 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Mon, 9 Sep 2019 13:40:52 +0100
Subject: drm/i915: cleanup cache-coloring

Try to tidy up the cache-coloring such that we rid the code of any
mm.color_adjust assumptions, this should hopefully make it more obvious
in the code when we need to actually use the cache-level as the color,
and as a bonus should make adding a different color-scheme simpler.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190909124052.22900-3-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/gem/i915_gem_domain.c      |  6 ++++--
 drivers/gpu/drm/i915/i915_drv.h                 |  2 +-
 drivers/gpu/drm/i915/i915_gem_evict.c           | 12 +++++-------
 drivers/gpu/drm/i915/i915_gem_gtt.h             |  6 ++++++
 drivers/gpu/drm/i915/i915_vma.c                 | 22 +++++++++++-----------
 drivers/gpu/drm/i915/i915_vma.h                 |  2 +-
 drivers/gpu/drm/i915/selftests/i915_gem_evict.c | 10 ++++++----
 7 files changed, 34 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 6af740a5e3db..da3e7cf12aa1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -294,8 +294,10 @@ restart:
 		}
 	}
 
-	list_for_each_entry(vma, &obj->vma.list, obj_link)
-		vma->node.color = cache_level;
+	list_for_each_entry(vma, &obj->vma.list, obj_link) {
+		if (i915_vm_has_cache_coloring(vma->vm))
+			vma->node.color = cache_level;
+	}
 	i915_gem_object_set_cache_coherency(obj, cache_level);
 	obj->cache_dirty = true; /* Always invalidate stale cachelines */
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index db7480831e52..e289b4ffd34b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2364,7 +2364,7 @@ i915_gem_context_lookup(struct drm_i915_file_private *file_priv, u32 id)
 /* i915_gem_evict.c */
 int __must_check i915_gem_evict_something(struct i915_address_space *vm,
 					  u64 min_size, u64 alignment,
-					  unsigned cache_level,
+					  unsigned long color,
 					  u64 start, u64 end,
 					  unsigned flags);
 int __must_check i915_gem_evict_for_node(struct i915_address_space *vm,
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 52c86c6e0673..e76c9da9992d 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -70,7 +70,7 @@ mark_free(struct drm_mm_scan *scan,
  * @vm: address space to evict from
  * @min_size: size of the desired free space
  * @alignment: alignment constraint of the desired free space
- * @cache_level: cache_level for the desired space
+ * @color: color for the desired space
  * @start: start (inclusive) of the range from which to evict objects
  * @end: end (exclusive) of the range from which to evict objects
  * @flags: additional flags to control the eviction algorithm
@@ -91,7 +91,7 @@ mark_free(struct drm_mm_scan *scan,
 int
 i915_gem_evict_something(struct i915_address_space *vm,
 			 u64 min_size, u64 alignment,
-			 unsigned cache_level,
+			 unsigned long color,
 			 u64 start, u64 end,
 			 unsigned flags)
 {
@@ -124,7 +124,7 @@ i915_gem_evict_something(struct i915_address_space *vm,
 	if (flags & PIN_MAPPABLE)
 		mode = DRM_MM_INSERT_LOW;
 	drm_mm_scan_init_with_range(&scan, &vm->mm,
-				    min_size, alignment, cache_level,
+				    min_size, alignment, color,
 				    start, end, mode);
 
 	/*
@@ -266,7 +266,6 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 	u64 start = target->start;
 	u64 end = start + target->size;
 	struct i915_vma *vma, *next;
-	bool check_color;
 	int ret = 0;
 
 	lockdep_assert_held(&vm->i915->drm.struct_mutex);
@@ -283,8 +282,7 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 	if (!(flags & PIN_NONBLOCK))
 		i915_retire_requests(vm->i915);
 
-	check_color = vm->mm.color_adjust;
-	if (check_color) {
+	if (i915_vm_has_cache_coloring(vm)) {
 		/* Expand search to cover neighbouring guard pages (or lack!) */
 		if (start)
 			start -= I915_GTT_PAGE_SIZE;
@@ -310,7 +308,7 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 		 * abutt and conflict. If they are in conflict, then we evict
 		 * those as well to make room for our guard pages.
 		 */
-		if (check_color) {
+		if (i915_vm_has_cache_coloring(vm)) {
 			if (node->start + node->size == target->start) {
 				if (node->color == target->color)
 					continue;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 07c85c134d4c..201788126a89 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -376,6 +376,12 @@ i915_vm_has_scratch_64K(struct i915_address_space *vm)
 	return vm->scratch_order == get_order(I915_GTT_PAGE_SIZE_64K);
 }
 
+static inline bool
+i915_vm_has_cache_coloring(struct i915_address_space *vm)
+{
+	return i915_is_ggtt(vm) && vm->mm.color_adjust;
+}
+
 /* The Graphics Translation Table is the way in which GEN hardware translates a
  * Graphics Virtual Address into a Physical Address. In addition to the normal
  * collateral associated with any va->pa translations GEN hardware also has a
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index a90bd2678353..68d9f9b4d050 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -477,7 +477,7 @@ void __i915_vma_set_map_and_fenceable(struct i915_vma *vma)
 		vma->flags &= ~I915_VMA_CAN_FENCE;
 }
 
-bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long cache_level)
+bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long color)
 {
 	struct drm_mm_node *node = &vma->node;
 	struct drm_mm_node *other;
@@ -489,7 +489,7 @@ bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long cache_level)
 	 * these constraints apply and set the drm_mm.color_adjust
 	 * appropriately.
 	 */
-	if (vma->vm->mm.color_adjust == NULL)
+	if (!i915_vm_has_cache_coloring(vma->vm))
 		return true;
 
 	/* Only valid to be called on an already inserted vma */
@@ -497,12 +497,12 @@ bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long cache_level)
 	GEM_BUG_ON(list_empty(&node->node_list));
 
 	other = list_prev_entry(node, node_list);
-	if (i915_node_color_differs(other, cache_level) &&
+	if (i915_node_color_differs(other, color) &&
 	    !drm_mm_hole_follows(other))
 		return false;
 
 	other = list_next_entry(node, node_list);
-	if (i915_node_color_differs(other, cache_level) &&
+	if (i915_node_color_differs(other, color) &&
 	    !drm_mm_hole_follows(node))
 		return false;
 
@@ -539,7 +539,7 @@ static int
 i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 {
 	struct drm_i915_private *dev_priv = vma->vm->i915;
-	unsigned int cache_level;
+	unsigned long color;
 	u64 start, end;
 	int ret;
 
@@ -580,14 +580,14 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		return -ENOSPC;
 	}
 
+	color = 0;
 	if (vma->obj) {
 		ret = i915_gem_object_pin_pages(vma->obj);
 		if (ret)
 			return ret;
 
-		cache_level = vma->obj->cache_level;
-	} else {
-		cache_level = 0;
+		if (i915_vm_has_cache_coloring(vma->vm))
+			color = vma->obj->cache_level;
 	}
 
 	GEM_BUG_ON(vma->pages);
@@ -605,7 +605,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		}
 
 		ret = i915_gem_gtt_reserve(vma->vm, &vma->node,
-					   size, offset, cache_level,
+					   size, offset, color,
 					   flags);
 		if (ret)
 			goto err_clear;
@@ -644,7 +644,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		}
 
 		ret = i915_gem_gtt_insert(vma->vm, &vma->node,
-					  size, alignment, cache_level,
+					  size, alignment, color,
 					  start, end, flags);
 		if (ret)
 			goto err_clear;
@@ -653,7 +653,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		GEM_BUG_ON(vma->node.start + vma->node.size > end);
 	}
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
-	GEM_BUG_ON(!i915_gem_valid_gtt_space(vma, cache_level));
+	GEM_BUG_ON(!i915_gem_valid_gtt_space(vma, color));
 
 	mutex_lock(&vma->vm->mutex);
 	list_move_tail(&vma->vm_link, &vma->vm->bound_list);
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 5b1e0cf7669d..425bda4db2c2 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -295,7 +295,7 @@ i915_vma_compare(struct i915_vma *vma,
 
 int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 		  u32 flags);
-bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long cache_level);
+bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long color);
 bool i915_vma_misplaced(const struct i915_vma *vma,
 			u64 size, u64 alignment, u64 flags);
 void __i915_vma_set_map_and_fenceable(struct i915_vma *vma);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index fca38167bdce..2905fb21d866 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -274,12 +274,14 @@ static int igt_evict_for_cache_color(void *arg)
 	LIST_HEAD(objects);
 	int err;
 
-	/* Currently the use of color_adjust is limited to cache domains within
-	 * the ggtt, and so the presence of mm.color_adjust is assumed to be
-	 * i915_ggtt_color_adjust throughout our driver, so using a mock color
-	 * adjust will work just fine for our purposes.
+	/*
+	 * Currently the use of color_adjust for the GGTT is limited to cache
+	 * coloring and guard pages, and so the presence of mm.color_adjust for
+	 * the GGTT is assumed to be i915_ggtt_color_adjust, hence using a mock
+	 * color adjust will work just fine for our purposes.
 	 */
 	ggtt->vm.mm.color_adjust = mock_color_adjust;
+	GEM_BUG_ON(!i915_vm_has_cache_coloring(&ggtt->vm));
 
 	obj = i915_gem_object_create_internal(i915, I915_GTT_PAGE_SIZE);
 	if (IS_ERR(obj)) {
-- 
cgit v1.2.3


From fd521d3b0ed2eb8b8c67c701795ecb08b9c3f544 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Mon, 9 Sep 2019 18:16:46 +0100
Subject: drm/i915: include GTT page-size info in error state

It might prove useful in the future to know if the vma is utilising
huge-GTT-pages. Related to this is the GTT cache, where there is some HW
"quirkiness" where it must be disabled if using 2M pages, so include
that for good measure.

Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190909171646.22090-1-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/gem/i915_gem_object_types.h |  1 -
 drivers/gpu/drm/i915/i915_gpu_error.c            | 10 ++++++++++
 drivers/gpu/drm/i915/i915_gpu_error.h            |  2 ++
 3 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index 13b9dc0e1a89..a558edf15ec8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -160,7 +160,6 @@ struct drm_i915_gem_object {
 		struct sg_table *pages;
 		void *mapping;
 
-		/* TODO: whack some of this into the error state */
 		struct i915_page_sizes {
 			/**
 			 * The sg mask of the pages sg_table. i.e the mask of
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 3ccf7fd9307f..6384a06aa5bf 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -575,6 +575,9 @@ static void print_error_obj(struct drm_i915_error_state_buf *m,
 			   lower_32_bits(obj->gtt_offset));
 	}
 
+	if (obj->gtt_page_sizes > I915_GTT_PAGE_SIZE_4K)
+		err_printf(m, "gtt_page_sizes = 0x%08x\n", obj->gtt_page_sizes);
+
 	err_compression_marker(m);
 	for (page = 0; page < obj->page_count; page++) {
 		int i, len;
@@ -735,6 +738,9 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
 	if (IS_GEN(m->i915, 7))
 		err_printf(m, "ERR_INT: 0x%08x\n", error->err_int);
 
+	if (IS_GEN_RANGE(m->i915, 8, 11))
+		err_printf(m, "GTT_CACHE_EN: 0x%08x\n", error->gtt_cache);
+
 	for (ee = error->engine; ee; ee = ee->next)
 		error_print_engine(m, ee, error->epoch);
 
@@ -985,6 +991,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 
 	dst->gtt_offset = vma->node.start;
 	dst->gtt_size = vma->node.size;
+	dst->gtt_page_sizes = vma->page_sizes.gtt;
 	dst->num_pages = num_pages;
 	dst->page_count = 0;
 	dst->unused = 0;
@@ -1554,6 +1561,9 @@ static void capture_reg_state(struct i915_gpu_state *error)
 		error->gac_eco = intel_uncore_read(uncore, GAC_ECO_BITS);
 	}
 
+	if (IS_GEN_RANGE(i915, 8, 11))
+		error->gtt_cache = intel_uncore_read(uncore, HSW_GTT_CACHE_EN);
+
 	/* 4: Everything else */
 	if (INTEL_GEN(i915) >= 11) {
 		error->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index df9f57766626..63cf387411e0 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -74,6 +74,7 @@ struct i915_gpu_state {
 	u32 gam_ecochk;
 	u32 gab_ctl;
 	u32 gfx_mode;
+	u32 gtt_cache;
 
 	u32 nfence;
 	u64 fence[I915_MAX_NUM_FENCES];
@@ -127,6 +128,7 @@ struct i915_gpu_state {
 		struct drm_i915_error_object {
 			u64 gtt_offset;
 			u64 gtt_size;
+			u32 gtt_page_sizes;
 			int num_pages;
 			int page_count;
 			int unused;
-- 
cgit v1.2.3


From fa9a09f15065650d97e3b1336d11e4ad9672b759 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 10 Sep 2019 09:02:08 +0100
Subject: drm/i915/execlists: Clear STOP_RING bit on reset

During reset, we try to ensure no forward progress of the CS prior to
the reset by setting the STOP_RING bit in RING_MI_MODE. Since gen9, this
register is context saved and do we end up in the odd situation where we
save the STOP_RING bit and so try to stop the engine again immediately
upon resume. This is quite unexpected and causes us to complain about an
early CS completion event!

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111514
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910080208.4223-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c     | 12 ++++++++++++
 drivers/gpu/drm/i915/gt/intel_lrc_reg.h |  2 ++
 2 files changed, 14 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index f073aea6a1fe..64170ce0c91b 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2368,6 +2368,17 @@ static struct i915_request *active_request(struct i915_request *rq)
 	return active;
 }
 
+static void __execlists_reset_reg_state(const struct intel_context *ce,
+					const struct intel_engine_cs *engine)
+{
+	u32 *regs = ce->lrc_reg_state;
+
+	if (INTEL_GEN(engine->i915) >= 9) {
+		regs[GEN9_CTX_RING_MI_MODE + 1] &= ~STOP_RING;
+		regs[GEN9_CTX_RING_MI_MODE + 1] |= STOP_RING << 16;
+	}
+}
+
 static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -2455,6 +2466,7 @@ out_replay:
 	GEM_TRACE("%s replay {head:%04x, tail:%04x\n",
 		  engine->name, ce->ring->head, ce->ring->tail);
 	intel_ring_update_space(ce->ring);
+	__execlists_reset_reg_state(ce, engine);
 	__execlists_update_reg_state(ce, engine);
 	mutex_release(&ce->pin_mutex.dep_map, 0, _THIS_IP_);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
index 68caf8541866..7e773e74a3fe 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
@@ -39,6 +39,8 @@
 #define CTX_R_PWR_CLK_STATE		0x42
 #define CTX_END				0x44
 
+#define GEN9_CTX_RING_MI_MODE		0x54
+
 /* GEN12+ Reg State Context */
 #define GEN12_CTX_BB_PER_CTX_PTR		0x12
 #define GEN12_CTX_LRI_HEADER_3			0x41
-- 
cgit v1.2.3


From b0a7c754140bee6a1124b5bfad17205149942fd7 Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Mon, 9 Sep 2019 17:31:41 +0530
Subject: drm/i915/display: Add gamma precision function for CHV

intel_color_get_gamma_bit_precision() is extended for
cherryview by adding chv_gamma_precision(), i965 will use existing
i9xx_gamma_precision() func only.

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1568030503-26747-2-git-send-email-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 6d641e159899..4d9a5686a4d7 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1400,6 +1400,14 @@ static int ilk_gamma_precision(const struct intel_crtc_state *crtc_state)
 	}
 }
 
+static int chv_gamma_precision(const struct intel_crtc_state *crtc_state)
+{
+	if (crtc_state->cgm_mode & CGM_PIPE_MODE_GAMMA)
+		return 10;
+	else
+		return i9xx_gamma_precision(crtc_state);
+}
+
 static int glk_gamma_precision(const struct intel_crtc_state *crtc_state)
 {
 	switch (crtc_state->gamma_mode) {
@@ -1421,12 +1429,17 @@ int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_stat
 	if (!crtc_state->gamma_enable)
 		return 0;
 
-	if (HAS_GMCH(dev_priv) && !IS_CHERRYVIEW(dev_priv))
-		return i9xx_gamma_precision(crtc_state);
-	else if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
-		return glk_gamma_precision(crtc_state);
-	else if (IS_IRONLAKE(dev_priv))
-		return ilk_gamma_precision(crtc_state);
+	if (HAS_GMCH(dev_priv)) {
+		if (IS_CHERRYVIEW(dev_priv))
+			return chv_gamma_precision(crtc_state);
+		else
+			return i9xx_gamma_precision(crtc_state);
+	} else {
+		if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+			return glk_gamma_precision(crtc_state);
+		else if (IS_IRONLAKE(dev_priv))
+			return ilk_gamma_precision(crtc_state);
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From 8efd06989df45fc81eb675e18e05b579bf064e8a Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Mon, 9 Sep 2019 17:31:42 +0530
Subject: drm/i915/display: Extract i965_read_luts()

For i965, add hw read out to create hw blob of gamma
lut values.

Review comments from old series:
https://patchwork.freedesktop.org/series/58039/

v4:  -No need to initialize *blob [Jani]
     -Removed right shifts [Jani]
     -Dropped dev local var [Jani]
v5:  -Returned blob instead of assigning it internally
      within the function [Ville]
     -Renamed i965_get_color_config() to i965_read_lut() [Ville]
     -Renamed i965_get_gamma_config_10p6() to i965_read_gamma_lut_10p6()
      [Ville]
v9:  -Typo and 80 character limit [Uma]
     -Made read func para as const [Ville, Uma]
     -Renamed i965_read_gamma_lut_10p6() to i965_read_lut_10p6() [Ville, Uma]
v10: -Swapped ldw and udw while creating hw blob [Jani]
     -Added last index rgb lut value from PIPEGCMAX to h/w blob [Jani]

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1568030503-26747-3-git-send-email-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 50 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_reg.h            |  4 +++
 2 files changed, 54 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 4d9a5686a4d7..765f858f66d7 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1569,6 +1569,55 @@ static void i9xx_read_luts(struct intel_crtc_state *crtc_state)
 	crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
 }
 
+static struct drm_property_blob *
+i965_read_lut_10p6(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	u32 lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
+	enum pipe pipe = crtc->pipe;
+	struct drm_property_blob *blob;
+	struct drm_color_lut *blob_data;
+	u32 i, val1, val2;
+
+	blob = drm_property_create_blob(&dev_priv->drm,
+					sizeof(struct drm_color_lut) * lut_size,
+					NULL);
+	if (IS_ERR(blob))
+		return NULL;
+
+	blob_data = blob->data;
+
+	for (i = 0; i < lut_size - 1; i++) {
+		val1 = I915_READ(PALETTE(pipe, 2 * i + 0));
+		val2 = I915_READ(PALETTE(pipe, 2 * i + 1));
+
+		blob_data[i].red = REG_FIELD_GET(PALETTE_RED_MASK, val2) << 8 |
+						 REG_FIELD_GET(PALETTE_RED_MASK, val1);
+		blob_data[i].green = REG_FIELD_GET(PALETTE_GREEN_MASK, val2) << 8 |
+						   REG_FIELD_GET(PALETTE_GREEN_MASK, val1);
+		blob_data[i].blue = REG_FIELD_GET(PALETTE_BLUE_MASK, val2) << 8 |
+						  REG_FIELD_GET(PALETTE_BLUE_MASK, val1);
+	}
+
+	blob_data[i].red = REG_FIELD_GET(PIPEGCMAX_RGB_MASK,
+					 I915_READ(PIPEGCMAX(pipe, 0)));
+	blob_data[i].green = REG_FIELD_GET(PIPEGCMAX_RGB_MASK,
+					   I915_READ(PIPEGCMAX(pipe, 1)));
+	blob_data[i].blue = REG_FIELD_GET(PIPEGCMAX_RGB_MASK,
+					  I915_READ(PIPEGCMAX(pipe, 2)));
+
+	return blob;
+}
+
+static void i965_read_luts(struct intel_crtc_state *crtc_state)
+{
+	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
+		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+	else
+		crtc_state->base.gamma_lut = i965_read_lut_10p6(crtc_state);
+}
+
 static struct drm_property_blob *
 ilk_read_lut_10(const struct intel_crtc_state *crtc_state)
 {
@@ -1672,6 +1721,7 @@ void intel_color_init(struct intel_crtc *crtc)
 			dev_priv->display.color_check = i9xx_color_check;
 			dev_priv->display.color_commit = i9xx_color_commit;
 			dev_priv->display.load_luts = i965_load_luts;
+			dev_priv->display.read_luts = i965_read_luts;
 		} else {
 			dev_priv->display.color_check = i9xx_color_check;
 			dev_priv->display.color_commit = i9xx_color_commit;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 006cffd56be2..1dc5487593f1 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3558,6 +3558,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define _PALETTE_A		0xa000
 #define _PALETTE_B		0xa800
 #define _CHV_PALETTE_C		0xc000
+#define PALETTE_RED_MASK        REG_GENMASK(23, 16)
+#define PALETTE_GREEN_MASK      REG_GENMASK(15, 8)
+#define PALETTE_BLUE_MASK       REG_GENMASK(7, 0)
 #define PALETTE(pipe, i)	_MMIO(DISPLAY_MMIO_BASE(dev_priv) + \
 				      _PICK((pipe), _PALETTE_A,		\
 					    _PALETTE_B, _CHV_PALETTE_C) + \
@@ -5767,6 +5770,7 @@ enum {
 
 #define  _PIPEAGCMAX           0x70010
 #define  _PIPEBGCMAX           0x71010
+#define PIPEGCMAX_RGB_MASK     REG_GENMASK(15, 0)
 #define PIPEGCMAX(pipe, i)     _MMIO_PIPE2(pipe, _PIPEAGCMAX + (i) * 4)
 
 #define _PIPE_MISC_A			0x70030
-- 
cgit v1.2.3


From 4d154d33941dad07b9bb49c9dee356342a98e00a Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Mon, 9 Sep 2019 17:31:43 +0530
Subject: drm/i915/display: Extract chv_read_luts()

For cherryview, add hw read out to create hw blob of gamma
lut values.

Review comments from previous series:
https://patchwork.freedesktop.org/patch/328252

v4: -No need to initialize *blob [Jani]
    -Removed right shifts [Jani]
    -Dropped dev local var [Jani]
v5: -Returned blob instead of assigning it internally within the
     function [Ville]
    -Renamed function cherryview_get_color_config() to chv_read_luts()
    -Renamed cherryview_get_gamma_config() to chv_read_cgm_gamma_lut()
     [Ville]
v9: -80 character limit [Uma]
    -Made read func para as const [Ville, Uma]
    -Renamed chv_read_cgm_gamma_lut() to chv_read_cgm_gamma_lut()
     [Ville, Uma]

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1568030503-26747-4-git-send-email-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 43 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_reg.h            |  3 +++
 2 files changed, 46 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 765f858f66d7..318308dc136c 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1618,6 +1618,48 @@ static void i965_read_luts(struct intel_crtc_state *crtc_state)
 		crtc_state->base.gamma_lut = i965_read_lut_10p6(crtc_state);
 }
 
+static struct drm_property_blob *
+chv_read_cgm_lut(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	u32 lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
+	enum pipe pipe = crtc->pipe;
+	struct drm_property_blob *blob;
+	struct drm_color_lut *blob_data;
+	u32 i, val;
+
+	blob = drm_property_create_blob(&dev_priv->drm,
+					sizeof(struct drm_color_lut) * lut_size,
+					NULL);
+	if (IS_ERR(blob))
+		return NULL;
+
+	blob_data = blob->data;
+
+	for (i = 0; i < lut_size; i++) {
+		val = I915_READ(CGM_PIPE_GAMMA(pipe, i, 0));
+		blob_data[i].green = intel_color_lut_pack(REG_FIELD_GET(
+							  CGM_PIPE_GAMMA_GREEN_MASK, val), 10);
+		blob_data[i].blue = intel_color_lut_pack(REG_FIELD_GET(
+							 CGM_PIPE_GAMMA_BLUE_MASK, val), 10);
+
+		val = I915_READ(CGM_PIPE_GAMMA(pipe, i, 1));
+		blob_data[i].red = intel_color_lut_pack(REG_FIELD_GET(
+							CGM_PIPE_GAMMA_RED_MASK, val), 10);
+	}
+
+	return blob;
+}
+
+static void chv_read_luts(struct intel_crtc_state *crtc_state)
+{
+	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
+		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+	else
+		crtc_state->base.gamma_lut = chv_read_cgm_lut(crtc_state);
+}
+
 static struct drm_property_blob *
 ilk_read_lut_10(const struct intel_crtc_state *crtc_state)
 {
@@ -1717,6 +1759,7 @@ void intel_color_init(struct intel_crtc *crtc)
 			dev_priv->display.color_check = chv_color_check;
 			dev_priv->display.color_commit = i9xx_color_commit;
 			dev_priv->display.load_luts = chv_load_luts;
+			dev_priv->display.read_luts = chv_read_luts;
 		} else if (INTEL_GEN(dev_priv) >= 4) {
 			dev_priv->display.color_check = i9xx_color_check;
 			dev_priv->display.color_commit = i9xx_color_commit;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 1dc5487593f1..bf37ecebc82f 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -10421,6 +10421,9 @@ enum skl_power_gate {
 #define   CGM_PIPE_MODE_GAMMA	(1 << 2)
 #define   CGM_PIPE_MODE_CSC	(1 << 1)
 #define   CGM_PIPE_MODE_DEGAMMA	(1 << 0)
+#define   CGM_PIPE_GAMMA_RED_MASK   REG_GENMASK(9, 0)
+#define   CGM_PIPE_GAMMA_GREEN_MASK REG_GENMASK(25, 16)
+#define   CGM_PIPE_GAMMA_BLUE_MASK  REG_GENMASK(9, 0)
 
 #define _CGM_PIPE_B_CSC_COEFF01	(VLV_DISPLAY_BASE + 0x69900)
 #define _CGM_PIPE_B_CSC_COEFF23	(VLV_DISPLAY_BASE + 0x69904)
-- 
cgit v1.2.3


From 198d2533669bbe162e52eee2c35ddd8594967556 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 7 Sep 2019 09:43:34 +0100
Subject: drm/i915/execlists: Ignore lost completion events

Icelake hit an issue where it missed reporting a completion event and
instead jumped straight to a idle->active event (skipping over the
active->idle and not even hitting the lite-restore preemption).

661497511us : process_csb: rcs0 cs-irq head=11, tail=0
661497512us : process_csb: rcs0 csb[0]: status=0x10008002:0x00000020 [lite-restore]
661497512us : trace_ports: rcs0: preempted { 28cc8:11052, 0:0 }
661497513us : trace_ports: rcs0: promote { 28cc8:11054, 0:0 }
661497514us : __i915_request_submit: rcs0 fence 28cc8:11056, current 11052
661497514us : __execlists_submission_tasklet: rcs0: queue_priority_hint:-2147483648, submit:yes
661497515us : trace_ports: rcs0: submit { 28cc8:11056, 0:0 }
661497530us : process_csb: rcs0 cs-irq head=0, tail=1
661497530us : process_csb: rcs0 csb[1]: status=0x10008002:0x00000020 [lite-restore]
661497531us : trace_ports: rcs0: preempted { 28cc8:11054!, 0:0 }
661497535us : trace_ports: rcs0: promote { 28cc8:11056, 0:0 }
661497540us : __i915_request_submit: rcs0 fence 28cc8:11058, current 11054
661497544us : __execlists_submission_tasklet: rcs0: queue_priority_hint:-2147483648, submit:yes
661497545us : trace_ports: rcs0: submit { 28cc8:11058, 0:0 }
661497553us : process_csb: rcs0 cs-irq head=1, tail=2
661497553us : process_csb: rcs0 csb[2]: status=0x10000001:0x00000000 [idle->active]
661497574us : process_csb: process_csb:1538 GEM_BUG_ON(*execlists->active)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190907084334.28952-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 63 +++++++++++--------------------------
 1 file changed, 18 insertions(+), 45 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 64170ce0c91b..dcdf7cf66e7e 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -692,6 +692,9 @@ trace_ports(const struct intel_engine_execlists *execlists,
 	const struct intel_engine_cs *engine =
 		container_of(execlists, typeof(*engine), execlists);
 
+	if (!ports[0])
+		return;
+
 	GEM_TRACE("%s: %s { %llx:%lld%s, %llx:%lld }\n",
 		  engine->name, msg,
 		  ports[0]->fence.context,
@@ -1380,13 +1383,6 @@ reset_in_progress(const struct intel_engine_execlists *execlists)
 	return unlikely(!__tasklet_is_enabled(&execlists->tasklet));
 }
 
-enum csb_step {
-	CSB_NOP,
-	CSB_PROMOTE,
-	CSB_PREEMPT,
-	CSB_COMPLETE,
-};
-
 /*
  * Starting with Gen12, the status has a new format:
  *
@@ -1413,7 +1409,7 @@ enum csb_step {
  *     bits 47-57: sw context id of the lrc the GT switched away from
  *     bits 58-63: sw counter of the lrc the GT switched away from
  */
-static inline enum csb_step
+static inline bool
 gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
 {
 	u32 lower_dw = csb[0];
@@ -1423,7 +1419,7 @@ gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
 	bool new_queue = lower_dw & GEN12_CTX_STATUS_SWITCHED_TO_NEW_QUEUE;
 
 	if (!ctx_away_valid && ctx_to_valid)
-		return CSB_PROMOTE;
+		return true;
 
 	/*
 	 * The context switch detail is not guaranteed to be 5 when a preemption
@@ -1433,7 +1429,7 @@ gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
 	 * would require some extra handling, but we don't support that.
 	 */
 	if (new_queue && ctx_away_valid)
-		return CSB_PREEMPT;
+		return true;
 
 	/*
 	 * switch detail = 5 is covered by the case above and we do not expect a
@@ -1442,29 +1438,13 @@ gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
 	 */
 	GEM_BUG_ON(GEN12_CTX_SWITCH_DETAIL(upper_dw));
 
-	if (*execlists->active) {
-		GEM_BUG_ON(!ctx_away_valid);
-		return CSB_COMPLETE;
-	}
-
-	return CSB_NOP;
+	return false;
 }
 
-static inline enum csb_step
+static inline bool
 gen8_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
 {
-	unsigned int status = *csb;
-
-	if (status & GEN8_CTX_STATUS_IDLE_ACTIVE)
-		return CSB_PROMOTE;
-
-	if (status & GEN8_CTX_STATUS_PREEMPTED)
-		return CSB_PREEMPT;
-
-	if (*execlists->active)
-		return CSB_COMPLETE;
-
-	return CSB_NOP;
+	return *csb & (GEN8_CTX_STATUS_IDLE_ACTIVE | GEN8_CTX_STATUS_PREEMPTED);
 }
 
 static void process_csb(struct intel_engine_cs *engine)
@@ -1503,7 +1483,7 @@ static void process_csb(struct intel_engine_cs *engine)
 	rmb();
 
 	do {
-		enum csb_step csb_step;
+		bool promote;
 
 		if (++head == num_entries)
 			head = 0;
@@ -1531,20 +1511,16 @@ static void process_csb(struct intel_engine_cs *engine)
 			  buf[2 * head + 0], buf[2 * head + 1]);
 
 		if (INTEL_GEN(engine->i915) >= 12)
-			csb_step = gen12_csb_parse(execlists, buf + 2 * head);
+			promote = gen12_csb_parse(execlists, buf + 2 * head);
 		else
-			csb_step = gen8_csb_parse(execlists, buf + 2 * head);
-
-		switch (csb_step) {
-		case CSB_PREEMPT: /* cancel old inflight, prepare for switch */
+			promote = gen8_csb_parse(execlists, buf + 2 * head);
+		if (promote) {
+			/* cancel old inflight, prepare for switch */
 			trace_ports(execlists, "preempted", execlists->active);
-
 			while (*execlists->active)
 				execlists_schedule_out(*execlists->active++);
 
-			/* fallthrough */
-		case CSB_PROMOTE: /* switch pending to inflight */
-			GEM_BUG_ON(*execlists->active);
+			/* switch pending to inflight */
 			GEM_BUG_ON(!assert_pending_valid(execlists, "promote"));
 			execlists->active =
 				memcpy(execlists->inflight,
@@ -1559,9 +1535,10 @@ static void process_csb(struct intel_engine_cs *engine)
 				ring_set_paused(engine, 0);
 
 			WRITE_ONCE(execlists->pending[0], NULL);
-			break;
+		} else {
+			GEM_BUG_ON(!*execlists->active);
 
-		case CSB_COMPLETE: /* port0 completed, advanced to port1 */
+			/* port0 completed, advanced to port1 */
 			trace_ports(execlists, "completed", execlists->active);
 
 			/*
@@ -1576,10 +1553,6 @@ static void process_csb(struct intel_engine_cs *engine)
 
 			GEM_BUG_ON(execlists->active - execlists->inflight >
 				   execlists_num_ports(execlists));
-			break;
-
-		case CSB_NOP:
-			break;
 		}
 	} while (head != tail);
 
-- 
cgit v1.2.3


From 0efa99dd58754d23e884b9ba41cd601f01b58c3d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 9 Sep 2019 12:30:18 +0100
Subject: drm/i915/ringbuffer: Flush writes before RING_TAIL update

Be paranoid and make sure we flush any and all writes out of the WCB
before performing the UC mmio to update the RING_TAIL. (An UC write
should itself be enough to do the flush, hence the paranoia here.) Quite
infrequently, we see problems where the GPU seems to overshoot the
RING_TAIL and so executes garbage, hence the speculation.

References: https://bugs.freedesktop.org/show_bug.cgi?id=111598
References: https://bugs.freedesktop.org/show_bug.cgi?id=111417
References: https://bugs.freedesktop.org/show_bug.cgi?id=111034
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190909113018.13300-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index ac55a0d054bd..a73296e6b13d 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -930,6 +930,7 @@ static void cancel_requests(struct intel_engine_cs *engine)
 static void i9xx_submit_request(struct i915_request *request)
 {
 	i915_request_submit(request);
+	wmb(); /* paranoid flush writes out of the WCB before mmio */
 
 	ENGINE_WRITE(request->engine, RING_TAIL,
 		     intel_ring_set_tail(request->ring, request->tail));
-- 
cgit v1.2.3


From cec5ca08e36fd18d2939b98055346b3b06f56c6c Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 9 Sep 2019 12:00:08 +0100
Subject: drm/i915: Perform GGTT restore much earlier during resume

As soon as we re-enable the various functions within the HW, they may go
off and read data via a GGTT offset. Hence, if we have not yet restored
the GGTT PTE before then, they may read and even *write* random locations
in memory.

Detected by DMAR faults during resume.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Martin Peres <martin.peres@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190909110011.8958-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_pm.c    | 3 ---
 drivers/gpu/drm/i915/i915_drv.c           | 5 +++++
 drivers/gpu/drm/i915/selftests/i915_gem.c | 6 ++++++
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index b3993d24b83d..9b1129aaacfe 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -242,9 +242,6 @@ void i915_gem_resume(struct drm_i915_private *i915)
 	mutex_lock(&i915->drm.struct_mutex);
 	intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
 
-	i915_gem_restore_gtt_mappings(i915);
-	i915_gem_restore_fences(i915);
-
 	if (i915_gem_init_hw(i915))
 		goto err_wedged;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 63e52e153414..0aadff9b8c88 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1914,6 +1914,11 @@ static int i915_drm_resume(struct drm_device *dev)
 	if (ret)
 		DRM_ERROR("failed to re-enable GGTT\n");
 
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	i915_gem_restore_gtt_mappings(dev_priv);
+	i915_gem_restore_fences(dev_priv);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
 	intel_csr_ucode_resume(dev_priv);
 
 	i915_restore_state(dev_priv);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index bb6dd54a6ff3..37593831b539 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -118,6 +118,12 @@ static void pm_resume(struct drm_i915_private *i915)
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
 		intel_gt_sanitize(&i915->gt, false);
 		i915_gem_sanitize(i915);
+
+		mutex_lock(&i915->drm.struct_mutex);
+		i915_gem_restore_gtt_mappings(i915);
+		i915_gem_restore_fences(i915);
+		mutex_unlock(&i915->drm.struct_mutex);
+
 		i915_gem_resume(i915);
 	}
 }
-- 
cgit v1.2.3


From 7c465310fefc6a600eb69521b8420564f0f37b2d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 9 Sep 2019 12:00:06 +0100
Subject: drm/i915/selftests: Take runtime wakeref for igt_ggtt_lowlevel

Being a "low-level" test, we opt to bypass the normal bind/unbind hooks
for the lower level insert_entries/clear_range. For ggtt, the
bind/unbind hooks provide the runtime wakeref and so we must also handle
this in exercising the low level hooks.

<4> [538.151672] RPM raw-wakeref not held
<4> [538.151825] WARNING: CPU: 0 PID: 11 at ./drivers/gpu/drm/i915/intel_runtime_pm.h:107 fwtable_read32+0x1be/0x300 [i915]
<4> [538.151830] Modules linked in: i915(+) amdgpu gpu_sched ttm vgem snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic mei_hdcp btusb btrtl btbcm x86_pkg_temp_thermal coretemp btintel crct10dif_pclmul bluetooth crc32_pclmul snd_intel_nhlt snd_hda_codec ecdh_generic ghash_clmulni_intel ecc snd_hwdep snd_hda_core lpc_ich r8169 realtek snd_pcm mei_me mei prime_numbers pinctrl_broxton pinctrl_intel [last unloaded: i915]
<4> [538.151861] CPU: 0 PID: 11 Comm: migration/0 Tainted: G     U            5.3.0-rc7-CI-Trybot_4938+ #1
<4> [538.151864] Hardware name: Intel corporation NUC6CAYS/NUC6CAYB, BIOS AYAPLCEL.86A.0056.2018.0926.1100 09/26/2018
<4> [538.151960] RIP: 0010:fwtable_read32+0x1be/0x300 [i915]
<4> [538.151965] Code: e8 e7 f9 5f e0 e9 0b ff ff ff 80 3d d5 8d 26 00 00 0f 85 81 fe ff ff 48 c7 c7 ef 01 bd a0 c6 05 c1 8d 26 00 01 e8 b2 e4 6a e0 <0f> 0b e9 67 fe ff ff 80 3d ad 8d 26 00 00 0f 85 65 fe ff ff 48 c7
<4> [538.151969] RSP: 0018:ffffc9000007be10 EFLAGS: 00010086
<4> [538.151972] RAX: 0000000000000000 RBX: ffff88826be10d50 RCX: 0000000000000002
<4> [538.151975] RDX: 0000000080000002 RSI: 0000000000000000 RDI: 00000000ffffffff
<4> [538.151978] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
<4> [538.151981] R10: 0000000000000000 R11: ffffc9000007bcb0 R12: 0000000000101008
<4> [538.151984] R13: 0000000000000000 R14: ffffc9000036f638 R15: 0000000000000002
<4> [538.151987] FS:  0000000000000000(0000) GS:ffff888277a00000(0000) knlGS:0000000000000000
<4> [538.151990] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
<4> [538.151993] CR2: 00007fd48e7052f8 CR3: 0000000005210000 CR4: 00000000003406f0
<4> [538.151995] Call Trace:
<4> [538.152106]  bxt_vtd_ggtt_clear_range__cb+0x38/0x40 [i915]

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190909110011.8958-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 31a51ca1ddcb..598c18d10640 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -293,18 +293,20 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 			mock_vma.node.size = BIT_ULL(size);
 			mock_vma.node.start = addr;
 
-			wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-			vm->insert_entries(vm, &mock_vma, I915_CACHE_NONE, 0);
-			intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+			with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+				vm->insert_entries(vm, &mock_vma,
+						   I915_CACHE_NONE, 0);
 		}
 		count = n;
 
 		i915_random_reorder(order, count, &prng);
 		for (n = 0; n < count; n++) {
 			u64 addr = hole_start + order[n] * BIT_ULL(size);
+			intel_wakeref_t wakeref;
 
 			GEM_BUG_ON(addr + BIT_ULL(size) > vm->total);
-			vm->clear_range(vm, addr, BIT_ULL(size));
+			with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+				vm->clear_range(vm, addr, BIT_ULL(size));
 		}
 
 		i915_gem_object_unpin_pages(obj);
-- 
cgit v1.2.3


From 07e98eb0a17482557198ae12a07a6e3a89de33a3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 10 Sep 2019 13:10:09 +0100
Subject: drm/i915/selftests: Tighten the timeout testing for partial mmaps

Currently, if there is time remaining before the start of the loop, we
do one full iteration over many possible different chunks within the
object. A full loop may take 50+s (depending on speed of indirect GTT
mmapings) and we try separately with LINEAR, X and Y -- at which point
igt times out. If we check more frequently, we will interrupt the loop
upon our timeout -- it is hard to argue for as this significantly reduces
the test coverage as we dramatically reduce the runtime. In practical
terms, the coverage we should prioritise is in using different fence
setups, forcing verification of the tile row computations over the
current preference of checking extracting chunks. Though the exhaustive
search is great given an infinite timeout, to improve our current
coverage, we also add a randomised smoketest of partial mmaps. So let's
do both, add a randomised smoketest of partial tiling chunks and the
exhaustive (though time limited) search for failures.

Even in adding another subtest, we should shave 100s off BAT! (With,
hopefully, no loss in coverage, at least over multiple runs.)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910121009.13431-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c | 255 ++++++++++++++++++---
 1 file changed, 223 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 1d27babff0ce..aefe557527f8 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -10,6 +10,7 @@
 #include "gt/intel_gt_pm.h"
 #include "huge_gem_object.h"
 #include "i915_selftest.h"
+#include "selftests/i915_random.h"
 #include "selftests/igt_flush_test.h"
 
 struct tile {
@@ -76,18 +77,103 @@ static u64 tiled_offset(const struct tile *tile, u64 v)
 
 static int check_partial_mapping(struct drm_i915_gem_object *obj,
 				 const struct tile *tile,
-				 unsigned long end_time)
+				 struct rnd_state *prng)
 {
-	const unsigned int nreal = obj->scratch / PAGE_SIZE;
 	const unsigned long npages = obj->base.size / PAGE_SIZE;
+	struct i915_ggtt_view view;
 	struct i915_vma *vma;
 	unsigned long page;
+	u32 __iomem *io;
+	struct page *p;
+	unsigned int n;
+	u64 offset;
+	u32 *cpu;
 	int err;
 
-	if (igt_timeout(end_time,
-			"%s: timed out before tiling=%d stride=%d\n",
-			__func__, tile->tiling, tile->stride))
-		return -EINTR;
+	err = i915_gem_object_set_tiling(obj, tile->tiling, tile->stride);
+	if (err) {
+		pr_err("Failed to set tiling mode=%u, stride=%u, err=%d\n",
+		       tile->tiling, tile->stride, err);
+		return err;
+	}
+
+	GEM_BUG_ON(i915_gem_object_get_tiling(obj) != tile->tiling);
+	GEM_BUG_ON(i915_gem_object_get_stride(obj) != tile->stride);
+
+	i915_gem_object_lock(obj);
+	err = i915_gem_object_set_to_gtt_domain(obj, true);
+	i915_gem_object_unlock(obj);
+	if (err) {
+		pr_err("Failed to flush to GTT write domain; err=%d\n", err);
+		return err;
+	}
+
+	page = i915_prandom_u32_max_state(npages, prng);
+	view = compute_partial_view(obj, page, MIN_CHUNK_PAGES);
+
+	vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, PIN_MAPPABLE);
+	if (IS_ERR(vma)) {
+		pr_err("Failed to pin partial view: offset=%lu; err=%d\n",
+		       page, (int)PTR_ERR(vma));
+		return PTR_ERR(vma);
+	}
+
+	n = page - view.partial.offset;
+	GEM_BUG_ON(n >= view.partial.size);
+
+	io = i915_vma_pin_iomap(vma);
+	i915_vma_unpin(vma);
+	if (IS_ERR(io)) {
+		pr_err("Failed to iomap partial view: offset=%lu; err=%d\n",
+		       page, (int)PTR_ERR(io));
+		err = PTR_ERR(io);
+		goto out;
+	}
+
+	iowrite32(page, io + n * PAGE_SIZE / sizeof(*io));
+	i915_vma_unpin_iomap(vma);
+
+	offset = tiled_offset(tile, page << PAGE_SHIFT);
+	if (offset >= obj->base.size)
+		goto out;
+
+	intel_gt_flush_ggtt_writes(&to_i915(obj->base.dev)->gt);
+
+	p = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
+	cpu = kmap(p) + offset_in_page(offset);
+	drm_clflush_virt_range(cpu, sizeof(*cpu));
+	if (*cpu != (u32)page) {
+		pr_err("Partial view for %lu [%u] (offset=%llu, size=%u [%llu, row size %u], fence=%d, tiling=%d, stride=%d) misalignment, expected write to page (%llu + %u [0x%llx]) of 0x%x, found 0x%x\n",
+		       page, n,
+		       view.partial.offset,
+		       view.partial.size,
+		       vma->size >> PAGE_SHIFT,
+		       tile->tiling ? tile_row_pages(obj) : 0,
+		       vma->fence ? vma->fence->id : -1, tile->tiling, tile->stride,
+		       offset >> PAGE_SHIFT,
+		       (unsigned int)offset_in_page(offset),
+		       offset,
+		       (u32)page, *cpu);
+		err = -EINVAL;
+	}
+	*cpu = 0;
+	drm_clflush_virt_range(cpu, sizeof(*cpu));
+	kunmap(p);
+
+out:
+	i915_vma_destroy(vma);
+	return err;
+}
+
+static int check_partial_mappings(struct drm_i915_gem_object *obj,
+				  const struct tile *tile,
+				  unsigned long end_time)
+{
+	const unsigned int nreal = obj->scratch / PAGE_SIZE;
+	const unsigned long npages = obj->base.size / PAGE_SIZE;
+	struct i915_vma *vma;
+	unsigned long page;
+	int err;
 
 	err = i915_gem_object_set_tiling(obj, tile->tiling, tile->stride);
 	if (err) {
@@ -170,11 +256,42 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj,
 			return err;
 
 		i915_vma_destroy(vma);
+
+		if (igt_timeout(end_time,
+				"%s: timed out after tiling=%d stride=%d\n",
+				__func__, tile->tiling, tile->stride))
+			return -EINTR;
 	}
 
 	return 0;
 }
 
+static unsigned int
+setup_tile_size(struct tile *tile, struct drm_i915_private *i915)
+{
+	if (INTEL_GEN(i915) <= 2) {
+		tile->height = 16;
+		tile->width = 128;
+		tile->size = 11;
+	} else if (tile->tiling == I915_TILING_Y &&
+		   HAS_128_BYTE_Y_TILING(i915)) {
+		tile->height = 32;
+		tile->width = 128;
+		tile->size = 12;
+	} else {
+		tile->height = 8;
+		tile->width = 512;
+		tile->size = 12;
+	}
+
+	if (INTEL_GEN(i915) < 4)
+		return 8192 / tile->width;
+	else if (INTEL_GEN(i915) < 7)
+		return 128 * I965_FENCE_MAX_PITCH_VAL / tile->width;
+	else
+		return 128 * GEN7_FENCE_MAX_PITCH_VAL / tile->width;
+}
+
 static int igt_partial_tiling(void *arg)
 {
 	const unsigned int nreal = 1 << 12; /* largest tile row x2 */
@@ -219,7 +336,7 @@ static int igt_partial_tiling(void *arg)
 		tile.swizzle = I915_BIT_6_SWIZZLE_NONE;
 		tile.tiling = I915_TILING_NONE;
 
-		err = check_partial_mapping(obj, &tile, end);
+		err = check_partial_mappings(obj, &tile, end);
 		if (err && err != -EINTR)
 			goto out_unlock;
 	}
@@ -253,31 +370,11 @@ static int igt_partial_tiling(void *arg)
 		    tile.swizzle == I915_BIT_6_SWIZZLE_9_10_17)
 			continue;
 
-		if (INTEL_GEN(i915) <= 2) {
-			tile.height = 16;
-			tile.width = 128;
-			tile.size = 11;
-		} else if (tile.tiling == I915_TILING_Y &&
-			   HAS_128_BYTE_Y_TILING(i915)) {
-			tile.height = 32;
-			tile.width = 128;
-			tile.size = 12;
-		} else {
-			tile.height = 8;
-			tile.width = 512;
-			tile.size = 12;
-		}
-
-		if (INTEL_GEN(i915) < 4)
-			max_pitch = 8192 / tile.width;
-		else if (INTEL_GEN(i915) < 7)
-			max_pitch = 128 * I965_FENCE_MAX_PITCH_VAL / tile.width;
-		else
-			max_pitch = 128 * GEN7_FENCE_MAX_PITCH_VAL / tile.width;
+		max_pitch = setup_tile_size(&tile, i915);
 
 		for (pitch = max_pitch; pitch; pitch >>= 1) {
 			tile.stride = tile.width * pitch;
-			err = check_partial_mapping(obj, &tile, end);
+			err = check_partial_mappings(obj, &tile, end);
 			if (err == -EINTR)
 				goto next_tiling;
 			if (err)
@@ -285,7 +382,7 @@ static int igt_partial_tiling(void *arg)
 
 			if (pitch > 2 && INTEL_GEN(i915) >= 4) {
 				tile.stride = tile.width * (pitch - 1);
-				err = check_partial_mapping(obj, &tile, end);
+				err = check_partial_mappings(obj, &tile, end);
 				if (err == -EINTR)
 					goto next_tiling;
 				if (err)
@@ -294,7 +391,7 @@ static int igt_partial_tiling(void *arg)
 
 			if (pitch < max_pitch && INTEL_GEN(i915) >= 4) {
 				tile.stride = tile.width * (pitch + 1);
-				err = check_partial_mapping(obj, &tile, end);
+				err = check_partial_mappings(obj, &tile, end);
 				if (err == -EINTR)
 					goto next_tiling;
 				if (err)
@@ -305,7 +402,7 @@ static int igt_partial_tiling(void *arg)
 		if (INTEL_GEN(i915) >= 4) {
 			for_each_prime_number(pitch, max_pitch) {
 				tile.stride = tile.width * pitch;
-				err = check_partial_mapping(obj, &tile, end);
+				err = check_partial_mappings(obj, &tile, end);
 				if (err == -EINTR)
 					goto next_tiling;
 				if (err)
@@ -325,6 +422,99 @@ out:
 	return err;
 }
 
+static int igt_smoke_tiling(void *arg)
+{
+	const unsigned int nreal = 1 << 12; /* largest tile row x2 */
+	struct drm_i915_private *i915 = arg;
+	struct drm_i915_gem_object *obj;
+	intel_wakeref_t wakeref;
+	I915_RND_STATE(prng);
+	unsigned long count;
+	IGT_TIMEOUT(end);
+	int err;
+
+	/*
+	 * igt_partial_tiling() does an exhastive check of partial tiling
+	 * chunking, but will undoubtably run out of time. Here, we do a
+	 * randomised search and hope over many runs of 1s with different
+	 * seeds we will do a thorough check.
+	 *
+	 * Remember to look at the st_seed if we see a flip-flop in BAT!
+	 */
+
+	if (i915->quirks & QUIRK_PIN_SWIZZLED_PAGES)
+		return 0;
+
+	obj = huge_gem_object(i915,
+			      nreal << PAGE_SHIFT,
+			      (1 + next_prime_number(i915->ggtt.vm.total >> PAGE_SHIFT)) << PAGE_SHIFT);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	err = i915_gem_object_pin_pages(obj);
+	if (err) {
+		pr_err("Failed to allocate %u pages (%lu total), err=%d\n",
+		       nreal, obj->base.size / PAGE_SIZE, err);
+		goto out;
+	}
+
+	mutex_lock(&i915->drm.struct_mutex);
+	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
+
+	count = 0;
+	do {
+		struct tile tile;
+
+		tile.tiling =
+			i915_prandom_u32_max_state(I915_TILING_Y + 1, &prng);
+		switch (tile.tiling) {
+		case I915_TILING_NONE:
+			tile.height = 1;
+			tile.width = 1;
+			tile.size = 0;
+			tile.stride = 0;
+			tile.swizzle = I915_BIT_6_SWIZZLE_NONE;
+			break;
+
+		case I915_TILING_X:
+			tile.swizzle = i915->mm.bit_6_swizzle_x;
+			break;
+		case I915_TILING_Y:
+			tile.swizzle = i915->mm.bit_6_swizzle_y;
+			break;
+		}
+
+		if (tile.swizzle == I915_BIT_6_SWIZZLE_9_17 ||
+		    tile.swizzle == I915_BIT_6_SWIZZLE_9_10_17)
+			continue;
+
+		if (tile.tiling != I915_TILING_NONE) {
+			unsigned int max_pitch = setup_tile_size(&tile, i915);
+
+			tile.stride =
+				i915_prandom_u32_max_state(max_pitch, &prng);
+			tile.stride = (1 + tile.stride) * tile.width;
+			if (INTEL_GEN(i915) < 4)
+				tile.stride = rounddown_pow_of_two(tile.stride);
+		}
+
+		err = check_partial_mapping(obj, &tile, &prng);
+		if (err)
+			break;
+
+		count++;
+	} while (!__igt_timeout(end, NULL));
+
+	pr_info("%s: Completed %lu trials\n", __func__, count);
+
+	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+	mutex_unlock(&i915->drm.struct_mutex);
+	i915_gem_object_unpin_pages(obj);
+out:
+	i915_gem_object_put(obj);
+	return err;
+}
+
 static int make_obj_busy(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
@@ -515,6 +705,7 @@ int i915_gem_mman_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_partial_tiling),
+		SUBTEST(igt_smoke_tiling),
 		SUBTEST(igt_mmap_offset_exhaustion),
 	};
 
-- 
cgit v1.2.3


From ab37c4d712c8b35c0c1e3237e04fe49f717055a4 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 10 Sep 2019 17:16:57 +0100
Subject: drm/i915/tgl: Disable rc6 for debugging

Empirical evidence from CI tells us that our rc6 setup for Tigerlake is
off. Disable rc6 on tgl temporary so that we gain CI coverage as we
prepare a fix. It also appears that the BIOS on our tgl leaves rc6
enabled, so we have to explicitly disable it on init.

References: https://bugs.freedesktop.org/show_bug.cgi?id=111593
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910161657.23037-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_pci.c | 1 +
 drivers/gpu/drm/i915/intel_pm.c | 3 +--
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index fbe98a2db88e..b3cc8560696b 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -797,6 +797,7 @@ static const struct intel_device_info intel_tigerlake_12_info = {
 	.display.has_modular_fia = 1,
 	.engine_mask =
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2),
+	.has_rc6 = false, /* XXX disabled for debugging */
 };
 
 #undef GEN
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 528e90ed5de4..54a8b7705bc6 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -8671,8 +8671,7 @@ void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
 {
 	mutex_lock(&dev_priv->gt_pm.rps.lock);
 
-	if (HAS_RC6(dev_priv))
-		intel_disable_rc6(dev_priv);
+	intel_disable_rc6(dev_priv);
 
 	intel_disable_rps(dev_priv);
 	if (HAS_LLC(dev_priv))
-- 
cgit v1.2.3


From 71dc367e2bc37e1c235029003fbbc56a07fb6d58 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Tue, 10 Sep 2019 09:05:20 -0700
Subject: drm/i915: Consolidate bxt/cnl/icl cdclk readout
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Aside from a few minor register changes and some different clock values,
cdclk design hasn't changed much since gen9lp.  Let's consolidate the
handlers for bxt, cnl, and icl to keep the codeflow consistent.

Also, while we're at it, s/bxt_de_pll_update/bxt_de_pll_readout/ since
"update" makes me think we should be writing to hardware rather than
reading from it.

v2:
 - Fix icl_calc_voltage_level() limits.  (Ville)
 - Use CNL_CDCLK_PLL_RATIO_MASK rather than BXT_DE_PLL_RATIO_MASK on
   gen10+ to avoid confusion.  (Ville)

v3:
 - Also fix ehl_calc_voltage_level() limits.  (Ville)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Suggested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910160520.6587-1-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 325 ++++++++++++-----------------
 1 file changed, 138 insertions(+), 187 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index d3e56628af70..dfcb1cc58951 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1190,6 +1190,36 @@ static u8 bxt_calc_voltage_level(int cdclk)
 	return DIV_ROUND_UP(cdclk, 25000);
 }
 
+static u8 cnl_calc_voltage_level(int cdclk)
+{
+	if (cdclk > 336000)
+		return 2;
+	else if (cdclk > 168000)
+		return 1;
+	else
+		return 0;
+}
+
+static u8 icl_calc_voltage_level(int cdclk)
+{
+	if (cdclk > 556800)
+		return 2;
+	else if (cdclk > 312000)
+		return 1;
+	else
+		return 0;
+}
+
+static u8 ehl_calc_voltage_level(int cdclk)
+{
+	if (cdclk > 312000)
+		return 2;
+	else if (cdclk > 180000)
+		return 1;
+	else
+		return 0;
+}
+
 static int bxt_de_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 {
 	int ratio;
@@ -1236,23 +1266,69 @@ static int glk_de_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 	return dev_priv->cdclk.hw.ref * ratio;
 }
 
-static void bxt_de_pll_update(struct drm_i915_private *dev_priv,
-			      struct intel_cdclk_state *cdclk_state)
+static void cnl_readout_refclk(struct drm_i915_private *dev_priv,
+			       struct intel_cdclk_state *cdclk_state)
 {
-	u32 val;
+	if (I915_READ(SKL_DSSM) & CNL_DSSM_CDCLK_PLL_REFCLK_24MHz)
+		cdclk_state->ref = 24000;
+	else
+		cdclk_state->ref = 19200;
+}
 
-	cdclk_state->ref = 19200;
-	cdclk_state->vco = 0;
+static void icl_readout_refclk(struct drm_i915_private *dev_priv,
+			       struct intel_cdclk_state *cdclk_state)
+{
+	u32 dssm = I915_READ(SKL_DSSM) & ICL_DSSM_CDCLK_PLL_REFCLK_MASK;
+
+	switch (dssm) {
+	default:
+		MISSING_CASE(dssm);
+		/* fall through */
+	case ICL_DSSM_CDCLK_PLL_REFCLK_24MHz:
+		cdclk_state->ref = 24000;
+		break;
+	case ICL_DSSM_CDCLK_PLL_REFCLK_19_2MHz:
+		cdclk_state->ref = 19200;
+		break;
+	case ICL_DSSM_CDCLK_PLL_REFCLK_38_4MHz:
+		cdclk_state->ref = 38400;
+		break;
+	}
+}
+
+static void bxt_de_pll_readout(struct drm_i915_private *dev_priv,
+			       struct intel_cdclk_state *cdclk_state)
+{
+	u32 val, ratio;
+
+	if (INTEL_GEN(dev_priv) >= 11)
+		icl_readout_refclk(dev_priv, cdclk_state);
+	else if (IS_CANNONLAKE(dev_priv))
+		cnl_readout_refclk(dev_priv, cdclk_state);
+	else
+		cdclk_state->ref = 19200;
 
 	val = I915_READ(BXT_DE_PLL_ENABLE);
-	if ((val & BXT_DE_PLL_PLL_ENABLE) == 0)
+	if ((val & BXT_DE_PLL_PLL_ENABLE) == 0 ||
+	    (val & BXT_DE_PLL_LOCK) == 0) {
+		/*
+		 * CDCLK PLL is disabled, the VCO/ratio doesn't matter, but
+		 * setting it to zero is a way to signal that.
+		 */
+		cdclk_state->vco = 0;
 		return;
+	}
 
-	if (WARN_ON((val & BXT_DE_PLL_LOCK) == 0))
-		return;
+	/*
+	 * CNL+ have the ratio directly in the PLL enable register, gen9lp had
+	 * it in a separate PLL control register.
+	 */
+	if (INTEL_GEN(dev_priv) >= 10)
+		ratio = val & CNL_CDCLK_PLL_RATIO_MASK;
+	else
+		ratio = I915_READ(BXT_DE_PLL_CTL) & BXT_DE_PLL_RATIO_MASK;
 
-	val = I915_READ(BXT_DE_PLL_CTL);
-	cdclk_state->vco = (val & BXT_DE_PLL_RATIO_MASK) * cdclk_state->ref;
+	cdclk_state->vco = ratio * cdclk_state->ref;
 }
 
 static void bxt_get_cdclk(struct drm_i915_private *dev_priv,
@@ -1261,12 +1337,18 @@ static void bxt_get_cdclk(struct drm_i915_private *dev_priv,
 	u32 divider;
 	int div;
 
-	bxt_de_pll_update(dev_priv, cdclk_state);
-
-	cdclk_state->cdclk = cdclk_state->bypass = cdclk_state->ref;
+	if (INTEL_GEN(dev_priv) >= 12)
+		cdclk_state->bypass = cdclk_state->ref / 2;
+	else if (INTEL_GEN(dev_priv) >= 11)
+		cdclk_state->bypass = 50000;
+	else
+		cdclk_state->bypass = cdclk_state->ref;
 
-	if (cdclk_state->vco == 0)
+	bxt_de_pll_readout(dev_priv, cdclk_state);
+	if (cdclk_state->vco == 0) {
+		cdclk_state->cdclk = cdclk_state->bypass;
 		goto out;
+	}
 
 	divider = I915_READ(CDCLK_CTL) & BXT_CDCLK_CD2X_DIV_SEL_MASK;
 
@@ -1275,13 +1357,15 @@ static void bxt_get_cdclk(struct drm_i915_private *dev_priv,
 		div = 2;
 		break;
 	case BXT_CDCLK_CD2X_DIV_SEL_1_5:
-		WARN(IS_GEMINILAKE(dev_priv), "Unsupported divider\n");
+		WARN(IS_GEMINILAKE(dev_priv) || INTEL_GEN(dev_priv) >= 10,
+		     "Unsupported divider\n");
 		div = 3;
 		break;
 	case BXT_CDCLK_CD2X_DIV_SEL_2:
 		div = 4;
 		break;
 	case BXT_CDCLK_CD2X_DIV_SEL_4:
+		WARN(INTEL_GEN(dev_priv) >= 10, "Unsupported divider\n");
 		div = 8;
 		break;
 	default:
@@ -1296,8 +1380,18 @@ static void bxt_get_cdclk(struct drm_i915_private *dev_priv,
 	 * Can't read this out :( Let's assume it's
 	 * at least what the CDCLK frequency requires.
 	 */
-	cdclk_state->voltage_level =
-		bxt_calc_voltage_level(cdclk_state->cdclk);
+	if (IS_ELKHARTLAKE(dev_priv))
+		cdclk_state->voltage_level =
+			ehl_calc_voltage_level(cdclk_state->cdclk);
+	else if (INTEL_GEN(dev_priv) >= 11)
+		cdclk_state->voltage_level =
+			icl_calc_voltage_level(cdclk_state->cdclk);
+	else if (INTEL_GEN(dev_priv) >= 10)
+		cdclk_state->voltage_level =
+			cnl_calc_voltage_level(cdclk_state->cdclk);
+	else
+		cdclk_state->voltage_level =
+			bxt_calc_voltage_level(cdclk_state->cdclk);
 }
 
 static void bxt_de_pll_disable(struct drm_i915_private *dev_priv)
@@ -1515,76 +1609,6 @@ static int cnl_calc_cdclk(int min_cdclk)
 		return 168000;
 }
 
-static u8 cnl_calc_voltage_level(int cdclk)
-{
-	if (cdclk > 336000)
-		return 2;
-	else if (cdclk > 168000)
-		return 1;
-	else
-		return 0;
-}
-
-static void cnl_cdclk_pll_update(struct drm_i915_private *dev_priv,
-				 struct intel_cdclk_state *cdclk_state)
-{
-	u32 val;
-
-	if (I915_READ(SKL_DSSM) & CNL_DSSM_CDCLK_PLL_REFCLK_24MHz)
-		cdclk_state->ref = 24000;
-	else
-		cdclk_state->ref = 19200;
-
-	cdclk_state->vco = 0;
-
-	val = I915_READ(BXT_DE_PLL_ENABLE);
-	if ((val & BXT_DE_PLL_PLL_ENABLE) == 0)
-		return;
-
-	if (WARN_ON((val & BXT_DE_PLL_LOCK) == 0))
-		return;
-
-	cdclk_state->vco = (val & CNL_CDCLK_PLL_RATIO_MASK) * cdclk_state->ref;
-}
-
-static void cnl_get_cdclk(struct drm_i915_private *dev_priv,
-			 struct intel_cdclk_state *cdclk_state)
-{
-	u32 divider;
-	int div;
-
-	cnl_cdclk_pll_update(dev_priv, cdclk_state);
-
-	cdclk_state->cdclk = cdclk_state->bypass = cdclk_state->ref;
-
-	if (cdclk_state->vco == 0)
-		goto out;
-
-	divider = I915_READ(CDCLK_CTL) & BXT_CDCLK_CD2X_DIV_SEL_MASK;
-
-	switch (divider) {
-	case BXT_CDCLK_CD2X_DIV_SEL_1:
-		div = 2;
-		break;
-	case BXT_CDCLK_CD2X_DIV_SEL_2:
-		div = 4;
-		break;
-	default:
-		MISSING_CASE(divider);
-		return;
-	}
-
-	cdclk_state->cdclk = DIV_ROUND_CLOSEST(cdclk_state->vco, div);
-
- out:
-	/*
-	 * Can't read this out :( Let's assume it's
-	 * at least what the CDCLK frequency requires.
-	 */
-	cdclk_state->voltage_level =
-		cnl_calc_voltage_level(cdclk_state->cdclk);
-}
-
 static void cnl_cdclk_pll_disable(struct drm_i915_private *dev_priv)
 {
 	u32 val;
@@ -1830,91 +1854,6 @@ static int icl_calc_cdclk_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 	return dev_priv->cdclk.hw.ref * ratio;
 }
 
-static u8 icl_calc_voltage_level(struct drm_i915_private *dev_priv, int cdclk)
-{
-	if (IS_ELKHARTLAKE(dev_priv)) {
-		if (cdclk > 312000)
-			return 2;
-		else if (cdclk > 180000)
-			return 1;
-		else
-			return 0;
-	} else {
-		if (cdclk > 556800)
-			return 2;
-		else if (cdclk > 312000)
-			return 1;
-		else
-			return 0;
-	}
-}
-
-static void icl_get_cdclk(struct drm_i915_private *dev_priv,
-			  struct intel_cdclk_state *cdclk_state)
-{
-	u32 val;
-	int div;
-
-	val = I915_READ(SKL_DSSM);
-	switch (val & ICL_DSSM_CDCLK_PLL_REFCLK_MASK) {
-	default:
-		MISSING_CASE(val);
-		/* fall through */
-	case ICL_DSSM_CDCLK_PLL_REFCLK_24MHz:
-		cdclk_state->ref = 24000;
-		break;
-	case ICL_DSSM_CDCLK_PLL_REFCLK_19_2MHz:
-		cdclk_state->ref = 19200;
-		break;
-	case ICL_DSSM_CDCLK_PLL_REFCLK_38_4MHz:
-		cdclk_state->ref = 38400;
-		break;
-	}
-
-	if (INTEL_GEN(dev_priv) >= 12)
-		cdclk_state->bypass = cdclk_state->ref / 2;
-	else
-		cdclk_state->bypass = 50000;
-
-	val = I915_READ(BXT_DE_PLL_ENABLE);
-	if ((val & BXT_DE_PLL_PLL_ENABLE) == 0 ||
-	    (val & BXT_DE_PLL_LOCK) == 0) {
-		/*
-		 * CDCLK PLL is disabled, the VCO/ratio doesn't matter, but
-		 * setting it to zero is a way to signal that.
-		 */
-		cdclk_state->vco = 0;
-		cdclk_state->cdclk = cdclk_state->bypass;
-		goto out;
-	}
-
-	cdclk_state->vco = (val & BXT_DE_PLL_RATIO_MASK) * cdclk_state->ref;
-
-	val = I915_READ(CDCLK_CTL) & BXT_CDCLK_CD2X_DIV_SEL_MASK;
-	switch (val) {
-	case BXT_CDCLK_CD2X_DIV_SEL_1:
-		div = 2;
-		break;
-	case BXT_CDCLK_CD2X_DIV_SEL_2:
-		div = 4;
-		break;
-	default:
-		MISSING_CASE(val);
-		div = 2;
-		break;
-	}
-
-	cdclk_state->cdclk = DIV_ROUND_CLOSEST(cdclk_state->vco, div);
-
-out:
-	/*
-	 * Can't read this out :( Let's assume it's
-	 * at least what the CDCLK frequency requires.
-	 */
-	cdclk_state->voltage_level =
-		icl_calc_voltage_level(dev_priv, cdclk_state->cdclk);
-}
-
 static void icl_init_cdclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_cdclk_state sanitized_state;
@@ -1946,9 +1885,12 @@ sanitize:
 	sanitized_state.cdclk = icl_calc_cdclk(0, sanitized_state.ref);
 	sanitized_state.vco = icl_calc_cdclk_pll_vco(dev_priv,
 						     sanitized_state.cdclk);
-	sanitized_state.voltage_level =
-				icl_calc_voltage_level(dev_priv,
-						       sanitized_state.cdclk);
+	if (IS_ELKHARTLAKE(dev_priv))
+		sanitized_state.voltage_level =
+			ehl_calc_voltage_level(sanitized_state.cdclk);
+	else
+		sanitized_state.voltage_level =
+			icl_calc_voltage_level(sanitized_state.cdclk);
 
 	cnl_set_cdclk(dev_priv, &sanitized_state, INVALID_PIPE);
 }
@@ -1959,8 +1901,12 @@ static void icl_uninit_cdclk(struct drm_i915_private *dev_priv)
 
 	cdclk_state.cdclk = cdclk_state.bypass;
 	cdclk_state.vco = 0;
-	cdclk_state.voltage_level = icl_calc_voltage_level(dev_priv,
-							   cdclk_state.cdclk);
+	if (IS_ELKHARTLAKE(dev_priv))
+		cdclk_state.voltage_level =
+			ehl_calc_voltage_level(cdclk_state.cdclk);
+	else
+		cdclk_state.voltage_level =
+			icl_calc_voltage_level(cdclk_state.cdclk);
 
 	cnl_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
@@ -2561,9 +2507,14 @@ static int icl_modeset_calc_cdclk(struct intel_atomic_state *state)
 
 	state->cdclk.logical.vco = vco;
 	state->cdclk.logical.cdclk = cdclk;
-	state->cdclk.logical.voltage_level =
-		max(icl_calc_voltage_level(dev_priv, cdclk),
-		    cnl_compute_min_voltage_level(state));
+	if (IS_ELKHARTLAKE(dev_priv))
+		state->cdclk.logical.voltage_level =
+			max(ehl_calc_voltage_level(cdclk),
+			    cnl_compute_min_voltage_level(state));
+	else
+		state->cdclk.logical.voltage_level =
+			max(icl_calc_voltage_level(cdclk),
+			    cnl_compute_min_voltage_level(state));
 
 	if (!state->active_pipes) {
 		cdclk = icl_calc_cdclk(state->cdclk.force_min_cdclk, ref);
@@ -2571,8 +2522,12 @@ static int icl_modeset_calc_cdclk(struct intel_atomic_state *state)
 
 		state->cdclk.actual.vco = vco;
 		state->cdclk.actual.cdclk = cdclk;
-		state->cdclk.actual.voltage_level =
-			icl_calc_voltage_level(dev_priv, cdclk);
+		if (IS_ELKHARTLAKE(dev_priv))
+			state->cdclk.actual.voltage_level =
+				ehl_calc_voltage_level(cdclk);
+		else
+			state->cdclk.actual.voltage_level =
+				icl_calc_voltage_level(cdclk);
 	} else {
 		state->cdclk.actual = state->cdclk.logical;
 	}
@@ -2819,11 +2774,7 @@ void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 		dev_priv->display.modeset_calc_cdclk = vlv_modeset_calc_cdclk;
 	}
 
-	if (INTEL_GEN(dev_priv) >= 11)
-		dev_priv->display.get_cdclk = icl_get_cdclk;
-	else if (IS_CANNONLAKE(dev_priv))
-		dev_priv->display.get_cdclk = cnl_get_cdclk;
-	else if (IS_GEN9_LP(dev_priv))
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEN9_LP(dev_priv))
 		dev_priv->display.get_cdclk = bxt_get_cdclk;
 	else if (IS_GEN9_BC(dev_priv))
 		dev_priv->display.get_cdclk = skl_get_cdclk;
-- 
cgit v1.2.3


From 736da8112fee663deed6efc53333c37dc0b04696 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Tue, 10 Sep 2019 09:15:06 -0700
Subject: drm/i915: Use literal representation of cdclk tables
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The bspec lays out legal cdclk frequencies, PLL ratios, and CD2X
dividers in an easy-to-read table for most recent platforms.  We've been
translating the data from that table into platform-specific code logic,
but it's easy to overlook an area we need to update when adding new
cdclk values or enabling new platforms.  Let's just add a form of the
bspec table to the code and then adjust our functions to pull what they
need directly out of the table.

v2: Fix comparison when finding best cdclk.

v3: Another logic fix for calc_cdclk.

v4:
 - Use named initializers for cdclk tables. (Ville)
 - Include refclk as a field in the table instead of adding all three
   ratios for each entry. (Ville)
 - Terminate tables with an empty entry to avoid needing to store the
   table size. (Ville)
 - Don't try so hard to return reasonable values from our lookup
   functions if we get impossible inputs; just WARN and return 0.
   (Ville)
 - Keep a bxt_ prefix on the lookup functions since they're still only
   used on bxt+ for now.  We can rename them later if we extend this
   table-based approach back to older platforms.  (Ville)

v5:
 - Fix cnl table's ratios for 24mhz refclk. (Ville)
 - Don't miss the named initializers on the cnl table. (Ville)
 - Represent refclk in table as u16 rather than u32. (Ville)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910161506.7158-1-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 303 ++++++++++-------------------
 drivers/gpu/drm/i915/display/intel_cdclk.h |   7 +
 drivers/gpu/drm/i915/i915_drv.h            |   3 +
 3 files changed, 110 insertions(+), 203 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index dfcb1cc58951..f3431b530966 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1161,28 +1161,88 @@ static void skl_uninit_cdclk(struct drm_i915_private *dev_priv)
 	skl_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
 
-static int bxt_calc_cdclk(int min_cdclk)
-{
-	if (min_cdclk > 576000)
-		return 624000;
-	else if (min_cdclk > 384000)
-		return 576000;
-	else if (min_cdclk > 288000)
-		return 384000;
-	else if (min_cdclk > 144000)
-		return 288000;
-	else
-		return 144000;
+static const struct intel_cdclk_vals bxt_cdclk_table[] = {
+	{ .refclk = 19200, .cdclk = 144000, .divider = 8, .ratio = 60 },
+	{ .refclk = 19200, .cdclk = 288000, .divider = 4, .ratio = 60 },
+	{ .refclk = 19200, .cdclk = 384000, .divider = 3, .ratio = 60 },
+	{ .refclk = 19200, .cdclk = 576000, .divider = 2, .ratio = 60 },
+	{ .refclk = 19200, .cdclk = 624000, .divider = 2, .ratio = 65 },
+	{}
+};
+
+static const struct intel_cdclk_vals glk_cdclk_table[] = {
+	{ .refclk = 19200, .cdclk =  79200, .divider = 8, .ratio = 33 },
+	{ .refclk = 19200, .cdclk = 158400, .divider = 4, .ratio = 33 },
+	{ .refclk = 19200, .cdclk = 316800, .divider = 2, .ratio = 33 },
+	{}
+};
+
+static const struct intel_cdclk_vals cnl_cdclk_table[] = {
+	{ .refclk = 19200, .cdclk = 168000, .divider = 4, .ratio = 35 },
+	{ .refclk = 19200, .cdclk = 336000, .divider = 2, .ratio = 35 },
+	{ .refclk = 19200, .cdclk = 528000, .divider = 2, .ratio = 55 },
+
+	{ .refclk = 24000, .cdclk = 168000, .divider = 4, .ratio = 28 },
+	{ .refclk = 24000, .cdclk = 336000, .divider = 2, .ratio = 28 },
+	{ .refclk = 24000, .cdclk = 528000, .divider = 2, .ratio = 44 },
+	{}
+};
+
+static const struct intel_cdclk_vals icl_cdclk_table[] = {
+	{ .refclk = 19200, .cdclk = 172800, .divider = 2, .ratio = 18 },
+	{ .refclk = 19200, .cdclk = 192000, .divider = 2, .ratio = 20 },
+	{ .refclk = 19200, .cdclk = 307200, .divider = 2, .ratio = 32 },
+	{ .refclk = 19200, .cdclk = 326400, .divider = 4, .ratio = 68 },
+	{ .refclk = 19200, .cdclk = 556800, .divider = 2, .ratio = 58 },
+	{ .refclk = 19200, .cdclk = 652800, .divider = 2, .ratio = 68 },
+
+	{ .refclk = 24000, .cdclk = 180000, .divider = 2, .ratio = 15 },
+	{ .refclk = 24000, .cdclk = 192000, .divider = 2, .ratio = 16 },
+	{ .refclk = 24000, .cdclk = 312000, .divider = 2, .ratio = 26 },
+	{ .refclk = 24000, .cdclk = 324000, .divider = 4, .ratio = 54 },
+	{ .refclk = 24000, .cdclk = 552000, .divider = 2, .ratio = 46 },
+	{ .refclk = 24000, .cdclk = 648000, .divider = 2, .ratio = 54 },
+
+	{ .refclk = 38400, .cdclk = 172800, .divider = 2, .ratio =  9 },
+	{ .refclk = 38400, .cdclk = 192000, .divider = 2, .ratio = 10 },
+	{ .refclk = 38400, .cdclk = 307200, .divider = 2, .ratio = 16 },
+	{ .refclk = 38400, .cdclk = 326400, .divider = 4, .ratio = 34 },
+	{ .refclk = 38400, .cdclk = 556800, .divider = 2, .ratio = 29 },
+	{ .refclk = 38400, .cdclk = 652800, .divider = 2, .ratio = 34 },
+	{}
+};
+
+static int bxt_calc_cdclk(struct drm_i915_private *dev_priv, int min_cdclk)
+{
+	const struct intel_cdclk_vals *table = dev_priv->cdclk.table;
+	int i;
+
+	for (i = 0; table[i].refclk; i++)
+		if (table[i].refclk == dev_priv->cdclk.hw.ref &&
+		    table[i].cdclk >= min_cdclk)
+			return table[i].cdclk;
+
+	WARN(1, "Cannot satisfy minimum cdclk %d with refclk %u\n",
+	     min_cdclk, dev_priv->cdclk.hw.ref);
+	return 0;
 }
 
-static int glk_calc_cdclk(int min_cdclk)
+static int bxt_calc_cdclk_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 {
-	if (min_cdclk > 158400)
-		return 316800;
-	else if (min_cdclk > 79200)
-		return 158400;
-	else
-		return 79200;
+	const struct intel_cdclk_vals *table = dev_priv->cdclk.table;
+	int i;
+
+	if (cdclk == dev_priv->cdclk.hw.bypass)
+		return 0;
+
+	for (i = 0; table[i].refclk; i++)
+		if (table[i].refclk == dev_priv->cdclk.hw.ref &&
+		    table[i].cdclk == cdclk)
+			return dev_priv->cdclk.hw.ref * table[i].ratio;
+
+	WARN(1, "cdclk %d not valid for refclk %u\n",
+	     cdclk, dev_priv->cdclk.hw.ref);
+	return 0;
 }
 
 static u8 bxt_calc_voltage_level(int cdclk)
@@ -1220,52 +1280,6 @@ static u8 ehl_calc_voltage_level(int cdclk)
 		return 0;
 }
 
-static int bxt_de_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
-{
-	int ratio;
-
-	if (cdclk == dev_priv->cdclk.hw.bypass)
-		return 0;
-
-	switch (cdclk) {
-	default:
-		MISSING_CASE(cdclk);
-		/* fall through */
-	case 144000:
-	case 288000:
-	case 384000:
-	case 576000:
-		ratio = 60;
-		break;
-	case 624000:
-		ratio = 65;
-		break;
-	}
-
-	return dev_priv->cdclk.hw.ref * ratio;
-}
-
-static int glk_de_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
-{
-	int ratio;
-
-	if (cdclk == dev_priv->cdclk.hw.bypass)
-		return 0;
-
-	switch (cdclk) {
-	default:
-		MISSING_CASE(cdclk);
-		/* fall through */
-	case  79200:
-	case 158400:
-	case 316800:
-		ratio = 33;
-		break;
-	}
-
-	return dev_priv->cdclk.hw.ref * ratio;
-}
-
 static void cnl_readout_refclk(struct drm_i915_private *dev_priv,
 			       struct intel_cdclk_state *cdclk_state)
 {
@@ -1576,13 +1590,8 @@ static void bxt_init_cdclk(struct drm_i915_private *dev_priv)
 	 * - The initial CDCLK needs to be read from VBT.
 	 *   Need to make this change after VBT has changes for BXT.
 	 */
-	if (IS_GEMINILAKE(dev_priv)) {
-		cdclk_state.cdclk = glk_calc_cdclk(0);
-		cdclk_state.vco = glk_de_pll_vco(dev_priv, cdclk_state.cdclk);
-	} else {
-		cdclk_state.cdclk = bxt_calc_cdclk(0);
-		cdclk_state.vco = bxt_de_pll_vco(dev_priv, cdclk_state.cdclk);
-	}
+	cdclk_state.cdclk = bxt_calc_cdclk(dev_priv, 0);
+	cdclk_state.vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk_state.cdclk);
 	cdclk_state.voltage_level = bxt_calc_voltage_level(cdclk_state.cdclk);
 
 	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
@@ -1599,16 +1608,6 @@ static void bxt_uninit_cdclk(struct drm_i915_private *dev_priv)
 	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
 
-static int cnl_calc_cdclk(int min_cdclk)
-{
-	if (min_cdclk > 336000)
-		return 528000;
-	else if (min_cdclk > 168000)
-		return 336000;
-	else
-		return 168000;
-}
-
 static void cnl_cdclk_pll_disable(struct drm_i915_private *dev_priv)
 {
 	u32 val;
@@ -1718,29 +1717,6 @@ static void cnl_set_cdclk(struct drm_i915_private *dev_priv,
 	dev_priv->cdclk.hw.voltage_level = cdclk_state->voltage_level;
 }
 
-static int cnl_cdclk_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
-{
-	int ratio;
-
-	if (cdclk == dev_priv->cdclk.hw.bypass)
-		return 0;
-
-	switch (cdclk) {
-	default:
-		MISSING_CASE(cdclk);
-		/* fall through */
-	case 168000:
-	case 336000:
-		ratio = dev_priv->cdclk.hw.ref == 19200 ? 35 : 28;
-		break;
-	case 528000:
-		ratio = dev_priv->cdclk.hw.ref == 19200 ? 55 : 44;
-		break;
-	}
-
-	return dev_priv->cdclk.hw.ref * ratio;
-}
-
 static void cnl_sanitize_cdclk(struct drm_i915_private *dev_priv)
 {
 	u32 cdctl, expected;
@@ -1783,77 +1759,6 @@ sanitize:
 	dev_priv->cdclk.hw.vco = -1;
 }
 
-static int icl_calc_cdclk(int min_cdclk, unsigned int ref)
-{
-	static const int ranges_24[] = { 180000, 192000, 312000, 324000,
-					 552000, 648000 };
-	static const int ranges_19_38[] = { 172800, 192000, 307200, 326400,
-					    556800, 652800 };
-	const int *ranges;
-	int len, i;
-
-	switch (ref) {
-	default:
-		MISSING_CASE(ref);
-		/* fall through */
-	case 24000:
-		ranges = ranges_24;
-		len = ARRAY_SIZE(ranges_24);
-		break;
-	case 19200:
-	case 38400:
-		ranges = ranges_19_38;
-		len = ARRAY_SIZE(ranges_19_38);
-		break;
-	}
-
-	for (i = 0; i < len; i++) {
-		if (min_cdclk <= ranges[i])
-			return ranges[i];
-	}
-
-	WARN_ON(min_cdclk > ranges[len - 1]);
-	return ranges[len - 1];
-}
-
-static int icl_calc_cdclk_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
-{
-	int ratio;
-
-	if (cdclk == dev_priv->cdclk.hw.bypass)
-		return 0;
-
-	switch (cdclk) {
-	default:
-		MISSING_CASE(cdclk);
-		/* fall through */
-	case 172800:
-	case 307200:
-	case 326400:
-	case 556800:
-	case 652800:
-		WARN_ON(dev_priv->cdclk.hw.ref != 19200 &&
-			dev_priv->cdclk.hw.ref != 38400);
-		break;
-	case 180000:
-	case 312000:
-	case 324000:
-	case 552000:
-	case 648000:
-		WARN_ON(dev_priv->cdclk.hw.ref != 24000);
-		break;
-	case 192000:
-		WARN_ON(dev_priv->cdclk.hw.ref != 19200 &&
-			dev_priv->cdclk.hw.ref != 38400 &&
-			dev_priv->cdclk.hw.ref != 24000);
-		break;
-	}
-
-	ratio = cdclk / (dev_priv->cdclk.hw.ref / 2);
-
-	return dev_priv->cdclk.hw.ref * ratio;
-}
-
 static void icl_init_cdclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_cdclk_state sanitized_state;
@@ -1882,8 +1787,8 @@ sanitize:
 	DRM_DEBUG_KMS("Sanitizing cdclk programmed by pre-os\n");
 
 	sanitized_state.ref = dev_priv->cdclk.hw.ref;
-	sanitized_state.cdclk = icl_calc_cdclk(0, sanitized_state.ref);
-	sanitized_state.vco = icl_calc_cdclk_pll_vco(dev_priv,
+	sanitized_state.cdclk = bxt_calc_cdclk(dev_priv, 0);
+	sanitized_state.vco = bxt_calc_cdclk_pll_vco(dev_priv,
 						     sanitized_state.cdclk);
 	if (IS_ELKHARTLAKE(dev_priv))
 		sanitized_state.voltage_level =
@@ -1923,8 +1828,8 @@ static void cnl_init_cdclk(struct drm_i915_private *dev_priv)
 
 	cdclk_state = dev_priv->cdclk.hw;
 
-	cdclk_state.cdclk = cnl_calc_cdclk(0);
-	cdclk_state.vco = cnl_cdclk_pll_vco(dev_priv, cdclk_state.cdclk);
+	cdclk_state.cdclk = bxt_calc_cdclk(dev_priv, 0);
+	cdclk_state.vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk_state.cdclk);
 	cdclk_state.voltage_level = cnl_calc_voltage_level(cdclk_state.cdclk);
 
 	cnl_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
@@ -2426,13 +2331,8 @@ static int bxt_modeset_calc_cdclk(struct intel_atomic_state *state)
 	if (min_cdclk < 0)
 		return min_cdclk;
 
-	if (IS_GEMINILAKE(dev_priv)) {
-		cdclk = glk_calc_cdclk(min_cdclk);
-		vco = glk_de_pll_vco(dev_priv, cdclk);
-	} else {
-		cdclk = bxt_calc_cdclk(min_cdclk);
-		vco = bxt_de_pll_vco(dev_priv, cdclk);
-	}
+	cdclk = bxt_calc_cdclk(dev_priv, min_cdclk);
+	vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
 
 	state->cdclk.logical.vco = vco;
 	state->cdclk.logical.cdclk = cdclk;
@@ -2440,13 +2340,8 @@ static int bxt_modeset_calc_cdclk(struct intel_atomic_state *state)
 		bxt_calc_voltage_level(cdclk);
 
 	if (!state->active_pipes) {
-		if (IS_GEMINILAKE(dev_priv)) {
-			cdclk = glk_calc_cdclk(state->cdclk.force_min_cdclk);
-			vco = glk_de_pll_vco(dev_priv, cdclk);
-		} else {
-			cdclk = bxt_calc_cdclk(state->cdclk.force_min_cdclk);
-			vco = bxt_de_pll_vco(dev_priv, cdclk);
-		}
+		cdclk = bxt_calc_cdclk(dev_priv, state->cdclk.force_min_cdclk);
+		vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
 
 		state->cdclk.actual.vco = vco;
 		state->cdclk.actual.cdclk = cdclk;
@@ -2468,8 +2363,8 @@ static int cnl_modeset_calc_cdclk(struct intel_atomic_state *state)
 	if (min_cdclk < 0)
 		return min_cdclk;
 
-	cdclk = cnl_calc_cdclk(min_cdclk);
-	vco = cnl_cdclk_pll_vco(dev_priv, cdclk);
+	cdclk = bxt_calc_cdclk(dev_priv, min_cdclk);
+	vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
 
 	state->cdclk.logical.vco = vco;
 	state->cdclk.logical.cdclk = cdclk;
@@ -2478,8 +2373,8 @@ static int cnl_modeset_calc_cdclk(struct intel_atomic_state *state)
 		    cnl_compute_min_voltage_level(state));
 
 	if (!state->active_pipes) {
-		cdclk = cnl_calc_cdclk(state->cdclk.force_min_cdclk);
-		vco = cnl_cdclk_pll_vco(dev_priv, cdclk);
+		cdclk = bxt_calc_cdclk(dev_priv, state->cdclk.force_min_cdclk);
+		vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
 
 		state->cdclk.actual.vco = vco;
 		state->cdclk.actual.cdclk = cdclk;
@@ -2495,15 +2390,14 @@ static int cnl_modeset_calc_cdclk(struct intel_atomic_state *state)
 static int icl_modeset_calc_cdclk(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
-	unsigned int ref = state->cdclk.logical.ref;
 	int min_cdclk, cdclk, vco;
 
 	min_cdclk = intel_compute_min_cdclk(state);
 	if (min_cdclk < 0)
 		return min_cdclk;
 
-	cdclk = icl_calc_cdclk(min_cdclk, ref);
-	vco = icl_calc_cdclk_pll_vco(dev_priv, cdclk);
+	cdclk = bxt_calc_cdclk(dev_priv, min_cdclk);
+	vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
 
 	state->cdclk.logical.vco = vco;
 	state->cdclk.logical.cdclk = cdclk;
@@ -2517,8 +2411,8 @@ static int icl_modeset_calc_cdclk(struct intel_atomic_state *state)
 			    cnl_compute_min_voltage_level(state));
 
 	if (!state->active_pipes) {
-		cdclk = icl_calc_cdclk(state->cdclk.force_min_cdclk, ref);
-		vco = icl_calc_cdclk_pll_vco(dev_priv, cdclk);
+		cdclk = bxt_calc_cdclk(dev_priv, state->cdclk.force_min_cdclk);
+		vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
 
 		state->cdclk.actual.vco = vco;
 		state->cdclk.actual.cdclk = cdclk;
@@ -2754,12 +2648,15 @@ void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 	if (INTEL_GEN(dev_priv) >= 11) {
 		dev_priv->display.set_cdclk = cnl_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = icl_modeset_calc_cdclk;
+		dev_priv->cdclk.table = icl_cdclk_table;
 	} else if (IS_CANNONLAKE(dev_priv)) {
 		dev_priv->display.set_cdclk = cnl_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = cnl_modeset_calc_cdclk;
+		dev_priv->cdclk.table = cnl_cdclk_table;
 	} else if (IS_GEN9_LP(dev_priv)) {
 		dev_priv->display.set_cdclk = bxt_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk;
+		dev_priv->cdclk.table = bxt_cdclk_table;
 	} else if (IS_GEN9_BC(dev_priv)) {
 		dev_priv->display.set_cdclk = skl_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = skl_modeset_calc_cdclk;
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h
index 4d6f7f5f8930..1afa84ab6018 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.h
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.h
@@ -15,6 +15,13 @@ struct intel_atomic_state;
 struct intel_cdclk_state;
 struct intel_crtc_state;
 
+struct intel_cdclk_vals {
+	u16 refclk;
+	u32 cdclk;
+	u8 divider;	/* CD2X divider * 2 */
+	u8 ratio;
+};
+
 int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state);
 void intel_cdclk_init(struct drm_i915_private *i915);
 void intel_cdclk_uninit(struct drm_i915_private *i915);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e289b4ffd34b..ff6aff2a4866 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1420,6 +1420,9 @@ struct drm_i915_private {
 		/* The current hardware cdclk state */
 		struct intel_cdclk_state hw;
 
+		/* cdclk, divider, and ratio table from bspec */
+		const struct intel_cdclk_vals *table;
+
 		int force_min_cdclk;
 	} cdclk;
 
-- 
cgit v1.2.3


From 1cbcd3b4b168a08620153d2c5d52461a75338349 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Tue, 10 Sep 2019 08:42:47 -0700
Subject: drm/i915: Combine bxt_set_cdclk and cnl_set_cdclk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We'd previously combined ICL/TGL logic into the cnl_set_cdclk function,
but BXT is pretty similar as well.  Roll the cnl/icl/tgl logic back into
the bxt function; the only things we really need to handle separately
are punit notification and calling different functions to enable/disable
the cdclk PLL.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910154252.30503-4-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 267 +++++++++++++----------------
 1 file changed, 119 insertions(+), 148 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index f3431b530966..1dcb8a113b4f 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1440,6 +1440,39 @@ static void bxt_de_pll_enable(struct drm_i915_private *dev_priv, int vco)
 	dev_priv->cdclk.hw.vco = vco;
 }
 
+static void cnl_cdclk_pll_disable(struct drm_i915_private *dev_priv)
+{
+	u32 val;
+
+	val = I915_READ(BXT_DE_PLL_ENABLE);
+	val &= ~BXT_DE_PLL_PLL_ENABLE;
+	I915_WRITE(BXT_DE_PLL_ENABLE, val);
+
+	/* Timeout 200us */
+	if (wait_for((I915_READ(BXT_DE_PLL_ENABLE) & BXT_DE_PLL_LOCK) == 0, 1))
+		DRM_ERROR("timeout waiting for CDCLK PLL unlock\n");
+
+	dev_priv->cdclk.hw.vco = 0;
+}
+
+static void cnl_cdclk_pll_enable(struct drm_i915_private *dev_priv, int vco)
+{
+	int ratio = DIV_ROUND_CLOSEST(vco, dev_priv->cdclk.hw.ref);
+	u32 val;
+
+	val = CNL_CDCLK_PLL_RATIO(ratio);
+	I915_WRITE(BXT_DE_PLL_ENABLE, val);
+
+	val |= BXT_DE_PLL_PLL_ENABLE;
+	I915_WRITE(BXT_DE_PLL_ENABLE, val);
+
+	/* Timeout 200us */
+	if (wait_for((I915_READ(BXT_DE_PLL_ENABLE) & BXT_DE_PLL_LOCK) != 0, 1))
+		DRM_ERROR("timeout waiting for CDCLK PLL lock\n");
+
+	dev_priv->cdclk.hw.vco = vco;
+}
+
 static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 			  const struct intel_cdclk_state *cdclk_state,
 			  enum pipe pipe)
@@ -1449,6 +1482,27 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 	u32 val, divider;
 	int ret;
 
+	/* Inform power controller of upcoming frequency change. */
+	if (INTEL_GEN(dev_priv) >= 10)
+		ret = skl_pcode_request(dev_priv, SKL_PCODE_CDCLK_CONTROL,
+					SKL_CDCLK_PREPARE_FOR_CHANGE,
+					SKL_CDCLK_READY_FOR_CHANGE,
+					SKL_CDCLK_READY_FOR_CHANGE, 3);
+	else
+		/*
+		 * BSpec requires us to wait up to 150usec, but that leads to
+		 * timeouts; the 2ms used here is based on experiment.
+		 */
+		ret = sandybridge_pcode_write_timeout(dev_priv,
+						      HSW_PCODE_DE_WRITE_FREQ_REQ,
+						      0x80000000, 150, 2);
+
+	if (ret) {
+		DRM_ERROR("Failed to inform PCU about cdclk change (err %d, freq %d)\n",
+			  ret, cdclk);
+		return;
+	}
+
 	/* cdclk = vco / 2 / div{1,1.5,2,4} */
 	switch (DIV_ROUND_CLOSEST(vco, cdclk)) {
 	default:
@@ -1459,63 +1513,82 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 		divider = BXT_CDCLK_CD2X_DIV_SEL_1;
 		break;
 	case 3:
-		WARN(IS_GEMINILAKE(dev_priv), "Unsupported divider\n");
+		WARN(IS_GEMINILAKE(dev_priv) || INTEL_GEN(dev_priv) >= 10,
+		     "Unsupported divider\n");
 		divider = BXT_CDCLK_CD2X_DIV_SEL_1_5;
 		break;
 	case 4:
 		divider = BXT_CDCLK_CD2X_DIV_SEL_2;
 		break;
 	case 8:
+		WARN(INTEL_GEN(dev_priv) >= 10, "Unsupported divider\n");
 		divider = BXT_CDCLK_CD2X_DIV_SEL_4;
 		break;
 	}
 
-	/*
-	 * Inform power controller of upcoming frequency change. BSpec
-	 * requires us to wait up to 150usec, but that leads to timeouts;
-	 * the 2ms used here is based on experiment.
-	 */
-	ret = sandybridge_pcode_write_timeout(dev_priv,
-					      HSW_PCODE_DE_WRITE_FREQ_REQ,
-					      0x80000000, 150, 2);
-	if (ret) {
-		DRM_ERROR("PCode CDCLK freq change notify failed (err %d, freq %d)\n",
-			  ret, cdclk);
-		return;
-	}
+	if (INTEL_GEN(dev_priv) >= 10) {
+		if (dev_priv->cdclk.hw.vco != 0 &&
+		    dev_priv->cdclk.hw.vco != vco)
+			cnl_cdclk_pll_disable(dev_priv);
 
-	if (dev_priv->cdclk.hw.vco != 0 &&
-	    dev_priv->cdclk.hw.vco != vco)
-		bxt_de_pll_disable(dev_priv);
+		if (dev_priv->cdclk.hw.vco != vco)
+			cnl_cdclk_pll_enable(dev_priv, vco);
 
-	if (dev_priv->cdclk.hw.vco != vco)
-		bxt_de_pll_enable(dev_priv, vco);
+	} else {
+		if (dev_priv->cdclk.hw.vco != 0 &&
+		    dev_priv->cdclk.hw.vco != vco)
+			bxt_de_pll_disable(dev_priv);
+
+		if (dev_priv->cdclk.hw.vco != vco)
+			bxt_de_pll_enable(dev_priv, vco);
+	}
 
 	val = divider | skl_cdclk_decimal(cdclk);
-	if (pipe == INVALID_PIPE)
-		val |= BXT_CDCLK_CD2X_PIPE_NONE;
-	else
-		val |= BXT_CDCLK_CD2X_PIPE(pipe);
+
+	if (INTEL_GEN(dev_priv) >= 12) {
+		if (pipe == INVALID_PIPE)
+			val |= TGL_CDCLK_CD2X_PIPE_NONE;
+		else
+			val |= TGL_CDCLK_CD2X_PIPE(pipe);
+	} else if (INTEL_GEN(dev_priv) >= 11) {
+		if (pipe == INVALID_PIPE)
+			val |= ICL_CDCLK_CD2X_PIPE_NONE;
+		else
+			val |= ICL_CDCLK_CD2X_PIPE(pipe);
+	} else {
+		if (pipe == INVALID_PIPE)
+			val |= BXT_CDCLK_CD2X_PIPE_NONE;
+		else
+			val |= BXT_CDCLK_CD2X_PIPE(pipe);
+	}
+
 	/*
 	 * Disable SSA Precharge when CD clock frequency < 500 MHz,
 	 * enable otherwise.
 	 */
-	if (cdclk >= 500000)
+	if (IS_GEN9_LP(dev_priv) && cdclk >= 500000)
 		val |= BXT_CDCLK_SSA_PRECHARGE_ENABLE;
 	I915_WRITE(CDCLK_CTL, val);
 
 	if (pipe != INVALID_PIPE)
 		intel_wait_for_vblank(dev_priv, pipe);
 
-	/*
-	 * The timeout isn't specified, the 2ms used here is based on
-	 * experiment.
-	 * FIXME: Waiting for the request completion could be delayed until
-	 * the next PCODE request based on BSpec.
-	 */
-	ret = sandybridge_pcode_write_timeout(dev_priv,
-					      HSW_PCODE_DE_WRITE_FREQ_REQ,
-					      cdclk_state->voltage_level, 150, 2);
+	if (INTEL_GEN(dev_priv) >= 10) {
+		ret = sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL,
+					      cdclk_state->voltage_level);
+	} else {
+		/*
+		 * The timeout isn't specified, the 2ms used here is based on
+		 * experiment.
+		 * FIXME: Waiting for the request completion could be delayed
+		 * until the next PCODE request based on BSpec.
+		 */
+		ret = sandybridge_pcode_write_timeout(dev_priv,
+						      HSW_PCODE_DE_WRITE_FREQ_REQ,
+						      cdclk_state->voltage_level,
+						      150, 2);
+	}
+
 	if (ret) {
 		DRM_ERROR("PCode CDCLK freq set failed, (err %d, freq %d)\n",
 			  ret, cdclk);
@@ -1523,6 +1596,13 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 	}
 
 	intel_update_cdclk(dev_priv);
+
+	if (INTEL_GEN(dev_priv) >= 10)
+		/*
+		 * Can't read out the voltage level :(
+		 * Let's just assume everything is as expected.
+		 */
+		dev_priv->cdclk.hw.voltage_level = cdclk_state->voltage_level;
 }
 
 static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv)
@@ -1608,115 +1688,6 @@ static void bxt_uninit_cdclk(struct drm_i915_private *dev_priv)
 	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
 
-static void cnl_cdclk_pll_disable(struct drm_i915_private *dev_priv)
-{
-	u32 val;
-
-	val = I915_READ(BXT_DE_PLL_ENABLE);
-	val &= ~BXT_DE_PLL_PLL_ENABLE;
-	I915_WRITE(BXT_DE_PLL_ENABLE, val);
-
-	/* Timeout 200us */
-	if (wait_for((I915_READ(BXT_DE_PLL_ENABLE) & BXT_DE_PLL_LOCK) == 0, 1))
-		DRM_ERROR("timeout waiting for CDCLK PLL unlock\n");
-
-	dev_priv->cdclk.hw.vco = 0;
-}
-
-static void cnl_cdclk_pll_enable(struct drm_i915_private *dev_priv, int vco)
-{
-	int ratio = DIV_ROUND_CLOSEST(vco, dev_priv->cdclk.hw.ref);
-	u32 val;
-
-	val = CNL_CDCLK_PLL_RATIO(ratio);
-	I915_WRITE(BXT_DE_PLL_ENABLE, val);
-
-	val |= BXT_DE_PLL_PLL_ENABLE;
-	I915_WRITE(BXT_DE_PLL_ENABLE, val);
-
-	/* Timeout 200us */
-	if (wait_for((I915_READ(BXT_DE_PLL_ENABLE) & BXT_DE_PLL_LOCK) != 0, 1))
-		DRM_ERROR("timeout waiting for CDCLK PLL lock\n");
-
-	dev_priv->cdclk.hw.vco = vco;
-}
-
-static void cnl_set_cdclk(struct drm_i915_private *dev_priv,
-			  const struct intel_cdclk_state *cdclk_state,
-			  enum pipe pipe)
-{
-	int cdclk = cdclk_state->cdclk;
-	int vco = cdclk_state->vco;
-	u32 val, divider;
-	int ret;
-
-	ret = skl_pcode_request(dev_priv, SKL_PCODE_CDCLK_CONTROL,
-				SKL_CDCLK_PREPARE_FOR_CHANGE,
-				SKL_CDCLK_READY_FOR_CHANGE,
-				SKL_CDCLK_READY_FOR_CHANGE, 3);
-	if (ret) {
-		DRM_ERROR("Failed to inform PCU about cdclk change (%d)\n",
-			  ret);
-		return;
-	}
-
-	/* cdclk = vco / 2 / div{1,2} */
-	switch (DIV_ROUND_CLOSEST(vco, cdclk)) {
-	default:
-		WARN_ON(cdclk != dev_priv->cdclk.hw.bypass);
-		WARN_ON(vco != 0);
-		/* fall through */
-	case 2:
-		divider = BXT_CDCLK_CD2X_DIV_SEL_1;
-		break;
-	case 4:
-		divider = BXT_CDCLK_CD2X_DIV_SEL_2;
-		break;
-	}
-
-	if (dev_priv->cdclk.hw.vco != 0 &&
-	    dev_priv->cdclk.hw.vco != vco)
-		cnl_cdclk_pll_disable(dev_priv);
-
-	if (dev_priv->cdclk.hw.vco != vco)
-		cnl_cdclk_pll_enable(dev_priv, vco);
-
-	val = divider | skl_cdclk_decimal(cdclk);
-
-	if (INTEL_GEN(dev_priv) >= 12) {
-		if (pipe == INVALID_PIPE)
-			val |= TGL_CDCLK_CD2X_PIPE_NONE;
-		else
-			val |= TGL_CDCLK_CD2X_PIPE(pipe);
-	} else if (INTEL_GEN(dev_priv) >= 11) {
-		if (pipe == INVALID_PIPE)
-			val |= ICL_CDCLK_CD2X_PIPE_NONE;
-		else
-			val |= ICL_CDCLK_CD2X_PIPE(pipe);
-	} else {
-		if (pipe == INVALID_PIPE)
-			val |= BXT_CDCLK_CD2X_PIPE_NONE;
-		else
-			val |= BXT_CDCLK_CD2X_PIPE(pipe);
-	}
-	I915_WRITE(CDCLK_CTL, val);
-
-	if (pipe != INVALID_PIPE)
-		intel_wait_for_vblank(dev_priv, pipe);
-
-	/* inform PCU of the change */
-	sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL,
-				cdclk_state->voltage_level);
-
-	intel_update_cdclk(dev_priv);
-
-	/*
-	 * Can't read out the voltage level :(
-	 * Let's just assume everything is as expected.
-	 */
-	dev_priv->cdclk.hw.voltage_level = cdclk_state->voltage_level;
-}
-
 static void cnl_sanitize_cdclk(struct drm_i915_private *dev_priv)
 {
 	u32 cdctl, expected;
@@ -1797,7 +1768,7 @@ sanitize:
 		sanitized_state.voltage_level =
 			icl_calc_voltage_level(sanitized_state.cdclk);
 
-	cnl_set_cdclk(dev_priv, &sanitized_state, INVALID_PIPE);
+	bxt_set_cdclk(dev_priv, &sanitized_state, INVALID_PIPE);
 }
 
 static void icl_uninit_cdclk(struct drm_i915_private *dev_priv)
@@ -1813,7 +1784,7 @@ static void icl_uninit_cdclk(struct drm_i915_private *dev_priv)
 		cdclk_state.voltage_level =
 			icl_calc_voltage_level(cdclk_state.cdclk);
 
-	cnl_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
+	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
 
 static void cnl_init_cdclk(struct drm_i915_private *dev_priv)
@@ -1832,7 +1803,7 @@ static void cnl_init_cdclk(struct drm_i915_private *dev_priv)
 	cdclk_state.vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk_state.cdclk);
 	cdclk_state.voltage_level = cnl_calc_voltage_level(cdclk_state.cdclk);
 
-	cnl_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
+	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
 
 static void cnl_uninit_cdclk(struct drm_i915_private *dev_priv)
@@ -1843,7 +1814,7 @@ static void cnl_uninit_cdclk(struct drm_i915_private *dev_priv)
 	cdclk_state.vco = 0;
 	cdclk_state.voltage_level = cnl_calc_voltage_level(cdclk_state.cdclk);
 
-	cnl_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
+	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
 
 /**
@@ -2646,11 +2617,11 @@ void intel_update_rawclk(struct drm_i915_private *dev_priv)
 void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 {
 	if (INTEL_GEN(dev_priv) >= 11) {
-		dev_priv->display.set_cdclk = cnl_set_cdclk;
+		dev_priv->display.set_cdclk = bxt_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = icl_modeset_calc_cdclk;
 		dev_priv->cdclk.table = icl_cdclk_table;
 	} else if (IS_CANNONLAKE(dev_priv)) {
-		dev_priv->display.set_cdclk = cnl_set_cdclk;
+		dev_priv->display.set_cdclk = bxt_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = cnl_modeset_calc_cdclk;
 		dev_priv->cdclk.table = cnl_cdclk_table;
 	} else if (IS_GEN9_LP(dev_priv)) {
-- 
cgit v1.2.3


From 5dac256bf76793d4e4c554a3c6784e39ccf06664 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Tue, 10 Sep 2019 08:42:48 -0700
Subject: drm/i915: Kill cnl_sanitize_cdclk()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The CNL variant of this function is identical to the BXT variant aside
from not needing to handle SSA precharge.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910154252.30503-5-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 46 ++----------------------------
 1 file changed, 2 insertions(+), 44 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 1dcb8a113b4f..ebed87a64c98 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1636,7 +1636,7 @@ static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv)
 	 * Disable SSA Precharge when CD clock frequency < 500 MHz,
 	 * enable otherwise.
 	 */
-	if (dev_priv->cdclk.hw.cdclk >= 500000)
+	if (IS_GEN9_LP(dev_priv) && dev_priv->cdclk.hw.cdclk >= 500000)
 		expected |= BXT_CDCLK_SSA_PRECHARGE_ENABLE;
 
 	if (cdctl == expected)
@@ -1688,48 +1688,6 @@ static void bxt_uninit_cdclk(struct drm_i915_private *dev_priv)
 	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
 
-static void cnl_sanitize_cdclk(struct drm_i915_private *dev_priv)
-{
-	u32 cdctl, expected;
-
-	intel_update_cdclk(dev_priv);
-	intel_dump_cdclk_state(&dev_priv->cdclk.hw, "Current CDCLK");
-
-	if (dev_priv->cdclk.hw.vco == 0 ||
-	    dev_priv->cdclk.hw.cdclk == dev_priv->cdclk.hw.bypass)
-		goto sanitize;
-
-	/* DPLL okay; verify the cdclock
-	 *
-	 * Some BIOS versions leave an incorrect decimal frequency value and
-	 * set reserved MBZ bits in CDCLK_CTL at least during exiting from S4,
-	 * so sanitize this register.
-	 */
-	cdctl = I915_READ(CDCLK_CTL);
-	/*
-	 * Let's ignore the pipe field, since BIOS could have configured the
-	 * dividers both synching to an active pipe, or asynchronously
-	 * (PIPE_NONE).
-	 */
-	cdctl &= ~BXT_CDCLK_CD2X_PIPE_NONE;
-
-	expected = (cdctl & BXT_CDCLK_CD2X_DIV_SEL_MASK) |
-		   skl_cdclk_decimal(dev_priv->cdclk.hw.cdclk);
-
-	if (cdctl == expected)
-		/* All well; nothing to sanitize */
-		return;
-
-sanitize:
-	DRM_DEBUG_KMS("Sanitizing cdclk programmed by pre-os\n");
-
-	/* force cdclk programming */
-	dev_priv->cdclk.hw.cdclk = 0;
-
-	/* force full PLL disable + enable */
-	dev_priv->cdclk.hw.vco = -1;
-}
-
 static void icl_init_cdclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_cdclk_state sanitized_state;
@@ -1791,7 +1749,7 @@ static void cnl_init_cdclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_cdclk_state cdclk_state;
 
-	cnl_sanitize_cdclk(dev_priv);
+	bxt_sanitize_cdclk(dev_priv);
 
 	if (dev_priv->cdclk.hw.cdclk != 0 &&
 	    dev_priv->cdclk.hw.vco != 0)
-- 
cgit v1.2.3


From 751a93a15cde277ada4e1be14d93eb13a0dc3edd Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Tue, 10 Sep 2019 08:42:49 -0700
Subject: drm/i915: Consolidate {bxt,cnl,icl}_uninit_cdclk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The uninitialize flow is the same on all of these platforms, aside from
calculating a different frequency level.

v2: Reverse platform conditional order for consistency.  (Ville)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910154252.30503-6-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 48 +++++++++---------------------
 1 file changed, 14 insertions(+), 34 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index ebed87a64c98..679aeebfbca5 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1683,7 +1683,18 @@ static void bxt_uninit_cdclk(struct drm_i915_private *dev_priv)
 
 	cdclk_state.cdclk = cdclk_state.bypass;
 	cdclk_state.vco = 0;
-	cdclk_state.voltage_level = bxt_calc_voltage_level(cdclk_state.cdclk);
+	if (IS_ELKHARTLAKE(dev_priv))
+		cdclk_state.voltage_level =
+			ehl_calc_voltage_level(cdclk_state.cdclk);
+	else if (INTEL_GEN(dev_priv) >= 11)
+		cdclk_state.voltage_level =
+			icl_calc_voltage_level(cdclk_state.cdclk);
+	else if (INTEL_GEN(dev_priv) >= 10)
+		cdclk_state.voltage_level =
+			cnl_calc_voltage_level(cdclk_state.cdclk);
+	else
+		cdclk_state.voltage_level =
+			bxt_calc_voltage_level(cdclk_state.cdclk);
 
 	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
@@ -1729,22 +1740,6 @@ sanitize:
 	bxt_set_cdclk(dev_priv, &sanitized_state, INVALID_PIPE);
 }
 
-static void icl_uninit_cdclk(struct drm_i915_private *dev_priv)
-{
-	struct intel_cdclk_state cdclk_state = dev_priv->cdclk.hw;
-
-	cdclk_state.cdclk = cdclk_state.bypass;
-	cdclk_state.vco = 0;
-	if (IS_ELKHARTLAKE(dev_priv))
-		cdclk_state.voltage_level =
-			ehl_calc_voltage_level(cdclk_state.cdclk);
-	else
-		cdclk_state.voltage_level =
-			icl_calc_voltage_level(cdclk_state.cdclk);
-
-	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
-}
-
 static void cnl_init_cdclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_cdclk_state cdclk_state;
@@ -1764,17 +1759,6 @@ static void cnl_init_cdclk(struct drm_i915_private *dev_priv)
 	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
 
-static void cnl_uninit_cdclk(struct drm_i915_private *dev_priv)
-{
-	struct intel_cdclk_state cdclk_state = dev_priv->cdclk.hw;
-
-	cdclk_state.cdclk = cdclk_state.bypass;
-	cdclk_state.vco = 0;
-	cdclk_state.voltage_level = cnl_calc_voltage_level(cdclk_state.cdclk);
-
-	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
-}
-
 /**
  * intel_cdclk_init - Initialize CDCLK
  * @i915: i915 device
@@ -1805,14 +1789,10 @@ void intel_cdclk_init(struct drm_i915_private *i915)
  */
 void intel_cdclk_uninit(struct drm_i915_private *i915)
 {
-	if (INTEL_GEN(i915) >= 11)
-		icl_uninit_cdclk(i915);
-	else if (IS_CANNONLAKE(i915))
-		cnl_uninit_cdclk(i915);
+	if (INTEL_GEN(i915) >= 10 || IS_GEN9_LP(i915))
+		bxt_uninit_cdclk(i915);
 	else if (IS_GEN9_BC(i915))
 		skl_uninit_cdclk(i915);
-	else if (IS_GEN9_LP(i915))
-		bxt_uninit_cdclk(i915);
 }
 
 /**
-- 
cgit v1.2.3


From d2f429ebb97725e9bec597aad2f0d2c7d203842f Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Tue, 10 Sep 2019 08:42:50 -0700
Subject: drm/i915: Add calc_voltage_level display vfunc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With all of the cdclk function consolidation, we can cut down on a lot
of platform if/else logic by creating a vfunc that's initialized at
startup.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910154252.30503-7-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 75 +++++++++++-------------------
 drivers/gpu/drm/i915/i915_drv.h            |  1 +
 2 files changed, 27 insertions(+), 49 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 679aeebfbca5..e1a4ac9bd4f0 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1394,18 +1394,8 @@ static void bxt_get_cdclk(struct drm_i915_private *dev_priv,
 	 * Can't read this out :( Let's assume it's
 	 * at least what the CDCLK frequency requires.
 	 */
-	if (IS_ELKHARTLAKE(dev_priv))
-		cdclk_state->voltage_level =
-			ehl_calc_voltage_level(cdclk_state->cdclk);
-	else if (INTEL_GEN(dev_priv) >= 11)
-		cdclk_state->voltage_level =
-			icl_calc_voltage_level(cdclk_state->cdclk);
-	else if (INTEL_GEN(dev_priv) >= 10)
-		cdclk_state->voltage_level =
-			cnl_calc_voltage_level(cdclk_state->cdclk);
-	else
-		cdclk_state->voltage_level =
-			bxt_calc_voltage_level(cdclk_state->cdclk);
+	cdclk_state->voltage_level =
+		dev_priv->display.calc_voltage_level(cdclk_state->cdclk);
 }
 
 static void bxt_de_pll_disable(struct drm_i915_private *dev_priv)
@@ -1672,7 +1662,8 @@ static void bxt_init_cdclk(struct drm_i915_private *dev_priv)
 	 */
 	cdclk_state.cdclk = bxt_calc_cdclk(dev_priv, 0);
 	cdclk_state.vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk_state.cdclk);
-	cdclk_state.voltage_level = bxt_calc_voltage_level(cdclk_state.cdclk);
+	cdclk_state.voltage_level =
+		dev_priv->display.calc_voltage_level(cdclk_state.cdclk);
 
 	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
@@ -1683,18 +1674,8 @@ static void bxt_uninit_cdclk(struct drm_i915_private *dev_priv)
 
 	cdclk_state.cdclk = cdclk_state.bypass;
 	cdclk_state.vco = 0;
-	if (IS_ELKHARTLAKE(dev_priv))
-		cdclk_state.voltage_level =
-			ehl_calc_voltage_level(cdclk_state.cdclk);
-	else if (INTEL_GEN(dev_priv) >= 11)
-		cdclk_state.voltage_level =
-			icl_calc_voltage_level(cdclk_state.cdclk);
-	else if (INTEL_GEN(dev_priv) >= 10)
-		cdclk_state.voltage_level =
-			cnl_calc_voltage_level(cdclk_state.cdclk);
-	else
-		cdclk_state.voltage_level =
-			bxt_calc_voltage_level(cdclk_state.cdclk);
+	cdclk_state.voltage_level =
+		dev_priv->display.calc_voltage_level(cdclk_state.cdclk);
 
 	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
@@ -1730,12 +1711,8 @@ sanitize:
 	sanitized_state.cdclk = bxt_calc_cdclk(dev_priv, 0);
 	sanitized_state.vco = bxt_calc_cdclk_pll_vco(dev_priv,
 						     sanitized_state.cdclk);
-	if (IS_ELKHARTLAKE(dev_priv))
-		sanitized_state.voltage_level =
-			ehl_calc_voltage_level(sanitized_state.cdclk);
-	else
-		sanitized_state.voltage_level =
-			icl_calc_voltage_level(sanitized_state.cdclk);
+	sanitized_state.voltage_level =
+		dev_priv->display.calc_voltage_level(sanitized_state.cdclk);
 
 	bxt_set_cdclk(dev_priv, &sanitized_state, INVALID_PIPE);
 }
@@ -1754,7 +1731,8 @@ static void cnl_init_cdclk(struct drm_i915_private *dev_priv)
 
 	cdclk_state.cdclk = bxt_calc_cdclk(dev_priv, 0);
 	cdclk_state.vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk_state.cdclk);
-	cdclk_state.voltage_level = cnl_calc_voltage_level(cdclk_state.cdclk);
+	cdclk_state.voltage_level =
+		dev_priv->display.calc_voltage_level(cdclk_state.cdclk);
 
 	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
@@ -2246,7 +2224,7 @@ static int bxt_modeset_calc_cdclk(struct intel_atomic_state *state)
 	state->cdclk.logical.vco = vco;
 	state->cdclk.logical.cdclk = cdclk;
 	state->cdclk.logical.voltage_level =
-		bxt_calc_voltage_level(cdclk);
+		dev_priv->display.calc_voltage_level(cdclk);
 
 	if (!state->active_pipes) {
 		cdclk = bxt_calc_cdclk(dev_priv, state->cdclk.force_min_cdclk);
@@ -2255,7 +2233,7 @@ static int bxt_modeset_calc_cdclk(struct intel_atomic_state *state)
 		state->cdclk.actual.vco = vco;
 		state->cdclk.actual.cdclk = cdclk;
 		state->cdclk.actual.voltage_level =
-			bxt_calc_voltage_level(cdclk);
+			dev_priv->display.calc_voltage_level(cdclk);
 	} else {
 		state->cdclk.actual = state->cdclk.logical;
 	}
@@ -2310,14 +2288,9 @@ static int icl_modeset_calc_cdclk(struct intel_atomic_state *state)
 
 	state->cdclk.logical.vco = vco;
 	state->cdclk.logical.cdclk = cdclk;
-	if (IS_ELKHARTLAKE(dev_priv))
-		state->cdclk.logical.voltage_level =
-			max(ehl_calc_voltage_level(cdclk),
-			    cnl_compute_min_voltage_level(state));
-	else
-		state->cdclk.logical.voltage_level =
-			max(icl_calc_voltage_level(cdclk),
-			    cnl_compute_min_voltage_level(state));
+	state->cdclk.logical.voltage_level =
+		max(dev_priv->display.calc_voltage_level(cdclk),
+		    cnl_compute_min_voltage_level(state));
 
 	if (!state->active_pipes) {
 		cdclk = bxt_calc_cdclk(dev_priv, state->cdclk.force_min_cdclk);
@@ -2325,12 +2298,8 @@ static int icl_modeset_calc_cdclk(struct intel_atomic_state *state)
 
 		state->cdclk.actual.vco = vco;
 		state->cdclk.actual.cdclk = cdclk;
-		if (IS_ELKHARTLAKE(dev_priv))
-			state->cdclk.actual.voltage_level =
-				ehl_calc_voltage_level(cdclk);
-		else
-			state->cdclk.actual.voltage_level =
-				icl_calc_voltage_level(cdclk);
+		state->cdclk.actual.voltage_level =
+			dev_priv->display.calc_voltage_level(cdclk);
 	} else {
 		state->cdclk.actual = state->cdclk.logical;
 	}
@@ -2554,17 +2523,25 @@ void intel_update_rawclk(struct drm_i915_private *dev_priv)
  */
 void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 {
-	if (INTEL_GEN(dev_priv) >= 11) {
+	if (IS_ELKHARTLAKE(dev_priv)) {
+		dev_priv->display.set_cdclk = bxt_set_cdclk;
+		dev_priv->display.modeset_calc_cdclk = icl_modeset_calc_cdclk;
+		dev_priv->display.calc_voltage_level = ehl_calc_voltage_level;
+		dev_priv->cdclk.table = icl_cdclk_table;
+	} else if (INTEL_GEN(dev_priv) >= 11) {
 		dev_priv->display.set_cdclk = bxt_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = icl_modeset_calc_cdclk;
+		dev_priv->display.calc_voltage_level = icl_calc_voltage_level;
 		dev_priv->cdclk.table = icl_cdclk_table;
 	} else if (IS_CANNONLAKE(dev_priv)) {
 		dev_priv->display.set_cdclk = bxt_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = cnl_modeset_calc_cdclk;
+		dev_priv->display.calc_voltage_level = cnl_calc_voltage_level;
 		dev_priv->cdclk.table = cnl_cdclk_table;
 	} else if (IS_GEN9_LP(dev_priv)) {
 		dev_priv->display.set_cdclk = bxt_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk;
+		dev_priv->display.calc_voltage_level = bxt_calc_voltage_level;
 		dev_priv->cdclk.table = bxt_cdclk_table;
 	} else if (IS_GEN9_BC(dev_priv)) {
 		dev_priv->display.set_cdclk = skl_set_cdclk;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ff6aff2a4866..dc4d40b44d74 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -276,6 +276,7 @@ struct drm_i915_display_funcs {
 	int (*compute_global_watermarks)(struct intel_atomic_state *state);
 	void (*update_wm)(struct intel_crtc *crtc);
 	int (*modeset_calc_cdclk)(struct intel_atomic_state *state);
+	u8 (*calc_voltage_level)(int cdclk);
 	/* Returns the active state of the crtc, and if the crtc is active,
 	 * fills out the pipe-config with the hw state. */
 	bool (*get_pipe_config)(struct intel_crtc *,
-- 
cgit v1.2.3


From 8f9f717d6c44649353e153cfcd32ad99618956a9 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Tue, 10 Sep 2019 08:42:51 -0700
Subject: drm/i915: Enhance cdclk sanitization
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When reading out the BIOS-programmed cdclk state, let's make sure that
the cdclk value is on the valid list for the platform, ensure that the
VCO matches the cdclk, and ensure that the CD2X divider was set
properly.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910154252.30503-8-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 34 ++++++++++++++++++++++++++++--
 1 file changed, 32 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index e1a4ac9bd4f0..988d0849ce09 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1598,6 +1598,7 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv)
 {
 	u32 cdctl, expected;
+	int cdclk, vco;
 
 	intel_update_cdclk(dev_priv);
 	intel_dump_cdclk_state(&dev_priv->cdclk.hw, "Current CDCLK");
@@ -1620,8 +1621,37 @@ static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv)
 	 */
 	cdctl &= ~BXT_CDCLK_CD2X_PIPE_NONE;
 
-	expected = (cdctl & BXT_CDCLK_CD2X_DIV_SEL_MASK) |
-		skl_cdclk_decimal(dev_priv->cdclk.hw.cdclk);
+	/* Make sure this is a legal cdclk value for the platform */
+	cdclk = bxt_calc_cdclk(dev_priv, dev_priv->cdclk.hw.cdclk);
+	if (cdclk != dev_priv->cdclk.hw.cdclk)
+		goto sanitize;
+
+	/* Make sure the VCO is correct for the cdclk */
+	vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
+	if (vco != dev_priv->cdclk.hw.vco)
+		goto sanitize;
+
+	expected = skl_cdclk_decimal(cdclk);
+
+	/* Figure out what CD2X divider we should be using for this cdclk */
+	switch (DIV_ROUND_CLOSEST(dev_priv->cdclk.hw.vco,
+				  dev_priv->cdclk.hw.cdclk)) {
+	case 2:
+		expected |= BXT_CDCLK_CD2X_DIV_SEL_1;
+		break;
+	case 3:
+		expected |= BXT_CDCLK_CD2X_DIV_SEL_1_5;
+		break;
+	case 4:
+		expected |= BXT_CDCLK_CD2X_DIV_SEL_2;
+		break;
+	case 8:
+		expected |= BXT_CDCLK_CD2X_DIV_SEL_4;
+		break;
+	default:
+		goto sanitize;
+	}
+
 	/*
 	 * Disable SSA Precharge when CD clock frequency < 500 MHz,
 	 * enable otherwise.
-- 
cgit v1.2.3


From 0c1279b58fc7de230d47bb0dc21b7a08417dee96 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Tue, 10 Sep 2019 08:42:52 -0700
Subject: drm/i915: Consolidate {bxt,cnl,icl}_init_cdclk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The BXT and CNL functions were already basically identical, whereas
ICL's function tried to do its own sanitization rather than calling
bxt_sanitize_cdclk.

This should actually fix a bug in our ICL initialization where it would
consider the /2 CD2X divider invalid and force an unnecessary
sanitization (we now have valid clock frequencies that use this
divider).

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910154252.30503-9-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 65 +-----------------------------
 1 file changed, 2 insertions(+), 63 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 988d0849ce09..618a93bad0a8 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1710,63 +1710,6 @@ static void bxt_uninit_cdclk(struct drm_i915_private *dev_priv)
 	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
 }
 
-static void icl_init_cdclk(struct drm_i915_private *dev_priv)
-{
-	struct intel_cdclk_state sanitized_state;
-	u32 val;
-
-	/* This sets dev_priv->cdclk.hw. */
-	intel_update_cdclk(dev_priv);
-	intel_dump_cdclk_state(&dev_priv->cdclk.hw, "Current CDCLK");
-
-	/* This means CDCLK disabled. */
-	if (dev_priv->cdclk.hw.cdclk == dev_priv->cdclk.hw.bypass)
-		goto sanitize;
-
-	val = I915_READ(CDCLK_CTL);
-
-	if ((val & BXT_CDCLK_CD2X_DIV_SEL_MASK) != 0)
-		goto sanitize;
-
-	if ((val & CDCLK_FREQ_DECIMAL_MASK) !=
-	    skl_cdclk_decimal(dev_priv->cdclk.hw.cdclk))
-		goto sanitize;
-
-	return;
-
-sanitize:
-	DRM_DEBUG_KMS("Sanitizing cdclk programmed by pre-os\n");
-
-	sanitized_state.ref = dev_priv->cdclk.hw.ref;
-	sanitized_state.cdclk = bxt_calc_cdclk(dev_priv, 0);
-	sanitized_state.vco = bxt_calc_cdclk_pll_vco(dev_priv,
-						     sanitized_state.cdclk);
-	sanitized_state.voltage_level =
-		dev_priv->display.calc_voltage_level(sanitized_state.cdclk);
-
-	bxt_set_cdclk(dev_priv, &sanitized_state, INVALID_PIPE);
-}
-
-static void cnl_init_cdclk(struct drm_i915_private *dev_priv)
-{
-	struct intel_cdclk_state cdclk_state;
-
-	bxt_sanitize_cdclk(dev_priv);
-
-	if (dev_priv->cdclk.hw.cdclk != 0 &&
-	    dev_priv->cdclk.hw.vco != 0)
-		return;
-
-	cdclk_state = dev_priv->cdclk.hw;
-
-	cdclk_state.cdclk = bxt_calc_cdclk(dev_priv, 0);
-	cdclk_state.vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk_state.cdclk);
-	cdclk_state.voltage_level =
-		dev_priv->display.calc_voltage_level(cdclk_state.cdclk);
-
-	bxt_set_cdclk(dev_priv, &cdclk_state, INVALID_PIPE);
-}
-
 /**
  * intel_cdclk_init - Initialize CDCLK
  * @i915: i915 device
@@ -1778,14 +1721,10 @@ static void cnl_init_cdclk(struct drm_i915_private *dev_priv)
  */
 void intel_cdclk_init(struct drm_i915_private *i915)
 {
-	if (INTEL_GEN(i915) >= 11)
-		icl_init_cdclk(i915);
-	else if (IS_CANNONLAKE(i915))
-		cnl_init_cdclk(i915);
+	if (IS_GEN9_LP(i915) || INTEL_GEN(i915) >= 10)
+		bxt_init_cdclk(i915);
 	else if (IS_GEN9_BC(i915))
 		skl_init_cdclk(i915);
-	else if (IS_GEN9_LP(i915))
-		bxt_init_cdclk(i915);
 }
 
 /**
-- 
cgit v1.2.3


From 61fa60ff6e6a0e16e9bcc15f632ce5437afa6494 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Tue, 10 Sep 2019 15:38:20 +0100
Subject: drm/i915: Move GT init to intel_gt.c

Code in i915_gem_init_hw is all about GT init so move it to intel_gt.c
renaming to intel_gt_init_hw.

Existing intel_gt_init_hw is renamed to intel_gt_init_hw_early since it
is currently called from driver probe.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Andi Shyti <andi.shyti@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910143823.10686-2-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/gem/i915_gem_pm.c    |  2 +-
 drivers/gpu/drm/i915/gt/intel_gt.c        | 92 ++++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/gt/intel_gt.h        |  3 +-
 drivers/gpu/drm/i915/gt/intel_reset.c     |  2 +-
 drivers/gpu/drm/i915/i915_drv.c           |  2 +-
 drivers/gpu/drm/i915/i915_drv.h           |  1 -
 drivers/gpu/drm/i915/i915_gem.c           | 91 +-----------------------------
 drivers/gpu/drm/i915/selftests/mock_gtt.c |  2 +-
 8 files changed, 98 insertions(+), 97 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 9b1129aaacfe..3bd764104d41 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -242,7 +242,7 @@ void i915_gem_resume(struct drm_i915_private *i915)
 	mutex_lock(&i915->drm.struct_mutex);
 	intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
 
-	if (i915_gem_init_hw(i915))
+	if (intel_gt_init_hw(&i915->gt))
 		goto err_wedged;
 
 	/*
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index e2cc697d27fb..eef9bdae8ebb 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -6,6 +6,7 @@
 #include "i915_drv.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
+#include "intel_mocs.h"
 #include "intel_uncore.h"
 #include "intel_pm.h"
 
@@ -25,7 +26,7 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 	intel_uc_init_early(&gt->uc);
 }
 
-void intel_gt_init_hw(struct drm_i915_private *i915)
+void intel_gt_init_hw_early(struct drm_i915_private *i915)
 {
 	i915->gt.ggtt = &i915->ggtt;
 
@@ -33,6 +34,95 @@ void intel_gt_init_hw(struct drm_i915_private *i915)
 	intel_gt_pm_disable(&i915->gt);
 }
 
+static void init_unused_ring(struct intel_gt *gt, u32 base)
+{
+	struct intel_uncore *uncore = gt->uncore;
+
+	intel_uncore_write(uncore, RING_CTL(base), 0);
+	intel_uncore_write(uncore, RING_HEAD(base), 0);
+	intel_uncore_write(uncore, RING_TAIL(base), 0);
+	intel_uncore_write(uncore, RING_START(base), 0);
+}
+
+static void init_unused_rings(struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+
+	if (IS_I830(i915)) {
+		init_unused_ring(gt, PRB1_BASE);
+		init_unused_ring(gt, SRB0_BASE);
+		init_unused_ring(gt, SRB1_BASE);
+		init_unused_ring(gt, SRB2_BASE);
+		init_unused_ring(gt, SRB3_BASE);
+	} else if (IS_GEN(i915, 2)) {
+		init_unused_ring(gt, SRB0_BASE);
+		init_unused_ring(gt, SRB1_BASE);
+	} else if (IS_GEN(i915, 3)) {
+		init_unused_ring(gt, PRB1_BASE);
+		init_unused_ring(gt, PRB2_BASE);
+	}
+}
+
+int intel_gt_init_hw(struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+	struct intel_uncore *uncore = gt->uncore;
+	int ret;
+
+	BUG_ON(!i915->kernel_context);
+	ret = intel_gt_terminally_wedged(gt);
+	if (ret)
+		return ret;
+
+	gt->last_init_time = ktime_get();
+
+	/* Double layer security blanket, see i915_gem_init() */
+	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
+
+	if (HAS_EDRAM(i915) && INTEL_GEN(i915) < 9)
+		intel_uncore_rmw(uncore, HSW_IDICR, 0, IDIHASHMSK(0xf));
+
+	if (IS_HASWELL(i915))
+		intel_uncore_write(uncore,
+				   MI_PREDICATE_RESULT_2,
+				   IS_HSW_GT3(i915) ?
+				   LOWER_SLICE_ENABLED : LOWER_SLICE_DISABLED);
+
+	/* Apply the GT workarounds... */
+	intel_gt_apply_workarounds(gt);
+	/* ...and determine whether they are sticking. */
+	intel_gt_verify_workarounds(gt, "init");
+
+	intel_gt_init_swizzling(gt);
+
+	/*
+	 * At least 830 can leave some of the unused rings
+	 * "active" (ie. head != tail) after resume which
+	 * will prevent c3 entry. Makes sure all unused rings
+	 * are totally idle.
+	 */
+	init_unused_rings(gt);
+
+	ret = i915_ppgtt_init_hw(gt);
+	if (ret) {
+		DRM_ERROR("Enabling PPGTT failed (%d)\n", ret);
+		goto out;
+	}
+
+	/* We can't enable contexts until all firmware is loaded */
+	ret = intel_uc_init_hw(&gt->uc);
+	if (ret) {
+		i915_probe_error(i915, "Enabling uc failed (%d)\n", ret);
+		goto out;
+	}
+
+	intel_mocs_init(gt);
+
+out:
+	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
+	return ret;
+}
+
 static void rmw_set(struct intel_uncore *uncore, i915_reg_t reg, u32 set)
 {
 	intel_uncore_rmw(uncore, reg, 0, set);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 17af21cb7ed3..e6ab0bff0efb 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -28,7 +28,8 @@ static inline struct intel_gt *huc_to_gt(struct intel_huc *huc)
 }
 
 void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915);
-void intel_gt_init_hw(struct drm_i915_private *i915);
+void intel_gt_init_hw_early(struct drm_i915_private *i915);
+int __must_check intel_gt_init_hw(struct intel_gt *gt);
 int intel_gt_init(struct intel_gt *gt);
 void intel_gt_driver_register(struct intel_gt *gt);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index b9d84d52e986..296bbc7745fb 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -972,7 +972,7 @@ void intel_gt_reset(struct intel_gt *gt,
 	 * was running at the time of the reset (i.e. we weren't VT
 	 * switched away).
 	 */
-	ret = i915_gem_init_hw(gt->i915);
+	ret = intel_gt_init_hw(gt);
 	if (ret) {
 		DRM_ERROR("Failed to initialise HW following reset (%d)\n",
 			  ret);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 0aadff9b8c88..8966672b0294 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1269,7 +1269,7 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 	if (ret)
 		goto err_ggtt;
 
-	intel_gt_init_hw(dev_priv);
+	intel_gt_init_hw_early(dev_priv);
 
 	ret = i915_ggtt_enable_hw(dev_priv);
 	if (ret) {
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index dc4d40b44d74..51d575cca2ac 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2322,7 +2322,6 @@ static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
 
 void i915_gem_init_mmio(struct drm_i915_private *i915);
 int __must_check i915_gem_init(struct drm_i915_private *dev_priv);
-int __must_check i915_gem_init_hw(struct drm_i915_private *dev_priv);
 void i915_gem_driver_register(struct drm_i915_private *i915);
 void i915_gem_driver_unregister(struct drm_i915_private *i915);
 void i915_gem_driver_remove(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 141024c66f36..db2681514a0b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1148,95 +1148,6 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 }
 
-static void init_unused_ring(struct intel_gt *gt, u32 base)
-{
-	struct intel_uncore *uncore = gt->uncore;
-
-	intel_uncore_write(uncore, RING_CTL(base), 0);
-	intel_uncore_write(uncore, RING_HEAD(base), 0);
-	intel_uncore_write(uncore, RING_TAIL(base), 0);
-	intel_uncore_write(uncore, RING_START(base), 0);
-}
-
-static void init_unused_rings(struct intel_gt *gt)
-{
-	struct drm_i915_private *i915 = gt->i915;
-
-	if (IS_I830(i915)) {
-		init_unused_ring(gt, PRB1_BASE);
-		init_unused_ring(gt, SRB0_BASE);
-		init_unused_ring(gt, SRB1_BASE);
-		init_unused_ring(gt, SRB2_BASE);
-		init_unused_ring(gt, SRB3_BASE);
-	} else if (IS_GEN(i915, 2)) {
-		init_unused_ring(gt, SRB0_BASE);
-		init_unused_ring(gt, SRB1_BASE);
-	} else if (IS_GEN(i915, 3)) {
-		init_unused_ring(gt, PRB1_BASE);
-		init_unused_ring(gt, PRB2_BASE);
-	}
-}
-
-int i915_gem_init_hw(struct drm_i915_private *i915)
-{
-	struct intel_uncore *uncore = &i915->uncore;
-	struct intel_gt *gt = &i915->gt;
-	int ret;
-
-	BUG_ON(!i915->kernel_context);
-	ret = intel_gt_terminally_wedged(gt);
-	if (ret)
-		return ret;
-
-	gt->last_init_time = ktime_get();
-
-	/* Double layer security blanket, see i915_gem_init() */
-	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
-
-	if (HAS_EDRAM(i915) && INTEL_GEN(i915) < 9)
-		intel_uncore_rmw(uncore, HSW_IDICR, 0, IDIHASHMSK(0xf));
-
-	if (IS_HASWELL(i915))
-		intel_uncore_write(uncore,
-				   MI_PREDICATE_RESULT_2,
-				   IS_HSW_GT3(i915) ?
-				   LOWER_SLICE_ENABLED : LOWER_SLICE_DISABLED);
-
-	/* Apply the GT workarounds... */
-	intel_gt_apply_workarounds(gt);
-	/* ...and determine whether they are sticking. */
-	intel_gt_verify_workarounds(gt, "init");
-
-	intel_gt_init_swizzling(gt);
-
-	/*
-	 * At least 830 can leave some of the unused rings
-	 * "active" (ie. head != tail) after resume which
-	 * will prevent c3 entry. Makes sure all unused rings
-	 * are totally idle.
-	 */
-	init_unused_rings(gt);
-
-	ret = i915_ppgtt_init_hw(gt);
-	if (ret) {
-		DRM_ERROR("Enabling PPGTT failed (%d)\n", ret);
-		goto out;
-	}
-
-	/* We can't enable contexts until all firmware is loaded */
-	ret = intel_uc_init_hw(&gt->uc);
-	if (ret) {
-		i915_probe_error(i915, "Enabling uc failed (%d)\n", ret);
-		goto out;
-	}
-
-	intel_mocs_init(gt);
-
-out:
-	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
-	return ret;
-}
-
 static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 {
 	struct i915_request *requests[I915_NUM_ENGINES] = {};
@@ -1449,7 +1360,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 
 	intel_uc_init(&dev_priv->gt.uc);
 
-	ret = i915_gem_init_hw(dev_priv);
+	ret = intel_gt_init_hw(&dev_priv->gt);
 	if (ret)
 		goto err_uc_init;
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index e62a67e0f79c..7d5fb60b43bb 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -118,7 +118,7 @@ void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt)
 
 	i915_address_space_init(&ggtt->vm, VM_CLASS_GGTT);
 
-	intel_gt_init_hw(i915);
+	intel_gt_init_hw_early(i915);
 }
 
 void mock_fini_ggtt(struct i915_ggtt *ggtt)
-- 
cgit v1.2.3


From dab3588a151e5edb0cb0d56476265d2e5b3b1c79 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Tue, 10 Sep 2019 15:38:21 +0100
Subject: drm/i915: Make wait_for_timelines take struct intel_gt

Timelines live in struct intel_gt so make wait_for_timelines take
exactly what it needs.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Andi Shyti <andi.shyti@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910143823.10686-3-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/i915_gem.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index db2681514a0b..2da9544fa9a4 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -888,10 +888,9 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915)
 }
 
 static long
-wait_for_timelines(struct drm_i915_private *i915,
-		   unsigned int wait, long timeout)
+wait_for_timelines(struct intel_gt *gt, unsigned int wait, long timeout)
 {
-	struct intel_gt_timelines *timelines = &i915->gt.timelines;
+	struct intel_gt_timelines *timelines = &gt->timelines;
 	struct intel_timeline *tl;
 	unsigned long flags;
 
@@ -934,15 +933,17 @@ wait_for_timelines(struct drm_i915_private *i915,
 int i915_gem_wait_for_idle(struct drm_i915_private *i915,
 			   unsigned int flags, long timeout)
 {
+	struct intel_gt *gt = &i915->gt;
+
 	/* If the device is asleep, we have no requests outstanding */
-	if (!intel_gt_pm_is_awake(&i915->gt))
+	if (!intel_gt_pm_is_awake(gt))
 		return 0;
 
 	GEM_TRACE("flags=%x (%s), timeout=%ld%s\n",
 		  flags, flags & I915_WAIT_LOCKED ? "locked" : "unlocked",
 		  timeout, timeout == MAX_SCHEDULE_TIMEOUT ? " (forever)" : "");
 
-	timeout = wait_for_timelines(i915, flags, timeout);
+	timeout = wait_for_timelines(gt, flags, timeout);
 	if (timeout < 0)
 		return timeout;
 
-- 
cgit v1.2.3


From ee236af8d51439ce2d4396ecaf84062b34b15f85 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Tue, 10 Sep 2019 15:38:22 +0100
Subject: drm/i915: Avoid round-trip via i915 in intel_gt_park

Both in the container_of and getting to gt->awake there is no need to go
via i915 since both the wakeref and awake are members of gt.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Andi Shyti <andi.shyti@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910143823.10686-4-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_gt_pm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 6ba0d2069f87..a2e29bcc9671 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -56,9 +56,9 @@ static int __gt_unpark(struct intel_wakeref *wf)
 
 static int __gt_park(struct intel_wakeref *wf)
 {
-	struct drm_i915_private *i915 =
-		container_of(wf, typeof(*i915), gt.wakeref);
-	intel_wakeref_t wakeref = fetch_and_zero(&i915->gt.awake);
+	struct intel_gt *gt = container_of(wf, typeof(*gt), wakeref);
+	intel_wakeref_t wakeref = fetch_and_zero(&gt->awake);
+	struct drm_i915_private *i915 = gt->i915;
 
 	GEM_TRACE("\n");
 
-- 
cgit v1.2.3


From 85dd14c2918d452fa875a4175bffb76e01c5af6e Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Tue, 10 Sep 2019 15:38:23 +0100
Subject: drm/i915: Make pm_notify take intel_gt

These notifications operate on intel_gt so make the code take what it
needs.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Andi Shyti <andi.shyti@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910143823.10686-5-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_gt_pm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index a2e29bcc9671..2ccf8cacaa0a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -13,9 +13,9 @@
 #include "intel_pm.h"
 #include "intel_wakeref.h"
 
-static void pm_notify(struct drm_i915_private *i915, int state)
+static void pm_notify(struct intel_gt *gt, int state)
 {
-	blocking_notifier_call_chain(&i915->gt.pm_notifications, state, i915);
+	blocking_notifier_call_chain(&gt->pm_notifications, state, gt->i915);
 }
 
 static int __gt_unpark(struct intel_wakeref *wf)
@@ -49,7 +49,7 @@ static int __gt_unpark(struct intel_wakeref *wf)
 
 	intel_gt_queue_hangcheck(gt);
 
-	pm_notify(i915, INTEL_GT_UNPARK);
+	pm_notify(gt, INTEL_GT_UNPARK);
 
 	return 0;
 }
@@ -62,7 +62,7 @@ static int __gt_park(struct intel_wakeref *wf)
 
 	GEM_TRACE("\n");
 
-	pm_notify(i915, INTEL_GT_PARK);
+	pm_notify(gt, INTEL_GT_PARK);
 
 	i915_pmu_gt_parked(i915);
 	if (INTEL_GEN(i915) >= 6)
-- 
cgit v1.2.3


From 99013b10100c4b552eec845ee2ca5604c8332e92 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 10 Sep 2019 22:22:04 +0100
Subject: drm/i915: Make shrink/unshrink be atomic

Add an atomic counter and always take the spinlock around the pin/unpin
events, so that we can perform the list manipulation concurrently.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910212204.17190-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_domain.c       |  3 +-
 drivers/gpu/drm/i915/gem/i915_gem_object_types.h |  1 +
 drivers/gpu/drm/i915/gem/i915_gem_pages.c        |  1 +
 drivers/gpu/drm/i915/gem/i915_gem_shrinker.c     | 36 ++++++++++++++----------
 drivers/gpu/drm/i915/gt/intel_context.c          |  2 +-
 5 files changed, 26 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index da3e7cf12aa1..55c3ab59e3aa 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -494,7 +494,8 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 
 		spin_lock_irqsave(&i915->mm.obj_lock, flags);
 
-		if (obj->mm.madv == I915_MADV_WILLNEED)
+		if (obj->mm.madv == I915_MADV_WILLNEED &&
+		    !atomic_read(&obj->mm.shrink_pin))
 			list_move_tail(&obj->mm.link, &i915->mm.shrink_list);
 
 		spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index a558edf15ec8..d695f187b790 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -156,6 +156,7 @@ struct drm_i915_gem_object {
 	struct {
 		struct mutex lock; /* protects the pages and their use */
 		atomic_t pages_pin_count;
+		atomic_t shrink_pin;
 
 		struct sg_table *pages;
 		void *mapping;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 18f0ce0135c1..2e941f093a20 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -71,6 +71,7 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
 			list = &i915->mm.shrink_list;
 		list_add_tail(&obj->mm.link, list);
 
+		atomic_set(&obj->mm.shrink_pin, 0);
 		spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
 	}
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index 4e55cfc2b0dc..d2c05d752909 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -516,46 +516,52 @@ void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915,
 
 void i915_gem_object_make_unshrinkable(struct drm_i915_gem_object *obj)
 {
+	struct drm_i915_private *i915 = obj_to_i915(obj);
+	unsigned long flags;
+
 	/*
 	 * We can only be called while the pages are pinned or when
 	 * the pages are released. If pinned, we should only be called
 	 * from a single caller under controlled conditions; and on release
 	 * only one caller may release us. Neither the two may cross.
 	 */
-	if (!list_empty(&obj->mm.link)) { /* pinned by caller */
-		struct drm_i915_private *i915 = obj_to_i915(obj);
-		unsigned long flags;
-
-		spin_lock_irqsave(&i915->mm.obj_lock, flags);
-		GEM_BUG_ON(list_empty(&obj->mm.link));
+	if (atomic_add_unless(&obj->mm.shrink_pin, 1, 0))
+		return;
 
+	spin_lock_irqsave(&i915->mm.obj_lock, flags);
+	if (!atomic_fetch_inc(&obj->mm.shrink_pin) &&
+	    !list_empty(&obj->mm.link)) {
 		list_del_init(&obj->mm.link);
 		i915->mm.shrink_count--;
 		i915->mm.shrink_memory -= obj->base.size;
-
-		spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
 	}
+	spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
 }
 
 static void __i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj,
 					      struct list_head *head)
 {
+	struct drm_i915_private *i915 = obj_to_i915(obj);
+	unsigned long flags;
+
 	GEM_BUG_ON(!i915_gem_object_has_pages(obj));
-	GEM_BUG_ON(!list_empty(&obj->mm.link));
+	if (!i915_gem_object_is_shrinkable(obj))
+		return;
 
-	if (i915_gem_object_is_shrinkable(obj)) {
-		struct drm_i915_private *i915 = obj_to_i915(obj);
-		unsigned long flags;
+	if (atomic_add_unless(&obj->mm.shrink_pin, -1, 1))
+		return;
 
-		spin_lock_irqsave(&i915->mm.obj_lock, flags);
-		GEM_BUG_ON(!kref_read(&obj->base.refcount));
+	spin_lock_irqsave(&i915->mm.obj_lock, flags);
+	GEM_BUG_ON(!kref_read(&obj->base.refcount));
+	if (atomic_dec_and_test(&obj->mm.shrink_pin)) {
+		GEM_BUG_ON(!list_empty(&obj->mm.link));
 
 		list_add_tail(&obj->mm.link, head);
 		i915->mm.shrink_count++;
 		i915->mm.shrink_memory += obj->base.size;
 
-		spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
 	}
+	spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
 }
 
 void i915_gem_object_make_shrinkable(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index f55691d151ae..c0495811f493 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -134,8 +134,8 @@ static int __context_pin_state(struct i915_vma *vma)
 
 static void __context_unpin_state(struct i915_vma *vma)
 {
-	__i915_vma_unpin(vma);
 	i915_vma_make_shrinkable(vma);
+	__i915_vma_unpin(vma);
 }
 
 static void __intel_context_retire(struct i915_active *active)
-- 
cgit v1.2.3


From 0606259e3b3a1220a0f04a92a1654a3f674f47ee Mon Sep 17 00:00:00 2001
From: Kenneth Graunke <kenneth@whitecape.org>
Date: Tue, 10 Sep 2019 18:48:01 -0700
Subject: drm/i915: Whitelist COMMON_SLICE_CHICKEN2

This allows userspace to use "legacy" mode for push constants, where
they are committed at 3DPRIMITIVE or flush time, rather than being
committed at 3DSTATE_BINDING_TABLE_POINTERS_XS time.  Gen6-8 and Gen11
both use the "legacy" behavior - only Gen9 works in the "new" way.

Conflating push constants with binding tables is painful for userspace,
we would like to be able to avoid doing so.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Cc: stable@vger.kernel.org
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911014801.26821-1-kenneth@whitecape.org
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 243d3f77be13..41d0f786e06d 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1062,6 +1062,9 @@ static void gen9_whitelist_build(struct i915_wa_list *w)
 
 	/* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl,glk,cfl */
 	whitelist_reg(w, GEN8_HDC_CHICKEN1);
+
+	/* WaSendPushConstantsFromMMIO:skl,bxt */
+	whitelist_reg(w, COMMON_SLICE_CHICKEN2);
 }
 
 static void skl_whitelist_build(struct intel_engine_cs *engine)
-- 
cgit v1.2.3


From 4dd2fbbfb532d0981b0ecd218c0597ac0047ca55 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 11 Sep 2019 10:02:43 +0100
Subject: drm/i915: Make i915_vma.flags atomic_t for mutex reduction

In preparation for reducing struct_mutex stranglehold around the vm,
make the vma.flags atomic so that we can acquire a pin on the vma
atomically before deciding if we need to take the mutex.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911090243.16786-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_object.c |  2 +-
 drivers/gpu/drm/i915/gem/i915_gem_stolen.c |  2 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c        | 14 +++----
 drivers/gpu/drm/i915/i915_vma.c            | 29 +++++++-------
 drivers/gpu/drm/i915/i915_vma.h            | 62 ++++++++++++++++++------------
 drivers/gpu/drm/i915/selftests/mock_gtt.c  |  4 +-
 6 files changed, 64 insertions(+), 49 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index d7855dc5a5c5..0ef60dae23a7 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -163,7 +163,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 
 		list_for_each_entry_safe(vma, vn, &obj->vma.list, obj_link) {
 			GEM_BUG_ON(i915_vma_is_active(vma));
-			vma->flags &= ~I915_VMA_PIN_MASK;
+			atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
 			i915_vma_destroy(vma);
 		}
 		GEM_BUG_ON(!list_empty(&obj->vma.list));
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index 7ce5259d73d6..bfbc3e3daf92 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -688,7 +688,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 
 	vma->pages = obj->mm.pages;
-	vma->flags |= I915_VMA_GLOBAL_BIND;
+	set_bit(I915_VMA_GLOBAL_BIND_BIT, __i915_vma_flags(vma));
 	__i915_vma_set_map_and_fenceable(vma);
 
 	mutex_lock(&ggtt->vm.mutex);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 48688d683e95..e4f66bfe74c2 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -155,7 +155,7 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
 	u32 pte_flags;
 	int err;
 
-	if (!(vma->flags & I915_VMA_LOCAL_BIND)) {
+	if (!i915_vma_is_bound(vma, I915_VMA_LOCAL_BIND)) {
 		err = vma->vm->allocate_va_range(vma->vm,
 						 vma->node.start, vma->size);
 		if (err)
@@ -1877,7 +1877,7 @@ static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
 
 	vma->size = size;
 	vma->fence_size = size;
-	vma->flags = I915_VMA_GGTT;
+	atomic_set(&vma->flags, I915_VMA_GGTT);
 	vma->ggtt_view.type = I915_GGTT_VIEW_ROTATED; /* prevent fencing */
 
 	INIT_LIST_HEAD(&vma->obj_link);
@@ -2440,7 +2440,7 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 	 * GLOBAL/LOCAL_BIND, it's all the same ptes. Hence unconditionally
 	 * upgrade to both bound if we bind either to avoid double-binding.
 	 */
-	vma->flags |= I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
+	atomic_or(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND, &vma->flags);
 
 	return 0;
 }
@@ -2470,7 +2470,7 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 	if (flags & I915_VMA_LOCAL_BIND) {
 		struct i915_ppgtt *alias = i915_vm_to_ggtt(vma->vm)->alias;
 
-		if (!(vma->flags & I915_VMA_LOCAL_BIND)) {
+		if (!i915_vma_is_bound(vma, I915_VMA_LOCAL_BIND)) {
 			ret = alias->vm.allocate_va_range(&alias->vm,
 							  vma->node.start,
 							  vma->size);
@@ -2498,7 +2498,7 @@ static void aliasing_gtt_unbind_vma(struct i915_vma *vma)
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
 
-	if (vma->flags & I915_VMA_GLOBAL_BIND) {
+	if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) {
 		struct i915_address_space *vm = vma->vm;
 		intel_wakeref_t wakeref;
 
@@ -2506,7 +2506,7 @@ static void aliasing_gtt_unbind_vma(struct i915_vma *vma)
 			vm->clear_range(vm, vma->node.start, vma->size);
 	}
 
-	if (vma->flags & I915_VMA_LOCAL_BIND) {
+	if (i915_vma_is_bound(vma, I915_VMA_LOCAL_BIND)) {
 		struct i915_address_space *vm =
 			&i915_vm_to_ggtt(vma->vm)->alias->vm;
 
@@ -3308,7 +3308,7 @@ static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
 	list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link) {
 		struct drm_i915_gem_object *obj = vma->obj;
 
-		if (!(vma->flags & I915_VMA_GLOBAL_BIND))
+		if (!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
 			continue;
 
 		mutex_unlock(&ggtt->vm.mutex);
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 68d9f9b4d050..411047d6a909 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -171,7 +171,7 @@ vma_create(struct drm_i915_gem_object *obj,
 								i915_gem_object_get_stride(obj));
 		GEM_BUG_ON(!is_power_of_2(vma->fence_alignment));
 
-		vma->flags |= I915_VMA_GGTT;
+		__set_bit(I915_VMA_GGTT_BIT, __i915_vma_flags(vma));
 	}
 
 	spin_lock(&obj->vma.lock);
@@ -325,7 +325,8 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 	if (flags & PIN_USER)
 		bind_flags |= I915_VMA_LOCAL_BIND;
 
-	vma_flags = vma->flags & (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND);
+	vma_flags = atomic_read(&vma->flags);
+	vma_flags &= I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
 	if (flags & PIN_UPDATE)
 		bind_flags |= vma_flags;
 	else
@@ -340,7 +341,7 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 	if (ret)
 		return ret;
 
-	vma->flags |= bind_flags;
+	atomic_or(bind_flags, &vma->flags);
 	return 0;
 }
 
@@ -359,7 +360,7 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 	}
 
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
-	GEM_BUG_ON((vma->flags & I915_VMA_GLOBAL_BIND) == 0);
+	GEM_BUG_ON(!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND));
 
 	ptr = vma->iomap;
 	if (ptr == NULL) {
@@ -472,9 +473,9 @@ void __i915_vma_set_map_and_fenceable(struct i915_vma *vma)
 	mappable = vma->node.start + vma->fence_size <= i915_vm_to_ggtt(vma->vm)->mappable_end;
 
 	if (mappable && fenceable)
-		vma->flags |= I915_VMA_CAN_FENCE;
+		set_bit(I915_VMA_CAN_FENCE_BIT, __i915_vma_flags(vma));
 	else
-		vma->flags &= ~I915_VMA_CAN_FENCE;
+		clear_bit(I915_VMA_CAN_FENCE_BIT, __i915_vma_flags(vma));
 }
 
 bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long color)
@@ -544,7 +545,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	int ret;
 
 	GEM_BUG_ON(i915_vma_is_closed(vma));
-	GEM_BUG_ON(vma->flags & (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
+	GEM_BUG_ON(i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
 	GEM_BUG_ON(drm_mm_node_allocated(&vma->node));
 
 	size = max(size, vma->size);
@@ -678,7 +679,7 @@ static void
 i915_vma_remove(struct i915_vma *vma)
 {
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
-	GEM_BUG_ON(vma->flags & (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
+	GEM_BUG_ON(i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
 
 	vma->ops->clear_pages(vma);
 
@@ -709,7 +710,7 @@ i915_vma_remove(struct i915_vma *vma)
 int __i915_vma_do_pin(struct i915_vma *vma,
 		      u64 size, u64 alignment, u64 flags)
 {
-	const unsigned int bound = vma->flags;
+	const unsigned int bound = atomic_read(&vma->flags);
 	int ret;
 
 	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
@@ -732,9 +733,9 @@ int __i915_vma_do_pin(struct i915_vma *vma,
 	if (ret)
 		goto err_remove;
 
-	GEM_BUG_ON((vma->flags & I915_VMA_BIND_MASK) == 0);
+	GEM_BUG_ON(!i915_vma_is_bound(vma, I915_VMA_BIND_MASK));
 
-	if ((bound ^ vma->flags) & I915_VMA_GLOBAL_BIND)
+	if ((bound ^ atomic_read(&vma->flags)) & I915_VMA_GLOBAL_BIND)
 		__i915_vma_set_map_and_fenceable(vma);
 
 	GEM_BUG_ON(i915_vma_misplaced(vma, size, alignment, flags));
@@ -744,7 +745,7 @@ err_remove:
 	if ((bound & I915_VMA_BIND_MASK) == 0) {
 		i915_vma_remove(vma);
 		GEM_BUG_ON(vma->pages);
-		GEM_BUG_ON(vma->flags & I915_VMA_BIND_MASK);
+		GEM_BUG_ON(atomic_read(&vma->flags) & I915_VMA_BIND_MASK);
 	}
 err_unpin:
 	__i915_vma_unpin(vma);
@@ -991,7 +992,7 @@ int i915_vma_unbind(struct i915_vma *vma)
 		mutex_unlock(&vma->vm->mutex);
 
 		__i915_vma_iounmap(vma);
-		vma->flags &= ~I915_VMA_CAN_FENCE;
+		clear_bit(I915_VMA_CAN_FENCE_BIT, __i915_vma_flags(vma));
 	}
 	GEM_BUG_ON(vma->fence);
 	GEM_BUG_ON(i915_vma_has_userfault(vma));
@@ -1000,7 +1001,7 @@ int i915_vma_unbind(struct i915_vma *vma)
 		trace_i915_vma_unbind(vma);
 		vma->ops->unbind_vma(vma);
 	}
-	vma->flags &= ~(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND);
+	atomic_and(~I915_VMA_BIND_MASK, &vma->flags);
 
 	i915_vma_remove(vma);
 
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 425bda4db2c2..8bcb5812c446 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -72,7 +72,7 @@ struct i915_vma {
 	 * that exist in the ctx->handle_vmas LUT for this vma.
 	 */
 	atomic_t open_count;
-	unsigned long flags;
+	atomic_t flags;
 	/**
 	 * How many users have pinned this object in GTT space.
 	 *
@@ -97,18 +97,29 @@ struct i915_vma {
 	 * users.
 	 */
 #define I915_VMA_PIN_MASK 0xff
-#define I915_VMA_PIN_OVERFLOW	BIT(8)
+#define I915_VMA_PIN_OVERFLOW_BIT 8
+#define I915_VMA_PIN_OVERFLOW	((int)BIT(I915_VMA_PIN_OVERFLOW_BIT))
 
 	/** Flags and address space this VMA is bound to */
-#define I915_VMA_GLOBAL_BIND	BIT(9)
-#define I915_VMA_LOCAL_BIND	BIT(10)
-#define I915_VMA_BIND_MASK (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND | I915_VMA_PIN_OVERFLOW)
+#define I915_VMA_GLOBAL_BIND_BIT 9
+#define I915_VMA_LOCAL_BIND_BIT 10
 
-#define I915_VMA_GGTT		BIT(11)
-#define I915_VMA_CAN_FENCE	BIT(12)
+#define I915_VMA_GLOBAL_BIND	((int)BIT(I915_VMA_GLOBAL_BIND_BIT))
+#define I915_VMA_LOCAL_BIND	((int)BIT(I915_VMA_LOCAL_BIND_BIT))
+
+#define I915_VMA_BIND_MASK (I915_VMA_GLOBAL_BIND | \
+			    I915_VMA_LOCAL_BIND | \
+			    I915_VMA_PIN_OVERFLOW)
+
+#define I915_VMA_GGTT_BIT	11
+#define I915_VMA_CAN_FENCE_BIT	12
 #define I915_VMA_USERFAULT_BIT	13
-#define I915_VMA_USERFAULT	BIT(I915_VMA_USERFAULT_BIT)
-#define I915_VMA_GGTT_WRITE	BIT(14)
+#define I915_VMA_GGTT_WRITE_BIT	14
+
+#define I915_VMA_GGTT		((int)BIT(I915_VMA_GGTT_BIT))
+#define I915_VMA_CAN_FENCE	((int)BIT(I915_VMA_CAN_FENCE_BIT))
+#define I915_VMA_USERFAULT	((int)BIT(I915_VMA_USERFAULT_BIT))
+#define I915_VMA_GGTT_WRITE	((int)BIT(I915_VMA_GGTT_WRITE_BIT))
 
 	struct i915_active active;
 
@@ -162,48 +173,51 @@ int __must_check i915_vma_move_to_active(struct i915_vma *vma,
 					 struct i915_request *rq,
 					 unsigned int flags);
 
+#define __i915_vma_flags(v) ((unsigned long *)&(v)->flags.counter)
+
 static inline bool i915_vma_is_ggtt(const struct i915_vma *vma)
 {
-	return vma->flags & I915_VMA_GGTT;
+	return test_bit(I915_VMA_GGTT_BIT, __i915_vma_flags(vma));
 }
 
 static inline bool i915_vma_has_ggtt_write(const struct i915_vma *vma)
 {
-	return vma->flags & I915_VMA_GGTT_WRITE;
+	return test_bit(I915_VMA_GGTT_WRITE_BIT, __i915_vma_flags(vma));
 }
 
 static inline void i915_vma_set_ggtt_write(struct i915_vma *vma)
 {
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
-	vma->flags |= I915_VMA_GGTT_WRITE;
+	set_bit(I915_VMA_GGTT_WRITE_BIT, __i915_vma_flags(vma));
 }
 
-static inline void i915_vma_unset_ggtt_write(struct i915_vma *vma)
+static inline bool i915_vma_unset_ggtt_write(struct i915_vma *vma)
 {
-	vma->flags &= ~I915_VMA_GGTT_WRITE;
+	return test_and_clear_bit(I915_VMA_GGTT_WRITE_BIT,
+				  __i915_vma_flags(vma));
 }
 
 void i915_vma_flush_writes(struct i915_vma *vma);
 
 static inline bool i915_vma_is_map_and_fenceable(const struct i915_vma *vma)
 {
-	return vma->flags & I915_VMA_CAN_FENCE;
+	return test_bit(I915_VMA_CAN_FENCE_BIT, __i915_vma_flags(vma));
 }
 
 static inline bool i915_vma_set_userfault(struct i915_vma *vma)
 {
 	GEM_BUG_ON(!i915_vma_is_map_and_fenceable(vma));
-	return __test_and_set_bit(I915_VMA_USERFAULT_BIT, &vma->flags);
+	return test_and_set_bit(I915_VMA_USERFAULT_BIT, __i915_vma_flags(vma));
 }
 
 static inline void i915_vma_unset_userfault(struct i915_vma *vma)
 {
-	return __clear_bit(I915_VMA_USERFAULT_BIT, &vma->flags);
+	return clear_bit(I915_VMA_USERFAULT_BIT, __i915_vma_flags(vma));
 }
 
 static inline bool i915_vma_has_userfault(const struct i915_vma *vma)
 {
-	return test_bit(I915_VMA_USERFAULT_BIT, &vma->flags);
+	return test_bit(I915_VMA_USERFAULT_BIT, __i915_vma_flags(vma));
 }
 
 static inline bool i915_vma_is_closed(const struct i915_vma *vma)
@@ -330,7 +344,7 @@ i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	/* Pin early to prevent the shrinker/eviction logic from destroying
 	 * our vma as we insert and bind.
 	 */
-	if (likely(((++vma->flags ^ flags) & I915_VMA_BIND_MASK) == 0)) {
+	if (likely(((atomic_inc_return(&vma->flags) ^ flags) & I915_VMA_BIND_MASK) == 0)) {
 		GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 		GEM_BUG_ON(i915_vma_misplaced(vma, size, alignment, flags));
 		return 0;
@@ -341,7 +355,7 @@ i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 
 static inline int i915_vma_pin_count(const struct i915_vma *vma)
 {
-	return vma->flags & I915_VMA_PIN_MASK;
+	return atomic_read(&vma->flags) & I915_VMA_PIN_MASK;
 }
 
 static inline bool i915_vma_is_pinned(const struct i915_vma *vma)
@@ -351,13 +365,13 @@ static inline bool i915_vma_is_pinned(const struct i915_vma *vma)
 
 static inline void __i915_vma_pin(struct i915_vma *vma)
 {
-	vma->flags++;
-	GEM_BUG_ON(vma->flags & I915_VMA_PIN_OVERFLOW);
+	atomic_inc(&vma->flags);
+	GEM_BUG_ON(atomic_read(&vma->flags) & I915_VMA_PIN_OVERFLOW);
 }
 
 static inline void __i915_vma_unpin(struct i915_vma *vma)
 {
-	vma->flags--;
+	atomic_dec(&vma->flags);
 }
 
 static inline void i915_vma_unpin(struct i915_vma *vma)
@@ -370,7 +384,7 @@ static inline void i915_vma_unpin(struct i915_vma *vma)
 static inline bool i915_vma_is_bound(const struct i915_vma *vma,
 				     unsigned int where)
 {
-	return vma->flags & where;
+	return atomic_read(&vma->flags) & where;
 }
 
 static inline bool i915_node_color_differs(const struct drm_mm_node *node,
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index 7d5fb60b43bb..173f2d4dbd14 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -43,7 +43,7 @@ static int mock_bind_ppgtt(struct i915_vma *vma,
 			   u32 flags)
 {
 	GEM_BUG_ON(flags & I915_VMA_GLOBAL_BIND);
-	vma->flags |= I915_VMA_LOCAL_BIND;
+	set_bit(I915_VMA_LOCAL_BIND_BIT, __i915_vma_flags(vma));
 	return 0;
 }
 
@@ -86,7 +86,7 @@ static int mock_bind_ggtt(struct i915_vma *vma,
 			  enum i915_cache_level cache_level,
 			  u32 flags)
 {
-	vma->flags |= I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
+	atomic_or(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND, &vma->flags);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 43ed22753cf18c4bf60de81d567beee908e5e9f3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 11 Sep 2019 08:47:27 +0100
Subject: drm/i915/display: Add glk_cdclk_table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 736da8112fee ("drm/i915: Use literal representation of cdclk
tables") pushed the cdclk logic into tables, adding glk_cdclk_table but
not using yet:

drivers/gpu/drm/i915/display/intel_cdclk.c:1173:38: error: ‘glk_cdclk_table’ defined but not used [-Werror=unused-const-variable=]

Fixes: 736da8112fee ("drm/i915: Use literal representation of cdclk tables")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911074727.32585-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 618a93bad0a8..13779b6029f5 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -2511,7 +2511,10 @@ void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 		dev_priv->display.set_cdclk = bxt_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk;
 		dev_priv->display.calc_voltage_level = bxt_calc_voltage_level;
-		dev_priv->cdclk.table = bxt_cdclk_table;
+		if (IS_GEMINILAKE(dev_priv))
+			dev_priv->cdclk.table = glk_cdclk_table;
+		else
+			dev_priv->cdclk.table = bxt_cdclk_table;
 	} else if (IS_GEN9_BC(dev_priv)) {
 		dev_priv->display.set_cdclk = skl_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = skl_modeset_calc_cdclk;
-- 
cgit v1.2.3


From c26a058680dcf3140b6c4e918a16074a5e739b95 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 10 Sep 2019 15:13:47 +0300
Subject: drm/i915: Use a high priority wq for nonblocking plane updates
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

system_unbound_wq can't keep up sometimes and we get dropped frames.
Switch to a high priority variant.

Reported-by: Heinrich Fink <heinrich.fink@daqri.com>
Tested-by: Heinrich Fink <heinrich.fink@daqri.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190910121347.22958-1-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/display/intel_display.c | 6 +++++-
 drivers/gpu/drm/i915/i915_drv.h              | 2 ++
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 3b5275ab66cf..2668744007b3 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -14272,7 +14272,7 @@ static int intel_atomic_commit(struct drm_device *dev,
 	if (nonblock && state->modeset) {
 		queue_work(dev_priv->modeset_wq, &state->base.commit_work);
 	} else if (nonblock) {
-		queue_work(system_unbound_wq, &state->base.commit_work);
+		queue_work(dev_priv->flip_wq, &state->base.commit_work);
 	} else {
 		if (state->modeset)
 			flush_workqueue(dev_priv->modeset_wq);
@@ -16181,6 +16181,8 @@ int intel_modeset_init(struct drm_device *dev)
 	int ret;
 
 	dev_priv->modeset_wq = alloc_ordered_workqueue("i915_modeset", 0);
+	dev_priv->flip_wq = alloc_workqueue("i915_flip", WQ_HIGHPRI |
+					    WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE);
 
 	drm_mode_config_init(dev);
 
@@ -17139,6 +17141,7 @@ void intel_modeset_driver_remove(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
+	flush_workqueue(dev_priv->flip_wq);
 	flush_workqueue(dev_priv->modeset_wq);
 
 	flush_work(&dev_priv->atomic_helper.free_work);
@@ -17175,6 +17178,7 @@ void intel_modeset_driver_remove(struct drm_device *dev)
 
 	intel_gmbus_teardown(dev_priv);
 
+	destroy_workqueue(dev_priv->flip_wq);
 	destroy_workqueue(dev_priv->modeset_wq);
 
 	intel_fbc_cleanup_cfb(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 51d575cca2ac..2ea11123e933 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1438,6 +1438,8 @@ struct drm_i915_private {
 
 	/* ordered wq for modesets */
 	struct workqueue_struct *modeset_wq;
+	/* unbound hipri wq for page flips/plane updates */
+	struct workqueue_struct *flip_wq;
 
 	/* Display functions */
 	struct drm_i915_display_funcs display;
-- 
cgit v1.2.3


From cfcbfdd8fe140af699b538a42cf0dd4933885fe5 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 8 Jul 2019 15:53:09 +0300
Subject: drm/i915: Remove pointless planes_changed=true assignment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

i915 doesn't use the crtc_state->plane_changed flag for anything,
so setting it is pointless.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190708125325.16576-4-ville.syrjala@linux.intel.com
Reviewed-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
---
 drivers/gpu/drm/i915/display/intel_atomic.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c
index d3fb75bb9eb1..698802da07b7 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic.c
@@ -378,13 +378,6 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 						plane->base.id);
 					return PTR_ERR(state);
 				}
-
-				/*
-				 * the plane is added after plane checks are run,
-				 * but since this plane is unchanged just do the
-				 * minimum required validation.
-				 */
-				crtc_state->base.planes_changed = true;
 			}
 
 			intel_plane = to_intel_plane(plane);
-- 
cgit v1.2.3


From 7cb8468bbede8cac0d9ed69b2549788ecaa6b558 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 11 Sep 2019 13:57:17 +0100
Subject: drm/i915/tgl: Disable read-only ppgtt support

The same read-only affliction as befell Icelake is affecting Tigerlake.
Disable the read-only support as clearly it was not fixed.

Testcase: igt/i915_selftests/live_gem_context
References: 3936867dbc1e ("drm/i915: Disable read only ppgtt support for gen11")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911125717.28997-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index e4f66bfe74c2..a09a9b62afbe 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1486,8 +1486,10 @@ static struct i915_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 	 *
 	 * Gen11 has HSDES#:1807136187 unresolved. Disable ro support
 	 * for now.
+	 *
+	 * Gen12 has inherited the same read-only fault issue from gen11.
 	 */
-	ppgtt->vm.has_read_only = INTEL_GEN(i915) != 11;
+	ppgtt->vm.has_read_only = !IS_GEN_RANGE(i915, 11, 12);
 
 	/* There are only few exceptions for gen >=6. chv and bxt.
 	 * And we are not sure about the latter so play safe for now.
-- 
cgit v1.2.3


From aac60f1a867773de9eb164013d89c99f3ea1f009 Mon Sep 17 00:00:00 2001
From: Zenghui Yu <yuzenghui@huawei.com>
Date: Wed, 11 Sep 2019 02:33:35 +0000
Subject: KVM: arm/arm64: vgic: Use the appropriate TRACE_INCLUDE_PATH

Commit 49dfe94fe5ad ("KVM: arm/arm64: Fix TRACE_INCLUDE_PATH") fixes
TRACE_INCLUDE_PATH to the correct relative path to the define_trace.h
and explains why did the old one work.

The same fix should be applied to virt/kvm/arm/vgic/trace.h.

Reviewed-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 virt/kvm/arm/vgic/trace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/virt/kvm/arm/vgic/trace.h b/virt/kvm/arm/vgic/trace.h
index 55fed77a9f73..4fd4f6db181b 100644
--- a/virt/kvm/arm/vgic/trace.h
+++ b/virt/kvm/arm/vgic/trace.h
@@ -30,7 +30,7 @@ TRACE_EVENT(vgic_update_irq_pending,
 #endif /* _TRACE_VGIC_H */
 
 #undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH ../../../virt/kvm/arm/vgic
+#define TRACE_INCLUDE_PATH ../../virt/kvm/arm/vgic
 #undef TRACE_INCLUDE_FILE
 #define TRACE_INCLUDE_FILE trace
 
-- 
cgit v1.2.3


From 023a125d1dded8e1c21bd9974373b697544ba18d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 11 Sep 2019 12:46:55 +0100
Subject: drm/i915: Squeeze iommu status into debugfs/i915_capabilities

There's no easy way of checking whether iommu is enabled for the GPU
(you can grep dmesg if you know the device, or you can grep
i915_gpu_info if that's available). We do have a central
i915_capabilities with the intent of listing such pertinent information,
so add the iommu status.

Suggested-by: Martin Peres <martin.peres@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Martin Peres <martin.peres@linux.intel.com>
Cc: Tomi Sarvela <tomi.p.sarvela@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Martin Peres <martin.peres@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911114655.9254-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_debugfs.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 708855e051b5..e5835337f022 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -61,11 +61,18 @@ static int i915_capabilities(struct seq_file *m, void *data)
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	const struct intel_device_info *info = INTEL_INFO(dev_priv);
 	struct drm_printer p = drm_seq_file_printer(m);
+	const char *msg;
 
 	seq_printf(m, "gen: %d\n", INTEL_GEN(dev_priv));
 	seq_printf(m, "platform: %s\n", intel_platform_name(info->platform));
 	seq_printf(m, "pch: %d\n", INTEL_PCH_TYPE(dev_priv));
 
+	msg = "n/a";
+#ifdef CONFIG_INTEL_IOMMU
+	msg = enableddisabled(intel_iommu_gfx_mapped);
+#endif
+	seq_printf(m, "iommu: %s\n", msg);
+
 	intel_device_info_dump_flags(info, &p);
 	intel_device_info_dump_runtime(RUNTIME_INFO(dev_priv), &p);
 	intel_driver_caps_print(&dev_priv->caps, &p);
-- 
cgit v1.2.3


From 249778704c01384d76984d83e6d6377ac96b2cc4 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 11 Sep 2019 12:26:08 +0300
Subject: drm/i915: add INTEL_NUM_PIPES() and use it
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Abstract away direct access to ->num_pipes to allow further
refactoring. No functional changes.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Acked-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911092608.13009-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c   | 12 ++++++------
 drivers/gpu/drm/i915/display/intel_display.h   |  4 ++--
 drivers/gpu/drm/i915/display/intel_lpe_audio.c |  2 +-
 drivers/gpu/drm/i915/i915_drv.c                |  2 +-
 drivers/gpu/drm/i915/i915_drv.h                |  4 +++-
 drivers/gpu/drm/i915/intel_pm.c                |  6 +++---
 6 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 2668744007b3..a19f8c73f2e0 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -7190,7 +7190,7 @@ static int ironlake_check_fdi_lanes(struct drm_device *dev, enum pipe pipe,
 		}
 	}
 
-	if (INTEL_INFO(dev_priv)->num_pipes == 2)
+	if (INTEL_NUM_PIPES(dev_priv) == 2)
 		return 0;
 
 	/* Ivybridge 3 pipe is really complicated */
@@ -9574,7 +9574,7 @@ static void ironlake_compute_dpll(struct intel_crtc *crtc,
 	 * clear if it''s a win or loss power wise. No point in doing
 	 * this on ILK at all since it has a fixed DPLL<->pipe mapping.
 	 */
-	if (INTEL_INFO(dev_priv)->num_pipes == 3 &&
+	if (INTEL_NUM_PIPES(dev_priv) == 3 &&
 	    intel_crtc_has_type(crtc_state, INTEL_OUTPUT_ANALOG))
 		dpll |= DPLL_SDVO_HIGH_SPEED;
 
@@ -13899,7 +13899,7 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 
 			if (skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb,
 							entries,
-							INTEL_INFO(dev_priv)->num_pipes, i))
+							INTEL_NUM_PIPES(dev_priv), i))
 				continue;
 
 			updated |= cmask;
@@ -16258,8 +16258,8 @@ int intel_modeset_init(struct drm_device *dev)
 	}
 
 	DRM_DEBUG_KMS("%d display pipe%s available.\n",
-		      INTEL_INFO(dev_priv)->num_pipes,
-		      INTEL_INFO(dev_priv)->num_pipes > 1 ? "s" : "");
+		      INTEL_NUM_PIPES(dev_priv),
+		      INTEL_NUM_PIPES(dev_priv) > 1 ? "s" : "");
 
 	for_each_pipe(dev_priv, pipe) {
 		ret = intel_crtc_init(dev_priv, pipe);
@@ -17352,7 +17352,7 @@ intel_display_print_error_state(struct drm_i915_error_state_buf *m,
 	if (!error)
 		return;
 
-	err_printf(m, "Num Pipes: %d\n", INTEL_INFO(dev_priv)->num_pipes);
+	err_printf(m, "Num Pipes: %d\n", INTEL_NUM_PIPES(dev_priv));
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		err_printf(m, "PWR_WELL_CTL2: %08x\n",
 			   error->power_well_driver);
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 33fd523c4622..f4ddde171655 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -307,10 +307,10 @@ enum phy_fia {
 };
 
 #define for_each_pipe(__dev_priv, __p) \
-	for ((__p) = 0; (__p) < INTEL_INFO(__dev_priv)->num_pipes; (__p)++)
+	for ((__p) = 0; (__p) < INTEL_NUM_PIPES(__dev_priv); (__p)++)
 
 #define for_each_pipe_masked(__dev_priv, __p, __mask) \
-	for ((__p) = 0; (__p) < INTEL_INFO(__dev_priv)->num_pipes; (__p)++) \
+	for ((__p) = 0; (__p) < INTEL_NUM_PIPES(__dev_priv); (__p)++) \
 		for_each_if((__mask) & BIT(__p))
 
 #define for_each_cpu_transcoder_masked(__dev_priv, __t, __mask) \
diff --git a/drivers/gpu/drm/i915/display/intel_lpe_audio.c b/drivers/gpu/drm/i915/display/intel_lpe_audio.c
index b19800b58442..0b67f7887cd0 100644
--- a/drivers/gpu/drm/i915/display/intel_lpe_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_lpe_audio.c
@@ -114,7 +114,7 @@ lpe_audio_platdev_create(struct drm_i915_private *dev_priv)
 	pinfo.size_data = sizeof(*pdata);
 	pinfo.dma_mask = DMA_BIT_MASK(32);
 
-	pdata->num_pipes = INTEL_INFO(dev_priv)->num_pipes;
+	pdata->num_pipes = INTEL_NUM_PIPES(dev_priv);
 	pdata->num_ports = IS_CHERRYVIEW(dev_priv) ? 3 : 2; /* B,C,D or B,C */
 	pdata->port[0].pipe = -1;
 	pdata->port[1].pipe = -1;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 8966672b0294..c52ef2223580 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -340,7 +340,7 @@ static int i915_driver_modeset_probe(struct drm_device *dev)
 
 	if (HAS_DISPLAY(dev_priv)) {
 		ret = drm_vblank_init(&dev_priv->drm,
-				      INTEL_INFO(dev_priv)->num_pipes);
+				      INTEL_NUM_PIPES(dev_priv));
 		if (ret)
 			goto out;
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 2ea11123e933..84fb0245cf62 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2188,7 +2188,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define GT_FREQUENCY_MULTIPLIER 50
 #define GEN9_FREQ_SCALER 3
 
-#define HAS_DISPLAY(dev_priv) (INTEL_INFO(dev_priv)->num_pipes > 0)
+#define INTEL_NUM_PIPES(dev_priv) (INTEL_INFO(dev_priv)->num_pipes)
+
+#define HAS_DISPLAY(dev_priv) (INTEL_NUM_PIPES(dev_priv) > 0)
 
 static inline bool intel_vtd_active(void)
 {
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 54a8b7705bc6..d0ceb272551f 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1909,7 +1909,7 @@ static int vlv_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 
 	for (level = 0; level < wm_state->num_levels; level++) {
 		const struct g4x_pipe_wm *raw = &crtc_state->wm.vlv.raw[level];
-		const int sr_fifo_size = INTEL_INFO(dev_priv)->num_pipes * 512 - 1;
+		const int sr_fifo_size = INTEL_NUM_PIPES(dev_priv) * 512 - 1;
 
 		if (!vlv_raw_crtc_wm_is_valid(crtc_state, level))
 			break;
@@ -2648,7 +2648,7 @@ static unsigned int ilk_plane_wm_max(const struct drm_i915_private *dev_priv,
 
 	/* HSW allows LP1+ watermarks even with multiple pipes */
 	if (level == 0 || config->num_pipes_active > 1) {
-		fifo_size /= INTEL_INFO(dev_priv)->num_pipes;
+		fifo_size /= INTEL_NUM_PIPES(dev_priv);
 
 		/*
 		 * For some reason the non self refresh
@@ -9733,7 +9733,7 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 		dev_priv->display.update_wm = i9xx_update_wm;
 		dev_priv->display.get_fifo_size = i9xx_get_fifo_size;
 	} else if (IS_GEN(dev_priv, 2)) {
-		if (INTEL_INFO(dev_priv)->num_pipes == 1) {
+		if (INTEL_NUM_PIPES(dev_priv) == 1) {
 			dev_priv->display.update_wm = i845_update_wm;
 			dev_priv->display.get_fifo_size = i845_get_fifo_size;
 		} else {
-- 
cgit v1.2.3


From 74689ddfb7574e2bf08c7206a4ab0dff04978b05 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 11 Sep 2019 16:31:26 +0300
Subject: drm/i915: Fix cdclk bypass freq readout for tgl/bxt/glk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On tgl/bxt/glk the cdclk bypass frequency depends on the PLL
reference clock. So let's read out the ref clock before we
try to compute the bypass clock.

Cc: Matt Roper <matthew.d.roper@intel.com>
Fixes: 71dc367e2bc3 ("drm/i915: Consolidate bxt/cnl/icl cdclk readout")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911133129.27466-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 13779b6029f5..6fc8e3c0cfba 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1351,6 +1351,8 @@ static void bxt_get_cdclk(struct drm_i915_private *dev_priv,
 	u32 divider;
 	int div;
 
+	bxt_de_pll_readout(dev_priv, cdclk_state);
+
 	if (INTEL_GEN(dev_priv) >= 12)
 		cdclk_state->bypass = cdclk_state->ref / 2;
 	else if (INTEL_GEN(dev_priv) >= 11)
@@ -1358,7 +1360,6 @@ static void bxt_get_cdclk(struct drm_i915_private *dev_priv,
 	else
 		cdclk_state->bypass = cdclk_state->ref;
 
-	bxt_de_pll_readout(dev_priv, cdclk_state);
 	if (cdclk_state->vco == 0) {
 		cdclk_state->cdclk = cdclk_state->bypass;
 		goto out;
-- 
cgit v1.2.3


From 0a12e437049786b9c33542d16b6a03f46fab46f8 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 11 Sep 2019 16:31:27 +0300
Subject: drm/i915: Fix CD2X pipe select masking during cdclk sanitation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We're forgetting to mask off all three pipe select bits from the
CDCLK_CTL value on icl+ which may lead to the extra bit being
left in. That will cause us to consider the current hardware
cdclk state as invalid, and we proceed to sanitize it even
though the hardware may have active pipes and whatnot.

Fix up the mask so we get rid of all three pipe select bits
and thus hopefully no longer sanitize cdclk when it's already
correctly programmed.

Cc: Matt Roper <matthew.d.roper@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111641
Fixes: 0c1279b58fc7 ("drm/i915: Consolidate {bxt,cnl,icl}_init_cdclk")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911133129.27466-2-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 42 ++++++++++++++++--------------
 1 file changed, 23 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 6fc8e3c0cfba..d838c34d9cac 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1464,6 +1464,26 @@ static void cnl_cdclk_pll_enable(struct drm_i915_private *dev_priv, int vco)
 	dev_priv->cdclk.hw.vco = vco;
 }
 
+static u32 bxt_cdclk_cd2x_pipe(struct drm_i915_private *dev_priv, enum pipe pipe)
+{
+	if (INTEL_GEN(dev_priv) >= 12) {
+		if (pipe == INVALID_PIPE)
+			return TGL_CDCLK_CD2X_PIPE_NONE;
+		else
+			return TGL_CDCLK_CD2X_PIPE(pipe);
+	} else if (INTEL_GEN(dev_priv) >= 11) {
+		if (pipe == INVALID_PIPE)
+			return ICL_CDCLK_CD2X_PIPE_NONE;
+		else
+			return ICL_CDCLK_CD2X_PIPE(pipe);
+	} else {
+		if (pipe == INVALID_PIPE)
+			return BXT_CDCLK_CD2X_PIPE_NONE;
+		else
+			return BXT_CDCLK_CD2X_PIPE(pipe);
+	}
+}
+
 static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 			  const struct intel_cdclk_state *cdclk_state,
 			  enum pipe pipe)
@@ -1534,24 +1554,8 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv,
 			bxt_de_pll_enable(dev_priv, vco);
 	}
 
-	val = divider | skl_cdclk_decimal(cdclk);
-
-	if (INTEL_GEN(dev_priv) >= 12) {
-		if (pipe == INVALID_PIPE)
-			val |= TGL_CDCLK_CD2X_PIPE_NONE;
-		else
-			val |= TGL_CDCLK_CD2X_PIPE(pipe);
-	} else if (INTEL_GEN(dev_priv) >= 11) {
-		if (pipe == INVALID_PIPE)
-			val |= ICL_CDCLK_CD2X_PIPE_NONE;
-		else
-			val |= ICL_CDCLK_CD2X_PIPE(pipe);
-	} else {
-		if (pipe == INVALID_PIPE)
-			val |= BXT_CDCLK_CD2X_PIPE_NONE;
-		else
-			val |= BXT_CDCLK_CD2X_PIPE(pipe);
-	}
+	val = divider | skl_cdclk_decimal(cdclk) |
+		bxt_cdclk_cd2x_pipe(dev_priv, pipe);
 
 	/*
 	 * Disable SSA Precharge when CD clock frequency < 500 MHz,
@@ -1620,7 +1624,7 @@ static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv)
 	 * dividers both synching to an active pipe, or asynchronously
 	 * (PIPE_NONE).
 	 */
-	cdctl &= ~BXT_CDCLK_CD2X_PIPE_NONE;
+	cdctl &= ~bxt_cdclk_cd2x_pipe(dev_priv, INVALID_PIPE);
 
 	/* Make sure this is a legal cdclk value for the platform */
 	cdclk = bxt_calc_cdclk(dev_priv, dev_priv->cdclk.hw.cdclk);
-- 
cgit v1.2.3


From 502d1c04f53c787dfd6268578393d340cf614cde Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 11 Sep 2019 16:31:28 +0300
Subject: drm/i915: Reuse cnl_modeset_calc_cdclk() on icl+
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The cnl and icl .modeset_calc_cdclk() functions are identical. Drop one
copy.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911133129.27466-3-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 37 ++----------------------------
 1 file changed, 2 insertions(+), 35 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index d838c34d9cac..3bc70472fb5f 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -2227,39 +2227,6 @@ static int cnl_modeset_calc_cdclk(struct intel_atomic_state *state)
 	cdclk = bxt_calc_cdclk(dev_priv, min_cdclk);
 	vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
 
-	state->cdclk.logical.vco = vco;
-	state->cdclk.logical.cdclk = cdclk;
-	state->cdclk.logical.voltage_level =
-		max(cnl_calc_voltage_level(cdclk),
-		    cnl_compute_min_voltage_level(state));
-
-	if (!state->active_pipes) {
-		cdclk = bxt_calc_cdclk(dev_priv, state->cdclk.force_min_cdclk);
-		vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
-
-		state->cdclk.actual.vco = vco;
-		state->cdclk.actual.cdclk = cdclk;
-		state->cdclk.actual.voltage_level =
-			cnl_calc_voltage_level(cdclk);
-	} else {
-		state->cdclk.actual = state->cdclk.logical;
-	}
-
-	return 0;
-}
-
-static int icl_modeset_calc_cdclk(struct intel_atomic_state *state)
-{
-	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
-	int min_cdclk, cdclk, vco;
-
-	min_cdclk = intel_compute_min_cdclk(state);
-	if (min_cdclk < 0)
-		return min_cdclk;
-
-	cdclk = bxt_calc_cdclk(dev_priv, min_cdclk);
-	vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
-
 	state->cdclk.logical.vco = vco;
 	state->cdclk.logical.cdclk = cdclk;
 	state->cdclk.logical.voltage_level =
@@ -2499,12 +2466,12 @@ void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 {
 	if (IS_ELKHARTLAKE(dev_priv)) {
 		dev_priv->display.set_cdclk = bxt_set_cdclk;
-		dev_priv->display.modeset_calc_cdclk = icl_modeset_calc_cdclk;
+		dev_priv->display.modeset_calc_cdclk = cnl_modeset_calc_cdclk;
 		dev_priv->display.calc_voltage_level = ehl_calc_voltage_level;
 		dev_priv->cdclk.table = icl_cdclk_table;
 	} else if (INTEL_GEN(dev_priv) >= 11) {
 		dev_priv->display.set_cdclk = bxt_set_cdclk;
-		dev_priv->display.modeset_calc_cdclk = icl_modeset_calc_cdclk;
+		dev_priv->display.modeset_calc_cdclk = cnl_modeset_calc_cdclk;
 		dev_priv->display.calc_voltage_level = icl_calc_voltage_level;
 		dev_priv->cdclk.table = icl_cdclk_table;
 	} else if (IS_CANNONLAKE(dev_priv)) {
-- 
cgit v1.2.3


From 933122cc7cd26e67dfc7975f821033e89f766963 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 11 Sep 2019 16:31:29 +0300
Subject: drm/i915: Remove duplicated bxt/cnl/icl .modeset_calc_cdclk() funcs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reuse the same .modeset_calc_cdclk() function for all bxt+.

The only difference in between the cnl/icl and the bxt variants
is the call to cnl_compute_min_voltage_level(). We can do that call
just fine on older platforms since they leave min_voltage_level[]
zeroed. Let's rename the function to bxt_compute_min_voltage_level()
just so it stays consistent with the rest of the naming scheme.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911133129.27466-4-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c | 46 ++++++------------------------
 1 file changed, 9 insertions(+), 37 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 3bc70472fb5f..ea3f75c72fe8 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -2017,6 +2017,10 @@ static int intel_compute_min_cdclk(struct intel_atomic_state *state)
 }
 
 /*
+ * Account for port clock min voltage level requirements.
+ * This only really does something on CNL+ but can be
+ * called on earlier platforms as well.
+ *
  * Note that this functions assumes that 0 is
  * the lowest voltage value, and higher values
  * correspond to increasingly higher voltages.
@@ -2025,7 +2029,7 @@ static int intel_compute_min_cdclk(struct intel_atomic_state *state)
  * future platforms this code will need to be
  * adjusted.
  */
-static u8 cnl_compute_min_voltage_level(struct intel_atomic_state *state)
+static u8 bxt_compute_min_voltage_level(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	struct intel_crtc *crtc;
@@ -2195,43 +2199,11 @@ static int bxt_modeset_calc_cdclk(struct intel_atomic_state *state)
 	cdclk = bxt_calc_cdclk(dev_priv, min_cdclk);
 	vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
 
-	state->cdclk.logical.vco = vco;
-	state->cdclk.logical.cdclk = cdclk;
-	state->cdclk.logical.voltage_level =
-		dev_priv->display.calc_voltage_level(cdclk);
-
-	if (!state->active_pipes) {
-		cdclk = bxt_calc_cdclk(dev_priv, state->cdclk.force_min_cdclk);
-		vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
-
-		state->cdclk.actual.vco = vco;
-		state->cdclk.actual.cdclk = cdclk;
-		state->cdclk.actual.voltage_level =
-			dev_priv->display.calc_voltage_level(cdclk);
-	} else {
-		state->cdclk.actual = state->cdclk.logical;
-	}
-
-	return 0;
-}
-
-static int cnl_modeset_calc_cdclk(struct intel_atomic_state *state)
-{
-	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
-	int min_cdclk, cdclk, vco;
-
-	min_cdclk = intel_compute_min_cdclk(state);
-	if (min_cdclk < 0)
-		return min_cdclk;
-
-	cdclk = bxt_calc_cdclk(dev_priv, min_cdclk);
-	vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
-
 	state->cdclk.logical.vco = vco;
 	state->cdclk.logical.cdclk = cdclk;
 	state->cdclk.logical.voltage_level =
 		max(dev_priv->display.calc_voltage_level(cdclk),
-		    cnl_compute_min_voltage_level(state));
+		    bxt_compute_min_voltage_level(state));
 
 	if (!state->active_pipes) {
 		cdclk = bxt_calc_cdclk(dev_priv, state->cdclk.force_min_cdclk);
@@ -2466,17 +2438,17 @@ void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 {
 	if (IS_ELKHARTLAKE(dev_priv)) {
 		dev_priv->display.set_cdclk = bxt_set_cdclk;
-		dev_priv->display.modeset_calc_cdclk = cnl_modeset_calc_cdclk;
+		dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk;
 		dev_priv->display.calc_voltage_level = ehl_calc_voltage_level;
 		dev_priv->cdclk.table = icl_cdclk_table;
 	} else if (INTEL_GEN(dev_priv) >= 11) {
 		dev_priv->display.set_cdclk = bxt_set_cdclk;
-		dev_priv->display.modeset_calc_cdclk = cnl_modeset_calc_cdclk;
+		dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk;
 		dev_priv->display.calc_voltage_level = icl_calc_voltage_level;
 		dev_priv->cdclk.table = icl_cdclk_table;
 	} else if (IS_CANNONLAKE(dev_priv)) {
 		dev_priv->display.set_cdclk = bxt_set_cdclk;
-		dev_priv->display.modeset_calc_cdclk = cnl_modeset_calc_cdclk;
+		dev_priv->display.modeset_calc_cdclk = bxt_modeset_calc_cdclk;
 		dev_priv->display.calc_voltage_level = cnl_calc_voltage_level;
 		dev_priv->cdclk.table = cnl_cdclk_table;
 	} else if (IS_GEN9_LP(dev_priv)) {
-- 
cgit v1.2.3


From e3cb653d5cc42c2073ad174ae1130dc9e39266e9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 11 Sep 2019 18:59:26 +0100
Subject: drm/i915: Disable FBC if BIOS reserved memory (stolen) is unavailable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The FBC requires a couple of contiguous buffers, which we allocate from
stolen memory. If stolen memory is unavailable, we cannot allocate those
buffers and so cannot support FBC. Mark it so.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911175926.31365-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/display/intel_fbc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index dc34b23e2320..3111ecaeabd0 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -1320,6 +1320,9 @@ void intel_fbc_init(struct drm_i915_private *dev_priv)
 	fbc->enabled = false;
 	fbc->active = false;
 
+	if (!drm_mm_initialized(&dev_priv->mm.stolen))
+		mkwrite_device_info(dev_priv)->display.has_fbc = false;
+
 	if (need_fbc_vtd_wa(dev_priv))
 		mkwrite_device_info(dev_priv)->display.has_fbc = false;
 
-- 
cgit v1.2.3


From 582a6f90aa0d9103ab834b3a48a5bb7e4d07cac6 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Sep 2019 10:29:32 +0100
Subject: drm/i915/execlists: Add a paranoid flush of the CSB pointers upon
 reset

After a GPU reset, we need to drain all the CS events so that we have an
accurate picture of the execlists state at the time of the reset. Be
paranoid and force a read of the CSB write pointer from memory.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190912092933.4729-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index dcdf7cf66e7e..dbc90da2341a 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2359,6 +2359,10 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	struct i915_request *rq;
 	u32 *regs;
 
+	mb(); /* paranoia: read the CSB pointers from after the reset */
+	clflush(execlists->csb_write);
+	mb();
+
 	process_csb(engine); /* drain preemption events */
 
 	/* Following the reset, we need to reload the CSB read/write pointers */
-- 
cgit v1.2.3


From a17592effdc16f3a51ef9c1dda30fe5c6d668263 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Sep 2019 10:29:33 +0100
Subject: drm/i915/execlists: Ensure the context is reloaded after a GPU reset

After we manipulate the context to allow replay after a GPU reset, force
that context to be reloaded. This should be a layer of paranoia, for if
the GPU was reset, the context will no longer be resident!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190912092933.4729-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index dbc90da2341a..47d766ccea71 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2445,6 +2445,7 @@ out_replay:
 	intel_ring_update_space(ce->ring);
 	__execlists_reset_reg_state(ce, engine);
 	__execlists_update_reg_state(ce, engine);
+	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */
 	mutex_release(&ce->pin_mutex.dep_map, 0, _THIS_IP_);
 
 unwind:
-- 
cgit v1.2.3


From 54fc577d90d01a28dbfccd277aa3de4d4abaf1ff Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Wed, 11 Sep 2019 17:07:30 +0100
Subject: drm/i915/pmu: Skip busyness sampling when and where not needed

Since d0aa694b9239 ("drm/i915/pmu: Always sample an active ringbuffer")
the cost of sampling the engine state on execlists platforms became a
little bit higher when both engine busyness and one of the wait states are
being monitored. (Previously the busyness sampling on legacy platforms was
done via seqno comparison so there was no cost of mmio read.)

We can avoid that by skipping busyness sampling when engine supports
software busy stats and so avoid the cost of potential mmio read and
sample accumulation.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911160730.22687-1-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/i915_pmu.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 8e251e719390..623ad32303a1 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -194,6 +194,10 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 		if (val & RING_WAIT_SEMAPHORE)
 			add_sample(&pmu->sample[I915_SAMPLE_SEMA], period_ns);
 
+		/* No need to sample when busy stats are supported. */
+		if (intel_engine_supports_stats(engine))
+			goto skip;
+
 		/*
 		 * While waiting on a semaphore or event, MI_MODE reports the
 		 * ring as idle. However, previously using the seqno, and with
-- 
cgit v1.2.3


From 8d8b00318593e2852aef19b92f99851d50a203fc Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 11 Sep 2019 23:29:08 +0300
Subject: drm/i915: convert device info num_pipes to pipe_mask
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace device info number of pipes with a bit mask of available
pipes. This will prove handy in the future. There's still a bunch of
future work to do to actually allow a non-consecutive mask of pipes, but
it's a start. No functional changes.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Acked-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911202908.19631-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h          |  4 ++--
 drivers/gpu/drm/i915/i915_pci.c          | 24 ++++++++++++------------
 drivers/gpu/drm/i915/intel_device_info.c | 10 +++++-----
 drivers/gpu/drm/i915/intel_device_info.h |  2 +-
 4 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 84fb0245cf62..bf600888b3f1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2188,9 +2188,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define GT_FREQUENCY_MULTIPLIER 50
 #define GEN9_FREQ_SCALER 3
 
-#define INTEL_NUM_PIPES(dev_priv) (INTEL_INFO(dev_priv)->num_pipes)
+#define INTEL_NUM_PIPES(dev_priv) (hweight8(INTEL_INFO(dev_priv)->pipe_mask))
 
-#define HAS_DISPLAY(dev_priv) (INTEL_NUM_PIPES(dev_priv) > 0)
+#define HAS_DISPLAY(dev_priv) (INTEL_INFO(dev_priv)->pipe_mask != 0)
 
 static inline bool intel_vtd_active(void)
 {
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index b3cc8560696b..698116276441 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -147,7 +147,7 @@
 #define I830_FEATURES \
 	GEN(2), \
 	.is_mobile = 1, \
-	.num_pipes = 2, \
+	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \
 	.display.has_overlay = 1, \
 	.display.cursor_needs_physical = 1, \
 	.display.overlay_needs_physical = 1, \
@@ -165,7 +165,7 @@
 
 #define I845_FEATURES \
 	GEN(2), \
-	.num_pipes = 1, \
+	.pipe_mask = BIT(PIPE_A), \
 	.display.has_overlay = 1, \
 	.display.overlay_needs_physical = 1, \
 	.display.has_gmch = 1, \
@@ -203,7 +203,7 @@ static const struct intel_device_info intel_i865g_info = {
 
 #define GEN3_FEATURES \
 	GEN(3), \
-	.num_pipes = 2, \
+	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \
 	.display.has_gmch = 1, \
 	.gpu_reset_clobbers_display = true, \
 	.engine_mask = BIT(RCS0), \
@@ -287,7 +287,7 @@ static const struct intel_device_info intel_pineview_m_info = {
 
 #define GEN4_FEATURES \
 	GEN(4), \
-	.num_pipes = 2, \
+	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \
 	.display.has_hotplug = 1, \
 	.display.has_gmch = 1, \
 	.gpu_reset_clobbers_display = true, \
@@ -337,7 +337,7 @@ static const struct intel_device_info intel_gm45_info = {
 
 #define GEN5_FEATURES \
 	GEN(5), \
-	.num_pipes = 2, \
+	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \
 	.display.has_hotplug = 1, \
 	.engine_mask = BIT(RCS0) | BIT(VCS0), \
 	.has_snoop = true, \
@@ -363,7 +363,7 @@ static const struct intel_device_info intel_ironlake_m_info = {
 
 #define GEN6_FEATURES \
 	GEN(6), \
-	.num_pipes = 2, \
+	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \
 	.display.has_hotplug = 1, \
 	.display.has_fbc = 1, \
 	.engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \
@@ -411,7 +411,7 @@ static const struct intel_device_info intel_sandybridge_m_gt2_info = {
 
 #define GEN7_FEATURES  \
 	GEN(7), \
-	.num_pipes = 3, \
+	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \
 	.display.has_hotplug = 1, \
 	.display.has_fbc = 1, \
 	.engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \
@@ -462,7 +462,7 @@ static const struct intel_device_info intel_ivybridge_q_info = {
 	GEN7_FEATURES,
 	PLATFORM(INTEL_IVYBRIDGE),
 	.gt = 2,
-	.num_pipes = 0, /* legal, last one wins */
+	.pipe_mask = 0, /* legal, last one wins */
 	.has_l3_dpf = 1,
 };
 
@@ -470,7 +470,7 @@ static const struct intel_device_info intel_valleyview_info = {
 	PLATFORM(INTEL_VALLEYVIEW),
 	GEN(7),
 	.is_lp = 1,
-	.num_pipes = 2,
+	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B),
 	.has_runtime_pm = 1,
 	.has_rc6 = 1,
 	.has_rps = true,
@@ -560,7 +560,7 @@ static const struct intel_device_info intel_broadwell_gt3_info = {
 static const struct intel_device_info intel_cherryview_info = {
 	PLATFORM(INTEL_CHERRYVIEW),
 	GEN(8),
-	.num_pipes = 3,
+	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C),
 	.display.has_hotplug = 1,
 	.is_lp = 1,
 	.engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0),
@@ -631,7 +631,7 @@ static const struct intel_device_info intel_skylake_gt4_info = {
 	.is_lp = 1, \
 	.display.has_hotplug = 1, \
 	.engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), \
-	.num_pipes = 3, \
+	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \
 	.has_64bit_reloc = 1, \
 	.display.has_ddi = 1, \
 	.has_fpga_dbg = 1, \
@@ -792,7 +792,7 @@ static const struct intel_device_info intel_elkhartlake_info = {
 static const struct intel_device_info intel_tigerlake_12_info = {
 	GEN12_FEATURES,
 	PLATFORM(INTEL_TIGERLAKE),
-	.num_pipes = 4,
+	.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D),
 	.require_force_probe = 1,
 	.display.has_modular_fia = 1,
 	.engine_mask =
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index d9b5baaef5d0..50b05a5de53b 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -896,7 +896,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 
 	if (i915_modparams.disable_display) {
 		DRM_INFO("Display disabled (module parameter)\n");
-		info->num_pipes = 0;
+		info->pipe_mask = 0;
 	} else if (HAS_DISPLAY(dev_priv) &&
 		   (IS_GEN_RANGE(dev_priv, 7, 8)) &&
 		   HAS_PCH_SPLIT(dev_priv)) {
@@ -917,14 +917,14 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 		    (HAS_PCH_CPT(dev_priv) &&
 		     !(sfuse_strap & SFUSE_STRAP_FUSE_LOCK))) {
 			DRM_INFO("Display fused off, disabling\n");
-			info->num_pipes = 0;
+			info->pipe_mask = 0;
 		} else if (fuse_strap & IVB_PIPE_C_DISABLE) {
 			DRM_INFO("PipeC fused off\n");
-			info->num_pipes -= 1;
+			info->pipe_mask &= ~BIT(PIPE_C);
 		}
 	} else if (HAS_DISPLAY(dev_priv) && INTEL_GEN(dev_priv) >= 9) {
 		u32 dfsm = I915_READ(SKL_DFSM);
-		u8 enabled_mask = BIT(info->num_pipes) - 1;
+		u8 enabled_mask = info->pipe_mask;
 
 		if (dfsm & SKL_DFSM_PIPE_A_DISABLE)
 			enabled_mask &= ~BIT(PIPE_A);
@@ -945,7 +945,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 			DRM_ERROR("invalid pipe fuse configuration: enabled_mask=0x%x\n",
 				  enabled_mask);
 		else
-			info->num_pipes = hweight8(enabled_mask);
+			info->pipe_mask = enabled_mask;
 	}
 
 	/* Initialize slice/subslice/EU info */
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 92e0c2e0954c..d4c288860aed 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -161,7 +161,7 @@ struct intel_device_info {
 
 	u32 display_mmio_offset;
 
-	u8 num_pipes;
+	u8 pipe_mask;
 
 #define DEFINE_FLAG(name) u8 name:1
 	DEV_INFO_FOR_EACH_FLAG(DEFINE_FLAG);
-- 
cgit v1.2.3


From 16ffe73c186b7897a1a6888ffb4949a8b4026624 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Sep 2019 13:48:13 +0100
Subject: drm/i915/pmu: Use GT parked for estimating RC6 while asleep

As we track when we put the GT device to sleep upon idling, we can use
that callback to sample the current rc6 counters and record the
timestamp for estimating samples after that point while asleep.

v2: Stick to using ktime_t
v3: Track user_wakerefs that interfere with the new
intel_gt_pm_wait_for_idle
v4: No need for parked/unparked estimation if !CONFIG_PM
v5: Keep timer park/unpark logic as was
v6: Refactor duplicated estimate/update rc6 logic
v7: Pull intel_get_pm_get_if_awake() out from the pmu->lock.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105010
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190912124813.19225-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_pm.c   |  22 +++
 drivers/gpu/drm/i915/gt/intel_gt_types.h |   1 +
 drivers/gpu/drm/i915/i915_debugfs.c      |  22 ++-
 drivers/gpu/drm/i915/i915_pmu.c          | 242 +++++++++++++++++--------------
 drivers/gpu/drm/i915/i915_pmu.h          |   4 +-
 5 files changed, 170 insertions(+), 121 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 3bd764104d41..a11ad4d914ca 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -141,6 +141,24 @@ bool i915_gem_load_power_context(struct drm_i915_private *i915)
 	return switch_to_kernel_context_sync(&i915->gt);
 }
 
+static void user_forcewake(struct intel_gt *gt, bool suspend)
+{
+	int count = atomic_read(&gt->user_wakeref);
+
+	/* Inside suspend/resume so single threaded, no races to worry about. */
+	if (likely(!count))
+		return;
+
+	intel_gt_pm_get(gt);
+	if (suspend) {
+		GEM_BUG_ON(count > atomic_read(&gt->wakeref.count));
+		atomic_sub(count, &gt->wakeref.count);
+	} else {
+		atomic_add(count, &gt->wakeref.count);
+	}
+	intel_gt_pm_put(gt);
+}
+
 void i915_gem_suspend(struct drm_i915_private *i915)
 {
 	GEM_TRACE("\n");
@@ -148,6 +166,8 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	intel_wakeref_auto(&i915->ggtt.userfault_wakeref, 0);
 	flush_workqueue(i915->wq);
 
+	user_forcewake(&i915->gt, true);
+
 	mutex_lock(&i915->drm.struct_mutex);
 
 	/*
@@ -259,6 +279,8 @@ void i915_gem_resume(struct drm_i915_private *i915)
 	if (!i915_gem_load_power_context(i915))
 		goto err_wedged;
 
+	user_forcewake(&i915->gt, false);
+
 out_unlock:
 	intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
 	mutex_unlock(&i915->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index dc295c196d11..3039cef64b11 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -50,6 +50,7 @@ struct intel_gt {
 	} timelines;
 
 	struct intel_wakeref wakeref;
+	atomic_t user_wakeref;
 
 	struct list_head closed_vma;
 	spinlock_t closed_lock; /* guards the list of closed_vma */
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index e5835337f022..f3ae525b77c0 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3995,13 +3995,12 @@ static int i915_sseu_status(struct seq_file *m, void *unused)
 static int i915_forcewake_open(struct inode *inode, struct file *file)
 {
 	struct drm_i915_private *i915 = inode->i_private;
+	struct intel_gt *gt = &i915->gt;
 
-	if (INTEL_GEN(i915) < 6)
-		return 0;
-
-	file->private_data =
-		(void *)(uintptr_t)intel_runtime_pm_get(&i915->runtime_pm);
-	intel_uncore_forcewake_user_get(&i915->uncore);
+	atomic_inc(&gt->user_wakeref);
+	intel_gt_pm_get(gt);
+	if (INTEL_GEN(i915) >= 6)
+		intel_uncore_forcewake_user_get(gt->uncore);
 
 	return 0;
 }
@@ -4009,13 +4008,12 @@ static int i915_forcewake_open(struct inode *inode, struct file *file)
 static int i915_forcewake_release(struct inode *inode, struct file *file)
 {
 	struct drm_i915_private *i915 = inode->i_private;
+	struct intel_gt *gt = &i915->gt;
 
-	if (INTEL_GEN(i915) < 6)
-		return 0;
-
-	intel_uncore_forcewake_user_put(&i915->uncore);
-	intel_runtime_pm_put(&i915->runtime_pm,
-			     (intel_wakeref_t)(uintptr_t)file->private_data);
+	if (INTEL_GEN(i915) >= 6)
+		intel_uncore_forcewake_user_put(&i915->uncore);
+	intel_gt_pm_put(gt);
+	atomic_dec(&gt->user_wakeref);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 623ad32303a1..3310353890fb 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -116,22 +116,124 @@ static bool pmu_needs_timer(struct i915_pmu *pmu, bool gpu_active)
 	return enable;
 }
 
-void i915_pmu_gt_parked(struct drm_i915_private *i915)
+static u64 __get_rc6(const struct intel_gt *gt)
 {
-	struct i915_pmu *pmu = &i915->pmu;
+	struct drm_i915_private *i915 = gt->i915;
+	u64 val;
 
-	if (!pmu->base.event_init)
-		return;
+	val = intel_rc6_residency_ns(i915,
+				     IS_VALLEYVIEW(i915) ?
+				     VLV_GT_RENDER_RC6 :
+				     GEN6_GT_GFX_RC6);
+
+	if (HAS_RC6p(i915))
+		val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6p);
+
+	if (HAS_RC6pp(i915))
+		val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6pp);
+
+	return val;
+}
+
+#if IS_ENABLED(CONFIG_PM)
+
+static inline s64 ktime_since(const ktime_t kt)
+{
+	return ktime_to_ns(ktime_sub(ktime_get(), kt));
+}
+
+static u64 __pmu_estimate_rc6(struct i915_pmu *pmu)
+{
+	u64 val;
 
-	spin_lock_irq(&pmu->lock);
 	/*
-	 * Signal sampling timer to stop if only engine events are enabled and
-	 * GPU went idle.
+	 * We think we are runtime suspended.
+	 *
+	 * Report the delta from when the device was suspended to now,
+	 * on top of the last known real value, as the approximated RC6
+	 * counter value.
 	 */
-	pmu->timer_enabled = pmu_needs_timer(pmu, false);
-	spin_unlock_irq(&pmu->lock);
+	val = ktime_since(pmu->sleep_last);
+	val += pmu->sample[__I915_SAMPLE_RC6].cur;
+
+	pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val;
+
+	return val;
+}
+
+static u64 __pmu_update_rc6(struct i915_pmu *pmu, u64 val)
+{
+	/*
+	 * If we are coming back from being runtime suspended we must
+	 * be careful not to report a larger value than returned
+	 * previously.
+	 */
+	if (val >= pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur) {
+		pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur = 0;
+		pmu->sample[__I915_SAMPLE_RC6].cur = val;
+	} else {
+		val = pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur;
+	}
+
+	return val;
+}
+
+static u64 get_rc6(struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+	struct i915_pmu *pmu = &i915->pmu;
+	unsigned long flags;
+	u64 val;
+
+	val = 0;
+	if (intel_gt_pm_get_if_awake(gt)) {
+		val = __get_rc6(gt);
+		intel_gt_pm_put(gt);
+	}
+
+	spin_lock_irqsave(&pmu->lock, flags);
+
+	if (val)
+		val = __pmu_update_rc6(pmu, val);
+	else
+		val = __pmu_estimate_rc6(pmu);
+
+	spin_unlock_irqrestore(&pmu->lock, flags);
+
+	return val;
+}
+
+static void park_rc6(struct drm_i915_private *i915)
+{
+	struct i915_pmu *pmu = &i915->pmu;
+
+	if (pmu->enable & config_enabled_mask(I915_PMU_RC6_RESIDENCY))
+		__pmu_update_rc6(pmu, __get_rc6(&i915->gt));
+
+	pmu->sleep_last = ktime_get();
+}
+
+static void unpark_rc6(struct drm_i915_private *i915)
+{
+	struct i915_pmu *pmu = &i915->pmu;
+
+	/* Estimate how long we slept and accumulate that into rc6 counters */
+	if (pmu->enable & config_enabled_mask(I915_PMU_RC6_RESIDENCY))
+		__pmu_estimate_rc6(pmu);
+}
+
+#else
+
+static u64 get_rc6(struct intel_gt *gt)
+{
+	return __get_rc6(gt);
 }
 
+static void park_rc6(struct drm_i915_private *i915) {}
+static void unpark_rc6(struct drm_i915_private *i915) {}
+
+#endif
+
 static void __i915_pmu_maybe_start_timer(struct i915_pmu *pmu)
 {
 	if (!pmu->timer_enabled && pmu_needs_timer(pmu, true)) {
@@ -143,6 +245,26 @@ static void __i915_pmu_maybe_start_timer(struct i915_pmu *pmu)
 	}
 }
 
+void i915_pmu_gt_parked(struct drm_i915_private *i915)
+{
+	struct i915_pmu *pmu = &i915->pmu;
+
+	if (!pmu->base.event_init)
+		return;
+
+	spin_lock_irq(&pmu->lock);
+
+	park_rc6(i915);
+
+	/*
+	 * Signal sampling timer to stop if only engine events are enabled and
+	 * GPU went idle.
+	 */
+	pmu->timer_enabled = pmu_needs_timer(pmu, false);
+
+	spin_unlock_irq(&pmu->lock);
+}
+
 void i915_pmu_gt_unparked(struct drm_i915_private *i915)
 {
 	struct i915_pmu *pmu = &i915->pmu;
@@ -151,10 +273,14 @@ void i915_pmu_gt_unparked(struct drm_i915_private *i915)
 		return;
 
 	spin_lock_irq(&pmu->lock);
+
 	/*
 	 * Re-enable sampling timer when GPU goes active.
 	 */
 	__i915_pmu_maybe_start_timer(pmu);
+
+	unpark_rc6(i915);
+
 	spin_unlock_irq(&pmu->lock);
 }
 
@@ -430,104 +556,6 @@ static int i915_pmu_event_init(struct perf_event *event)
 	return 0;
 }
 
-static u64 __get_rc6(struct intel_gt *gt)
-{
-	struct drm_i915_private *i915 = gt->i915;
-	u64 val;
-
-	val = intel_rc6_residency_ns(i915,
-				     IS_VALLEYVIEW(i915) ?
-				     VLV_GT_RENDER_RC6 :
-				     GEN6_GT_GFX_RC6);
-
-	if (HAS_RC6p(i915))
-		val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6p);
-
-	if (HAS_RC6pp(i915))
-		val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6pp);
-
-	return val;
-}
-
-static u64 get_rc6(struct intel_gt *gt)
-{
-#if IS_ENABLED(CONFIG_PM)
-	struct drm_i915_private *i915 = gt->i915;
-	struct intel_runtime_pm *rpm = &i915->runtime_pm;
-	struct i915_pmu *pmu = &i915->pmu;
-	intel_wakeref_t wakeref;
-	unsigned long flags;
-	u64 val;
-
-	wakeref = intel_runtime_pm_get_if_in_use(rpm);
-	if (wakeref) {
-		val = __get_rc6(gt);
-		intel_runtime_pm_put(rpm, wakeref);
-
-		/*
-		 * If we are coming back from being runtime suspended we must
-		 * be careful not to report a larger value than returned
-		 * previously.
-		 */
-
-		spin_lock_irqsave(&pmu->lock, flags);
-
-		if (val >= pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur) {
-			pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur = 0;
-			pmu->sample[__I915_SAMPLE_RC6].cur = val;
-		} else {
-			val = pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur;
-		}
-
-		spin_unlock_irqrestore(&pmu->lock, flags);
-	} else {
-		struct device *kdev = rpm->kdev;
-
-		/*
-		 * We are runtime suspended.
-		 *
-		 * Report the delta from when the device was suspended to now,
-		 * on top of the last known real value, as the approximated RC6
-		 * counter value.
-		 */
-		spin_lock_irqsave(&pmu->lock, flags);
-
-		/*
-		 * After the above branch intel_runtime_pm_get_if_in_use failed
-		 * to get the runtime PM reference we cannot assume we are in
-		 * runtime suspend since we can either: a) race with coming out
-		 * of it before we took the power.lock, or b) there are other
-		 * states than suspended which can bring us here.
-		 *
-		 * We need to double-check that we are indeed currently runtime
-		 * suspended and if not we cannot do better than report the last
-		 * known RC6 value.
-		 */
-		if (pm_runtime_status_suspended(kdev)) {
-			val = pm_runtime_suspended_time(kdev);
-
-			if (!pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur)
-				pmu->suspended_time_last = val;
-
-			val -= pmu->suspended_time_last;
-			val += pmu->sample[__I915_SAMPLE_RC6].cur;
-
-			pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur = val;
-		} else if (pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur) {
-			val = pmu->sample[__I915_SAMPLE_RC6_ESTIMATED].cur;
-		} else {
-			val = pmu->sample[__I915_SAMPLE_RC6].cur;
-		}
-
-		spin_unlock_irqrestore(&pmu->lock, flags);
-	}
-
-	return val;
-#else
-	return __get_rc6(gt);
-#endif
-}
-
 static u64 __i915_pmu_event_read(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index 4fc4f2478301..067dbbf3bdff 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -97,9 +97,9 @@ struct i915_pmu {
 	 */
 	struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS];
 	/**
-	 * @suspended_time_last: Cached suspend time from PM core.
+	 * @sleep_last: Last time GT parked for RC6 estimation.
 	 */
-	u64 suspended_time_last;
+	ktime_t sleep_last;
 	/**
 	 * @i915_attr: Memory block holding device attributes.
 	 */
-- 
cgit v1.2.3


From ee73e2795b416b829f0e00e7c43154922dff495b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Sep 2019 14:23:13 +0100
Subject: drm/i915/tgl: Disable preemption while being debugged

We see failures where the context continues executing past a
preemption event, eventually leading to situations where a request has
executed before we have event submitted it to HW! It seems like tgl is
ignoring our RING_TAIL updates, but more likely is that there is a
missing update required for our semaphore waits around preemption.

v2: And disable internal semaphore usage

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190912132313.12751-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 3 +++
 drivers/gpu/drm/i915/i915_pci.c     | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 47d766ccea71..a3f0e4999744 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2939,6 +2939,9 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 			engine->flags |= I915_ENGINE_HAS_PREEMPTION;
 	}
 
+	if (INTEL_GEN(engine->i915) >= 12) /* XXX disabled for debugging */
+		engine->flags &= ~I915_ENGINE_HAS_SEMAPHORES;
+
 	if (engine->class != COPY_ENGINE_CLASS && INTEL_GEN(engine->i915) >= 12)
 		engine->flags |= I915_ENGINE_HAS_RELATIVE_MMIO;
 }
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 698116276441..9236fccb3a83 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -798,6 +798,7 @@ static const struct intel_device_info intel_tigerlake_12_info = {
 	.engine_mask =
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2),
 	.has_rc6 = false, /* XXX disabled for debugging */
+	.has_logical_ring_preemption = false, /* XXX disabled for debugging */
 };
 
 #undef GEN
-- 
cgit v1.2.3


From 0c653722e6e669fae969c178f0d4a55d9c2dc922 Mon Sep 17 00:00:00 2001
From: Arkadiusz Hiler <arkadiusz.hiler@intel.com>
Date: Thu, 12 Sep 2019 15:54:18 +0300
Subject: drm/i915: Get the correct wakeref for reading HOTPLUG_EN et al.

Without it we get:
 Unclaimed read from register 0x1e1110
 WARNING: CPU: 2 PID: 1029 at drivers/gpu/drm/i915/intel_uncore.c:1101 __unclaimed_reg_debug+0x40/0x50 [i915]
 Call Trace:
  fwtable_read32+0x233/0x300 [i915]
  i915_interrupt_info+0xa73/0xd60 [i915]
  seq_read+0xdb/0x3c0
  full_proxy_read+0x51/0x80
  vfs_read+0x9e/0x160
  ksys_read+0x8f/0xe0
  do_syscall_64+0x55/0x1c0
  entry_SYSCALL_64_after_hwframe+0x49/0xbe

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109824
Signed-off-by: Arkadiusz Hiler <arkadiusz.hiler@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190912125418.23115-2-arkadiusz.hiler@intel.com
---
 drivers/gpu/drm/i915/i915_debugfs.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index f3ae525b77c0..43db50095257 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -534,6 +534,8 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 
 		gen8_display_interrupt_info(m);
 	} else if (IS_VALLEYVIEW(dev_priv)) {
+		intel_wakeref_t pref;
+
 		seq_printf(m, "Display IER:\t%08x\n",
 			   I915_READ(VLV_IER));
 		seq_printf(m, "Display IIR:\t%08x\n",
@@ -544,7 +546,6 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 			   I915_READ(VLV_IMR));
 		for_each_pipe(dev_priv, pipe) {
 			enum intel_display_power_domain power_domain;
-			intel_wakeref_t pref;
 
 			power_domain = POWER_DOMAIN_PIPE(pipe);
 			pref = intel_display_power_get_if_enabled(dev_priv,
@@ -578,12 +579,14 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 		seq_printf(m, "PM IMR:\t\t%08x\n",
 			   I915_READ(GEN6_PMIMR));
 
+		pref = intel_display_power_get(dev_priv, POWER_DOMAIN_INIT);
 		seq_printf(m, "Port hotplug:\t%08x\n",
 			   I915_READ(PORT_HOTPLUG_EN));
 		seq_printf(m, "DPFLIPSTAT:\t%08x\n",
 			   I915_READ(VLV_DPFLIPSTAT));
 		seq_printf(m, "DPINVGTT:\t%08x\n",
 			   I915_READ(DPINVGTT));
+		intel_display_power_put(dev_priv, POWER_DOMAIN_INIT, pref);
 
 	} else if (!HAS_PCH_SPLIT(dev_priv)) {
 		seq_printf(m, "Interrupt enable:    %08x\n",
-- 
cgit v1.2.3


From 0b8d6273db0635acd0dae983a39600b1b96fe77d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Sep 2019 13:26:39 +0100
Subject: drm/i915/selftests: Keep the engine awake while we keep for
 preemption

Keep the engine awake to ensure that we don't inject any pm-idle
requests.

References: https://bugs.freedesktop.org/show_bug.cgi?id=111108
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190912122639.25224-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/selftest_lrc.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index d791158988d6..26d05bd1bdc8 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -897,6 +897,10 @@ static int live_suppress_self_preempt(void *arg)
 		if (!intel_engine_has_preemption(engine))
 			continue;
 
+		if (igt_flush_test(i915, I915_WAIT_LOCKED))
+			goto err_wedged;
+
+		intel_engine_pm_get(engine);
 		engine->execlists.preempt_hang.count = 0;
 
 		rq_a = spinner_create_request(&a.spin,
@@ -904,12 +908,14 @@ static int live_suppress_self_preempt(void *arg)
 					      MI_NOOP);
 		if (IS_ERR(rq_a)) {
 			err = PTR_ERR(rq_a);
+			intel_engine_pm_put(engine);
 			goto err_client_b;
 		}
 
 		i915_request_add(rq_a);
 		if (!igt_wait_for_spinner(&a.spin, rq_a)) {
 			pr_err("First client failed to start\n");
+			intel_engine_pm_put(engine);
 			goto err_wedged;
 		}
 
@@ -921,6 +927,7 @@ static int live_suppress_self_preempt(void *arg)
 						      MI_NOOP);
 			if (IS_ERR(rq_b)) {
 				err = PTR_ERR(rq_b);
+				intel_engine_pm_put(engine);
 				goto err_client_b;
 			}
 			i915_request_add(rq_b);
@@ -931,6 +938,7 @@ static int live_suppress_self_preempt(void *arg)
 
 			if (!igt_wait_for_spinner(&b.spin, rq_b)) {
 				pr_err("Second client failed to start\n");
+				intel_engine_pm_put(engine);
 				goto err_wedged;
 			}
 
@@ -944,10 +952,12 @@ static int live_suppress_self_preempt(void *arg)
 			       engine->name,
 			       engine->execlists.preempt_hang.count,
 			       depth);
+			intel_engine_pm_put(engine);
 			err = -EINVAL;
 			goto err_client_b;
 		}
 
+		intel_engine_pm_put(engine);
 		if (igt_flush_test(i915, I915_WAIT_LOCKED))
 			goto err_wedged;
 	}
-- 
cgit v1.2.3


From c8185520aed6faab58b310f573790badfca27981 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 13 Sep 2019 07:42:00 +0100
Subject: drm/i915/gtt: Make sure the gen6 ppgtt is bound before first use

As we remove the struct_mutex protection from around the vma pinning,
counters need to be atomic and aware that there may be multiple threads
simultaneously active.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190913064200.24297-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 40 ++++++++++++++++++++-----------------
 drivers/gpu/drm/i915/i915_gem_gtt.h |  4 +++-
 2 files changed, 25 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index a09a9b62afbe..e62e9d1a1307 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1790,6 +1790,8 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 
 	gen6_ppgtt_free_pd(ppgtt);
 	free_scratch(vm);
+
+	mutex_destroy(&ppgtt->pin_mutex);
 	kfree(ppgtt->base.pd);
 }
 
@@ -1895,7 +1897,7 @@ static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
 int gen6_ppgtt_pin(struct i915_ppgtt *base)
 {
 	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
-	int err;
+	int err = 0;
 
 	GEM_BUG_ON(ppgtt->base.vm.closed);
 
@@ -1905,24 +1907,26 @@ int gen6_ppgtt_pin(struct i915_ppgtt *base)
 	 * (When vma->pin_count becomes atomic, I expect we will naturally
 	 * need a larger, unpacked, type and kill this redundancy.)
 	 */
-	if (ppgtt->pin_count++)
+	if (atomic_add_unless(&ppgtt->pin_count, 1, 0))
 		return 0;
 
+	if (mutex_lock_interruptible(&ppgtt->pin_mutex))
+		return -EINTR;
+
 	/*
 	 * PPGTT PDEs reside in the GGTT and consists of 512 entries. The
 	 * allocator works in address space sizes, so it's multiplied by page
 	 * size. We allocate at the top of the GTT to avoid fragmentation.
 	 */
-	err = i915_vma_pin(ppgtt->vma,
-			   0, GEN6_PD_ALIGN,
-			   PIN_GLOBAL | PIN_HIGH);
-	if (err)
-		goto unpin;
-
-	return 0;
+	if (!atomic_read(&ppgtt->pin_count)) {
+		err = i915_vma_pin(ppgtt->vma,
+				   0, GEN6_PD_ALIGN,
+				   PIN_GLOBAL | PIN_HIGH);
+	}
+	if (!err)
+		atomic_inc(&ppgtt->pin_count);
+	mutex_unlock(&ppgtt->pin_mutex);
 
-unpin:
-	ppgtt->pin_count = 0;
 	return err;
 }
 
@@ -1930,22 +1934,20 @@ void gen6_ppgtt_unpin(struct i915_ppgtt *base)
 {
 	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
 
-	GEM_BUG_ON(!ppgtt->pin_count);
-	if (--ppgtt->pin_count)
-		return;
-
-	i915_vma_unpin(ppgtt->vma);
+	GEM_BUG_ON(!atomic_read(&ppgtt->pin_count));
+	if (atomic_dec_and_test(&ppgtt->pin_count))
+		i915_vma_unpin(ppgtt->vma);
 }
 
 void gen6_ppgtt_unpin_all(struct i915_ppgtt *base)
 {
 	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
 
-	if (!ppgtt->pin_count)
+	if (!atomic_read(&ppgtt->pin_count))
 		return;
 
-	ppgtt->pin_count = 0;
 	i915_vma_unpin(ppgtt->vma);
+	atomic_set(&ppgtt->pin_count, 0);
 }
 
 static struct i915_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
@@ -1958,6 +1960,8 @@ static struct i915_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 	if (!ppgtt)
 		return ERR_PTR(-ENOMEM);
 
+	mutex_init(&ppgtt->pin_mutex);
+
 	ppgtt_init(&ppgtt->base, &i915->gt);
 	ppgtt->base.vm.top = 1;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 201788126a89..8fd2234ba0bf 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -437,7 +437,9 @@ struct gen6_ppgtt {
 	struct i915_vma *vma;
 	gen6_pte_t __iomem *pd_addr;
 
-	unsigned int pin_count;
+	atomic_t pin_count;
+	struct mutex pin_mutex;
+
 	bool scan_for_unused_pt;
 };
 
-- 
cgit v1.2.3


From 12a97df00e2aa6fb2200a8935e78f3e00fab4eb2 Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Fri, 12 Jul 2019 13:22:13 -0700
Subject: drm/i915/display/icl: Bump up the hdisplay and vdisplay as per
 transcoder limits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On ICL+, the vertical limits for the transcoders are increased to 8192
and horizontal limits are bumped to 16K so bump up
limits in intel_mode_valid()

v4:
* Increase the hdisplay to 16K (Ville)
v3:
* Supported starting ICL (Ville)
* Use the higher limits from TRANS_VTOTAL register (Ville)
v2:
* Checkpatch warning (Manasi)

Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190712202214.3906-1-manasi.d.navare@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index a19f8c73f2e0..d77fd6ddac49 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -15839,8 +15839,13 @@ intel_mode_valid(struct drm_device *dev,
 			   DRM_MODE_FLAG_CLKDIV2))
 		return MODE_BAD;
 
-	if (INTEL_GEN(dev_priv) >= 9 ||
-	    IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 11) {
+		hdisplay_max = 16384;
+		vdisplay_max = 8192;
+		htotal_max = 16384;
+		vtotal_max = 8192;
+	} else if (INTEL_GEN(dev_priv) >= 9 ||
+		   IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) {
 		hdisplay_max = 8192; /* FDI max 4096 handled elsewhere */
 		vdisplay_max = 4096;
 		htotal_max = 8192;
-- 
cgit v1.2.3


From e91c8a29b452671d9af7259cd30980e6a2d78005 Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Fri, 12 Jul 2019 13:38:08 -0700
Subject: drm/i915/display/icl: Bump up the plane/fb height
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On ICL+, the max supported plane height is 4320, so bump it up
To support 4320, we need to increase the number of bits used to
read plane_height to 13 as opposed to older 12 bits.

v4:
* Adjust the width mask also since extra bits are mbz (Ville)
v3:
* Use 0xffff for mask as extra bits are mbz (Ville)
v2:
* ICL plane height supported is 4320 (Ville)
* Add a new line between max width and max height (Jose)

Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190712203808.4126-1-manasi.d.navare@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index d77fd6ddac49..4e001113e828 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3333,6 +3333,16 @@ static int icl_max_plane_width(const struct drm_framebuffer *fb,
 	return 5120;
 }
 
+static int skl_max_plane_height(void)
+{
+	return 4096;
+}
+
+static int icl_max_plane_height(void)
+{
+	return 4320;
+}
+
 static bool skl_check_main_ccs_coordinates(struct intel_plane_state *plane_state,
 					   int main_x, int main_y, u32 main_offset)
 {
@@ -3381,7 +3391,7 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 	int w = drm_rect_width(&plane_state->base.src) >> 16;
 	int h = drm_rect_height(&plane_state->base.src) >> 16;
 	int max_width;
-	int max_height = 4096;
+	int max_height;
 	u32 alignment, offset, aux_offset = plane_state->color_plane[1].offset;
 
 	if (INTEL_GEN(dev_priv) >= 11)
@@ -3391,6 +3401,11 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 	else
 		max_width = skl_max_plane_width(fb, 0, rotation);
 
+	if (INTEL_GEN(dev_priv) >= 11)
+		max_height = icl_max_plane_height();
+	else
+		max_height = skl_max_plane_height();
+
 	if (w > max_width || h > max_height) {
 		DRM_DEBUG_KMS("requested Y/RGB source size %dx%d too big (limit %dx%d)\n",
 			      w, h, max_width, max_height);
@@ -9873,8 +9888,8 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
 	offset = I915_READ(PLANE_OFFSET(pipe, plane_id));
 
 	val = I915_READ(PLANE_SIZE(pipe, plane_id));
-	fb->height = ((val >> 16) & 0xfff) + 1;
-	fb->width = ((val >> 0) & 0x1fff) + 1;
+	fb->height = ((val >> 16) & 0xffff) + 1;
+	fb->width = ((val >> 0) & 0xffff) + 1;
 
 	val = I915_READ(PLANE_STRIDE(pipe, plane_id));
 	stride_mult = skl_plane_stride_mult(fb, 0, DRM_MODE_ROTATE_0);
-- 
cgit v1.2.3


From eebab60f224fcfd560957715d08c31564d8672ed Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Sep 2019 17:08:34 +0100
Subject: drm/i915: Don't mix srcu tag and negative error codes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While srcu may use an integer tag, it does not exclude potential error
codes and so may overlap with our own use of -EINTR. Use a separate
outparam to store the tag, and report the error code separately.

Fixes: 2caffbf11762 ("drm/i915: Revoke mmaps and prevent access to fence registers across reset")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190912160834.30601-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_mman.c | 6 ++----
 drivers/gpu/drm/i915/gt/intel_reset.c    | 8 +++-----
 drivers/gpu/drm/i915/gt/intel_reset.h    | 2 +-
 3 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 82db2b783123..1748e63156a2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -245,11 +245,9 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 
 	wakeref = intel_runtime_pm_get(rpm);
 
-	srcu = intel_gt_reset_trylock(ggtt->vm.gt);
-	if (srcu < 0) {
-		ret = srcu;
+	ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu);
+	if (ret)
 		goto err_rpm;
-	}
 
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 296bbc7745fb..8327220ac558 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -1214,10 +1214,8 @@ out:
 	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
 }
 
-int intel_gt_reset_trylock(struct intel_gt *gt)
+int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
 {
-	int srcu;
-
 	might_lock(&gt->reset.backoff_srcu);
 	might_sleep();
 
@@ -1232,10 +1230,10 @@ int intel_gt_reset_trylock(struct intel_gt *gt)
 
 		rcu_read_lock();
 	}
-	srcu = srcu_read_lock(&gt->reset.backoff_srcu);
+	*srcu = srcu_read_lock(&gt->reset.backoff_srcu);
 	rcu_read_unlock();
 
-	return srcu;
+	return 0;
 }
 
 void intel_gt_reset_unlock(struct intel_gt *gt, int tag)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h
index 37a987b17108..52c00199e069 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.h
+++ b/drivers/gpu/drm/i915/gt/intel_reset.h
@@ -38,7 +38,7 @@ int intel_engine_reset(struct intel_engine_cs *engine,
 
 void __i915_request_reset(struct i915_request *rq, bool guilty);
 
-int __must_check intel_gt_reset_trylock(struct intel_gt *gt);
+int __must_check intel_gt_reset_trylock(struct intel_gt *gt, int *srcu);
 void intel_gt_reset_unlock(struct intel_gt *gt, int tag);
 
 void intel_gt_set_wedged(struct intel_gt *gt);
-- 
cgit v1.2.3


From 6da301e5291717861fb25025b782922d3a36c7af Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 13 Sep 2019 15:55:56 +0100
Subject: drm/i915/tgl: Limit ourselves to just rcs0

More pruning away of features until we have a stable system and a basis
for debugging what's missing.

v2: Fixup vdbox/vebox fusing

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190913145556.23912-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_pci.c          | 1 +
 drivers/gpu/drm/i915/intel_device_info.c | 8 ++++++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 9236fccb3a83..ee9a7959204c 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -799,6 +799,7 @@ static const struct intel_device_info intel_tigerlake_12_info = {
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2),
 	.has_rc6 = false, /* XXX disabled for debugging */
 	.has_logical_ring_preemption = false, /* XXX disabled for debugging */
+	.engine_mask = BIT(RCS0), /* XXX reduced for debugging */
 };
 
 #undef GEN
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 50b05a5de53b..727089dcd280 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -1004,8 +1004,10 @@ void intel_device_info_init_mmio(struct drm_i915_private *dev_priv)
 		      GEN11_GT_VEBOX_DISABLE_SHIFT;
 
 	for (i = 0; i < I915_MAX_VCS; i++) {
-		if (!HAS_ENGINE(dev_priv, _VCS(i)))
+		if (!HAS_ENGINE(dev_priv, _VCS(i))) {
+			vdbox_mask &= ~BIT(i);
 			continue;
+		}
 
 		if (!(BIT(i) & vdbox_mask)) {
 			info->engine_mask &= ~BIT(_VCS(i));
@@ -1026,8 +1028,10 @@ void intel_device_info_init_mmio(struct drm_i915_private *dev_priv)
 	GEM_BUG_ON(vdbox_mask != VDBOX_MASK(dev_priv));
 
 	for (i = 0; i < I915_MAX_VECS; i++) {
-		if (!HAS_ENGINE(dev_priv, _VECS(i)))
+		if (!HAS_ENGINE(dev_priv, _VECS(i))) {
+			vebox_mask &= ~BIT(i);
 			continue;
+		}
 
 		if (!(BIT(i) & vebox_mask)) {
 			info->engine_mask &= ~BIT(_VECS(i));
-- 
cgit v1.2.3


From c9f8d18710bee1c5b87d54007c24d8bf79029fb6 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Fri, 13 Sep 2019 17:16:50 +0300
Subject: drm/i915: Update Gen11 forcewake ranges

Daniele noticed new render ranges in Gen11 fw table.

Bspec: 18331
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190913141652.27958-1-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/intel_uncore.c | 23 +++++++++--------------
 1 file changed, 9 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 9e583f13a9e4..732082a72022 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -805,9 +805,6 @@ void assert_forcewakes_active(struct intel_uncore *uncore,
 /* We give fast paths for the really cool registers */
 #define NEEDS_FORCE_WAKE(reg) ((reg) < 0x40000)
 
-#define GEN11_NEEDS_FORCE_WAKE(reg) \
-	((reg) < 0x40000 || ((reg) >= 0x1c0000 && (reg) < 0x1dc000))
-
 #define __gen6_reg_read_fw_domains(uncore, offset) \
 ({ \
 	enum forcewake_domains __fwd; \
@@ -903,12 +900,7 @@ static const struct intel_forcewake_range __vlv_fw_ranges[] = {
 })
 
 #define __gen11_fwtable_reg_read_fw_domains(uncore, offset) \
-({ \
-	enum forcewake_domains __fwd = 0; \
-	if (GEN11_NEEDS_FORCE_WAKE((offset))) \
-		__fwd = find_fw_domain(uncore, offset); \
-	__fwd; \
-})
+	find_fw_domain(uncore, offset)
 
 /* *Must* be sorted by offset! See intel_shadow_table_check(). */
 static const i915_reg_t gen8_shadowed_regs[] = {
@@ -1005,8 +997,9 @@ static const struct intel_forcewake_range __chv_fw_ranges[] = {
 #define __gen11_fwtable_reg_write_fw_domains(uncore, offset) \
 ({ \
 	enum forcewake_domains __fwd = 0; \
-	if (GEN11_NEEDS_FORCE_WAKE((offset)) && !is_gen11_shadowed(offset)) \
-		__fwd = find_fw_domain(uncore, offset); \
+	const u32 __offset = (offset); \
+	if (!is_gen11_shadowed(__offset)) \
+		__fwd = find_fw_domain(uncore, __offset); \
 	__fwd; \
 })
 
@@ -1065,9 +1058,11 @@ static const struct intel_forcewake_range __gen11_fw_ranges[] = {
 	GEN_FW_RANGE(0x9400, 0x97ff, FORCEWAKE_ALL),
 	GEN_FW_RANGE(0x9800, 0xafff, FORCEWAKE_BLITTER),
 	GEN_FW_RANGE(0xb000, 0xb47f, FORCEWAKE_RENDER),
-	GEN_FW_RANGE(0xb480, 0xdfff, FORCEWAKE_BLITTER),
-	GEN_FW_RANGE(0xe000, 0xe8ff, FORCEWAKE_RENDER),
-	GEN_FW_RANGE(0xe900, 0x243ff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0xb480, 0xdeff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0xdf00, 0xe8ff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0xe900, 0x16dff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x16e00, 0x19fff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x1a000, 0x243ff, FORCEWAKE_BLITTER),
 	GEN_FW_RANGE(0x24400, 0x247ff, FORCEWAKE_RENDER),
 	GEN_FW_RANGE(0x24800, 0x3ffff, FORCEWAKE_BLITTER),
 	GEN_FW_RANGE(0x40000, 0x1bffff, 0),
-- 
cgit v1.2.3


From cf82d9ddd3b5203dea5561dfabd1216b8159af37 Mon Sep 17 00:00:00 2001
From: Michel Thierry <michel.thierry@intel.com>
Date: Fri, 13 Sep 2019 17:16:51 +0300
Subject: drm/i915/tgl: Introduce gen12 forcewake ranges

The media ranges extend beyond what gen11 gives so we can't piggypack
on gen11 ranges, even on read side.

Introduce a table for gen12 and accessors for it.

v2: correctly implement gen12_fwtable_write/read (Daniele)
v3: update with ranges from bspec.
v4: avoid GEN11_NEEDS_FORCEWAKE (Mika)
v5: bspec ref (Daniele)

BSpec: 52078
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190913141652.27958-2-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/intel_uncore.c           | 75 ++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/selftests/intel_uncore.c |  2 +
 2 files changed, 76 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 732082a72022..94a97bf8c021 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -902,6 +902,9 @@ static const struct intel_forcewake_range __vlv_fw_ranges[] = {
 #define __gen11_fwtable_reg_read_fw_domains(uncore, offset) \
 	find_fw_domain(uncore, offset)
 
+#define __gen12_fwtable_reg_read_fw_domains(uncore, offset) \
+	find_fw_domain(uncore, offset)
+
 /* *Must* be sorted by offset! See intel_shadow_table_check(). */
 static const i915_reg_t gen8_shadowed_regs[] = {
 	RING_TAIL(RENDER_RING_BASE),	/* 0x2000 (base) */
@@ -927,6 +930,20 @@ static const i915_reg_t gen11_shadowed_regs[] = {
 	/* TODO: Other registers are not yet used */
 };
 
+static const i915_reg_t gen12_shadowed_regs[] = {
+	RING_TAIL(RENDER_RING_BASE),		/* 0x2000 (base) */
+	GEN6_RPNSWREQ,				/* 0xA008 */
+	GEN6_RC_VIDEO_FREQ,			/* 0xA00C */
+	RING_TAIL(BLT_RING_BASE),		/* 0x22000 (base) */
+	RING_TAIL(GEN11_BSD_RING_BASE),		/* 0x1C0000 (base) */
+	RING_TAIL(GEN11_BSD2_RING_BASE),	/* 0x1C4000 (base) */
+	RING_TAIL(GEN11_VEBOX_RING_BASE),	/* 0x1C8000 (base) */
+	RING_TAIL(GEN11_BSD3_RING_BASE),	/* 0x1D0000 (base) */
+	RING_TAIL(GEN11_BSD4_RING_BASE),	/* 0x1D4000 (base) */
+	RING_TAIL(GEN11_VEBOX2_RING_BASE),	/* 0x1D8000 (base) */
+	/* TODO: Other registers are not yet used */
+};
+
 static int mmio_reg_cmp(u32 key, const i915_reg_t *reg)
 {
 	u32 offset = i915_mmio_reg_offset(*reg);
@@ -949,6 +966,7 @@ static bool is_gen##x##_shadowed(u32 offset) \
 
 __is_genX_shadowed(8)
 __is_genX_shadowed(11)
+__is_genX_shadowed(12)
 
 static enum forcewake_domains
 gen6_reg_write_fw_domains(struct intel_uncore *uncore, i915_reg_t reg)
@@ -1003,6 +1021,15 @@ static const struct intel_forcewake_range __chv_fw_ranges[] = {
 	__fwd; \
 })
 
+#define __gen12_fwtable_reg_write_fw_domains(uncore, offset) \
+({ \
+	enum forcewake_domains __fwd = 0; \
+	const u32 __offset = (offset); \
+	if (!is_gen12_shadowed(__offset)) \
+		__fwd = find_fw_domain(uncore, __offset); \
+	__fwd; \
+})
+
 /* *Must* be sorted by offset ranges! See intel_fw_table_check(). */
 static const struct intel_forcewake_range __gen9_fw_ranges[] = {
 	GEN_FW_RANGE(0x0, 0xaff, FORCEWAKE_BLITTER),
@@ -1075,6 +1102,46 @@ static const struct intel_forcewake_range __gen11_fw_ranges[] = {
 	GEN_FW_RANGE(0x1d8000, 0x1dbfff, FORCEWAKE_MEDIA_VEBOX1)
 };
 
+/* *Must* be sorted by offset ranges! See intel_fw_table_check(). */
+static const struct intel_forcewake_range __gen12_fw_ranges[] = {
+	GEN_FW_RANGE(0x0, 0xaff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0xb00, 0x1fff, 0), /* uncore range */
+	GEN_FW_RANGE(0x2000, 0x26ff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x2700, 0x2fff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x3000, 0x3fff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x4000, 0x51ff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x5200, 0x7fff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x8000, 0x813f, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x8140, 0x815f, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x8160, 0x82ff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x8300, 0x84ff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x8500, 0x8bff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x8c00, 0x8cff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x8d00, 0x93ff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x9400, 0x97ff, FORCEWAKE_ALL),
+	GEN_FW_RANGE(0x9800, 0xafff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0xb000, 0xb47f, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0xb480, 0xdfff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0xe000, 0xe8ff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0xe900, 0x147ff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x14800, 0x148ff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x14900, 0x19fff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x1a000, 0x1a7ff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x1a800, 0x1afff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x1b000, 0x1bfff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x1c000, 0x243ff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x24400, 0x247ff, FORCEWAKE_RENDER),
+	GEN_FW_RANGE(0x24800, 0x3ffff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x40000, 0x1bffff, 0),
+	GEN_FW_RANGE(0x1c0000, 0x1c3fff, FORCEWAKE_MEDIA_VDBOX0),
+	GEN_FW_RANGE(0x1c4000, 0x1c7fff, FORCEWAKE_MEDIA_VDBOX1),
+	GEN_FW_RANGE(0x1c8000, 0x1cbfff, FORCEWAKE_MEDIA_VEBOX0),
+	GEN_FW_RANGE(0x1cc000, 0x1cffff, FORCEWAKE_BLITTER),
+	GEN_FW_RANGE(0x1d0000, 0x1d3fff, FORCEWAKE_MEDIA_VDBOX2),
+	GEN_FW_RANGE(0x1d4000, 0x1d7fff, FORCEWAKE_MEDIA_VDBOX3),
+	GEN_FW_RANGE(0x1d8000, 0x1dbfff, FORCEWAKE_MEDIA_VEBOX1)
+};
+
 static void
 ilk_dummy_write(struct intel_uncore *uncore)
 {
@@ -1223,6 +1290,7 @@ __gen_read(func, 16) \
 __gen_read(func, 32) \
 __gen_read(func, 64)
 
+__gen_reg_read_funcs(gen12_fwtable);
 __gen_reg_read_funcs(gen11_fwtable);
 __gen_reg_read_funcs(fwtable);
 __gen_reg_read_funcs(gen6);
@@ -1314,6 +1382,7 @@ __gen_write(func, 8) \
 __gen_write(func, 16) \
 __gen_write(func, 32)
 
+__gen_reg_write_funcs(gen12_fwtable);
 __gen_reg_write_funcs(gen11_fwtable);
 __gen_reg_write_funcs(fwtable);
 __gen_reg_write_funcs(gen8);
@@ -1685,10 +1754,14 @@ static int uncore_forcewake_init(struct intel_uncore *uncore)
 		ASSIGN_FW_DOMAINS_TABLE(uncore, __gen9_fw_ranges);
 		ASSIGN_WRITE_MMIO_VFUNCS(uncore, fwtable);
 		ASSIGN_READ_MMIO_VFUNCS(uncore, fwtable);
-	} else {
+	} else if (IS_GEN(i915, 11)) {
 		ASSIGN_FW_DOMAINS_TABLE(uncore, __gen11_fw_ranges);
 		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen11_fwtable);
 		ASSIGN_READ_MMIO_VFUNCS(uncore, gen11_fwtable);
+	} else {
+		ASSIGN_FW_DOMAINS_TABLE(uncore, __gen12_fw_ranges);
+		ASSIGN_WRITE_MMIO_VFUNCS(uncore, gen12_fwtable);
+		ASSIGN_READ_MMIO_VFUNCS(uncore, gen12_fwtable);
 	}
 
 	uncore->pmic_bus_access_nb.notifier_call = i915_pmic_bus_access_notifier;
diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c
index 86815c6072a1..0ffb141eb988 100644
--- a/drivers/gpu/drm/i915/selftests/intel_uncore.c
+++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c
@@ -67,6 +67,7 @@ static int intel_shadow_table_check(void)
 	} reg_lists[] = {
 		{ gen8_shadowed_regs, ARRAY_SIZE(gen8_shadowed_regs) },
 		{ gen11_shadowed_regs, ARRAY_SIZE(gen11_shadowed_regs) },
+		{ gen12_shadowed_regs, ARRAY_SIZE(gen12_shadowed_regs) },
 	};
 	const i915_reg_t *reg;
 	unsigned int i, j;
@@ -101,6 +102,7 @@ int intel_uncore_mock_selftests(void)
 		{ __chv_fw_ranges, ARRAY_SIZE(__chv_fw_ranges), false },
 		{ __gen9_fw_ranges, ARRAY_SIZE(__gen9_fw_ranges), true },
 		{ __gen11_fw_ranges, ARRAY_SIZE(__gen11_fw_ranges), true },
+		{ __gen12_fw_ranges, ARRAY_SIZE(__gen12_fw_ranges), true },
 	};
 	int err, i;
 
-- 
cgit v1.2.3


From 2f7155629c9dd4d4ed0c2ec95a8982c84882b9e2 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Fri, 13 Sep 2019 21:06:38 +0100
Subject: drm/i915/tgl: Re-enable rc6

We think that we got rc6 problems sorted out. Flip the switch
and let CI expose our tendency to naive optimism.

Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190913200638.31939-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_pci.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index ee9a7959204c..e4a26bbd8788 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -797,7 +797,6 @@ static const struct intel_device_info intel_tigerlake_12_info = {
 	.display.has_modular_fia = 1,
 	.engine_mask =
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2),
-	.has_rc6 = false, /* XXX disabled for debugging */
 	.has_logical_ring_preemption = false, /* XXX disabled for debugging */
 	.engine_mask = BIT(RCS0), /* XXX reduced for debugging */
 };
-- 
cgit v1.2.3


From a2b69ea4d26d1077b00924ff34e46b28d997aae2 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 13 Sep 2019 13:04:07 +0300
Subject: drm/i915: introduce INTEL_DISPLAY_ENABLED()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prepare for making a distinction between not having display and having
disabled display. Add INTEL_DISPLAY_ENABLED() and use it where
HAS_DISPLAY() is used after intel_device_info_runtime_init(). This is
initially duplication, as disabling display still leads to ->pipe_mask =
0 and HAS_DISPLAY() being false.

Note that ever since i915.display_disable was introduced, it has not
affected PCH detection even if it uses HAS_DISPLAY(), as display disable
happens after that.

Since INTEL_DISPLAY_ENABLED() will not make sense unless HAS_DISPLAY()
is true, include a warning for catching misuses making decisions on
INTEL_DISPLAY_ENABLED() when HAS_DISPLAY() is false.

v2: Remove INTEL_DISPLAY_ENABLED() check from intel_detect_pch() (Chris)

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Acked-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190913100407.30991-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/display/intel_bios.c    | 2 +-
 drivers/gpu/drm/i915/display/intel_display.c | 4 ++--
 drivers/gpu/drm/i915/display/intel_fbdev.c   | 2 +-
 drivers/gpu/drm/i915/display/intel_gmbus.c   | 2 +-
 drivers/gpu/drm/i915/i915_drv.c              | 8 ++++----
 drivers/gpu/drm/i915/i915_drv.h              | 3 +++
 6 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index efb39f350b19..1def550c68c8 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1833,7 +1833,7 @@ void intel_bios_init(struct drm_i915_private *dev_priv)
 	const struct bdb_header *bdb;
 	u8 __iomem *bios = NULL;
 
-	if (!HAS_DISPLAY(dev_priv)) {
+	if (!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv)) {
 		DRM_DEBUG_KMS("Skipping VBT init due to disabled display.\n");
 		return;
 	}
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 4e001113e828..e75945a53e06 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -15381,7 +15381,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 
 	intel_pps_init(dev_priv);
 
-	if (!HAS_DISPLAY(dev_priv))
+	if (!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv))
 		return;
 
 	if (INTEL_GEN(dev_priv) >= 12) {
@@ -17293,7 +17293,7 @@ intel_display_capture_error_state(struct drm_i915_private *dev_priv)
 
 	BUILD_BUG_ON(ARRAY_SIZE(transcoders) != ARRAY_SIZE(error->transcoder));
 
-	if (!HAS_DISPLAY(dev_priv))
+	if (!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv))
 		return NULL;
 
 	error = kzalloc(sizeof(*error), GFP_ATOMIC);
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index d59eee5c5d9c..68338669f054 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -444,7 +444,7 @@ int intel_fbdev_init(struct drm_device *dev)
 	struct intel_fbdev *ifbdev;
 	int ret;
 
-	if (WARN_ON(!HAS_DISPLAY(dev_priv)))
+	if (WARN_ON(!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv)))
 		return -ENODEV;
 
 	ifbdev = kzalloc(sizeof(struct intel_fbdev), GFP_KERNEL);
diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c
index d6775a005726..3d4d19ac1d14 100644
--- a/drivers/gpu/drm/i915/display/intel_gmbus.c
+++ b/drivers/gpu/drm/i915/display/intel_gmbus.c
@@ -836,7 +836,7 @@ int intel_gmbus_setup(struct drm_i915_private *dev_priv)
 	unsigned int pin;
 	int ret;
 
-	if (!HAS_DISPLAY(dev_priv))
+	if (!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv))
 		return 0;
 
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index c52ef2223580..c95986a984c8 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -338,7 +338,7 @@ static int i915_driver_modeset_probe(struct drm_device *dev)
 	if (i915_inject_probe_failure(dev_priv))
 		return -ENODEV;
 
-	if (HAS_DISPLAY(dev_priv)) {
+	if (HAS_DISPLAY(dev_priv) && INTEL_DISPLAY_ENABLED(dev_priv)) {
 		ret = drm_vblank_init(&dev_priv->drm,
 				      INTEL_NUM_PIPES(dev_priv));
 		if (ret)
@@ -389,7 +389,7 @@ static int i915_driver_modeset_probe(struct drm_device *dev)
 
 	intel_overlay_setup(dev_priv);
 
-	if (!HAS_DISPLAY(dev_priv))
+	if (!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv))
 		return 0;
 
 	ret = intel_fbdev_init(dev);
@@ -1415,7 +1415,7 @@ static void i915_driver_register(struct drm_i915_private *dev_priv)
 	} else
 		DRM_ERROR("Failed to register driver for userspace access!\n");
 
-	if (HAS_DISPLAY(dev_priv)) {
+	if (HAS_DISPLAY(dev_priv) && INTEL_DISPLAY_ENABLED(dev_priv)) {
 		/* Must be done after probing outputs */
 		intel_opregion_register(dev_priv);
 		acpi_video_register();
@@ -1438,7 +1438,7 @@ static void i915_driver_register(struct drm_i915_private *dev_priv)
 	 * We need to coordinate the hotplugs with the asynchronous fbdev
 	 * configuration, for which we use the fbdev->async_cookie.
 	 */
-	if (HAS_DISPLAY(dev_priv))
+	if (HAS_DISPLAY(dev_priv) && INTEL_DISPLAY_ENABLED(dev_priv))
 		drm_kms_helper_poll_init(dev);
 
 	intel_power_domains_enable(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index bf600888b3f1..4faec2f94e19 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2192,6 +2192,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 
 #define HAS_DISPLAY(dev_priv) (INTEL_INFO(dev_priv)->pipe_mask != 0)
 
+/* Only valid when HAS_DISPLAY() is true */
+#define INTEL_DISPLAY_ENABLED(dev_priv) (WARN_ON(!HAS_DISPLAY(dev_priv)), !i915_modparams.disable_display)
+
 static inline bool intel_vtd_active(void)
 {
 #ifdef CONFIG_INTEL_IOMMU
-- 
cgit v1.2.3


From d1d23d7f4be6a619af4ab729a12856e9cbded985 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 13 Sep 2019 22:31:54 +0300
Subject: drm/i915: Replace is_planar_yuv_format() with
 drm_format_info_is_yuv_semiplanar()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There's a helper in drm_fourcc.h these days to check of we're dealing
with a two plane YUV format. Make use if it.

Also s/plane/color_plane/ in skl_plane_relative_data_rate() to reduce
the confusion.

Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190913193157.9556-2-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_atomic_plane.c |  5 +++--
 drivers/gpu/drm/i915/display/intel_display.c      | 10 ++++-----
 drivers/gpu/drm/i915/display/intel_display.h      |  3 ++-
 drivers/gpu/drm/i915/display/intel_sprite.c       | 20 ++++-------------
 drivers/gpu/drm/i915/display/intel_sprite.h       |  1 -
 drivers/gpu/drm/i915/intel_pm.c                   | 27 +++++++++++------------
 6 files changed, 27 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index d1fcdf206da4..476ef0906ba0 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -144,6 +144,7 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 					struct intel_plane_state *new_plane_state)
 {
 	struct intel_plane *plane = to_intel_plane(new_plane_state->base.plane);
+	const struct drm_framebuffer *fb = new_plane_state->base.fb;
 	int ret;
 
 	new_crtc_state->active_planes &= ~BIT(plane->id);
@@ -164,11 +165,11 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 		new_crtc_state->active_planes |= BIT(plane->id);
 
 	if (new_plane_state->base.visible &&
-	    is_planar_yuv_format(new_plane_state->base.fb->format->format))
+	    drm_format_info_is_yuv_semiplanar(fb->format))
 		new_crtc_state->nv12_planes |= BIT(plane->id);
 
 	if (new_plane_state->base.visible &&
-	    new_plane_state->base.fb->format->format == DRM_FORMAT_C8)
+	    fb->format->format == DRM_FORMAT_C8)
 		new_crtc_state->c8_planes |= BIT(plane->id);
 
 	if (new_plane_state->base.visible || old_plane_state->base.visible)
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index e75945a53e06..276adc303564 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3545,7 +3545,7 @@ int skl_check_plane_surface(struct intel_plane_state *plane_state)
 	 * Handle the AUX surface first since
 	 * the main surface setup depends on it.
 	 */
-	if (is_planar_yuv_format(fb->format->format)) {
+	if (drm_format_info_is_yuv_semiplanar(fb->format)) {
 		ret = skl_check_nv12_aux_surface(plane_state);
 		if (ret)
 			return ret;
@@ -5463,7 +5463,7 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		return 0;
 	}
 
-	if (format && is_planar_yuv_format(format->format) &&
+	if (format && drm_format_info_is_yuv_semiplanar(format) &&
 	    (src_h < SKL_MIN_YUV_420_SRC_H || src_w < SKL_MIN_YUV_420_SRC_W)) {
 		DRM_DEBUG_KMS("Planar YUV: src dimensions not met\n");
 		return -EINVAL;
@@ -5540,7 +5540,7 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 
 	/* Pre-gen11 and SDR planes always need a scaler for planar formats. */
 	if (!icl_is_hdr_plane(dev_priv, intel_plane->id) &&
-	    fb && is_planar_yuv_format(fb->format->format))
+	    fb && drm_format_info_is_yuv_semiplanar(fb->format))
 		need_scaler = true;
 
 	ret = skl_update_scaler(crtc_state, force_detach,
@@ -14552,7 +14552,7 @@ intel_cleanup_plane_fb(struct drm_plane *plane,
 
 int
 skl_max_scale(const struct intel_crtc_state *crtc_state,
-	      u32 pixel_format)
+	      const struct drm_format_info *format)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
@@ -14577,7 +14577,7 @@ skl_max_scale(const struct intel_crtc_state *crtc_state,
 	 *            or
 	 *    cdclk/crtc_clock
 	 */
-	mult = is_planar_yuv_format(pixel_format) ? 2 : 3;
+	mult = drm_format_info_is_yuv_semiplanar(format) ? 2 : 3;
 	tmpclk1 = (1 << 16) * mult - 1;
 	tmpclk2 = (1 << 8) * ((max_dotclk << 8) / crtc_clock);
 	max_scale = min(tmpclk1, tmpclk2);
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index f4ddde171655..66330fcb10d4 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -34,6 +34,7 @@ struct drm_connector;
 struct drm_device;
 struct drm_encoder;
 struct drm_file;
+struct drm_format_info;
 struct drm_framebuffer;
 struct drm_i915_error_state_buf;
 struct drm_i915_gem_object;
@@ -548,7 +549,7 @@ void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 u16 skl_scaler_calc_phase(int sub, int scale, bool chroma_center);
 int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
 int skl_max_scale(const struct intel_crtc_state *crtc_state,
-		  u32 pixel_format);
+		  const struct drm_format_info *format);
 u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state);
 u32 glk_plane_color_ctl_crtc(const struct intel_crtc_state *crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index e415b0ad4a42..7a7078d0ba23 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -48,19 +48,6 @@
 #include "intel_psr.h"
 #include "intel_sprite.h"
 
-bool is_planar_yuv_format(u32 pixelformat)
-{
-	switch (pixelformat) {
-	case DRM_FORMAT_NV12:
-	case DRM_FORMAT_P010:
-	case DRM_FORMAT_P012:
-	case DRM_FORMAT_P016:
-		return true;
-	default:
-		return false;
-	}
-}
-
 int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
 			     int usecs)
 {
@@ -361,6 +348,7 @@ skl_program_scaler(struct intel_plane *plane,
 		   const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
+	const struct drm_framebuffer *fb = plane_state->base.fb;
 	enum pipe pipe = plane->pipe;
 	int scaler_id = plane_state->scaler_id;
 	const struct intel_scaler *scaler =
@@ -381,7 +369,7 @@ skl_program_scaler(struct intel_plane *plane,
 				      0, INT_MAX);
 
 	/* TODO: handle sub-pixel coordinates */
-	if (is_planar_yuv_format(plane_state->base.fb->format->format) &&
+	if (drm_format_info_is_yuv_semiplanar(fb->format) &&
 	    !icl_is_hdr_plane(dev_priv, plane->id)) {
 		y_hphase = skl_scaler_calc_phase(1, hscale, false);
 		y_vphase = skl_scaler_calc_phase(1, vscale, false);
@@ -1790,7 +1778,7 @@ static int skl_plane_check_nv12_rotation(const struct intel_plane_state *plane_s
 	int src_w = drm_rect_width(&plane_state->base.src) >> 16;
 
 	/* Display WA #1106 */
-	if (is_planar_yuv_format(fb->format->format) && src_w & 3 &&
+	if (drm_format_info_is_yuv_semiplanar(fb->format) && src_w & 3 &&
 	    (rotation == DRM_MODE_ROTATE_270 ||
 	     rotation == (DRM_MODE_REFLECT_X | DRM_MODE_ROTATE_90))) {
 		DRM_DEBUG_KMS("src width must be multiple of 4 for rotated planar YUV\n");
@@ -1817,7 +1805,7 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state,
 	/* use scaler when colorkey is not required */
 	if (!plane_state->ckey.flags && intel_fb_scalable(fb)) {
 		min_scale = 1;
-		max_scale = skl_max_scale(crtc_state, fb->format->format);
+		max_scale = skl_max_scale(crtc_state, fb->format);
 	}
 
 	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.h b/drivers/gpu/drm/i915/display/intel_sprite.h
index 093a2d156f1e..229336214f68 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.h
+++ b/drivers/gpu/drm/i915/display/intel_sprite.h
@@ -17,7 +17,6 @@ struct drm_i915_private;
 struct intel_crtc_state;
 struct intel_plane_state;
 
-bool is_planar_yuv_format(u32 pixelformat);
 int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
 			     int usecs);
 struct intel_plane *intel_sprite_plane_create(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index d0ceb272551f..6aa40f546226 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4009,7 +4009,8 @@ skl_ddb_get_hw_plane_state(struct drm_i915_private *dev_priv,
 		val = I915_READ(PLANE_BUF_CFG(pipe, plane_id));
 		val2 = I915_READ(PLANE_NV12_BUF_CFG(pipe, plane_id));
 
-		if (is_planar_yuv_format(fourcc))
+		if (fourcc &&
+		    drm_format_info_is_yuv_semiplanar(drm_format_info(fourcc)))
 			swap(val, val2);
 
 		skl_ddb_entry_init_from_hw(dev_priv, ddb_y, val);
@@ -4197,25 +4198,23 @@ int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
 static u64
 skl_plane_relative_data_rate(const struct intel_crtc_state *crtc_state,
 			     const struct intel_plane_state *plane_state,
-			     const int plane)
+			     int color_plane)
 {
-	struct intel_plane *intel_plane = to_intel_plane(plane_state->base.plane);
+	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	const struct drm_framebuffer *fb = plane_state->base.fb;
 	u32 data_rate;
 	u32 width = 0, height = 0;
-	struct drm_framebuffer *fb;
-	u32 format;
 	uint_fixed_16_16_t down_scale_amount;
 	u64 rate;
 
 	if (!plane_state->base.visible)
 		return 0;
 
-	fb = plane_state->base.fb;
-	format = fb->format->format;
-
-	if (intel_plane->id == PLANE_CURSOR)
+	if (plane->id == PLANE_CURSOR)
 		return 0;
-	if (plane == 1 && !is_planar_yuv_format(format))
+
+	if (color_plane == 1 &&
+	    !drm_format_info_is_yuv_semiplanar(fb->format))
 		return 0;
 
 	/*
@@ -4227,7 +4226,7 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *crtc_state,
 	height = drm_rect_height(&plane_state->base.src) >> 16;
 
 	/* UV plane does 1/2 pixel sub-sampling */
-	if (plane == 1 && is_planar_yuv_format(format)) {
+	if (color_plane == 1) {
 		width /= 2;
 		height /= 2;
 	}
@@ -4238,7 +4237,7 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *crtc_state,
 
 	rate = mul_round_up_u32_fixed16(data_rate, down_scale_amount);
 
-	rate *= fb->format->cpp[plane];
+	rate *= fb->format->cpp[color_plane];
 	return rate;
 }
 
@@ -4643,7 +4642,7 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
 	u32 interm_pbpl;
 
 	/* only planar format has two planes */
-	if (color_plane == 1 && !is_planar_yuv_format(format->format)) {
+	if (color_plane == 1 && !drm_format_info_is_yuv_semiplanar(format)) {
 		DRM_DEBUG_KMS("Non planar format have single plane\n");
 		return -EINVAL;
 	}
@@ -4655,7 +4654,7 @@ skl_compute_wm_params(const struct intel_crtc_state *crtc_state,
 	wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED;
 	wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS ||
 			 modifier == I915_FORMAT_MOD_Yf_TILED_CCS;
-	wp->is_planar = is_planar_yuv_format(format->format);
+	wp->is_planar = drm_format_info_is_yuv_semiplanar(format);
 
 	wp->width = width;
 	if (color_plane == 1 && wp->is_planar)
-- 
cgit v1.2.3


From 76c36a4391641aa37ce7adede32d511a07450d5a Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 13 Sep 2019 22:31:55 +0300
Subject: drm/i915: Allow downscale factor of <3.0 on glk+ for all formats
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Bspec says that glk+ max downscale factor is <3.0 for all pixel formats.
Older platforms had a max of <2.0 for NV12. Update the code to deal with
this.

Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190913193157.9556-3-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 276adc303564..1a72706ebee2 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -14556,7 +14556,7 @@ skl_max_scale(const struct intel_crtc_state *crtc_state,
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	int max_scale, mult;
+	int max_scale;
 	int crtc_clock, max_dotclk, tmpclk1, tmpclk2;
 
 	if (!crtc_state->base.enable)
@@ -14577,8 +14577,11 @@ skl_max_scale(const struct intel_crtc_state *crtc_state,
 	 *            or
 	 *    cdclk/crtc_clock
 	 */
-	mult = drm_format_info_is_yuv_semiplanar(format) ? 2 : 3;
-	tmpclk1 = (1 << 16) * mult - 1;
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv) ||
+	    !drm_format_info_is_yuv_semiplanar(format))
+		tmpclk1 = 0x30000 - 1;
+	else
+		tmpclk1 = 0x20000 - 1;
 	tmpclk2 = (1 << 8) * ((max_dotclk << 8) / crtc_clock);
 	max_scale = min(tmpclk1, tmpclk2);
 
-- 
cgit v1.2.3


From fe4709a8d033975a328a665a627acd35e628117a Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 13 Sep 2019 22:31:56 +0300
Subject: drm/i915: Extract intel_modeset_calc_cdclk()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Exfiltrate the cdclk code from intel_modeset_checks() into
intel_modeset_calc_cdclk().

Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190913193157.9556-4-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_cdclk.c   | 135 ++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/display/intel_cdclk.h   |   6 +-
 drivers/gpu/drm/i915/display/intel_display.c | 123 +-----------------------
 3 files changed, 135 insertions(+), 129 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index ea3f75c72fe8..43564295b864 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -21,6 +21,7 @@
  * DEALINGS IN THE SOFTWARE.
  */
 
+#include "intel_atomic.h"
 #include "intel_cdclk.h"
 #include "intel_display_types.h"
 #include "intel_sideband.h"
@@ -1772,9 +1773,9 @@ bool intel_cdclk_needs_modeset(const struct intel_cdclk_state *a,
  * Returns:
  * True if the CDCLK states require just a cd2x divider update, false if not.
  */
-bool intel_cdclk_needs_cd2x_update(struct drm_i915_private *dev_priv,
-				   const struct intel_cdclk_state *a,
-				   const struct intel_cdclk_state *b)
+static bool intel_cdclk_needs_cd2x_update(struct drm_i915_private *dev_priv,
+					  const struct intel_cdclk_state *a,
+					  const struct intel_cdclk_state *b)
 {
 	/* Older hw doesn't have the capability */
 	if (INTEL_GEN(dev_priv) < 10 && !IS_GEN9_LP(dev_priv))
@@ -1793,8 +1794,8 @@ bool intel_cdclk_needs_cd2x_update(struct drm_i915_private *dev_priv,
  * Returns:
  * True if the CDCLK states don't match, false if they do.
  */
-bool intel_cdclk_changed(const struct intel_cdclk_state *a,
-			 const struct intel_cdclk_state *b)
+static bool intel_cdclk_changed(const struct intel_cdclk_state *a,
+				const struct intel_cdclk_state *b)
 {
 	return intel_cdclk_needs_modeset(a, b) ||
 		a->voltage_level != b->voltage_level;
@@ -2220,6 +2221,130 @@ static int bxt_modeset_calc_cdclk(struct intel_atomic_state *state)
 	return 0;
 }
 
+static int intel_lock_all_pipes(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_crtc *crtc;
+
+	/* Add all pipes to the state */
+	for_each_intel_crtc(&dev_priv->drm, crtc) {
+		struct intel_crtc_state *crtc_state;
+
+		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
+		if (IS_ERR(crtc_state))
+			return PTR_ERR(crtc_state);
+	}
+
+	return 0;
+}
+
+static int intel_modeset_all_pipes(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_crtc *crtc;
+
+	/*
+	 * Add all pipes to the state, and force
+	 * a modeset on all the active ones.
+	 */
+	for_each_intel_crtc(&dev_priv->drm, crtc) {
+		struct intel_crtc_state *crtc_state;
+		int ret;
+
+		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
+		if (IS_ERR(crtc_state))
+			return PTR_ERR(crtc_state);
+
+		if (!crtc_state->base.active ||
+		    drm_atomic_crtc_needs_modeset(&crtc_state->base))
+			continue;
+
+		crtc_state->base.mode_changed = true;
+
+		ret = drm_atomic_add_affected_connectors(&state->base,
+							 &crtc->base);
+		if (ret)
+			return ret;
+
+		ret = drm_atomic_add_affected_planes(&state->base,
+						     &crtc->base);
+		if (ret)
+			return ret;
+
+		crtc_state->update_planes |= crtc_state->active_planes;
+	}
+
+	return 0;
+}
+
+int intel_modeset_calc_cdclk(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	enum pipe pipe;
+	int ret;
+
+	if (!dev_priv->display.modeset_calc_cdclk)
+		return 0;
+
+	ret = dev_priv->display.modeset_calc_cdclk(state);
+	if (ret)
+		return ret;
+
+	/*
+	 * Writes to dev_priv->cdclk.logical must protected by
+	 * holding all the crtc locks, even if we don't end up
+	 * touching the hardware
+	 */
+	if (intel_cdclk_changed(&dev_priv->cdclk.logical,
+				&state->cdclk.logical)) {
+		ret = intel_lock_all_pipes(state);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (is_power_of_2(state->active_pipes)) {
+		struct intel_crtc *crtc;
+		struct intel_crtc_state *crtc_state;
+
+		pipe = ilog2(state->active_pipes);
+		crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
+		crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
+		if (crtc_state &&
+		    drm_atomic_crtc_needs_modeset(&crtc_state->base))
+			pipe = INVALID_PIPE;
+	} else {
+		pipe = INVALID_PIPE;
+	}
+
+	/* All pipes must be switched off while we change the cdclk. */
+	if (pipe != INVALID_PIPE &&
+	    intel_cdclk_needs_cd2x_update(dev_priv,
+					  &dev_priv->cdclk.actual,
+					  &state->cdclk.actual)) {
+		ret = intel_lock_all_pipes(state);
+		if (ret)
+			return ret;
+
+		state->cdclk.pipe = pipe;
+	} else if (intel_cdclk_needs_modeset(&dev_priv->cdclk.actual,
+					     &state->cdclk.actual)) {
+		ret = intel_modeset_all_pipes(state);
+		if (ret)
+			return ret;
+
+		state->cdclk.pipe = INVALID_PIPE;
+	}
+
+	DRM_DEBUG_KMS("New cdclk calculated to be logical %u kHz, actual %u kHz\n",
+		      state->cdclk.logical.cdclk,
+		      state->cdclk.actual.cdclk);
+	DRM_DEBUG_KMS("New voltage level calculated to be logical %u, actual %u\n",
+		      state->cdclk.logical.voltage_level,
+		      state->cdclk.actual.voltage_level);
+
+	return 0;
+}
+
 static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv)
 {
 	int max_cdclk_freq = dev_priv->max_cdclk_freq;
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h
index 1afa84ab6018..cf71394cc79c 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.h
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.h
@@ -29,13 +29,8 @@ void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv);
 void intel_update_max_cdclk(struct drm_i915_private *dev_priv);
 void intel_update_cdclk(struct drm_i915_private *dev_priv);
 void intel_update_rawclk(struct drm_i915_private *dev_priv);
-bool intel_cdclk_needs_cd2x_update(struct drm_i915_private *dev_priv,
-				   const struct intel_cdclk_state *a,
-				   const struct intel_cdclk_state *b);
 bool intel_cdclk_needs_modeset(const struct intel_cdclk_state *a,
 			       const struct intel_cdclk_state *b);
-bool intel_cdclk_changed(const struct intel_cdclk_state *a,
-			 const struct intel_cdclk_state *b);
 void intel_cdclk_swap_state(struct intel_atomic_state *state);
 void
 intel_set_cdclk_pre_plane_update(struct drm_i915_private *dev_priv,
@@ -49,5 +44,6 @@ intel_set_cdclk_post_plane_update(struct drm_i915_private *dev_priv,
 				  enum pipe pipe);
 void intel_dump_cdclk_state(const struct intel_cdclk_state *cdclk_state,
 			    const char *context);
+int intel_modeset_calc_cdclk(struct intel_atomic_state *state);
 
 #endif /* __INTEL_CDCLK_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 1a72706ebee2..befebfd5db66 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -13433,65 +13433,12 @@ static int haswell_mode_set_planes_workaround(struct intel_atomic_state *state)
 	return 0;
 }
 
-static int intel_lock_all_pipes(struct intel_atomic_state *state)
-{
-	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
-	struct intel_crtc *crtc;
-
-	/* Add all pipes to the state */
-	for_each_intel_crtc(&dev_priv->drm, crtc) {
-		struct intel_crtc_state *crtc_state;
-
-		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
-		if (IS_ERR(crtc_state))
-			return PTR_ERR(crtc_state);
-	}
-
-	return 0;
-}
-
-static int intel_modeset_all_pipes(struct intel_atomic_state *state)
-{
-	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
-	struct intel_crtc *crtc;
-
-	/*
-	 * Add all pipes to the state, and force
-	 * a modeset on all the active ones.
-	 */
-	for_each_intel_crtc(&dev_priv->drm, crtc) {
-		struct intel_crtc_state *crtc_state;
-		int ret;
-
-		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
-		if (IS_ERR(crtc_state))
-			return PTR_ERR(crtc_state);
-
-		if (!crtc_state->base.active || needs_modeset(crtc_state))
-			continue;
-
-		crtc_state->base.mode_changed = true;
-
-		ret = drm_atomic_add_affected_connectors(&state->base,
-							 &crtc->base);
-		if (ret)
-			return ret;
-
-		ret = drm_atomic_add_affected_planes(&state->base,
-						     &crtc->base);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
 static int intel_modeset_checks(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	struct intel_crtc_state *old_crtc_state, *new_crtc_state;
 	struct intel_crtc *crtc;
-	int ret = 0, i;
+	int ret, i;
 
 	if (!check_digital_port_conflicts(state)) {
 		DRM_DEBUG_KMS("rejecting conflicting digital port configuration\n");
@@ -13519,71 +13466,9 @@ static int intel_modeset_checks(struct intel_atomic_state *state)
 			state->active_pipe_changes |= BIT(crtc->pipe);
 	}
 
-	/*
-	 * See if the config requires any additional preparation, e.g.
-	 * to adjust global state with pipes off.  We need to do this
-	 * here so we can get the modeset_pipe updated config for the new
-	 * mode set on this crtc.  For other crtcs we need to use the
-	 * adjusted_mode bits in the crtc directly.
-	 */
-	if (dev_priv->display.modeset_calc_cdclk) {
-		enum pipe pipe;
-
-		ret = dev_priv->display.modeset_calc_cdclk(state);
-		if (ret < 0)
-			return ret;
-
-		/*
-		 * Writes to dev_priv->cdclk.logical must protected by
-		 * holding all the crtc locks, even if we don't end up
-		 * touching the hardware
-		 */
-		if (intel_cdclk_changed(&dev_priv->cdclk.logical,
-					&state->cdclk.logical)) {
-			ret = intel_lock_all_pipes(state);
-			if (ret < 0)
-				return ret;
-		}
-
-		if (is_power_of_2(state->active_pipes)) {
-			struct intel_crtc *crtc;
-			struct intel_crtc_state *crtc_state;
-
-			pipe = ilog2(state->active_pipes);
-			crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
-			crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
-			if (crtc_state && needs_modeset(crtc_state))
-				pipe = INVALID_PIPE;
-		} else {
-			pipe = INVALID_PIPE;
-		}
-
-		/* All pipes must be switched off while we change the cdclk. */
-		if (pipe != INVALID_PIPE &&
-		    intel_cdclk_needs_cd2x_update(dev_priv,
-						  &dev_priv->cdclk.actual,
-						  &state->cdclk.actual)) {
-			ret = intel_lock_all_pipes(state);
-			if (ret < 0)
-				return ret;
-
-			state->cdclk.pipe = pipe;
-		} else if (intel_cdclk_needs_modeset(&dev_priv->cdclk.actual,
-						     &state->cdclk.actual)) {
-			ret = intel_modeset_all_pipes(state);
-			if (ret < 0)
-				return ret;
-
-			state->cdclk.pipe = INVALID_PIPE;
-		}
-
-		DRM_DEBUG_KMS("New cdclk calculated to be logical %u kHz, actual %u kHz\n",
-			      state->cdclk.logical.cdclk,
-			      state->cdclk.actual.cdclk);
-		DRM_DEBUG_KMS("New voltage level calculated to be logical %u, actual %u\n",
-			      state->cdclk.logical.voltage_level,
-			      state->cdclk.actual.voltage_level);
-	}
+	ret = intel_modeset_calc_cdclk(state);
+	if (ret)
+		return ret;
 
 	intel_modeset_clear_plls(state);
 
-- 
cgit v1.2.3


From 2e7f76c1e4b6480226cee3f6e358172891012882 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 13 Sep 2019 22:31:57 +0300
Subject: drm/i915: s/pipe_config/crtc_state/ in intel_crtc_atomic_check()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Clean up the mess with the drm vs. intel types in
intel_crtc_atomic_check() and rename varibles accordingly.

Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190913193157.9556-5-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 54 ++++++++++++++--------------
 1 file changed, 26 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index befebfd5db66..12bb8f951edf 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -11760,25 +11760,24 @@ static bool c8_planes_changed(const struct intel_crtc_state *new_crtc_state)
 	return !old_crtc_state->c8_planes != !new_crtc_state->c8_planes;
 }
 
-static int intel_crtc_atomic_check(struct drm_crtc *crtc,
-				   struct drm_crtc_state *crtc_state)
+static int intel_crtc_atomic_check(struct drm_crtc *_crtc,
+				   struct drm_crtc_state *_crtc_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct intel_crtc_state *pipe_config =
-		to_intel_crtc_state(crtc_state);
+	struct intel_crtc *crtc = to_intel_crtc(_crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	struct intel_crtc_state *crtc_state =
+		to_intel_crtc_state(_crtc_state);
 	int ret;
-	bool mode_changed = needs_modeset(pipe_config);
+	bool mode_changed = needs_modeset(crtc_state);
 
 	if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv) &&
-	    mode_changed && !crtc_state->active)
-		pipe_config->update_wm_post = true;
+	    mode_changed && !crtc_state->base.active)
+		crtc_state->update_wm_post = true;
 
-	if (mode_changed && crtc_state->enable &&
+	if (mode_changed && crtc_state->base.enable &&
 	    dev_priv->display.crtc_compute_clock &&
-	    !WARN_ON(pipe_config->shared_dpll)) {
-		ret = dev_priv->display.crtc_compute_clock(intel_crtc,
-							   pipe_config);
+	    !WARN_ON(crtc_state->shared_dpll)) {
+		ret = dev_priv->display.crtc_compute_clock(crtc, crtc_state);
 		if (ret)
 			return ret;
 	}
@@ -11787,19 +11786,19 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc,
 	 * May need to update pipe gamma enable bits
 	 * when C8 planes are getting enabled/disabled.
 	 */
-	if (c8_planes_changed(pipe_config))
-		crtc_state->color_mgmt_changed = true;
+	if (c8_planes_changed(crtc_state))
+		crtc_state->base.color_mgmt_changed = true;
 
-	if (mode_changed || pipe_config->update_pipe ||
-	    crtc_state->color_mgmt_changed) {
-		ret = intel_color_check(pipe_config);
+	if (mode_changed || crtc_state->update_pipe ||
+	    crtc_state->base.color_mgmt_changed) {
+		ret = intel_color_check(crtc_state);
 		if (ret)
 			return ret;
 	}
 
 	ret = 0;
 	if (dev_priv->display.compute_pipe_wm) {
-		ret = dev_priv->display.compute_pipe_wm(pipe_config);
+		ret = dev_priv->display.compute_pipe_wm(crtc_state);
 		if (ret) {
 			DRM_DEBUG_KMS("Target pipe watermarks are invalid\n");
 			return ret;
@@ -11815,7 +11814,7 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc,
 		 * old state and the new state.  We can program these
 		 * immediately.
 		 */
-		ret = dev_priv->display.compute_intermediate_wm(pipe_config);
+		ret = dev_priv->display.compute_intermediate_wm(crtc_state);
 		if (ret) {
 			DRM_DEBUG_KMS("No valid intermediate pipe watermarks are possible\n");
 			return ret;
@@ -11823,21 +11822,20 @@ static int intel_crtc_atomic_check(struct drm_crtc *crtc,
 	}
 
 	if (INTEL_GEN(dev_priv) >= 9) {
-		if (mode_changed || pipe_config->update_pipe)
-			ret = skl_update_scaler_crtc(pipe_config);
+		if (mode_changed || crtc_state->update_pipe)
+			ret = skl_update_scaler_crtc(crtc_state);
 
 		if (!ret)
-			ret = icl_check_nv12_planes(pipe_config);
+			ret = icl_check_nv12_planes(crtc_state);
 		if (!ret)
-			ret = skl_check_pipe_max_pixel_rate(intel_crtc,
-							    pipe_config);
+			ret = skl_check_pipe_max_pixel_rate(crtc, crtc_state);
 		if (!ret)
-			ret = intel_atomic_setup_scalers(dev_priv, intel_crtc,
-							 pipe_config);
+			ret = intel_atomic_setup_scalers(dev_priv, crtc,
+							 crtc_state);
 	}
 
 	if (HAS_IPS(dev_priv))
-		pipe_config->ips_enabled = hsw_compute_ips_config(pipe_config);
+		crtc_state->ips_enabled = hsw_compute_ips_config(crtc_state);
 
 	return ret;
 }
-- 
cgit v1.2.3


From ef404bc6592075925997d3626e968e4bcd59721f Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 16 Sep 2019 12:29:01 +0300
Subject: drm/i915: stop conflating HAS_DISPLAY() and disabled display
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Stop setting ->pipe_mask to zero when display is disabled, allowing us
to have different code paths for not actually having display hardware,
and having display hardware disabled. This lets us develop those two
avenues independently.

There are no functional changes for when there is no display. However,
all uses of for_each_pipe() and for_each_pipe_masked() will start
running for the disabled display case. Put one of the more significant
ones behind checks for INTEL_DISPLAY_ENABLED(), otherwise the cases
should not be hit with disabled display, or they seem benign. Fingers
crossed.

All in all, this might not be the ideal solution. In fact we may have
had something along the lines of this in the past, but we ended up
conflating the two cases. Possibly even by recommendation by yours
truly; I did not dare dig up that part of the history. But the perfect
is the enemy of the good, this is a straightforward change, and lets us
get actual work done in both fronts without interfering with each other.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190916092901.31440-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 12 +++++++-----
 drivers/gpu/drm/i915/intel_device_info.c     |  8 ++------
 2 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 12bb8f951edf..1cc74844d3ea 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -16167,11 +16167,13 @@ int intel_modeset_init(struct drm_device *dev)
 		      INTEL_NUM_PIPES(dev_priv),
 		      INTEL_NUM_PIPES(dev_priv) > 1 ? "s" : "");
 
-	for_each_pipe(dev_priv, pipe) {
-		ret = intel_crtc_init(dev_priv, pipe);
-		if (ret) {
-			drm_mode_config_cleanup(dev);
-			return ret;
+	if (HAS_DISPLAY(dev_priv) && INTEL_DISPLAY_ENABLED(dev_priv)) {
+		for_each_pipe(dev_priv, pipe) {
+			ret = intel_crtc_init(dev_priv, pipe);
+			if (ret) {
+				drm_mode_config_cleanup(dev);
+				return ret;
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 727089dcd280..728c881718a2 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -894,12 +894,8 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 			runtime->num_sprites[pipe] = 1;
 	}
 
-	if (i915_modparams.disable_display) {
-		DRM_INFO("Display disabled (module parameter)\n");
-		info->pipe_mask = 0;
-	} else if (HAS_DISPLAY(dev_priv) &&
-		   (IS_GEN_RANGE(dev_priv, 7, 8)) &&
-		   HAS_PCH_SPLIT(dev_priv)) {
+	if (HAS_DISPLAY(dev_priv) && IS_GEN_RANGE(dev_priv, 7, 8) &&
+	    HAS_PCH_SPLIT(dev_priv)) {
 		u32 fuse_strap = I915_READ(FUSE_STRAP);
 		u32 sfuse_strap = I915_READ(SFUSE_STRAP);
 
-- 
cgit v1.2.3


From bb120e1171a966429287865134265811887daa6c Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sun, 15 Sep 2019 21:37:00 +0100
Subject: drm/i915: Show the logical context ring state on dumping

Include the active context register state when dumping the engine.

Suggested-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190915203701.29163-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index a8014c59b388..3c176b0f4b45 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1404,6 +1404,11 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 			   rq->timeline->hwsp_offset);
 
 		print_request_ring(m, rq);
+
+		if (rq->hw_context->lrc_reg_state) {
+			drm_printf(m, "Logical Ring Context:\n");
+			hexdump(m, rq->hw_context->lrc_reg_state, PAGE_SIZE);
+		}
 	}
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 
-- 
cgit v1.2.3


From 80fa64d62067ea7390cd27d924dcb7c028e455e9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 17 Sep 2019 09:00:29 +0100
Subject: drm/i915: Only apply a rmw mmio update if the value changes

If we try to clear, or even set, a bit in the register that doesn't
change the register state; skip the write. There's a slight danger in
that the register acts as a latch-on-write, but I do not think we use a
rmw cycle with any such latch registers.

Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190917080029.27632-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_uncore.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
index 414fc2cb0459..dcfa243892c6 100644
--- a/drivers/gpu/drm/i915/intel_uncore.h
+++ b/drivers/gpu/drm/i915/intel_uncore.h
@@ -378,23 +378,23 @@ intel_uncore_read64_2x32(struct intel_uncore *uncore,
 static inline void intel_uncore_rmw(struct intel_uncore *uncore,
 				    i915_reg_t reg, u32 clear, u32 set)
 {
-	u32 val;
+	u32 old, val;
 
-	val = intel_uncore_read(uncore, reg);
-	val &= ~clear;
-	val |= set;
-	intel_uncore_write(uncore, reg, val);
+	old = intel_uncore_read(uncore, reg);
+	val = (old & ~clear) | set;
+	if (val != old)
+		intel_uncore_write(uncore, reg, val);
 }
 
 static inline void intel_uncore_rmw_fw(struct intel_uncore *uncore,
 				       i915_reg_t reg, u32 clear, u32 set)
 {
-	u32 val;
+	u32 old, val;
 
-	val = intel_uncore_read_fw(uncore, reg);
-	val &= ~clear;
-	val |= set;
-	intel_uncore_write_fw(uncore, reg, val);
+	old = intel_uncore_read_fw(uncore, reg);
+	val = (old & ~clear) | set;
+	if (val != old)
+		intel_uncore_write_fw(uncore, reg, val);
 }
 
 static inline int intel_uncore_write_and_verify(struct intel_uncore *uncore,
-- 
cgit v1.2.3


From c210e85b8f3371168ce78c8da00b913839a84ec7 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 17 Sep 2019 13:30:55 +0100
Subject: drm/i915/tgl: Extend MI_SEMAPHORE_WAIT

On Tigerlake, MI_SEMAPHORE_WAIT grew an extra dword, so be sure to
update the length field and emit that extra parameter and any padding
noop as required.

v2: Define the token shift while we are adding the updated MI_SEMAPHORE_WAIT
v3: Use int instead of bool in the addition so that readers are not left
wondering about the intricacies of the C spec. Now they just have to
worry what the integer value of a boolean operation is...

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190917123055.28965-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h |  3 ++
 drivers/gpu/drm/i915/gt/intel_lrc.c          | 71 +++++++++++++++++++++++++---
 drivers/gpu/drm/i915/i915_pci.c              |  1 -
 drivers/gpu/drm/i915/i915_request.c          | 21 ++++++--
 4 files changed, 84 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index fbad403ab7ac..f78b13d74e17 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -112,6 +112,7 @@
 #define MI_SEMAPHORE_SIGNAL	MI_INSTR(0x1b, 0) /* GEN8+ */
 #define   MI_SEMAPHORE_TARGET(engine)	((engine)<<15)
 #define MI_SEMAPHORE_WAIT	MI_INSTR(0x1c, 2) /* GEN8+ */
+#define MI_SEMAPHORE_WAIT_TOKEN	MI_INSTR(0x1c, 3) /* GEN12+ */
 #define   MI_SEMAPHORE_POLL		(1 << 15)
 #define   MI_SEMAPHORE_SAD_GT_SDD	(0 << 12)
 #define   MI_SEMAPHORE_SAD_GTE_SDD	(1 << 12)
@@ -119,6 +120,8 @@
 #define   MI_SEMAPHORE_SAD_LTE_SDD	(3 << 12)
 #define   MI_SEMAPHORE_SAD_EQ_SDD	(4 << 12)
 #define   MI_SEMAPHORE_SAD_NEQ_SDD	(5 << 12)
+#define   MI_SEMAPHORE_TOKEN_MASK	REG_GENMASK(9, 5)
+#define   MI_SEMAPHORE_TOKEN_SHIFT	5
 #define MI_STORE_DWORD_IMM	MI_INSTR(0x20, 1)
 #define MI_STORE_DWORD_IMM_GEN4	MI_INSTR(0x20, 2)
 #define   MI_MEM_VIRTUAL	(1 << 22) /* 945,g33,965 */
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index a3f0e4999744..a99166a2d2eb 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2879,6 +2879,22 @@ static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 	return gen8_emit_fini_breadcrumb_footer(request, cs);
 }
 
+static u32 *
+gen11_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
+{
+	cs = gen8_emit_ggtt_write_rcs(cs,
+				      request->fence.seqno,
+				      request->timeline->hwsp_offset,
+				      PIPE_CONTROL_CS_STALL |
+				      PIPE_CONTROL_TILE_CACHE_FLUSH |
+				      PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+				      PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+				      PIPE_CONTROL_DC_FLUSH_ENABLE |
+				      PIPE_CONTROL_FLUSH_ENABLE);
+
+	return gen8_emit_fini_breadcrumb_footer(request, cs);
+}
+
 /*
  * Note that the CS instruction pre-parser will not stall on the breadcrumb
  * flush and will continue pre-fetching the instructions after it before the
@@ -2897,8 +2913,49 @@ static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
  * All the above applies only to the instructions themselves. Non-inline data
  * used by the instructions is not pre-fetched.
  */
-static u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *request,
-					   u32 *cs)
+
+static u32 *gen12_emit_preempt_busywait(struct i915_request *request, u32 *cs)
+{
+	*cs++ = MI_SEMAPHORE_WAIT_TOKEN |
+		MI_SEMAPHORE_GLOBAL_GTT |
+		MI_SEMAPHORE_POLL |
+		MI_SEMAPHORE_SAD_EQ_SDD;
+	*cs++ = 0;
+	*cs++ = intel_hws_preempt_address(request->engine);
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = MI_NOOP;
+
+	return cs;
+}
+
+static __always_inline u32*
+gen12_emit_fini_breadcrumb_footer(struct i915_request *request, u32 *cs)
+{
+	*cs++ = MI_USER_INTERRUPT;
+
+	*cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
+	if (intel_engine_has_semaphores(request->engine))
+		cs = gen12_emit_preempt_busywait(request, cs);
+
+	request->tail = intel_ring_offset(request, cs);
+	assert_ring_tail_valid(request->ring, request->tail);
+
+	return gen8_emit_wa_tail(request, cs);
+}
+
+static u32 *gen12_emit_fini_breadcrumb(struct i915_request *request, u32 *cs)
+{
+	cs = gen8_emit_ggtt_write(cs,
+				  request->fence.seqno,
+				  request->timeline->hwsp_offset,
+				  0);
+
+	return gen12_emit_fini_breadcrumb_footer(request, cs);
+}
+
+static u32 *
+gen12_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 {
 	cs = gen8_emit_ggtt_write_rcs(cs,
 				      request->fence.seqno,
@@ -2910,7 +2967,7 @@ static u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *request,
 				      PIPE_CONTROL_DC_FLUSH_ENABLE |
 				      PIPE_CONTROL_FLUSH_ENABLE);
 
-	return gen8_emit_fini_breadcrumb_footer(request, cs);
+	return gen12_emit_fini_breadcrumb_footer(request, cs);
 }
 
 static void execlists_park(struct intel_engine_cs *engine)
@@ -2939,9 +2996,6 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 			engine->flags |= I915_ENGINE_HAS_PREEMPTION;
 	}
 
-	if (INTEL_GEN(engine->i915) >= 12) /* XXX disabled for debugging */
-		engine->flags &= ~I915_ENGINE_HAS_SEMAPHORES;
-
 	if (engine->class != COPY_ENGINE_CLASS && INTEL_GEN(engine->i915) >= 12)
 		engine->flags |= I915_ENGINE_HAS_RELATIVE_MMIO;
 }
@@ -2971,6 +3025,8 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 	engine->emit_flush = gen8_emit_flush;
 	engine->emit_init_breadcrumb = gen8_emit_init_breadcrumb;
 	engine->emit_fini_breadcrumb = gen8_emit_fini_breadcrumb;
+	if (INTEL_GEN(engine->i915) >= 12)
+		engine->emit_fini_breadcrumb = gen12_emit_fini_breadcrumb;
 
 	engine->set_default_submission = intel_execlists_set_default_submission;
 
@@ -3016,6 +3072,9 @@ static void rcs_submission_override(struct intel_engine_cs *engine)
 {
 	switch (INTEL_GEN(engine->i915)) {
 	case 12:
+		engine->emit_flush = gen11_emit_flush_render;
+		engine->emit_fini_breadcrumb = gen12_emit_fini_breadcrumb_rcs;
+		break;
 	case 11:
 		engine->emit_flush = gen11_emit_flush_render;
 		engine->emit_fini_breadcrumb = gen11_emit_fini_breadcrumb_rcs;
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index e4a26bbd8788..fe6941c8fc99 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -797,7 +797,6 @@ static const struct intel_device_info intel_tigerlake_12_info = {
 	.display.has_modular_fia = 1,
 	.engine_mask =
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2),
-	.has_logical_ring_preemption = false, /* XXX disabled for debugging */
 	.engine_mask = BIT(RCS0), /* XXX reduced for debugging */
 };
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 754a78364a63..3ecf92aa5fc1 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -783,7 +783,9 @@ emit_semaphore_wait(struct i915_request *to,
 		    struct i915_request *from,
 		    gfp_t gfp)
 {
+	const int has_token = INTEL_GEN(to->i915) >= 12;
 	u32 hwsp_offset;
+	int len;
 	u32 *cs;
 	int err;
 
@@ -810,7 +812,11 @@ emit_semaphore_wait(struct i915_request *to,
 	if (err)
 		return err;
 
-	cs = intel_ring_begin(to, 4);
+	len = 4;
+	if (has_token)
+		len += 2;
+
+	cs = intel_ring_begin(to, len);
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
@@ -822,13 +828,18 @@ emit_semaphore_wait(struct i915_request *to,
 	 * (post-wrap) values than they were expecting (and so wait
 	 * forever).
 	 */
-	*cs++ = MI_SEMAPHORE_WAIT |
-		MI_SEMAPHORE_GLOBAL_GTT |
-		MI_SEMAPHORE_POLL |
-		MI_SEMAPHORE_SAD_GTE_SDD;
+	*cs++ = (MI_SEMAPHORE_WAIT |
+		 MI_SEMAPHORE_GLOBAL_GTT |
+		 MI_SEMAPHORE_POLL |
+		 MI_SEMAPHORE_SAD_GTE_SDD) +
+		has_token;
 	*cs++ = from->fence.seqno;
 	*cs++ = hwsp_offset;
 	*cs++ = 0;
+	if (has_token) {
+		*cs++ = 0;
+		*cs++ = MI_NOOP;
+	}
 
 	intel_ring_advance(to, cs);
 	to->sched.semaphores |= from->engine->mask;
-- 
cgit v1.2.3


From 8698ba53cd7173c32320ebbef4d389d41ebb5780 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Mon, 16 Sep 2019 16:32:51 -0700
Subject: drm/i915/cml: Add second PCH ID for CMP

The CMP PCH ID we have in the driver is correct for the CML-U machines we have
in our CI system, but the CML-S and CML-H CI machines appear to use a
different PCH ID, leading our driver to detect no PCH for them.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
References: 729ae330a0f2e2 ("drm/i915/cml: Introduce Comet Lake PCH")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111461
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190916233251.387-1-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/intel_pch.c | 1 +
 drivers/gpu/drm/i915/intel_pch.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c
index fa864d8f2b73..15f8bff141f9 100644
--- a/drivers/gpu/drm/i915/intel_pch.c
+++ b/drivers/gpu/drm/i915/intel_pch.c
@@ -69,6 +69,7 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 		WARN_ON(!IS_CANNONLAKE(dev_priv) && !IS_COFFEELAKE(dev_priv));
 		return PCH_CNP;
 	case INTEL_PCH_CMP_DEVICE_ID_TYPE:
+	case INTEL_PCH_CMP2_DEVICE_ID_TYPE:
 		DRM_DEBUG_KMS("Found Comet Lake PCH (CMP)\n");
 		WARN_ON(!IS_COFFEELAKE(dev_priv));
 		/* CometPoint is CNP Compatible */
diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h
index e6a2d65f19c6..c29c81ec7971 100644
--- a/drivers/gpu/drm/i915/intel_pch.h
+++ b/drivers/gpu/drm/i915/intel_pch.h
@@ -41,6 +41,7 @@ enum intel_pch {
 #define INTEL_PCH_CNP_DEVICE_ID_TYPE		0xA300
 #define INTEL_PCH_CNP_LP_DEVICE_ID_TYPE		0x9D80
 #define INTEL_PCH_CMP_DEVICE_ID_TYPE		0x0280
+#define INTEL_PCH_CMP2_DEVICE_ID_TYPE		0x0680
 #define INTEL_PCH_ICP_DEVICE_ID_TYPE		0x3480
 #define INTEL_PCH_MCC_DEVICE_ID_TYPE		0x4B00
 #define INTEL_PCH_MCC2_DEVICE_ID_TYPE		0x3880
-- 
cgit v1.2.3


From c107d613f9204ff9c7624c229938153d7492c56e Mon Sep 17 00:00:00 2001
From: Zenghui Yu <yuzenghui@huawei.com>
Date: Wed, 18 Sep 2019 06:57:30 +0000
Subject: irqchip/gic-v3: Fix GIC_LINE_NR accessor

As per GIC spec, ITLinesNumber indicates the maximum SPI INTID that
the GIC implementation supports. And the maximum SPI INTID an
implementation might support is 1019 (field value 11111).

max(GICD_TYPER_SPIS(...), 1020) is not what we actually want for
GIC_LINE_NR. Fix it to min(GICD_TYPER_SPIS(...), 1020).

Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/1568789850-14080-1-git-send-email-yuzenghui@huawei.com
---
 drivers/irqchip/irq-gic-v3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 422664ac5f53..1edc99335a94 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -59,7 +59,7 @@ static struct gic_chip_data gic_data __read_mostly;
 static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
 
 #define GIC_ID_NR	(1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer))
-#define GIC_LINE_NR	max(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U)
+#define GIC_LINE_NR	min(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U)
 #define GIC_ESPI_NR	GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer)
 
 /*
-- 
cgit v1.2.3


From 56c05de6bd773b96deca379370965c49042b5fbf Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 17 Sep 2019 20:47:46 +0100
Subject: drm/i915: Extend Haswell GT1 PSMI workaround to all

A few times in CI, we have detected a GPU hang on our Haswell GT2
systems with the characteristic IPEHR of 0x780c0000. When the PSMI w/a
was first introducted, it was applied to all Haswell, but later on we
found an erratum that supposedly restricted the issue to GT1 and so
constrained it only be applied on GT1. That may have been a mistake...

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111692
Fixes: 167bc759e823 ("drm/i915: Restrict PSMI context load w/a to Haswell GT1")
References: 2c550183476d ("drm/i915: Disable PSMI sleep messages on all rings around context switches")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190917194746.26710-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index a73296e6b13d..a25b84b12ef1 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -1574,7 +1574,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 	struct intel_engine_cs *engine = rq->engine;
 	enum intel_engine_id id;
 	const int num_engines =
-		IS_HSW_GT1(i915) ? RUNTIME_INFO(i915)->num_engines - 1 : 0;
+		IS_HASWELL(i915) ? RUNTIME_INFO(i915)->num_engines - 1 : 0;
 	bool force_restore = false;
 	int len;
 	u32 *cs;
-- 
cgit v1.2.3


From bb0fed1c60cccbe4063b455a7228818395dac86e Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sun, 15 Sep 2019 15:17:45 +0100
Subject: irqchip/sifive-plic: Switch to fasteoi flow

The SiFive PLIC interrupt controller seems to have all the HW
features to support the fasteoi flow, but the driver seems to be
stuck in a distant past. Bring it into the 21st century.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: Palmer Dabbelt <palmer@sifive.com> (QEMU Boot)
Tested-by: Darius Rad <darius@bluespec.com> (on 2 HW PLIC implementations)
Tested-by: Paul Walmsley <paul.walmsley@sifive.com> (HiFive Unleashed)
Reviewed-by: Palmer Dabbelt <palmer@sifive.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/8636gxskmj.wl-maz@kernel.org
---
 drivers/irqchip/irq-sifive-plic.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index cf755964f2f8..3e51deedbcc8 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -97,7 +97,7 @@ static inline void plic_irq_toggle(const struct cpumask *mask,
 	}
 }
 
-static void plic_irq_enable(struct irq_data *d)
+static void plic_irq_unmask(struct irq_data *d)
 {
 	unsigned int cpu = cpumask_any_and(irq_data_get_affinity_mask(d),
 					   cpu_online_mask);
@@ -106,7 +106,7 @@ static void plic_irq_enable(struct irq_data *d)
 	plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1);
 }
 
-static void plic_irq_disable(struct irq_data *d)
+static void plic_irq_mask(struct irq_data *d)
 {
 	plic_irq_toggle(cpu_possible_mask, d->hwirq, 0);
 }
@@ -125,10 +125,8 @@ static int plic_set_affinity(struct irq_data *d,
 	if (cpu >= nr_cpu_ids)
 		return -EINVAL;
 
-	if (!irqd_irq_disabled(d)) {
-		plic_irq_toggle(cpu_possible_mask, d->hwirq, 0);
-		plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1);
-	}
+	plic_irq_toggle(cpu_possible_mask, d->hwirq, 0);
+	plic_irq_toggle(cpumask_of(cpu), d->hwirq, 1);
 
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
@@ -136,14 +134,18 @@ static int plic_set_affinity(struct irq_data *d,
 }
 #endif
 
+static void plic_irq_eoi(struct irq_data *d)
+{
+	struct plic_handler *handler = this_cpu_ptr(&plic_handlers);
+
+	writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM);
+}
+
 static struct irq_chip plic_chip = {
 	.name		= "SiFive PLIC",
-	/*
-	 * There is no need to mask/unmask PLIC interrupts.  They are "masked"
-	 * by reading claim and "unmasked" when writing it back.
-	 */
-	.irq_enable	= plic_irq_enable,
-	.irq_disable	= plic_irq_disable,
+	.irq_mask	= plic_irq_mask,
+	.irq_unmask	= plic_irq_unmask,
+	.irq_eoi	= plic_irq_eoi,
 #ifdef CONFIG_SMP
 	.irq_set_affinity = plic_set_affinity,
 #endif
@@ -152,7 +154,7 @@ static struct irq_chip plic_chip = {
 static int plic_irqdomain_map(struct irq_domain *d, unsigned int irq,
 			      irq_hw_number_t hwirq)
 {
-	irq_set_chip_and_handler(irq, &plic_chip, handle_simple_irq);
+	irq_set_chip_and_handler(irq, &plic_chip, handle_fasteoi_irq);
 	irq_set_chip_data(irq, NULL);
 	irq_set_noprobe(irq);
 	return 0;
@@ -188,7 +190,6 @@ static void plic_handle_irq(struct pt_regs *regs)
 					hwirq);
 		else
 			generic_handle_irq(irq);
-		writel(hwirq, claim);
 	}
 	csr_set(sie, SIE_SEIE);
 }
-- 
cgit v1.2.3


From 0d333ac7eb17f0f6c86db66afba70135f11da4a9 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Wed, 18 Sep 2019 18:53:30 -0700
Subject: drm/i915: fix SFC reset flow

Our assumption that the we can ask the HW to lock the SFC even if not
currently in use does not match the HW commitment. The expectation from
the HW is that SW will not try to lock the SFC if the engine is not
using it and if we do that the behavior is undefined; on ICL the HW
ends up to returning the ack and ignoring our lock request, but this is
not guaranteed and we shouldn't expect it going forward.

Also, failing to get the ack while the SFC is in use means that we can't
cleanly reset it, so fail the engine reset in that scenario.

v2: drop rmw change, keep the log as debug and handle failure (Chris),
    improve comments (Tvrtko).

Reported-by: Owen Zhang <owen.zhang@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919015330.15435-1-daniele.ceraolospurio@intel.com
---
 drivers/gpu/drm/i915/gt/intel_reset.c | 50 +++++++++++++++++++++++------------
 1 file changed, 33 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 8327220ac558..89048ca8924c 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -309,7 +309,7 @@ static int gen6_reset_engines(struct intel_gt *gt,
 	return gen6_hw_domain_reset(gt, hw_mask);
 }
 
-static u32 gen11_lock_sfc(struct intel_engine_cs *engine)
+static int gen11_lock_sfc(struct intel_engine_cs *engine, u32 *hw_mask)
 {
 	struct intel_uncore *uncore = engine->uncore;
 	u8 vdbox_sfc_access = RUNTIME_INFO(engine->i915)->vdbox_sfc_access;
@@ -318,6 +318,7 @@ static u32 gen11_lock_sfc(struct intel_engine_cs *engine)
 	i915_reg_t sfc_usage;
 	u32 sfc_usage_bit;
 	u32 sfc_reset_bit;
+	int ret;
 
 	switch (engine->class) {
 	case VIDEO_DECODE_CLASS:
@@ -352,27 +353,33 @@ static u32 gen11_lock_sfc(struct intel_engine_cs *engine)
 	}
 
 	/*
-	 * Tell the engine that a software reset is going to happen. The engine
-	 * will then try to force lock the SFC (if currently locked, it will
-	 * remain so until we tell the engine it is safe to unlock; if currently
-	 * unlocked, it will ignore this and all new lock requests). If SFC
-	 * ends up being locked to the engine we want to reset, we have to reset
-	 * it as well (we will unlock it once the reset sequence is completed).
+	 * If the engine is using a SFC, tell the engine that a software reset
+	 * is going to happen. The engine will then try to force lock the SFC.
+	 * If SFC ends up being locked to the engine we want to reset, we have
+	 * to reset it as well (we will unlock it once the reset sequence is
+	 * completed).
 	 */
+	if (!(intel_uncore_read_fw(uncore, sfc_usage) & sfc_usage_bit))
+		return 0;
+
 	rmw_set_fw(uncore, sfc_forced_lock, sfc_forced_lock_bit);
 
-	if (__intel_wait_for_register_fw(uncore,
-					 sfc_forced_lock_ack,
-					 sfc_forced_lock_ack_bit,
-					 sfc_forced_lock_ack_bit,
-					 1000, 0, NULL)) {
-		DRM_DEBUG_DRIVER("Wait for SFC forced lock ack failed\n");
+	ret = __intel_wait_for_register_fw(uncore,
+					   sfc_forced_lock_ack,
+					   sfc_forced_lock_ack_bit,
+					   sfc_forced_lock_ack_bit,
+					   1000, 0, NULL);
+
+	/* Was the SFC released while we were trying to lock it? */
+	if (!(intel_uncore_read_fw(uncore, sfc_usage) & sfc_usage_bit))
 		return 0;
-	}
 
-	if (intel_uncore_read_fw(uncore, sfc_usage) & sfc_usage_bit)
-		return sfc_reset_bit;
+	if (ret) {
+		DRM_DEBUG_DRIVER("Wait for SFC forced lock ack failed\n");
+		return ret;
+	}
 
+	*hw_mask |= sfc_reset_bit;
 	return 0;
 }
 
@@ -430,12 +437,21 @@ static int gen11_reset_engines(struct intel_gt *gt,
 		for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
 			GEM_BUG_ON(engine->id >= ARRAY_SIZE(hw_engine_mask));
 			hw_mask |= hw_engine_mask[engine->id];
-			hw_mask |= gen11_lock_sfc(engine);
+			ret = gen11_lock_sfc(engine, &hw_mask);
+			if (ret)
+				goto sfc_unlock;
 		}
 	}
 
 	ret = gen6_hw_domain_reset(gt, hw_mask);
 
+sfc_unlock:
+	/*
+	 * We unlock the SFC based on the lock status and not the result of
+	 * gen11_lock_sfc to make sure that we clean properly if something
+	 * wrong happened during the lock (e.g. lock acquired after timeout
+	 * expiration).
+	 */
 	if (engine_mask != ALL_ENGINES)
 		for_each_engine_masked(engine, gt->i915, engine_mask, tmp)
 			gen11_unlock_sfc(engine);
-- 
cgit v1.2.3


From 37fa0de3c137d5f54f7e64f53495c9d501d42a4d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 18 Sep 2019 15:54:50 +0100
Subject: drm/i915: Verify the engine after acquiring the active.lock

When using virtual engines, the rq->engine is not stable until we hold
the engine->active.lock (as the virtual engine may be exchanged with the
sibling). Since commit 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
we may retire a request concurrently with resubmitting it to HW, we need
to be extra careful to verify we are holding the correct lock for the
request's active list. This is similar to the issue we saw with
rescheduling the virtual requests, see sched_lock_engine().

Or else:

<4> [876.736126] list_add corruption. prev->next should be next (ffff8883f931a1f8), but was dead000000000100. (prev=ffff888361ffa610).
<4> [876.736136] WARNING: CPU: 2 PID: 21 at lib/list_debug.c:28 __list_add_valid+0x4d/0x70
<4> [876.736137] Modules linked in: i915(+) amdgpu gpu_sched ttm vgem snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic mei_hdcp x86_pkg_temp_thermal coretemp crct10dif_pclmul crc32_pclmul snd_intel_nhlt snd_hda_codec snd_hwdep snd_hda_core ghash_clmulni_intel e1000e cdc_ether usbnet mii snd_pcm ptp pps_core mei_me mei prime_numbers btusb btrtl btbcm btintel bluetooth ecdh_generic ecc [last unloaded: i915]
<4> [876.736154] CPU: 2 PID: 21 Comm: ksoftirqd/2 Tainted: G     U            5.3.0-CI-CI_DRM_6898+ #1
<4> [876.736156] Hardware name: Intel Corporation Ice Lake Client Platform/IceLake U DDR4 SODIMM PD RVP TLC, BIOS ICLSFWR1.R00.3183.A00.1905020411 05/02/2019
<4> [876.736157] RIP: 0010:__list_add_valid+0x4d/0x70
<4> [876.736159] Code: c3 48 89 d1 48 c7 c7 20 33 0e 82 48 89 c2 e8 4a 4a bc ff 0f 0b 31 c0 c3 48 89 c1 4c 89 c6 48 c7 c7 70 33 0e 82 e8 33 4a bc ff <0f> 0b 31 c0 c3 48 89 f2 4c 89 c1 48 89 fe 48 c7 c7 c0 33 0e 82 e8
<4> [876.736160] RSP: 0018:ffffc9000018bd30 EFLAGS: 00010082
<4> [876.736162] RAX: 0000000000000000 RBX: ffff888361ffc840 RCX: 0000000000000104
<4> [876.736163] RDX: 0000000080000104 RSI: 0000000000000000 RDI: 00000000ffffffff
<4> [876.736164] RBP: ffffc9000018bd68 R08: 0000000000000000 R09: 0000000000000001
<4> [876.736165] R10: 00000000aed95de3 R11: 000000007fe927eb R12: ffff888361ffca10
<4> [876.736166] R13: ffff888361ffa610 R14: ffff888361ffc880 R15: ffff8883f931a1f8
<4> [876.736168] FS:  0000000000000000(0000) GS:ffff88849fd00000(0000) knlGS:0000000000000000
<4> [876.736169] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
<4> [876.736170] CR2: 00007f093a9173c0 CR3: 00000003bba08005 CR4: 0000000000760ee0
<4> [876.736171] PKRU: 55555554
<4> [876.736172] Call Trace:
<4> [876.736226]  __i915_request_submit+0x152/0x370 [i915]
<4> [876.736263]  __execlists_submission_tasklet+0x6da/0x1f50 [i915]
<4> [876.736293]  ? execlists_submission_tasklet+0x29/0x50 [i915]
<4> [876.736321]  execlists_submission_tasklet+0x34/0x50 [i915]
<4> [876.736325]  tasklet_action_common.isra.5+0x47/0xb0
<4> [876.736328]  __do_softirq+0xd8/0x4ae
<4> [876.736332]  ? smpboot_thread_fn+0x23/0x280
<4> [876.736334]  ? smpboot_thread_fn+0x6b/0x280
<4> [876.736336]  run_ksoftirqd+0x2b/0x50
<4> [876.736338]  smpboot_thread_fn+0x1d3/0x280
<4> [876.736341]  ? sort_range+0x20/0x20
<4> [876.736343]  kthread+0x119/0x130
<4> [876.736345]  ? kthread_park+0xa0/0xa0
<4> [876.736347]  ret_from_fork+0x24/0x50
<4> [876.736353] irq event stamp: 2290145
<4> [876.736356] hardirqs last  enabled at (2290144): [<ffffffff8123cde8>] __slab_free+0x3e8/0x500
<4> [876.736358] hardirqs last disabled at (2290145): [<ffffffff819cfb4d>] _raw_spin_lock_irqsave+0xd/0x50
<4> [876.736360] softirqs last  enabled at (2290114): [<ffffffff81c0033e>] __do_softirq+0x33e/0x4ae
<4> [876.736361] softirqs last disabled at (2290119): [<ffffffff810b815b>] run_ksoftirqd+0x2b/0x50
<4> [876.736363] WARNING: CPU: 2 PID: 21 at lib/list_debug.c:28 __list_add_valid+0x4d/0x70
<4> [876.736364] ---[ end trace 3e58d6c7356c65bf ]---
<4> [876.736406] ------------[ cut here ]------------
<4> [876.736415] list_del corruption. prev->next should be ffff888361ffca10, but was ffff88840ac2c730
<4> [876.736421] WARNING: CPU: 2 PID: 5490 at lib/list_debug.c:53 __list_del_entry_valid+0x79/0x90
<4> [876.736422] Modules linked in: i915(+) amdgpu gpu_sched ttm vgem snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic mei_hdcp x86_pkg_temp_thermal coretemp crct10dif_pclmul crc32_pclmul snd_intel_nhlt snd_hda_codec snd_hwdep snd_hda_core ghash_clmulni_intel e1000e cdc_ether usbnet mii snd_pcm ptp pps_core mei_me mei prime_numbers btusb btrtl btbcm btintel bluetooth ecdh_generic ecc [last unloaded: i915]
<4> [876.736433] CPU: 2 PID: 5490 Comm: i915_selftest Tainted: G     U  W         5.3.0-CI-CI_DRM_6898+ #1
<4> [876.736435] Hardware name: Intel Corporation Ice Lake Client Platform/IceLake U DDR4 SODIMM PD RVP TLC, BIOS ICLSFWR1.R00.3183.A00.1905020411 05/02/2019
<4> [876.736436] RIP: 0010:__list_del_entry_valid+0x79/0x90
<4> [876.736438] Code: 0b 31 c0 c3 48 89 fe 48 c7 c7 30 34 0e 82 e8 ae 49 bc ff 0f 0b 31 c0 c3 48 89 f2 48 89 fe 48 c7 c7 68 34 0e 82 e8 97 49 bc ff <0f> 0b 31 c0 c3 48 c7 c7 a8 34 0e 82 e8 86 49 bc ff 0f 0b 31 c0 c3
<4> [876.736439] RSP: 0018:ffffc900003ef758 EFLAGS: 00010086
<4> [876.736440] RAX: 0000000000000000 RBX: ffff888361ffc840 RCX: 0000000000000002
<4> [876.736442] RDX: 0000000080000002 RSI: 0000000000000000 RDI: 00000000ffffffff
<4> [876.736443] RBP: ffffc900003ef780 R08: 0000000000000000 R09: 0000000000000001
<4> [876.736444] R10: 000000001418e4b7 R11: 000000007f0ea93b R12: ffff888361ffcab8
<4> [876.736445] R13: ffff88843b6d0000 R14: 000000000000217c R15: 0000000000000001
<4> [876.736447] FS:  00007f4e6f255240(0000) GS:ffff88849fd00000(0000) knlGS:0000000000000000
<4> [876.736448] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
<4> [876.736449] CR2: 00007f093a9173c0 CR3: 00000003bba08005 CR4: 0000000000760ee0
<4> [876.736450] PKRU: 55555554
<4> [876.736451] Call Trace:
<4> [876.736488]  i915_request_retire+0x224/0x8e0 [i915]
<4> [876.736521]  i915_request_create+0x4b/0x1b0 [i915]
<4> [876.736550]  nop_virtual_engine+0x230/0x4d0 [i915]

Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111695
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190918145453.8800-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_request.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 3ecf92aa5fc1..606acde47fa0 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -195,6 +195,27 @@ static void free_capture_list(struct i915_request *request)
 	}
 }
 
+static void remove_from_engine(struct i915_request *rq)
+{
+	struct intel_engine_cs *engine, *locked;
+
+	/*
+	 * Virtual engines complicate acquiring the engine timeline lock,
+	 * as their rq->engine pointer is not stable until under that
+	 * engine lock. The simple ploy we use is to take the lock then
+	 * check that the rq still belongs to the newly locked engine.
+	 */
+	locked = READ_ONCE(rq->engine);
+	spin_lock(&locked->active.lock);
+	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
+		spin_unlock(&locked->active.lock);
+		spin_lock(&engine->active.lock);
+		locked = engine;
+	}
+	list_del(&rq->sched.link);
+	spin_unlock(&locked->active.lock);
+}
+
 static bool i915_request_retire(struct i915_request *rq)
 {
 	struct i915_active_request *active, *next;
@@ -260,9 +281,7 @@ static bool i915_request_retire(struct i915_request *rq)
 	 * request that we have removed from the HW and put back on a run
 	 * queue.
 	 */
-	spin_lock(&rq->engine->active.lock);
-	list_del(&rq->sched.link);
-	spin_unlock(&rq->engine->active.lock);
+	remove_from_engine(rq);
 
 	spin_lock(&rq->lock);
 	i915_request_mark_complete(rq);
-- 
cgit v1.2.3


From 7fd25e6fc035f4b04b75bca6d7e8daa069603a76 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 19 Sep 2019 14:12:34 +0200
Subject: ieee802154: atusb: fix use-after-free at disconnect

The disconnect callback was accessing the hardware-descriptor private
data after having having freed it.

Fixes: 7490b008d123 ("ieee802154: add support for atusb transceiver")
Cc: stable <stable@vger.kernel.org>     # 4.2
Cc: Alexander Aring <alex.aring@gmail.com>
Reported-by: syzbot+f4509a9138a1472e7e80@syzkaller.appspotmail.com
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 drivers/net/ieee802154/atusb.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c
index ceddb424f887..0dd0ba915ab9 100644
--- a/drivers/net/ieee802154/atusb.c
+++ b/drivers/net/ieee802154/atusb.c
@@ -1137,10 +1137,11 @@ static void atusb_disconnect(struct usb_interface *interface)
 
 	ieee802154_unregister_hw(atusb->hw);
 
+	usb_put_dev(atusb->usb_dev);
+
 	ieee802154_free_hw(atusb->hw);
 
 	usb_set_intfdata(interface, NULL);
-	usb_put_dev(atusb->usb_dev);
 
 	pr_debug("%s done\n", __func__);
 }
-- 
cgit v1.2.3


From a47e788c2310a59b8e42e0bfc18d810118dff7bf Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 19 Sep 2019 14:14:14 +0100
Subject: drm/i915/selftests: Exercise CS TLB invalidation

Check that we are correctly invalidating the TLB at the start of a
batch after updating the GTT.

v2: Comments and hold the request reference while spinning

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919131414.7495-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 308 ++++++++++++++++++++++++++
 1 file changed, 308 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 598c18d10640..0d40e0b42923 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -25,13 +25,16 @@
 #include <linux/list_sort.h>
 #include <linux/prime_numbers.h>
 
+#include "gem/i915_gem_context.h"
 #include "gem/selftests/mock_context.h"
+#include "gt/intel_context.h"
 
 #include "i915_random.h"
 #include "i915_selftest.h"
 
 #include "mock_drm.h"
 #include "mock_gem_device.h"
+#include "igt_flush_test.h"
 
 static void cleanup_freed_objects(struct drm_i915_private *i915)
 {
@@ -1705,6 +1708,310 @@ out_put:
 	return err;
 }
 
+static int context_sync(struct intel_context *ce)
+{
+	struct i915_request *rq;
+	long timeout;
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+
+	timeout = i915_request_wait(rq, 0, HZ / 5);
+	i915_request_put(rq);
+
+	return timeout < 0 ? -EIO : 0;
+}
+
+static struct i915_request *
+submit_batch(struct intel_context *ce, u64 addr)
+{
+	struct i915_request *rq;
+	int err;
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq))
+		return rq;
+
+	err = 0;
+	if (rq->engine->emit_init_breadcrumb) /* detect a hang */
+		err = rq->engine->emit_init_breadcrumb(rq);
+	if (err == 0)
+		err = rq->engine->emit_bb_start(rq, addr, 0, 0);
+
+	if (err == 0)
+		i915_request_get(rq);
+	i915_request_add(rq);
+
+	return err ? ERR_PTR(err) : rq;
+}
+
+static u32 *spinner(u32 *batch, int i)
+{
+	return batch + i * 64 / sizeof(*batch) + 4;
+}
+
+static void end_spin(u32 *batch, int i)
+{
+	*spinner(batch, i) = MI_BATCH_BUFFER_END;
+	wmb();
+}
+
+static int igt_cs_tlb(void *arg)
+{
+	const unsigned int count = PAGE_SIZE / 64;
+	const unsigned int chunk_size = count * PAGE_SIZE;
+	struct drm_i915_private *i915 = arg;
+	struct drm_i915_gem_object *bbe, *act, *out;
+	struct i915_gem_engines_iter it;
+	struct i915_address_space *vm;
+	struct i915_gem_context *ctx;
+	struct intel_context *ce;
+	struct drm_file *file;
+	struct i915_vma *vma;
+	unsigned int i;
+	u32 *result;
+	u32 *batch;
+	int err = 0;
+
+	/*
+	 * Our mission here is to fool the hardware to execute something
+	 * from scratch as it has not seen the batch move (due to missing
+	 * the TLB invalidate).
+	 */
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	mutex_lock(&i915->drm.struct_mutex);
+	ctx = live_context(i915, file);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out_unlock;
+	}
+
+	vm = ctx->vm;
+	if (!vm)
+		goto out_unlock;
+
+	/* Create two pages; dummy we prefill the TLB, and intended */
+	bbe = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(bbe)) {
+		err = PTR_ERR(bbe);
+		goto out_unlock;
+	}
+
+	batch = i915_gem_object_pin_map(bbe, I915_MAP_WC);
+	if (IS_ERR(batch)) {
+		err = PTR_ERR(batch);
+		goto out_put_bbe;
+	}
+	memset32(batch, MI_BATCH_BUFFER_END, PAGE_SIZE / sizeof(u32));
+	i915_gem_object_flush_map(bbe);
+	i915_gem_object_unpin_map(bbe);
+
+	act = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(act)) {
+		err = PTR_ERR(act);
+		goto out_put_bbe;
+	}
+
+	/* Track the execution of each request by writing into different slot */
+	batch = i915_gem_object_pin_map(act, I915_MAP_WC);
+	if (IS_ERR(batch)) {
+		err = PTR_ERR(batch);
+		goto out_put_act;
+	}
+	for (i = 0; i < count; i++) {
+		u32 *cs = batch + i * 64 / sizeof(*cs);
+		u64 addr = (vm->total - PAGE_SIZE) + i * sizeof(u32);
+
+		GEM_BUG_ON(INTEL_GEN(i915) < 6);
+		cs[0] = MI_STORE_DWORD_IMM_GEN4;
+		if (INTEL_GEN(i915) >= 8) {
+			cs[1] = lower_32_bits(addr);
+			cs[2] = upper_32_bits(addr);
+			cs[3] = i;
+			cs[4] = MI_NOOP;
+			cs[5] = MI_BATCH_BUFFER_START_GEN8;
+		} else {
+			cs[1] = 0;
+			cs[2] = lower_32_bits(addr);
+			cs[3] = i;
+			cs[4] = MI_NOOP;
+			cs[5] = MI_BATCH_BUFFER_START;
+		}
+	}
+
+	out = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(out)) {
+		err = PTR_ERR(out);
+		goto out_put_batch;
+	}
+	i915_gem_object_set_cache_coherency(out, I915_CACHING_CACHED);
+
+	vma = i915_vma_instance(out, vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto out_put_batch;
+	}
+
+	err = i915_vma_pin(vma, 0, 0,
+			   PIN_USER |
+			   PIN_OFFSET_FIXED |
+			   (vm->total - PAGE_SIZE));
+	if (err)
+		goto out_put_out;
+	GEM_BUG_ON(vma->node.start != vm->total - PAGE_SIZE);
+
+	result = i915_gem_object_pin_map(out, I915_MAP_WB);
+	if (IS_ERR(result)) {
+		err = PTR_ERR(result);
+		goto out_put_out;
+	}
+
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+		IGT_TIMEOUT(end_time);
+		unsigned long pass = 0;
+
+		if (!intel_engine_can_store_dword(ce->engine))
+			continue;
+
+		while (!__igt_timeout(end_time, NULL)) {
+			struct i915_request *rq;
+			u64 offset;
+
+			offset = random_offset(0, vm->total - PAGE_SIZE,
+					       chunk_size, PAGE_SIZE);
+
+			err = vm->allocate_va_range(vm, offset, chunk_size);
+			if (err)
+				goto end;
+
+			memset32(result, STACK_MAGIC, PAGE_SIZE / sizeof(u32));
+
+			vma = i915_vma_instance(bbe, vm, NULL);
+			if (IS_ERR(vma)) {
+				err = PTR_ERR(vma);
+				goto end;
+			}
+
+			err = vma->ops->set_pages(vma);
+			if (err)
+				goto end;
+
+			/* Prime the TLB with the dummy pages */
+			for (i = 0; i < count; i++) {
+				vma->node.start = offset + i * PAGE_SIZE;
+				vm->insert_entries(vm, vma, I915_CACHE_NONE, 0);
+
+				rq = submit_batch(ce, vma->node.start);
+				if (IS_ERR(rq)) {
+					err = PTR_ERR(rq);
+					goto end;
+				}
+				i915_request_put(rq);
+			}
+
+			vma->ops->clear_pages(vma);
+
+			err = context_sync(ce);
+			if (err) {
+				pr_err("%s: dummy setup timed out\n",
+				       ce->engine->name);
+				goto end;
+			}
+
+			vma = i915_vma_instance(act, vm, NULL);
+			if (IS_ERR(vma)) {
+				err = PTR_ERR(vma);
+				goto end;
+			}
+
+			err = vma->ops->set_pages(vma);
+			if (err)
+				goto end;
+
+			/* Replace the TLB with target batches */
+			for (i = 0; i < count; i++) {
+				struct i915_request *rq;
+				u32 *cs = batch + i * 64 / sizeof(*cs);
+				u64 addr;
+
+				vma->node.start = offset + i * PAGE_SIZE;
+				vm->insert_entries(vm, vma, I915_CACHE_NONE, 0);
+
+				addr = vma->node.start + i * 64;
+				cs[4] = MI_NOOP;
+				cs[6] = lower_32_bits(addr);
+				cs[7] = upper_32_bits(addr);
+				wmb();
+
+				rq = submit_batch(ce, addr);
+				if (IS_ERR(rq)) {
+					err = PTR_ERR(rq);
+					goto end;
+				}
+
+				/* Wait until the context chain has started */
+				if (i == 0) {
+					while (READ_ONCE(result[i]) &&
+					       !i915_request_completed(rq))
+						cond_resched();
+				} else {
+					end_spin(batch, i - 1);
+				}
+
+				i915_request_put(rq);
+			}
+			end_spin(batch, count - 1);
+
+			vma->ops->clear_pages(vma);
+
+			err = context_sync(ce);
+			if (err) {
+				pr_err("%s: writes timed out\n",
+				       ce->engine->name);
+				goto end;
+			}
+
+			for (i = 0; i < count; i++) {
+				if (result[i] != i) {
+					pr_err("%s: Write lost on pass %lu, at offset %llx, index %d, found %x, expected %x\n",
+					       ce->engine->name, pass,
+					       offset, i, result[i], i);
+					err = -EINVAL;
+					goto end;
+				}
+			}
+
+			vm->clear_range(vm, offset, chunk_size);
+			pass++;
+		}
+	}
+end:
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		err = -EIO;
+	i915_gem_context_unlock_engines(ctx);
+	i915_gem_object_unpin_map(out);
+out_put_out:
+	i915_gem_object_put(out);
+out_put_batch:
+	i915_gem_object_unpin_map(act);
+out_put_act:
+	i915_gem_object_put(act);
+out_put_bbe:
+	i915_gem_object_put(bbe);
+out_unlock:
+	mutex_unlock(&i915->drm.struct_mutex);
+	mock_file_free(i915, file);
+	return err;
+}
+
 int i915_gem_gtt_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
@@ -1722,6 +2029,7 @@ int i915_gem_gtt_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_ggtt_pot),
 		SUBTEST(igt_ggtt_fill),
 		SUBTEST(igt_ggtt_page),
+		SUBTEST(igt_cs_tlb),
 	};
 
 	GEM_BUG_ON(offset_in_page(i915->ggtt.vm.total));
-- 
cgit v1.2.3


From b01a3ef34816461c31711e5559663e453cb83aba Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Wed, 18 Sep 2019 16:56:25 -0700
Subject: drm/i915: Future-proof DDC pin mapping
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We generally assume future platforms will inherit the behavior of the
most recent platforms, so update our DDC pin mapping defaults to match
how ICP/TGP behave (i.e., pins starting from GMBUS_PIN_1_BXT for combo
PHY's and pins starting from GMBUS_PIN_9_TC1_ICP for TC PHY's).  MCC's
non-standard handling of combo PHY C seems like a platform-specific
quirk that is unlikely to be duplicated on future platforms, so continue
handling it as a special case.

Without this change, future platforms would default to gen4-style pin
mapping which is almost certainly not what we'll want.

Cc: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190918235626.3750-1-matthew.d.roper@intel.com
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/display/intel_hdmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 640254feef27..f81541cff5df 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -3028,7 +3028,7 @@ static u8 intel_hdmi_ddc_pin(struct drm_i915_private *dev_priv,
 
 	if (HAS_PCH_MCC(dev_priv))
 		ddc_pin = mcc_port_to_ddc_pin(dev_priv, port);
-	else if (HAS_PCH_TGP(dev_priv) || HAS_PCH_ICP(dev_priv))
+	else if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP)
 		ddc_pin = icl_port_to_ddc_pin(dev_priv, port);
 	else if (HAS_PCH_CNP(dev_priv))
 		ddc_pin = cnp_port_to_ddc_pin(dev_priv, port);
-- 
cgit v1.2.3


From d09ad3e7af3ab230323c2c00e190f801feb3a343 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Wed, 18 Sep 2019 16:56:26 -0700
Subject: drm/i915: Unify ICP and MCC hotplug pin tables
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The MCC hpd table is just a subset of the ICP table; we can eliminate it
and use the ICP table everywhere.  The extra pins in the table won't be
a problem for MCC since we still supply an appropriate hotplug trigger
mask anywhere the pin table is used.

Cc: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190918235626.3750-2-matthew.d.roper@intel.com
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index ae7228032d2c..bc83f094065a 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -157,12 +157,6 @@ static const u32 hpd_icp[HPD_NUM_PINS] = {
 	[HPD_PORT_F] = SDE_TC_HOTPLUG_ICP(PORT_TC4),
 };
 
-static const u32 hpd_mcc[HPD_NUM_PINS] = {
-	[HPD_PORT_A] = SDE_DDI_HOTPLUG_ICP(PORT_A),
-	[HPD_PORT_B] = SDE_DDI_HOTPLUG_ICP(PORT_B),
-	[HPD_PORT_C] = SDE_TC_HOTPLUG_ICP(PORT_TC1),
-};
-
 static const u32 hpd_tgp[HPD_NUM_PINS] = {
 	[HPD_PORT_A] = SDE_DDI_HOTPLUG_ICP(PORT_A),
 	[HPD_PORT_B] = SDE_DDI_HOTPLUG_ICP(PORT_B),
@@ -2258,7 +2252,7 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 	} else if (HAS_PCH_MCC(dev_priv)) {
 		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_TGP;
 		tc_hotplug_trigger = 0;
-		pins = hpd_mcc;
+		pins = hpd_icp;
 	} else {
 		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP;
 		tc_hotplug_trigger = pch_iir & SDE_TC_MASK_ICP;
@@ -3434,7 +3428,7 @@ static void mcc_hpd_irq_setup(struct drm_i915_private *dev_priv)
 	icp_hpd_irq_setup(dev_priv,
 			  SDE_DDI_MASK_TGP, 0,
 			  TGP_DDI_HPD_ENABLE_MASK, 0,
-			  hpd_mcc);
+			  hpd_icp);
 }
 
 static void gen11_hpd_detection_setup(struct drm_i915_private *dev_priv)
-- 
cgit v1.2.3


From 1c757497096f55d2e037462bfcdfed50877b4cf5 Mon Sep 17 00:00:00 2001
From: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Date: Mon, 9 Sep 2019 16:14:45 -0700
Subject: drm/i915/tgl: Implement Wa_1409142259

Disable CPS aware color pipe by setting chicken bit.

BSpec: 52890
HSDES: 1409142259

v2: Move WA to ctx WA's(Daniele)

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190909231445.23815-1-radhakrishna.sripada@intel.com
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 3 +++
 drivers/gpu/drm/i915/i915_reg.h             | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 41d0f786e06d..ba65e5018978 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -567,6 +567,9 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
+	/* Wa_1409142259 */
+	WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
+			  GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
 }
 
 static void
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index bf37ecebc82f..f8f52ae6cc6f 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7672,6 +7672,7 @@ enum {
 
 #define GEN11_COMMON_SLICE_CHICKEN3		_MMIO(0x7304)
   #define GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC	(1 << 11)
+  #define GEN12_DISABLE_CPS_AWARE_COLOR_PIPE	(1 << 9)
 
 #define HIZ_CHICKEN					_MMIO(0x7018)
 # define CHV_HZ_8X8_MODE_IN_1X				(1 << 15)
-- 
cgit v1.2.3


From 7f0cc34b5349cfb2867358737b3338cb2fcbc354 Mon Sep 17 00:00:00 2001
From: Michel Thierry <michel.thierry@intel.com>
Date: Thu, 25 Jul 2019 17:02:26 -0700
Subject: drm/i915/tgl: Implement Wa_1406941453

Enable Small PL for power benefit.

Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190713010940.17711-18-lucas.demarchi@intel.com
Link: https://patchwork.freedesktop.org/patch/msgid/20190726000226.26914-4-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 7 +++++++
 drivers/gpu/drm/i915/i915_reg.h             | 3 +++
 2 files changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index ba65e5018978..25ae60846398 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1260,6 +1260,13 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 {
 	struct drm_i915_private *i915 = engine->i915;
 
+	if (IS_GEN(i915, 12)) {
+		/* Wa_1406941453:tgl */
+		wa_masked_en(wal,
+			     SAMPLER_MODE,
+			     SAMPLER_ENABLE_SMALL_PL);
+	}
+
 	if (IS_GEN(i915, 11)) {
 		/* This is not an Wa. Enable for better image quality */
 		wa_masked_en(wal,
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f8f52ae6cc6f..5e3a6178aff4 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -8965,6 +8965,9 @@ enum {
 #define   GEN9_DG_MIRROR_FIX_ENABLE	(1 << 5)
 #define   GEN9_CCS_TLB_PREFETCH_ENABLE	(1 << 3)
 
+#define SAMPLER_MODE			_MMIO(0xe18c)
+#define   SAMPLER_ENABLE_SMALL_PL	(1 << 15)
+
 #define GEN8_ROW_CHICKEN		_MMIO(0xe4f0)
 #define   FLOW_CONTROL_ENABLE		(1 << 15)
 #define   PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE	(1 << 8)
-- 
cgit v1.2.3


From bed34ef544f9ab37ab349c04cf4142282c4dcf5d Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Sep 2019 16:50:43 +0300
Subject: drm/i915: Bump skl+ max plane width to 5k for linear/x-tiled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The officially validated plane width limit is 4k on skl+, however
we already had people using 5k displays before we started to enforce
the limit. Also it seems Windows allows 5k resolutions as well
(though not sure if they do it with one plane or two).

According to hw folks 5k should work with the possible
exception of the following features:
- Ytile (already limited to 4k)
- FP16 (already limited to 4k)
- render compression (already limited to 4k)
- KVMR sprite and cursor (don't care)
- horizontal panning (need to verify this)
- pipe and plane scaling (need to verify this)

So apart from last two items on that list we are already
fine. We should really verify what happens with those last
two items but I don't have a 5k display on hand atm so it'll
have to wait.

In the meantime let's just bump the limit back up to 5k since
several users have already been using it without apparent issues.
At least we'll be no worse off than we were prior to lowering
the limits.

Cc: stable@vger.kernel.org
Cc: Sean Paul <sean@poorly.run>
Cc: José Roberto de Souza <jose.souza@intel.com>
Tested-by: Leho Kraav <leho@kraav.com>
Fixes: 372b9ffb5799 ("drm/i915: Fix skl+ max plane width")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111501
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190905135044.2001-1-ville.syrjala@linux.intel.com
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Sean Paul <sean@poorly.run>
---
 drivers/gpu/drm/i915/display/intel_display.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 1cc74844d3ea..a61f4dfbf540 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3282,7 +3282,20 @@ static int skl_max_plane_width(const struct drm_framebuffer *fb,
 	switch (fb->modifier) {
 	case DRM_FORMAT_MOD_LINEAR:
 	case I915_FORMAT_MOD_X_TILED:
-		return 4096;
+		/*
+		 * Validated limit is 4k, but has 5k should
+		 * work apart from the following features:
+		 * - Ytile (already limited to 4k)
+		 * - FP16 (already limited to 4k)
+		 * - render compression (already limited to 4k)
+		 * - KVMR sprite and cursor (don't care)
+		 * - horizontal panning (TODO verify this)
+		 * - pipe and plane scaling (TODO verify this)
+		 */
+		if (cpp == 8)
+			return 4096;
+		else
+			return 5120;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
 		/* FIXME AUX plane? */
-- 
cgit v1.2.3


From 2d20411e25a3bf3d2914a2219f47ed48dc57aed5 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 18 Sep 2019 18:07:07 +0300
Subject: drm/i915: Don't advertise modes that exceed the max plane size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Modern platforms allow the transcoders hdisplay/vdisplay to exceed the
planes' max resolution. This has the nasty implication that modes on the
connectors' mode list may not be usable when the user asks for a
fullscreen plane. Seeing as that is the most common use case it seems
prudent to filter out modes that don't allow for fullscreen planes to
be enabled.

Let's do that in the connetor .mode_valid() hook so that normally
such modes are kept hidden but the user is still able to forcibly
specify such a mode if they know they don't need fullscreen planes.

This is in line with ealier policies regarding certain clock limits.
The idea is to prevent the casual user from encountering a mode that
would fail under typical conditions, but allow the expert user to
force things if they so wish.

Maybe in the future we should consider automagically using two
planes when one can't cover the entire screen? Wouldn't be a
great match for the current uapi with explicit planes though,
but I guess no worse than using two pipes (which we apparently
have to in the future anyway). Either that or we'd have to
teach userspace to do it for us.

v2: Fix icl+ max plane heigth (Manasi)

Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Leho Kraav <leho@kraav.com>
Cc: Sean Paul <sean@poorly.run>
Cc: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190918150707.32420-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 36 ++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_display.h |  4 ++++
 drivers/gpu/drm/i915/display/intel_dp.c      |  2 +-
 drivers/gpu/drm/i915/display/intel_dsi.c     |  3 ++-
 drivers/gpu/drm/i915/display/intel_hdmi.c    |  4 +++-
 5 files changed, 46 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index a61f4dfbf540..e0033d99f6e3 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -15753,6 +15753,7 @@ intel_mode_valid(struct drm_device *dev,
 			   DRM_MODE_FLAG_CLKDIV2))
 		return MODE_BAD;
 
+	/* Transcoder timing limits */
 	if (INTEL_GEN(dev_priv) >= 11) {
 		hdisplay_max = 16384;
 		vdisplay_max = 8192;
@@ -15791,6 +15792,41 @@ intel_mode_valid(struct drm_device *dev,
 	return MODE_OK;
 }
 
+enum drm_mode_status
+intel_mode_valid_max_plane_size(struct drm_i915_private *dev_priv,
+				const struct drm_display_mode *mode)
+{
+	int plane_width_max, plane_height_max;
+
+	/*
+	 * intel_mode_valid() should be
+	 * sufficient on older platforms.
+	 */
+	if (INTEL_GEN(dev_priv) < 9)
+		return MODE_OK;
+
+	/*
+	 * Most people will probably want a fullscreen
+	 * plane so let's not advertize modes that are
+	 * too big for that.
+	 */
+	if (INTEL_GEN(dev_priv) >= 11) {
+		plane_width_max = 5120;
+		plane_height_max = 4320;
+	} else {
+		plane_width_max = 5120;
+		plane_height_max = 4096;
+	}
+
+	if (mode->hdisplay > plane_width_max)
+		return MODE_H_ILLEGAL;
+
+	if (mode->vdisplay > plane_height_max)
+		return MODE_V_ILLEGAL;
+
+	return MODE_OK;
+}
+
 static const struct drm_mode_config_funcs intel_mode_funcs = {
 	.fb_create = intel_user_framebuffer_create,
 	.get_format_info = intel_get_format_info,
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 66330fcb10d4..b1ae0e59c715 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -32,6 +32,7 @@ enum link_m_n_set;
 struct dpll;
 struct drm_connector;
 struct drm_device;
+struct drm_display_mode;
 struct drm_encoder;
 struct drm_file;
 struct drm_format_info;
@@ -448,6 +449,9 @@ void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv);
 u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv,
 			      u32 pixel_format, u64 modifier);
 bool intel_plane_can_remap(const struct intel_plane_state *plane_state);
+enum drm_mode_status
+intel_mode_valid_max_plane_size(struct drm_i915_private *dev_priv,
+				const struct drm_display_mode *mode);
 enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port);
 
 void intel_plane_destroy(struct drm_plane *plane);
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index f06fbca5cb3e..0c7755e915d9 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -562,7 +562,7 @@ intel_dp_mode_valid(struct drm_connector *connector,
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		return MODE_H_ILLEGAL;
 
-	return MODE_OK;
+	return intel_mode_valid_max_plane_size(dev_priv, mode);
 }
 
 u32 intel_dp_pack_aux(const u8 *src, int src_bytes)
diff --git a/drivers/gpu/drm/i915/display/intel_dsi.c b/drivers/gpu/drm/i915/display/intel_dsi.c
index 5fec02aceaed..a2a937109a5a 100644
--- a/drivers/gpu/drm/i915/display/intel_dsi.c
+++ b/drivers/gpu/drm/i915/display/intel_dsi.c
@@ -55,6 +55,7 @@ int intel_dsi_get_modes(struct drm_connector *connector)
 enum drm_mode_status intel_dsi_mode_valid(struct drm_connector *connector,
 					  struct drm_display_mode *mode)
 {
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	const struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
@@ -73,7 +74,7 @@ enum drm_mode_status intel_dsi_mode_valid(struct drm_connector *connector,
 			return MODE_CLOCK_HIGH;
 	}
 
-	return MODE_OK;
+	return intel_mode_valid_max_plane_size(dev_priv, mode);
 }
 
 struct intel_dsi_host *intel_dsi_host_init(struct intel_dsi *intel_dsi,
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index f81541cff5df..04a8718bd2d7 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2188,8 +2188,10 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 			status = hdmi_port_clock_valid(hdmi, clock * 5 / 4,
 						       true, force_dvi);
 	}
+	if (status != MODE_OK)
+		return status;
 
-	return status;
+	return intel_mode_valid_max_plane_size(dev_priv, mode);
 }
 
 static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state,
-- 
cgit v1.2.3


From c45e788d95b470e9f68fabe1f3cb44beb5dd7840 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 19 Sep 2019 16:18:11 +0100
Subject: drm/i915/tgl: Suspend pre-parser across GTT invalidations

Before we execute a batch, we must first issue any and all TLB
invalidations so that batch picks up the new page table entries.
Tigerlake's preparser is weakening our post-sync CS_STALL inside the
invalidate pipe-control and allowing the loading of the batch buffer
before we have setup its page table (and so it loads the wrong page and
executes indefinitely).

The igt_cs_tlb indicates that this issue can only be observed on rcs,
even though the preparser is common to all engines. Alternatively, we
could do TLB shootdown via mmio on updating the GTT.

By inserting the pre-parser disable inside EMIT_INVALIDATE, we will also
accidentally fixup execution that writes into subsequent batches, such
as gem_exec_whisper and even relocations performed on the GPU. We should
be careful not to allow this disable to become baked into the uABI! The
issue is that if userspace relies on our disabling of the HW
optimisation, when we are ready to enable that optimisation, userspace
will then be broken...

Testcase: igt/i915_selftests/live_gtt/igt_cs_tlb
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111753
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919151811.9526-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 74 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 73 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index a99166a2d2eb..49ed9230a2cb 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2807,6 +2807,78 @@ static int gen11_emit_flush_render(struct i915_request *request,
 	return 0;
 }
 
+static u32 preparser_disable(bool state)
+{
+	return MI_ARB_CHECK | 1 << 8 | state;
+}
+
+static int gen12_emit_flush_render(struct i915_request *request,
+				   u32 mode)
+{
+	const u32 scratch_addr =
+		intel_gt_scratch_offset(request->engine->gt,
+					INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH);
+
+	if (mode & EMIT_FLUSH) {
+		u32 flags = 0;
+		u32 *cs;
+
+		flags |= PIPE_CONTROL_TILE_CACHE_FLUSH;
+		flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
+		flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
+		flags |= PIPE_CONTROL_DC_FLUSH_ENABLE;
+		flags |= PIPE_CONTROL_FLUSH_ENABLE;
+
+		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+		flags |= PIPE_CONTROL_QW_WRITE;
+
+		flags |= PIPE_CONTROL_CS_STALL;
+
+		cs = intel_ring_begin(request, 6);
+		if (IS_ERR(cs))
+			return PTR_ERR(cs);
+
+		cs = gen8_emit_pipe_control(cs, flags, scratch_addr);
+		intel_ring_advance(request, cs);
+	}
+
+	if (mode & EMIT_INVALIDATE) {
+		u32 flags = 0;
+		u32 *cs;
+
+		flags |= PIPE_CONTROL_COMMAND_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_TLB_INVALIDATE;
+		flags |= PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+
+		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+		flags |= PIPE_CONTROL_QW_WRITE;
+
+		flags |= PIPE_CONTROL_CS_STALL;
+
+		cs = intel_ring_begin(request, 8);
+		if (IS_ERR(cs))
+			return PTR_ERR(cs);
+
+		/*
+		 * Prevent the pre-parser from skipping past the TLB
+		 * invalidate and loading a stale page for the batch
+		 * buffer / request payload.
+		 */
+		*cs++ = preparser_disable(true);
+
+		cs = gen8_emit_pipe_control(cs, flags, scratch_addr);
+
+		*cs++ = preparser_disable(false);
+		intel_ring_advance(request, cs);
+	}
+
+	return 0;
+}
+
 /*
  * Reserve space for 2 NOOPs at the end of each request to be
  * used as a workaround for not being allowed to do lite
@@ -3072,7 +3144,7 @@ static void rcs_submission_override(struct intel_engine_cs *engine)
 {
 	switch (INTEL_GEN(engine->i915)) {
 	case 12:
-		engine->emit_flush = gen11_emit_flush_render;
+		engine->emit_flush = gen12_emit_flush_render;
 		engine->emit_fini_breadcrumb = gen12_emit_fini_breadcrumb_rcs;
 		break;
 	case 11:
-- 
cgit v1.2.3


From d19d71fc2b15bf30ff3e56932eae23ff096c1396 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 19 Sep 2019 12:19:10 +0100
Subject: drm/i915: Mark i915_request.timeline as a volatile, rcu pointer

The request->timeline is only valid until the request is retired (i.e.
before it is completed). Upon retiring the request, the context may be
unpinned and freed, and along with it the timeline may be freed. We
therefore need to be very careful when chasing rq->timeline that the
pointer does not disappear beneath us. The vast majority of users are in
a protected context, either during request construction or retirement,
where the timeline->mutex is held and the timeline cannot disappear. It
is those few off the beaten path (where we access a second timeline) that
need extra scrutiny -- to be added in the next patch after first adding
the warnings about dangerous access.

One complication, where we cannot use the timeline->mutex itself, is
during request submission onto hardware (under spinlocks). Here, we want
to check on the timeline to finalize the breadcrumb, and so we need to
impose a second rule to ensure that the request->timeline is indeed
valid. As we are submitting the request, it's context and timeline must
be pinned, as it will be used by the hardware. Since it is pinned, we
know the request->timeline must still be valid, and we cannot submit the
idle barrier until after we release the engine->active.lock, ergo while
submitting and holding that spinlock, a second thread cannot release the
timeline.

v2: Don't be lazy inside selftests; hold the timeline->mutex for as long
as we need it, and tidy up acquiring the timeline with a bit of
refactoring (i915_active_add_request)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919111912.21631-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/display/intel_overlay.c   |  2 +-
 drivers/gpu/drm/i915/gem/i915_gem_client_blt.c |  2 +-
 drivers/gpu/drm/i915/gem/i915_gem_context.c    |  2 +-
 drivers/gpu/drm/i915/gt/intel_context.c        |  4 +-
 drivers/gpu/drm/i915/gt/intel_engine_cs.c      | 57 ++++++++++++++++++++++----
 drivers/gpu/drm/i915/gt/intel_engine_pm.c      |  2 +-
 drivers/gpu/drm/i915/gt/intel_engine_pool.h    |  2 +-
 drivers/gpu/drm/i915/gt/intel_lrc.c            | 17 ++++----
 drivers/gpu/drm/i915/gt/intel_ringbuffer.c     | 27 ++++++------
 drivers/gpu/drm/i915/gt/intel_timeline.c       |  6 +--
 drivers/gpu/drm/i915/gt/intel_timeline_types.h |  1 +
 drivers/gpu/drm/i915/gt/selftest_context.c     | 18 +++++---
 drivers/gpu/drm/i915/gt/selftest_lrc.c         |  2 +-
 drivers/gpu/drm/i915/i915_active.c             |  2 +-
 drivers/gpu/drm/i915/i915_active.h             |  6 +++
 drivers/gpu/drm/i915/i915_request.c            | 28 ++++++++-----
 drivers/gpu/drm/i915/i915_request.h            | 22 +++++++++-
 drivers/gpu/drm/i915/i915_vma.c                |  6 +--
 drivers/gpu/drm/i915/selftests/i915_active.c   |  2 +-
 drivers/gpu/drm/i915/selftests/igt_spinner.c   |  2 +-
 20 files changed, 147 insertions(+), 63 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 29edfc343716..5efef9babadb 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -230,7 +230,7 @@ alloc_request(struct intel_overlay *overlay, void (*fn)(struct intel_overlay *))
 	if (IS_ERR(rq))
 		return rq;
 
-	err = i915_active_ref(&overlay->last_flip, rq->timeline, rq);
+	err = i915_active_add_request(&overlay->last_flip, rq);
 	if (err) {
 		i915_request_add(rq);
 		return ERR_PTR(err);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
index f99920652751..7f61a8024133 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
@@ -211,7 +211,7 @@ static void clear_pages_worker(struct work_struct *work)
 	 * keep track of the GPU activity within this vma/request, and
 	 * propagate the signal from the request to w->dma.
 	 */
-	err = i915_active_ref(&vma->active, rq->timeline, rq);
+	err = i915_active_add_request(&vma->active, rq);
 	if (err)
 		goto out_request;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index f1c0e5d958f3..4a34c4f62065 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -910,7 +910,7 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 		if (emit)
 			err = emit(rq, data);
 		if (err == 0)
-			err = i915_active_ref(&cb->base, rq->timeline, rq);
+			err = i915_active_add_request(&cb->base, rq);
 
 		i915_request_add(rq);
 		if (err)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index c0495811f493..26cb838c272c 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -298,7 +298,7 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 	/* Only suitable for use in remotely modifying this context */
 	GEM_BUG_ON(rq->hw_context == ce);
 
-	if (rq->timeline != tl) { /* beware timeline sharing */
+	if (rcu_access_pointer(rq->timeline) != tl) { /* timeline sharing! */
 		err = mutex_lock_interruptible_nested(&tl->mutex,
 						      SINGLE_DEPTH_NESTING);
 		if (err)
@@ -319,7 +319,7 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 	 * words transfer the pinned ce object to tracked active request.
 	 */
 	GEM_BUG_ON(i915_active_is_idle(&ce->active));
-	return i915_active_ref(&ce->active, rq->timeline, rq);
+	return i915_active_add_request(&ce->active, rq);
 }
 
 struct i915_request *intel_context_create_request(struct intel_context *ce)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 3c176b0f4b45..f451d5076bde 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -680,6 +680,8 @@ static int measure_breadcrumb_dw(struct intel_engine_cs *engine)
 				engine->status_page.vma))
 		goto out_frame;
 
+	mutex_lock(&frame->timeline.mutex);
+
 	frame->ring.vaddr = frame->cs;
 	frame->ring.size = sizeof(frame->cs);
 	frame->ring.effective_size = frame->ring.size;
@@ -688,18 +690,22 @@ static int measure_breadcrumb_dw(struct intel_engine_cs *engine)
 	frame->rq.i915 = engine->i915;
 	frame->rq.engine = engine;
 	frame->rq.ring = &frame->ring;
-	frame->rq.timeline = &frame->timeline;
+	rcu_assign_pointer(frame->rq.timeline, &frame->timeline);
 
 	dw = intel_timeline_pin(&frame->timeline);
 	if (dw < 0)
 		goto out_timeline;
 
+	spin_lock_irq(&engine->active.lock);
 	dw = engine->emit_fini_breadcrumb(&frame->rq, frame->cs) - frame->cs;
+	spin_unlock_irq(&engine->active.lock);
+
 	GEM_BUG_ON(dw & 1); /* RING_TAIL must be qword aligned */
 
 	intel_timeline_unpin(&frame->timeline);
 
 out_timeline:
+	mutex_unlock(&frame->timeline.mutex);
 	intel_timeline_fini(&frame->timeline);
 out_frame:
 	kfree(frame);
@@ -1196,6 +1202,27 @@ static void hexdump(struct drm_printer *m, const void *buf, size_t len)
 	}
 }
 
+static struct intel_timeline *get_timeline(struct i915_request *rq)
+{
+	struct intel_timeline *tl;
+
+	/*
+	 * Even though we are holding the engine->active.lock here, there
+	 * is no control over the submission queue per-se and we are
+	 * inspecting the active state at a random point in time, with an
+	 * unknown queue. Play safe and make sure the timeline remains valid.
+	 * (Only being used for pretty printing, one extra kref shouldn't
+	 * cause a camel stampede!)
+	 */
+	rcu_read_lock();
+	tl = rcu_dereference(rq->timeline);
+	if (!kref_get_unless_zero(&tl->kref))
+		tl = NULL;
+	rcu_read_unlock();
+
+	return tl;
+}
+
 static void intel_engine_print_registers(struct intel_engine_cs *engine,
 					 struct drm_printer *m)
 {
@@ -1290,27 +1317,37 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 			int len;
 
 			len = snprintf(hdr, sizeof(hdr),
-				       "\t\tActive[%d: ",
+				       "\t\tActive[%d]: ",
 				       (int)(port - execlists->active));
-			if (!i915_request_signaled(rq))
+			if (!i915_request_signaled(rq)) {
+				struct intel_timeline *tl = get_timeline(rq);
+
 				len += snprintf(hdr + len, sizeof(hdr) - len,
 						"ring:{start:%08x, hwsp:%08x, seqno:%08x}, ",
 						i915_ggtt_offset(rq->ring->vma),
-						rq->timeline->hwsp_offset,
+						tl ? tl->hwsp_offset : 0,
 						hwsp_seqno(rq));
+
+				if (tl)
+					intel_timeline_put(tl);
+			}
 			snprintf(hdr + len, sizeof(hdr) - len, "rq: ");
 			print_request(m, rq, hdr);
 		}
 		for (port = execlists->pending; (rq = *port); port++) {
+			struct intel_timeline *tl = get_timeline(rq);
 			char hdr[80];
 
 			snprintf(hdr, sizeof(hdr),
 				 "\t\tPending[%d] ring:{start:%08x, hwsp:%08x, seqno:%08x}, rq: ",
 				 (int)(port - execlists->pending),
 				 i915_ggtt_offset(rq->ring->vma),
-				 rq->timeline->hwsp_offset,
+				 tl ? tl->hwsp_offset : 0,
 				 hwsp_seqno(rq));
 			print_request(m, rq, hdr);
+
+			if (tl)
+				intel_timeline_put(tl);
 		}
 		spin_unlock_irqrestore(&engine->active.lock, flags);
 	} else if (INTEL_GEN(dev_priv) > 6) {
@@ -1388,6 +1425,8 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	spin_lock_irqsave(&engine->active.lock, flags);
 	rq = intel_engine_find_active_request(engine);
 	if (rq) {
+		struct intel_timeline *tl = get_timeline(rq);
+
 		print_request(m, rq, "\t\tactive ");
 
 		drm_printf(m, "\t\tring->start:  0x%08x\n",
@@ -1400,8 +1439,12 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 			   rq->ring->emit);
 		drm_printf(m, "\t\tring->space:  0x%08x\n",
 			   rq->ring->space);
-		drm_printf(m, "\t\tring->hwsp:   0x%08x\n",
-			   rq->timeline->hwsp_offset);
+
+		if (tl) {
+			drm_printf(m, "\t\tring->hwsp:   0x%08x\n",
+				   tl->hwsp_offset);
+			intel_timeline_put(tl);
+		}
 
 		print_request_ring(m, rq);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 65b5ca74b394..ce61c83d68e9 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -103,7 +103,7 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 		/* Context switch failed, hope for the best! Maybe reset? */
 		goto out_unlock;
 
-	intel_timeline_enter(rq->timeline);
+	intel_timeline_enter(i915_request_timeline(rq));
 
 	/* Check again on the next retirement. */
 	engine->wakeref_serial = engine->serial + 1;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pool.h b/drivers/gpu/drm/i915/gt/intel_engine_pool.h
index 7e2123b33594..1bd89cadc3b7 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pool.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pool.h
@@ -18,7 +18,7 @@ static inline int
 intel_engine_pool_mark_active(struct intel_engine_pool_node *node,
 			      struct i915_request *rq)
 {
-	return i915_active_ref(&node->active, rq->timeline, rq);
+	return i915_active_add_request(&node->active, rq);
 }
 
 static inline void
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 49ed9230a2cb..1a2b71157f08 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1825,7 +1825,7 @@ static int gen8_emit_init_breadcrumb(struct i915_request *rq)
 {
 	u32 *cs;
 
-	GEM_BUG_ON(!rq->timeline->has_initial_breadcrumb);
+	GEM_BUG_ON(!i915_request_timeline(rq)->has_initial_breadcrumb);
 
 	cs = intel_ring_begin(rq, 6);
 	if (IS_ERR(cs))
@@ -1841,7 +1841,7 @@ static int gen8_emit_init_breadcrumb(struct i915_request *rq)
 	*cs++ = MI_NOOP;
 
 	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
-	*cs++ = rq->timeline->hwsp_offset;
+	*cs++ = i915_request_timeline(rq)->hwsp_offset;
 	*cs++ = 0;
 	*cs++ = rq->fence.seqno - 1;
 
@@ -2324,7 +2324,8 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
 
 static struct i915_request *active_request(struct i915_request *rq)
 {
-	const struct list_head * const list = &rq->timeline->requests;
+	const struct list_head * const list =
+		&i915_request_active_timeline(rq)->requests;
 	const struct intel_context * const ce = rq->hw_context;
 	struct i915_request *active = NULL;
 
@@ -2927,7 +2928,7 @@ static u32 *gen8_emit_fini_breadcrumb(struct i915_request *request, u32 *cs)
 {
 	cs = gen8_emit_ggtt_write(cs,
 				  request->fence.seqno,
-				  request->timeline->hwsp_offset,
+				  i915_request_active_timeline(request)->hwsp_offset,
 				  0);
 
 	return gen8_emit_fini_breadcrumb_footer(request, cs);
@@ -2944,7 +2945,7 @@ static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 	/* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */
 	cs = gen8_emit_ggtt_write_rcs(cs,
 				      request->fence.seqno,
-				      request->timeline->hwsp_offset,
+				      i915_request_active_timeline(request)->hwsp_offset,
 				      PIPE_CONTROL_FLUSH_ENABLE |
 				      PIPE_CONTROL_CS_STALL);
 
@@ -2956,7 +2957,7 @@ gen11_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 {
 	cs = gen8_emit_ggtt_write_rcs(cs,
 				      request->fence.seqno,
-				      request->timeline->hwsp_offset,
+				      i915_request_active_timeline(request)->hwsp_offset,
 				      PIPE_CONTROL_CS_STALL |
 				      PIPE_CONTROL_TILE_CACHE_FLUSH |
 				      PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
@@ -3020,7 +3021,7 @@ static u32 *gen12_emit_fini_breadcrumb(struct i915_request *request, u32 *cs)
 {
 	cs = gen8_emit_ggtt_write(cs,
 				  request->fence.seqno,
-				  request->timeline->hwsp_offset,
+				  i915_request_active_timeline(request)->hwsp_offset,
 				  0);
 
 	return gen12_emit_fini_breadcrumb_footer(request, cs);
@@ -3031,7 +3032,7 @@ gen12_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 {
 	cs = gen8_emit_ggtt_write_rcs(cs,
 				      request->fence.seqno,
-				      request->timeline->hwsp_offset,
+				      i915_request_active_timeline(request)->hwsp_offset,
 				      PIPE_CONTROL_CS_STALL |
 				      PIPE_CONTROL_TILE_CACHE_FLUSH |
 				      PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index a25b84b12ef1..0747b8c9f768 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -322,7 +322,8 @@ static u32 *gen6_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 		 PIPE_CONTROL_DC_FLUSH_ENABLE |
 		 PIPE_CONTROL_QW_WRITE |
 		 PIPE_CONTROL_CS_STALL);
-	*cs++ = rq->timeline->hwsp_offset | PIPE_CONTROL_GLOBAL_GTT;
+	*cs++ = i915_request_active_timeline(rq)->hwsp_offset |
+		PIPE_CONTROL_GLOBAL_GTT;
 	*cs++ = rq->fence.seqno;
 
 	*cs++ = MI_USER_INTERRUPT;
@@ -425,7 +426,7 @@ static u32 *gen7_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 		 PIPE_CONTROL_QW_WRITE |
 		 PIPE_CONTROL_GLOBAL_GTT_IVB |
 		 PIPE_CONTROL_CS_STALL);
-	*cs++ = rq->timeline->hwsp_offset;
+	*cs++ = i915_request_active_timeline(rq)->hwsp_offset;
 	*cs++ = rq->fence.seqno;
 
 	*cs++ = MI_USER_INTERRUPT;
@@ -439,8 +440,8 @@ static u32 *gen7_rcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 
 static u32 *gen6_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 {
-	GEM_BUG_ON(rq->timeline->hwsp_ggtt != rq->engine->status_page.vma);
-	GEM_BUG_ON(offset_in_page(rq->timeline->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR);
+	GEM_BUG_ON(i915_request_active_timeline(rq)->hwsp_ggtt != rq->engine->status_page.vma);
+	GEM_BUG_ON(offset_in_page(i915_request_active_timeline(rq)->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR);
 
 	*cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
 	*cs++ = I915_GEM_HWS_SEQNO_ADDR | MI_FLUSH_DW_USE_GTT;
@@ -459,8 +460,8 @@ static u32 *gen7_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 {
 	int i;
 
-	GEM_BUG_ON(rq->timeline->hwsp_ggtt != rq->engine->status_page.vma);
-	GEM_BUG_ON(offset_in_page(rq->timeline->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR);
+	GEM_BUG_ON(i915_request_active_timeline(rq)->hwsp_ggtt != rq->engine->status_page.vma);
+	GEM_BUG_ON(offset_in_page(i915_request_active_timeline(rq)->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR);
 
 	*cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
 	*cs++ = I915_GEM_HWS_SEQNO_ADDR | MI_FLUSH_DW_USE_GTT;
@@ -938,8 +939,8 @@ static void i9xx_submit_request(struct i915_request *request)
 
 static u32 *i9xx_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 {
-	GEM_BUG_ON(rq->timeline->hwsp_ggtt != rq->engine->status_page.vma);
-	GEM_BUG_ON(offset_in_page(rq->timeline->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR);
+	GEM_BUG_ON(i915_request_active_timeline(rq)->hwsp_ggtt != rq->engine->status_page.vma);
+	GEM_BUG_ON(offset_in_page(i915_request_active_timeline(rq)->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR);
 
 	*cs++ = MI_FLUSH;
 
@@ -961,8 +962,8 @@ static u32 *gen5_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 {
 	int i;
 
-	GEM_BUG_ON(rq->timeline->hwsp_ggtt != rq->engine->status_page.vma);
-	GEM_BUG_ON(offset_in_page(rq->timeline->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR);
+	GEM_BUG_ON(i915_request_active_timeline(rq)->hwsp_ggtt != rq->engine->status_page.vma);
+	GEM_BUG_ON(offset_in_page(i915_request_active_timeline(rq)->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR);
 
 	*cs++ = MI_FLUSH;
 
@@ -1815,7 +1816,7 @@ static int ring_request_alloc(struct i915_request *request)
 	int ret;
 
 	GEM_BUG_ON(!intel_context_is_pinned(request->hw_context));
-	GEM_BUG_ON(request->timeline->has_initial_breadcrumb);
+	GEM_BUG_ON(i915_request_timeline(request)->has_initial_breadcrumb);
 
 	/*
 	 * Flush enough space to reduce the likelihood of waiting after
@@ -1926,7 +1927,9 @@ u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords)
 		 */
 		GEM_BUG_ON(!rq->reserved_space);
 
-		ret = wait_for_space(ring, rq->timeline, total_bytes);
+		ret = wait_for_space(ring,
+				     i915_request_timeline(rq),
+				     total_bytes);
 		if (unlikely(ret))
 			return ERR_PTR(ret);
 	}
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 9cb01d9828f1..115a24d4a20a 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -493,7 +493,7 @@ int intel_timeline_get_seqno(struct intel_timeline *tl,
 static int cacheline_ref(struct intel_timeline_cacheline *cl,
 			 struct i915_request *rq)
 {
-	return i915_active_ref(&cl->active, rq->timeline, rq);
+	return i915_active_add_request(&cl->active, rq);
 }
 
 int intel_timeline_read_hwsp(struct i915_request *from,
@@ -504,7 +504,7 @@ int intel_timeline_read_hwsp(struct i915_request *from,
 	struct intel_timeline *tl = from->timeline;
 	int err;
 
-	GEM_BUG_ON(to->timeline == tl);
+	GEM_BUG_ON(rcu_access_pointer(to->timeline) == tl);
 
 	mutex_lock_nested(&tl->mutex, SINGLE_DEPTH_NESTING);
 	err = i915_request_completed(from);
@@ -541,7 +541,7 @@ void __intel_timeline_free(struct kref *kref)
 		container_of(kref, typeof(*timeline), kref);
 
 	intel_timeline_fini(timeline);
-	kfree(timeline);
+	kfree_rcu(timeline, rcu);
 }
 
 static void timelines_fini(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
index 2b1baf2fcc8e..c668c4c50e75 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
@@ -80,6 +80,7 @@ struct intel_timeline {
 	struct intel_gt *gt;
 
 	struct kref kref;
+	struct rcu_head rcu;
 };
 
 #endif /* __I915_TIMELINE_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index 9d1ea26c7a2d..4ce1e25433d2 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -14,22 +14,28 @@
 
 static int request_sync(struct i915_request *rq)
 {
+	struct intel_timeline *tl = i915_request_timeline(rq);
 	long timeout;
 	int err = 0;
 
+	intel_timeline_get(tl);
 	i915_request_get(rq);
 
-	i915_request_add(rq);
+	/* Opencode i915_request_add() so we can keep the timeline locked. */
+	__i915_request_commit(rq);
+	__i915_request_queue(rq, NULL);
+
 	timeout = i915_request_wait(rq, 0, HZ / 10);
-	if (timeout < 0) {
+	if (timeout < 0)
 		err = timeout;
-	} else {
-		mutex_lock(&rq->timeline->mutex);
+	else
 		i915_request_retire_upto(rq);
-		mutex_unlock(&rq->timeline->mutex);
-	}
+
+	lockdep_unpin_lock(&tl->mutex, rq->cookie);
+	mutex_unlock(&tl->mutex);
 
 	i915_request_put(rq);
+	intel_timeline_put(tl);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 26d05bd1bdc8..93a871bfd95d 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -1089,7 +1089,7 @@ static int live_suppress_wait_preempt(void *arg)
 				}
 
 				/* Disable NEWCLIENT promotion */
-				__i915_active_request_set(&rq[i]->timeline->last_request,
+				__i915_active_request_set(&i915_request_timeline(rq[i])->last_request,
 							  dummy);
 				i915_request_add(rq[i]);
 			}
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 6a447f1d0110..d5aac6ff803a 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -695,7 +695,7 @@ void i915_request_add_active_barriers(struct i915_request *rq)
 	struct llist_node *node, *next;
 
 	GEM_BUG_ON(intel_engine_is_virtual(engine));
-	GEM_BUG_ON(rq->timeline != engine->kernel_context->timeline);
+	GEM_BUG_ON(i915_request_timeline(rq) != engine->kernel_context->timeline);
 
 	/*
 	 * Attach the list of proto-fences to the in-flight request such
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index f95058f99057..949c6835335b 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -373,6 +373,12 @@ int i915_active_ref(struct i915_active *ref,
 		    struct intel_timeline *tl,
 		    struct i915_request *rq);
 
+static inline int
+i915_active_add_request(struct i915_active *ref, struct i915_request *rq)
+{
+	return i915_active_ref(ref, i915_request_timeline(rq), rq);
+}
+
 int i915_active_wait(struct i915_active *ref);
 
 int i915_request_await_active(struct i915_request *rq,
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 606acde47fa0..fb6f21c41934 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -220,7 +220,6 @@ static bool i915_request_retire(struct i915_request *rq)
 {
 	struct i915_active_request *active, *next;
 
-	lockdep_assert_held(&rq->timeline->mutex);
 	if (!i915_request_completed(rq))
 		return false;
 
@@ -241,7 +240,8 @@ static bool i915_request_retire(struct i915_request *rq)
 	 * Note this requires that we are always called in request
 	 * completion order.
 	 */
-	GEM_BUG_ON(!list_is_first(&rq->link, &rq->timeline->requests));
+	GEM_BUG_ON(!list_is_first(&rq->link,
+				  &i915_request_timeline(rq)->requests));
 	rq->ring->head = rq->postfix;
 
 	/*
@@ -317,7 +317,7 @@ static bool i915_request_retire(struct i915_request *rq)
 
 void i915_request_retire_upto(struct i915_request *rq)
 {
-	struct intel_timeline * const tl = rq->timeline;
+	struct intel_timeline * const tl = i915_request_timeline(rq);
 	struct i915_request *tmp;
 
 	GEM_TRACE("%s fence %llx:%lld, current %d\n",
@@ -325,7 +325,6 @@ void i915_request_retire_upto(struct i915_request *rq)
 		  rq->fence.context, rq->fence.seqno,
 		  hwsp_seqno(rq));
 
-	lockdep_assert_held(&tl->mutex);
 	GEM_BUG_ON(!i915_request_completed(rq));
 
 	do {
@@ -661,9 +660,11 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->gem_context = ce->gem_context;
 	rq->engine = ce->engine;
 	rq->ring = ce->ring;
-	rq->timeline = tl;
+
+	rcu_assign_pointer(rq->timeline, tl);
 	rq->hwsp_seqno = tl->hwsp_seqno;
 	rq->hwsp_cacheline = tl->hwsp_cacheline;
+
 	rq->rcustate = get_state_synchronize_rcu(); /* acts as smp_mb() */
 
 	spin_lock_init(&rq->lock);
@@ -771,7 +772,8 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 		return 0;
 
 	signal = list_prev_entry(signal, link);
-	if (intel_timeline_sync_is_later(rq->timeline, &signal->fence))
+	if (intel_timeline_sync_is_later(i915_request_timeline(rq),
+					 &signal->fence))
 		return 0;
 
 	return i915_sw_fence_await_dma_fence(&rq->submit,
@@ -947,7 +949,8 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 
 		/* Squash repeated waits to the same timelines */
 		if (fence->context &&
-		    intel_timeline_sync_is_later(rq->timeline, fence))
+		    intel_timeline_sync_is_later(i915_request_timeline(rq),
+						 fence))
 			continue;
 
 		if (dma_fence_is_i915(fence))
@@ -961,7 +964,8 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 
 		/* Record the latest fence used against each timeline */
 		if (fence->context)
-			intel_timeline_sync_set(rq->timeline, fence);
+			intel_timeline_sync_set(i915_request_timeline(rq),
+						fence);
 	} while (--nchild);
 
 	return 0;
@@ -1103,7 +1107,7 @@ void i915_request_skip(struct i915_request *rq, int error)
 static struct i915_request *
 __i915_request_add_to_timeline(struct i915_request *rq)
 {
-	struct intel_timeline *timeline = rq->timeline;
+	struct intel_timeline *timeline = i915_request_timeline(rq);
 	struct i915_request *prev;
 
 	/*
@@ -1216,7 +1220,7 @@ void __i915_request_queue(struct i915_request *rq,
 void i915_request_add(struct i915_request *rq)
 {
 	struct i915_sched_attr attr = rq->gem_context->sched;
-	struct intel_timeline * const tl = rq->timeline;
+	struct intel_timeline * const tl = i915_request_timeline(rq);
 	struct i915_request *prev;
 
 	lockdep_assert_held(&tl->mutex);
@@ -1271,7 +1275,9 @@ void i915_request_add(struct i915_request *rq)
 	 * work on behalf of others -- but instead we should benefit from
 	 * improved resource management. (Well, that's the theory at least.)
 	 */
-	if (prev && i915_request_completed(prev) && prev->timeline == tl)
+	if (prev &&
+	    i915_request_completed(prev) &&
+	    rcu_access_pointer(prev->timeline) == tl)
 		i915_request_retire_upto(prev);
 
 	mutex_unlock(&tl->mutex);
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 8ac6e1226a56..b18f49528ded 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -113,7 +113,7 @@ struct i915_request {
 	struct intel_engine_cs *engine;
 	struct intel_context *hw_context;
 	struct intel_ring *ring;
-	struct intel_timeline *timeline;
+	struct intel_timeline __rcu *timeline;
 	struct list_head signal_link;
 
 	/*
@@ -442,6 +442,26 @@ static inline bool i915_request_has_nopreempt(const struct i915_request *rq)
 	return unlikely(rq->flags & I915_REQUEST_NOPREEMPT);
 }
 
+static inline struct intel_timeline *
+i915_request_timeline(struct i915_request *rq)
+{
+	/* Valid only while the request is being constructed (or retired). */
+	return rcu_dereference_protected(rq->timeline,
+					 lockdep_is_held(&rcu_access_pointer(rq->timeline)->mutex));
+}
+
+static inline struct intel_timeline *
+i915_request_active_timeline(struct i915_request *rq)
+{
+	/*
+	 * When in use during submission, we are protected by a guarantee that
+	 * the context/timeline is pinned and must remain pinned until after
+	 * this submission.
+	 */
+	return rcu_dereference_protected(rq->timeline,
+					 lockdep_is_held(&rq->engine->active.lock));
+}
+
 bool i915_retire_requests(struct drm_i915_private *i915);
 
 #endif /* I915_REQUEST_H */
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 411047d6a909..9d5b0f87c210 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -900,15 +900,13 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 	 * add the active reference first and queue for it to be dropped
 	 * *last*.
 	 */
-	err = i915_active_ref(&vma->active, rq->timeline, rq);
+	err = i915_active_add_request(&vma->active, rq);
 	if (unlikely(err))
 		return err;
 
 	if (flags & EXEC_OBJECT_WRITE) {
 		if (intel_frontbuffer_invalidate(obj->frontbuffer, ORIGIN_CS))
-			i915_active_ref(&obj->frontbuffer->write,
-					rq->timeline,
-					rq);
+			i915_active_add_request(&obj->frontbuffer->write, rq);
 
 		dma_resv_add_excl_fence(vma->resv, &rq->fence);
 		obj->write_domain = I915_GEM_DOMAIN_RENDER;
diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
index 77d844ac8b71..afecfa081ff4 100644
--- a/drivers/gpu/drm/i915/selftests/i915_active.c
+++ b/drivers/gpu/drm/i915/selftests/i915_active.c
@@ -110,7 +110,7 @@ __live_active_setup(struct drm_i915_private *i915)
 						       submit,
 						       GFP_KERNEL);
 		if (err >= 0)
-			err = i915_active_ref(&active->base, rq->timeline, rq);
+			err = i915_active_add_request(&active->base, rq);
 		i915_request_add(rq);
 		if (err) {
 			pr_err("Failed to track active ref!\n");
diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c
index 11f04ad48e68..ee8450b871da 100644
--- a/drivers/gpu/drm/i915/selftests/igt_spinner.c
+++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c
@@ -147,7 +147,7 @@ igt_spinner_create_request(struct igt_spinner *spin,
 	intel_gt_chipset_flush(engine->gt);
 
 	if (engine->emit_init_breadcrumb &&
-	    rq->timeline->has_initial_breadcrumb) {
+	    i915_request_timeline(rq)->has_initial_breadcrumb) {
 		err = engine->emit_init_breadcrumb(rq);
 		if (err)
 			goto cancel_rq;
-- 
cgit v1.2.3


From 6a79d848403ded2245fbe4aaf50b33118d12daf0 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 19 Sep 2019 12:19:11 +0100
Subject: drm/i915: Lock signaler timeline while navigating

As we need to take a walk back along the signaler timeline to find the
fence before upon which we want to wait, we need to lock that timeline
to prevent it being modified as we walk. Similarly, we also need to
acquire a reference to the earlier fence while it still exists!

Though we lack the correct locking today, we are saved by the
overarching struct_mutex -- but that protection is being removed.

v2: Tvrtko made me realise I was being lax and using annotations to
ignore the AB-BA deadlock from the timeline overlap. As it would be
possible to construct a second request that was using a semaphore from the
same timeline as ourselves, we could quite easily end up in a situation
where we deadlocked in our mutex waits. Avoid that by using a trylock
and falling back to a normal dma-fence await if contended.

v3: Eek, the signal->timeline is volatile and must be carefully
dereferenced to ensure it is valid.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919111912.21631-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_request.c | 68 +++++++++++++++++++++++++------------
 1 file changed, 46 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index fb6f21c41934..9bd8538b1907 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -768,17 +768,43 @@ err_unlock:
 static int
 i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 {
-	if (list_is_first(&signal->link, &signal->timeline->requests))
-		return 0;
+	struct intel_timeline *tl;
+	struct dma_fence *fence;
+	int err;
+
+	GEM_BUG_ON(i915_request_timeline(rq) ==
+		   rcu_access_pointer(signal->timeline));
 
-	signal = list_prev_entry(signal, link);
-	if (intel_timeline_sync_is_later(i915_request_timeline(rq),
-					 &signal->fence))
+	rcu_read_lock();
+	tl = rcu_dereference(signal->timeline);
+	if (i915_request_started(signal) || !kref_get_unless_zero(&tl->kref))
+		tl = NULL;
+	rcu_read_unlock();
+	if (!tl) /* already started or maybe even completed */
 		return 0;
 
-	return i915_sw_fence_await_dma_fence(&rq->submit,
-					     &signal->fence, 0,
-					     I915_FENCE_GFP);
+	fence = ERR_PTR(-EBUSY);
+	if (mutex_trylock(&tl->mutex)) {
+		fence = NULL;
+		if (!i915_request_started(signal) &&
+		    !list_is_first(&signal->link, &tl->requests)) {
+			signal = list_prev_entry(signal, link);
+			fence = dma_fence_get(&signal->fence);
+		}
+		mutex_unlock(&tl->mutex);
+	}
+	intel_timeline_put(tl);
+	if (IS_ERR_OR_NULL(fence))
+		return PTR_ERR_OR_ZERO(fence);
+
+	err = 0;
+	if (intel_timeline_sync_is_later(i915_request_timeline(rq), fence))
+		err = i915_sw_fence_await_dma_fence(&rq->submit,
+						    fence, 0,
+						    I915_FENCE_GFP);
+	dma_fence_put(fence);
+
+	return err;
 }
 
 static intel_engine_mask_t
@@ -808,30 +834,23 @@ emit_semaphore_wait(struct i915_request *to,
 	u32 hwsp_offset;
 	int len;
 	u32 *cs;
-	int err;
 
-	GEM_BUG_ON(!from->timeline->has_initial_breadcrumb);
 	GEM_BUG_ON(INTEL_GEN(to->i915) < 8);
 
 	/* Just emit the first semaphore we see as request space is limited. */
 	if (already_busywaiting(to) & from->engine->mask)
-		return i915_sw_fence_await_dma_fence(&to->submit,
-						     &from->fence, 0,
-						     I915_FENCE_GFP);
+		goto await_fence;
 
-	err = i915_request_await_start(to, from);
-	if (err < 0)
-		return err;
+	if (i915_request_await_start(to, from) < 0)
+		goto await_fence;
 
 	/* Only submit our spinner after the signaler is running! */
-	err = __i915_request_await_execution(to, from, NULL, gfp);
-	if (err)
-		return err;
+	if (__i915_request_await_execution(to, from, NULL, gfp))
+		goto await_fence;
 
 	/* We need to pin the signaler's HWSP until we are finished reading. */
-	err = intel_timeline_read_hwsp(from, to, &hwsp_offset);
-	if (err)
-		return err;
+	if (intel_timeline_read_hwsp(from, to, &hwsp_offset))
+		goto await_fence;
 
 	len = 4;
 	if (has_token)
@@ -866,6 +885,11 @@ emit_semaphore_wait(struct i915_request *to,
 	to->sched.semaphores |= from->engine->mask;
 	to->sched.flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
 	return 0;
+
+await_fence:
+	return i915_sw_fence_await_dma_fence(&to->submit,
+					     &from->fence, 0,
+					     I915_FENCE_GFP);
 }
 
 static int
-- 
cgit v1.2.3


From 9eee0dd7d3a4e2620257f1532cba8f013aee954f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 19 Sep 2019 12:19:12 +0100
Subject: drm/i915: Protect timeline->hwsp dereferencing

As not only is the signal->timeline volatile, so will be acquiring the
timeline's HWSP. We must first carefully acquire the timeline from the
signaling request and then lock the timeline. With the removal of the
struct_mutex serialisation of request construction, we can have multiple
timelines active at once, and so we must avoid using the nested mutex
lock as it is quite possible for both timelines to be establishing
semaphores on the other and so deadlock.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919111912.21631-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_timeline.c | 32 +++++++++++++++++++++++++-------
 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 115a24d4a20a..9d436e14ea8d 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -500,17 +500,32 @@ int intel_timeline_read_hwsp(struct i915_request *from,
 			     struct i915_request *to,
 			     u32 *hwsp)
 {
-	struct intel_timeline_cacheline *cl = from->hwsp_cacheline;
-	struct intel_timeline *tl = from->timeline;
+	struct intel_timeline *tl;
 	int err;
 
+	rcu_read_lock();
+	tl = rcu_dereference(from->timeline);
+	if (i915_request_completed(from) || !kref_get_unless_zero(&tl->kref))
+		tl = NULL;
+	rcu_read_unlock();
+	if (!tl) /* already completed */
+		return 1;
+
 	GEM_BUG_ON(rcu_access_pointer(to->timeline) == tl);
 
-	mutex_lock_nested(&tl->mutex, SINGLE_DEPTH_NESTING);
-	err = i915_request_completed(from);
-	if (!err)
+	err = -EBUSY;
+	if (mutex_trylock(&tl->mutex)) {
+		struct intel_timeline_cacheline *cl = from->hwsp_cacheline;
+
+		if (i915_request_completed(from)) {
+			err = 1;
+			goto unlock;
+		}
+
 		err = cacheline_ref(cl, to);
-	if (!err) {
+		if (err)
+			goto unlock;
+
 		if (likely(cl == tl->hwsp_cacheline)) {
 			*hwsp = tl->hwsp_offset;
 		} else { /* across a seqno wrap, recover the original offset */
@@ -518,8 +533,11 @@ int intel_timeline_read_hwsp(struct i915_request *from,
 				ptr_unmask_bits(cl->vaddr, CACHELINE_BITS) *
 				CACHELINE_BYTES;
 		}
+
+unlock:
+		mutex_unlock(&tl->mutex);
 	}
-	mutex_unlock(&tl->mutex);
+	intel_timeline_put(tl);
 
 	return err;
 }
-- 
cgit v1.2.3


From e5de91e68c5ccaf4ef3e5aa265b469e186ebfa65 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 20 Sep 2019 09:12:54 +0100
Subject: Revert "drm/i915/tgl: Implement Wa_1406941453"

Our sanitychecks indicate that while this register is context
saved/restore, the HW does not preserve this bit within the register --
it likely doesn't exist, or one of those mythical bits that the
architects insist does something despite all appearances to the
contrary.

For reference, SAMPLER_MODE is already in i915_reg.h as
GEN10_SAMPLER_MODE and is being setup in icl_ctx_workarounds_init() as
opposed to the chosen location here of rcs_engine_wa_init).

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111754
Fixes: 7f0cc34b5349 ("drm/i915/tgl: Implement Wa_1406941453")
Testcase: igt/i915_selftest/live_workarounds
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Cc: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920081254.18389-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 7 -------
 drivers/gpu/drm/i915/i915_reg.h             | 3 ---
 2 files changed, 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 25ae60846398..ba65e5018978 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1260,13 +1260,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 {
 	struct drm_i915_private *i915 = engine->i915;
 
-	if (IS_GEN(i915, 12)) {
-		/* Wa_1406941453:tgl */
-		wa_masked_en(wal,
-			     SAMPLER_MODE,
-			     SAMPLER_ENABLE_SMALL_PL);
-	}
-
 	if (IS_GEN(i915, 11)) {
 		/* This is not an Wa. Enable for better image quality */
 		wa_masked_en(wal,
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 5e3a6178aff4..f8f52ae6cc6f 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -8965,9 +8965,6 @@ enum {
 #define   GEN9_DG_MIRROR_FIX_ENABLE	(1 << 5)
 #define   GEN9_CCS_TLB_PREFETCH_ENABLE	(1 << 3)
 
-#define SAMPLER_MODE			_MMIO(0xe18c)
-#define   SAMPLER_ENABLE_SMALL_PL	(1 << 15)
-
 #define GEN8_ROW_CHICKEN		_MMIO(0xe4f0)
 #define   FLOW_CONTROL_ENABLE		(1 << 15)
 #define   PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE	(1 << 8)
-- 
cgit v1.2.3


From 35d97e43bb217446cdf128c6b6dfec423ed81ddf Mon Sep 17 00:00:00 2001
From: Anusha Srivatsa <anusha.srivatsa@intel.com>
Date: Thu, 19 Sep 2019 13:12:03 -0700
Subject: drm/i915/uc: Update HuC firmware naming convention and load latest
 HuC

Make both GuC and HuC to use "." as the separator. Hardcode
the separator in MAKE_UC_FW_PATH. Remove the usage of "ver" from HuC.

The current convention being:
<platform>_<g/h>uc_<major>.<minor>.patch.bin

Update the versions of HuC being loaded of the platforms.

SKL - v2.0.0
BXT - v2.0.0
KBL - v4.0.0
GLK - v4.0.0
CFL - KBL v4.0.0
ICL - v9.0.0
CML - v4.0.0

v2: Remove the separator parameter altogether from
__MAKE_UC_FW_PATH.(Daniele)
- Squash all firmware update patches (Daniele)
v3: s/huc/HuC
- Correct the order of platforms
- Change REVID of cml to 5(Michal)
- Code space changes in huc_def (Daniele)

Suggested-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919201204.9691-1-daniele.ceraolospurio@intel.com
---
 drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c | 27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 296a82603be0..ea9a807abd4f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -39,26 +39,27 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
  * Must be ordered based on platform + revid, from newer to older.
  */
 #define INTEL_UC_FIRMWARE_DEFS(fw_def, guc_def, huc_def) \
-	fw_def(ELKHARTLAKE, 0, guc_def(ehl, 33, 0, 4), huc_def(ehl,  9,  0,    0)) \
-	fw_def(ICELAKE,     0, guc_def(icl, 33, 0, 0), huc_def(icl,  8,  4, 3238)) \
-	fw_def(COFFEELAKE,  0, guc_def(kbl, 33, 0, 0), huc_def(kbl, 02, 00, 1810)) \
-	fw_def(GEMINILAKE,  0, guc_def(glk, 33, 0, 0), huc_def(glk, 03, 01, 2893)) \
-	fw_def(KABYLAKE,    0, guc_def(kbl, 33, 0, 0), huc_def(kbl, 02, 00, 1810)) \
-	fw_def(BROXTON,     0, guc_def(bxt, 33, 0, 0), huc_def(bxt, 01,  8, 2893)) \
-	fw_def(SKYLAKE,     0, guc_def(skl, 33, 0, 0), huc_def(skl, 01, 07, 1398))
-
-#define __MAKE_UC_FW_PATH(prefix_, name_, separator_, major_, minor_, patch_) \
+	fw_def(ELKHARTLAKE, 0, guc_def(ehl, 33, 0, 4), huc_def(ehl,  9, 0, 0)) \
+	fw_def(ICELAKE,     0, guc_def(icl, 33, 0, 0), huc_def(icl,  9, 0, 0)) \
+	fw_def(COFFEELAKE,  5, guc_def(cml, 33, 0, 0), huc_def(cml,  4, 0, 0)) \
+	fw_def(COFFEELAKE,  0, guc_def(kbl, 33, 0, 0), huc_def(kbl,  4, 0, 0)) \
+	fw_def(GEMINILAKE,  0, guc_def(glk, 33, 0, 0), huc_def(glk,  4, 0, 0)) \
+	fw_def(KABYLAKE,    0, guc_def(kbl, 33, 0, 0), huc_def(kbl,  4, 0, 0)) \
+	fw_def(BROXTON,     0, guc_def(bxt, 33, 0, 0), huc_def(bxt,  2, 0, 0)) \
+	fw_def(SKYLAKE,     0, guc_def(skl, 33, 0, 0), huc_def(skl,  2, 0, 0))
+
+#define __MAKE_UC_FW_PATH(prefix_, name_, major_, minor_, patch_) \
 	"i915/" \
 	__stringify(prefix_) name_ \
-	__stringify(major_) separator_ \
-	__stringify(minor_) separator_ \
+	__stringify(major_) "." \
+	__stringify(minor_) "." \
 	__stringify(patch_) ".bin"
 
 #define MAKE_GUC_FW_PATH(prefix_, major_, minor_, patch_) \
-	__MAKE_UC_FW_PATH(prefix_, "_guc_", ".", major_, minor_, patch_)
+	__MAKE_UC_FW_PATH(prefix_, "_guc_", major_, minor_, patch_)
 
 #define MAKE_HUC_FW_PATH(prefix_, major_, minor_, bld_num_) \
-	__MAKE_UC_FW_PATH(prefix_, "_huc_ver", "_", major_, minor_, bld_num_)
+	__MAKE_UC_FW_PATH(prefix_, "_huc_", major_, minor_, bld_num_)
 
 /* All blobs need to be declared via MODULE_FIRMWARE() */
 #define INTEL_UC_MODULE_FW(platform_, revid_, guc_, huc_) \
-- 
cgit v1.2.3


From 646d3dc855212855b708da4d481051a5e8cd1946 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jul 2019 17:50:43 +0300
Subject: drm/i915: Fix HSW+ DP MSA YCbCr colorspace indication
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Looks like we're currently setting the MSA to xvYCC BT.709 instead
of the YCbCr BT.601 claimed by the comment. But even that comment
is wrong since we configure the CSC matrix to BT.709.

Let's remove the bogus statement from the comment and fix the
MSA to indicate YCbCr BT.709 so that it matches the actual
pixel data we're transmitting.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190718145053.25808-3-ville.syrjala@linux.intel.com
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 6 ++++--
 drivers/gpu/drm/i915/i915_reg.h          | 3 ++-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 3e6394139964..fb6cb6aca188 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -1730,10 +1730,12 @@ void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state)
 	/*
 	 * As per DP 1.2 spec section 2.3.4.3 while sending
 	 * YCBCR 444 signals we should program MSA MISC1/0 fields with
-	 * colorspace information. The output colorspace encoding is BT601.
+	 * colorspace information.
 	 */
 	if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR444)
-		temp |= TRANS_MSA_SAMPLING_444 | TRANS_MSA_CLRSP_YCBCR;
+		temp |= TRANS_MSA_SAMPLING_444 | TRANS_MSA_CLRSP_YCBCR |
+			TRANS_MSA_YCBCR_BT709;
+
 	/*
 	 * As per DP 1.4a spec section 2.2.4.3 [MSA Field for Indication
 	 * of Color Encoding Format and Content Color Gamut] while sending
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f8f52ae6cc6f..2a1a1e84d1bc 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -9733,7 +9733,8 @@ enum skl_power_gate {
 
 #define  TRANS_MSA_SYNC_CLK		(1 << 0)
 #define  TRANS_MSA_SAMPLING_444		(2 << 1)
-#define  TRANS_MSA_CLRSP_YCBCR		(2 << 3)
+#define  TRANS_MSA_CLRSP_YCBCR		(1 << 3)
+#define  TRANS_MSA_YCBCR_BT709		(1 << 4)
 #define  TRANS_MSA_6_BPC		(0 << 5)
 #define  TRANS_MSA_8_BPC		(1 << 5)
 #define  TRANS_MSA_10_BPC		(2 << 5)
-- 
cgit v1.2.3


From 791ad5f1e1af2926adef5bb1998eb445681e31f0 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jul 2019 17:50:44 +0300
Subject: drm/i915: Fix AVI infoframe quantization range for YCbCr output
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We're configuring the AVI infoframe quantization range bits as if
we're always transmitting RGB pixels. Let's fix this so that we
correctly indicate limited range YCC quantization range when
transmitting YCbCr instead.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190718145053.25808-4-ville.syrjala@linux.intel.com
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
---
 drivers/gpu/drm/i915/display/intel_hdmi.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 04a8718bd2d7..0082c4620246 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -724,11 +724,16 @@ intel_hdmi_compute_avi_infoframe(struct intel_encoder *encoder,
 
 	drm_hdmi_avi_infoframe_colorspace(frame, conn_state);
 
-	drm_hdmi_avi_infoframe_quant_range(frame, connector,
-					   adjusted_mode,
-					   crtc_state->limited_color_range ?
-					   HDMI_QUANTIZATION_RANGE_LIMITED :
-					   HDMI_QUANTIZATION_RANGE_FULL);
+	if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_RGB) {
+		drm_hdmi_avi_infoframe_quant_range(frame, connector,
+						   adjusted_mode,
+						   crtc_state->limited_color_range ?
+						   HDMI_QUANTIZATION_RANGE_LIMITED :
+						   HDMI_QUANTIZATION_RANGE_FULL);
+	} else {
+		frame->quantization_range = HDMI_QUANTIZATION_RANGE_DEFAULT;
+		frame->ycc_quantization_range = HDMI_YCC_QUANTIZATION_RANGE_LIMITED;
+	}
 
 	drm_hdmi_avi_infoframe_content_type(frame, conn_state);
 
-- 
cgit v1.2.3


From ba2d08c2a9ad96e592ee357ef5d46cbe1dc18bc9 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jul 2019 17:50:45 +0300
Subject: drm/i915: Extract intel_hdmi_limited_color_range()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Pull the code for computing the limited color range
setting into a small helper. We'll add a bit more to it
later.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190718145053.25808-5-ville.syrjala@linux.intel.com
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
---
 drivers/gpu/drm/i915/display/intel_hdmi.c | 30 ++++++++++++++++++++----------
 1 file changed, 20 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 0082c4620246..b781e0d1962e 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2365,6 +2365,24 @@ static int intel_hdmi_compute_clock(struct intel_encoder *encoder,
 	return 0;
 }
 
+static bool intel_hdmi_limited_color_range(const struct intel_crtc_state *crtc_state,
+					   const struct drm_connector_state *conn_state)
+{
+	const struct intel_digital_connector_state *intel_conn_state =
+		to_intel_digital_connector_state(conn_state);
+	const struct drm_display_mode *adjusted_mode =
+		&crtc_state->base.adjusted_mode;
+
+	if (intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_AUTO) {
+		/* See CEA-861-E - 5.1 Default Encoding Parameters */
+		return crtc_state->has_hdmi_sink &&
+			drm_default_rgb_quant_range(adjusted_mode) ==
+			HDMI_QUANTIZATION_RANGE_LIMITED;
+	} else {
+		return intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_LIMITED;
+	}
+}
+
 int intel_hdmi_compute_config(struct intel_encoder *encoder,
 			      struct intel_crtc_state *pipe_config,
 			      struct drm_connector_state *conn_state)
@@ -2388,16 +2406,8 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 	if (pipe_config->has_hdmi_sink)
 		pipe_config->has_infoframe = true;
 
-	if (intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_AUTO) {
-		/* See CEA-861-E - 5.1 Default Encoding Parameters */
-		pipe_config->limited_color_range =
-			pipe_config->has_hdmi_sink &&
-			drm_default_rgb_quant_range(adjusted_mode) ==
-			HDMI_QUANTIZATION_RANGE_LIMITED;
-	} else {
-		pipe_config->limited_color_range =
-			intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_LIMITED;
-	}
+	pipe_config->limited_color_range =
+		intel_hdmi_limited_color_range(pipe_config, conn_state);
 
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
 		pipe_config->pixel_multiplier = 2;
-- 
cgit v1.2.3


From cae154fcaefeb1ddab491d6fb651452a93bbf81d Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jul 2019 19:45:23 +0300
Subject: drm/i915: Never set limited_color_range=true for YCbCr output
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

crtc_state->limited_color_range only applies to RGB output but
we're currently setting it even for YCbCr output. That will
lead to conflicting MSA and PIPECONF settings which can mess
up the image. Let's make sure limited_color_range stays unset
with YCbCr output.

Also WARN if we end up with such a bogus combination when
programming the MSA MISC bits as it's impossible to even
indicate quantization rangle for YCbCr via MSA MISC. YCbCr
output is simply assumed to be limited range always. Note
that VSC SDP does provide a mechanism for full range YCbCr,
so in the future we may want to rethink how we compute/store
this state.

And for good measure we add the same WARN to the HDMI path.

v2: s/==/!=/ in the HDMI WARN

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190718164523.11738-1-ville.syrjala@linux.intel.com
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c  | 10 +++++++---
 drivers/gpu/drm/i915/display/intel_dp.c   | 10 ++++++++++
 drivers/gpu/drm/i915/display/intel_hdmi.c | 20 +++++++++++++++++---
 3 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index fb6cb6aca188..0c0da9f6c2e8 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -1706,9 +1706,6 @@ void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state)
 
 	temp = TRANS_MSA_SYNC_CLK;
 
-	if (crtc_state->limited_color_range)
-		temp |= TRANS_MSA_CEA_RANGE;
-
 	switch (crtc_state->pipe_bpp) {
 	case 18:
 		temp |= TRANS_MSA_6_BPC;
@@ -1727,6 +1724,13 @@ void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state)
 		break;
 	}
 
+	/* nonsense combination */
+	WARN_ON(crtc_state->limited_color_range &&
+		crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB);
+
+	if (crtc_state->limited_color_range)
+		temp |= TRANS_MSA_CEA_RANGE;
+
 	/*
 	 * As per DP 1.2 spec section 2.3.4.3 while sending
 	 * YCBCR 444 signals we should program MSA MISC1/0 fields with
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 0c7755e915d9..5cce9459e93c 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2150,6 +2150,16 @@ bool intel_dp_limited_color_range(const struct intel_crtc_state *crtc_state,
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->base.adjusted_mode;
 
+	/*
+	 * Our YCbCr output is always limited range.
+	 * crtc_state->limited_color_range only applies to RGB,
+	 * and it must never be set for YCbCr or we risk setting
+	 * some conflicting bits in PIPECONF which will mess up
+	 * the colors on the monitor.
+	 */
+	if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB)
+		return false;
+
 	if (intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_AUTO) {
 		/*
 		 * See:
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index b781e0d1962e..5ab73331d35d 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -724,6 +724,10 @@ intel_hdmi_compute_avi_infoframe(struct intel_encoder *encoder,
 
 	drm_hdmi_avi_infoframe_colorspace(frame, conn_state);
 
+	/* nonsense combination */
+	WARN_ON(crtc_state->limited_color_range &&
+		crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB);
+
 	if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_RGB) {
 		drm_hdmi_avi_infoframe_quant_range(frame, connector,
 						   adjusted_mode,
@@ -2373,6 +2377,16 @@ static bool intel_hdmi_limited_color_range(const struct intel_crtc_state *crtc_s
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->base.adjusted_mode;
 
+	/*
+	 * Our YCbCr output is always limited range.
+	 * crtc_state->limited_color_range only applies to RGB,
+	 * and it must never be set for YCbCr or we risk setting
+	 * some conflicting bits in PIPECONF which will mess up
+	 * the colors on the monitor.
+	 */
+	if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB)
+		return false;
+
 	if (intel_conn_state->broadcast_rgb == INTEL_BROADCAST_RGB_AUTO) {
 		/* See CEA-861-E - 5.1 Default Encoding Parameters */
 		return crtc_state->has_hdmi_sink &&
@@ -2406,9 +2420,6 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 	if (pipe_config->has_hdmi_sink)
 		pipe_config->has_infoframe = true;
 
-	pipe_config->limited_color_range =
-		intel_hdmi_limited_color_range(pipe_config, conn_state);
-
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
 		pipe_config->pixel_multiplier = 2;
 
@@ -2419,6 +2430,9 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 		}
 	}
 
+	pipe_config->limited_color_range =
+		intel_hdmi_limited_color_range(pipe_config, conn_state);
+
 	if (HAS_PCH_SPLIT(dev_priv) && !HAS_DDI(dev_priv))
 		pipe_config->has_pch_encoder = true;
 
-- 
cgit v1.2.3


From 60a02311cc588ae92b4732763650f187c506bc3a Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jul 2019 17:50:48 +0300
Subject: drm/i915: Don't look at unrelated PIPECONF bits for interlaced
 readout
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since HSW the PIPECONF progressive vs. interlaced selection is done
with just two bits instead of the earlier three. Let's not look at the
extra bit on HSW+. Also gen2 doesn't support interlaced displays at all.

This is actually fine as is currently because the extra bit is mbz (as
are all three bits on gen2). But just to avoid mishaps in the future
if the bits get reused let's only look at what's properly defined.

v2: constify crtc_state

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190718145053.25808-8-ville.syrjala@linux.intel.com
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index e0033d99f6e3..44460bf70d6b 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -8203,6 +8203,21 @@ static void intel_set_pipe_src_size(const struct intel_crtc_state *crtc_state)
 		   (crtc_state->pipe_src_h - 1));
 }
 
+static bool intel_pipe_is_interlaced(const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
+
+	if (IS_GEN(dev_priv, 2))
+		return false;
+
+	if (INTEL_GEN(dev_priv) >= 9 ||
+	    IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv))
+		return I915_READ(PIPECONF(cpu_transcoder)) & PIPECONF_INTERLACE_MASK_HSW;
+	else
+		return I915_READ(PIPECONF(cpu_transcoder)) & PIPECONF_INTERLACE_MASK;
+}
+
 static void intel_get_pipe_timings(struct intel_crtc *crtc,
 				   struct intel_crtc_state *pipe_config)
 {
@@ -8241,7 +8256,7 @@ static void intel_get_pipe_timings(struct intel_crtc *crtc,
 	pipe_config->base.adjusted_mode.crtc_vsync_start = (tmp & 0xffff) + 1;
 	pipe_config->base.adjusted_mode.crtc_vsync_end = ((tmp >> 16) & 0xffff) + 1;
 
-	if (I915_READ(PIPECONF(cpu_transcoder)) & PIPECONF_INTERLACE_MASK) {
+	if (intel_pipe_is_interlaced(pipe_config)) {
 		pipe_config->base.adjusted_mode.flags |= DRM_MODE_FLAG_INTERLACE;
 		pipe_config->base.adjusted_mode.crtc_vtotal += 1;
 		pipe_config->base.adjusted_mode.crtc_vblank_end += 1;
-- 
cgit v1.2.3


From b10d1173eecf811d5293c5097f1025fc20915171 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jul 2019 17:50:49 +0300
Subject: drm/i915: Simplify intel_get_crtc_ycbcr_config()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make intel_get_crtc_ycbcr_config() simpler and rename it
to bdw_get_pipemisc_output_format() to better reflect what
it does.

Also toss in some comments to document that the 4:2:0 PIPECONF
bits are glk+ only. They are mbz on earlier platforms so reading
them unconditionally is safe however.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190718145053.25808-9-ville.syrjala@linux.intel.com
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 71 +++++++++++++---------------
 drivers/gpu/drm/i915/i915_reg.h              |  4 +-
 2 files changed, 34 insertions(+), 41 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 44460bf70d6b..95a63acc43a3 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -8727,47 +8727,24 @@ static void chv_crtc_clock_get(struct intel_crtc *crtc,
 	pipe_config->port_clock = chv_calc_dpll_params(refclk, &clock);
 }
 
-static void intel_get_crtc_ycbcr_config(struct intel_crtc *crtc,
-					struct intel_crtc_state *pipe_config)
+static enum intel_output_format
+bdw_get_pipemisc_output_format(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	enum intel_output_format output = INTEL_OUTPUT_FORMAT_RGB;
-
-	pipe_config->lspcon_downsampling = false;
-
-	if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9) {
-		u32 tmp = I915_READ(PIPEMISC(crtc->pipe));
-
-		if (tmp & PIPEMISC_OUTPUT_COLORSPACE_YUV) {
-			bool ycbcr420_enabled = tmp & PIPEMISC_YUV420_ENABLE;
-			bool blend = tmp & PIPEMISC_YUV420_MODE_FULL_BLEND;
-
-			if (ycbcr420_enabled) {
-				/* We support 4:2:0 in full blend mode only */
-				if (!blend)
-					output = INTEL_OUTPUT_FORMAT_INVALID;
-				else if (!(IS_GEMINILAKE(dev_priv) ||
-					   INTEL_GEN(dev_priv) >= 10))
-					output = INTEL_OUTPUT_FORMAT_INVALID;
-				else
-					output = INTEL_OUTPUT_FORMAT_YCBCR420;
-			} else {
-				/*
-				 * Currently there is no interface defined to
-				 * check user preference between RGB/YCBCR444
-				 * or YCBCR420. So the only possible case for
-				 * YCBCR444 usage is driving YCBCR420 output
-				 * with LSPCON, when pipe is configured for
-				 * YCBCR444 output and LSPCON takes care of
-				 * downsampling it.
-				 */
-				pipe_config->lspcon_downsampling = true;
-				output = INTEL_OUTPUT_FORMAT_YCBCR444;
-			}
-		}
-	}
+	u32 tmp;
+
+	tmp = I915_READ(PIPEMISC(crtc->pipe));
 
-	pipe_config->output_format = output;
+	if (tmp & PIPEMISC_YUV420_ENABLE) {
+		/* We support 4:2:0 in full blend mode only */
+		WARN_ON((tmp & PIPEMISC_YUV420_MODE_FULL_BLEND) == 0);
+
+		return INTEL_OUTPUT_FORMAT_YCBCR420;
+	} else if (tmp & PIPEMISC_OUTPUT_COLORSPACE_YUV) {
+		return INTEL_OUTPUT_FORMAT_YCBCR444;
+	} else {
+		return INTEL_OUTPUT_FORMAT_RGB;
+	}
 }
 
 static void i9xx_get_pipe_color_config(struct intel_crtc_state *crtc_state)
@@ -10462,7 +10439,23 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 	}
 
 	intel_get_pipe_src_size(crtc, pipe_config);
-	intel_get_crtc_ycbcr_config(crtc, pipe_config);
+
+	if (INTEL_GEN(dev_priv) >= 9 || IS_BROADWELL(dev_priv)) {
+		pipe_config->output_format =
+			bdw_get_pipemisc_output_format(crtc);
+
+		/*
+		 * Currently there is no interface defined to
+		 * check user preference between RGB/YCBCR444
+		 * or YCBCR420. So the only possible case for
+		 * YCBCR444 usage is driving YCBCR420 output
+		 * with LSPCON, when pipe is configured for
+		 * YCBCR444 output and LSPCON takes care of
+		 * downsampling it.
+		 */
+		pipe_config->lspcon_downsampling =
+			pipe_config->output_format == INTEL_OUTPUT_FORMAT_YCBCR444;
+	}
 
 	pipe_config->gamma_mode = I915_READ(GAMMA_MODE(crtc->pipe));
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 2a1a1e84d1bc..3cc1baa0b915 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5775,8 +5775,8 @@ enum {
 
 #define _PIPE_MISC_A			0x70030
 #define _PIPE_MISC_B			0x71030
-#define   PIPEMISC_YUV420_ENABLE	(1 << 27)
-#define   PIPEMISC_YUV420_MODE_FULL_BLEND (1 << 26)
+#define   PIPEMISC_YUV420_ENABLE	(1 << 27) /* glk+ */
+#define   PIPEMISC_YUV420_MODE_FULL_BLEND (1 << 26) /* glk+ */
 #define   PIPEMISC_HDR_MODE_PRECISION	(1 << 23) /* icl+ */
 #define   PIPEMISC_OUTPUT_COLORSPACE_YUV  (1 << 11)
 #define   PIPEMISC_DITHER_BPC_MASK	(7 << 5)
-- 
cgit v1.2.3


From ac0f01cee94702d49aad3ff4d0607024fa34c9dd Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jul 2019 17:50:50 +0300
Subject: drm/i915: Add PIPECONF YCbCr 4:4:4 programming for HSW
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On HSW the pipe colorspace is configured via PIPECONF
(as opposed to PIPEMISC in BDW+). Let's configure+readout
that stuff correctly.

Enabling YCbCr 4:4:4 output will now be a simple matter of
setting crtc_state->output_format appropriately in the encoder
.compute_config().

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190718145053.25808-10-ville.syrjala@linux.intel.com
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 13 ++++++++++++-
 drivers/gpu/drm/i915/i915_reg.h              |  1 +
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 95a63acc43a3..1bd91a061a0a 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -9444,6 +9444,10 @@ static void haswell_set_pipeconf(const struct intel_crtc_state *crtc_state)
 	else
 		val |= PIPECONF_PROGRESSIVE;
 
+	if (IS_HASWELL(dev_priv) &&
+	    crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB)
+		val |= PIPECONF_OUTPUT_COLORSPACE_YUV_HSW;
+
 	I915_WRITE(PIPECONF(cpu_transcoder), val);
 	POSTING_READ(PIPECONF(cpu_transcoder));
 }
@@ -10440,7 +10444,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 
 	intel_get_pipe_src_size(crtc, pipe_config);
 
-	if (INTEL_GEN(dev_priv) >= 9 || IS_BROADWELL(dev_priv)) {
+	if (IS_HASWELL(dev_priv)) {
+		u32 tmp = I915_READ(PIPECONF(pipe_config->cpu_transcoder));
+
+		if (tmp & PIPECONF_OUTPUT_COLORSPACE_YUV_HSW)
+			pipe_config->output_format = INTEL_OUTPUT_FORMAT_YCBCR444;
+		else
+			pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB;
+	} else {
 		pipe_config->output_format =
 			bdw_get_pipemisc_output_format(crtc);
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 3cc1baa0b915..6f2eda76da4a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5683,6 +5683,7 @@ enum {
 #define   PIPECONF_CXSR_DOWNCLOCK	(1 << 16)
 #define   PIPECONF_EDP_RR_MODE_SWITCH_VLV	(1 << 14)
 #define   PIPECONF_COLOR_RANGE_SELECT	(1 << 13)
+#define   PIPECONF_OUTPUT_COLORSPACE_YUV_HSW	(1 << 11) /* hsw only */
 #define   PIPECONF_BPC_MASK	(0x7 << 5)
 #define   PIPECONF_8BPC		(0 << 5)
 #define   PIPECONF_10BPC	(1 << 5)
-- 
cgit v1.2.3


From 174d12bcc0874d78ad7fd63ae769cac864ee9f4f Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jul 2019 17:50:51 +0300
Subject: drm/i915: Document ILK+ pipe csc matrix better
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add comments to explain the ilk pipe csc operation a bit better.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190718145053.25808-11-ville.syrjala@linux.intel.com
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
---
 drivers/gpu/drm/i915/display/intel_color.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 318308dc136c..de31b4c251fa 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -42,6 +42,21 @@
 
 #define LEGACY_LUT_LENGTH		256
 
+/*
+ * ILK+ csc matrix:
+ *
+ * |R/Cr|   | c0 c1 c2 |   ( |R/Cr|   |preoff0| )   |postoff0|
+ * |G/Y | = | c3 c4 c5 | x ( |G/Y | + |preoff1| ) + |postoff1|
+ * |B/Cb|   | c6 c7 c8 |   ( |B/Cb|   |preoff2| )   |postoff2|
+ *
+ * ILK/SNB don't have explicit post offsets, and instead
+ * CSC_MODE_YUV_TO_RGB and CSC_BLACK_SCREEN_OFFSET are used:
+ *  CSC_MODE_YUV_TO_RGB=0 + CSC_BLACK_SCREEN_OFFSET=0 -> 1/2, 0, 1/2
+ *  CSC_MODE_YUV_TO_RGB=0 + CSC_BLACK_SCREEN_OFFSET=1 -> 1/2, 1/16, 1/2
+ *  CSC_MODE_YUV_TO_RGB=1 + CSC_BLACK_SCREEN_OFFSET=0 -> 0, 0, 0
+ *  CSC_MODE_YUV_TO_RGB=1 + CSC_BLACK_SCREEN_OFFSET=1 -> 1/16, 1/16, 1/16
+ */
+
 /*
  * Extract the CSC coefficient from a CTM coefficient (in U32.32 fixed point
  * format). This macro takes the coefficient we want transformed and the
@@ -59,37 +74,38 @@
 
 #define ILK_CSC_POSTOFF_LIMITED_RANGE (16 * (1 << 12) / 255)
 
+/* Nop pre/post offsets */
 static const u16 ilk_csc_off_zero[3] = {};
 
+/* Identity matrix */
 static const u16 ilk_csc_coeff_identity[9] = {
 	ILK_CSC_COEFF_1_0, 0, 0,
 	0, ILK_CSC_COEFF_1_0, 0,
 	0, 0, ILK_CSC_COEFF_1_0,
 };
 
+/* Limited range RGB post offsets */
 static const u16 ilk_csc_postoff_limited_range[3] = {
 	ILK_CSC_POSTOFF_LIMITED_RANGE,
 	ILK_CSC_POSTOFF_LIMITED_RANGE,
 	ILK_CSC_POSTOFF_LIMITED_RANGE,
 };
 
+/* Full range RGB -> limited range RGB matrix */
 static const u16 ilk_csc_coeff_limited_range[9] = {
 	ILK_CSC_COEFF_LIMITED_RANGE, 0, 0,
 	0, ILK_CSC_COEFF_LIMITED_RANGE, 0,
 	0, 0, ILK_CSC_COEFF_LIMITED_RANGE,
 };
 
-/*
- * These values are direct register values specified in the Bspec,
- * for RGB->YUV conversion matrix (colorspace BT709)
- */
+/* BT.709 full range RGB -> limited range YCbCr matrix */
 static const u16 ilk_csc_coeff_rgb_to_ycbcr[9] = {
 	0x1e08, 0x9cc0, 0xb528,
 	0x2ba8, 0x09d8, 0x37e8,
 	0xbce8, 0x9ad8, 0x1e08,
 };
 
-/* Post offset values for RGB->YCBCR conversion */
+/* Limited range YCbCr post offsets */
 static const u16 ilk_csc_postoff_rgb_to_ycbcr[3] = {
 	0x0800, 0x0100, 0x0800,
 };
-- 
cgit v1.2.3


From af28cc4c289600ad05da85e466517757a26ce216 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jul 2019 17:50:52 +0300
Subject: drm/i915: Set up ILK/SNB csc unit properly for YCbCr output
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prepare the pipe csc for YCbCr output on ilk/snb. The main difference
to IVB+ is the lack of explicit post offsets, and instead we must
configure the CSC info RGB->YUV mode (which takes care of offsetting
Cb/Cr properly) and enable the "black screen offset" bit to add the
required offset to Y.

And while at it throw some comments around the bit defines to
document which platforms have which bits.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190718145053.25808-12-ville.syrjala@linux.intel.com
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
---
 drivers/gpu/drm/i915/display/intel_color.c | 25 ++++++++++++++++++++-----
 drivers/gpu/drm/i915/i915_reg.h            | 10 +++++-----
 2 files changed, 25 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index de31b4c251fa..2de640bd3e73 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1213,6 +1213,21 @@ static u32 ilk_gamma_mode(const struct intel_crtc_state *crtc_state)
 		return GAMMA_MODE_MODE_10BIT;
 }
 
+static u32 ilk_csc_mode(const struct intel_crtc_state *crtc_state)
+{
+	/*
+	 * CSC comes after the LUT in RGB->YCbCr mode.
+	 * RGB->YCbCr needs the limited range offsets added to
+	 * the output. RGB limited range output is handled by
+	 * the hw automagically elsewhere.
+	 */
+	if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB)
+		return CSC_BLACK_SCREEN_OFFSET;
+
+	return CSC_MODE_YUV_TO_RGB |
+		CSC_POSITION_BEFORE_GAMMA;
+}
+
 static int ilk_color_check(struct intel_crtc_state *crtc_state)
 {
 	int ret;
@@ -1226,15 +1241,15 @@ static int ilk_color_check(struct intel_crtc_state *crtc_state)
 		!crtc_state->c8_planes;
 
 	/*
-	 * We don't expose the ctm on ilk/snb currently,
-	 * nor do we enable YCbCr output. Also RGB limited
-	 * range output is handled by the hw automagically.
+	 * We don't expose the ctm on ilk/snb currently, also RGB
+	 * limited range output is handled by the hw automagically.
 	 */
-	crtc_state->csc_enable = false;
+	crtc_state->csc_enable =
+		crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB;
 
 	crtc_state->gamma_mode = ilk_gamma_mode(crtc_state);
 
-	crtc_state->csc_mode = 0;
+	crtc_state->csc_mode = ilk_csc_mode(crtc_state);
 
 	ret = intel_color_add_affected_planes(crtc_state);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6f2eda76da4a..90c45fee9ce7 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -10249,11 +10249,11 @@ enum skl_power_gate {
 #define _PIPE_A_CSC_COEFF_BV	0x49024
 
 #define _PIPE_A_CSC_MODE	0x49028
-#define  ICL_CSC_ENABLE			(1 << 31)
-#define  ICL_OUTPUT_CSC_ENABLE		(1 << 30)
-#define  CSC_BLACK_SCREEN_OFFSET	(1 << 2)
-#define  CSC_POSITION_BEFORE_GAMMA	(1 << 1)
-#define  CSC_MODE_YUV_TO_RGB		(1 << 0)
+#define  ICL_CSC_ENABLE			(1 << 31) /* icl+ */
+#define  ICL_OUTPUT_CSC_ENABLE		(1 << 30) /* icl+ */
+#define  CSC_BLACK_SCREEN_OFFSET	(1 << 2) /* ilk/snb */
+#define  CSC_POSITION_BEFORE_GAMMA	(1 << 1) /* pre-glk */
+#define  CSC_MODE_YUV_TO_RGB		(1 << 0) /* ilk/snb */
 
 #define _PIPE_A_CSC_PREOFF_HI	0x49030
 #define _PIPE_A_CSC_PREOFF_ME	0x49034
-- 
cgit v1.2.3


From d1844606fd63af1994e153a8607d4b13709bc395 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jul 2019 17:50:53 +0300
Subject: drm/i915: Add PIPECONF YCbCr 4:4:4 programming for ILK-IVB
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On ILK-IVB the pipe colorspace is configured via PIPECONF
(as opposed to PIPEMISC in BDW+). Let's configure+readout
that stuff correctly.

Enabling YCbCr 4:4:4 output will now be a simple matter of
setting crtc_state->output_format appropriately in the encoder
.compute_config(). However, when we do that we must be
aware of the fact that YCbCr DP output doesn't seem to work
on ILK (resulting image is totally garbled), but on SNB+
it works fine. However HDMI YCbCr output does work correctly
even on ILK.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190718145053.25808-13-ville.syrjala@linux.intel.com
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 21 ++++++++++++++++++++-
 drivers/gpu/drm/i915/i915_reg.h              |  4 ++++
 2 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 1bd91a061a0a..f5f655cde43a 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -9420,9 +9420,19 @@ static void ironlake_set_pipeconf(const struct intel_crtc_state *crtc_state)
 	else
 		val |= PIPECONF_PROGRESSIVE;
 
+	/*
+	 * This would end up with an odd purple hue over
+	 * the entire display. Make sure we don't do it.
+	 */
+	WARN_ON(crtc_state->limited_color_range &&
+		crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB);
+
 	if (crtc_state->limited_color_range)
 		val |= PIPECONF_COLOR_RANGE_SELECT;
 
+	if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB)
+		val |= PIPECONF_OUTPUT_COLORSPACE_YUV709;
+
 	val |= PIPECONF_GAMMA_MODE(crtc_state->gamma_mode);
 
 	I915_WRITE(PIPECONF(pipe), val);
@@ -9959,7 +9969,6 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 	if (!wakeref)
 		return false;
 
-	pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB;
 	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = NULL;
 
@@ -9988,6 +9997,16 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 	if (tmp & PIPECONF_COLOR_RANGE_SELECT)
 		pipe_config->limited_color_range = true;
 
+	switch (tmp & PIPECONF_OUTPUT_COLORSPACE_MASK) {
+	case PIPECONF_OUTPUT_COLORSPACE_YUV601:
+	case PIPECONF_OUTPUT_COLORSPACE_YUV709:
+		pipe_config->output_format = INTEL_OUTPUT_FORMAT_YCBCR444;
+		break;
+	default:
+		pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB;
+		break;
+	}
+
 	pipe_config->gamma_mode = (tmp & PIPECONF_GAMMA_MODE_MASK_ILK) >>
 		PIPECONF_GAMMA_MODE_SHIFT;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 90c45fee9ce7..acbda6d89a9b 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5683,6 +5683,10 @@ enum {
 #define   PIPECONF_CXSR_DOWNCLOCK	(1 << 16)
 #define   PIPECONF_EDP_RR_MODE_SWITCH_VLV	(1 << 14)
 #define   PIPECONF_COLOR_RANGE_SELECT	(1 << 13)
+#define   PIPECONF_OUTPUT_COLORSPACE_MASK	(3 << 11) /* ilk-ivb */
+#define   PIPECONF_OUTPUT_COLORSPACE_RGB	(0 << 11) /* ilk-ivb */
+#define   PIPECONF_OUTPUT_COLORSPACE_YUV601	(1 << 11) /* ilk-ivb */
+#define   PIPECONF_OUTPUT_COLORSPACE_YUV709	(2 << 11) /* ilk-ivb */
 #define   PIPECONF_OUTPUT_COLORSPACE_YUV_HSW	(1 << 11) /* hsw only */
 #define   PIPECONF_BPC_MASK	(0x7 << 5)
 #define   PIPECONF_8BPC		(0 << 5)
-- 
cgit v1.2.3


From 601734f7aabd46d3a988554e59908d9de7f8b013 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Fri, 13 Sep 2019 08:51:37 +0100
Subject: drm/i915/tgl: s/ss/eu fuse reading support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Gen12 has dual-subslices (DSS), which compared to gen11 subslices have
some duplicated resources/paths. Although DSS behave similarly to 2
subslices, instead of splitting this and presenting userspace with bits
not directly representative of hardware resources, present userspace
with a subslice_mask made up of DSS bits instead.

v2: GEM_BUG_ON on mask size (Lionel)

Bspec: 29547
Bspec: 12247
Cc: Kelvin Gardiner <kelvin.gardiner@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
CC: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com> #v1
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: James Ausmus <james.ausmus@intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Sudeep Dutt <sudeep.dutt@intel.com>
Signed-off-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190913075137.18476-2-chris@chris-wilson.co.uk
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_sseu.h     |  9 +---
 drivers/gpu/drm/i915/i915_debugfs.c      |  3 +-
 drivers/gpu/drm/i915/i915_reg.h          |  2 +
 drivers/gpu/drm/i915/intel_device_info.c | 83 ++++++++++++++++++++++++--------
 include/uapi/drm/i915_drm.h              |  6 ++-
 5 files changed, 72 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h
index 4070f6ff1db6..d1d225204f09 100644
--- a/drivers/gpu/drm/i915/gt/intel_sseu.h
+++ b/drivers/gpu/drm/i915/gt/intel_sseu.h
@@ -18,12 +18,13 @@ struct drm_i915_private;
 #define GEN_MAX_SUBSLICES	(8) /* ICL upper bound */
 #define GEN_SSEU_STRIDE(max_entries) DIV_ROUND_UP(max_entries, BITS_PER_BYTE)
 #define GEN_MAX_SUBSLICE_STRIDE GEN_SSEU_STRIDE(GEN_MAX_SUBSLICES)
-#define GEN_MAX_EUS		(10) /* HSW upper bound */
+#define GEN_MAX_EUS		(16) /* TGL upper bound */
 #define GEN_MAX_EU_STRIDE GEN_SSEU_STRIDE(GEN_MAX_EUS)
 
 struct sseu_dev_info {
 	u8 slice_mask;
 	u8 subslice_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICE_STRIDE];
+	u8 eu_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICES * GEN_MAX_EU_STRIDE];
 	u16 eu_total;
 	u8 eu_per_subslice;
 	u8 min_eu_in_pool;
@@ -40,12 +41,6 @@ struct sseu_dev_info {
 
 	u8 ss_stride;
 	u8 eu_stride;
-
-	/* We don't have more than 8 eus per subslice at the moment and as we
-	 * store eus enabled using bits, no need to multiply by eus per
-	 * subslice.
-	 */
-	u8 eu_mask[GEN_MAX_SLICES * GEN_MAX_SUBSLICES];
 };
 
 /*
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 43db50095257..b5b449a88cf1 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3823,7 +3823,8 @@ static void gen10_sseu_device_status(struct drm_i915_private *dev_priv,
 		for (ss = 0; ss < info->sseu.max_subslices; ss++) {
 			unsigned int eu_cnt;
 
-			if (!(s_reg[s] & (GEN9_PGCTL_SS_ACK(ss))))
+			if (info->sseu.has_subslice_pg &&
+			    !(s_reg[s] & (GEN9_PGCTL_SS_ACK(ss))))
 				/* skip disabled subslice */
 				continue;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index acbda6d89a9b..7c64768976ac 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2956,6 +2956,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 #define GEN11_GT_SUBSLICE_DISABLE _MMIO(0x913C)
 
+#define GEN12_GT_DSS_ENABLE _MMIO(0x913C)
+
 #define GEN6_BSD_SLEEP_PSMI_CONTROL	_MMIO(0x12050)
 #define   GEN6_BSD_SLEEP_MSG_DISABLE	(1 << 0)
 #define   GEN6_BSD_SLEEP_FLUSH_DISABLE	(1 << 2)
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 728c881718a2..85e480bdc673 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -182,13 +182,69 @@ static u16 compute_eu_total(const struct sseu_dev_info *sseu)
 	return total;
 }
 
+static void gen11_compute_sseu_info(struct sseu_dev_info *sseu,
+				    u8 s_en, u32 ss_en, u16 eu_en)
+{
+	int s, ss;
+
+	/* ss_en represents entire subslice mask across all slices */
+	GEM_BUG_ON(sseu->max_slices * sseu->max_subslices >
+		   sizeof(ss_en) * BITS_PER_BYTE);
+
+	for (s = 0; s < sseu->max_slices; s++) {
+		if ((s_en & BIT(s)) == 0)
+			continue;
+
+		sseu->slice_mask |= BIT(s);
+
+		intel_sseu_set_subslices(sseu, s, ss_en);
+
+		for (ss = 0; ss < sseu->max_subslices; ss++)
+			if (intel_sseu_has_subslice(sseu, s, ss))
+				sseu_set_eus(sseu, s, ss, eu_en);
+	}
+	sseu->eu_per_subslice = hweight16(eu_en);
+	sseu->eu_total = compute_eu_total(sseu);
+}
+
+static void gen12_sseu_info_init(struct drm_i915_private *dev_priv)
+{
+	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
+	u8 s_en;
+	u32 dss_en;
+	u16 eu_en = 0;
+	u8 eu_en_fuse;
+	int eu;
+
+	/*
+	 * Gen12 has Dual-Subslices, which behave similarly to 2 gen11 SS.
+	 * Instead of splitting these, provide userspace with an array
+	 * of DSS to more closely represent the hardware resource.
+	 */
+	intel_sseu_set_info(sseu, 1, 6, 16);
+
+	s_en = I915_READ(GEN11_GT_SLICE_ENABLE) & GEN11_GT_S_ENA_MASK;
+
+	dss_en = I915_READ(GEN12_GT_DSS_ENABLE);
+
+	/* one bit per pair of EUs */
+	eu_en_fuse = ~(I915_READ(GEN11_EU_DISABLE) & GEN11_EU_DIS_MASK);
+	for (eu = 0; eu < sseu->max_eus_per_subslice / 2; eu++)
+		if (eu_en_fuse & BIT(eu))
+			eu_en |= BIT(eu * 2) | BIT(eu * 2 + 1);
+
+	gen11_compute_sseu_info(sseu, s_en, dss_en, eu_en);
+
+	/* TGL only supports slice-level power gating */
+	sseu->has_slice_pg = 1;
+}
+
 static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
 {
 	struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
 	u8 s_en;
-	u32 ss_en, ss_en_mask;
+	u32 ss_en;
 	u8 eu_en;
-	int s;
 
 	if (IS_ELKHARTLAKE(dev_priv))
 		intel_sseu_set_info(sseu, 1, 4, 8);
@@ -197,26 +253,9 @@ static void gen11_sseu_info_init(struct drm_i915_private *dev_priv)
 
 	s_en = I915_READ(GEN11_GT_SLICE_ENABLE) & GEN11_GT_S_ENA_MASK;
 	ss_en = ~I915_READ(GEN11_GT_SUBSLICE_DISABLE);
-	ss_en_mask = BIT(sseu->max_subslices) - 1;
 	eu_en = ~(I915_READ(GEN11_EU_DISABLE) & GEN11_EU_DIS_MASK);
 
-	for (s = 0; s < sseu->max_slices; s++) {
-		if (s_en & BIT(s)) {
-			int ss_idx = sseu->max_subslices * s;
-			int ss;
-
-			sseu->slice_mask |= BIT(s);
-
-			intel_sseu_set_subslices(sseu, s, (ss_en >> ss_idx) &
-							  ss_en_mask);
-
-			for (ss = 0; ss < sseu->max_subslices; ss++)
-				if (intel_sseu_has_subslice(sseu, s, ss))
-					sseu_set_eus(sseu, s, ss, eu_en);
-		}
-	}
-	sseu->eu_per_subslice = hweight8(eu_en);
-	sseu->eu_total = compute_eu_total(sseu);
+	gen11_compute_sseu_info(sseu, s_en, ss_en, eu_en);
 
 	/* ICL has no power gating restrictions. */
 	sseu->has_slice_pg = 1;
@@ -955,8 +994,10 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 		gen9_sseu_info_init(dev_priv);
 	else if (IS_GEN(dev_priv, 10))
 		gen10_sseu_info_init(dev_priv);
-	else if (INTEL_GEN(dev_priv) >= 11)
+	else if (IS_GEN(dev_priv, 11))
 		gen11_sseu_info_init(dev_priv);
+	else if (INTEL_GEN(dev_priv) >= 12)
+		gen12_sseu_info_init(dev_priv);
 
 	if (IS_GEN(dev_priv, 6) && intel_vtd_active()) {
 		DRM_INFO("Disabling ppGTT for VT-d support\n");
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 469dc512cca3..30c542144016 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -2033,8 +2033,10 @@ struct drm_i915_query {
  *           (data[X / 8] >> (X % 8)) & 1
  *
  * - the subslice mask for each slice with one bit per subslice telling
- *   whether a subslice is available. The availability of subslice Y in slice
- *   X can be queried with the following formula :
+ *   whether a subslice is available. Gen12 has dual-subslices, which are
+ *   similar to two gen11 subslices. For gen12, this array represents dual-
+ *   subslices. The availability of subslice Y in slice X can be queried
+ *   with the following formula :
  *
  *           (data[subslice_offset +
  *                 X * subslice_stride +
-- 
cgit v1.2.3


From d4f4de5e5ef8efde85febb6876cd3c8ab1631999 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 15 Sep 2019 12:12:39 -0400
Subject: Fix the locking in dcache_readdir() and friends

There are two problems in dcache_readdir() - one is that lockless traversal
of the list needs non-trivial cooperation of d_alloc() (at least a switch
to list_add_rcu(), and probably more than just that) and another is that
it assumes that no removal will happen without the directory locked exclusive.
Said assumption had always been there, never had been stated explicitly and
is violated by several places in the kernel (devpts and selinuxfs).

        * replacement of next_positive() with different calling conventions:
it returns struct list_head * instead of struct dentry *; the latter is
passed in and out by reference, grabbing the result and dropping the original
value.
        * scan is under ->d_lock.  If we run out of timeslice, cursor is moved
after the last position we'd reached and we reschedule; then the scan continues
from that place.  To avoid livelocks between multiple lseek() (with cursors
getting moved past each other, never reaching the real entries) we always
skip the cursors, need_resched() or not.
        * returned list_head * is either ->d_child of dentry we'd found or
->d_subdirs of parent (if we got to the end of the list).
        * dcache_readdir() and dcache_dir_lseek() switched to new helper.
dcache_readdir() always holds a reference to dentry passed to dir_emit() now.
Cursor is moved to just before the entry where dir_emit() has failed or into
the very end of the list, if we'd run out.
        * move_cursor() eliminated - it had sucky calling conventions and
after fixing that it became simply list_move() (in lseek and scan_positives)
or list_move_tail() (in readdir).

        All operations with the list are under ->d_lock now, and we do not
depend upon having all file removals done with parent locked exclusive
anymore.

Cc: stable@vger.kernel.org
Reported-by: "zhengbin (A)" <zhengbin13@huawei.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/libfs.c | 134 +++++++++++++++++++++++++++++++------------------------------
 1 file changed, 69 insertions(+), 65 deletions(-)

diff --git a/fs/libfs.c b/fs/libfs.c
index c9b2850c0f7c..8e023b08a240 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -89,58 +89,47 @@ int dcache_dir_close(struct inode *inode, struct file *file)
 EXPORT_SYMBOL(dcache_dir_close);
 
 /* parent is locked at least shared */
-static struct dentry *next_positive(struct dentry *parent,
-				    struct list_head *from,
-				    int count)
+/*
+ * Returns an element of siblings' list.
+ * We are looking for <count>th positive after <p>; if
+ * found, dentry is grabbed and passed to caller via *<res>.
+ * If no such element exists, the anchor of list is returned
+ * and *<res> is set to NULL.
+ */
+static struct list_head *scan_positives(struct dentry *cursor,
+					struct list_head *p,
+					loff_t count,
+					struct dentry **res)
 {
-	unsigned *seq = &parent->d_inode->i_dir_seq, n;
-	struct dentry *res;
-	struct list_head *p;
-	bool skipped;
-	int i;
+	struct dentry *dentry = cursor->d_parent, *found = NULL;
 
-retry:
-	i = count;
-	skipped = false;
-	n = smp_load_acquire(seq) & ~1;
-	res = NULL;
-	rcu_read_lock();
-	for (p = from->next; p != &parent->d_subdirs; p = p->next) {
+	spin_lock(&dentry->d_lock);
+	while ((p = p->next) != &dentry->d_subdirs) {
 		struct dentry *d = list_entry(p, struct dentry, d_child);
-		if (!simple_positive(d)) {
-			skipped = true;
-		} else if (!--i) {
-			res = d;
-			break;
+		// we must at least skip cursors, to avoid livelocks
+		if (d->d_flags & DCACHE_DENTRY_CURSOR)
+			continue;
+		if (simple_positive(d) && !--count) {
+			spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
+			if (simple_positive(d))
+				found = dget_dlock(d);
+			spin_unlock(&d->d_lock);
+			if (likely(found))
+				break;
+			count = 1;
+		}
+		if (need_resched()) {
+			list_move(&cursor->d_child, p);
+			p = &cursor->d_child;
+			spin_unlock(&dentry->d_lock);
+			cond_resched();
+			spin_lock(&dentry->d_lock);
 		}
 	}
-	rcu_read_unlock();
-	if (skipped) {
-		smp_rmb();
-		if (unlikely(*seq != n))
-			goto retry;
-	}
-	return res;
-}
-
-static void move_cursor(struct dentry *cursor, struct list_head *after)
-{
-	struct dentry *parent = cursor->d_parent;
-	unsigned n, *seq = &parent->d_inode->i_dir_seq;
-	spin_lock(&parent->d_lock);
-	for (;;) {
-		n = *seq;
-		if (!(n & 1) && cmpxchg(seq, n, n + 1) == n)
-			break;
-		cpu_relax();
-	}
-	__list_del(cursor->d_child.prev, cursor->d_child.next);
-	if (after)
-		list_add(&cursor->d_child, after);
-	else
-		list_add_tail(&cursor->d_child, &parent->d_subdirs);
-	smp_store_release(seq, n + 2);
-	spin_unlock(&parent->d_lock);
+	spin_unlock(&dentry->d_lock);
+	dput(*res);
+	*res = found;
+	return p;
 }
 
 loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
@@ -158,17 +147,28 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 			return -EINVAL;
 	}
 	if (offset != file->f_pos) {
+		struct dentry *cursor = file->private_data;
+		struct dentry *to = NULL;
+		struct list_head *p;
+
 		file->f_pos = offset;
-		if (file->f_pos >= 2) {
-			struct dentry *cursor = file->private_data;
-			struct dentry *to;
-			loff_t n = file->f_pos - 2;
-
-			inode_lock_shared(dentry->d_inode);
-			to = next_positive(dentry, &dentry->d_subdirs, n);
-			move_cursor(cursor, to ? &to->d_child : NULL);
-			inode_unlock_shared(dentry->d_inode);
+		inode_lock_shared(dentry->d_inode);
+
+		if (file->f_pos > 2) {
+			p = scan_positives(cursor, &dentry->d_subdirs,
+					   file->f_pos - 2, &to);
+			spin_lock(&dentry->d_lock);
+			list_move(&cursor->d_child, p);
+			spin_unlock(&dentry->d_lock);
+		} else {
+			spin_lock(&dentry->d_lock);
+			list_del_init(&cursor->d_child);
+			spin_unlock(&dentry->d_lock);
 		}
+
+		dput(to);
+
+		inode_unlock_shared(dentry->d_inode);
 	}
 	return offset;
 }
@@ -190,25 +190,29 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct dentry *cursor = file->private_data;
-	struct list_head *p = &cursor->d_child;
-	struct dentry *next;
-	bool moved = false;
+	struct list_head *anchor = &dentry->d_subdirs;
+	struct dentry *next = NULL;
+	struct list_head *p;
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
 
 	if (ctx->pos == 2)
-		p = &dentry->d_subdirs;
-	while ((next = next_positive(dentry, p, 1)) != NULL) {
+		p = anchor;
+	else
+		p = &cursor->d_child;
+
+	while ((p = scan_positives(cursor, p, 1, &next)) != anchor) {
 		if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
 			      d_inode(next)->i_ino, dt_type(d_inode(next))))
 			break;
-		moved = true;
-		p = &next->d_child;
 		ctx->pos++;
 	}
-	if (moved)
-		move_cursor(cursor, p);
+	spin_lock(&dentry->d_lock);
+	list_move_tail(&cursor->d_child, p);
+	spin_unlock(&dentry->d_lock);
+	dput(next);
+
 	return 0;
 }
 EXPORT_SYMBOL(dcache_readdir);
-- 
cgit v1.2.3


From bf93b7246548289a797798051198c9664af2931c Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Sun, 22 Sep 2019 01:40:52 +0530
Subject: drm/i915/color: Fix formatting issues

Fixed few formatting issues in multi-segmented load_lut().

v3: -style nitting [Jani]
    -balanced parentheses moved from patch 2 to 1 [Jani]
    -subject prefix change [Jani]
    -added commit message [Jani]
v4: -rearranged INDEX register write in ilk_read_luts()

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1569096654-24433-2-git-send-email-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 40 ++++++++++++++----------------
 1 file changed, 19 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 2de640bd3e73..91435ba426d0 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -823,11 +823,11 @@ icl_program_gamma_superfine_segment(const struct intel_crtc_state *crtc_state)
 	u32 i;
 
 	/*
-	 * Every entry in the multi-segment LUT is corresponding to a superfine
-	 * segment step which is 1/(8 * 128 * 256).
+	 * Program Super Fine segment (let's call it seg1)...
 	 *
-	 * Superfine segment has 9 entries, corresponding to values
-	 * 0, 1/(8 * 128 * 256), 2/(8 * 128 * 256) .... 8/(8 * 128 * 256).
+	 * Super Fine segment's step is 1/(8 * 128 * 256) and it has
+	 * 9 entries, corresponding to values 0, 1/(8 * 128 * 256),
+	 * 2/(8 * 128 * 256) ... 8/(8 * 128 * 256).
 	 */
 	I915_WRITE(PREC_PAL_MULTI_SEG_INDEX(pipe), PAL_PREC_AUTO_INCREMENT);
 
@@ -853,17 +853,17 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 	u32 i;
 
 	/*
-	 *
 	 * Program Fine segment (let's call it seg2)...
 	 *
-	 * Fine segment's step is 1/(128 * 256) ie 1/(128 * 256),  2/(128*256)
-	 * ... 256/(128*256). So in order to program fine segment of LUT we
-	 * need to pick every 8'th entry in LUT, and program 256 indexes.
+	 * Fine segment's step is 1/(128 * 256) i.e. 1/(128 * 256), 2/(128 * 256)
+	 * ... 256/(128 * 256). So in order to program fine segment of LUT we
+	 * need to pick every 8th entry in the LUT, and program 256 indexes.
 	 *
 	 * PAL_PREC_INDEX[0] and PAL_PREC_INDEX[1] map to seg2[1],
-	 * with seg2[0] being unused by the hardware.
+	 * seg2[0] being unused by the hardware.
 	 */
 	I915_WRITE(PREC_PAL_INDEX(pipe), PAL_PREC_AUTO_INCREMENT);
+
 	for (i = 1; i < 257; i++) {
 		entry = &lut[i * 8];
 		I915_WRITE(PREC_PAL_DATA(pipe), ilk_lut_12p4_ldw(entry));
@@ -873,8 +873,8 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 	/*
 	 * Program Coarse segment (let's call it seg3)...
 	 *
-	 * Coarse segment's starts from index 0 and it's step is 1/256 ie 0,
-	 * 1/256, 2/256 ...256/256. As per the description of each entry in LUT
+	 * Coarse segment starts from index 0 and it's step is 1/256 ie 0,
+	 * 1/256, 2/256 ... 256/256. As per the description of each entry in LUT
 	 * above, we need to pick every (8 * 128)th entry in LUT, and
 	 * program 256 of those.
 	 *
@@ -906,12 +906,10 @@ static void icl_load_luts(const struct intel_crtc_state *crtc_state)
 	case GAMMA_MODE_MODE_8BIT:
 		i9xx_load_luts(crtc_state);
 		break;
-
 	case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED:
 		icl_program_gamma_superfine_segment(crtc_state);
 		icl_program_gamma_multi_segment(crtc_state);
 		break;
-
 	default:
 		bdw_load_lut_10(crtc, gamma_lut, PAL_PREC_INDEX_VALUE(0));
 		ivb_load_lut_ext_max(crtc);
@@ -1743,9 +1741,6 @@ glk_read_lut_10(const struct intel_crtc_state *crtc_state, u32 prec_index)
 	struct drm_color_lut *blob_data;
 	u32 i, val;
 
-	I915_WRITE(PREC_PAL_INDEX(pipe), prec_index |
-		   PAL_PREC_AUTO_INCREMENT);
-
 	blob = drm_property_create_blob(&dev_priv->drm,
 					sizeof(struct drm_color_lut) * hw_lut_size,
 					NULL);
@@ -1754,6 +1749,9 @@ glk_read_lut_10(const struct intel_crtc_state *crtc_state, u32 prec_index)
 
 	blob_data = blob->data;
 
+	I915_WRITE(PREC_PAL_INDEX(pipe), prec_index |
+		   PAL_PREC_AUTO_INCREMENT);
+
 	for (i = 0; i < hw_lut_size; i++) {
 		val = I915_READ(PREC_PAL_DATA(pipe));
 
@@ -1819,16 +1817,16 @@ void intel_color_init(struct intel_crtc *crtc)
 		else
 			dev_priv->display.color_commit = ilk_color_commit;
 
-		if (INTEL_GEN(dev_priv) >= 11)
+		if (INTEL_GEN(dev_priv) >= 11) {
 			dev_priv->display.load_luts = icl_load_luts;
-		else if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv)) {
+		} else if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv)) {
 			dev_priv->display.load_luts = glk_load_luts;
 			dev_priv->display.read_luts = glk_read_luts;
-		} else if (INTEL_GEN(dev_priv) >= 8)
+		} else if (INTEL_GEN(dev_priv) >= 8) {
 			dev_priv->display.load_luts = bdw_load_luts;
-		else if (INTEL_GEN(dev_priv) >= 7)
+		} else if (INTEL_GEN(dev_priv) >= 7) {
 			dev_priv->display.load_luts = ivb_load_luts;
-		else {
+		} else {
 			dev_priv->display.load_luts = ilk_load_luts;
 			dev_priv->display.read_luts = ilk_read_luts;
 		}
-- 
cgit v1.2.3


From 84af7649188194a74cdd6437235a5e3c86108f0f Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Sun, 22 Sep 2019 01:40:53 +0530
Subject: drm/i915/color: Extract icl_read_luts()

For icl+, have hw read out to create hw blob of gamma
lut values. icl+ platforms supports multi segmented gamma
mode by default, add hw lut creation for this mode.

This will be used to validate gamma programming using dsb
(display state buffer) which is a tgl specific feature.

Major change done-removal of readouts of coarse and fine segments
because PAL_PREC_DATA register isn't giving propoer values.
State checker limited only to "fine segment"

v2: -readout code for multisegmented gamma has to come
     up with some intermediate entries that aren't preserved
     in hardware (Jani N)
    -linear interpolation (Ville)
    -moved common code to check gamma_enable to specific funcs,
     since icl doesn't support that
v3: -use u16 instead of __u16 [Jani N]
    -used single lut [Jani N]
    -improved and more readable for loops [Jani N]
    -read values directly to actual locations and then fill gaps [Jani N]
    -moved cleaning to patch 1 [Jani N]
    -renamed icl_read_lut_multi_seg() to icl_read_lut_multi_segment to
     make it similar to icl_load_luts()
    -renamed icl_compute_interpolated_gamma_blob() to
     icl_compute_interpolated_gamma_lut_values() more sensible, I guess
v4: -removed interpolated func for creating gamma lut values
    -removed readouts of fine and coarse segments, failure to read PAL_PREC_DATA
     correctly

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1569096654-24433-3-git-send-email-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 126 +++++++++++++++++++++++++----
 drivers/gpu/drm/i915/i915_reg.h            |   6 ++
 2 files changed, 117 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 91435ba426d0..b0268a9bde8a 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1402,6 +1402,9 @@ static int icl_color_check(struct intel_crtc_state *crtc_state)
 
 static int i9xx_gamma_precision(const struct intel_crtc_state *crtc_state)
 {
+	if (!crtc_state->gamma_enable)
+		return 0;
+
 	switch (crtc_state->gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
 		return 8;
@@ -1415,6 +1418,9 @@ static int i9xx_gamma_precision(const struct intel_crtc_state *crtc_state)
 
 static int ilk_gamma_precision(const struct intel_crtc_state *crtc_state)
 {
+	if (!crtc_state->gamma_enable)
+		return 0;
+
 	if ((crtc_state->csc_mode & CSC_POSITION_BEFORE_GAMMA) == 0)
 		return 0;
 
@@ -1431,6 +1437,9 @@ static int ilk_gamma_precision(const struct intel_crtc_state *crtc_state)
 
 static int chv_gamma_precision(const struct intel_crtc_state *crtc_state)
 {
+	if (!crtc_state->gamma_enable)
+		return 0;
+
 	if (crtc_state->cgm_mode & CGM_PIPE_MODE_GAMMA)
 		return 10;
 	else
@@ -1439,6 +1448,9 @@ static int chv_gamma_precision(const struct intel_crtc_state *crtc_state)
 
 static int glk_gamma_precision(const struct intel_crtc_state *crtc_state)
 {
+	if (!crtc_state->gamma_enable)
+		return 0;
+
 	switch (crtc_state->gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
 		return 8;
@@ -1450,21 +1462,39 @@ static int glk_gamma_precision(const struct intel_crtc_state *crtc_state)
 	}
 }
 
+static int icl_gamma_precision(const struct intel_crtc_state *crtc_state)
+{
+	if ((crtc_state->gamma_mode & POST_CSC_GAMMA_ENABLE) == 0)
+		return 0;
+
+	switch (crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) {
+	case GAMMA_MODE_MODE_8BIT:
+		return 8;
+	case GAMMA_MODE_MODE_10BIT:
+		return 10;
+	case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED:
+		return 16;
+	default:
+		MISSING_CASE(crtc_state->gamma_mode);
+		return 0;
+	}
+
+}
+
 int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
-	if (!crtc_state->gamma_enable)
-		return 0;
-
 	if (HAS_GMCH(dev_priv)) {
 		if (IS_CHERRYVIEW(dev_priv))
 			return chv_gamma_precision(crtc_state);
 		else
 			return i9xx_gamma_precision(crtc_state);
 	} else {
-		if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+		if (INTEL_GEN(dev_priv) >= 11)
+			return icl_gamma_precision(crtc_state);
+		else if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
 			return glk_gamma_precision(crtc_state);
 		else if (IS_IRONLAKE(dev_priv))
 			return ilk_gamma_precision(crtc_state);
@@ -1495,6 +1525,20 @@ static bool intel_color_lut_entry_equal(struct drm_color_lut *lut1,
 	return true;
 }
 
+static bool intel_color_lut_entry_multi_equal(struct drm_color_lut *lut1,
+					      struct drm_color_lut *lut2,
+					      int lut_size, u32 err)
+{
+	int i;
+
+	for (i = 0; i < 9; i++) {
+		if (!err_check(&lut1[i], &lut2[i], err))
+			return false;
+	}
+
+	return true;
+}
+
 bool intel_color_lut_equal(struct drm_property_blob *blob1,
 			   struct drm_property_blob *blob2,
 			   u32 gamma_mode, u32 bit_precision)
@@ -1513,16 +1557,8 @@ bool intel_color_lut_equal(struct drm_property_blob *blob1,
 	lut_size2 = drm_color_lut_size(blob2);
 
 	/* check sw and hw lut size */
-	switch (gamma_mode) {
-	case GAMMA_MODE_MODE_8BIT:
-	case GAMMA_MODE_MODE_10BIT:
-		if (lut_size1 != lut_size2)
-			return false;
-		break;
-	default:
-		MISSING_CASE(gamma_mode);
-			return false;
-	}
+	if (lut_size1 != lut_size2)
+		return false;
 
 	lut1 = blob1->data;
 	lut2 = blob2->data;
@@ -1530,13 +1566,18 @@ bool intel_color_lut_equal(struct drm_property_blob *blob1,
 	err = 0xffff >> bit_precision;
 
 	/* check sw and hw lut entry to be equal */
-	switch (gamma_mode) {
+	switch (gamma_mode & GAMMA_MODE_MODE_MASK) {
 	case GAMMA_MODE_MODE_8BIT:
 	case GAMMA_MODE_MODE_10BIT:
 		if (!intel_color_lut_entry_equal(lut1, lut2,
 						 lut_size2, err))
 			return false;
 		break;
+	case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED:
+		if (!intel_color_lut_entry_multi_equal(lut1, lut2,
+						       lut_size2, err))
+			return false;
+		break;
 	default:
 		MISSING_CASE(gamma_mode);
 			return false;
@@ -1776,6 +1817,60 @@ static void glk_read_luts(struct intel_crtc_state *crtc_state)
 		crtc_state->base.gamma_lut = glk_read_lut_10(crtc_state, PAL_PREC_INDEX_VALUE(0));
 }
 
+static struct drm_property_blob *
+icl_read_lut_multi_segment(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	int lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
+	enum pipe pipe = crtc->pipe;
+	struct drm_property_blob *blob;
+	struct drm_color_lut *blob_data;
+	u32 i, val1, val2;
+
+	blob = drm_property_create_blob(&dev_priv->drm,
+					sizeof(struct drm_color_lut) * lut_size,
+					NULL);
+	if (IS_ERR(blob))
+		return NULL;
+
+	blob_data = blob->data;
+
+	I915_WRITE(PREC_PAL_MULTI_SEG_INDEX(pipe), PAL_PREC_AUTO_INCREMENT);
+
+	for (i = 0; i < 9; i++) {
+		val1 = I915_READ(PREC_PAL_MULTI_SEG_DATA(pipe));
+		val2 = I915_READ(PREC_PAL_MULTI_SEG_DATA(pipe));
+
+		blob_data[i].red = REG_FIELD_GET(PAL_PREC_MULTI_SEG_RED_UDW_MASK, val2) << 6 |
+				   REG_FIELD_GET(PAL_PREC_MULTI_SEG_RED_LDW_MASK, val1);
+		blob_data[i].green = REG_FIELD_GET(PAL_PREC_MULTI_SEG_GREEN_UDW_MASK, val2) << 6 |
+				     REG_FIELD_GET(PAL_PREC_MULTI_SEG_GREEN_LDW_MASK, val1);
+		blob_data[i].blue = REG_FIELD_GET(PAL_PREC_MULTI_SEG_BLUE_UDW_MASK, val2) << 6 |
+				    REG_FIELD_GET(PAL_PREC_MULTI_SEG_BLUE_LDW_MASK, val1);
+	}
+
+	/*
+	 * FIXME readouts from PAL_PREC_DATA register aren't giving correct values
+	 * in the case of fine and coarse segments. Restricting readouts only for
+	 * super fine segment as of now.
+	 */
+
+	return blob;
+}
+
+static void icl_read_luts(struct intel_crtc_state *crtc_state)
+{
+	if ((crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) ==
+	    GAMMA_MODE_MODE_8BIT)
+		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
+	else if ((crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) ==
+		 GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED)
+		crtc_state->base.gamma_lut = icl_read_lut_multi_segment(crtc_state);
+	else
+		crtc_state->base.gamma_lut = glk_read_lut_10(crtc_state, PAL_PREC_INDEX_VALUE(0));
+}
+
 void intel_color_init(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
@@ -1819,6 +1914,7 @@ void intel_color_init(struct intel_crtc *crtc)
 
 		if (INTEL_GEN(dev_priv) >= 11) {
 			dev_priv->display.load_luts = icl_load_luts;
+			dev_priv->display.read_luts = icl_read_luts;
 		} else if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv)) {
 			dev_priv->display.load_luts = glk_load_luts;
 			dev_priv->display.read_luts = glk_read_luts;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 7c64768976ac..9eb71a547103 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -10410,6 +10410,12 @@ enum skl_power_gate {
 
 #define _PAL_PREC_MULTI_SEG_DATA_A	0x4A40C
 #define _PAL_PREC_MULTI_SEG_DATA_B	0x4AC0C
+#define  PAL_PREC_MULTI_SEG_RED_LDW_MASK   REG_GENMASK(29, 24)
+#define  PAL_PREC_MULTI_SEG_RED_UDW_MASK   REG_GENMASK(29, 20)
+#define  PAL_PREC_MULTI_SEG_GREEN_LDW_MASK REG_GENMASK(19, 14)
+#define  PAL_PREC_MULTI_SEG_GREEN_UDW_MASK REG_GENMASK(19, 10)
+#define  PAL_PREC_MULTI_SEG_BLUE_LDW_MASK  REG_GENMASK(9, 4)
+#define  PAL_PREC_MULTI_SEG_BLUE_UDW_MASK  REG_GENMASK(9, 0)
 
 #define PREC_PAL_MULTI_SEG_INDEX(pipe)	_MMIO_PIPE(pipe, \
 					_PAL_PREC_MULTI_SEG_INDEX_A, \
-- 
cgit v1.2.3


From 18febcb74ed37abd835da0ab5335df67ed40e4b5 Mon Sep 17 00:00:00 2001
From: Animesh Manna <animesh.manna@intel.com>
Date: Fri, 20 Sep 2019 17:29:21 +0530
Subject: drm/i915/dsb: feature flag added for display state buffer.

Display State Buffer(DSB) is a new hardware capability, introduced
in GEN12 display. DSB allows a driver to batch-program display HW
registers.

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Shashank Sharma <shashank.sharma@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Signed-off-by: Animesh Manna <animesh.manna@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920115930.27829-2-animesh.manna@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h          | 2 ++
 drivers/gpu/drm/i915/intel_device_info.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4faec2f94e19..84b9b138d7ac 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1863,6 +1863,8 @@ static inline struct drm_i915_private *pdev_to_i915(struct pci_dev *pdev)
 	(BUILD_BUG_ON_ZERO(!__builtin_constant_p(n)) + \
 	 INTEL_INFO(dev_priv)->gen == (n))
 
+#define HAS_DSB(dev_priv)	(INTEL_INFO(dev_priv)->display.has_dsb)
+
 /*
  * Return true if revision is in range [since,until] inclusive.
  *
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index d4c288860aed..0cdc2465534b 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -135,6 +135,7 @@ enum intel_ppgtt_type {
 	func(has_csr); \
 	func(has_ddi); \
 	func(has_dp_mst); \
+	func(has_dsb); \
 	func(has_fbc); \
 	func(has_gmch); \
 	func(has_hotplug); \
-- 
cgit v1.2.3


From 67f3b58f3bac975f35c312fd8876edb599cc24be Mon Sep 17 00:00:00 2001
From: Animesh Manna <animesh.manna@intel.com>
Date: Fri, 20 Sep 2019 17:29:22 +0530
Subject: drm/i915/dsb: DSB context creation.

This patch adds a function, which will internally get the gem buffer
for DSB engine. The GEM buffer is from global GTT, and is mapped into
CPU domain, contains the data + opcode to be feed to DSB engine.

v1: Initial version.

v2:
- removed some unwanted code. (Chris)
- Used i915_gem_object_create_internal instead of _shmem. (Chris)
- cmd_buf_tail removed and can be derived through vma object. (Chris)

v3: vma realeased if i915_gem_object_pin_map() failed. (Shashank)

v4: for simplification and based on current usage added single dsb
object in intel_crtc. (Shashank)

v5: seting NULL to cmd_buf moved outside of mutex in dsb-put(). (Shashank)

v6:
- refcount machanism added.
- Used atomic_add_return and atomic_dec_and_test instead of
atomic_inc and atomic_dec. (Jani)

Cc: Imre Deak <imre.deak@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Shashank Sharma <shashank.sharma@intel.com>
Signed-off-by: Animesh Manna <animesh.manna@intel.com>
[Jani: added #include <linux/types.h> while pushing]
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920115930.27829-3-animesh.manna@intel.com
---
 drivers/gpu/drm/i915/Makefile                      |  1 +
 drivers/gpu/drm/i915/display/intel_display_types.h |  3 +
 drivers/gpu/drm/i915/display/intel_dsb.c           | 80 ++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_dsb.h           | 33 +++++++++
 drivers/gpu/drm/i915/i915_drv.h                    |  1 +
 5 files changed, 118 insertions(+)
 create mode 100644 drivers/gpu/drm/i915/display/intel_dsb.c
 create mode 100644 drivers/gpu/drm/i915/display/intel_dsb.h

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 658b930d34a8..6313e7b4bd78 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -172,6 +172,7 @@ i915-y += \
 	display/intel_display_power.o \
 	display/intel_dpio_phy.o \
 	display/intel_dpll_mgr.o \
+	display/intel_dsb.o \
 	display/intel_fbc.o \
 	display/intel_fifo_underrun.o \
 	display/intel_frontbuffer.o \
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index d5cc4b810d9e..49c902b00484 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1033,6 +1033,9 @@ struct intel_crtc {
 
 	/* scalers available on this crtc */
 	int num_scalers;
+
+	/* per pipe DSB related info */
+	struct intel_dsb dsb;
 };
 
 struct intel_plane {
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
new file mode 100644
index 000000000000..2ed277670f15
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ *
+ */
+
+#include "i915_drv.h"
+#include "intel_display_types.h"
+
+#define DSB_BUF_SIZE    (2 * PAGE_SIZE)
+
+struct intel_dsb *
+intel_dsb_get(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *i915 = to_i915(dev);
+	struct intel_dsb *dsb = &crtc->dsb;
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	intel_wakeref_t wakeref;
+
+	if (!HAS_DSB(i915))
+		return dsb;
+
+	if (atomic_add_return(1, &dsb->refcount) != 1)
+		return dsb;
+
+	dsb->id = DSB1;
+	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
+
+	obj = i915_gem_object_create_internal(i915, DSB_BUF_SIZE);
+	if (IS_ERR(obj)) {
+		DRM_ERROR("Gem object creation failed\n");
+		goto err;
+	}
+
+	mutex_lock(&i915->drm.struct_mutex);
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
+	mutex_unlock(&i915->drm.struct_mutex);
+	if (IS_ERR(vma)) {
+		DRM_ERROR("Vma creation failed\n");
+		i915_gem_object_put(obj);
+		atomic_dec(&dsb->refcount);
+		goto err;
+	}
+
+	dsb->cmd_buf = i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
+	if (IS_ERR(dsb->cmd_buf)) {
+		DRM_ERROR("Command buffer creation failed\n");
+		i915_vma_unpin_and_release(&vma, 0);
+		dsb->cmd_buf = NULL;
+		atomic_dec(&dsb->refcount);
+		goto err;
+	}
+	dsb->vma = vma;
+
+err:
+	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+	return dsb;
+}
+
+void intel_dsb_put(struct intel_dsb *dsb)
+{
+	struct intel_crtc *crtc = container_of(dsb, typeof(*crtc), dsb);
+	struct drm_i915_private *i915 = to_i915(crtc->base.dev);
+
+	if (!HAS_DSB(i915))
+		return;
+
+	if (WARN_ON(atomic_read(&dsb->refcount) == 0))
+		return;
+
+	if (atomic_dec_and_test(&dsb->refcount)) {
+		mutex_lock(&i915->drm.struct_mutex);
+		i915_gem_object_unpin_map(dsb->vma->obj);
+		i915_vma_unpin_and_release(&dsb->vma, 0);
+		mutex_unlock(&i915->drm.struct_mutex);
+		dsb->cmd_buf = NULL;
+	}
+}
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.h b/drivers/gpu/drm/i915/display/intel_dsb.h
new file mode 100644
index 000000000000..b8639864df50
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_dsb.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef _INTEL_DSB_H
+#define _INTEL_DSB_H
+
+#include <linux/types.h>
+
+struct intel_crtc;
+struct i915_vma;
+
+enum dsb_id {
+	INVALID_DSB = -1,
+	DSB1,
+	DSB2,
+	DSB3,
+	MAX_DSB_PER_PIPE
+};
+
+struct intel_dsb {
+	atomic_t refcount;
+	enum dsb_id id;
+	u32 *cmd_buf;
+	struct i915_vma *vma;
+};
+
+struct intel_dsb *
+intel_dsb_get(struct intel_crtc *crtc);
+void intel_dsb_put(struct intel_dsb *dsb);
+
+#endif
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 84b9b138d7ac..07f1e89a55ca 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -67,6 +67,7 @@
 #include "display/intel_display.h"
 #include "display/intel_display_power.h"
 #include "display/intel_dpll_mgr.h"
+#include "display/intel_dsb.h"
 #include "display/intel_frontbuffer.h"
 #include "display/intel_gmbus.h"
 #include "display/intel_opregion.h"
-- 
cgit v1.2.3


From 061489c65ff57ee9f757d7a519fb9a09e5fbadd6 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Mon, 23 Sep 2019 10:09:23 +0300
Subject: drm/i915/dsb: single register write function for DSB.

DSB support single register write through opcode 0x1. Generic
api created which accumulate all single register write in a batch
buffer and once DSB is triggered, it will program all the registers
at the same time.

v1: Initial version.
v2: Unused macro removed and cosmetic changes done. (Shashank)
v3: set free_pos to zero in dsb-put() instead dsb-get() and
a cosmetic change. (Shashank)
v4: macro of indexed-write is moved. (Shashank)

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Shashank Sharma <shashank.sharma@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Signed-off-by: Animesh Manna <animesh.manna@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920115930.27829-4-animesh.manna@intel.com
---
 drivers/gpu/drm/i915/display/intel_dsb.c | 29 +++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_dsb.h |  9 +++++++++
 2 files changed, 38 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index 2ed277670f15..f94cd6dc98b6 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -9,6 +9,12 @@
 
 #define DSB_BUF_SIZE    (2 * PAGE_SIZE)
 
+/* DSB opcodes. */
+#define DSB_OPCODE_SHIFT		24
+#define DSB_OPCODE_MMIO_WRITE		0x1
+#define DSB_BYTE_EN			0xF
+#define DSB_BYTE_EN_SHIFT		20
+
 struct intel_dsb *
 intel_dsb_get(struct intel_crtc *crtc)
 {
@@ -76,5 +82,28 @@ void intel_dsb_put(struct intel_dsb *dsb)
 		i915_vma_unpin_and_release(&dsb->vma, 0);
 		mutex_unlock(&i915->drm.struct_mutex);
 		dsb->cmd_buf = NULL;
+		dsb->free_pos = 0;
+	}
+}
+
+void intel_dsb_reg_write(struct intel_dsb *dsb, i915_reg_t reg, u32 val)
+{
+	struct intel_crtc *crtc = container_of(dsb, typeof(*crtc), dsb);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	u32 *buf = dsb->cmd_buf;
+
+	if (!buf) {
+		I915_WRITE(reg, val);
+		return;
+	}
+
+	if (WARN_ON(dsb->free_pos >= DSB_BUF_SIZE)) {
+		DRM_DEBUG_KMS("DSB buffer overflow\n");
+		return;
 	}
+
+	buf[dsb->free_pos++] = val;
+	buf[dsb->free_pos++] = (DSB_OPCODE_MMIO_WRITE  << DSB_OPCODE_SHIFT) |
+			       (DSB_BYTE_EN << DSB_BYTE_EN_SHIFT) |
+			       i915_mmio_reg_offset(reg);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.h b/drivers/gpu/drm/i915/display/intel_dsb.h
index b8639864df50..839cbf621fa2 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.h
+++ b/drivers/gpu/drm/i915/display/intel_dsb.h
@@ -8,6 +8,8 @@
 
 #include <linux/types.h>
 
+#include "i915_reg.h"
+
 struct intel_crtc;
 struct i915_vma;
 
@@ -24,10 +26,17 @@ struct intel_dsb {
 	enum dsb_id id;
 	u32 *cmd_buf;
 	struct i915_vma *vma;
+
+	/*
+	 * free_pos will point the first free entry position
+	 * and help in calculating tail of command buffer.
+	 */
+	int free_pos;
 };
 
 struct intel_dsb *
 intel_dsb_get(struct intel_crtc *crtc);
 void intel_dsb_put(struct intel_dsb *dsb);
+void intel_dsb_reg_write(struct intel_dsb *dsb, i915_reg_t reg, u32 val);
 
 #endif
-- 
cgit v1.2.3


From b27a96ad72fd706adc5dbbfd7bba76f698fe3875 Mon Sep 17 00:00:00 2001
From: Animesh Manna <animesh.manna@intel.com>
Date: Fri, 20 Sep 2019 17:29:24 +0530
Subject: drm/i915/dsb: Indexed register write function for DSB.

DSB can program large set of data through indexed register write
(opcode 0x9) in one shot. DSB feature can be used for bulk register
programming e.g. gamma lut programming, HDR meta data programming.

v1: initial version.
v2: simplified code by using ALIGN(). (Chris)
v3: ascii table added as code comment. (Shashank)
v4: cosmetic changes done. (Shashank)
v5: reset ins_start_offset. (Jani)
v6: update ins_start_offset in inel_dsb_reg_write.

Cc: Shashank Sharma <shashank.sharma@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Signed-off-by: Animesh Manna <animesh.manna@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920115930.27829-5-animesh.manna@intel.com
---
 drivers/gpu/drm/i915/display/intel_dsb.c | 68 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_dsb.h |  9 +++++
 2 files changed, 77 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index f94cd6dc98b6..faa853b08458 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -12,8 +12,10 @@
 /* DSB opcodes. */
 #define DSB_OPCODE_SHIFT		24
 #define DSB_OPCODE_MMIO_WRITE		0x1
+#define DSB_OPCODE_INDEXED_WRITE	0x9
 #define DSB_BYTE_EN			0xF
 #define DSB_BYTE_EN_SHIFT		20
+#define DSB_REG_VALUE_MASK		0xfffff
 
 struct intel_dsb *
 intel_dsb_get(struct intel_crtc *crtc)
@@ -83,9 +85,74 @@ void intel_dsb_put(struct intel_dsb *dsb)
 		mutex_unlock(&i915->drm.struct_mutex);
 		dsb->cmd_buf = NULL;
 		dsb->free_pos = 0;
+		dsb->ins_start_offset = 0;
 	}
 }
 
+void intel_dsb_indexed_reg_write(struct intel_dsb *dsb, i915_reg_t reg,
+				 u32 val)
+{
+	struct intel_crtc *crtc = container_of(dsb, typeof(*crtc), dsb);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	u32 *buf = dsb->cmd_buf;
+	u32 reg_val;
+
+	if (!buf) {
+		I915_WRITE(reg, val);
+		return;
+	}
+
+	if (WARN_ON(dsb->free_pos >= DSB_BUF_SIZE)) {
+		DRM_DEBUG_KMS("DSB buffer overflow\n");
+		return;
+	}
+
+	/*
+	 * For example the buffer will look like below for 3 dwords for auto
+	 * increment register:
+	 * +--------------------------------------------------------+
+	 * | size = 3 | offset &| value1 | value2 | value3 | zero   |
+	 * |          | opcode  |        |        |        |        |
+	 * +--------------------------------------------------------+
+	 * +          +         +        +        +        +        +
+	 * 0          4         8        12       16       20       24
+	 * Byte
+	 *
+	 * As every instruction is 8 byte aligned the index of dsb instruction
+	 * will start always from even number while dealing with u32 array. If
+	 * we are writing odd no of dwords, Zeros will be added in the end for
+	 * padding.
+	 */
+	reg_val = buf[dsb->ins_start_offset + 1] & DSB_REG_VALUE_MASK;
+	if (reg_val != i915_mmio_reg_offset(reg)) {
+		/* Every instruction should be 8 byte aligned. */
+		dsb->free_pos = ALIGN(dsb->free_pos, 2);
+
+		dsb->ins_start_offset = dsb->free_pos;
+
+		/* Update the size. */
+		buf[dsb->free_pos++] = 1;
+
+		/* Update the opcode and reg. */
+		buf[dsb->free_pos++] = (DSB_OPCODE_INDEXED_WRITE  <<
+					DSB_OPCODE_SHIFT) |
+					i915_mmio_reg_offset(reg);
+
+		/* Update the value. */
+		buf[dsb->free_pos++] = val;
+	} else {
+		/* Update the new value. */
+		buf[dsb->free_pos++] = val;
+
+		/* Update the size. */
+		buf[dsb->ins_start_offset]++;
+	}
+
+	/* if number of data words is odd, then the last dword should be 0.*/
+	if (dsb->free_pos & 0x1)
+		buf[dsb->free_pos] = 0;
+}
+
 void intel_dsb_reg_write(struct intel_dsb *dsb, i915_reg_t reg, u32 val)
 {
 	struct intel_crtc *crtc = container_of(dsb, typeof(*crtc), dsb);
@@ -102,6 +169,7 @@ void intel_dsb_reg_write(struct intel_dsb *dsb, i915_reg_t reg, u32 val)
 		return;
 	}
 
+	dsb->ins_start_offset = dsb->free_pos;
 	buf[dsb->free_pos++] = val;
 	buf[dsb->free_pos++] = (DSB_OPCODE_MMIO_WRITE  << DSB_OPCODE_SHIFT) |
 			       (DSB_BYTE_EN << DSB_BYTE_EN_SHIFT) |
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.h b/drivers/gpu/drm/i915/display/intel_dsb.h
index 839cbf621fa2..e4dd0ab799ec 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.h
+++ b/drivers/gpu/drm/i915/display/intel_dsb.h
@@ -32,11 +32,20 @@ struct intel_dsb {
 	 * and help in calculating tail of command buffer.
 	 */
 	int free_pos;
+
+	/*
+	 * ins_start_offset will help to store start address of the dsb
+	 * instuction and help in identifying the batch of auto-increment
+	 * register.
+	 */
+	u32 ins_start_offset;
 };
 
 struct intel_dsb *
 intel_dsb_get(struct intel_crtc *crtc);
 void intel_dsb_put(struct intel_dsb *dsb);
 void intel_dsb_reg_write(struct intel_dsb *dsb, i915_reg_t reg, u32 val);
+void intel_dsb_indexed_reg_write(struct intel_dsb *dsb, i915_reg_t reg,
+				 u32 val);
 
 #endif
-- 
cgit v1.2.3


From a6e58d9a2e045e800ac54b838c05656f982c36fe Mon Sep 17 00:00:00 2001
From: Animesh Manna <animesh.manna@intel.com>
Date: Fri, 20 Sep 2019 17:29:25 +0530
Subject: drm/i915/dsb: Check DSB engine status.

As per bspec check for DSB status before programming any
of its register. Inline function added to check the dsb status.

Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Shashank Sharma <shashank.sharma@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Signed-off-by: Animesh Manna <animesh.manna@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920115930.27829-6-animesh.manna@intel.com
---
 drivers/gpu/drm/i915/display/intel_dsb.c | 9 +++++++++
 drivers/gpu/drm/i915/i915_reg.h          | 7 +++++++
 2 files changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index faa853b08458..6000050b18a6 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -17,6 +17,15 @@
 #define DSB_BYTE_EN_SHIFT		20
 #define DSB_REG_VALUE_MASK		0xfffff
 
+static inline bool is_dsb_busy(struct intel_dsb *dsb)
+{
+	struct intel_crtc *crtc = container_of(dsb, typeof(*crtc), dsb);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
+
+	return DSB_STATUS & I915_READ(DSB_CTRL(pipe, dsb->id));
+}
+
 struct intel_dsb *
 intel_dsb_get(struct intel_crtc *crtc)
 {
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 9eb71a547103..fba3e8b26296 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -11698,4 +11698,11 @@ enum skl_power_gate {
 #define PORT_TX_DFLEXDPCSSS(fia)		_MMIO_FIA((fia), 0x00894)
 #define   DP_PHY_MODE_STATUS_NOT_SAFE(tc_port)		(1 << (tc_port))
 
+/* This register controls the Display State Buffer (DSB) engines. */
+#define _DSBSL_INSTANCE_BASE		0x70B00
+#define DSBSL_INSTANCE(pipe, id)	(_DSBSL_INSTANCE_BASE + \
+					 (pipe) * 0x1000 + (id) * 100)
+#define DSB_CTRL(pipe, id)		_MMIO(DSBSL_INSTANCE(pipe, id) + 0x8)
+#define   DSB_STATUS			(1 << 0)
+
 #endif /* _I915_REG_H_ */
-- 
cgit v1.2.3


From f7619c47983431fc5ddfa30d8f921a6a40e0223a Mon Sep 17 00:00:00 2001
From: Animesh Manna <animesh.manna@intel.com>
Date: Fri, 20 Sep 2019 17:29:26 +0530
Subject: drm/i915/dsb: functions to enable/disable DSB engine.

DSB will be used for performance improvement for some special scenario.
DSB engine will be enabled based on need and after completion of its work
will be disabled. Api added for enable/disable operation by using DSB_CTRL
register.

v1: Initial version.
v2: POSTING_READ added after writing control register. (Shashank)
v3: cosmetic changes done. (Shashank)

Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Shashank Sharma <shashank.sharma@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Signed-off-by: Animesh Manna <animesh.manna@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920115930.27829-7-animesh.manna@intel.com
---
 drivers/gpu/drm/i915/display/intel_dsb.c | 40 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_reg.h          |  1 +
 2 files changed, 41 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index 6000050b18a6..6fb4529689f1 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -26,6 +26,46 @@ static inline bool is_dsb_busy(struct intel_dsb *dsb)
 	return DSB_STATUS & I915_READ(DSB_CTRL(pipe, dsb->id));
 }
 
+static inline bool intel_dsb_enable_engine(struct intel_dsb *dsb)
+{
+	struct intel_crtc *crtc = container_of(dsb, typeof(*crtc), dsb);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
+	u32 dsb_ctrl;
+
+	dsb_ctrl = I915_READ(DSB_CTRL(pipe, dsb->id));
+	if (DSB_STATUS & dsb_ctrl) {
+		DRM_DEBUG_KMS("DSB engine is busy.\n");
+		return false;
+	}
+
+	dsb_ctrl |= DSB_ENABLE;
+	I915_WRITE(DSB_CTRL(pipe, dsb->id), dsb_ctrl);
+
+	POSTING_READ(DSB_CTRL(pipe, dsb->id));
+	return true;
+}
+
+static inline bool intel_dsb_disable_engine(struct intel_dsb *dsb)
+{
+	struct intel_crtc *crtc = container_of(dsb, typeof(*crtc), dsb);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum pipe pipe = crtc->pipe;
+	u32 dsb_ctrl;
+
+	dsb_ctrl = I915_READ(DSB_CTRL(pipe, dsb->id));
+	if (DSB_STATUS & dsb_ctrl) {
+		DRM_DEBUG_KMS("DSB engine is busy.\n");
+		return false;
+	}
+
+	dsb_ctrl &= ~DSB_ENABLE;
+	I915_WRITE(DSB_CTRL(pipe, dsb->id), dsb_ctrl);
+
+	POSTING_READ(DSB_CTRL(pipe, dsb->id));
+	return true;
+}
+
 struct intel_dsb *
 intel_dsb_get(struct intel_crtc *crtc)
 {
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index fba3e8b26296..5fcbaaa8f3c6 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -11703,6 +11703,7 @@ enum skl_power_gate {
 #define DSBSL_INSTANCE(pipe, id)	(_DSBSL_INSTANCE_BASE + \
 					 (pipe) * 0x1000 + (id) * 100)
 #define DSB_CTRL(pipe, id)		_MMIO(DSBSL_INSTANCE(pipe, id) + 0x8)
+#define   DSB_ENABLE			(1 << 31)
 #define   DSB_STATUS			(1 << 0)
 
 #endif /* _I915_REG_H_ */
-- 
cgit v1.2.3


From 1abf329a713d2772257470873d57794d2404018d Mon Sep 17 00:00:00 2001
From: Animesh Manna <animesh.manna@intel.com>
Date: Fri, 20 Sep 2019 17:29:27 +0530
Subject: drm/i915/dsb: function to trigger workload execution of DSB.

Batch buffer will be created through dsb-reg-write function which can have
single/multiple request based on usecase and once the buffer is ready
commit function will trigger the execution of the batch buffer. All
the registers will be updated simultaneously.

v1: Initial version.
v2: Optimized code few places. (Chris)
v3: USed DRM_ERROR for dsb head/tail programming failure. (Shashank)
v4: reset ins_start_offset after commit. (Jani)

Cc: Imre Deak <imre.deak@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Shashank Sharma <shashank.sharma@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Signed-off-by: Animesh Manna <animesh.manna@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920115930.27829-8-animesh.manna@intel.com
---
 drivers/gpu/drm/i915/display/intel_dsb.c | 43 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_dsb.h |  1 +
 drivers/gpu/drm/i915/i915_reg.h          |  2 ++
 3 files changed, 46 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index 6fb4529689f1..f4c0b37683a5 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -224,3 +224,46 @@ void intel_dsb_reg_write(struct intel_dsb *dsb, i915_reg_t reg, u32 val)
 			       (DSB_BYTE_EN << DSB_BYTE_EN_SHIFT) |
 			       i915_mmio_reg_offset(reg);
 }
+
+void intel_dsb_commit(struct intel_dsb *dsb)
+{
+	struct intel_crtc *crtc = container_of(dsb, typeof(*crtc), dsb);
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	enum pipe pipe = crtc->pipe;
+	u32 tail;
+
+	if (!dsb->free_pos)
+		return;
+
+	if (!intel_dsb_enable_engine(dsb))
+		goto reset;
+
+	if (is_dsb_busy(dsb)) {
+		DRM_ERROR("HEAD_PTR write failed - dsb engine is busy.\n");
+		goto reset;
+	}
+	I915_WRITE(DSB_HEAD(pipe, dsb->id), i915_ggtt_offset(dsb->vma));
+
+	tail = ALIGN(dsb->free_pos * 4, CACHELINE_BYTES);
+	if (tail > dsb->free_pos * 4)
+		memset(&dsb->cmd_buf[dsb->free_pos], 0,
+		       (tail - dsb->free_pos * 4));
+
+	if (is_dsb_busy(dsb)) {
+		DRM_ERROR("TAIL_PTR write failed - dsb engine is busy.\n");
+		goto reset;
+	}
+	DRM_DEBUG_KMS("DSB execution started - head 0x%x, tail 0x%x\n",
+		      i915_ggtt_offset(dsb->vma), tail);
+	I915_WRITE(DSB_TAIL(pipe, dsb->id), i915_ggtt_offset(dsb->vma) + tail);
+	if (wait_for(!is_dsb_busy(dsb), 1)) {
+		DRM_ERROR("Timed out waiting for DSB workload completion.\n");
+		goto reset;
+	}
+
+reset:
+	dsb->free_pos = 0;
+	dsb->ins_start_offset = 0;
+	intel_dsb_disable_engine(dsb);
+}
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.h b/drivers/gpu/drm/i915/display/intel_dsb.h
index e4dd0ab799ec..6f95c8e909e6 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.h
+++ b/drivers/gpu/drm/i915/display/intel_dsb.h
@@ -47,5 +47,6 @@ void intel_dsb_put(struct intel_dsb *dsb);
 void intel_dsb_reg_write(struct intel_dsb *dsb, i915_reg_t reg, u32 val);
 void intel_dsb_indexed_reg_write(struct intel_dsb *dsb, i915_reg_t reg,
 				 u32 val);
+void intel_dsb_commit(struct intel_dsb *dsb);
 
 #endif
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 5fcbaaa8f3c6..8649a3028963 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -11702,6 +11702,8 @@ enum skl_power_gate {
 #define _DSBSL_INSTANCE_BASE		0x70B00
 #define DSBSL_INSTANCE(pipe, id)	(_DSBSL_INSTANCE_BASE + \
 					 (pipe) * 0x1000 + (id) * 100)
+#define DSB_HEAD(pipe, id)		_MMIO(DSBSL_INSTANCE(pipe, id) + 0x0)
+#define DSB_TAIL(pipe, id)		_MMIO(DSBSL_INSTANCE(pipe, id) + 0x4)
 #define DSB_CTRL(pipe, id)		_MMIO(DSBSL_INSTANCE(pipe, id) + 0x8)
 #define   DSB_ENABLE			(1 << 31)
 #define   DSB_STATUS			(1 << 0)
-- 
cgit v1.2.3


From 49e3fb7fd880f294643304f3f374d553dd6a4c11 Mon Sep 17 00:00:00 2001
From: Animesh Manna <animesh.manna@intel.com>
Date: Fri, 20 Sep 2019 17:29:28 +0530
Subject: drm/i915/dsb: Enable gamma lut programming using DSB.

Gamma lut programming can be programmed using DSB
where bulk register programming can be done using indexed
register write which takes number of data and the mmio offset
to be written.

Currently enabled for 12-bit gamma LUT which is enabled by
default and later 8-bit/10-bit will be enabled in future
based on need.

v1: Initial version.
v2: Directly call dsb-api at callsites. (Jani)
v3:
- modified the code as per single dsb instance per crtc. (Shashank)
- Added dsb get/put call in platform specific load_lut hook. (Jani)
- removed dsb pointer from dev_priv. (Jani)
v4: simplified code by dropping ref-count implementation. (Shashank)

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Shashank Sharma <shashank.sharma@intel.com>
Signed-off-by: Animesh Manna <animesh.manna@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20190920115930.27829-9-animesh.manna@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 64 +++++++++++++++++++-----------
 1 file changed, 41 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index b0268a9bde8a..402151128e1f 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -627,12 +627,13 @@ static void bdw_load_lut_10(struct intel_crtc *crtc,
 static void ivb_load_lut_ext_max(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	struct intel_dsb *dsb = intel_dsb_get(crtc);
 	enum pipe pipe = crtc->pipe;
 
 	/* Program the max register to clamp values > 1.0. */
-	I915_WRITE(PREC_PAL_EXT_GC_MAX(pipe, 0), 1 << 16);
-	I915_WRITE(PREC_PAL_EXT_GC_MAX(pipe, 1), 1 << 16);
-	I915_WRITE(PREC_PAL_EXT_GC_MAX(pipe, 2), 1 << 16);
+	intel_dsb_reg_write(dsb, PREC_PAL_EXT_GC_MAX(pipe, 0), 1 << 16);
+	intel_dsb_reg_write(dsb, PREC_PAL_EXT_GC_MAX(pipe, 1), 1 << 16);
+	intel_dsb_reg_write(dsb, PREC_PAL_EXT_GC_MAX(pipe, 2), 1 << 16);
 
 	/*
 	 * Program the gc max 2 register to clamp values > 1.0.
@@ -640,10 +641,15 @@ static void ivb_load_lut_ext_max(struct intel_crtc *crtc)
 	 * from 3.0 to 7.0
 	 */
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
-		I915_WRITE(PREC_PAL_EXT2_GC_MAX(pipe, 0), 1 << 16);
-		I915_WRITE(PREC_PAL_EXT2_GC_MAX(pipe, 1), 1 << 16);
-		I915_WRITE(PREC_PAL_EXT2_GC_MAX(pipe, 2), 1 << 16);
+		intel_dsb_reg_write(dsb, PREC_PAL_EXT2_GC_MAX(pipe, 0),
+				    1 << 16);
+		intel_dsb_reg_write(dsb, PREC_PAL_EXT2_GC_MAX(pipe, 1),
+				    1 << 16);
+		intel_dsb_reg_write(dsb, PREC_PAL_EXT2_GC_MAX(pipe, 2),
+				    1 << 16);
 	}
+
+	intel_dsb_put(dsb);
 }
 
 static void ivb_load_luts(const struct intel_crtc_state *crtc_state)
@@ -803,22 +809,23 @@ icl_load_gcmax(const struct intel_crtc_state *crtc_state,
 	       const struct drm_color_lut *color)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	struct intel_dsb *dsb = intel_dsb_get(crtc);
 	enum pipe pipe = crtc->pipe;
 
 	/* Fixme: LUT entries are 16 bit only, so we can prog 0xFFFF max */
-	I915_WRITE(PREC_PAL_GC_MAX(pipe, 0), color->red);
-	I915_WRITE(PREC_PAL_GC_MAX(pipe, 1), color->green);
-	I915_WRITE(PREC_PAL_GC_MAX(pipe, 2), color->blue);
+	intel_dsb_reg_write(dsb, PREC_PAL_GC_MAX(pipe, 0), color->red);
+	intel_dsb_reg_write(dsb, PREC_PAL_GC_MAX(pipe, 1), color->green);
+	intel_dsb_reg_write(dsb, PREC_PAL_GC_MAX(pipe, 2), color->blue);
+	intel_dsb_put(dsb);
 }
 
 static void
 icl_program_gamma_superfine_segment(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	const struct drm_property_blob *blob = crtc_state->base.gamma_lut;
 	const struct drm_color_lut *lut = blob->data;
+	struct intel_dsb *dsb = intel_dsb_get(crtc);
 	enum pipe pipe = crtc->pipe;
 	u32 i;
 
@@ -829,26 +836,29 @@ icl_program_gamma_superfine_segment(const struct intel_crtc_state *crtc_state)
 	 * 9 entries, corresponding to values 0, 1/(8 * 128 * 256),
 	 * 2/(8 * 128 * 256) ... 8/(8 * 128 * 256).
 	 */
-	I915_WRITE(PREC_PAL_MULTI_SEG_INDEX(pipe), PAL_PREC_AUTO_INCREMENT);
+	intel_dsb_reg_write(dsb, PREC_PAL_MULTI_SEG_INDEX(pipe),
+			    PAL_PREC_AUTO_INCREMENT);
 
 	for (i = 0; i < 9; i++) {
 		const struct drm_color_lut *entry = &lut[i];
 
-		I915_WRITE(PREC_PAL_MULTI_SEG_DATA(pipe),
-			   ilk_lut_12p4_ldw(entry));
-		I915_WRITE(PREC_PAL_MULTI_SEG_DATA(pipe),
-			   ilk_lut_12p4_udw(entry));
+		intel_dsb_indexed_reg_write(dsb, PREC_PAL_MULTI_SEG_DATA(pipe),
+					    ilk_lut_12p4_ldw(entry));
+		intel_dsb_indexed_reg_write(dsb, PREC_PAL_MULTI_SEG_DATA(pipe),
+					    ilk_lut_12p4_udw(entry));
 	}
+
+	intel_dsb_put(dsb);
 }
 
 static void
 icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	const struct drm_property_blob *blob = crtc_state->base.gamma_lut;
 	const struct drm_color_lut *lut = blob->data;
 	const struct drm_color_lut *entry;
+	struct intel_dsb *dsb = intel_dsb_get(crtc);
 	enum pipe pipe = crtc->pipe;
 	u32 i;
 
@@ -862,12 +872,13 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 	 * PAL_PREC_INDEX[0] and PAL_PREC_INDEX[1] map to seg2[1],
 	 * seg2[0] being unused by the hardware.
 	 */
-	I915_WRITE(PREC_PAL_INDEX(pipe), PAL_PREC_AUTO_INCREMENT);
-
+	intel_dsb_reg_write(dsb, PREC_PAL_INDEX(pipe), PAL_PREC_AUTO_INCREMENT);
 	for (i = 1; i < 257; i++) {
 		entry = &lut[i * 8];
-		I915_WRITE(PREC_PAL_DATA(pipe), ilk_lut_12p4_ldw(entry));
-		I915_WRITE(PREC_PAL_DATA(pipe), ilk_lut_12p4_udw(entry));
+		intel_dsb_indexed_reg_write(dsb, PREC_PAL_DATA(pipe),
+					    ilk_lut_12p4_ldw(entry));
+		intel_dsb_indexed_reg_write(dsb, PREC_PAL_DATA(pipe),
+					    ilk_lut_12p4_udw(entry));
 	}
 
 	/*
@@ -884,20 +895,24 @@ icl_program_gamma_multi_segment(const struct intel_crtc_state *crtc_state)
 	 */
 	for (i = 0; i < 256; i++) {
 		entry = &lut[i * 8 * 128];
-		I915_WRITE(PREC_PAL_DATA(pipe), ilk_lut_12p4_ldw(entry));
-		I915_WRITE(PREC_PAL_DATA(pipe), ilk_lut_12p4_udw(entry));
+		intel_dsb_indexed_reg_write(dsb, PREC_PAL_DATA(pipe),
+					    ilk_lut_12p4_ldw(entry));
+		intel_dsb_indexed_reg_write(dsb, PREC_PAL_DATA(pipe),
+					    ilk_lut_12p4_udw(entry));
 	}
 
 	/* The last entry in the LUT is to be programmed in GCMAX */
 	entry = &lut[256 * 8 * 128];
 	icl_load_gcmax(crtc_state, entry);
 	ivb_load_lut_ext_max(crtc);
+	intel_dsb_put(dsb);
 }
 
 static void icl_load_luts(const struct intel_crtc_state *crtc_state)
 {
 	const struct drm_property_blob *gamma_lut = crtc_state->base.gamma_lut;
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_dsb *dsb = intel_dsb_get(crtc);
 
 	if (crtc_state->base.degamma_lut)
 		glk_load_degamma_lut(crtc_state);
@@ -914,6 +929,9 @@ static void icl_load_luts(const struct intel_crtc_state *crtc_state)
 		bdw_load_lut_10(crtc, gamma_lut, PAL_PREC_INDEX_VALUE(0));
 		ivb_load_lut_ext_max(crtc);
 	}
+
+	intel_dsb_commit(dsb);
+	intel_dsb_put(dsb);
 }
 
 static u32 chv_cgm_degamma_ldw(const struct drm_color_lut *color)
-- 
cgit v1.2.3


From dfaa6f285bd8eee63866df8b0474858e8a1cc40d Mon Sep 17 00:00:00 2001
From: Animesh Manna <animesh.manna@intel.com>
Date: Fri, 20 Sep 2019 17:29:29 +0530
Subject: drm/i915/dsb: Enable DSB for gen12.

Enabling DSB by setting 1 to has_dsb flag for gen12.

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Shashank Sharma <shashank.sharma@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Signed-off-by: Animesh Manna <animesh.manna@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920115930.27829-10-animesh.manna@intel.com
---
 drivers/gpu/drm/i915/i915_pci.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index fe6941c8fc99..c2faa679658c 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -787,7 +787,8 @@ static const struct intel_device_info intel_elkhartlake_info = {
 		[TRANSCODER_DSI_0] = TRANSCODER_DSI0_OFFSET, \
 		[TRANSCODER_DSI_1] = TRANSCODER_DSI1_OFFSET, \
 	}, \
-	.has_global_mocs = 1
+	.has_global_mocs = 1, \
+	.display.has_dsb = 1
 
 static const struct intel_device_info intel_tigerlake_12_info = {
 	GEN12_FEATURES,
-- 
cgit v1.2.3


From 5dd85e72bc922379fec10969c9390a72aaa4746f Mon Sep 17 00:00:00 2001
From: Animesh Manna <animesh.manna@intel.com>
Date: Fri, 20 Sep 2019 17:29:30 +0530
Subject: drm/i915/dsb: Documentation for DSB.

Added docbook info regarding Display State Buffer(DSB) which
is added from gen12 onwards to batch submit display HW programming.

v1: Initial version as RFC.

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Shashank Sharma <shashank.sharma@intel.com>
Reviewed-by: Shashank Sharma <shashank.sharma@intel.com>
Signed-off-by: Animesh Manna <animesh.manna@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920115930.27829-11-animesh.manna@intel.com
---
 Documentation/gpu/i915.rst               |  9 +++++
 drivers/gpu/drm/i915/display/intel_dsb.c | 68 ++++++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+)

diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index e249ea7b0ec7..465779670fd4 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -246,6 +246,15 @@ Display PLLs
 .. kernel-doc:: drivers/gpu/drm/i915/display/intel_dpll_mgr.h
    :internal:
 
+Display State Buffer
+--------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/display/intel_dsb.c
+   :doc: DSB
+
+.. kernel-doc:: drivers/gpu/drm/i915/display/intel_dsb.c
+   :internal:
+
 Memory Management and Command Submission
 ========================================
 
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index f4c0b37683a5..0a0a1536ac96 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -9,6 +9,23 @@
 
 #define DSB_BUF_SIZE    (2 * PAGE_SIZE)
 
+/**
+ * DOC: DSB
+ *
+ * A DSB (Display State Buffer) is a queue of MMIO instructions in the memory
+ * which can be offloaded to DSB HW in Display Controller. DSB HW is a DMA
+ * engine that can be programmed to download the DSB from memory.
+ * It allows driver to batch submit display HW programming. This helps to
+ * reduce loading time and CPU activity, thereby making the context switch
+ * faster. DSB Support added from Gen12 Intel graphics based platform.
+ *
+ * DSB's can access only the pipe, plane, and transcoder Data Island Packet
+ * registers.
+ *
+ * DSB HW can support only register writes (both indexed and direct MMIO
+ * writes). There are no registers reads possible with DSB HW engine.
+ */
+
 /* DSB opcodes. */
 #define DSB_OPCODE_SHIFT		24
 #define DSB_OPCODE_MMIO_WRITE		0x1
@@ -66,6 +83,17 @@ static inline bool intel_dsb_disable_engine(struct intel_dsb *dsb)
 	return true;
 }
 
+/**
+ * intel_dsb_get() - Allocate DSB context and return a DSB instance.
+ * @crtc: intel_crtc structure to get pipe info.
+ *
+ * This function provides handle of a DSB instance, for the further DSB
+ * operations.
+ *
+ * Returns: address of Intel_dsb instance requested for.
+ * Failure: Returns the same DSB instance, but without a command buffer.
+ */
+
 struct intel_dsb *
 intel_dsb_get(struct intel_crtc *crtc)
 {
@@ -116,6 +144,14 @@ err:
 	return dsb;
 }
 
+/**
+ * intel_dsb_put() - To destroy DSB context.
+ * @dsb: intel_dsb structure.
+ *
+ * This function destroys the DSB context allocated by a dsb_get(), by
+ * unpinning and releasing the VMA object associated with it.
+ */
+
 void intel_dsb_put(struct intel_dsb *dsb)
 {
 	struct intel_crtc *crtc = container_of(dsb, typeof(*crtc), dsb);
@@ -138,6 +174,19 @@ void intel_dsb_put(struct intel_dsb *dsb)
 	}
 }
 
+/**
+ * intel_dsb_indexed_reg_write() -Write to the DSB context for auto
+ * increment register.
+ * @dsb: intel_dsb structure.
+ * @reg: register address.
+ * @val: value.
+ *
+ * This function is used for writing register-value pair in command
+ * buffer of DSB for auto-increment register. During command buffer overflow,
+ * a warning is thrown and rest all erroneous condition register programming
+ * is done through mmio write.
+ */
+
 void intel_dsb_indexed_reg_write(struct intel_dsb *dsb, i915_reg_t reg,
 				 u32 val)
 {
@@ -202,6 +251,18 @@ void intel_dsb_indexed_reg_write(struct intel_dsb *dsb, i915_reg_t reg,
 		buf[dsb->free_pos] = 0;
 }
 
+/**
+ * intel_dsb_reg_write() -Write to the DSB context for normal
+ * register.
+ * @dsb: intel_dsb structure.
+ * @reg: register address.
+ * @val: value.
+ *
+ * This function is used for writing register-value pair in command
+ * buffer of DSB. During command buffer overflow, a warning  is thrown
+ * and rest all erroneous condition register programming is done
+ * through mmio write.
+ */
 void intel_dsb_reg_write(struct intel_dsb *dsb, i915_reg_t reg, u32 val)
 {
 	struct intel_crtc *crtc = container_of(dsb, typeof(*crtc), dsb);
@@ -225,6 +286,13 @@ void intel_dsb_reg_write(struct intel_dsb *dsb, i915_reg_t reg, u32 val)
 			       i915_mmio_reg_offset(reg);
 }
 
+/**
+ * intel_dsb_commit() - Trigger workload execution of DSB.
+ * @dsb: intel_dsb structure.
+ *
+ * This function is used to do actual write to hardware using DSB.
+ * On errors, fall back to MMIO. Also this function help to reset the context.
+ */
 void intel_dsb_commit(struct intel_dsb *dsb)
 {
 	struct intel_crtc *crtc = container_of(dsb, typeof(*crtc), dsb);
-- 
cgit v1.2.3


From 8581d51055a08cc6eb061c8856062290e8582ce4 Mon Sep 17 00:00:00 2001
From: "Lowry Li (Arm Technology China)" <Lowry.Li@arm.com>
Date: Wed, 31 Jul 2019 11:04:38 +0000
Subject: drm: Free the writeback_job when it with an empty fb

Adds the check if the writeback_job with an empty fb, then it should
be freed in atomic_check phase.

With this change, the driver users will not check empty fb case any more.
So refined accordingly.

Signed-off-by: Lowry Li (Arm Technology China) <lowry.li@arm.com>
Reviewed-by: Liviu Dudau <liviu.dudau@arm.com>
Reviewed-by: James Qian Wang (Arm Technology China) <james.qian.wang@arm.com>
Signed-off-by: james qian wang (Arm Technology China) <james.qian.wang@arm.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1564571048-15029-2-git-send-email-lowry.li@arm.com
---
 drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c |  3 +--
 drivers/gpu/drm/arm/malidp_mw.c                          |  4 ++--
 drivers/gpu/drm/drm_atomic.c                             | 13 +++++++++----
 drivers/gpu/drm/rcar-du/rcar_du_writeback.c              |  4 ++--
 drivers/gpu/drm/vc4/vc4_txp.c                            |  5 ++---
 5 files changed, 16 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
index 2851cac94d86..23fbee268119 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
@@ -43,9 +43,8 @@ komeda_wb_encoder_atomic_check(struct drm_encoder *encoder,
 	struct komeda_data_flow_cfg dflow;
 	int err;
 
-	if (!writeback_job || !writeback_job->fb) {
+	if (!writeback_job)
 		return 0;
-	}
 
 	if (!crtc_st->active) {
 		DRM_DEBUG_ATOMIC("Cannot write the composition result out on a inactive CRTC.\n");
diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
index 2e812525025d..a59227b2cdb5 100644
--- a/drivers/gpu/drm/arm/malidp_mw.c
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -130,7 +130,7 @@ malidp_mw_encoder_atomic_check(struct drm_encoder *encoder,
 	struct drm_framebuffer *fb;
 	int i, n_planes;
 
-	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+	if (!conn_state->writeback_job)
 		return 0;
 
 	fb = conn_state->writeback_job->fb;
@@ -247,7 +247,7 @@ void malidp_mw_atomic_commit(struct drm_device *drm,
 
 	mw_state = to_mw_state(conn_state);
 
-	if (conn_state->writeback_job && conn_state->writeback_job->fb) {
+	if (conn_state->writeback_job) {
 		struct drm_framebuffer *fb = conn_state->writeback_job->fb;
 
 		DRM_DEV_DEBUG_DRIVER(drm->dev,
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 419381abbdd1..14aeaf736321 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -430,10 +430,15 @@ static int drm_atomic_connector_check(struct drm_connector *connector,
 		return -EINVAL;
 	}
 
-	if (writeback_job->out_fence && !writeback_job->fb) {
-		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n",
-				 connector->base.id, connector->name);
-		return -EINVAL;
+	if (!writeback_job->fb) {
+		if (writeback_job->out_fence) {
+			DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n",
+					 connector->base.id, connector->name);
+			return -EINVAL;
+		}
+
+		drm_writeback_cleanup_job(writeback_job);
+		state->writeback_job = NULL;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
index ae07290bba6a..04efa78d70b6 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c
@@ -147,7 +147,7 @@ static int rcar_du_wb_enc_atomic_check(struct drm_encoder *encoder,
 	struct drm_device *dev = encoder->dev;
 	struct drm_framebuffer *fb;
 
-	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+	if (!conn_state->writeback_job)
 		return 0;
 
 	fb = conn_state->writeback_job->fb;
@@ -221,7 +221,7 @@ void rcar_du_writeback_setup(struct rcar_du_crtc *rcrtc,
 	unsigned int i;
 
 	state = rcrtc->writeback.base.state;
-	if (!state || !state->writeback_job || !state->writeback_job->fb)
+	if (!state || !state->writeback_job)
 		return;
 
 	fb = state->writeback_job->fb;
diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c
index 96f91c1b4b6e..e92fa1275034 100644
--- a/drivers/gpu/drm/vc4/vc4_txp.c
+++ b/drivers/gpu/drm/vc4/vc4_txp.c
@@ -229,7 +229,7 @@ static int vc4_txp_connector_atomic_check(struct drm_connector *conn,
 	int i;
 
 	conn_state = drm_atomic_get_new_connector_state(state, conn);
-	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+	if (!conn_state->writeback_job)
 		return 0;
 
 	crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc);
@@ -269,8 +269,7 @@ static void vc4_txp_connector_atomic_commit(struct drm_connector *conn,
 	u32 ctrl;
 	int i;
 
-	if (WARN_ON(!conn_state->writeback_job ||
-		    !conn_state->writeback_job->fb))
+	if (WARN_ON(!conn_state->writeback_job))
 		return;
 
 	mode = &conn_state->crtc->state->adjusted_mode;
-- 
cgit v1.2.3


From b1066a123538044117f0a78ba8c6a50cf5a04c86 Mon Sep 17 00:00:00 2001
From: "Lowry Li (Arm Technology China)" <Lowry.Li@arm.com>
Date: Wed, 31 Jul 2019 11:04:45 +0000
Subject: drm: Clear the fence pointer when writeback job signaled

During it signals the completion of a writeback job, after releasing
the out_fence, we'd clear the pointer.

Check if fence left over in drm_writeback_cleanup_job(), release it.

Signed-off-by: Lowry Li (Arm Technology China) <lowry.li@arm.com>
Reviewed-by: Brian Starkey <brian.starkey@arm.com>
Reviewed-by: James Qian Wang (Arm Technology China) <james.qian.wang@arm.com>
Signed-off-by: james qian wang (Arm Technology China) <james.qian.wang@arm.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1564571048-15029-3-git-send-email-lowry.li@arm.com
---
 drivers/gpu/drm/drm_writeback.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
index ff138b6ec48b..43d9e3bb3a94 100644
--- a/drivers/gpu/drm/drm_writeback.c
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -324,6 +324,9 @@ void drm_writeback_cleanup_job(struct drm_writeback_job *job)
 	if (job->fb)
 		drm_framebuffer_put(job->fb);
 
+	if (job->out_fence)
+		dma_fence_put(job->out_fence);
+
 	kfree(job);
 }
 EXPORT_SYMBOL(drm_writeback_cleanup_job);
@@ -366,25 +369,29 @@ drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector,
 {
 	unsigned long flags;
 	struct drm_writeback_job *job;
+	struct dma_fence *out_fence;
 
 	spin_lock_irqsave(&wb_connector->job_lock, flags);
 	job = list_first_entry_or_null(&wb_connector->job_queue,
 				       struct drm_writeback_job,
 				       list_entry);
-	if (job) {
+	if (job)
 		list_del(&job->list_entry);
-		if (job->out_fence) {
-			if (status)
-				dma_fence_set_error(job->out_fence, status);
-			dma_fence_signal(job->out_fence);
-			dma_fence_put(job->out_fence);
-		}
-	}
+
 	spin_unlock_irqrestore(&wb_connector->job_lock, flags);
 
 	if (WARN_ON(!job))
 		return;
 
+	out_fence = job->out_fence;
+	if (out_fence) {
+		if (status)
+			dma_fence_set_error(out_fence, status);
+		dma_fence_signal(out_fence);
+		dma_fence_put(out_fence);
+		job->out_fence = NULL;
+	}
+
 	INIT_WORK(&job->cleanup_work, cleanup_work);
 	queue_work(system_long_wq, &job->cleanup_work);
 }
-- 
cgit v1.2.3


From 87c1694533c947bf950251df3da04a32a05ede64 Mon Sep 17 00:00:00 2001
From: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Date: Fri, 20 Sep 2019 11:39:18 +0300
Subject: drm/i915: save AUD_FREQ_CNTRL state at audio domain suspend

When audio power domain is suspended, the display driver must
save state of AUD_FREQ_CNTRL on Tiger Lake and Ice Lake
systems. The initial value of the register is set by BIOS and
is read by driver during the audio component init sequence.

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920083918.27057-1-kai.vehmanen@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_audio.c | 17 +++++++++++++++--
 drivers/gpu/drm/i915/i915_drv.h            |  1 +
 drivers/gpu/drm/i915/i915_reg.h            |  2 ++
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index aac089c79ceb..54638d99e021 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -852,10 +852,17 @@ static unsigned long i915_audio_component_get_power(struct device *kdev)
 
 	ret = intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO);
 
-	/* Force CDCLK to 2*BCLK as long as we need audio to be powered. */
-	if (dev_priv->audio_power_refcount++ == 0)
+	if (dev_priv->audio_power_refcount++ == 0) {
+		if (IS_TIGERLAKE(dev_priv) || IS_ICELAKE(dev_priv)) {
+			I915_WRITE(AUD_FREQ_CNTRL, dev_priv->audio_freq_cntrl);
+			DRM_DEBUG_KMS("restored AUD_FREQ_CNTRL to 0x%x\n",
+				      dev_priv->audio_freq_cntrl);
+		}
+
+		/* Force CDCLK to 2*BCLK as long as we need audio powered. */
 		if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
 			glk_force_audio_cdclk(dev_priv, true);
+	}
 
 	return ret;
 }
@@ -1116,6 +1123,12 @@ static void i915_audio_component_init(struct drm_i915_private *dev_priv)
 		return;
 	}
 
+	if (IS_TIGERLAKE(dev_priv) || IS_ICELAKE(dev_priv)) {
+		dev_priv->audio_freq_cntrl = I915_READ(AUD_FREQ_CNTRL);
+		DRM_DEBUG_KMS("init value of AUD_FREQ_CNTRL of 0x%x\n",
+			      dev_priv->audio_freq_cntrl);
+	}
+
 	dev_priv->audio_component_registered = true;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 07f1e89a55ca..fcf7423075ef 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1541,6 +1541,7 @@ struct drm_i915_private {
 	 */
 	struct mutex av_mutex;
 	int audio_power_refcount;
+	u32 audio_freq_cntrl;
 
 	struct {
 		struct mutex mutex;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 8649a3028963..6ecb64c042ef 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -9127,6 +9127,8 @@ enum {
 #define HSW_AUD_CHICKENBIT			_MMIO(0x65f10)
 #define   SKL_AUD_CODEC_WAKE_SIGNAL		(1 << 15)
 
+#define AUD_FREQ_CNTRL			_MMIO(0x65900)
+
 /*
  * HSW - ICL power wells
  *
-- 
cgit v1.2.3


From 2d6f6f359fd841a6ce3133470859035037ff0f75 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 20 Sep 2019 21:54:16 +0300
Subject: drm/i915: add i915_driver_modeset_remove()

For completeness, add counterpart to i915_driver_modeset_probe() and
remove the asymmetry in the probe/remove parts. No functional changes.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920185421.17822-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/i915_drv.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index c95986a984c8..acccf852e654 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -447,6 +447,20 @@ static int i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
+static void i915_driver_modeset_remove(struct drm_i915_private *i915)
+{
+	struct pci_dev *pdev = i915->drm.pdev;
+
+	intel_modeset_driver_remove(&i915->drm);
+
+	intel_bios_driver_remove(i915);
+
+	vga_switcheroo_unregister_client(pdev);
+	vga_client_register(pdev, NULL, NULL, NULL);
+
+	intel_csr_ucode_fini(i915);
+}
+
 static void intel_init_dpio(struct drm_i915_private *dev_priv)
 {
 	/*
@@ -1623,8 +1637,6 @@ out_fini:
 
 void i915_driver_remove(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = i915->drm.pdev;
-
 	disable_rpm_wakeref_asserts(&i915->runtime_pm);
 
 	i915_driver_unregister(i915);
@@ -1645,14 +1657,7 @@ void i915_driver_remove(struct drm_i915_private *i915)
 
 	intel_gvt_driver_remove(i915);
 
-	intel_modeset_driver_remove(&i915->drm);
-
-	intel_bios_driver_remove(i915);
-
-	vga_switcheroo_unregister_client(pdev);
-	vga_client_register(pdev, NULL, NULL, NULL);
-
-	intel_csr_ucode_fini(i915);
+	i915_driver_modeset_remove(i915);
 
 	/* Free error state after interrupts are fully disabled. */
 	cancel_delayed_work_sync(&i915->gt.hangcheck.work);
-- 
cgit v1.2.3


From 5bcd53aa39f3dd054328e0a29a343e0254709908 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 20 Sep 2019 21:54:17 +0300
Subject: drm/i915: pass i915 to i915_driver_modeset_probe()

In general, prefer struct drm_i915_private * over struct drm_device *
when either will do. Rename the local variable to i915. No functional
changes.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920185421.17822-2-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/i915_drv.c | 59 ++++++++++++++++++++---------------------
 1 file changed, 29 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index acccf852e654..fbf1b9e1e059 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -329,23 +329,22 @@ static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {
 	.can_switch = i915_switcheroo_can_switch,
 };
 
-static int i915_driver_modeset_probe(struct drm_device *dev)
+static int i915_driver_modeset_probe(struct drm_i915_private *i915)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct pci_dev *pdev = i915->drm.pdev;
 	int ret;
 
-	if (i915_inject_probe_failure(dev_priv))
+	if (i915_inject_probe_failure(i915))
 		return -ENODEV;
 
-	if (HAS_DISPLAY(dev_priv) && INTEL_DISPLAY_ENABLED(dev_priv)) {
-		ret = drm_vblank_init(&dev_priv->drm,
-				      INTEL_NUM_PIPES(dev_priv));
+	if (HAS_DISPLAY(i915) && INTEL_DISPLAY_ENABLED(i915)) {
+		ret = drm_vblank_init(&i915->drm,
+				      INTEL_NUM_PIPES(i915));
 		if (ret)
 			goto out;
 	}
 
-	intel_bios_init(dev_priv);
+	intel_bios_init(i915);
 
 	/* If we have > 1 VGA cards, then we need to arbitrate access
 	 * to the common VGA resources.
@@ -354,7 +353,7 @@ static int i915_driver_modeset_probe(struct drm_device *dev)
 	 * then we do not take part in VGA arbitration and the
 	 * vga_client_register() fails with -ENODEV.
 	 */
-	ret = vga_client_register(pdev, dev_priv, NULL, i915_vga_set_decode);
+	ret = vga_client_register(pdev, i915, NULL, i915_vga_set_decode);
 	if (ret && ret != -ENODEV)
 		goto out;
 
@@ -365,56 +364,56 @@ static int i915_driver_modeset_probe(struct drm_device *dev)
 		goto cleanup_vga_client;
 
 	/* must happen before intel_power_domains_init_hw() on VLV/CHV */
-	intel_update_rawclk(dev_priv);
+	intel_update_rawclk(i915);
 
-	intel_power_domains_init_hw(dev_priv, false);
+	intel_power_domains_init_hw(i915, false);
 
-	intel_csr_ucode_init(dev_priv);
+	intel_csr_ucode_init(i915);
 
-	ret = intel_irq_install(dev_priv);
+	ret = intel_irq_install(i915);
 	if (ret)
 		goto cleanup_csr;
 
-	intel_gmbus_setup(dev_priv);
+	intel_gmbus_setup(i915);
 
 	/* Important: The output setup functions called by modeset_init need
 	 * working irqs for e.g. gmbus and dp aux transfers. */
-	ret = intel_modeset_init(dev);
+	ret = intel_modeset_init(&i915->drm);
 	if (ret)
 		goto cleanup_irq;
 
-	ret = i915_gem_init(dev_priv);
+	ret = i915_gem_init(i915);
 	if (ret)
 		goto cleanup_modeset;
 
-	intel_overlay_setup(dev_priv);
+	intel_overlay_setup(i915);
 
-	if (!HAS_DISPLAY(dev_priv) || !INTEL_DISPLAY_ENABLED(dev_priv))
+	if (!HAS_DISPLAY(i915) || !INTEL_DISPLAY_ENABLED(i915))
 		return 0;
 
-	ret = intel_fbdev_init(dev);
+	ret = intel_fbdev_init(&i915->drm);
 	if (ret)
 		goto cleanup_gem;
 
 	/* Only enable hotplug handling once the fbdev is fully set up. */
-	intel_hpd_init(dev_priv);
+	intel_hpd_init(i915);
 
-	intel_init_ipc(dev_priv);
+	intel_init_ipc(i915);
 
 	return 0;
 
 cleanup_gem:
-	i915_gem_suspend(dev_priv);
-	i915_gem_driver_remove(dev_priv);
-	i915_gem_driver_release(dev_priv);
+	i915_gem_suspend(i915);
+	i915_gem_driver_remove(i915);
+	i915_gem_driver_release(i915);
 cleanup_modeset:
-	intel_modeset_driver_remove(dev);
+	intel_modeset_driver_remove(&i915->drm);
 cleanup_irq:
-	intel_irq_uninstall(dev_priv);
-	intel_gmbus_teardown(dev_priv);
+	intel_irq_uninstall(i915);
+	intel_gmbus_teardown(i915);
 cleanup_csr:
-	intel_csr_ucode_fini(dev_priv);
-	intel_power_domains_driver_remove(dev_priv);
+	intel_csr_ucode_fini(i915);
+	intel_power_domains_driver_remove(i915);
 	vga_switcheroo_unregister_client(pdev);
 cleanup_vga_client:
 	vga_client_register(pdev, NULL, NULL, NULL);
@@ -1607,7 +1606,7 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret < 0)
 		goto out_cleanup_mmio;
 
-	ret = i915_driver_modeset_probe(&dev_priv->drm);
+	ret = i915_driver_modeset_probe(dev_priv);
 	if (ret < 0)
 		goto out_cleanup_hw;
 
-- 
cgit v1.2.3


From 9980c3c11060e177e6ccb0012371ade24a9543a4 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 20 Sep 2019 21:54:18 +0300
Subject: drm/i915: pass i915 to intel_modeset_driver_remove()

In general, prefer struct drm_i915_private * over struct drm_device *
when either will do. Rename the local variable to i915. Also propagate
to intel_hpd_poll_fini(). No functional changes.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920185421.17822-3-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 38 +++++++++++++---------------
 drivers/gpu/drm/i915/display/intel_display.h |  2 +-
 drivers/gpu/drm/i915/i915_drv.c              |  4 +--
 3 files changed, 21 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index f5f655cde43a..74da12d3911c 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -17114,13 +17114,13 @@ void intel_display_resume(struct drm_device *dev)
 		drm_atomic_state_put(state);
 }
 
-static void intel_hpd_poll_fini(struct drm_device *dev)
+static void intel_hpd_poll_fini(struct drm_i915_private *i915)
 {
 	struct intel_connector *connector;
 	struct drm_connector_list_iter conn_iter;
 
 	/* Kill all the work that may have been queued by hpd. */
-	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_connector_list_iter_begin(&i915->drm, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter) {
 		if (connector->modeset_retry_work.func)
 			cancel_work_sync(&connector->modeset_retry_work);
@@ -17132,51 +17132,49 @@ static void intel_hpd_poll_fini(struct drm_device *dev)
 	drm_connector_list_iter_end(&conn_iter);
 }
 
-void intel_modeset_driver_remove(struct drm_device *dev)
+void intel_modeset_driver_remove(struct drm_i915_private *i915)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	flush_workqueue(dev_priv->flip_wq);
-	flush_workqueue(dev_priv->modeset_wq);
+	flush_workqueue(i915->flip_wq);
+	flush_workqueue(i915->modeset_wq);
 
-	flush_work(&dev_priv->atomic_helper.free_work);
-	WARN_ON(!llist_empty(&dev_priv->atomic_helper.free_list));
+	flush_work(&i915->atomic_helper.free_work);
+	WARN_ON(!llist_empty(&i915->atomic_helper.free_list));
 
 	/*
 	 * Interrupts and polling as the first thing to avoid creating havoc.
 	 * Too much stuff here (turning of connectors, ...) would
 	 * experience fancy races otherwise.
 	 */
-	intel_irq_uninstall(dev_priv);
+	intel_irq_uninstall(i915);
 
 	/*
 	 * Due to the hpd irq storm handling the hotplug work can re-arm the
 	 * poll handlers. Hence disable polling after hpd handling is shut down.
 	 */
-	intel_hpd_poll_fini(dev);
+	intel_hpd_poll_fini(i915);
 
 	/* poll work can call into fbdev, hence clean that up afterwards */
-	intel_fbdev_fini(dev_priv);
+	intel_fbdev_fini(i915);
 
 	intel_unregister_dsm_handler();
 
-	intel_fbc_global_disable(dev_priv);
+	intel_fbc_global_disable(i915);
 
 	/* flush any delayed tasks or pending work */
 	flush_scheduled_work();
 
-	intel_hdcp_component_fini(dev_priv);
+	intel_hdcp_component_fini(i915);
 
-	drm_mode_config_cleanup(dev);
+	drm_mode_config_cleanup(&i915->drm);
 
-	intel_overlay_cleanup(dev_priv);
+	intel_overlay_cleanup(i915);
 
-	intel_gmbus_teardown(dev_priv);
+	intel_gmbus_teardown(i915);
 
-	destroy_workqueue(dev_priv->flip_wq);
-	destroy_workqueue(dev_priv->modeset_wq);
+	destroy_workqueue(i915->flip_wq);
+	destroy_workqueue(i915->modeset_wq);
 
-	intel_fbc_cleanup_cfb(dev_priv);
+	intel_fbc_cleanup_cfb(i915);
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index b1ae0e59c715..933cbe36bb59 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -578,7 +578,7 @@ void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
 /* modesetting */
 void intel_modeset_init_hw(struct drm_device *dev);
 int intel_modeset_init(struct drm_device *dev);
-void intel_modeset_driver_remove(struct drm_device *dev);
+void intel_modeset_driver_remove(struct drm_i915_private *i915);
 int intel_modeset_vga_set_state(struct drm_i915_private *dev_priv, bool state);
 void intel_display_resume(struct drm_device *dev);
 void i915_redisable_vga(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index fbf1b9e1e059..9b1788b4589e 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -407,7 +407,7 @@ cleanup_gem:
 	i915_gem_driver_remove(i915);
 	i915_gem_driver_release(i915);
 cleanup_modeset:
-	intel_modeset_driver_remove(&i915->drm);
+	intel_modeset_driver_remove(i915);
 cleanup_irq:
 	intel_irq_uninstall(i915);
 	intel_gmbus_teardown(i915);
@@ -450,7 +450,7 @@ static void i915_driver_modeset_remove(struct drm_i915_private *i915)
 {
 	struct pci_dev *pdev = i915->drm.pdev;
 
-	intel_modeset_driver_remove(&i915->drm);
+	intel_modeset_driver_remove(i915);
 
 	intel_bios_driver_remove(i915);
 
-- 
cgit v1.2.3


From 064bd628fde6665c38d8aa02ff7a0a9ad36db482 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 20 Sep 2019 21:54:19 +0300
Subject: drm/i915: abstract intel_panel_sanitize_ssc() from
 intel_modeset_init()

The code is too specific and detailed to have open in a high level
function. Abstract away. As a drive-by improvement switch to using
enableddisabled() in logging and git rid of a redundant !!. No
functional changes.

v2: drop the !! while at it too (Chris)

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920185421.17822-4-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 39 ++++++++++++++++------------
 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 74da12d3911c..9df7ee5a26bb 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -7552,6 +7552,27 @@ intel_link_compute_m_n(u16 bits_per_pixel, int nlanes,
 		    constant_n);
 }
 
+static void intel_panel_sanitize_ssc(struct drm_i915_private *dev_priv)
+{
+	/*
+	 * There may be no VBT; and if the BIOS enabled SSC we can
+	 * just keep using it to avoid unnecessary flicker.  Whereas if the
+	 * BIOS isn't using it, don't assume it will work even if the VBT
+	 * indicates as much.
+	 */
+	if (HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv)) {
+		bool bios_lvds_use_ssc = I915_READ(PCH_DREF_CONTROL) &
+			DREF_SSC1_ENABLE;
+
+		if (dev_priv->vbt.lvds_use_ssc != bios_lvds_use_ssc) {
+			DRM_DEBUG_KMS("SSC %s by BIOS, overriding VBT which says %s\n",
+				      enableddisabled(bios_lvds_use_ssc),
+				      enableddisabled(dev_priv->vbt.lvds_use_ssc));
+			dev_priv->vbt.lvds_use_ssc = bios_lvds_use_ssc;
+		}
+	}
+}
+
 static inline bool intel_panel_use_ssc(struct drm_i915_private *dev_priv)
 {
 	if (i915_modparams.panel_use_ssc >= 0)
@@ -16203,23 +16224,7 @@ int intel_modeset_init(struct drm_device *dev)
 
 	intel_init_pm(dev_priv);
 
-	/*
-	 * There may be no VBT; and if the BIOS enabled SSC we can
-	 * just keep using it to avoid unnecessary flicker.  Whereas if the
-	 * BIOS isn't using it, don't assume it will work even if the VBT
-	 * indicates as much.
-	 */
-	if (HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv)) {
-		bool bios_lvds_use_ssc = !!(I915_READ(PCH_DREF_CONTROL) &
-					    DREF_SSC1_ENABLE);
-
-		if (dev_priv->vbt.lvds_use_ssc != bios_lvds_use_ssc) {
-			DRM_DEBUG_KMS("SSC %sabled by BIOS, overriding VBT which says %sabled\n",
-				     bios_lvds_use_ssc ? "en" : "dis",
-				     dev_priv->vbt.lvds_use_ssc ? "en" : "dis");
-			dev_priv->vbt.lvds_use_ssc = bios_lvds_use_ssc;
-		}
-	}
+	intel_panel_sanitize_ssc(dev_priv);
 
 	/*
 	 * Maximum framebuffer dimensions, chosen to match
-- 
cgit v1.2.3


From e1a3d9895ddcec20cbb7353e77759589cf010275 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 20 Sep 2019 21:54:20 +0300
Subject: drm/i915: abstract intel_mode_config_init() from intel_modeset_init()

The i915 specific mode config init code is too specific and detailed to
have open in a high level function. Abstract away. No functional
changes.

v2: nest drm_mode_config_init() in the function too (Chris)

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920185421.17822-5-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 87 +++++++++++++++-------------
 1 file changed, 47 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 9df7ee5a26bb..06946f9ffd27 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -16187,6 +16187,52 @@ out:
 	return ret;
 }
 
+static void intel_mode_config_init(struct drm_i915_private *i915)
+{
+	struct drm_mode_config *mode_config = &i915->drm.mode_config;
+
+	drm_mode_config_init(&i915->drm);
+
+	mode_config->min_width = 0;
+	mode_config->min_height = 0;
+
+	mode_config->preferred_depth = 24;
+	mode_config->prefer_shadow = 1;
+
+	mode_config->allow_fb_modifiers = true;
+
+	mode_config->funcs = &intel_mode_funcs;
+
+	/*
+	 * Maximum framebuffer dimensions, chosen to match
+	 * the maximum render engine surface size on gen4+.
+	 */
+	if (INTEL_GEN(i915) >= 7) {
+		mode_config->max_width = 16384;
+		mode_config->max_height = 16384;
+	} else if (INTEL_GEN(i915) >= 4) {
+		mode_config->max_width = 8192;
+		mode_config->max_height = 8192;
+	} else if (IS_GEN(i915, 3)) {
+		mode_config->max_width = 4096;
+		mode_config->max_height = 4096;
+	} else {
+		mode_config->max_width = 2048;
+		mode_config->max_height = 2048;
+	}
+
+	if (IS_I845G(i915) || IS_I865G(i915)) {
+		mode_config->cursor_width = IS_I845G(i915) ? 64 : 512;
+		mode_config->cursor_height = 1023;
+	} else if (IS_GEN(i915, 2)) {
+		mode_config->cursor_width = 64;
+		mode_config->cursor_height = 64;
+	} else {
+		mode_config->cursor_width = 256;
+		mode_config->cursor_height = 256;
+	}
+}
+
 int intel_modeset_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -16198,22 +16244,12 @@ int intel_modeset_init(struct drm_device *dev)
 	dev_priv->flip_wq = alloc_workqueue("i915_flip", WQ_HIGHPRI |
 					    WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE);
 
-	drm_mode_config_init(dev);
+	intel_mode_config_init(dev_priv);
 
 	ret = intel_bw_init(dev_priv);
 	if (ret)
 		return ret;
 
-	dev->mode_config.min_width = 0;
-	dev->mode_config.min_height = 0;
-
-	dev->mode_config.preferred_depth = 24;
-	dev->mode_config.prefer_shadow = 1;
-
-	dev->mode_config.allow_fb_modifiers = true;
-
-	dev->mode_config.funcs = &intel_mode_funcs;
-
 	init_llist_head(&dev_priv->atomic_helper.free_list);
 	INIT_WORK(&dev_priv->atomic_helper.free_work,
 		  intel_atomic_helper_free_state_worker);
@@ -16226,35 +16262,6 @@ int intel_modeset_init(struct drm_device *dev)
 
 	intel_panel_sanitize_ssc(dev_priv);
 
-	/*
-	 * Maximum framebuffer dimensions, chosen to match
-	 * the maximum render engine surface size on gen4+.
-	 */
-	if (INTEL_GEN(dev_priv) >= 7) {
-		dev->mode_config.max_width = 16384;
-		dev->mode_config.max_height = 16384;
-	} else if (INTEL_GEN(dev_priv) >= 4) {
-		dev->mode_config.max_width = 8192;
-		dev->mode_config.max_height = 8192;
-	} else if (IS_GEN(dev_priv, 3)) {
-		dev->mode_config.max_width = 4096;
-		dev->mode_config.max_height = 4096;
-	} else {
-		dev->mode_config.max_width = 2048;
-		dev->mode_config.max_height = 2048;
-	}
-
-	if (IS_I845G(dev_priv) || IS_I865G(dev_priv)) {
-		dev->mode_config.cursor_width = IS_I845G(dev_priv) ? 64 : 512;
-		dev->mode_config.cursor_height = 1023;
-	} else if (IS_GEN(dev_priv, 2)) {
-		dev->mode_config.cursor_width = 64;
-		dev->mode_config.cursor_height = 64;
-	} else {
-		dev->mode_config.cursor_width = 256;
-		dev->mode_config.cursor_height = 256;
-	}
-
 	DRM_DEBUG_KMS("%d display pipe%s available.\n",
 		      INTEL_NUM_PIPES(dev_priv),
 		      INTEL_NUM_PIPES(dev_priv) > 1 ? "s" : "");
-- 
cgit v1.2.3


From 6cd02e77757a8fb0089053045932455355d2c4fd Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 20 Sep 2019 21:54:21 +0300
Subject: drm/i915: pass i915 to intel_modeset_init() and
 intel_modeset_init_hw()

In general, prefer struct drm_i915_private * over struct drm_device *
when either will do. Rename the local variables to i915. No functional
changes.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920185421.17822-6-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 69 +++++++++++++---------------
 drivers/gpu/drm/i915/display/intel_display.h |  4 +-
 drivers/gpu/drm/i915/i915_drv.c              |  4 +-
 3 files changed, 37 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 06946f9ffd27..5ecf54270181 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -4360,7 +4360,7 @@ void intel_finish_reset(struct drm_i915_private *dev_priv)
 		 * so need a full re-initialization.
 		 */
 		intel_pps_unlock_regs_wa(dev_priv);
-		intel_modeset_init_hw(dev);
+		intel_modeset_init_hw(dev_priv);
 		intel_init_clock_gating(dev_priv);
 
 		spin_lock_irq(&dev_priv->irq_lock);
@@ -16021,13 +16021,11 @@ static void i915_disable_vga(struct drm_i915_private *dev_priv)
 	POSTING_READ(vga_reg);
 }
 
-void intel_modeset_init_hw(struct drm_device *dev)
+void intel_modeset_init_hw(struct drm_i915_private *i915)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	intel_update_cdclk(dev_priv);
-	intel_dump_cdclk_state(&dev_priv->cdclk.hw, "Current CDCLK");
-	dev_priv->cdclk.logical = dev_priv->cdclk.actual = dev_priv->cdclk.hw;
+	intel_update_cdclk(i915);
+	intel_dump_cdclk_state(&i915->cdclk.hw, "Current CDCLK");
+	i915->cdclk.logical = i915->cdclk.actual = i915->cdclk.hw;
 }
 
 /*
@@ -16233,42 +16231,42 @@ static void intel_mode_config_init(struct drm_i915_private *i915)
 	}
 }
 
-int intel_modeset_init(struct drm_device *dev)
+int intel_modeset_init(struct drm_i915_private *i915)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_device *dev = &i915->drm;
 	enum pipe pipe;
 	struct intel_crtc *crtc;
 	int ret;
 
-	dev_priv->modeset_wq = alloc_ordered_workqueue("i915_modeset", 0);
-	dev_priv->flip_wq = alloc_workqueue("i915_flip", WQ_HIGHPRI |
-					    WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE);
+	i915->modeset_wq = alloc_ordered_workqueue("i915_modeset", 0);
+	i915->flip_wq = alloc_workqueue("i915_flip", WQ_HIGHPRI |
+					WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE);
 
-	intel_mode_config_init(dev_priv);
+	intel_mode_config_init(i915);
 
-	ret = intel_bw_init(dev_priv);
+	ret = intel_bw_init(i915);
 	if (ret)
 		return ret;
 
-	init_llist_head(&dev_priv->atomic_helper.free_list);
-	INIT_WORK(&dev_priv->atomic_helper.free_work,
+	init_llist_head(&i915->atomic_helper.free_list);
+	INIT_WORK(&i915->atomic_helper.free_work,
 		  intel_atomic_helper_free_state_worker);
 
-	intel_init_quirks(dev_priv);
+	intel_init_quirks(i915);
 
-	intel_fbc_init(dev_priv);
+	intel_fbc_init(i915);
 
-	intel_init_pm(dev_priv);
+	intel_init_pm(i915);
 
-	intel_panel_sanitize_ssc(dev_priv);
+	intel_panel_sanitize_ssc(i915);
 
 	DRM_DEBUG_KMS("%d display pipe%s available.\n",
-		      INTEL_NUM_PIPES(dev_priv),
-		      INTEL_NUM_PIPES(dev_priv) > 1 ? "s" : "");
+		      INTEL_NUM_PIPES(i915),
+		      INTEL_NUM_PIPES(i915) > 1 ? "s" : "");
 
-	if (HAS_DISPLAY(dev_priv) && INTEL_DISPLAY_ENABLED(dev_priv)) {
-		for_each_pipe(dev_priv, pipe) {
-			ret = intel_crtc_init(dev_priv, pipe);
+	if (HAS_DISPLAY(i915) && INTEL_DISPLAY_ENABLED(i915)) {
+		for_each_pipe(i915, pipe) {
+			ret = intel_crtc_init(i915, pipe);
 			if (ret) {
 				drm_mode_config_cleanup(dev);
 				return ret;
@@ -16277,19 +16275,19 @@ int intel_modeset_init(struct drm_device *dev)
 	}
 
 	intel_shared_dpll_init(dev);
-	intel_update_fdi_pll_freq(dev_priv);
+	intel_update_fdi_pll_freq(i915);
 
-	intel_update_czclk(dev_priv);
-	intel_modeset_init_hw(dev);
+	intel_update_czclk(i915);
+	intel_modeset_init_hw(i915);
 
-	intel_hdcp_component_init(dev_priv);
+	intel_hdcp_component_init(i915);
 
-	if (dev_priv->max_cdclk_freq == 0)
-		intel_update_max_cdclk(dev_priv);
+	if (i915->max_cdclk_freq == 0)
+		intel_update_max_cdclk(i915);
 
 	/* Just disable it once at startup */
-	i915_disable_vga(dev_priv);
-	intel_setup_outputs(dev_priv);
+	i915_disable_vga(i915);
+	intel_setup_outputs(i915);
 
 	drm_modeset_lock_all(dev);
 	intel_modeset_setup_hw_state(dev, dev->mode_config.acquire_ctx);
@@ -16308,8 +16306,7 @@ int intel_modeset_init(struct drm_device *dev)
 		 * can even allow for smooth boot transitions if the BIOS
 		 * fb is large enough for the active pipe configuration.
 		 */
-		dev_priv->display.get_initial_plane_config(crtc,
-							   &plane_config);
+		i915->display.get_initial_plane_config(crtc, &plane_config);
 
 		/*
 		 * If the fb is shared between multiple heads, we'll
@@ -16323,7 +16320,7 @@ int intel_modeset_init(struct drm_device *dev)
 	 * Note that we need to do this after reconstructing the BIOS fb's
 	 * since the watermark calculation done here will use pstate->fb.
 	 */
-	if (!HAS_GMCH(dev_priv))
+	if (!HAS_GMCH(i915))
 		sanitize_watermarks(dev);
 
 	/*
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 933cbe36bb59..5cea6f8e107a 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -576,8 +576,8 @@ void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
 				     struct intel_display_error_state *error);
 
 /* modesetting */
-void intel_modeset_init_hw(struct drm_device *dev);
-int intel_modeset_init(struct drm_device *dev);
+void intel_modeset_init_hw(struct drm_i915_private *i915);
+int intel_modeset_init(struct drm_i915_private *i915);
 void intel_modeset_driver_remove(struct drm_i915_private *i915);
 int intel_modeset_vga_set_state(struct drm_i915_private *dev_priv, bool state);
 void intel_display_resume(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 9b1788b4589e..dd9613e45723 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -378,7 +378,7 @@ static int i915_driver_modeset_probe(struct drm_i915_private *i915)
 
 	/* Important: The output setup functions called by modeset_init need
 	 * working irqs for e.g. gmbus and dp aux transfers. */
-	ret = intel_modeset_init(&i915->drm);
+	ret = intel_modeset_init(i915);
 	if (ret)
 		goto cleanup_irq;
 
@@ -1946,7 +1946,7 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	i915_gem_resume(dev_priv);
 
-	intel_modeset_init_hw(dev);
+	intel_modeset_init_hw(dev_priv);
 	intel_init_clock_gating(dev_priv);
 
 	spin_lock_irq(&dev_priv->irq_lock);
-- 
cgit v1.2.3


From ae911b23d2f06c5d0a3e32768bedea857cadd269 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 12:00:53 +0100
Subject: drm/i915/execlists: Relax assertion for a pinned context image on
 reset

A gpu hang can occur at any time, given a sufficiently angry gpu. An
example is when it forgets to perform a context-switch at the end of a
request, leaving us with a hanging GPU on a completed request. Here, we
may retire the request, only leaving its context alive via the active
barrier. When we reset the GPU on a completed request, we do not modify
its context image (just updating the ring state) and can safely defer
the assertion that we have the image pinned and ready to modify.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111639
Fixes: dffa8feb3084 ("drm/i915/perf: Assert locking for i915_init_oa_perf_state()")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923110056.15176-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 1a2b71157f08..80ded99bcb15 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2383,7 +2383,6 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
 	/* Proclaim we have exclusive access to the context image! */
-	GEM_BUG_ON(!intel_context_is_pinned(ce));
 	mutex_acquire(&ce->pin_mutex.dep_map, 2, 0, _THIS_IP_);
 
 	rq = active_request(rq);
@@ -2432,6 +2431,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	 * future request will be after userspace has had the opportunity
 	 * to recreate its own state.
 	 */
+	GEM_BUG_ON(!intel_context_is_pinned(ce));
 	regs = ce->lrc_reg_state;
 	if (engine->pinned_default_state) {
 		memcpy(regs, /* skip restoring the vanilla PPHWSP */
-- 
cgit v1.2.3


From 3231f8c01121ee1febfd82398ee22f7ff9dc5d76 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 12:00:54 +0100
Subject: drm/i915/execlists: Drop redundant list_del_init(&rq->sched.link)

Since amalgamating the queued and active lists in commit 422d7df4f090
("drm/i915: Replace engine->timeline with a plain list"), performing a
i915_request_submit() will remove the request from the execlists
priority queue.

References: 422d7df4f090 ("drm/i915: Replace engine->timeline with a plain list")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923110056.15176-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 80ded99bcb15..0a4812ebd184 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2514,7 +2514,6 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
-			list_del_init(&rq->sched.link);
 			__i915_request_submit(rq);
 			dma_fence_set_error(&rq->fence, -EIO);
 			i915_request_mark_complete(rq);
-- 
cgit v1.2.3


From c0bb487dc19fc45dbeede7dcf8f513df51a3cd33 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 12:00:55 +0100
Subject: drm/i915: Only enqueue already completed requests

If we are asked to submit a completed request, just move it onto the
active-list without modifying it's payload. If we try to emit the
modified payload of a completed request, we risk racing with the
ring->head update during retirement which may advance the head past our
breadcrumb and so we generate a warning for the emission being behind
the RING_HEAD.

v2: Commentary for the sneaky, shared responsibility between functions.
v3: Spelling mistakes and bonus assertion

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923110056.15176-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 66 +++++++++++++++++++++++--------------
 drivers/gpu/drm/i915/i915_request.c | 44 ++++++++++++++++++-------
 drivers/gpu/drm/i915/i915_request.h |  2 +-
 3 files changed, 74 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 0a4812ebd184..bc9badd9c046 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -799,6 +799,17 @@ static bool can_merge_rq(const struct i915_request *prev,
 	GEM_BUG_ON(prev == next);
 	GEM_BUG_ON(!assert_priority_queue(prev, next));
 
+	/*
+	 * We do not submit known completed requests. Therefore if the next
+	 * request is already completed, we can pretend to merge it in
+	 * with the previous context (and we will skip updating the ELSP
+	 * and tracking). Thus hopefully keeping the ELSP full with active
+	 * contexts, despite the best efforts of preempt-to-busy to confuse
+	 * us.
+	 */
+	if (i915_request_completed(next))
+		return true;
+
 	if (!can_merge_ctx(prev->hw_context, next->hw_context))
 		return false;
 
@@ -1181,21 +1192,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				continue;
 			}
 
-			if (i915_request_completed(rq)) {
-				ve->request = NULL;
-				ve->base.execlists.queue_priority_hint = INT_MIN;
-				rb_erase_cached(rb, &execlists->virtual);
-				RB_CLEAR_NODE(rb);
-
-				rq->engine = engine;
-				__i915_request_submit(rq);
-
-				spin_unlock(&ve->base.active.lock);
-
-				rb = rb_first_cached(&execlists->virtual);
-				continue;
-			}
-
 			if (last && !can_merge_rq(last, rq)) {
 				spin_unlock(&ve->base.active.lock);
 				return; /* leave this for another */
@@ -1249,11 +1245,23 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				GEM_BUG_ON(ve->siblings[0] != engine);
 			}
 
-			__i915_request_submit(rq);
-			if (!i915_request_completed(rq)) {
+			if (__i915_request_submit(rq)) {
 				submit = true;
 				last = rq;
 			}
+
+			/*
+			 * Hmm, we have a bunch of virtual engine requests,
+			 * but the first one was already completed (thanks
+			 * preempt-to-busy!). Keep looking at the veng queue
+			 * until we have no more relevant requests (i.e.
+			 * the normal submit queue has higher priority).
+			 */
+			if (!submit) {
+				spin_unlock(&ve->base.active.lock);
+				rb = rb_first_cached(&execlists->virtual);
+				continue;
+			}
 		}
 
 		spin_unlock(&ve->base.active.lock);
@@ -1266,8 +1274,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
-			if (i915_request_completed(rq))
-				goto skip;
+			bool merge = true;
 
 			/*
 			 * Can we combine this request with the current port?
@@ -1308,14 +1315,23 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				    ctx_single_port_submission(rq->hw_context))
 					goto done;
 
-				*port = execlists_schedule_in(last, port - execlists->pending);
-				port++;
+				merge = false;
 			}
 
-			last = rq;
-			submit = true;
-skip:
-			__i915_request_submit(rq);
+			if (__i915_request_submit(rq)) {
+				if (!merge) {
+					*port = execlists_schedule_in(last, port - execlists->pending);
+					port++;
+					last = NULL;
+				}
+
+				GEM_BUG_ON(last &&
+					   !can_merge_ctx(last->hw_context,
+							  rq->hw_context));
+
+				submit = true;
+				last = rq;
+			}
 		}
 
 		rb_erase_cached(&p->node, &execlists->queue);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 9bd8538b1907..a8916412759b 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -377,9 +377,10 @@ __i915_request_await_execution(struct i915_request *rq,
 	return 0;
 }
 
-void __i915_request_submit(struct i915_request *request)
+bool __i915_request_submit(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
+	bool result = false;
 
 	GEM_TRACE("%s fence %llx:%lld, current %d\n",
 		  engine->name,
@@ -389,6 +390,25 @@ void __i915_request_submit(struct i915_request *request)
 	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->active.lock);
 
+	/*
+	 * With the advent of preempt-to-busy, we frequently encounter
+	 * requests that we have unsubmitted from HW, but left running
+	 * until the next ack and so have completed in the meantime. On
+	 * resubmission of that completed request, we can skip
+	 * updating the payload, and execlists can even skip submitting
+	 * the request.
+	 *
+	 * We must remove the request from the caller's priority queue,
+	 * and the caller must only call us when the request is in their
+	 * priority queue, under the active.lock. This ensures that the
+	 * request has *not* yet been retired and we can safely move
+	 * the request into the engine->active.list where it will be
+	 * dropped upon retiring. (Otherwise if resubmit a *retired*
+	 * request, this would be a horrible use-after-free.)
+	 */
+	if (i915_request_completed(request))
+		goto xfer;
+
 	if (i915_gem_context_is_banned(request->gem_context))
 		i915_request_skip(request, -EIO);
 
@@ -412,13 +432,18 @@ void __i915_request_submit(struct i915_request *request)
 	    i915_sw_fence_signaled(&request->semaphore))
 		engine->saturated |= request->sched.semaphores;
 
-	/* We may be recursing from the signal callback of another i915 fence */
-	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
+	engine->emit_fini_breadcrumb(request,
+				     request->ring->vaddr + request->postfix);
+
+	trace_i915_request_execute(request);
+	engine->serial++;
+	result = true;
 
-	list_move_tail(&request->sched.link, &engine->active.requests);
+xfer:	/* We may be recursing from the signal callback of another i915 fence */
+	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
 
-	GEM_BUG_ON(test_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags));
-	set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags);
+	if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags))
+		list_move_tail(&request->sched.link, &engine->active.requests);
 
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
 	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) &&
@@ -429,12 +454,7 @@ void __i915_request_submit(struct i915_request *request)
 
 	spin_unlock(&request->lock);
 
-	engine->emit_fini_breadcrumb(request,
-				     request->ring->vaddr + request->postfix);
-
-	engine->serial++;
-
-	trace_i915_request_execute(request);
+	return result;
 }
 
 void i915_request_submit(struct i915_request *request)
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index b18f49528ded..ec5bb4c2e5ae 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -292,7 +292,7 @@ int i915_request_await_execution(struct i915_request *rq,
 
 void i915_request_add(struct i915_request *rq);
 
-void __i915_request_submit(struct i915_request *request);
+bool __i915_request_submit(struct i915_request *request);
 void i915_request_submit(struct i915_request *request);
 
 void i915_request_skip(struct i915_request *request, int error);
-- 
cgit v1.2.3


From 0d7cf7bc15e75bf79f2f65d61d19f896609f816a Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 12:00:56 +0100
Subject: drm/i915/execlists: Refactor -EIO markup of hung requests

Pull setting -EIO on the hung requests into its own utility function.
Having allowed ourselves to short-circuit submission of completed
requests, we can now do the mark_eio() prior to submission and avoid
some redundant operations.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923110056.15176-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 31 +++++++++++++++++--------------
 1 file changed, 17 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index bc9badd9c046..bff4c6a735cf 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -234,6 +234,13 @@ static void execlists_init_reg_state(u32 *reg_state,
 				     struct intel_engine_cs *engine,
 				     struct intel_ring *ring);
 
+static void mark_eio(struct i915_request *rq)
+{
+	if (!i915_request_signaled(rq))
+		dma_fence_set_error(&rq->fence, -EIO);
+	i915_request_mark_complete(rq);
+}
+
 static inline u32 intel_hws_preempt_address(struct intel_engine_cs *engine)
 {
 	return (i915_ggtt_offset(engine->status_page.vma) +
@@ -2517,12 +2524,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	__execlists_reset(engine, true);
 
 	/* Mark all executing requests as skipped. */
-	list_for_each_entry(rq, &engine->active.requests, sched.link) {
-		if (!i915_request_signaled(rq))
-			dma_fence_set_error(&rq->fence, -EIO);
-
-		i915_request_mark_complete(rq);
-	}
+	list_for_each_entry(rq, &engine->active.requests, sched.link)
+		mark_eio(rq);
 
 	/* Flush the queued requests to the timeline list (for retiring). */
 	while ((rb = rb_first_cached(&execlists->queue))) {
@@ -2530,9 +2533,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
+			mark_eio(rq);
 			__i915_request_submit(rq);
-			dma_fence_set_error(&rq->fence, -EIO);
-			i915_request_mark_complete(rq);
 		}
 
 		rb_erase_cached(&p->node, &execlists->queue);
@@ -2548,13 +2550,14 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 		RB_CLEAR_NODE(rb);
 
 		spin_lock(&ve->base.active.lock);
-		if (ve->request) {
-			ve->request->engine = engine;
-			__i915_request_submit(ve->request);
-			dma_fence_set_error(&ve->request->fence, -EIO);
-			i915_request_mark_complete(ve->request);
+		rq = fetch_and_zero(&ve->request);
+		if (rq) {
+			mark_eio(rq);
+
+			rq->engine = engine;
+			__i915_request_submit(rq);
+
 			ve->base.execlists.queue_priority_hint = INT_MIN;
-			ve->request = NULL;
 		}
 		spin_unlock(&ve->base.active.lock);
 	}
-- 
cgit v1.2.3


From dd8882a255388ba66175098b1560d4f81c100d30 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Mon, 23 Sep 2019 10:32:37 -0700
Subject: clk: ti: dra7: Fix mcasp8 clock bits

There's a typo for dra7 mcasp clkctrl bit, it should be 22 like the other
macasp instances, and not 24. And in dra7xx_clks[] we have the bits wrong
way around.

Fixes: dffa9051d546 ("clk: ti: dra7: add new clkctrl data")
Cc: linux-clk@vger.kernel.org
Cc: Michael Turquette <mturquette@baylibre.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: Suman Anna <s-anna@ti.com>
Cc: Tero Kristo <t-kristo@ti.com>
Acked-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 drivers/clk/ti/clk-7xx.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c
index b57fe09b428b..9dd6185a4b4e 100644
--- a/drivers/clk/ti/clk-7xx.c
+++ b/drivers/clk/ti/clk-7xx.c
@@ -683,7 +683,7 @@ static const struct omap_clkctrl_reg_data dra7_l4per2_clkctrl_regs[] __initconst
 	{ DRA7_L4PER2_MCASP2_CLKCTRL, dra7_mcasp2_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:0154:22" },
 	{ DRA7_L4PER2_MCASP3_CLKCTRL, dra7_mcasp3_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:015c:22" },
 	{ DRA7_L4PER2_MCASP5_CLKCTRL, dra7_mcasp5_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:016c:22" },
-	{ DRA7_L4PER2_MCASP8_CLKCTRL, dra7_mcasp8_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:0184:24" },
+	{ DRA7_L4PER2_MCASP8_CLKCTRL, dra7_mcasp8_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:0184:22" },
 	{ DRA7_L4PER2_MCASP4_CLKCTRL, dra7_mcasp4_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:018c:22" },
 	{ DRA7_L4PER2_UART7_CLKCTRL, dra7_uart7_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:01c4:24" },
 	{ DRA7_L4PER2_UART8_CLKCTRL, dra7_uart8_bit_data, CLKF_SW_SUP, "l4per2-clkctrl:01d4:24" },
@@ -828,8 +828,8 @@ static struct ti_dt_clk dra7xx_clks[] = {
 	DT_CLK(NULL, "mcasp6_aux_gfclk_mux", "l4per2-clkctrl:01f8:22"),
 	DT_CLK(NULL, "mcasp7_ahclkx_mux", "l4per2-clkctrl:01fc:24"),
 	DT_CLK(NULL, "mcasp7_aux_gfclk_mux", "l4per2-clkctrl:01fc:22"),
-	DT_CLK(NULL, "mcasp8_ahclkx_mux", "l4per2-clkctrl:0184:22"),
-	DT_CLK(NULL, "mcasp8_aux_gfclk_mux", "l4per2-clkctrl:0184:24"),
+	DT_CLK(NULL, "mcasp8_ahclkx_mux", "l4per2-clkctrl:0184:24"),
+	DT_CLK(NULL, "mcasp8_aux_gfclk_mux", "l4per2-clkctrl:0184:22"),
 	DT_CLK(NULL, "mmc1_clk32k", "l3init-clkctrl:0008:8"),
 	DT_CLK(NULL, "mmc1_fclk_div", "l3init-clkctrl:0008:25"),
 	DT_CLK(NULL, "mmc1_fclk_mux", "l3init-clkctrl:0008:24"),
-- 
cgit v1.2.3


From 2d3c8ba3cffa00f76bedb713c8c2126c82d8cd13 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Mon, 23 Sep 2019 10:32:38 -0700
Subject: ARM: dts: Fix wrong clocks for dra7 mcasp

The ahclkr clkctrl clock bit 28 only exists for mcasp 1 and 2 on dra7.
This causes the following warning on beagle-x15:

ti-sysc 48468000.target-module: could not add child clock ahclkr: -19

Also the mcasp clkctrl clock bits are wrong:

For mcasp1 and 2 we have four clocks at bits 28, 24, 22 and 0:

bit 28 is ahclkr
bit 24 is ahclkx
bit 22 is auxclk
bit 0 is fck

For mcasp3 to 8 we have three clocks at bits 24, 22 and 0.

bit 24 is ahclkx
bit 22 is auxclk
bit 0 is fck

We do not have currently mapped auxclk at bit 22 for the drivers, that can
be added if needed.

Fixes: 5241ccbf2819 ("ARM: dts: Add missing ranges for dra7 mcasp l3 ports")
Cc: Suman Anna <s-anna@ti.com>
Cc: Tero Kristo <t-kristo@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/boot/dts/dra7-l4.dtsi | 48 ++++++++++++++++++------------------------
 1 file changed, 21 insertions(+), 27 deletions(-)

diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi
index 21e5914fdd62..099d6fe2a57a 100644
--- a/arch/arm/boot/dts/dra7-l4.dtsi
+++ b/arch/arm/boot/dts/dra7-l4.dtsi
@@ -2762,7 +2762,7 @@
 				interrupt-names = "tx", "rx";
 				dmas = <&edma_xbar 129 1>, <&edma_xbar 128 1>;
 				dma-names = "tx", "rx";
-				clocks = <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 22>,
+				clocks = <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 0>,
 					 <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 24>,
 					 <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 28>;
 				clock-names = "fck", "ahclkx", "ahclkr";
@@ -2799,8 +2799,8 @@
 				interrupt-names = "tx", "rx";
 				dmas = <&edma_xbar 131 1>, <&edma_xbar 130 1>;
 				dma-names = "tx", "rx";
-				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP2_CLKCTRL 22>,
-					 <&l4per2_clkctrl DRA7_L4PER2_MCASP2_CLKCTRL 24>,
+				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP2_CLKCTRL 0>,
+					 <&ipu_clkctrl DRA7_IPU_MCASP1_CLKCTRL 24>,
 					 <&l4per2_clkctrl DRA7_L4PER2_MCASP2_CLKCTRL 28>;
 				clock-names = "fck", "ahclkx", "ahclkr";
 				status = "disabled";
@@ -2818,9 +2818,8 @@
 					<SYSC_IDLE_SMART>;
 			/* Domains (P, C): l4per_pwrdm, l4per2_clkdm */
 			clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 0>,
-				 <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 24>,
-				 <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 28>;
-			clock-names = "fck", "ahclkx", "ahclkr";
+				 <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 24>;
+			clock-names = "fck", "ahclkx";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0x68000 0x2000>,
@@ -2836,7 +2835,7 @@
 				interrupt-names = "tx", "rx";
 				dmas = <&edma_xbar 133 1>, <&edma_xbar 132 1>;
 				dma-names = "tx", "rx";
-				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 22>,
+				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 0>,
 					 <&l4per2_clkctrl DRA7_L4PER2_MCASP3_CLKCTRL 24>;
 				clock-names = "fck", "ahclkx";
 				status = "disabled";
@@ -2854,9 +2853,8 @@
 					<SYSC_IDLE_SMART>;
 			/* Domains (P, C): l4per_pwrdm, l4per2_clkdm */
 			clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 0>,
-				 <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 24>,
-				 <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 28>;
-			clock-names = "fck", "ahclkx", "ahclkr";
+				 <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 24>;
+			clock-names = "fck", "ahclkx";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0x6c000 0x2000>,
@@ -2872,7 +2870,7 @@
 				interrupt-names = "tx", "rx";
 				dmas = <&edma_xbar 135 1>, <&edma_xbar 134 1>;
 				dma-names = "tx", "rx";
-				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 22>,
+				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 0>,
 					 <&l4per2_clkctrl DRA7_L4PER2_MCASP4_CLKCTRL 24>;
 				clock-names = "fck", "ahclkx";
 				status = "disabled";
@@ -2890,9 +2888,8 @@
 					<SYSC_IDLE_SMART>;
 			/* Domains (P, C): l4per_pwrdm, l4per2_clkdm */
 			clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 0>,
-				 <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 24>,
-				 <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 28>;
-			clock-names = "fck", "ahclkx", "ahclkr";
+				 <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 24>;
+			clock-names = "fck", "ahclkx";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0x70000 0x2000>,
@@ -2908,7 +2905,7 @@
 				interrupt-names = "tx", "rx";
 				dmas = <&edma_xbar 137 1>, <&edma_xbar 136 1>;
 				dma-names = "tx", "rx";
-				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 22>,
+				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 0>,
 					 <&l4per2_clkctrl DRA7_L4PER2_MCASP5_CLKCTRL 24>;
 				clock-names = "fck", "ahclkx";
 				status = "disabled";
@@ -2926,9 +2923,8 @@
 					<SYSC_IDLE_SMART>;
 			/* Domains (P, C): l4per_pwrdm, l4per2_clkdm */
 			clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 0>,
-				 <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 24>,
-				 <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 28>;
-			clock-names = "fck", "ahclkx", "ahclkr";
+				 <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 24>;
+			clock-names = "fck", "ahclkx";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0x74000 0x2000>,
@@ -2944,7 +2940,7 @@
 				interrupt-names = "tx", "rx";
 				dmas = <&edma_xbar 139 1>, <&edma_xbar 138 1>;
 				dma-names = "tx", "rx";
-				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 22>,
+				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 0>,
 					 <&l4per2_clkctrl DRA7_L4PER2_MCASP6_CLKCTRL 24>;
 				clock-names = "fck", "ahclkx";
 				status = "disabled";
@@ -2962,9 +2958,8 @@
 					<SYSC_IDLE_SMART>;
 			/* Domains (P, C): l4per_pwrdm, l4per2_clkdm */
 			clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 0>,
-				 <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 24>,
-				 <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 28>;
-			clock-names = "fck", "ahclkx", "ahclkr";
+				 <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 24>;
+			clock-names = "fck", "ahclkx";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0x78000 0x2000>,
@@ -2980,7 +2975,7 @@
 				interrupt-names = "tx", "rx";
 				dmas = <&edma_xbar 141 1>, <&edma_xbar 140 1>;
 				dma-names = "tx", "rx";
-				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 22>,
+				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 0>,
 					 <&l4per2_clkctrl DRA7_L4PER2_MCASP7_CLKCTRL 24>;
 				clock-names = "fck", "ahclkx";
 				status = "disabled";
@@ -2998,9 +2993,8 @@
 					<SYSC_IDLE_SMART>;
 			/* Domains (P, C): l4per_pwrdm, l4per2_clkdm */
 			clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 0>,
-				 <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 24>,
-				 <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 28>;
-			clock-names = "fck", "ahclkx", "ahclkr";
+				 <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 24>;
+			clock-names = "fck", "ahclkx";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0x7c000 0x2000>,
@@ -3016,7 +3010,7 @@
 				interrupt-names = "tx", "rx";
 				dmas = <&edma_xbar 143 1>, <&edma_xbar 142 1>;
 				dma-names = "tx", "rx";
-				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 22>,
+				clocks = <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 0>,
 					 <&l4per2_clkctrl DRA7_L4PER2_MCASP8_CLKCTRL 24>;
 				clock-names = "fck", "ahclkx";
 				status = "disabled";
-- 
cgit v1.2.3


From f1f028ff89cb0d37db299d48e7b2ce19be040d52 Mon Sep 17 00:00:00 2001
From: "H. Nikolaus Schaller" <hns@goldelico.com>
Date: Fri, 20 Sep 2019 18:11:15 +0200
Subject: DTS: ARM: gta04: introduce legacy spi-cs-high to make display work
 again

commit 6953c57ab172 "gpio: of: Handle SPI chipselect legacy bindings"

did introduce logic to centrally handle the legacy spi-cs-high property
in combination with cs-gpios. This assumes that the polarity
of the CS has to be inverted if spi-cs-high is missing, even
and especially if non-legacy GPIO_ACTIVE_HIGH is specified.

The DTS for the GTA04 was orginally introduced under the assumption
that there is no need for spi-cs-high if the gpio is defined with
proper polarity GPIO_ACTIVE_HIGH.

This was not a problem until gpiolib changed the interpretation of
GPIO_ACTIVE_HIGH and missing spi-cs-high.

The effect is that the missing spi-cs-high is now interpreted as CS being
low (despite GPIO_ACTIVE_HIGH) which turns off the SPI interface when the
panel is to be programmed by the panel driver.

Therefore, we have to add the redundant and legacy spi-cs-high property
to properly activate CS.

Cc: stable@vger.kernel.org
Signed-off-by: H. Nikolaus Schaller <hns@goldelico.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/boot/dts/omap3-gta04.dtsi | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi
index b295f6fad2a5..954c216140ad 100644
--- a/arch/arm/boot/dts/omap3-gta04.dtsi
+++ b/arch/arm/boot/dts/omap3-gta04.dtsi
@@ -120,6 +120,7 @@
 			spi-max-frequency = <100000>;
 			spi-cpol;
 			spi-cpha;
+			spi-cs-high;
 
 			backlight= <&backlight>;
 			label = "lcd";
-- 
cgit v1.2.3


From 6171e58b1ff5c41632d8fb87f0e6bd003ed34c13 Mon Sep 17 00:00:00 2001
From: Clinton A Taylor <clinton.a.taylor@intel.com>
Date: Fri, 20 Sep 2019 13:58:05 -0700
Subject: drm/i915/tgl: Add missing ddi clock select during DP init sequence
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Step 4.b was complete missed because it is only required to TC and TBT.

Bspec: 49190
Reviewed-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Clinton A Taylor <clinton.a.taylor@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920205810.211048-2-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 0c0da9f6c2e8..dfd6b064cbc3 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3230,11 +3230,14 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	intel_edp_panel_on(intel_dp);
 
 	/*
-	 * 1.b, 3. and 4. is done before tgl_ddi_pre_enable_dp() by:
+	 * 1.b, 3. and 4.a is done before tgl_ddi_pre_enable_dp() by:
 	 * haswell_crtc_enable()->intel_encoders_pre_pll_enable() and
 	 * haswell_crtc_enable()->intel_enable_shared_dpll()
 	 */
 
+	/* 4.b */
+	intel_ddi_clk_select(encoder, crtc_state);
+
 	/* 5. */
 	if (!intel_phy_is_tc(dev_priv, phy) ||
 	    dig_port->tc_mode != TC_PORT_TBT_ALT)
-- 
cgit v1.2.3


From 31d9ae9d734226b2ce3a1bc2ce1ed29a6997d556 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Fri, 20 Sep 2019 13:58:06 -0700
Subject: drm/i915/tgl: Finish modular FIA support on registers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If platform supports and has modular FIA is enabled, the registers
bits also change, example: reading TC3 registers with modular FIA
enabled, driver should read from FIA2 but with TC1 bits offsets.

It is described in BSpec 50231 for DFLEXDPSP, other registers don't
have the BSpec description but testing in real hardware have proven
that it had moved for all other registers too.

v2:
- Caching index in tc_phy_fia_idx, instead of calculate it each time

v3:
- Setting tc_phy_fia and tc_phy_fia_idx in the same function

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920205810.211048-3-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_display_types.h |  1 +
 drivers/gpu/drm/i915/display/intel_tc.c            | 72 ++++++++++++----------
 drivers/gpu/drm/i915/i915_reg.h                    | 28 ++++-----
 3 files changed, 53 insertions(+), 48 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 49c902b00484..6b0a646f0170 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1288,6 +1288,7 @@ struct intel_digital_port {
 	char tc_port_name[8];
 	enum tc_port_mode tc_mode;
 	enum phy_fia tc_phy_fia;
+	u8 tc_phy_fia_idx;
 
 	void (*write_infoframe)(struct intel_encoder *encoder,
 				const struct intel_crtc_state *crtc_state,
diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index 85743a43bee2..f923f9cbd33c 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -23,32 +23,38 @@ static const char *tc_port_mode_name(enum tc_port_mode mode)
 	return names[mode];
 }
 
-static bool has_modular_fia(struct drm_i915_private *i915)
-{
-	if (!INTEL_INFO(i915)->display.has_modular_fia)
-		return false;
-
-	return intel_uncore_read(&i915->uncore,
-				 PORT_TX_DFLEXDPSP(FIA1)) & MODULAR_FIA_MASK;
-}
-
-static enum phy_fia tc_port_to_fia(struct drm_i915_private *i915,
-				   enum tc_port tc_port)
+static void
+tc_port_load_fia_params(struct drm_i915_private *i915,
+			struct intel_digital_port *dig_port)
 {
-	if (!has_modular_fia(i915))
-		return FIA1;
+	enum port port = dig_port->base.port;
+	enum tc_port tc_port = intel_port_to_tc(i915, port);
+	u32 modular_fia;
+
+	if (INTEL_INFO(i915)->display.has_modular_fia) {
+		modular_fia = intel_uncore_read(&i915->uncore,
+						PORT_TX_DFLEXDPSP(FIA1));
+		modular_fia &= MODULAR_FIA_MASK;
+	} else {
+		modular_fia = 0;
+	}
 
 	/*
 	 * Each Modular FIA instance houses 2 TC ports. In SOC that has more
 	 * than two TC ports, there are multiple instances of Modular FIA.
 	 */
-	return tc_port / 2;
+	if (modular_fia) {
+		dig_port->tc_phy_fia = tc_port / 2;
+		dig_port->tc_phy_fia_idx = tc_port % 2;
+	} else {
+		dig_port->tc_phy_fia = FIA1;
+		dig_port->tc_phy_fia_idx = tc_port;
+	}
 }
 
 u32 intel_tc_port_get_lane_mask(struct intel_digital_port *dig_port)
 {
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
-	enum tc_port tc_port = intel_port_to_tc(i915, dig_port->base.port);
 	struct intel_uncore *uncore = &i915->uncore;
 	u32 lane_mask;
 
@@ -57,8 +63,8 @@ u32 intel_tc_port_get_lane_mask(struct intel_digital_port *dig_port)
 
 	WARN_ON(lane_mask == 0xffffffff);
 
-	return (lane_mask & DP_LANE_ASSIGNMENT_MASK(tc_port)) >>
-	       DP_LANE_ASSIGNMENT_SHIFT(tc_port);
+	lane_mask &= DP_LANE_ASSIGNMENT_MASK(dig_port->tc_phy_fia_idx);
+	return lane_mask >> DP_LANE_ASSIGNMENT_SHIFT(dig_port->tc_phy_fia_idx);
 }
 
 int intel_tc_port_fia_max_lane_count(struct intel_digital_port *dig_port)
@@ -95,7 +101,6 @@ void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,
 				      int required_lanes)
 {
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
-	enum tc_port tc_port = intel_port_to_tc(i915, dig_port->base.port);
 	bool lane_reversal = dig_port->saved_port_bits & DDI_BUF_PORT_REVERSAL;
 	struct intel_uncore *uncore = &i915->uncore;
 	u32 val;
@@ -104,19 +109,21 @@ void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,
 
 	val = intel_uncore_read(uncore,
 				PORT_TX_DFLEXDPMLE1(dig_port->tc_phy_fia));
-	val &= ~DFLEXDPMLE1_DPMLETC_MASK(tc_port);
+	val &= ~DFLEXDPMLE1_DPMLETC_MASK(dig_port->tc_phy_fia_idx);
 
 	switch (required_lanes) {
 	case 1:
-		val |= lane_reversal ? DFLEXDPMLE1_DPMLETC_ML3(tc_port) :
-			DFLEXDPMLE1_DPMLETC_ML0(tc_port);
+		val |= lane_reversal ?
+			DFLEXDPMLE1_DPMLETC_ML3(dig_port->tc_phy_fia_idx) :
+			DFLEXDPMLE1_DPMLETC_ML0(dig_port->tc_phy_fia_idx);
 		break;
 	case 2:
-		val |= lane_reversal ? DFLEXDPMLE1_DPMLETC_ML3_2(tc_port) :
-			DFLEXDPMLE1_DPMLETC_ML1_0(tc_port);
+		val |= lane_reversal ?
+			DFLEXDPMLE1_DPMLETC_ML3_2(dig_port->tc_phy_fia_idx) :
+			DFLEXDPMLE1_DPMLETC_ML1_0(dig_port->tc_phy_fia_idx);
 		break;
 	case 4:
-		val |= DFLEXDPMLE1_DPMLETC_ML3_0(tc_port);
+		val |= DFLEXDPMLE1_DPMLETC_ML3_0(dig_port->tc_phy_fia_idx);
 		break;
 	default:
 		MISSING_CASE(required_lanes);
@@ -164,9 +171,9 @@ static u32 tc_port_live_status_mask(struct intel_digital_port *dig_port)
 		return mask;
 	}
 
-	if (val & TC_LIVE_STATE_TBT(tc_port))
+	if (val & TC_LIVE_STATE_TBT(dig_port->tc_phy_fia_idx))
 		mask |= BIT(TC_PORT_TBT_ALT);
-	if (val & TC_LIVE_STATE_TC(tc_port))
+	if (val & TC_LIVE_STATE_TC(dig_port->tc_phy_fia_idx))
 		mask |= BIT(TC_PORT_DP_ALT);
 
 	if (intel_uncore_read(uncore, SDEISR) & SDE_TC_HOTPLUG_ICP(tc_port))
@@ -182,7 +189,6 @@ static u32 tc_port_live_status_mask(struct intel_digital_port *dig_port)
 static bool icl_tc_phy_status_complete(struct intel_digital_port *dig_port)
 {
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
-	enum tc_port tc_port = intel_port_to_tc(i915, dig_port->base.port);
 	struct intel_uncore *uncore = &i915->uncore;
 	u32 val;
 
@@ -194,14 +200,13 @@ static bool icl_tc_phy_status_complete(struct intel_digital_port *dig_port)
 		return false;
 	}
 
-	return val & DP_PHY_MODE_STATUS_COMPLETED(tc_port);
+	return val & DP_PHY_MODE_STATUS_COMPLETED(dig_port->tc_phy_fia_idx);
 }
 
 static bool icl_tc_phy_set_safe_mode(struct intel_digital_port *dig_port,
 				     bool enable)
 {
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
-	enum tc_port tc_port = intel_port_to_tc(i915, dig_port->base.port);
 	struct intel_uncore *uncore = &i915->uncore;
 	u32 val;
 
@@ -215,9 +220,9 @@ static bool icl_tc_phy_set_safe_mode(struct intel_digital_port *dig_port,
 		return false;
 	}
 
-	val &= ~DP_PHY_MODE_STATUS_NOT_SAFE(tc_port);
+	val &= ~DP_PHY_MODE_STATUS_NOT_SAFE(dig_port->tc_phy_fia_idx);
 	if (!enable)
-		val |= DP_PHY_MODE_STATUS_NOT_SAFE(tc_port);
+		val |= DP_PHY_MODE_STATUS_NOT_SAFE(dig_port->tc_phy_fia_idx);
 
 	intel_uncore_write(uncore,
 			   PORT_TX_DFLEXDPCSSS(dig_port->tc_phy_fia), val);
@@ -232,7 +237,6 @@ static bool icl_tc_phy_set_safe_mode(struct intel_digital_port *dig_port,
 static bool icl_tc_phy_is_in_safe_mode(struct intel_digital_port *dig_port)
 {
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
-	enum tc_port tc_port = intel_port_to_tc(i915, dig_port->base.port);
 	struct intel_uncore *uncore = &i915->uncore;
 	u32 val;
 
@@ -244,7 +248,7 @@ static bool icl_tc_phy_is_in_safe_mode(struct intel_digital_port *dig_port)
 		return true;
 	}
 
-	return !(val & DP_PHY_MODE_STATUS_NOT_SAFE(tc_port));
+	return !(val & DP_PHY_MODE_STATUS_NOT_SAFE(dig_port->tc_phy_fia_idx));
 }
 
 /*
@@ -540,5 +544,5 @@ void intel_tc_port_init(struct intel_digital_port *dig_port, bool is_legacy)
 	mutex_init(&dig_port->tc_lock);
 	dig_port->tc_legacy_port = is_legacy;
 	dig_port->tc_link_refcount = 0;
-	dig_port->tc_phy_fia = tc_port_to_fia(i915, tc_port);
+	tc_port_load_fia_params(i915, dig_port);
 }
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6ecb64c042ef..4236cb5d12df 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2166,13 +2166,13 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define _MMIO_FIA(fia, off)		_MMIO(_FIA(fia) + (off))
 
 /* ICL PHY DFLEX registers */
-#define PORT_TX_DFLEXDPMLE1(fia)	_MMIO_FIA((fia),  0x008C0)
-#define   DFLEXDPMLE1_DPMLETC_MASK(tc_port)	(0xf << (4 * (tc_port)))
-#define   DFLEXDPMLE1_DPMLETC_ML0(tc_port)	(1 << (4 * (tc_port)))
-#define   DFLEXDPMLE1_DPMLETC_ML1_0(tc_port)	(3 << (4 * (tc_port)))
-#define   DFLEXDPMLE1_DPMLETC_ML3(tc_port)	(8 << (4 * (tc_port)))
-#define   DFLEXDPMLE1_DPMLETC_ML3_2(tc_port)	(12 << (4 * (tc_port)))
-#define   DFLEXDPMLE1_DPMLETC_ML3_0(tc_port)	(15 << (4 * (tc_port)))
+#define PORT_TX_DFLEXDPMLE1(fia)		_MMIO_FIA((fia),  0x008C0)
+#define   DFLEXDPMLE1_DPMLETC_MASK(idx)		(0xf << (4 * (idx)))
+#define   DFLEXDPMLE1_DPMLETC_ML0(idx)		(1 << (4 * (idx)))
+#define   DFLEXDPMLE1_DPMLETC_ML1_0(idx)	(3 << (4 * (idx)))
+#define   DFLEXDPMLE1_DPMLETC_ML3(idx)		(8 << (4 * (idx)))
+#define   DFLEXDPMLE1_DPMLETC_ML3_2(idx)	(12 << (4 * (idx)))
+#define   DFLEXDPMLE1_DPMLETC_ML3_0(idx)	(15 << (4 * (idx)))
 
 /* BXT PHY Ref registers */
 #define _PORT_REF_DW3_A			0x16218C
@@ -11688,17 +11688,17 @@ enum skl_power_gate {
 
 #define PORT_TX_DFLEXDPSP(fia)			_MMIO_FIA((fia), 0x008A0)
 #define   MODULAR_FIA_MASK			(1 << 4)
-#define   TC_LIVE_STATE_TBT(tc_port)		(1 << ((tc_port) * 8 + 6))
-#define   TC_LIVE_STATE_TC(tc_port)		(1 << ((tc_port) * 8 + 5))
-#define   DP_LANE_ASSIGNMENT_SHIFT(tc_port)	((tc_port) * 8)
-#define   DP_LANE_ASSIGNMENT_MASK(tc_port)	(0xf << ((tc_port) * 8))
-#define   DP_LANE_ASSIGNMENT(tc_port, x)	((x) << ((tc_port) * 8))
+#define   TC_LIVE_STATE_TBT(idx)		(1 << ((idx) * 8 + 6))
+#define   TC_LIVE_STATE_TC(idx)			(1 << ((idx) * 8 + 5))
+#define   DP_LANE_ASSIGNMENT_SHIFT(idx)		((idx) * 8)
+#define   DP_LANE_ASSIGNMENT_MASK(idx)		(0xf << ((idx) * 8))
+#define   DP_LANE_ASSIGNMENT(idx, x)		((x) << ((idx) * 8))
 
 #define PORT_TX_DFLEXDPPMS(fia)			_MMIO_FIA((fia), 0x00890)
-#define   DP_PHY_MODE_STATUS_COMPLETED(tc_port)		(1 << (tc_port))
+#define   DP_PHY_MODE_STATUS_COMPLETED(idx)	(1 << (idx))
 
 #define PORT_TX_DFLEXDPCSSS(fia)		_MMIO_FIA((fia), 0x00894)
-#define   DP_PHY_MODE_STATUS_NOT_SAFE(tc_port)		(1 << (tc_port))
+#define   DP_PHY_MODE_STATUS_NOT_SAFE(idx)	(1 << (idx))
 
 /* This register controls the Display State Buffer (DSB) engines. */
 #define _DSBSL_INSTANCE_BASE		0x70B00
-- 
cgit v1.2.3


From 57bd1798b1809a003c5354403a94f2ecb02bf3ae Mon Sep 17 00:00:00 2001
From: Clinton A Taylor <clinton.a.taylor@intel.com>
Date: Fri, 20 Sep 2019 13:58:07 -0700
Subject: drm/i915/tgl/pll: Set update_active_dpll
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 24a7bfe0c2d7 ("drm/i915: Keep the TypeC port mode fixed when the
port is active") added this new hook while in parallel TGL upstream was
happening and this was missed.

Without this driver will crash when TC DDI is added and driver is
preparing to do a full modeset.

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Clinton A Taylor <clinton.a.taylor@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920205810.211048-4-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_dpll_mgr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 98288edf88f0..84e734d44828 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -3479,6 +3479,7 @@ static const struct intel_dpll_mgr tgl_pll_mgr = {
 	.dpll_info = tgl_plls,
 	.get_dplls = icl_get_dplls,
 	.put_dplls = icl_put_dplls,
+	.update_active_dpll = icl_update_active_dpll,
 	.dump_hw_state = icl_dump_hw_state,
 };
 
-- 
cgit v1.2.3


From f15a4eb18264a6eba30fb32f21ae76b010a691d5 Mon Sep 17 00:00:00 2001
From: Vandita Kulkarni <vandita.kulkarni@intel.com>
Date: Fri, 20 Sep 2019 13:58:08 -0700
Subject: drm/i915/tgl: Add dkl phy registers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These are the registers needed to program Dekel phy. Some register
definitions will be reused from MG PHY definitions, so adding a
comment on those.

Bspec: 49295

Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Vandita Kulkarni <vandita.kulkarni@intel.com>
Signed-off-by: Clinton A Taylor <clinton.a.taylor@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920205810.211048-5-jose.souza@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 162 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 162 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4236cb5d12df..a69c19aae5bb 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -10115,6 +10115,168 @@ enum skl_power_gate {
 						   _TGL_DPLL1_CFGCR1, \
 						   _TGL_TBTPLL_CFGCR1)
 
+#define _DKL_PHY1_BASE			0x168000
+#define _DKL_PHY2_BASE			0x169000
+#define _DKL_PHY3_BASE			0x16A000
+#define _DKL_PHY4_BASE			0x16B000
+#define _DKL_PHY5_BASE			0x16C000
+#define _DKL_PHY6_BASE			0x16D000
+
+/* DEKEL PHY MMIO Address = Phy base + (internal address & ~index_mask) */
+#define _DKL_PLL_DIV0			0x200
+#define   DKL_PLL_DIV0_INTEG_COEFF(x)	((x) << 16)
+#define   DKL_PLL_DIV0_INTEG_COEFF_MASK	(0x1F << 16)
+#define   DKL_PLL_DIV0_PROP_COEFF(x)	((x) << 12)
+#define   DKL_PLL_DIV0_PROP_COEFF_MASK	(0xF << 12)
+#define   DKL_PLL_DIV0_FBPREDIV_SHIFT   (8)
+#define   DKL_PLL_DIV0_FBPREDIV(x)	((x) << DKL_PLL_DIV0_FBPREDIV_SHIFT)
+#define   DKL_PLL_DIV0_FBPREDIV_MASK	(0xF << DKL_PLL_DIV0_FBPREDIV_SHIFT)
+#define   DKL_PLL_DIV0_FBDIV_INT(x)	((x) << 0)
+#define   DKL_PLL_DIV0_FBDIV_INT_MASK	(0xFF << 0)
+#define DKL_PLL_DIV0(tc_port)		_MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \
+						    _DKL_PHY2_BASE) + \
+						    _DKL_PLL_DIV0)
+
+#define _DKL_PLL_DIV1				0x204
+#define   DKL_PLL_DIV1_IREF_TRIM(x)		((x) << 16)
+#define   DKL_PLL_DIV1_IREF_TRIM_MASK		(0x1F << 16)
+#define   DKL_PLL_DIV1_TDC_TARGET_CNT(x)	((x) << 0)
+#define   DKL_PLL_DIV1_TDC_TARGET_CNT_MASK	(0xFF << 0)
+#define DKL_PLL_DIV1(tc_port)		_MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \
+						    _DKL_PHY2_BASE) + \
+						    _DKL_PLL_DIV1)
+
+#define _DKL_PLL_SSC				0x210
+#define   DKL_PLL_SSC_IREF_NDIV_RATIO(x)	((x) << 29)
+#define   DKL_PLL_SSC_IREF_NDIV_RATIO_MASK	(0x7 << 29)
+#define   DKL_PLL_SSC_STEP_LEN(x)		((x) << 16)
+#define   DKL_PLL_SSC_STEP_LEN_MASK		(0xFF << 16)
+#define   DKL_PLL_SSC_STEP_NUM(x)		((x) << 11)
+#define   DKL_PLL_SSC_STEP_NUM_MASK		(0x7 << 11)
+#define   DKL_PLL_SSC_EN			(1 << 9)
+#define DKL_PLL_SSC(tc_port)		_MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \
+						    _DKL_PHY2_BASE) + \
+						    _DKL_PLL_SSC)
+
+#define _DKL_PLL_BIAS			0x214
+#define   DKL_PLL_BIAS_FRAC_EN_H	(1 << 30)
+#define   DKL_PLL_BIAS_FBDIV_SHIFT	(8)
+#define   DKL_PLL_BIAS_FBDIV_FRAC(x)	((x) << DKL_PLL_BIAS_FBDIV_SHIFT)
+#define   DKL_PLL_BIAS_FBDIV_FRAC_MASK	(0x3FFFFF << DKL_PLL_BIAS_FBDIV_SHIFT)
+#define DKL_PLL_BIAS(tc_port)		_MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \
+						    _DKL_PHY2_BASE) + \
+						    _DKL_PLL_BIAS)
+
+#define _DKL_PLL_TDC_COLDST_BIAS		0x218
+#define   DKL_PLL_TDC_SSC_STEP_SIZE(x)		((x) << 8)
+#define   DKL_PLL_TDC_SSC_STEP_SIZE_MASK	(0xFF << 8)
+#define   DKL_PLL_TDC_FEED_FWD_GAIN(x)		((x) << 0)
+#define   DKL_PLL_TDC_FEED_FWD_GAIN_MASK	(0xFF << 0)
+#define DKL_PLL_TDC_COLDST_BIAS(tc_port) _MMIO(_PORT(tc_port, \
+						     _DKL_PHY1_BASE, \
+						     _DKL_PHY2_BASE) + \
+						     _DKL_PLL_TDC_COLDST_BIAS)
+
+#define _DKL_REFCLKIN_CTL		0x12C
+/* Bits are the same as MG_REFCLKIN_CTL */
+#define DKL_REFCLKIN_CTL(tc_port)	_MMIO(_PORT(tc_port, \
+						    _DKL_PHY1_BASE, \
+						    _DKL_PHY2_BASE) + \
+					      _DKL_REFCLKIN_CTL)
+
+#define _DKL_CLKTOP2_HSCLKCTL		0xD4
+/* Bits are the same as MG_CLKTOP2_HSCLKCTL */
+#define DKL_CLKTOP2_HSCLKCTL(tc_port)	_MMIO(_PORT(tc_port, \
+						    _DKL_PHY1_BASE, \
+						    _DKL_PHY2_BASE) + \
+					      _DKL_CLKTOP2_HSCLKCTL)
+
+#define _DKL_CLKTOP2_CORECLKCTL1		0xD8
+/* Bits are the same as MG_CLKTOP2_CORECLKCTL1 */
+#define DKL_CLKTOP2_CORECLKCTL1(tc_port)	_MMIO(_PORT(tc_port, \
+							    _DKL_PHY1_BASE, \
+							    _DKL_PHY2_BASE) + \
+						      _DKL_CLKTOP2_CORECLKCTL1)
+
+#define _DKL_TX_DPCNTL0				0x2C0
+#define  DKL_TX_PRESHOOT_COEFF(x)			((x) << 13)
+#define  DKL_TX_PRESHOOT_COEFF_MASK			(0x1f << 13)
+#define  DKL_TX_DE_EMPHASIS_COEFF(x)		((x) << 8)
+#define  DKL_TX_DE_EMPAHSIS_COEFF_MASK		(0x1f << 8)
+#define  DKL_TX_VSWING_CONTROL(x)			((x) << 0)
+#define  DKL_TX_VSWING_CONTROL_MASK			(0x7 << 0)
+#define DKL_TX_DPCNTL0(tc_port) _MMIO(_PORT(tc_port, \
+						     _DKL_PHY1_BASE, \
+						     _DKL_PHY2_BASE) + \
+						     _DKL_TX_DPCNTL0)
+
+#define _DKL_TX_DPCNTL1				0x2C4
+/* Bits are the same as DKL_TX_DPCNTRL0 */
+#define DKL_TX_DPCNTL1(tc_port) _MMIO(_PORT(tc_port, \
+						     _DKL_PHY1_BASE, \
+						     _DKL_PHY2_BASE) + \
+						     _DKL_TX_DPCNTL1)
+
+#define _DKL_TX_DPCNTL2				0x2C8
+#define  DKL_TX_DP20BITMODE				(1 << 2)
+#define DKL_TX_DPCNTL2(tc_port) _MMIO(_PORT(tc_port, \
+						     _DKL_PHY1_BASE, \
+						     _DKL_PHY2_BASE) + \
+						     _DKL_TX_DPCNTL2)
+
+#define _DKL_TX_FW_CALIB				0x2F8
+#define  DKL_TX_CFG_DISABLE_WAIT_INIT			(1 << 7)
+#define DKL_TX_FW_CALIB(tc_port) _MMIO(_PORT(tc_port, \
+						     _DKL_PHY1_BASE, \
+						     _DKL_PHY2_BASE) + \
+						     _DKL_TX_FW_CALIB)
+
+#define _DKL_TX_DW17					0xDC4
+#define DKL_TX_DW17(tc_port) _MMIO(_PORT(tc_port, \
+						     _DKL_PHY1_BASE, \
+						     _DKL_PHY2_BASE) + \
+						     _DKL_TX_DW17)
+
+#define _DKL_TX_DW18					0xDC8
+#define DKL_TX_DW18(tc_port) _MMIO(_PORT(tc_port, \
+						     _DKL_PHY1_BASE, \
+						     _DKL_PHY2_BASE) + \
+						     _DKL_TX_DW18)
+
+#define _DKL_DP_MODE					0xA0
+#define  DKL_DP_MODE_CFG_GAONPWR_GATING		(1 << 1)
+#define  DKL_DP_MODE_CFG_DIGPWR_GATING		(1 << 2)
+#define  DKL_DP_MODE_CFG_CLNPWR_GATING		(1 << 3)
+#define  DKL_DP_MODE_CFG_TRPWR_GATING		(1 << 4)
+#define  DKL_DP_MODE_CFG_TR2PWR_GATING		(1 << 5)
+#define  DKL_DP_MODE_CFG_GATING_CTRL_MASK	(0x1f << 1)
+#define  DKL_DP_MODE_CFG_DP_X1_MODE			(1 << 6)
+#define  DKL_DP_MODE_CFG_DP_X2_MODE			(1 << 7)
+#define DKL_DP_MODE(tc_port) _MMIO(_PORT(tc_port, \
+						     _DKL_PHY1_BASE, \
+						     _DKL_PHY2_BASE) + \
+						     _DKL_DP_MODE)
+
+#define _DKL_CMN_UC_DW27			0x36C
+#define  DKL_CMN_UC_DW27_UC_HEALTH		(0x1 << 15)
+#define DKL_CMN_UC_DW_27(tc_port)		_MMIO(_PORT(tc_port, \
+							    _DKL_PHY1_BASE, \
+							    _DKL_PHY2_BASE) + \
+							    _DKL_CMN_UC_DW27)
+
+/*
+ * Each Dekel PHY is addressed through a 4KB aperture. Each PHY has more than
+ * 4KB of register space, so a separate index is programmed in HIP_INDEX_REG0
+ * or HIP_INDEX_REG1, based on the port number, to set the upper 2 address
+ * bits that point the 4KB window into the full PHY register space.
+ */
+#define _HIP_INDEX_REG0			0x1010A0
+#define _HIP_INDEX_REG1			0x1010A4
+#define HIP_INDEX_REG(tc_port)		_MMIO((tc_port) < 4 ? _HIP_INDEX_REG0 \
+					      : _HIP_INDEX_REG1)
+#define _HIP_INDEX_SHIFT(tc_port)	(8 * ((tc_port) % 4))
+#define HIP_INDEX_VAL(tc_port, val)	((val) << _HIP_INDEX_SHIFT(tc_port))
+
 /* BXT display engine PLL */
 #define BXT_DE_PLL_CTL			_MMIO(0x6d000)
 #define   BXT_DE_PLL_RATIO(x)		(x)	/* {60,65,100} * 19.2MHz */
-- 
cgit v1.2.3


From 8aaf5cbda8f1684ffb7027724f67da086f46a0f4 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Fri, 20 Sep 2019 13:58:09 -0700
Subject: drm/i915/icl: Unify disable and enable phy clock gating functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Adding a enable parameters allow us to share most of the code between
enable and disable functions.

v3:
Renamed icl_phy_clock_gating() to icl_phy_set_clock_gating()

Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920205810.211048-6-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 73 ++++++++++----------------------
 1 file changed, 23 insertions(+), 50 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index dfd6b064cbc3..33cd766f9eea 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3033,67 +3033,40 @@ static void intel_ddi_clk_disable(struct intel_encoder *encoder)
 	}
 }
 
-static void icl_enable_phy_clock_gating(struct intel_digital_port *dig_port)
+static void
+icl_phy_set_clock_gating(struct intel_digital_port *dig_port, bool enable)
 {
 	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
 	enum port port = dig_port->base.port;
 	enum tc_port tc_port = intel_port_to_tc(dev_priv, port);
-	u32 val;
+	u32 val, bits;
 	int ln;
 
 	if (tc_port == PORT_TC_NONE)
 		return;
 
-	for (ln = 0; ln < 2; ln++) {
-		val = I915_READ(MG_DP_MODE(ln, port));
-		val |= MG_DP_MODE_CFG_TR2PWR_GATING |
-		       MG_DP_MODE_CFG_TRPWR_GATING |
-		       MG_DP_MODE_CFG_CLNPWR_GATING |
-		       MG_DP_MODE_CFG_DIGPWR_GATING |
-		       MG_DP_MODE_CFG_GAONPWR_GATING;
-		I915_WRITE(MG_DP_MODE(ln, port), val);
-	}
-
-	val = I915_READ(MG_MISC_SUS0(tc_port));
-	val |= MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE(3) |
-	       MG_MISC_SUS0_CFG_TR2PWR_GATING |
-	       MG_MISC_SUS0_CFG_CL2PWR_GATING |
-	       MG_MISC_SUS0_CFG_GAONPWR_GATING |
-	       MG_MISC_SUS0_CFG_TRPWR_GATING |
-	       MG_MISC_SUS0_CFG_CL1PWR_GATING |
-	       MG_MISC_SUS0_CFG_DGPWR_GATING;
-	I915_WRITE(MG_MISC_SUS0(tc_port), val);
-}
-
-static void icl_disable_phy_clock_gating(struct intel_digital_port *dig_port)
-{
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	enum port port = dig_port->base.port;
-	enum tc_port tc_port = intel_port_to_tc(dev_priv, port);
-	u32 val;
-	int ln;
-
-	if (tc_port == PORT_TC_NONE)
-		return;
+	bits = MG_DP_MODE_CFG_TR2PWR_GATING | MG_DP_MODE_CFG_TRPWR_GATING |
+	       MG_DP_MODE_CFG_CLNPWR_GATING | MG_DP_MODE_CFG_DIGPWR_GATING |
+	       MG_DP_MODE_CFG_GAONPWR_GATING;
 
 	for (ln = 0; ln < 2; ln++) {
 		val = I915_READ(MG_DP_MODE(ln, port));
-		val &= ~(MG_DP_MODE_CFG_TR2PWR_GATING |
-			 MG_DP_MODE_CFG_TRPWR_GATING |
-			 MG_DP_MODE_CFG_CLNPWR_GATING |
-			 MG_DP_MODE_CFG_DIGPWR_GATING |
-			 MG_DP_MODE_CFG_GAONPWR_GATING);
+		if (enable)
+			val |= bits;
+		else
+			val &= ~bits;
 		I915_WRITE(MG_DP_MODE(ln, port), val);
 	}
 
+	bits = MG_MISC_SUS0_CFG_TR2PWR_GATING | MG_MISC_SUS0_CFG_CL2PWR_GATING |
+	       MG_MISC_SUS0_CFG_GAONPWR_GATING | MG_MISC_SUS0_CFG_TRPWR_GATING |
+	       MG_MISC_SUS0_CFG_CL1PWR_GATING | MG_MISC_SUS0_CFG_DGPWR_GATING;
+
 	val = I915_READ(MG_MISC_SUS0(tc_port));
-	val &= ~(MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE_MASK |
-		 MG_MISC_SUS0_CFG_TR2PWR_GATING |
-		 MG_MISC_SUS0_CFG_CL2PWR_GATING |
-		 MG_MISC_SUS0_CFG_GAONPWR_GATING |
-		 MG_MISC_SUS0_CFG_TRPWR_GATING |
-		 MG_MISC_SUS0_CFG_CL1PWR_GATING |
-		 MG_MISC_SUS0_CFG_DGPWR_GATING);
+	if (enable)
+		val |= (bits | MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE(3));
+	else
+		val &= ~(bits | MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE_MASK);
 	I915_WRITE(MG_MISC_SUS0(tc_port), val);
 }
 
@@ -3258,7 +3231,7 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	intel_ddi_config_transcoder_func(crtc_state);
 
 	/* 7.d */
-	icl_disable_phy_clock_gating(dig_port);
+	icl_phy_set_clock_gating(dig_port, false);
 
 	/* 7.e */
 	icl_ddi_vswing_sequence(encoder, crtc_state->port_clock, level,
@@ -3328,7 +3301,7 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 					dig_port->ddi_io_power_domain);
 
 	icl_program_mg_dp_mode(dig_port);
-	icl_disable_phy_clock_gating(dig_port);
+	icl_phy_set_clock_gating(dig_port, false);
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		icl_ddi_vswing_sequence(encoder, crtc_state->port_clock,
@@ -3361,7 +3334,7 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 
 	intel_ddi_enable_fec(encoder, crtc_state);
 
-	icl_enable_phy_clock_gating(dig_port);
+	icl_phy_set_clock_gating(dig_port, true);
 
 	if (!is_mst)
 		intel_ddi_enable_pipe_clock(crtc_state);
@@ -3398,7 +3371,7 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 	intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain);
 
 	icl_program_mg_dp_mode(dig_port);
-	icl_disable_phy_clock_gating(dig_port);
+	icl_phy_set_clock_gating(dig_port, false);
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		icl_ddi_vswing_sequence(encoder, crtc_state->port_clock,
@@ -3410,7 +3383,7 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 	else
 		intel_prepare_hdmi_ddi_buffers(encoder, level);
 
-	icl_enable_phy_clock_gating(dig_port);
+	icl_phy_set_clock_gating(dig_port, true);
 
 	if (IS_GEN9_BC(dev_priv))
 		skl_ddi_set_iboost(encoder, level, INTEL_OUTPUT_HDMI);
-- 
cgit v1.2.3


From 27ffe6e570aa93e8389f7b0299a329e51d02843c Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Fri, 20 Sep 2019 13:58:10 -0700
Subject: drm/i915/tgl: Check the UC health of tc controllers after power on
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

New step added for TGL, required for us to check the TC
microcontroller health after power on TC aux.

BSpec: 49294

Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920205810.211048-7-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_display_power.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index ce88a27229ef..f1186bc23542 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -562,6 +562,8 @@ static void icl_tc_port_assert_ref_held(struct drm_i915_private *dev_priv,
 
 #endif
 
+#define TGL_AUX_PW_TO_TC_PORT(pw_idx)	((pw_idx) - TGL_PW_CTL_IDX_AUX_TC1)
+
 static void
 icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
 				 struct i915_power_well *power_well)
@@ -578,6 +580,17 @@ icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
 	I915_WRITE(DP_AUX_CH_CTL(aux_ch), val);
 
 	hsw_power_well_enable(dev_priv, power_well);
+
+	if (INTEL_GEN(dev_priv) >= 12 && !power_well->desc->hsw.is_tc_tbt) {
+		enum tc_port tc_port;
+
+		tc_port = TGL_AUX_PW_TO_TC_PORT(power_well->desc->hsw.idx);
+		I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, 0x2));
+
+		if (intel_de_wait_for_set(dev_priv, DKL_CMN_UC_DW_27(tc_port),
+					  DKL_CMN_UC_DW27_UC_HEALTH, 1))
+			DRM_WARN("Timeout waiting TC uC health\n");
+	}
 }
 
 static void
-- 
cgit v1.2.3


From 04e0e1777a792223897b8c21eb4e0a5b2624d9df Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Mon, 23 Sep 2019 11:25:31 -0700
Subject: ARM: omap2plus_defconfig: Enable DRM_TI_TFP410

The TFP410 driver was removed but the replacement driver was
never enabled.  This patch enableds the DRM_TI_TFP410

Fixes: be3143d8b27f ("drm/omap: Remove TFP410 and DVI connector drivers")

Signed-off-by: Adam Ford <aford173@gmail.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/configs/omap2plus_defconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 64eb896907bf..ab046eb41c7a 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -364,6 +364,7 @@ CONFIG_DRM_OMAP_PANEL_TPO_TD043MTEA1=m
 CONFIG_DRM_OMAP_PANEL_NEC_NL8048HL11=m
 CONFIG_DRM_TILCDC=m
 CONFIG_DRM_PANEL_SIMPLE=m
+CONFIG_DRM_TI_TFP410=m
 CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_MODE_HELPERS=y
-- 
cgit v1.2.3


From 1d70ded8567ccf70353ff97e3b13f267c889f934 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Sun, 22 Sep 2019 10:57:40 -0700
Subject: ARM: omap2plus_defconfig: Enable more droid4 devices as loadable
 modules

Droid4 needs USB option serial driver for modem, and lm3532 for the
LCD backlight.

Note that the LCD backlight does not yet get enabled automatically,
but needs to be done manually with:

# echo 50 > /sys/class/leds/lm3532::backlight/brightness

Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/configs/omap2plus_defconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index ab046eb41c7a..ae326572c62a 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -424,6 +424,7 @@ CONFIG_USB_SERIAL_GENERIC=y
 CONFIG_USB_SERIAL_SIMPLE=m
 CONFIG_USB_SERIAL_FTDI_SIO=m
 CONFIG_USB_SERIAL_PL2303=m
+CONFIG_USB_SERIAL_OPTION=m
 CONFIG_USB_TEST=m
 CONFIG_NOP_USB_XCEIV=m
 CONFIG_AM335X_PHY_USB=m
@@ -461,6 +462,7 @@ CONFIG_MMC_SDHCI_OMAP=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=m
 CONFIG_LEDS_CPCAP=m
+CONFIG_LEDS_LM3532=m
 CONFIG_LEDS_GPIO=m
 CONFIG_LEDS_PCA963X=m
 CONFIG_LEDS_PWM=m
-- 
cgit v1.2.3


From b647c7df01b75761b4c0b1cb6f4841088c0b1121 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 16:28:42 +0100
Subject: drm/i915: Fixup preempt-to-busy vs resubmission of a virtual request

As preempt-to-busy leaves the request on the HW as the resubmission is
processed, that request may complete in the background and even cause a
second virtual request to enter queue. This second virtual request
breaks our "single request in the virtual pipeline" assumptions.
Furthermore, as the virtual request may be completed and retired, we
lose the reference the virtual engine assumes is held. Normally, just
removing the request from the scheduler queue removes it from the
engine, but the virtual engine keeps track of its singleton request via
its ve->request. This pointer needs protecting with a reference.

v2: Drop unnecessary motion of rq->engine = owner

Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923152844.8914-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 32 ++++++++++++++++++++++++++------
 1 file changed, 26 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index bff4c6a735cf..114819fb5a24 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1256,6 +1256,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				submit = true;
 				last = rq;
 			}
+			i915_request_put(rq);
 
 			/*
 			 * Hmm, we have a bunch of virtual engine requests,
@@ -2556,6 +2557,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 
 			rq->engine = engine;
 			__i915_request_submit(rq);
+			i915_request_put(rq);
 
 			ve->base.execlists.queue_priority_hint = INT_MIN;
 		}
@@ -3809,6 +3811,8 @@ submit_engine:
 static void virtual_submit_request(struct i915_request *rq)
 {
 	struct virtual_engine *ve = to_virtual_engine(rq->engine);
+	struct i915_request *old;
+	unsigned long flags;
 
 	GEM_TRACE("%s: rq=%llx:%lld\n",
 		  ve->base.name,
@@ -3817,15 +3821,31 @@ static void virtual_submit_request(struct i915_request *rq)
 
 	GEM_BUG_ON(ve->base.submit_request != virtual_submit_request);
 
-	GEM_BUG_ON(ve->request);
-	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+	spin_lock_irqsave(&ve->base.active.lock, flags);
+
+	old = ve->request;
+	if (old) { /* background completion event from preempt-to-busy */
+		GEM_BUG_ON(!i915_request_completed(old));
+		__i915_request_submit(old);
+		i915_request_put(old);
+	}
 
-	ve->base.execlists.queue_priority_hint = rq_prio(rq);
-	WRITE_ONCE(ve->request, rq);
+	if (i915_request_completed(rq)) {
+		__i915_request_submit(rq);
 
-	list_move_tail(&rq->sched.link, virtual_queue(ve));
+		ve->base.execlists.queue_priority_hint = INT_MIN;
+		ve->request = NULL;
+	} else {
+		ve->base.execlists.queue_priority_hint = rq_prio(rq);
+		ve->request = i915_request_get(rq);
+
+		GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+		list_move_tail(&rq->sched.link, virtual_queue(ve));
+
+		tasklet_schedule(&ve->base.execlists.tasklet);
+	}
 
-	tasklet_schedule(&ve->base.execlists.tasklet);
+	spin_unlock_irqrestore(&ve->base.active.lock, flags);
 }
 
 static struct ve_bond *
-- 
cgit v1.2.3


From cb2377a919bbe8107af269c5a31a8d5cfb27d867 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 16:28:43 +0100
Subject: drm/i915: Fixup preempt-to-busy vs reset of a virtual request

Due to the nature of preempt-to-busy the execlists active tracking and
the schedule queue may become temporarily desync'ed (between resubmission
to HW and its ack from HW). This means that we may have unwound a
request and passed it back to the virtual engine, but it is still
inflight on the HW and may even result in a GPU hang. If we detect that
GPU hang and try to reset, the hanging request->engine will no longer
match the current engine, which means that the request is not on the
execlists active list and we should not try to find an older incomplete
request. Given that we have deduced this must be a request on a virtual
engine, it is the single active request in the context and so must be
guilty (as the context is still inflight, it is prevented from being
executed on another engine as we process the reset).

Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923152844.8914-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c   | 7 +++++--
 drivers/gpu/drm/i915/gt/intel_reset.c | 4 +---
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 114819fb5a24..322287943e33 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2348,11 +2348,14 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
 
 static struct i915_request *active_request(struct i915_request *rq)
 {
-	const struct list_head * const list =
-		&i915_request_active_timeline(rq)->requests;
 	const struct intel_context * const ce = rq->hw_context;
 	struct i915_request *active = NULL;
+	struct list_head *list;
 
+	if (!i915_request_is_active(rq)) /* unwound, but incomplete! */
+		return rq;
+
+	list = &i915_request_active_timeline(rq)->requests;
 	list_for_each_entry_from_reverse(rq, list, link) {
 		if (i915_request_completed(rq))
 			break;
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 89048ca8924c..ae68c3786f63 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -42,11 +42,10 @@ static void engine_skip_context(struct i915_request *rq)
 	struct intel_engine_cs *engine = rq->engine;
 	struct i915_gem_context *hung_ctx = rq->gem_context;
 
-	lockdep_assert_held(&engine->active.lock);
-
 	if (!i915_request_is_active(rq))
 		return;
 
+	lockdep_assert_held(&engine->active.lock);
 	list_for_each_entry_continue(rq, &engine->active.requests, sched.link)
 		if (rq->gem_context == hung_ctx)
 			i915_request_skip(rq, -EIO);
@@ -123,7 +122,6 @@ void __i915_request_reset(struct i915_request *rq, bool guilty)
 		  rq->fence.seqno,
 		  yesno(guilty));
 
-	lockdep_assert_held(&rq->engine->active.lock);
 	GEM_BUG_ON(i915_request_completed(rq));
 
 	if (guilty) {
-- 
cgit v1.2.3


From e2144503bf3b22275dd33cef2880e1cb5fb200c5 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 16:28:44 +0100
Subject: drm/i915: Prevent bonded requests from overtaking each other on
 preemption

Force bonded requests to run on distinct engines so that they cannot be
shuffled onto the same engine where timeslicing will reverse the order.
A bonded request will often wait on a semaphore signaled by its master,
creating an implicit dependency -- if we ignore that implicit dependency
and allow the bonded request to run on the same engine and before its
master, we will cause a GPU hang. [Whether it will hang the GPU is
debatable, we should keep on timeslicing and each timeslice should be
"accidentally" counted as forward progress, in which case it should run
but at one-half to one-third speed.]

We can prevent this inversion by restricting which engines we allow
ourselves to jump to upon preemption, i.e. baking in the arrangement
established at first execution. (We should also consider capturing the
implicit dependency using i915_sched_add_dependency(), but first we need
to think about the constraints that requires on the execution/retirement
ordering.)

Fixes: 8ee36e048c98 ("drm/i915/execlists: Minimalistic timeslicing")
References: ee1136908e9b ("drm/i915/execlists: Virtual engine bonding")
Testcase: igt/gem_exec_balancer/bonded-slice
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923152844.8914-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 322287943e33..6cfdc0f9f2b9 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -3869,18 +3869,22 @@ static void
 virtual_bond_execute(struct i915_request *rq, struct dma_fence *signal)
 {
 	struct virtual_engine *ve = to_virtual_engine(rq->engine);
+	intel_engine_mask_t allowed, exec;
 	struct ve_bond *bond;
 
+	allowed = ~to_request(signal)->engine->mask;
+
 	bond = virtual_find_bond(ve, to_request(signal)->engine);
-	if (bond) {
-		intel_engine_mask_t old, new, cmp;
+	if (bond)
+		allowed &= bond->sibling_mask;
 
-		cmp = READ_ONCE(rq->execution_mask);
-		do {
-			old = cmp;
-			new = cmp & bond->sibling_mask;
-		} while ((cmp = cmpxchg(&rq->execution_mask, old, new)) != old);
-	}
+	/* Restrict the bonded request to run on only the available engines */
+	exec = READ_ONCE(rq->execution_mask);
+	while (!try_cmpxchg(&rq->execution_mask, &exec, exec & allowed))
+		;
+
+	/* Prevent the master from being re-run on the bonded engines */
+	to_request(signal)->execution_mask &= ~allowed;
 }
 
 struct intel_context *
-- 
cgit v1.2.3


From 0ec64895b05269c1814ea5befcadcd1184a12915 Mon Sep 17 00:00:00 2001
From: John Pittman <jpittman@redhat.com>
Date: Tue, 17 Sep 2019 14:52:00 -0400
Subject: nvmet: change ppl to lpp

In nvmet_bdev_set_limits() the number of logical blocks per
physical block is calculated, but the opposite is mentioned in
the associated comment and reflected in the variable name. Correct
the comment and adjust the variable name to reflect the calculation
done.

Signed-off-by: John Pittman <jpittman@redhat.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/target/io-cmd-bdev.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index de0bff70ebb6..32008d85172b 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -11,10 +11,10 @@
 void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
 {
 	const struct queue_limits *ql = &bdev_get_queue(bdev)->limits;
-	/* Number of physical blocks per logical block. */
-	const u32 ppl = ql->physical_block_size / ql->logical_block_size;
-	/* Physical blocks per logical block, 0's based. */
-	const __le16 ppl0b = to0based(ppl);
+	/* Number of logical blocks per physical block. */
+	const u32 lpp = ql->physical_block_size / ql->logical_block_size;
+	/* Logical blocks per physical block, 0's based. */
+	const __le16 lpp0b = to0based(lpp);
 
 	/*
 	 * For NVMe 1.2 and later, bit 1 indicates that the fields NAWUN,
@@ -25,9 +25,9 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
 	 * field from the identify controller data structure should be used.
 	 */
 	id->nsfeat |= 1 << 1;
-	id->nawun = ppl0b;
-	id->nawupf = ppl0b;
-	id->nacwu = ppl0b;
+	id->nawun = lpp0b;
+	id->nawupf = lpp0b;
+	id->nacwu = lpp0b;
 
 	/*
 	 * Bit 4 indicates that the fields NPWG, NPWA, NPDG, NPDA, and
@@ -36,7 +36,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id)
 	 */
 	id->nsfeat |= 1 << 4;
 	/* NPWG = Namespace Preferred Write Granularity. 0's based */
-	id->npwg = ppl0b;
+	id->npwg = lpp0b;
 	/* NPWA = Namespace Preferred Write Alignment. 0's based */
 	id->npwa = id->npwg;
 	/* NPDG = Namespace Preferred Deallocate Granularity. 0's based */
-- 
cgit v1.2.3


From b224726de5e496dbf78147a66755c3d81e28bdd2 Mon Sep 17 00:00:00 2001
From: Balbir Singh <sblbir@amzn.com>
Date: Wed, 18 Sep 2019 00:27:20 +0000
Subject: nvme-pci: Fix a race in controller removal

User space programs like udevd may try to read to partitions at the
same time the driver detects a namespace is unusable, and may deadlock
if revalidate_disk() is called while such a process is waiting to
enter the frozen queue. On detecting a dead namespace, move the disk
revalidate after unblocking dispatchers that may be holding bd_butex.

changelog Suggested-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Balbir Singh <sblbir@amzn.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 108f60b46804..0c385b1994fe 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -102,10 +102,13 @@ static void nvme_set_queue_dying(struct nvme_ns *ns)
 	 */
 	if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
 		return;
-	revalidate_disk(ns->disk);
 	blk_set_queue_dying(ns->queue);
 	/* Forcibly unquiesce queues to avoid blocking dispatch */
 	blk_mq_unquiesce_queue(ns->queue);
+	/*
+	 * Revalidate after unblocking dispatchers that may be holding bd_butex
+	 */
+	revalidate_disk(ns->disk);
 }
 
 static void nvme_queue_scan(struct nvme_ctrl *ctrl)
-- 
cgit v1.2.3


From 82a9ac7130cf51c2640800fb0ef19d3a05cb8fff Mon Sep 17 00:00:00 2001
From: Steffen Maier <maier@linux.ibm.com>
Date: Wed, 7 Aug 2019 16:49:47 +0200
Subject: scsi: core: fix missing .cleanup_rq for SCSI hosts without request
 batching

This was missing from scsi_mq_ops_no_commit of linux-next commit
8930a6c20791 ("scsi: core: add support for request batching") from Martin's
scsi/5.4/scsi-queue or James' scsi/misc.

See also linux-next commit b7e9e1fb7a92 ("scsi: implement .cleanup_rq
callback") from block/for-next.

Signed-off-by: Steffen Maier <maier@linux.ibm.com>
Fixes: 8930a6c20791 ("scsi: core: add support for request batching")
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index dc210b9d4896..12db0c13a927 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1834,6 +1834,7 @@ static const struct blk_mq_ops scsi_mq_ops_no_commit = {
 	.init_request	= scsi_mq_init_request,
 	.exit_request	= scsi_mq_exit_request,
 	.initialize_rq_fn = scsi_initialize_rq,
+	.cleanup_rq	= scsi_cleanup_rq,
 	.busy		= scsi_mq_lld_busy,
 	.map_queues	= scsi_map_queues,
 };
-- 
cgit v1.2.3


From 6b6fa7a5c86e1269d9f0c9a5b902072351317387 Mon Sep 17 00:00:00 2001
From: Steffen Maier <maier@linux.ibm.com>
Date: Wed, 7 Aug 2019 16:49:48 +0200
Subject: scsi: core: fix dh and multipathing for SCSI hosts without request
 batching

This was missing from scsi_device_from_queue() due to the introduction of
another new scsi_mq_ops_no_commit of linux-next commit 8930a6c20791 ("scsi:
core: add support for request batching") from Martin's scsi/5.4/scsi-queue
or James' scsi/misc.

Only devicehandler code seems to call scsi_device_from_queue():
*** drivers/scsi/scsi_dh.c:
scsi_dh_activate[255]          sdev = scsi_device_from_queue(q);
scsi_dh_set_params[302]        sdev = scsi_device_from_queue(q);
scsi_dh_attach[325]            sdev = scsi_device_from_queue(q);
scsi_dh_attached_handler_name[363] sdev = scsi_device_from_queue(q);

Fixes multipath tools follow-on errors:

$ multipath -v6
...
libdevmapper: ioctl/libdm-iface.c(1887): device-mapper: reload ioctl on mpatha  failed: No such device
...
mpatha: failed to load map, error 19
...

showing also as kernel messages:

device-mapper: table: 252:0: multipath: error attaching hardware handler
device-mapper: ioctl: error adding target to table

Signed-off-by: Steffen Maier <maier@linux.ibm.com>
Fixes: 8930a6c20791 ("scsi: core: add support for request batching")
Cc: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 12db0c13a927..5447738906ac 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1922,7 +1922,8 @@ struct scsi_device *scsi_device_from_queue(struct request_queue *q)
 {
 	struct scsi_device *sdev = NULL;
 
-	if (q->mq_ops == &scsi_mq_ops)
+	if (q->mq_ops == &scsi_mq_ops_no_commit ||
+	    q->mq_ops == &scsi_mq_ops)
 		sdev = q->queuedata;
 	if (!sdev || !get_device(&sdev->sdev_gendev))
 		sdev = NULL;
-- 
cgit v1.2.3


From c9c53749375ccce0191f89b86732e642f914bd82 Mon Sep 17 00:00:00 2001
From: Laurence Oberman <loberman@redhat.com>
Date: Wed, 11 Sep 2019 09:56:42 -0400
Subject: scsi: bnx2fc: Handle scope bits when array returns BUSY or TSF

The qla2xxx driver had this issue as well when the newer array firmware
returned the retry_delay_timer in the fcp_rsp.  The bnx2fc is not handling
the masking of the scope bits either so the retry_delay_timestamp value
lands up being a large value added to the timer timestamp delaying I/O for
up to 27 Minutes.  This patch adds similar code to handle this to the
bnx2fc driver to avoid the huge delay.

Link: https://lore.kernel.org/r/1568210202-12794-1-git-send-email-loberman@redhat.com
Signed-off-by: Laurence Oberman <loberman@redhat.com>
Reported-by: David Jeffery <djeffery@redhat.com>
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/bnx2fc/bnx2fc_io.c | 29 ++++++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c
index da00ca5fa5dc..401743e2b429 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_io.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_io.c
@@ -1923,6 +1923,7 @@ void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req,
 	struct fcoe_fcp_rsp_payload *fcp_rsp;
 	struct bnx2fc_rport *tgt = io_req->tgt;
 	struct scsi_cmnd *sc_cmd;
+	u16 scope = 0, qualifier = 0;
 
 	/* scsi_cmd_cmpl is called with tgt lock held */
 
@@ -1990,12 +1991,30 @@ void bnx2fc_process_scsi_cmd_compl(struct bnx2fc_cmd *io_req,
 
 			if (io_req->cdb_status == SAM_STAT_TASK_SET_FULL ||
 			    io_req->cdb_status == SAM_STAT_BUSY) {
-				/* Set the jiffies + retry_delay_timer * 100ms
-				   for the rport/tgt */
-				tgt->retry_delay_timestamp = jiffies +
-					fcp_rsp->retry_delay_timer * HZ / 10;
+				/* Newer array firmware with BUSY or
+				 * TASK_SET_FULL may return a status that needs
+				 * the scope bits masked.
+				 * Or a huge delay timestamp up to 27 minutes
+				 * can result.
+				 */
+				if (fcp_rsp->retry_delay_timer) {
+					/* Upper 2 bits */
+					scope = fcp_rsp->retry_delay_timer
+						& 0xC000;
+					/* Lower 14 bits */
+					qualifier = fcp_rsp->retry_delay_timer
+						& 0x3FFF;
+				}
+				if (scope > 0 && qualifier > 0 &&
+					qualifier <= 0x3FEF) {
+					/* Set the jiffies +
+					 * retry_delay_timer * 100ms
+					 * for the rport/tgt
+					 */
+					tgt->retry_delay_timestamp = jiffies +
+						(qualifier * HZ / 10);
+				}
 			}
-
 		}
 		if (io_req->fcp_resid)
 			scsi_set_resid(sc_cmd, io_req->fcp_resid);
-- 
cgit v1.2.3


From f51913eef23f74c3bd07899dc7f1ed6df9e521d8 Mon Sep 17 00:00:00 2001
From: Stanley Chu <stanley.chu@mediatek.com>
Date: Wed, 18 Sep 2019 12:20:38 +0800
Subject: scsi: ufs: skip shutdown if hba is not powered

In some cases, hba may go through shutdown flow without successful
initialization and then make system hang.

For example, if ufshcd_change_power_mode() gets error and leads to
ufshcd_hba_exit() to release resources of the host, future shutdown flow
may hang the system since the host register will be accessed in unpowered
state.

To solve this issue, simply add checking to skip shutdown for above kind of
situation.

Link: https://lore.kernel.org/r/1568780438-28753-1-git-send-email-stanley.chu@mediatek.com
Signed-off-by: Stanley Chu <stanley.chu@mediatek.com>
Acked-by: Bean Huo <beanhuo@micron.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ufs/ufshcd.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index c4a015e42045..57b2c3a8def3 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -8140,6 +8140,9 @@ int ufshcd_shutdown(struct ufs_hba *hba)
 {
 	int ret = 0;
 
+	if (!hba->is_powered)
+		goto out;
+
 	if (ufshcd_is_ufs_dev_poweroff(hba) && ufshcd_is_link_off(hba))
 		goto out;
 
-- 
cgit v1.2.3


From 4b062e7cf940aa4f38fedc3a964b24cb095373f0 Mon Sep 17 00:00:00 2001
From: Austin Kim <austindh.kim@gmail.com>
Date: Thu, 19 Sep 2019 16:55:48 +0900
Subject: scsi: qedf: Remove always false 'tmp_prio < 0' statement

Since tmp_prio is declared as u8, the following statement is always false.
   tmp_prio < 0

So remove 'always false' statement.

Link: https://lore.kernel.org/r/20190919075548.GA112801@LGEARND20B15
Signed-off-by: Austin Kim <austindh.kim@gmail.com>
Acked-by: Saurav Kashyap <skashyap@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qedf/qedf_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 9c24f3834d70..1d2c111bdf82 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -596,7 +596,7 @@ static void qedf_dcbx_handler(void *dev, struct qed_dcbx_get *get, u32 mib_type)
 		tmp_prio = get->operational.app_prio.fcoe;
 		if (qedf_default_prio > -1)
 			qedf->prio = qedf_default_prio;
-		else if (tmp_prio < 0 || tmp_prio > 7) {
+		else if (tmp_prio > 7) {
 			QEDF_INFO(&(qedf->dbg_ctx), QEDF_LOG_DISC,
 			    "FIP/FCoE prio %d out of range, setting to %d.\n",
 			    tmp_prio, QEDF_DEFAULT_PRIO);
-- 
cgit v1.2.3


From 0ed8810276907c8a633dc8cecc48dabb6678cd23 Mon Sep 17 00:00:00 2001
From: Long Li <longli@microsoft.com>
Date: Fri, 6 Sep 2019 10:24:20 -0700
Subject: scsi: storvsc: setup 1:1 mapping between hardware queue and CPU queue

storvsc doesn't use a dedicated hardware queue for a given CPU queue. When
issuing I/O, it selects returning CPU (hardware queue) dynamically based on
vmbus channel usage across all channels.

This patch advertises num_present_cpus() as number of hardware queues. This
will have upper layer setup 1:1 mapping between hardware queue and CPU
queue and avoid unnecessary locking when issuing I/O.

Link: https://lore.kernel.org/r/1567790660-48142-1-git-send-email-longli@linuxonhyperv.com
Signed-off-by: Long Li <longli@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/storvsc_drv.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index ed8b9ac805e6..542d2bac2922 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1837,8 +1837,7 @@ static int storvsc_probe(struct hv_device *device,
 	/*
 	 * Set the number of HW queues we are supporting.
 	 */
-	if (stor_device->num_sc != 0)
-		host->nr_hw_queues = stor_device->num_sc + 1;
+	host->nr_hw_queues = num_present_cpus();
 
 	/*
 	 * Set the error handler work queue.
-- 
cgit v1.2.3


From 70054aa39a013fa52eff432f2223b8bd5c0048f8 Mon Sep 17 00:00:00 2001
From: Xiang Chen <chenxiang66@hisilicon.com>
Date: Sat, 7 Sep 2019 09:07:30 +0800
Subject: scsi: megaraid: disable device when probe failed after enabled device

For pci device, need to disable device when probe failed after enabled
device.

Link: https://lore.kernel.org/r/1567818450-173315-1-git-send-email-chenxiang66@hisilicon.com
Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Reviewed-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/megaraid.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 45a66048801b..ff6d4aa92421 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -4183,11 +4183,11 @@ megaraid_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		 */
 		if (pdev->subsystem_vendor == PCI_VENDOR_ID_COMPAQ &&
 		    pdev->subsystem_device == 0xC000)
-		   	return -ENODEV;
+			goto out_disable_device;
 		/* Now check the magic signature byte */
 		pci_read_config_word(pdev, PCI_CONF_AMISIG, &magic);
 		if (magic != HBA_SIGNATURE_471 && magic != HBA_SIGNATURE)
-			return -ENODEV;
+			goto out_disable_device;
 		/* Ok it is probably a megaraid */
 	}
 
-- 
cgit v1.2.3


From 4b6b1bb68628ec49e4cbfabd8ac17a169f079cd8 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 23 Sep 2019 13:40:35 +0800
Subject: scsi: hisi_sas: Make three functions static

Fix sparse warnings:

drivers/scsi/hisi_sas/hisi_sas_main.c:3686:6:
 warning: symbol 'hisi_sas_debugfs_release' was not declared. Should it be static?
drivers/scsi/hisi_sas/hisi_sas_main.c:3708:5:
 warning: symbol 'hisi_sas_debugfs_alloc' was not declared. Should it be static?
drivers/scsi/hisi_sas/hisi_sas_main.c:3799:6:
 warning: symbol 'hisi_sas_debugfs_bist_init' was not declared. Should it be static?

Link: https://lore.kernel.org/r/20190923054035.19036-1-yuehaibing@huawei.com
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index d1513fdf1e00..0847e682797b 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -3683,7 +3683,7 @@ void hisi_sas_debugfs_work_handler(struct work_struct *work)
 }
 EXPORT_SYMBOL_GPL(hisi_sas_debugfs_work_handler);
 
-void hisi_sas_debugfs_release(struct hisi_hba *hisi_hba)
+static void hisi_sas_debugfs_release(struct hisi_hba *hisi_hba)
 {
 	struct device *dev = hisi_hba->dev;
 	int i;
@@ -3705,7 +3705,7 @@ void hisi_sas_debugfs_release(struct hisi_hba *hisi_hba)
 		devm_kfree(dev, hisi_hba->debugfs_port_reg[i]);
 }
 
-int hisi_sas_debugfs_alloc(struct hisi_hba *hisi_hba)
+static int hisi_sas_debugfs_alloc(struct hisi_hba *hisi_hba)
 {
 	const struct hisi_sas_hw *hw = hisi_hba->hw;
 	struct device *dev = hisi_hba->dev;
@@ -3796,7 +3796,7 @@ fail:
 	return -ENOMEM;
 }
 
-void hisi_sas_debugfs_bist_init(struct hisi_hba *hisi_hba)
+static void hisi_sas_debugfs_bist_init(struct hisi_hba *hisi_hba)
 {
 	hisi_hba->debugfs_bist_dentry =
 			debugfs_create_dir("bist", hisi_hba->debugfs_dir);
-- 
cgit v1.2.3


From 248a445adfc8c33ffd67cf1f2e336578e34f9e21 Mon Sep 17 00:00:00 2001
From: Himanshu Madhani <hmadhani@marvell.com>
Date: Thu, 12 Sep 2019 11:09:05 -0700
Subject: scsi: qla2xxx: Silence fwdump template message

Print if fwdt template is present or not, only when
ql2xextended_error_logging is enabled.

Link: https://lore.kernel.org/r/20190912180918.6436-2-hmadhani@marvell.com
Signed-off-by: Himanshu Madhani <hmadhani@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_init.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index b6cdf108994c..f6a5d78f93c9 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -3190,7 +3190,7 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *vha)
 
 		for (j = 0; j < 2; j++, fwdt++) {
 			if (!fwdt->template) {
-				ql_log(ql_log_warn, vha, 0x00ba,
+				ql_dbg(ql_dbg_init, vha, 0x00ba,
 				    "-> fwdt%u no template\n", j);
 				continue;
 			}
-- 
cgit v1.2.3


From c3b6a1d397420a0fdd97af2f06abfb78adc370df Mon Sep 17 00:00:00 2001
From: Quinn Tran <qutran@marvell.com>
Date: Thu, 12 Sep 2019 11:09:06 -0700
Subject: scsi: qla2xxx: Fix unbound sleep in fcport delete path.

There are instances, though rare, where a LOGO request cannot be sent out
and the thread in free session done can wait indefinitely. Fix this by
putting an upper bound to sleep.

Link: https://lore.kernel.org/r/20190912180918.6436-3-hmadhani@marvell.com
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Himanshu Madhani <hmadhani@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_target.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 0ffda6171614..b58ecd2d7fb6 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1020,6 +1020,7 @@ void qlt_free_session_done(struct work_struct *work)
 
 	if (logout_started) {
 		bool traced = false;
+		u16 cnt = 0;
 
 		while (!READ_ONCE(sess->logout_completed)) {
 			if (!traced) {
@@ -1029,6 +1030,9 @@ void qlt_free_session_done(struct work_struct *work)
 				traced = true;
 			}
 			msleep(100);
+			cnt++;
+			if (cnt > 200)
+				break;
 		}
 
 		ql_dbg(ql_dbg_disc, vha, 0xf087,
-- 
cgit v1.2.3


From fd5564ba54e0d8a9e3e823d311b764232e09eb5f Mon Sep 17 00:00:00 2001
From: Quinn Tran <qutran@marvell.com>
Date: Thu, 12 Sep 2019 11:09:07 -0700
Subject: scsi: qla2xxx: Fix stale mem access on driver unload

On driver unload, 'remove_one' thread was allowed to advance, while session
cleanup still lag behind.  This patch ensures session deletion will finish
before remove_one can advance.

Link: https://lore.kernel.org/r/20190912180918.6436-4-hmadhani@marvell.com
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Himanshu Madhani <hmadhani@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_os.c     |  1 +
 drivers/scsi/qla2xxx/qla_target.c | 21 ++++++++-------------
 2 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 51154c049385..42980e52fb41 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1118,6 +1118,7 @@ qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha)
 	qla2x00_mark_all_devices_lost(vha, 0);
 
 	wait_event_timeout(vha->fcport_waitQ, test_fcport_count(vha), 10*HZ);
+	flush_workqueue(vha->hw->wq);
 }
 
 /*
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index b58ecd2d7fb6..b5315be00b4d 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -953,7 +953,7 @@ void qlt_free_session_done(struct work_struct *work)
 	struct qla_hw_data *ha = vha->hw;
 	unsigned long flags;
 	bool logout_started = false;
-	scsi_qla_host_t *base_vha;
+	scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
 	struct qlt_plogi_ack_t *own =
 		sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN];
 
@@ -1105,6 +1105,7 @@ void qlt_free_session_done(struct work_struct *work)
 	}
 
 	spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+	sess->free_pending = 0;
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001,
 	    "Unregistration of sess %p %8phC finished fcp_cnt %d\n",
@@ -1113,17 +1114,8 @@ void qlt_free_session_done(struct work_struct *work)
 	if (tgt && (tgt->sess_count == 0))
 		wake_up_all(&tgt->waitQ);
 
-	if (vha->fcport_count == 0)
-		wake_up_all(&vha->fcport_waitQ);
-
-	base_vha = pci_get_drvdata(ha->pdev);
-
-	sess->free_pending = 0;
-
-	if (test_bit(PFLG_DRIVER_REMOVING, &base_vha->pci_flags))
-		return;
-
-	if ((!tgt || !tgt->tgt_stop) && !LOOP_TRANSITION(vha)) {
+	if (!test_bit(PFLG_DRIVER_REMOVING, &base_vha->pci_flags) &&
+	    (!tgt || !tgt->tgt_stop) && !LOOP_TRANSITION(vha)) {
 		switch (vha->host->active_mode) {
 		case MODE_INITIATOR:
 		case MODE_DUAL:
@@ -1136,6 +1128,9 @@ void qlt_free_session_done(struct work_struct *work)
 			break;
 		}
 	}
+
+	if (vha->fcport_count == 0)
+		wake_up_all(&vha->fcport_waitQ);
 }
 
 /* ha->tgt.sess_lock supposed to be held on entry */
@@ -1165,7 +1160,7 @@ void qlt_unreg_sess(struct fc_port *sess)
 	sess->last_login_gen = sess->login_gen;
 
 	INIT_WORK(&sess->free_work, qlt_free_session_done);
-	schedule_work(&sess->free_work);
+	queue_work(sess->vha->hw->wq, &sess->free_work);
 }
 EXPORT_SYMBOL(qlt_unreg_sess);
 
-- 
cgit v1.2.3


From f5187b7d1ac66b61676f896751d3af9fcf8dd592 Mon Sep 17 00:00:00 2001
From: Quinn Tran <qutran@marvell.com>
Date: Thu, 12 Sep 2019 11:09:08 -0700
Subject: scsi: qla2xxx: Optimize NPIV tear down process

In the case of NPIV port is being torn down, this patch will set a flag to
indicate VPORT_DELETE. This would prevent relogin to be triggered.

Link: https://lore.kernel.org/r/20190912180918.6436-5-hmadhani@marvell.com
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Himanshu Madhani <hmadhani@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_attr.c   |  2 ++
 drivers/scsi/qla2xxx/qla_def.h    |  1 +
 drivers/scsi/qla2xxx/qla_gs.c     |  3 ++-
 drivers/scsi/qla2xxx/qla_mid.c    | 32 ++++++++++++++++++++++----------
 drivers/scsi/qla2xxx/qla_os.c     |  7 ++++++-
 drivers/scsi/qla2xxx/qla_target.c |  1 +
 6 files changed, 34 insertions(+), 12 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index e9c449ef515c..8b3015361428 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -2920,6 +2920,8 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)
 	struct qla_hw_data *ha = vha->hw;
 	uint16_t id = vha->vp_idx;
 
+	set_bit(VPORT_DELETE, &vha->dpc_flags);
+
 	while (test_bit(LOOP_RESYNC_ACTIVE, &vha->dpc_flags) ||
 	    test_bit(FCPORT_UPDATE_NEEDED, &vha->dpc_flags))
 		msleep(1000);
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 873a6aef1c5c..fa038568beb6 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -4394,6 +4394,7 @@ typedef struct scsi_qla_host {
 #define IOCB_WORK_ACTIVE	31
 #define SET_ZIO_THRESHOLD_NEEDED 32
 #define ISP_ABORT_TO_ROM	33
+#define VPORT_DELETE		34
 
 	unsigned long	pci_flags;
 #define PFLG_DISCONNECTED	0	/* PCI device removed */
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index dc0e36676313..5298ed10059f 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -3102,7 +3102,8 @@ int qla24xx_post_gpnid_work(struct scsi_qla_host *vha, port_id_t *id)
 {
 	struct qla_work_evt *e;
 
-	if (test_bit(UNLOADING, &vha->dpc_flags))
+	if (test_bit(UNLOADING, &vha->dpc_flags) ||
+	    (vha->vp_idx && test_bit(VPORT_DELETE, &vha->dpc_flags)))
 		return 0;
 
 	e = qla2x00_alloc_work(vha, QLA_EVT_GPNID);
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index 1a9a11ae7285..6afad68e5ba2 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -66,6 +66,7 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha)
 	uint16_t vp_id;
 	struct qla_hw_data *ha = vha->hw;
 	unsigned long flags = 0;
+	u8 i;
 
 	mutex_lock(&ha->vport_lock);
 	/*
@@ -75,8 +76,9 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha)
 	 * ensures no active vp_list traversal while the vport is removed
 	 * from the queue)
 	 */
-	wait_event_timeout(vha->vref_waitq, !atomic_read(&vha->vref_count),
-	    10*HZ);
+	for (i = 0; i < 10 && atomic_read(&vha->vref_count); i++)
+		wait_event_timeout(vha->vref_waitq,
+		    atomic_read(&vha->vref_count), HZ);
 
 	spin_lock_irqsave(&ha->vport_slock, flags);
 	if (atomic_read(&vha->vref_count)) {
@@ -262,6 +264,9 @@ qla2x00_alert_all_vps(struct rsp_que *rsp, uint16_t *mb)
 	spin_lock_irqsave(&ha->vport_slock, flags);
 	list_for_each_entry(vha, &ha->vp_list, list) {
 		if (vha->vp_idx) {
+			if (test_bit(VPORT_DELETE, &vha->dpc_flags))
+				continue;
+
 			atomic_inc(&vha->vref_count);
 			spin_unlock_irqrestore(&ha->vport_slock, flags);
 
@@ -300,6 +305,20 @@ qla2x00_alert_all_vps(struct rsp_que *rsp, uint16_t *mb)
 int
 qla2x00_vp_abort_isp(scsi_qla_host_t *vha)
 {
+	fc_port_t *fcport;
+
+	/*
+	 * To exclusively reset vport, we need to log it out first.
+	 * Note: This control_vp can fail if ISP reset is already
+	 * issued, this is expected, as the vp would be already
+	 * logged out due to ISP reset.
+	 */
+	if (!test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags)) {
+		qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL);
+		list_for_each_entry(fcport, &vha->vp_fcports, list)
+			fcport->logout_on_delete = 0;
+	}
+
 	/*
 	 * Physical port will do most of the abort and recovery work. We can
 	 * just treat it as a loop down
@@ -312,16 +331,9 @@ qla2x00_vp_abort_isp(scsi_qla_host_t *vha)
 			atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
 	}
 
-	/*
-	 * To exclusively reset vport, we need to log it out first.  Note: this
-	 * control_vp can fail if ISP reset is already issued, this is
-	 * expected, as the vp would be already logged out due to ISP reset.
-	 */
-	if (!test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags))
-		qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL);
-
 	ql_dbg(ql_dbg_taskm, vha, 0x801d,
 	    "Scheduling enable of Vport %d.\n", vha->vp_idx);
+
 	return qla24xx_enable_vp(vha);
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 42980e52fb41..5eda86ff6606 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1115,9 +1115,14 @@ static inline int test_fcport_count(scsi_qla_host_t *vha)
 void
 qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha)
 {
+	u8 i;
+
 	qla2x00_mark_all_devices_lost(vha, 0);
 
-	wait_event_timeout(vha->fcport_waitQ, test_fcport_count(vha), 10*HZ);
+	for (i = 0; i < 10; i++)
+		wait_event_timeout(vha->fcport_waitQ, test_fcport_count(vha),
+		    HZ);
+
 	flush_workqueue(vha->hw->wq);
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index b5315be00b4d..a06e56224a55 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1115,6 +1115,7 @@ void qlt_free_session_done(struct work_struct *work)
 		wake_up_all(&tgt->waitQ);
 
 	if (!test_bit(PFLG_DRIVER_REMOVING, &base_vha->pci_flags) &&
+	    !(vha->vp_idx && test_bit(VPORT_DELETE, &vha->dpc_flags)) &&
 	    (!tgt || !tgt->tgt_stop) && !LOOP_TRANSITION(vha)) {
 		switch (vha->host->active_mode) {
 		case MODE_INITIATOR:
-- 
cgit v1.2.3


From 7f2a398d59d658818f3d219645164676fbbc88e8 Mon Sep 17 00:00:00 2001
From: Quinn Tran <qutran@marvell.com>
Date: Thu, 12 Sep 2019 11:09:09 -0700
Subject: scsi: qla2xxx: Fix N2N link reset

Fix stalled link recovery for N2N with FC-NVMe connection.

Link: https://lore.kernel.org/r/20190912180918.6436-6-hmadhani@marvell.com
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Himanshu Madhani <hmadhani@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_def.h  |   3 +-
 drivers/scsi/qla2xxx/qla_init.c | 107 +++++++++++++++++++++++++++++-----------
 drivers/scsi/qla2xxx/qla_mbx.c  |  23 +++++++--
 drivers/scsi/qla2xxx/qla_os.c   |   4 ++
 4 files changed, 103 insertions(+), 34 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index fa038568beb6..6ffa9877c28b 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2396,6 +2396,7 @@ typedef struct fc_port {
 	unsigned int query:1;
 	unsigned int id_changed:1;
 	unsigned int scan_needed:1;
+	unsigned int n2n_flag:1;
 
 	struct completion nvme_del_done;
 	uint32_t nvme_prli_service_param;
@@ -2446,7 +2447,6 @@ typedef struct fc_port {
 	uint8_t fc4_type;
 	uint8_t	fc4f_nvme;
 	uint8_t scan_state;
-	uint8_t n2n_flag;
 
 	unsigned long last_queue_full;
 	unsigned long last_ramp_up;
@@ -3036,6 +3036,7 @@ enum scan_flags_t {
 enum fc4type_t {
 	FS_FC4TYPE_FCP	= BIT_0,
 	FS_FC4TYPE_NVME	= BIT_1,
+	FS_FCP_IS_N2N = BIT_7,
 };
 
 struct fab_scan_rp {
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index f6a5d78f93c9..67f522a8a9d4 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -746,12 +746,15 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 			break;
 		default:
 			if ((id.b24 != fcport->d_id.b24 &&
-			    fcport->d_id.b24) ||
+			    fcport->d_id.b24 &&
+			    fcport->loop_id != FC_NO_LOOP_ID) ||
 			    (fcport->loop_id != FC_NO_LOOP_ID &&
 				fcport->loop_id != loop_id)) {
 				ql_dbg(ql_dbg_disc, vha, 0x20e3,
 				    "%s %d %8phC post del sess\n",
 				    __func__, __LINE__, fcport->port_name);
+				if (fcport->n2n_flag)
+					fcport->d_id.b24 = 0;
 				qlt_schedule_sess_for_deletion(fcport);
 				return;
 			}
@@ -759,6 +762,8 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 		}
 
 		fcport->loop_id = loop_id;
+		if (fcport->n2n_flag)
+			fcport->d_id.b24 = id.b24;
 
 		wwn = wwn_to_u64(fcport->port_name);
 		qlt_find_sess_invalidate_other(vha, wwn,
@@ -972,7 +977,7 @@ static void qla24xx_async_gnl_sp_done(srb_t *sp, int res)
 		wwn = wwn_to_u64(e->port_name);
 
 		ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x20e8,
-		    "%s %8phC %02x:%02x:%02x state %d/%d lid %x \n",
+		    "%s %8phC %02x:%02x:%02x CLS %x/%x lid %x \n",
 		    __func__, (void *)&wwn, e->port_id[2], e->port_id[1],
 		    e->port_id[0], e->current_login_state, e->last_login_state,
 		    (loop_id & 0x7fff));
@@ -1499,7 +1504,8 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 	     (fcport->fw_login_state == DSC_LS_PRLI_PEND)))
 		return 0;
 
-	if (fcport->fw_login_state == DSC_LS_PLOGI_COMP) {
+	if (fcport->fw_login_state == DSC_LS_PLOGI_COMP &&
+	    !N2N_TOPO(vha->hw)) {
 		if (time_before_eq(jiffies, fcport->plogi_nack_done_deadline)) {
 			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
 			return 0;
@@ -1570,8 +1576,9 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 				qla24xx_post_gpdb_work(vha, fcport, 0);
 			}  else {
 				ql_dbg(ql_dbg_disc, vha, 0x2118,
-				    "%s %d %8phC post NVMe PRLI\n",
-				    __func__, __LINE__, fcport->port_name);
+				    "%s %d %8phC post %s PRLI\n",
+				    __func__, __LINE__, fcport->port_name,
+				    fcport->fc4f_nvme ? "NVME" : "FC");
 				qla24xx_post_prli_work(vha, fcport);
 			}
 			break;
@@ -1853,17 +1860,38 @@ qla24xx_handle_prli_done_event(struct scsi_qla_host *vha, struct event_arg *ea)
 			break;
 		}
 
-		if (ea->fcport->n2n_flag) {
+		if (ea->fcport->fc4f_nvme) {
 			ql_dbg(ql_dbg_disc, vha, 0x2118,
 				"%s %d %8phC post fc4 prli\n",
 				__func__, __LINE__, ea->fcport->port_name);
 			ea->fcport->fc4f_nvme = 0;
-			ea->fcport->n2n_flag = 0;
 			qla24xx_post_prli_work(vha, ea->fcport);
+			return;
+		}
+
+		/* at this point both PRLI NVME & PRLI FCP failed */
+		if (N2N_TOPO(vha->hw)) {
+			if (ea->fcport->n2n_link_reset_cnt < 3) {
+				ea->fcport->n2n_link_reset_cnt++;
+				/*
+				 * remote port is not sending Plogi. Reset
+				 * link to kick start his state machine
+				 */
+				set_bit(N2N_LINK_RESET, &vha->dpc_flags);
+			} else {
+				ql_log(ql_log_warn, vha, 0x2119,
+				    "%s %d %8phC Unable to reconnect\n",
+				    __func__, __LINE__, ea->fcport->port_name);
+			}
+		} else {
+			/*
+			 * switch connect. login failed. Take connection
+			 * down and allow relogin to retrigger
+			 */
+			ea->fcport->flags &= ~FCF_ASYNC_SENT;
+			ea->fcport->keep_nport_handle = 0;
+			qlt_schedule_sess_for_deletion(ea->fcport);
 		}
-		ql_dbg(ql_dbg_disc, vha, 0x2119,
-		    "%s %d %8phC unhandle event of %x\n",
-		    __func__, __LINE__, ea->fcport->port_name, ea->data[0]);
 		break;
 	}
 }
@@ -5000,28 +5028,47 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 	unsigned long flags;
 
 	/* Inititae N2N login. */
-	if (test_and_clear_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags)) {
-		/* borrowing */
-		u32 *bp, i, sz;
-
-		memset(ha->init_cb, 0, ha->init_cb_size);
-		sz = min_t(int, sizeof(struct els_plogi_payload),
-		    ha->init_cb_size);
-		rval = qla24xx_get_port_login_templ(vha, ha->init_cb_dma,
-		    (void *)ha->init_cb, sz);
-		if (rval == QLA_SUCCESS) {
-			bp = (uint32_t *)ha->init_cb;
-			for (i = 0; i < sz/4 ; i++, bp++)
-				*bp = cpu_to_be32(*bp);
+	if (N2N_TOPO(ha)) {
+		if (test_and_clear_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags)) {
+			/* borrowing */
+			u32 *bp, i, sz;
+
+			memset(ha->init_cb, 0, ha->init_cb_size);
+			sz = min_t(int, sizeof(struct els_plogi_payload),
+			    ha->init_cb_size);
+			rval = qla24xx_get_port_login_templ(vha,
+			    ha->init_cb_dma, (void *)ha->init_cb, sz);
+			if (rval == QLA_SUCCESS) {
+				bp = (uint32_t *)ha->init_cb;
+				for (i = 0; i < sz/4 ; i++, bp++)
+					*bp = cpu_to_be32(*bp);
 
-			memcpy(&ha->plogi_els_payld.data, (void *)ha->init_cb,
-			    sizeof(ha->plogi_els_payld.data));
-			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-		} else {
-			ql_dbg(ql_dbg_init, vha, 0x00d1,
-			    "PLOGI ELS param read fail.\n");
+				memcpy(&ha->plogi_els_payld.data,
+				    (void *)ha->init_cb,
+				    sizeof(ha->plogi_els_payld.data));
+				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+			} else {
+				ql_dbg(ql_dbg_init, vha, 0x00d1,
+				    "PLOGI ELS param read fail.\n");
+				goto skip_login;
+			}
+		}
+
+		list_for_each_entry(fcport, &vha->vp_fcports, list) {
+			if (fcport->n2n_flag) {
+				qla24xx_fcport_handle_login(vha, fcport);
+				return QLA_SUCCESS;
+			}
+		}
+skip_login:
+		spin_lock_irqsave(&vha->work_lock, flags);
+		vha->scan.scan_retry++;
+		spin_unlock_irqrestore(&vha->work_lock, flags);
+
+		if (vha->scan.scan_retry < MAX_SCAN_RETRIES) {
+			set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
+			set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
 		}
-		return QLA_SUCCESS;
 	}
 
 	found_devs = 0;
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 4c858e2d0ea8..6d6e10812b42 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -2249,7 +2249,7 @@ qla2x00_lip_reset(scsi_qla_host_t *vha)
 	mbx_cmd_t mc;
 	mbx_cmd_t *mcp = &mc;
 
-	ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x105a,
+	ql_dbg(ql_dbg_disc, vha, 0x105a,
 	    "Entered %s.\n", __func__);
 
 	if (IS_CNA_CAPABLE(vha->hw)) {
@@ -3883,14 +3883,23 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 		case TOPO_N2N:
 			ha->current_topology = ISP_CFG_N;
 			spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+			list_for_each_entry(fcport, &vha->vp_fcports, list) {
+				fcport->scan_state = QLA_FCPORT_SCAN;
+				fcport->n2n_flag = 0;
+			}
+
 			fcport = qla2x00_find_fcport_by_wwpn(vha,
 			    rptid_entry->u.f1.port_name, 1);
 			spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 
 			if (fcport) {
 				fcport->plogi_nack_done_deadline = jiffies + HZ;
-				fcport->dm_login_expire = jiffies + 3*HZ;
+				fcport->dm_login_expire = jiffies + 2*HZ;
 				fcport->scan_state = QLA_FCPORT_FOUND;
+				fcport->n2n_flag = 1;
+				if (vha->flags.nvme_enabled)
+					fcport->fc4f_nvme = 1;
+
 				switch (fcport->disc_state) {
 				case DSC_DELETED:
 					set_bit(RELOGIN_NEEDED,
@@ -3924,7 +3933,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 				    rptid_entry->u.f1.port_name,
 				    rptid_entry->u.f1.node_name,
 				    NULL,
-				    FC4_TYPE_UNKNOWN);
+				    FS_FCP_IS_N2N);
 			}
 
 			/* if our portname is higher then initiate N2N login */
@@ -4023,6 +4032,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 
 		list_for_each_entry(fcport, &vha->vp_fcports, list) {
 			fcport->scan_state = QLA_FCPORT_SCAN;
+			fcport->n2n_flag = 0;
 		}
 
 		fcport = qla2x00_find_fcport_by_wwpn(vha,
@@ -4032,6 +4042,13 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 			fcport->login_retry = vha->hw->login_retry_count;
 			fcport->plogi_nack_done_deadline = jiffies + HZ;
 			fcport->scan_state = QLA_FCPORT_FOUND;
+			fcport->n2n_flag = 1;
+			fcport->d_id.b.domain =
+				rptid_entry->u.f2.remote_nport_id[2];
+			fcport->d_id.b.area =
+				rptid_entry->u.f2.remote_nport_id[1];
+			fcport->d_id.b.al_pa =
+				rptid_entry->u.f2.remote_nport_id[0];
 		}
 	}
 }
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 5eda86ff6606..8411dd5acd43 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -5033,6 +5033,10 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 
 			memcpy(fcport->port_name, e->u.new_sess.port_name,
 			    WWN_SIZE);
+
+			if (e->u.new_sess.fc4_type & FS_FCP_IS_N2N)
+				fcport->n2n_flag = 1;
+
 		} else {
 			ql_dbg(ql_dbg_disc, vha, 0xffff,
 				   "%s %8phC mem alloc fail.\n",
-- 
cgit v1.2.3


From f3f1938bb673b1b5ad182c4608f5f8a24921eea3 Mon Sep 17 00:00:00 2001
From: Quinn Tran <qutran@marvell.com>
Date: Thu, 12 Sep 2019 11:09:10 -0700
Subject: scsi: qla2xxx: Fix N2N link up fail

During link up/bounce, qla driver would do command flush as part of
cleanup.  In this case, the flush can intefere with FW state.  This patch
allows FW to be in control of link up.

Link: https://lore.kernel.org/r/20190912180918.6436-7-hmadhani@marvell.com
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Himanshu Madhani <hmadhani@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_mbx.c | 2 ++
 drivers/scsi/qla2xxx/qla_os.c  | 6 ++----
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 6d6e10812b42..1cc6913f76c4 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -3897,6 +3897,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 				fcport->dm_login_expire = jiffies + 2*HZ;
 				fcport->scan_state = QLA_FCPORT_FOUND;
 				fcport->n2n_flag = 1;
+				fcport->keep_nport_handle = 1;
 				if (vha->flags.nvme_enabled)
 					fcport->fc4f_nvme = 1;
 
@@ -4042,6 +4043,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 			fcport->login_retry = vha->hw->login_retry_count;
 			fcport->plogi_nack_done_deadline = jiffies + HZ;
 			fcport->scan_state = QLA_FCPORT_FOUND;
+			fcport->keep_nport_handle = 1;
 			fcport->n2n_flag = 1;
 			fcport->d_id.b.domain =
 				rptid_entry->u.f2.remote_nport_id[2];
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 8411dd5acd43..ee47de9fbc05 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -5135,11 +5135,9 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 			if (dfcp)
 				qlt_schedule_sess_for_deletion(tfcp);
 
-
-			if (N2N_TOPO(vha->hw))
-				fcport->flags &= ~FCF_FABRIC_DEVICE;
-
 			if (N2N_TOPO(vha->hw)) {
+				fcport->flags &= ~FCF_FABRIC_DEVICE;
+				fcport->keep_nport_handle = 1;
 				if (vha->flags.nvme_enabled) {
 					fcport->fc4f_nvme = 1;
 					fcport->n2n_flag = 1;
-- 
cgit v1.2.3


From 0aabb6b699f72dca96988d3f428e222f932dc889 Mon Sep 17 00:00:00 2001
From: Quinn Tran <qutran@marvell.com>
Date: Thu, 12 Sep 2019 11:09:11 -0700
Subject: scsi: qla2xxx: Fix Nport ID display value

For N2N, the NPort ID is assigned by driver in the PLOGI ELS.  According to
FW Spec the byte order for SID is not the same as DID.

Link: https://lore.kernel.org/r/20190912180918.6436-8-hmadhani@marvell.com
Reviewed-by: Roman Bolshakov <r.bolshakov@yadro.com>
Tested-by: Roman Bolshakov <r.bolshakov@yadro.com>
Signed-off-by: Quinn Tran <qutran@marvell.com>
Signed-off-by: Himanshu Madhani <hmadhani@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_iocb.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index e92e52aa6e9b..518eb954cf42 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2656,9 +2656,10 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 	els_iocb->port_id[0] = sp->fcport->d_id.b.al_pa;
 	els_iocb->port_id[1] = sp->fcport->d_id.b.area;
 	els_iocb->port_id[2] = sp->fcport->d_id.b.domain;
-	els_iocb->s_id[0] = vha->d_id.b.al_pa;
-	els_iocb->s_id[1] = vha->d_id.b.area;
-	els_iocb->s_id[2] = vha->d_id.b.domain;
+	/* For SID the byte order is different than DID */
+	els_iocb->s_id[1] = vha->d_id.b.al_pa;
+	els_iocb->s_id[2] = vha->d_id.b.area;
+	els_iocb->s_id[0] = vha->d_id.b.domain;
 
 	if (elsio->u.els_logo.els_cmd == ELS_DCMD_PLOGI) {
 		els_iocb->control_flags = 0;
-- 
cgit v1.2.3


From 5028851cdfdf78dc22eacbc44a0ab0b3f599ee4a Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 20 Sep 2019 13:18:21 +0100
Subject: drm/i915: Mark contents as dirty on a write fault
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since dropping the set-to-gtt-domain in commit a679f58d0510 ("drm/i915:
Flush pages on acquisition"), we no longer mark the contents as dirty on
a write fault. This has the issue of us then not marking the pages as
dirty on releasing the buffer, which means the contents are not written
out to the swap device (should we ever pick that buffer as a victim).
Notably, this is visible in the dumb buffer interface used for cursors.
Having updated the cursor contents via mmap, and swapped away, if the
shrinker should evict the old cursor, upon next reuse, the cursor would
be invisible.

E.g. echo 80 > /proc/sys/kernel/sysrq ; echo f > /proc/sysrq-trigger

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111541
Fixes: a679f58d0510 ("drm/i915: Flush pages on acquisition")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.2+
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920121821.7223-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_mman.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 1748e63156a2..860b751c51f1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -319,7 +319,11 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 		intel_wakeref_auto(&i915->ggtt.userfault_wakeref,
 				   msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND));
 
-	i915_vma_set_ggtt_write(vma);
+	if (write) {
+		GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
+		i915_vma_set_ggtt_write(vma);
+		obj->mm.dirty = true;
+	}
 
 err_fence:
 	i915_vma_unpin_fence(vma);
-- 
cgit v1.2.3


From 1b74d46782d0615dace4729c22d1862a0355b124 Mon Sep 17 00:00:00 2001
From: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Date: Fri, 20 Sep 2019 11:37:54 +0300
Subject: drm/i915: Add TigerLake bandwidth checking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Added bandwidth calculation algorithm and checks,
similar way as it was done for ICL, some constants
were corrected according to BSpec 53998.

v2: Start using same icl_get_bw_info function to avoid
    code duplication. Moved mpagesize to memory info
    related structure as it is now dependent on memory type.
    Fixed qi.t_bl field assignment.

v3: Removed mpagesize as unused. Duplicate code and redundant blankline
    fixed.

v4: Changed ordering of IS_GEN checks as agreed. Minor commit
    message fixes.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111600
Reviewed-by: James Ausmus <james.ausmus@intel.com>
Signed-off-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920083754.5920-1-stanislav.lisovskiy@intel.com
---
 drivers/gpu/drm/i915/display/intel_bw.c | 26 ++++++++++++++++++--------
 1 file changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index 688858ebe4d0..cd58e47ab7b2 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -56,7 +56,10 @@ static int icl_pcode_read_mem_global_info(struct drm_i915_private *dev_priv,
 	qi->num_channels = (val & 0xf0) >> 4;
 	qi->num_points = (val & 0xf00) >> 8;
 
-	qi->t_bl = qi->dram_type == INTEL_DRAM_DDR4 ? 4 : 8;
+	if (IS_GEN(dev_priv, 12))
+		qi->t_bl = qi->dram_type == INTEL_DRAM_DDR4 ? 4 : 16;
+	else if (IS_GEN(dev_priv, 11))
+		qi->t_bl = qi->dram_type == INTEL_DRAM_DDR4 ? 4 : 8;
 
 	return 0;
 }
@@ -132,20 +135,25 @@ static int icl_sagv_max_dclk(const struct intel_qgv_info *qi)
 }
 
 struct intel_sa_info {
-	u8 deburst, mpagesize, deprogbwlimit, displayrtids;
+	u16 displayrtids;
+	u8 deburst, deprogbwlimit;
 };
 
 static const struct intel_sa_info icl_sa_info = {
 	.deburst = 8,
-	.mpagesize = 16,
 	.deprogbwlimit = 25, /* GB/s */
 	.displayrtids = 128,
 };
 
-static int icl_get_bw_info(struct drm_i915_private *dev_priv)
+static const struct intel_sa_info tgl_sa_info = {
+	.deburst = 16,
+	.deprogbwlimit = 34, /* GB/s */
+	.displayrtids = 256,
+};
+
+static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel_sa_info *sa)
 {
 	struct intel_qgv_info qi = {};
-	const struct intel_sa_info *sa = &icl_sa_info;
 	bool is_y_tile = true; /* assume y tile may be used */
 	int num_channels;
 	int deinterleave;
@@ -233,14 +241,16 @@ static unsigned int icl_max_bw(struct drm_i915_private *dev_priv,
 
 void intel_bw_init_hw(struct drm_i915_private *dev_priv)
 {
-	if (IS_GEN(dev_priv, 11))
-		icl_get_bw_info(dev_priv);
+	if (IS_GEN(dev_priv, 12))
+		icl_get_bw_info(dev_priv, &tgl_sa_info);
+	else if (IS_GEN(dev_priv, 11))
+		icl_get_bw_info(dev_priv, &icl_sa_info);
 }
 
 static unsigned int intel_max_data_rate(struct drm_i915_private *dev_priv,
 					int num_planes)
 {
-	if (IS_GEN(dev_priv, 11))
+	if (INTEL_GEN(dev_priv) >= 11)
 		/*
 		 * FIXME with SAGV disabled maybe we can assume
 		 * point 1 will always be used? Seems to match
-- 
cgit v1.2.3


From 4ef5d76b453908f21341e661a9b6f96862f6f589 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 24 Sep 2019 09:24:28 -0700
Subject: ARM: dts: Fix gpio0 flags for am335x-icev2

The ti,no-idle-on-init and ti,no-reset-on-init flags need to be at
the interconnect target module level for the modules that have it
defined. Otherwise we get the following warnings:

dts flag should be at module level for ti,no-idle-on-init
dts flag should be at module level for ti,no-reset-on-init

Fixes: 87fc89ced3a7 ("ARM: dts: am335x: Move l4 child devices to probe them with ti-sysc")
Cc: Lokesh Vutla <lokeshvutla@ti.com>
Reported-by: Suman Anna <s-anna@ti.com>
Reviewed-by: Lokesh Vutla <lokeshvutla@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/boot/dts/am335x-icev2.dts | 2 +-
 arch/arm/boot/dts/am33xx-l4.dtsi   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/boot/dts/am335x-icev2.dts b/arch/arm/boot/dts/am335x-icev2.dts
index 18f70b35da4c..204bccfcc110 100644
--- a/arch/arm/boot/dts/am335x-icev2.dts
+++ b/arch/arm/boot/dts/am335x-icev2.dts
@@ -432,7 +432,7 @@
 	pinctrl-0 = <&mmc0_pins_default>;
 };
 
-&gpio0 {
+&gpio0_target {
 	/* Do not idle the GPIO used for holding the VTT regulator */
 	ti,no-reset-on-init;
 	ti,no-idle-on-init;
diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi
index 46849d6ecb3e..1515f4f91499 100644
--- a/arch/arm/boot/dts/am33xx-l4.dtsi
+++ b/arch/arm/boot/dts/am33xx-l4.dtsi
@@ -127,7 +127,7 @@
 			ranges = <0x0 0x5000 0x1000>;
 		};
 
-		target-module@7000 {			/* 0x44e07000, ap 14 20.0 */
+		gpio0_target: target-module@7000 {	/* 0x44e07000, ap 14 20.0 */
 			compatible = "ti,sysc-omap2", "ti,sysc";
 			ti,hwmods = "gpio1";
 			reg = <0x7000 0x4>,
-- 
cgit v1.2.3


From 7dc56af5260e958e36a08b2e0822029ddf765770 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 24 Sep 2019 15:59:50 +0100
Subject: drm/i915/selftests: Verify the LRC register layout between init and
 HW

Before we submit the first context to HW, we need to construct a valid
image of the register state. This layout is defined by the HW and should
match the layout generated by HW when it saves the context image.
Asserting that this should be equivalent should help avoid any undefined
behaviour and verify that we haven't missed anything important!

Of course, having insisted that the initial register state within the
LRC should match that returned by HW, we need to ensure that it does.

v2: Drop the RELATIVE_MMIO flag from gen11, we ignore it for
constructing the lrc image.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190924145950.3011-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c        |   2 +-
 drivers/gpu/drm/i915/gt/intel_lrc.c                | 667 ++++++++++++++-------
 drivers/gpu/drm/i915/gt/intel_lrc_reg.h            |  62 +-
 drivers/gpu/drm/i915/gt/selftest_lrc.c             | 142 +++++
 drivers/gpu/drm/i915/i915_perf.c                   |  35 +-
 drivers/gpu/drm/i915/i915_perf.h                   |   5 +-
 .../gpu/drm/i915/selftests/i915_live_selftests.h   |   1 +
 7 files changed, 648 insertions(+), 266 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 4a34c4f62065..f7ba0935ed67 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1115,7 +1115,7 @@ static int gen8_emit_rpcs_config(struct i915_request *rq,
 
 	offset = i915_ggtt_offset(ce->state) +
 		 LRC_STATE_PN * PAGE_SIZE +
-		 (CTX_R_PWR_CLK_STATE + 1) * 4;
+		 CTX_R_PWR_CLK_STATE * 4;
 
 	*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
 	*cs++ = lower_32_bits(offset);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 6cfdc0f9f2b9..caac091b3eb9 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -230,9 +230,10 @@ static int __execlists_context_alloc(struct intel_context *ce,
 				     struct intel_engine_cs *engine);
 
 static void execlists_init_reg_state(u32 *reg_state,
-				     struct intel_context *ce,
-				     struct intel_engine_cs *engine,
-				     struct intel_ring *ring);
+				     const struct intel_context *ce,
+				     const struct intel_engine_cs *engine,
+				     const struct intel_ring *ring,
+				     bool close);
 
 static void mark_eio(struct i915_request *rq)
 {
@@ -471,6 +472,411 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 	return desc;
 }
 
+static u32 *set_offsets(u32 *regs,
+			const u8 *data,
+			const struct intel_engine_cs *engine)
+#define NOP(x) (BIT(7) | (x))
+#define LRI(count, flags) ((flags) << 6 | (count))
+#define POSTED BIT(0)
+#define REG(x) (((x) >> 2) | BUILD_BUG_ON_ZERO(x >= 0x200))
+#define REG16(x) \
+	(((x) >> 9) | BIT(7) | BUILD_BUG_ON_ZERO(x >= 0x10000)), \
+	(((x) >> 2) & 0x7f)
+#define END() 0
+{
+	const u32 base = engine->mmio_base;
+
+	while (*data) {
+		u8 count, flags;
+
+		if (*data & BIT(7)) { /* skip */
+			regs += *data++ & ~BIT(7);
+			continue;
+		}
+
+		count = *data & 0x3f;
+		flags = *data >> 6;
+		data++;
+
+		*regs = MI_LOAD_REGISTER_IMM(count);
+		if (flags & POSTED)
+			*regs |= MI_LRI_FORCE_POSTED;
+		if (INTEL_GEN(engine->i915) >= 11)
+			*regs |= MI_LRI_CS_MMIO;
+		regs++;
+
+		GEM_BUG_ON(!count);
+		do {
+			u32 offset = 0;
+			u8 v;
+
+			do {
+				v = *data++;
+				offset <<= 7;
+				offset |= v & ~BIT(7);
+			} while (v & BIT(7));
+
+			*regs = base + (offset << 2);
+			regs += 2;
+		} while (--count);
+	}
+
+	return regs;
+}
+
+static const u8 gen8_xcs_offsets[] = {
+	NOP(1),
+	LRI(11, 0),
+	REG16(0x244),
+	REG(0x034),
+	REG(0x030),
+	REG(0x038),
+	REG(0x03c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x11c),
+	REG(0x114),
+	REG(0x118),
+
+	NOP(9),
+	LRI(9, 0),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	NOP(13),
+	LRI(2, 0),
+	REG16(0x200),
+	REG(0x028),
+
+	END(),
+};
+
+static const u8 gen9_xcs_offsets[] = {
+	NOP(1),
+	LRI(14, POSTED),
+	REG16(0x244),
+	REG(0x034),
+	REG(0x030),
+	REG(0x038),
+	REG(0x03c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x11c),
+	REG(0x114),
+	REG(0x118),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+
+	NOP(3),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	NOP(13),
+	LRI(1, POSTED),
+	REG16(0x200),
+
+	NOP(13),
+	LRI(44, POSTED),
+	REG(0x028),
+	REG(0x09c),
+	REG(0x0c0),
+	REG(0x178),
+	REG(0x17c),
+	REG16(0x358),
+	REG(0x170),
+	REG(0x150),
+	REG(0x154),
+	REG(0x158),
+	REG16(0x41c),
+	REG16(0x600),
+	REG16(0x604),
+	REG16(0x608),
+	REG16(0x60c),
+	REG16(0x610),
+	REG16(0x614),
+	REG16(0x618),
+	REG16(0x61c),
+	REG16(0x620),
+	REG16(0x624),
+	REG16(0x628),
+	REG16(0x62c),
+	REG16(0x630),
+	REG16(0x634),
+	REG16(0x638),
+	REG16(0x63c),
+	REG16(0x640),
+	REG16(0x644),
+	REG16(0x648),
+	REG16(0x64c),
+	REG16(0x650),
+	REG16(0x654),
+	REG16(0x658),
+	REG16(0x65c),
+	REG16(0x660),
+	REG16(0x664),
+	REG16(0x668),
+	REG16(0x66c),
+	REG16(0x670),
+	REG16(0x674),
+	REG16(0x678),
+	REG16(0x67c),
+	REG(0x068),
+
+	END(),
+};
+
+static const u8 gen12_xcs_offsets[] = {
+	NOP(1),
+	LRI(13, POSTED),
+	REG16(0x244),
+	REG(0x034),
+	REG(0x030),
+	REG(0x038),
+	REG(0x03c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+	REG(0x180),
+	REG16(0x2b4),
+
+	NOP(5),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	NOP(13),
+	LRI(2, POSTED),
+	REG16(0x200),
+	REG16(0x204),
+
+	NOP(11),
+	LRI(50, POSTED),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG16(0x588),
+	REG(0x028),
+	REG(0x09c),
+	REG(0x0c0),
+	REG(0x178),
+	REG(0x17c),
+	REG16(0x358),
+	REG(0x170),
+	REG(0x150),
+	REG(0x154),
+	REG(0x158),
+	REG16(0x41c),
+	REG16(0x600),
+	REG16(0x604),
+	REG16(0x608),
+	REG16(0x60c),
+	REG16(0x610),
+	REG16(0x614),
+	REG16(0x618),
+	REG16(0x61c),
+	REG16(0x620),
+	REG16(0x624),
+	REG16(0x628),
+	REG16(0x62c),
+	REG16(0x630),
+	REG16(0x634),
+	REG16(0x638),
+	REG16(0x63c),
+	REG16(0x640),
+	REG16(0x644),
+	REG16(0x648),
+	REG16(0x64c),
+	REG16(0x650),
+	REG16(0x654),
+	REG16(0x658),
+	REG16(0x65c),
+	REG16(0x660),
+	REG16(0x664),
+	REG16(0x668),
+	REG16(0x66c),
+	REG16(0x670),
+	REG16(0x674),
+	REG16(0x678),
+	REG16(0x67c),
+	REG(0x068),
+
+	END(),
+};
+
+static const u8 gen8_rcs_offsets[] = {
+	NOP(1),
+	LRI(14, POSTED),
+	REG16(0x244),
+	REG(0x034),
+	REG(0x030),
+	REG(0x038),
+	REG(0x03c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x11c),
+	REG(0x114),
+	REG(0x118),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+
+	NOP(3),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	NOP(13),
+	LRI(1, 0),
+	REG(0x0c8),
+
+	END(),
+};
+
+static const u8 gen11_rcs_offsets[] = {
+	NOP(1),
+	LRI(15, POSTED),
+	REG16(0x244),
+	REG(0x034),
+	REG(0x030),
+	REG(0x038),
+	REG(0x03c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x11c),
+	REG(0x114),
+	REG(0x118),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+	REG(0x180),
+
+	NOP(1),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	LRI(1, POSTED),
+	REG(0x1b0),
+
+	NOP(10),
+	LRI(1, 0),
+	REG(0x0c8),
+
+	END(),
+};
+
+static const u8 gen12_rcs_offsets[] = {
+	NOP(1),
+	LRI(13, POSTED),
+	REG16(0x244),
+	REG(0x034),
+	REG(0x030),
+	REG(0x038),
+	REG(0x03c),
+	REG(0x168),
+	REG(0x140),
+	REG(0x110),
+	REG(0x1c0),
+	REG(0x1c4),
+	REG(0x1c8),
+	REG(0x180),
+	REG16(0x2b4),
+
+	NOP(5),
+	LRI(9, POSTED),
+	REG16(0x3a8),
+	REG16(0x28c),
+	REG16(0x288),
+	REG16(0x284),
+	REG16(0x280),
+	REG16(0x27c),
+	REG16(0x278),
+	REG16(0x274),
+	REG16(0x270),
+
+	LRI(3, POSTED),
+	REG(0x1b0),
+	REG16(0x5a8),
+	REG16(0x5ac),
+
+	NOP(6),
+	LRI(1, 0),
+	REG(0x0c8),
+
+	END(),
+};
+
+#undef END
+#undef REG16
+#undef REG
+#undef LRI
+#undef NOP
+
+static const u8 *reg_offsets(const struct intel_engine_cs *engine)
+{
+	if (engine->class == RENDER_CLASS) {
+		if (INTEL_GEN(engine->i915) >= 12)
+			return gen12_rcs_offsets;
+		else if (INTEL_GEN(engine->i915) >= 11)
+			return gen11_rcs_offsets;
+		else
+			return gen8_rcs_offsets;
+	} else {
+		if (INTEL_GEN(engine->i915) >= 12)
+			return gen12_xcs_offsets;
+		else if (INTEL_GEN(engine->i915) >= 9)
+			return gen9_xcs_offsets;
+		else
+			return gen8_xcs_offsets;
+	}
+}
+
 static void unwind_wa_tail(struct i915_request *rq)
 {
 	rq->tail = intel_ring_wrap(rq->ring, rq->wa_tail - WA_TAIL_BYTES);
@@ -654,7 +1060,7 @@ static u64 execlists_update_context(const struct i915_request *rq)
 	struct intel_context *ce = rq->hw_context;
 	u64 desc;
 
-	ce->lrc_reg_state[CTX_RING_TAIL + 1] =
+	ce->lrc_reg_state[CTX_RING_TAIL] =
 		intel_ring_set_tail(rq->ring, rq->tail);
 
 	/*
@@ -826,54 +1232,7 @@ static bool can_merge_rq(const struct i915_request *prev,
 static void virtual_update_register_offsets(u32 *regs,
 					    struct intel_engine_cs *engine)
 {
-	u32 base = engine->mmio_base;
-
-	/* Refactor so that we only have one place that knows all the offsets! */
-	GEM_WARN_ON(INTEL_GEN(engine->i915) >= 12);
-
-	/* Must match execlists_init_reg_state()! */
-
-	/* Common part */
-	regs[CTX_CONTEXT_CONTROL] =
-		i915_mmio_reg_offset(RING_CONTEXT_CONTROL(base));
-	regs[CTX_RING_HEAD] = i915_mmio_reg_offset(RING_HEAD(base));
-	regs[CTX_RING_TAIL] = i915_mmio_reg_offset(RING_TAIL(base));
-	regs[CTX_RING_BUFFER_START] = i915_mmio_reg_offset(RING_START(base));
-	regs[CTX_RING_BUFFER_CONTROL] = i915_mmio_reg_offset(RING_CTL(base));
-
-	regs[CTX_BB_HEAD_U] = i915_mmio_reg_offset(RING_BBADDR_UDW(base));
-	regs[CTX_BB_HEAD_L] = i915_mmio_reg_offset(RING_BBADDR(base));
-	regs[CTX_BB_STATE] = i915_mmio_reg_offset(RING_BBSTATE(base));
-
-	regs[CTX_SECOND_BB_HEAD_U] =
-		i915_mmio_reg_offset(RING_SBBADDR_UDW(base));
-	regs[CTX_SECOND_BB_HEAD_L] = i915_mmio_reg_offset(RING_SBBADDR(base));
-	regs[CTX_SECOND_BB_STATE] = i915_mmio_reg_offset(RING_SBBSTATE(base));
-
-	/* PPGTT part */
-	regs[CTX_CTX_TIMESTAMP] =
-		i915_mmio_reg_offset(RING_CTX_TIMESTAMP(base));
-
-	regs[CTX_PDP3_UDW] = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 3));
-	regs[CTX_PDP3_LDW] = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, 3));
-	regs[CTX_PDP2_UDW] = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 2));
-	regs[CTX_PDP2_LDW] = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, 2));
-	regs[CTX_PDP1_UDW] = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 1));
-	regs[CTX_PDP1_LDW] = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, 1));
-	regs[CTX_PDP0_UDW] = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(base, 0));
-	regs[CTX_PDP0_LDW] = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(base, 0));
-
-	if (engine->class == RENDER_CLASS) {
-		regs[CTX_RCS_INDIRECT_CTX] =
-			i915_mmio_reg_offset(RING_INDIRECT_CTX(base));
-		regs[CTX_RCS_INDIRECT_CTX_OFFSET] =
-			i915_mmio_reg_offset(RING_INDIRECT_CTX_OFFSET(base));
-		regs[CTX_BB_PER_CTX_PTR] =
-			i915_mmio_reg_offset(RING_BB_PER_CTX_PTR(base));
-
-		regs[CTX_R_PWR_CLK_STATE] =
-			i915_mmio_reg_offset(GEN8_R_PWR_CLK_STATE);
-	}
+	set_offsets(regs, reg_offsets(engine), engine);
 }
 
 static bool virtual_matches(const struct virtual_engine *ve,
@@ -1738,8 +2097,8 @@ static void execlists_context_unpin(struct intel_context *ce)
 }
 
 static void
-__execlists_update_reg_state(struct intel_context *ce,
-			     struct intel_engine_cs *engine)
+__execlists_update_reg_state(const struct intel_context *ce,
+			     const struct intel_engine_cs *engine)
 {
 	struct intel_ring *ring = ce->ring;
 	u32 *regs = ce->lrc_reg_state;
@@ -1747,16 +2106,16 @@ __execlists_update_reg_state(struct intel_context *ce,
 	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head));
 	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail));
 
-	regs[CTX_RING_BUFFER_START + 1] = i915_ggtt_offset(ring->vma);
-	regs[CTX_RING_HEAD + 1] = ring->head;
-	regs[CTX_RING_TAIL + 1] = ring->tail;
+	regs[CTX_RING_BUFFER_START] = i915_ggtt_offset(ring->vma);
+	regs[CTX_RING_HEAD] = ring->head;
+	regs[CTX_RING_TAIL] = ring->tail;
 
 	/* RPCS */
 	if (engine->class == RENDER_CLASS) {
-		regs[CTX_R_PWR_CLK_STATE + 1] =
+		regs[CTX_R_PWR_CLK_STATE] =
 			intel_sseu_make_rpcs(engine->i915, &ce->sseu);
 
-		i915_oa_init_reg_state(engine, ce, regs);
+		i915_oa_init_reg_state(ce, engine);
 	}
 }
 
@@ -2465,7 +2824,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 		       engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
 		       engine->context_size - PAGE_SIZE);
 	}
-	execlists_init_reg_state(regs, ce, engine, ce->ring);
+	execlists_init_reg_state(regs, ce, engine, ce->ring, false);
 
 out_replay:
 	GEM_TRACE("%s replay {head:%04x, tail:%04x\n",
@@ -3243,7 +3602,7 @@ int intel_execlists_submission_init(struct intel_engine_cs *engine)
 	return 0;
 }
 
-static u32 intel_lr_indirect_ctx_offset(struct intel_engine_cs *engine)
+static u32 intel_lr_indirect_ctx_offset(const struct intel_engine_cs *engine)
 {
 	u32 indirect_ctx_offset;
 
@@ -3278,75 +3637,48 @@ static u32 intel_lr_indirect_ctx_offset(struct intel_engine_cs *engine)
 
 
 static void init_common_reg_state(u32 * const regs,
-				  struct i915_ppgtt * const ppgtt,
-				  struct intel_engine_cs *engine,
-				  struct intel_ring *ring)
+				  const struct intel_engine_cs *engine,
+				  const struct intel_ring *ring)
 {
-	const u32 base = engine->mmio_base;
-
-	CTX_REG(regs, CTX_CONTEXT_CONTROL, RING_CONTEXT_CONTROL(base),
+	regs[CTX_CONTEXT_CONTROL] =
 		_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) |
-		_MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH));
-	if (INTEL_GEN(engine->i915) < 11) {
-		regs[CTX_CONTEXT_CONTROL + 1] |=
+		_MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH);
+	if (INTEL_GEN(engine->i915) < 11)
+		regs[CTX_CONTEXT_CONTROL] |=
 			_MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT |
 					    CTX_CTRL_RS_CTX_ENABLE);
-	}
-	CTX_REG(regs, CTX_RING_HEAD, RING_HEAD(base), 0);
-	CTX_REG(regs, CTX_RING_TAIL, RING_TAIL(base), 0);
-	CTX_REG(regs, CTX_RING_BUFFER_START, RING_START(base), 0);
-	CTX_REG(regs, CTX_RING_BUFFER_CONTROL, RING_CTL(base),
-		RING_CTL_SIZE(ring->size) | RING_VALID);
-	CTX_REG(regs, CTX_BB_HEAD_U, RING_BBADDR_UDW(base), 0);
-	CTX_REG(regs, CTX_BB_HEAD_L, RING_BBADDR(base), 0);
-	CTX_REG(regs, CTX_BB_STATE, RING_BBSTATE(base), RING_BB_PPGTT);
+
+	regs[CTX_RING_BUFFER_CONTROL] = RING_CTL_SIZE(ring->size) | RING_VALID;
+	regs[CTX_BB_STATE] = RING_BB_PPGTT;
 }
 
 static void init_wa_bb_reg_state(u32 * const regs,
-				 struct intel_engine_cs *engine,
+				 const struct intel_engine_cs *engine,
 				 u32 pos_bb_per_ctx)
 {
-	struct i915_ctx_workarounds * const wa_ctx = &engine->wa_ctx;
-	const u32 base = engine->mmio_base;
-	const u32 pos_indirect_ctx = pos_bb_per_ctx + 2;
-	const u32 pos_indirect_ctx_offset = pos_indirect_ctx + 2;
+	const struct i915_ctx_workarounds * const wa_ctx = &engine->wa_ctx;
+
+	if (wa_ctx->per_ctx.size) {
+		const u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
+
+		regs[pos_bb_per_ctx] =
+			(ggtt_offset + wa_ctx->per_ctx.offset) | 0x01;
+	}
 
-	CTX_REG(regs, pos_indirect_ctx, RING_INDIRECT_CTX(base), 0);
-	CTX_REG(regs, pos_indirect_ctx_offset,
-		RING_INDIRECT_CTX_OFFSET(base), 0);
 	if (wa_ctx->indirect_ctx.size) {
 		const u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
 
-		regs[pos_indirect_ctx + 1] =
+		regs[pos_bb_per_ctx + 2] =
 			(ggtt_offset + wa_ctx->indirect_ctx.offset) |
 			(wa_ctx->indirect_ctx.size / CACHELINE_BYTES);
 
-		regs[pos_indirect_ctx_offset + 1] =
+		regs[pos_bb_per_ctx + 4] =
 			intel_lr_indirect_ctx_offset(engine) << 6;
 	}
-
-	CTX_REG(regs, pos_bb_per_ctx, RING_BB_PER_CTX_PTR(base), 0);
-	if (wa_ctx->per_ctx.size) {
-		const u32 ggtt_offset = i915_ggtt_offset(wa_ctx->vma);
-
-		regs[pos_bb_per_ctx + 1] =
-			(ggtt_offset + wa_ctx->per_ctx.offset) | 0x01;
-	}
 }
 
-static void init_ppgtt_reg_state(u32 *regs, u32 base,
-				 struct i915_ppgtt *ppgtt)
+static void init_ppgtt_reg_state(u32 *regs, const struct i915_ppgtt *ppgtt)
 {
-	/* PDP values well be assigned later if needed */
-	CTX_REG(regs, CTX_PDP3_UDW, GEN8_RING_PDP_UDW(base, 3), 0);
-	CTX_REG(regs, CTX_PDP3_LDW, GEN8_RING_PDP_LDW(base, 3), 0);
-	CTX_REG(regs, CTX_PDP2_UDW, GEN8_RING_PDP_UDW(base, 2), 0);
-	CTX_REG(regs, CTX_PDP2_LDW, GEN8_RING_PDP_LDW(base, 2), 0);
-	CTX_REG(regs, CTX_PDP1_UDW, GEN8_RING_PDP_UDW(base, 1), 0);
-	CTX_REG(regs, CTX_PDP1_LDW, GEN8_RING_PDP_LDW(base, 1), 0);
-	CTX_REG(regs, CTX_PDP0_UDW, GEN8_RING_PDP_UDW(base, 0), 0);
-	CTX_REG(regs, CTX_PDP0_LDW, GEN8_RING_PDP_LDW(base, 0), 0);
-
 	if (i915_vm_is_4lvl(&ppgtt->vm)) {
 		/* 64b PPGTT (48bit canonical)
 		 * PDP0_DESCRIPTOR contains the base address to PML4 and
@@ -3369,91 +3701,11 @@ static struct i915_ppgtt *vm_alias(struct i915_address_space *vm)
 		return i915_vm_to_ppgtt(vm);
 }
 
-static void gen8_init_reg_state(u32 * const regs,
-				struct intel_context *ce,
-				struct intel_engine_cs *engine,
-				struct intel_ring *ring)
-{
-	struct i915_ppgtt * const ppgtt = vm_alias(ce->vm);
-	const bool rcs = engine->class == RENDER_CLASS;
-	const u32 base = engine->mmio_base;
-	const u32 lri_base =
-		intel_engine_has_relative_mmio(engine) ? MI_LRI_CS_MMIO : 0;
-
-	regs[CTX_LRI_HEADER_0] =
-		MI_LOAD_REGISTER_IMM(rcs ? 14 : 11) |
-		MI_LRI_FORCE_POSTED |
-		lri_base;
-
-	init_common_reg_state(regs, ppgtt, engine, ring);
-	CTX_REG(regs, CTX_SECOND_BB_HEAD_U, RING_SBBADDR_UDW(base), 0);
-	CTX_REG(regs, CTX_SECOND_BB_HEAD_L, RING_SBBADDR(base), 0);
-	CTX_REG(regs, CTX_SECOND_BB_STATE, RING_SBBSTATE(base), 0);
-	if (rcs)
-		init_wa_bb_reg_state(regs, engine, CTX_BB_PER_CTX_PTR);
-
-	regs[CTX_LRI_HEADER_1] =
-		MI_LOAD_REGISTER_IMM(9) |
-		MI_LRI_FORCE_POSTED |
-		lri_base;
-
-	CTX_REG(regs, CTX_CTX_TIMESTAMP, RING_CTX_TIMESTAMP(base), 0);
-
-	init_ppgtt_reg_state(regs, base, ppgtt);
-
-	if (rcs) {
-		regs[CTX_LRI_HEADER_2] = MI_LOAD_REGISTER_IMM(1) | lri_base;
-		CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, 0);
-	}
-
-	regs[CTX_END] = MI_BATCH_BUFFER_END;
-	if (INTEL_GEN(engine->i915) >= 10)
-		regs[CTX_END] |= BIT(0);
-}
-
-static void gen12_init_reg_state(u32 * const regs,
-				 struct intel_context *ce,
-				 struct intel_engine_cs *engine,
-				 struct intel_ring *ring)
-{
-	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(ce->vm);
-	const bool rcs = engine->class == RENDER_CLASS;
-	const u32 base = engine->mmio_base;
-	const u32 lri_base =
-		intel_engine_has_relative_mmio(engine) ? MI_LRI_CS_MMIO : 0;
-
-	regs[CTX_LRI_HEADER_0] =
-		MI_LOAD_REGISTER_IMM(rcs ? 11 : 9) |
-		MI_LRI_FORCE_POSTED |
-		lri_base;
-
-	init_common_reg_state(regs, ppgtt, engine, ring);
-
-	/* We want ctx_ptr for all engines to be set */
-	init_wa_bb_reg_state(regs, engine, GEN12_CTX_BB_PER_CTX_PTR);
-
-	regs[CTX_LRI_HEADER_1] =
-		MI_LOAD_REGISTER_IMM(9) |
-		MI_LRI_FORCE_POSTED |
-		lri_base;
-
-	CTX_REG(regs, CTX_CTX_TIMESTAMP, RING_CTX_TIMESTAMP(base), 0);
-
-	init_ppgtt_reg_state(regs, base, ppgtt);
-
-	if (rcs) {
-		regs[GEN12_CTX_LRI_HEADER_3] =
-			MI_LOAD_REGISTER_IMM(1) | lri_base;
-		CTX_REG(regs, CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE, 0);
-
-		/* TODO: oa_init_reg_state ? */
-	}
-}
-
 static void execlists_init_reg_state(u32 *regs,
-				     struct intel_context *ce,
-				     struct intel_engine_cs *engine,
-				     struct intel_ring *ring)
+				     const struct intel_context *ce,
+				     const struct intel_engine_cs *engine,
+				     const struct intel_ring *ring,
+				     bool close)
 {
 	/*
 	 * A context is actually a big batch buffer with several
@@ -3465,10 +3717,21 @@ static void execlists_init_reg_state(u32 *regs,
 	 *
 	 * Must keep consistent with virtual_update_register_offsets().
 	 */
-	if (INTEL_GEN(engine->i915) >= 12)
-		gen12_init_reg_state(regs, ce, engine, ring);
-	else
-		gen8_init_reg_state(regs, ce, engine, ring);
+	u32 *bbe = set_offsets(regs, reg_offsets(engine), engine);
+
+	if (close) { /* Close the batch; used mainly by live_lrc_layout() */
+		*bbe = MI_BATCH_BUFFER_END;
+		if (INTEL_GEN(engine->i915) >= 10)
+			*bbe |= BIT(0);
+	}
+
+	init_common_reg_state(regs, engine, ring);
+	init_ppgtt_reg_state(regs, vm_alias(ce->vm));
+
+	init_wa_bb_reg_state(regs, engine,
+			     INTEL_GEN(engine->i915) >= 12 ?
+			     GEN12_CTX_BB_PER_CTX_PTR :
+			     CTX_BB_PER_CTX_PTR);
 }
 
 static int
@@ -3477,6 +3740,7 @@ populate_lr_context(struct intel_context *ce,
 		    struct intel_engine_cs *engine,
 		    struct intel_ring *ring)
 {
+	bool inhibit = true;
 	void *vaddr;
 	u32 *regs;
 	int ret;
@@ -3508,14 +3772,15 @@ populate_lr_context(struct intel_context *ce,
 
 		memcpy(vaddr + start, defaults + start, engine->context_size);
 		i915_gem_object_unpin_map(engine->default_state);
+		inhibit = false;
 	}
 
 	/* The second page of the context object contains some fields which must
 	 * be set up prior to the first execution. */
 	regs = vaddr + LRC_STATE_PN * PAGE_SIZE;
-	execlists_init_reg_state(regs, ce, engine, ring);
-	if (!engine->default_state)
-		regs[CTX_CONTEXT_CONTROL + 1] |=
+	execlists_init_reg_state(regs, ce, engine, ring, inhibit);
+	if (inhibit)
+		regs[CTX_CONTEXT_CONTROL] |=
 			_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
 
 	ret = 0;
@@ -4212,7 +4477,7 @@ void intel_lr_context_reset(struct intel_engine_cs *engine,
 			       engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
 			       engine->context_size - PAGE_SIZE);
 		}
-		execlists_init_reg_state(regs, ce, engine, ce->ring);
+		execlists_init_reg_state(regs, ce, engine, ce->ring, false);
 	}
 
 	/* Rerun the request; its payload has been neutered (if guilty). */
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
index 7e773e74a3fe..06ab0276e10e 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h
@@ -10,60 +10,40 @@
 #include <linux/types.h>
 
 /* GEN8 to GEN11 Reg State Context */
-#define CTX_LRI_HEADER_0		0x01
-#define CTX_CONTEXT_CONTROL		0x02
-#define CTX_RING_HEAD			0x04
-#define CTX_RING_TAIL			0x06
-#define CTX_RING_BUFFER_START		0x08
-#define CTX_RING_BUFFER_CONTROL		0x0a
-#define CTX_BB_HEAD_U			0x0c
-#define CTX_BB_HEAD_L			0x0e
-#define CTX_BB_STATE			0x10
-#define CTX_SECOND_BB_HEAD_U		0x12
-#define CTX_SECOND_BB_HEAD_L		0x14
-#define CTX_SECOND_BB_STATE		0x16
-#define CTX_BB_PER_CTX_PTR		0x18
-#define CTX_RCS_INDIRECT_CTX		0x1a
-#define CTX_RCS_INDIRECT_CTX_OFFSET	0x1c
-#define CTX_LRI_HEADER_1		0x21
-#define CTX_CTX_TIMESTAMP		0x22
-#define CTX_PDP3_UDW			0x24
-#define CTX_PDP3_LDW			0x26
-#define CTX_PDP2_UDW			0x28
-#define CTX_PDP2_LDW			0x2a
-#define CTX_PDP1_UDW			0x2c
-#define CTX_PDP1_LDW			0x2e
-#define CTX_PDP0_UDW			0x30
-#define CTX_PDP0_LDW			0x32
-#define CTX_LRI_HEADER_2		0x41
-#define CTX_R_PWR_CLK_STATE		0x42
-#define CTX_END				0x44
+#define CTX_CONTEXT_CONTROL		(0x02 + 1)
+#define CTX_RING_HEAD			(0x04 + 1)
+#define CTX_RING_TAIL			(0x06 + 1)
+#define CTX_RING_BUFFER_START		(0x08 + 1)
+#define CTX_RING_BUFFER_CONTROL		(0x0a + 1)
+#define CTX_BB_STATE			(0x10 + 1)
+#define CTX_BB_PER_CTX_PTR		(0x18 + 1)
+#define CTX_PDP3_UDW			(0x24 + 1)
+#define CTX_PDP3_LDW			(0x26 + 1)
+#define CTX_PDP2_UDW			(0x28 + 1)
+#define CTX_PDP2_LDW			(0x2a + 1)
+#define CTX_PDP1_UDW			(0x2c + 1)
+#define CTX_PDP1_LDW			(0x2e + 1)
+#define CTX_PDP0_UDW			(0x30 + 1)
+#define CTX_PDP0_LDW			(0x32 + 1)
+#define CTX_R_PWR_CLK_STATE		(0x42 + 1)
 
 #define GEN9_CTX_RING_MI_MODE		0x54
 
 /* GEN12+ Reg State Context */
-#define GEN12_CTX_BB_PER_CTX_PTR		0x12
-#define GEN12_CTX_LRI_HEADER_3			0x41
-
-#define CTX_REG(reg_state, pos, reg, val) do { \
-	u32 *reg_state__ = (reg_state); \
-	const u32 pos__ = (pos); \
-	(reg_state__)[(pos__) + 0] = i915_mmio_reg_offset(reg); \
-	(reg_state__)[(pos__) + 1] = (val); \
-} while (0)
+#define GEN12_CTX_BB_PER_CTX_PTR		(0x12 + 1)
 
 #define ASSIGN_CTX_PDP(ppgtt, reg_state, n) do { \
 	u32 *reg_state__ = (reg_state); \
 	const u64 addr__ = i915_page_dir_dma_addr((ppgtt), (n)); \
-	(reg_state__)[CTX_PDP ## n ## _UDW + 1] = upper_32_bits(addr__); \
-	(reg_state__)[CTX_PDP ## n ## _LDW + 1] = lower_32_bits(addr__); \
+	(reg_state__)[CTX_PDP ## n ## _UDW] = upper_32_bits(addr__); \
+	(reg_state__)[CTX_PDP ## n ## _LDW] = lower_32_bits(addr__); \
 } while (0)
 
 #define ASSIGN_CTX_PML4(ppgtt, reg_state) do { \
 	u32 *reg_state__ = (reg_state); \
 	const u64 addr__ = px_dma(ppgtt->pd); \
-	(reg_state__)[CTX_PDP0_UDW + 1] = upper_32_bits(addr__); \
-	(reg_state__)[CTX_PDP0_LDW + 1] = lower_32_bits(addr__); \
+	(reg_state__)[CTX_PDP0_UDW] = upper_32_bits(addr__); \
+	(reg_state__)[CTX_PDP0_LDW] = lower_32_bits(addr__); \
 } while (0)
 
 #define GEN8_CTX_RCS_INDIRECT_CTX_OFFSET_DEFAULT	0x17
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 93a871bfd95d..22ea2e747064 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -2201,3 +2201,145 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 
 	return i915_live_subtests(tests, i915);
 }
+
+static void hexdump(const void *buf, size_t len)
+{
+	const size_t rowsize = 8 * sizeof(u32);
+	const void *prev = NULL;
+	bool skip = false;
+	size_t pos;
+
+	for (pos = 0; pos < len; pos += rowsize) {
+		char line[128];
+
+		if (prev && !memcmp(prev, buf + pos, rowsize)) {
+			if (!skip) {
+				pr_info("*\n");
+				skip = true;
+			}
+			continue;
+		}
+
+		WARN_ON_ONCE(hex_dump_to_buffer(buf + pos, len - pos,
+						rowsize, sizeof(u32),
+						line, sizeof(line),
+						false) >= sizeof(line));
+		pr_info("[%04zx] %s\n", pos, line);
+
+		prev = buf + pos;
+		skip = false;
+	}
+}
+
+static int live_lrc_layout(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	u32 *mem;
+	int err;
+
+	/*
+	 * Check the registers offsets we use to create the initial reg state
+	 * match the layout saved by HW.
+	 */
+
+	mem = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!mem)
+		return -ENOMEM;
+
+	err = 0;
+	for_each_engine(engine, gt->i915, id) {
+		u32 *hw, *lrc;
+		int dw;
+
+		if (!engine->default_state)
+			continue;
+
+		hw = i915_gem_object_pin_map(engine->default_state,
+					     I915_MAP_WB);
+		if (IS_ERR(hw)) {
+			err = PTR_ERR(hw);
+			break;
+		}
+		hw += LRC_STATE_PN * PAGE_SIZE / sizeof(*hw);
+
+		lrc = memset(mem, 0, PAGE_SIZE);
+		execlists_init_reg_state(lrc,
+					 engine->kernel_context,
+					 engine,
+					 engine->kernel_context->ring,
+					 true);
+
+		dw = 0;
+		do {
+			u32 lri = hw[dw];
+
+			if (lri == 0) {
+				dw++;
+				continue;
+			}
+
+			if ((lri & GENMASK(31, 23)) != MI_INSTR(0x22, 0)) {
+				pr_err("%s: Expected LRI command at dword %d, found %08x\n",
+				       engine->name, dw, lri);
+				err = -EINVAL;
+				break;
+			}
+
+			if (lrc[dw] != lri) {
+				pr_err("%s: LRI command mismatch at dword %d, expected %08x found %08x\n",
+				       engine->name, dw, lri, lrc[dw]);
+				err = -EINVAL;
+				break;
+			}
+
+			lri &= 0x7f;
+			lri++;
+			dw++;
+
+			while (lri) {
+				if (hw[dw] != lrc[dw]) {
+					pr_err("%s: Different registers found at dword %d, expected %x, found %x\n",
+					       engine->name, dw, hw[dw], lrc[dw]);
+					err = -EINVAL;
+					break;
+				}
+
+				/*
+				 * Skip over the actual register value as we
+				 * expect that to differ.
+				 */
+				dw += 2;
+				lri -= 2;
+			}
+		} while ((lrc[dw] & ~BIT(0)) != MI_BATCH_BUFFER_END);
+
+		if (err) {
+			pr_info("%s: HW register image:\n", engine->name);
+			hexdump(hw, PAGE_SIZE);
+
+			pr_info("%s: SW register image:\n", engine->name);
+			hexdump(lrc, PAGE_SIZE);
+		}
+
+		i915_gem_object_unpin_map(engine->default_state);
+		if (err)
+			break;
+	}
+
+	kfree(mem);
+	return err;
+}
+
+int intel_lrc_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_lrc_layout),
+	};
+
+	if (!HAS_LOGICAL_RING_CONTEXTS(i915))
+		return 0;
+
+	return intel_gt_live_subtests(tests, &i915->gt);
+}
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index c1b764233761..524f6710b7aa 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1673,10 +1673,8 @@ static u32 oa_config_flex_reg(const struct i915_oa_config *oa_config,
  * in the case that the OA unit has been disabled.
  */
 static void
-gen8_update_reg_state_unlocked(struct i915_perf_stream *stream,
-			       struct intel_context *ce,
-			       u32 *reg_state,
-			       const struct i915_oa_config *oa_config)
+gen8_update_reg_state_unlocked(const struct intel_context *ce,
+			       const struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *i915 = ce->engine->i915;
 	u32 ctx_oactxctrl = i915->perf.ctx_oactxctrl_offset;
@@ -1691,21 +1689,19 @@ gen8_update_reg_state_unlocked(struct i915_perf_stream *stream,
 		EU_PERF_CNTL5,
 		EU_PERF_CNTL6,
 	};
+	u32 *reg_state = ce->lrc_reg_state;
 	int i;
 
-	CTX_REG(reg_state, ctx_oactxctrl, GEN8_OACTXCONTROL,
+	reg_state[ctx_oactxctrl + 1] =
 		(stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
 		(stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
-		GEN8_OA_COUNTER_RESUME);
+		GEN8_OA_COUNTER_RESUME;
 
-	for (i = 0; i < ARRAY_SIZE(flex_regs); i++) {
-		CTX_REG(reg_state, ctx_flexeu0 + i * 2, flex_regs[i],
-			oa_config_flex_reg(oa_config, flex_regs[i]));
-	}
+	for (i = 0; i < ARRAY_SIZE(flex_regs); i++)
+		reg_state[ctx_flexeu0 + i * 2 + 1] =
+			oa_config_flex_reg(stream->oa_config, flex_regs[i]);
 
-	CTX_REG(reg_state,
-		CTX_R_PWR_CLK_STATE, GEN8_R_PWR_CLK_STATE,
-		intel_sseu_make_rpcs(i915, &ce->sseu));
+	reg_state[CTX_R_PWR_CLK_STATE] = intel_sseu_make_rpcs(i915, &ce->sseu);
 }
 
 struct flex {
@@ -1729,7 +1725,7 @@ gen8_store_flex(struct i915_request *rq,
 	offset = i915_ggtt_offset(ce->state) + LRC_STATE_PN * PAGE_SIZE;
 	do {
 		*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
-		*cs++ = offset + (flex->offset + 1) * sizeof(u32);
+		*cs++ = offset + flex->offset * sizeof(u32);
 		*cs++ = 0;
 		*cs++ = flex->value;
 	} while (flex++, --count);
@@ -1863,7 +1859,7 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 	struct drm_i915_private *i915 = stream->dev_priv;
 	/* The MMIO offsets for Flex EU registers aren't contiguous */
 	const u32 ctx_flexeu0 = i915->perf.ctx_flexeu0_offset;
-#define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N))
+#define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1)
 	struct flex regs[] = {
 		{
 			GEN8_R_PWR_CLK_STATE,
@@ -1871,7 +1867,7 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 		},
 		{
 			GEN8_OACTXCONTROL,
-			i915->perf.ctx_oactxctrl_offset,
+			i915->perf.ctx_oactxctrl_offset + 1,
 			((stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
 			 (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
 			 GEN8_OA_COUNTER_RESUME)
@@ -2299,9 +2295,8 @@ err_config:
 	return ret;
 }
 
-void i915_oa_init_reg_state(struct intel_engine_cs *engine,
-			    struct intel_context *ce,
-			    u32 *regs)
+void i915_oa_init_reg_state(const struct intel_context *ce,
+			    const struct intel_engine_cs *engine)
 {
 	struct i915_perf_stream *stream;
 
@@ -2313,7 +2308,7 @@ void i915_oa_init_reg_state(struct intel_engine_cs *engine,
 
 	stream = engine->i915->perf.exclusive_stream;
 	if (stream)
-		gen8_update_reg_state_unlocked(stream, ce, regs, stream->oa_config);
+		gen8_update_reg_state_unlocked(ce, stream);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h
index a412b16d9ffc..f4fb311184b1 100644
--- a/drivers/gpu/drm/i915/i915_perf.h
+++ b/drivers/gpu/drm/i915/i915_perf.h
@@ -25,8 +25,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file);
 int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file);
-void i915_oa_init_reg_state(struct intel_engine_cs *engine,
-			    struct intel_context *ce,
-			    u32 *reg_state);
+void i915_oa_init_reg_state(const struct intel_context *ce,
+			    const struct intel_engine_cs *engine);
 
 #endif /* __I915_PERF_H__ */
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index 1ccf0f731ac0..66d83c1390c1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -15,6 +15,7 @@ selftest(workarounds, intel_workarounds_live_selftests)
 selftest(gt_engines, intel_engine_live_selftests)
 selftest(gt_timelines, intel_timeline_live_selftests)
 selftest(gt_contexts, intel_context_live_selftests)
+selftest(gt_lrc, intel_lrc_live_selftests)
 selftest(requests, i915_request_live_selftests)
 selftest(active, i915_active_live_selftests)
 selftest(objects, i915_gem_object_live_selftests)
-- 
cgit v1.2.3


From 6ea3cee6d77d2c5513d5a61162b209f671fb3bb8 Mon Sep 17 00:00:00 2001
From: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Date: Tue, 24 Sep 2019 13:01:52 +0530
Subject: drm/i915: Add Pipe D cursor ctrl register for Gen12

Currently the offset for PIPE D cursor control register is missing in
i915_reg.h due to which the cursor plane cannot be enabled for Pipe D.
This also causes kernel Warning, when a user requests to enable cursor
plane for PIPE D for Gen 12 platforms.

This patch adds the CURSOR_CTL_D register in the i915_reg.h.

v2: Rebase

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111640
Signed-off-by: Ankit Nautiyal <ankit.k.nautiyal@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
[Lucas: remove extra blank line]
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1569310312-12313-1-git-send-email-ankit.k.nautiyal@intel.com
---
 drivers/gpu/drm/i915/i915_pci.c | 9 +++++++++
 drivers/gpu/drm/i915/i915_reg.h | 1 +
 2 files changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index c2faa679658c..43530b0abc96 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -118,6 +118,14 @@
 		[PIPE_C] = IVB_CURSOR_C_OFFSET, \
 	}
 
+#define TGL_CURSOR_OFFSETS \
+	.cursor_offsets = { \
+		[PIPE_A] = CURSOR_A_OFFSET, \
+		[PIPE_B] = IVB_CURSOR_B_OFFSET, \
+		[PIPE_C] = IVB_CURSOR_C_OFFSET, \
+		[PIPE_D] = TGL_CURSOR_D_OFFSET, \
+	}
+
 #define I9XX_COLORS \
 	.color = { .gamma_lut_size = 256 }
 #define I965_COLORS \
@@ -787,6 +795,7 @@ static const struct intel_device_info intel_elkhartlake_info = {
 		[TRANSCODER_DSI_0] = TRANSCODER_DSI0_OFFSET, \
 		[TRANSCODER_DSI_1] = TRANSCODER_DSI1_OFFSET, \
 	}, \
+	TGL_CURSOR_OFFSETS, \
 	.has_global_mocs = 1, \
 	.display.has_dsb = 1
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index a69c19aae5bb..28c483a3bbba 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -6240,6 +6240,7 @@ enum {
 #define CHV_CURSOR_C_OFFSET 0x700e0
 #define IVB_CURSOR_B_OFFSET 0x71080
 #define IVB_CURSOR_C_OFFSET 0x72080
+#define TGL_CURSOR_D_OFFSET 0x73080
 
 /* Display A control */
 #define _DSPACNTR				0x70180
-- 
cgit v1.2.3


From b1da91c9ddcef7ee077ea04797db7fa3a952d683 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 24 Sep 2019 18:35:01 +0100
Subject: drm/i915/tgl: Swap engines for no rps (gpu reclocking)

If we disable rps, it appears the Tigerlake is stable enough to run
multiple engines simultaneously in CI. As disabling rps should only
cause the execution to be slow, whereas many features depend on the
different engines, we would prefer to have the engines enabled while the
machine hangs are being debugged.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111714
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190924173501.21956-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 43530b0abc96..ea53dfe2fba0 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -807,7 +807,7 @@ static const struct intel_device_info intel_tigerlake_12_info = {
 	.display.has_modular_fia = 1,
 	.engine_mask =
 		BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2),
-	.engine_mask = BIT(RCS0), /* XXX reduced for debugging */
+	.has_rps = false, /* XXX disabled for debugging */
 };
 
 #undef GEN
-- 
cgit v1.2.3


From 21a045e430e56725628f361dede8a882e92469b9 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Fri, 20 Sep 2019 21:45:33 +0200
Subject: ieee802154: mcr20a: simplify a bit
 'mcr20a_handle_rx_read_buf_complete()'

Use a 'skb_put_data()' variant instead of rewritting it.
The __skb_put_data variant is safe here. It is obvious that the skb can
not overflow. It has just been allocated a few lines above with the same
'len'.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Acked-by: Xue Liu <liuxuenetmail@gmail.com>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 drivers/net/ieee802154/mcr20a.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c
index 17f2300e63ee..8dc04e2590b1 100644
--- a/drivers/net/ieee802154/mcr20a.c
+++ b/drivers/net/ieee802154/mcr20a.c
@@ -800,7 +800,7 @@ mcr20a_handle_rx_read_buf_complete(void *context)
 	if (!skb)
 		return;
 
-	memcpy(skb_put(skb, len), lp->rx_buf, len);
+	__skb_put_data(skb, lp->rx_buf, len);
 	ieee802154_rx_irqsafe(lp->hw, skb, lp->rx_lqi[0]);
 
 	print_hex_dump_debug("mcr20a rx: ", DUMP_PREFIX_OFFSET, 16, 1,
-- 
cgit v1.2.3


From 1b8588741fdcb5976a343f7e5f47c5c97593d6d5 Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Tue, 24 Sep 2019 19:28:20 +0530
Subject: Revert "drm/i915/color: Extract icl_read_luts()"

This reverts commit 84af7649188194a74cdd6437235a5e3c86108f0f.

This is causing problems with the display, displays are all
bright colors.

Fixes: 84af76491881 ("drm/i915/color: Extract icl_read_luts()")
Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190924135820.11850-1-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 126 ++++-------------------------
 drivers/gpu/drm/i915/i915_reg.h            |   6 --
 2 files changed, 15 insertions(+), 117 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 402151128e1f..9ab34902663e 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1420,9 +1420,6 @@ static int icl_color_check(struct intel_crtc_state *crtc_state)
 
 static int i9xx_gamma_precision(const struct intel_crtc_state *crtc_state)
 {
-	if (!crtc_state->gamma_enable)
-		return 0;
-
 	switch (crtc_state->gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
 		return 8;
@@ -1436,9 +1433,6 @@ static int i9xx_gamma_precision(const struct intel_crtc_state *crtc_state)
 
 static int ilk_gamma_precision(const struct intel_crtc_state *crtc_state)
 {
-	if (!crtc_state->gamma_enable)
-		return 0;
-
 	if ((crtc_state->csc_mode & CSC_POSITION_BEFORE_GAMMA) == 0)
 		return 0;
 
@@ -1455,9 +1449,6 @@ static int ilk_gamma_precision(const struct intel_crtc_state *crtc_state)
 
 static int chv_gamma_precision(const struct intel_crtc_state *crtc_state)
 {
-	if (!crtc_state->gamma_enable)
-		return 0;
-
 	if (crtc_state->cgm_mode & CGM_PIPE_MODE_GAMMA)
 		return 10;
 	else
@@ -1466,9 +1457,6 @@ static int chv_gamma_precision(const struct intel_crtc_state *crtc_state)
 
 static int glk_gamma_precision(const struct intel_crtc_state *crtc_state)
 {
-	if (!crtc_state->gamma_enable)
-		return 0;
-
 	switch (crtc_state->gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
 		return 8;
@@ -1480,39 +1468,21 @@ static int glk_gamma_precision(const struct intel_crtc_state *crtc_state)
 	}
 }
 
-static int icl_gamma_precision(const struct intel_crtc_state *crtc_state)
-{
-	if ((crtc_state->gamma_mode & POST_CSC_GAMMA_ENABLE) == 0)
-		return 0;
-
-	switch (crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) {
-	case GAMMA_MODE_MODE_8BIT:
-		return 8;
-	case GAMMA_MODE_MODE_10BIT:
-		return 10;
-	case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED:
-		return 16;
-	default:
-		MISSING_CASE(crtc_state->gamma_mode);
-		return 0;
-	}
-
-}
-
 int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
+	if (!crtc_state->gamma_enable)
+		return 0;
+
 	if (HAS_GMCH(dev_priv)) {
 		if (IS_CHERRYVIEW(dev_priv))
 			return chv_gamma_precision(crtc_state);
 		else
 			return i9xx_gamma_precision(crtc_state);
 	} else {
-		if (INTEL_GEN(dev_priv) >= 11)
-			return icl_gamma_precision(crtc_state);
-		else if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+		if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
 			return glk_gamma_precision(crtc_state);
 		else if (IS_IRONLAKE(dev_priv))
 			return ilk_gamma_precision(crtc_state);
@@ -1543,20 +1513,6 @@ static bool intel_color_lut_entry_equal(struct drm_color_lut *lut1,
 	return true;
 }
 
-static bool intel_color_lut_entry_multi_equal(struct drm_color_lut *lut1,
-					      struct drm_color_lut *lut2,
-					      int lut_size, u32 err)
-{
-	int i;
-
-	for (i = 0; i < 9; i++) {
-		if (!err_check(&lut1[i], &lut2[i], err))
-			return false;
-	}
-
-	return true;
-}
-
 bool intel_color_lut_equal(struct drm_property_blob *blob1,
 			   struct drm_property_blob *blob2,
 			   u32 gamma_mode, u32 bit_precision)
@@ -1575,8 +1531,16 @@ bool intel_color_lut_equal(struct drm_property_blob *blob1,
 	lut_size2 = drm_color_lut_size(blob2);
 
 	/* check sw and hw lut size */
-	if (lut_size1 != lut_size2)
-		return false;
+	switch (gamma_mode) {
+	case GAMMA_MODE_MODE_8BIT:
+	case GAMMA_MODE_MODE_10BIT:
+		if (lut_size1 != lut_size2)
+			return false;
+		break;
+	default:
+		MISSING_CASE(gamma_mode);
+			return false;
+	}
 
 	lut1 = blob1->data;
 	lut2 = blob2->data;
@@ -1584,18 +1548,13 @@ bool intel_color_lut_equal(struct drm_property_blob *blob1,
 	err = 0xffff >> bit_precision;
 
 	/* check sw and hw lut entry to be equal */
-	switch (gamma_mode & GAMMA_MODE_MODE_MASK) {
+	switch (gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
 	case GAMMA_MODE_MODE_10BIT:
 		if (!intel_color_lut_entry_equal(lut1, lut2,
 						 lut_size2, err))
 			return false;
 		break;
-	case GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED:
-		if (!intel_color_lut_entry_multi_equal(lut1, lut2,
-						       lut_size2, err))
-			return false;
-		break;
 	default:
 		MISSING_CASE(gamma_mode);
 			return false;
@@ -1835,60 +1794,6 @@ static void glk_read_luts(struct intel_crtc_state *crtc_state)
 		crtc_state->base.gamma_lut = glk_read_lut_10(crtc_state, PAL_PREC_INDEX_VALUE(0));
 }
 
-static struct drm_property_blob *
-icl_read_lut_multi_segment(const struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	int lut_size = INTEL_INFO(dev_priv)->color.gamma_lut_size;
-	enum pipe pipe = crtc->pipe;
-	struct drm_property_blob *blob;
-	struct drm_color_lut *blob_data;
-	u32 i, val1, val2;
-
-	blob = drm_property_create_blob(&dev_priv->drm,
-					sizeof(struct drm_color_lut) * lut_size,
-					NULL);
-	if (IS_ERR(blob))
-		return NULL;
-
-	blob_data = blob->data;
-
-	I915_WRITE(PREC_PAL_MULTI_SEG_INDEX(pipe), PAL_PREC_AUTO_INCREMENT);
-
-	for (i = 0; i < 9; i++) {
-		val1 = I915_READ(PREC_PAL_MULTI_SEG_DATA(pipe));
-		val2 = I915_READ(PREC_PAL_MULTI_SEG_DATA(pipe));
-
-		blob_data[i].red = REG_FIELD_GET(PAL_PREC_MULTI_SEG_RED_UDW_MASK, val2) << 6 |
-				   REG_FIELD_GET(PAL_PREC_MULTI_SEG_RED_LDW_MASK, val1);
-		blob_data[i].green = REG_FIELD_GET(PAL_PREC_MULTI_SEG_GREEN_UDW_MASK, val2) << 6 |
-				     REG_FIELD_GET(PAL_PREC_MULTI_SEG_GREEN_LDW_MASK, val1);
-		blob_data[i].blue = REG_FIELD_GET(PAL_PREC_MULTI_SEG_BLUE_UDW_MASK, val2) << 6 |
-				    REG_FIELD_GET(PAL_PREC_MULTI_SEG_BLUE_LDW_MASK, val1);
-	}
-
-	/*
-	 * FIXME readouts from PAL_PREC_DATA register aren't giving correct values
-	 * in the case of fine and coarse segments. Restricting readouts only for
-	 * super fine segment as of now.
-	 */
-
-	return blob;
-}
-
-static void icl_read_luts(struct intel_crtc_state *crtc_state)
-{
-	if ((crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) ==
-	    GAMMA_MODE_MODE_8BIT)
-		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
-	else if ((crtc_state->gamma_mode & GAMMA_MODE_MODE_MASK) ==
-		 GAMMA_MODE_MODE_12BIT_MULTI_SEGMENTED)
-		crtc_state->base.gamma_lut = icl_read_lut_multi_segment(crtc_state);
-	else
-		crtc_state->base.gamma_lut = glk_read_lut_10(crtc_state, PAL_PREC_INDEX_VALUE(0));
-}
-
 void intel_color_init(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
@@ -1932,7 +1837,6 @@ void intel_color_init(struct intel_crtc *crtc)
 
 		if (INTEL_GEN(dev_priv) >= 11) {
 			dev_priv->display.load_luts = icl_load_luts;
-			dev_priv->display.read_luts = icl_read_luts;
 		} else if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv)) {
 			dev_priv->display.load_luts = glk_load_luts;
 			dev_priv->display.read_luts = glk_read_luts;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 28c483a3bbba..e752de9470bd 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -10575,12 +10575,6 @@ enum skl_power_gate {
 
 #define _PAL_PREC_MULTI_SEG_DATA_A	0x4A40C
 #define _PAL_PREC_MULTI_SEG_DATA_B	0x4AC0C
-#define  PAL_PREC_MULTI_SEG_RED_LDW_MASK   REG_GENMASK(29, 24)
-#define  PAL_PREC_MULTI_SEG_RED_UDW_MASK   REG_GENMASK(29, 20)
-#define  PAL_PREC_MULTI_SEG_GREEN_LDW_MASK REG_GENMASK(19, 14)
-#define  PAL_PREC_MULTI_SEG_GREEN_UDW_MASK REG_GENMASK(19, 10)
-#define  PAL_PREC_MULTI_SEG_BLUE_LDW_MASK  REG_GENMASK(9, 4)
-#define  PAL_PREC_MULTI_SEG_BLUE_UDW_MASK  REG_GENMASK(9, 0)
 
 #define PREC_PAL_MULTI_SEG_INDEX(pipe)	_MMIO_PIPE(pipe, \
 					_PAL_PREC_MULTI_SEG_INDEX_A, \
-- 
cgit v1.2.3


From ed06efb801bd291e935238d3fba46fa03d098f0e Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Wed, 25 Sep 2019 10:21:09 +0200
Subject: drm/i915/dp: Fix dsc bpp calculations, v5.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There was a integer wraparound when mode_clock became too high,
and we didn't correct for the FEC overhead factor when dividing,
with the calculations breaking at HBR3.

As a result our calculated bpp was way too high, and the link width
limitation never came into effect.

Print out the resulting bpp calcululations as a sanity check, just
in case we ever have to debug it later on again.

We also used the wrong factor for FEC. While bspec mentions 2.4%,
all the calculations use 1/0.972261, and the same ratio should be
applied to data M/N as well, so use it there when FEC is enabled.

This fixes the FIFO underrun we are seeing with FEC enabled.

Changes since v2:
- Handle fec_enable in intel_link_compute_m_n, so only data M/N is adjusted. (Ville)
- Fix initial hardware readout for FEC. (Ville)
Changes since v3:
- Remove bogus fec_to_mode_clock. (Ville)
Changes since v4:
- Use the correct register for icl. (Ville)
- Split hw readout to a separate patch.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Fixes: d9218c8f6cf4 ("drm/i915/dp: Add helpers for Compressed BPP and Slice Count for DSC")
Cc: <stable@vger.kernel.org> # v5.0+
Cc: Manasi Navare <manasi.d.navare@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190925082110.17439-1-maarten.lankhorst@linux.intel.com
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c |  12 +-
 drivers/gpu/drm/i915/display/intel_display.h |   2 +-
 drivers/gpu/drm/i915/display/intel_dp.c      | 184 ++++++++++++++-------------
 drivers/gpu/drm/i915/display/intel_dp.h      |   6 +-
 drivers/gpu/drm/i915/display/intel_dp_mst.c  |   2 +-
 5 files changed, 107 insertions(+), 99 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 5ecf54270181..c4c9286be987 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -7291,7 +7291,7 @@ retry:
 	pipe_config->fdi_lanes = lane;
 
 	intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock,
-			       link_bw, &pipe_config->fdi_m_n, false);
+			       link_bw, &pipe_config->fdi_m_n, false, false);
 
 	ret = ironlake_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config);
 	if (ret == -EDEADLK)
@@ -7538,11 +7538,15 @@ void
 intel_link_compute_m_n(u16 bits_per_pixel, int nlanes,
 		       int pixel_clock, int link_clock,
 		       struct intel_link_m_n *m_n,
-		       bool constant_n)
+		       bool constant_n, bool fec_enable)
 {
-	m_n->tu = 64;
+	u32 data_clock = bits_per_pixel * pixel_clock;
+
+	if (fec_enable)
+		data_clock = intel_dp_mode_to_fec_clock(data_clock);
 
-	compute_m_n(bits_per_pixel * pixel_clock,
+	m_n->tu = 64;
+	compute_m_n(data_clock,
 		    link_clock * nlanes * 8,
 		    &m_n->gmch_m, &m_n->gmch_n,
 		    constant_n);
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 5cea6f8e107a..4b9e18e5a263 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -443,7 +443,7 @@ enum phy_fia {
 void intel_link_compute_m_n(u16 bpp, int nlanes,
 			    int pixel_clock, int link_clock,
 			    struct intel_link_m_n *m_n,
-			    bool constant_n);
+			    bool constant_n, bool fec_enable);
 bool is_ccs_modifier(u64 modifier);
 void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv);
 u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 5cce9459e93c..893c9807755c 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -76,8 +76,8 @@
 #define DP_DSC_MAX_ENC_THROUGHPUT_0		340000
 #define DP_DSC_MAX_ENC_THROUGHPUT_1		400000
 
-/* DP DSC FEC Overhead factor = (100 - 2.4)/100 */
-#define DP_DSC_FEC_OVERHEAD_FACTOR		976
+/* DP DSC FEC Overhead factor = 1/(0.972261) */
+#define DP_DSC_FEC_OVERHEAD_FACTOR		972261
 
 /* Compliance test status bits  */
 #define INTEL_DP_RESOLUTION_SHIFT_MASK	0
@@ -492,6 +492,97 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp,
 	return 0;
 }
 
+u32 intel_dp_mode_to_fec_clock(u32 mode_clock)
+{
+	return div_u64(mul_u32_u32(mode_clock, 1000000U),
+		       DP_DSC_FEC_OVERHEAD_FACTOR);
+}
+
+static u16 intel_dp_dsc_get_output_bpp(u32 link_clock, u32 lane_count,
+				       u32 mode_clock, u32 mode_hdisplay)
+{
+	u32 bits_per_pixel, max_bpp_small_joiner_ram;
+	int i;
+
+	/*
+	 * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)*
+	 * (LinkSymbolClock)* 8 * (TimeSlotsPerMTP)
+	 * for SST -> TimeSlotsPerMTP is 1,
+	 * for MST -> TimeSlotsPerMTP has to be calculated
+	 */
+	bits_per_pixel = (link_clock * lane_count * 8) /
+			 intel_dp_mode_to_fec_clock(mode_clock);
+	DRM_DEBUG_KMS("Max link bpp: %u\n", bits_per_pixel);
+
+	/* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */
+	max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER / mode_hdisplay;
+	DRM_DEBUG_KMS("Max small joiner bpp: %u\n", max_bpp_small_joiner_ram);
+
+	/*
+	 * Greatest allowed DSC BPP = MIN (output BPP from available Link BW
+	 * check, output bpp from small joiner RAM check)
+	 */
+	bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram);
+
+	/* Error out if the max bpp is less than smallest allowed valid bpp */
+	if (bits_per_pixel < valid_dsc_bpp[0]) {
+		DRM_DEBUG_KMS("Unsupported BPP %u, min %u\n",
+			      bits_per_pixel, valid_dsc_bpp[0]);
+		return 0;
+	}
+
+	/* Find the nearest match in the array of known BPPs from VESA */
+	for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) {
+		if (bits_per_pixel < valid_dsc_bpp[i + 1])
+			break;
+	}
+	bits_per_pixel = valid_dsc_bpp[i];
+
+	/*
+	 * Compressed BPP in U6.4 format so multiply by 16, for Gen 11,
+	 * fractional part is 0
+	 */
+	return bits_per_pixel << 4;
+}
+
+static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
+				       int mode_clock, int mode_hdisplay)
+{
+	u8 min_slice_count, i;
+	int max_slice_width;
+
+	if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE)
+		min_slice_count = DIV_ROUND_UP(mode_clock,
+					       DP_DSC_MAX_ENC_THROUGHPUT_0);
+	else
+		min_slice_count = DIV_ROUND_UP(mode_clock,
+					       DP_DSC_MAX_ENC_THROUGHPUT_1);
+
+	max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd);
+	if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) {
+		DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n",
+			      max_slice_width);
+		return 0;
+	}
+	/* Also take into account max slice width */
+	min_slice_count = min_t(u8, min_slice_count,
+				DIV_ROUND_UP(mode_hdisplay,
+					     max_slice_width));
+
+	/* Find the closest match to the valid slice count values */
+	for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) {
+		if (valid_dsc_slicecount[i] >
+		    drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd,
+						    false))
+			break;
+		if (min_slice_count  <= valid_dsc_slicecount[i])
+			return valid_dsc_slicecount[i];
+	}
+
+	DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count);
+	return 0;
+}
+
 static enum drm_mode_status
 intel_dp_mode_valid(struct drm_connector *connector,
 		    struct drm_display_mode *mode)
@@ -2259,7 +2350,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 			       adjusted_mode->crtc_clock,
 			       pipe_config->port_clock,
 			       &pipe_config->dp_m_n,
-			       constant_n);
+			       constant_n, pipe_config->fec_enable);
 
 	if (intel_connector->panel.downclock_mode != NULL &&
 		dev_priv->drrs.type == SEAMLESS_DRRS_SUPPORT) {
@@ -2269,7 +2360,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 					       intel_connector->panel.downclock_mode->clock,
 					       pipe_config->port_clock,
 					       &pipe_config->dp_m2_n2,
-					       constant_n);
+					       constant_n, pipe_config->fec_enable);
 	}
 
 	if (!HAS_DDI(dev_priv))
@@ -4373,91 +4464,6 @@ intel_dp_get_sink_irq_esi(struct intel_dp *intel_dp, u8 *sink_irq_vector)
 		DP_DPRX_ESI_LEN;
 }
 
-u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count,
-				int mode_clock, int mode_hdisplay)
-{
-	u16 bits_per_pixel, max_bpp_small_joiner_ram;
-	int i;
-
-	/*
-	 * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)*
-	 * (LinkSymbolClock)* 8 * ((100-FECOverhead)/100)*(TimeSlotsPerMTP)
-	 * FECOverhead = 2.4%, for SST -> TimeSlotsPerMTP is 1,
-	 * for MST -> TimeSlotsPerMTP has to be calculated
-	 */
-	bits_per_pixel = (link_clock * lane_count * 8 *
-			  DP_DSC_FEC_OVERHEAD_FACTOR) /
-		mode_clock;
-
-	/* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */
-	max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER /
-		mode_hdisplay;
-
-	/*
-	 * Greatest allowed DSC BPP = MIN (output BPP from avaialble Link BW
-	 * check, output bpp from small joiner RAM check)
-	 */
-	bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram);
-
-	/* Error out if the max bpp is less than smallest allowed valid bpp */
-	if (bits_per_pixel < valid_dsc_bpp[0]) {
-		DRM_DEBUG_KMS("Unsupported BPP %d\n", bits_per_pixel);
-		return 0;
-	}
-
-	/* Find the nearest match in the array of known BPPs from VESA */
-	for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) {
-		if (bits_per_pixel < valid_dsc_bpp[i + 1])
-			break;
-	}
-	bits_per_pixel = valid_dsc_bpp[i];
-
-	/*
-	 * Compressed BPP in U6.4 format so multiply by 16, for Gen 11,
-	 * fractional part is 0
-	 */
-	return bits_per_pixel << 4;
-}
-
-u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
-				int mode_clock,
-				int mode_hdisplay)
-{
-	u8 min_slice_count, i;
-	int max_slice_width;
-
-	if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE)
-		min_slice_count = DIV_ROUND_UP(mode_clock,
-					       DP_DSC_MAX_ENC_THROUGHPUT_0);
-	else
-		min_slice_count = DIV_ROUND_UP(mode_clock,
-					       DP_DSC_MAX_ENC_THROUGHPUT_1);
-
-	max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd);
-	if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) {
-		DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n",
-			      max_slice_width);
-		return 0;
-	}
-	/* Also take into account max slice width */
-	min_slice_count = min_t(u8, min_slice_count,
-				DIV_ROUND_UP(mode_hdisplay,
-					     max_slice_width));
-
-	/* Find the closest match to the valid slice count values */
-	for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) {
-		if (valid_dsc_slicecount[i] >
-		    drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd,
-						    false))
-			break;
-		if (min_slice_count  <= valid_dsc_slicecount[i])
-			return valid_dsc_slicecount[i];
-	}
-
-	DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count);
-	return 0;
-}
-
 static void
 intel_pixel_encoding_setup_vsc(struct intel_dp *intel_dp,
 			       const struct intel_crtc_state *crtc_state)
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index e01d1f89409d..a194b5b6da05 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -103,10 +103,6 @@ bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp);
 bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp);
 bool
 intel_dp_get_link_status(struct intel_dp *intel_dp, u8 *link_status);
-u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count,
-				int mode_clock, int mode_hdisplay);
-u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, int mode_clock,
-				int mode_hdisplay);
 
 bool intel_dp_read_dpcd(struct intel_dp *intel_dp);
 bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp);
@@ -119,4 +115,6 @@ static inline unsigned int intel_dp_unused_lane_mask(int lane_count)
 	return ~((1 << lane_count) - 1) & 0xf;
 }
 
+u32 intel_dp_mode_to_fec_clock(u32 mode_clock);
+
 #endif /* __INTEL_DP_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index eeeb3f933aa4..cf4d851a5139 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -81,7 +81,7 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 			       adjusted_mode->crtc_clock,
 			       crtc_state->port_clock,
 			       &crtc_state->dp_m_n,
-			       constant_n);
+			       constant_n, crtc_state->fec_enable);
 	crtc_state->dp_m_n.tu = slots;
 
 	return 0;
-- 
cgit v1.2.3


From 8aa940c8551cce80bafcd8e1cd93d7b39a1acd8a Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Wed, 25 Sep 2019 10:21:10 +0200
Subject: drm/i915: Add hardware readout for FEC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Readout the FEC state in encoder->get_config(), this will allow
us to ensure that we can correctly inherit the state from boot,
and that we set FEC during modeset.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190925082110.17439-2-maarten.lankhorst@linux.intel.com
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c     | 17 +++++++++++++++++
 drivers/gpu/drm/i915/display/intel_display.c |  1 +
 2 files changed, 18 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 33cd766f9eea..14fe987888a6 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -4021,6 +4021,23 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 		pipe_config->lane_count =
 			((temp & DDI_PORT_WIDTH_MASK) >> DDI_PORT_WIDTH_SHIFT) + 1;
 		intel_dp_get_m_n(intel_crtc, pipe_config);
+
+		if (INTEL_GEN(dev_priv) >= 11) {
+			i915_reg_t dp_tp_ctl;
+
+			if (IS_GEN(dev_priv, 11))
+				dp_tp_ctl = DP_TP_CTL(encoder->port);
+			else
+				dp_tp_ctl = TGL_DP_TP_CTL(pipe_config->cpu_transcoder);
+
+			pipe_config->fec_enable =
+				I915_READ(dp_tp_ctl) & DP_TP_CTL_FEC_ENABLE;
+
+			DRM_DEBUG_KMS("[ENCODER:%d:%s] Fec status: %u\n",
+				      encoder->base.base.id, encoder->base.name,
+				      pipe_config->fec_enable);
+		}
+
 		break;
 	case TRANS_DDI_MODE_SELECT_DP_MST:
 		pipe_config->output_types |= BIT(INTEL_OUTPUT_DP_MST);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index c4c9286be987..31698a57773f 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -12836,6 +12836,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	PIPE_CONF_CHECK_BOOL(hdmi_scrambling);
 	PIPE_CONF_CHECK_BOOL(hdmi_high_tmds_clock_ratio);
 	PIPE_CONF_CHECK_BOOL(has_infoframe);
+	PIPE_CONF_CHECK_BOOL(fec_enable);
 
 	PIPE_CONF_CHECK_BOOL_INCOMPLETE(has_audio);
 
-- 
cgit v1.2.3


From c22d62e6e49beadea0024fe4eb9a02ce0f635657 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Fri, 20 Sep 2019 13:42:18 +0200
Subject: drm/i915: Get rid of crtc_state->fb_changed

We had this as an optimization to not do a plane update, but we killed
it off because there are so many reasons we may have to do a plane
update or fastset that it's best to just assume everything changed.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920114235.22411-6-maarten.lankhorst@linux.intel.com
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/i915/display/intel_atomic.c        |  1 -
 drivers/gpu/drm/i915/display/intel_display.c       | 10 +---------
 drivers/gpu/drm/i915/display/intel_display_types.h |  1 -
 3 files changed, 1 insertion(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c
index 698802da07b7..f7a981ff6812 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic.c
@@ -199,7 +199,6 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc)
 	crtc_state->disable_cxsr = false;
 	crtc_state->update_wm_pre = false;
 	crtc_state->update_wm_post = false;
-	crtc_state->fb_changed = false;
 	crtc_state->fifo_changed = false;
 	crtc_state->wm.need_postvbl_update = false;
 	crtc_state->fb_bits = 0;
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 31698a57773f..292be4b71a82 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -11582,7 +11582,6 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat
 	bool was_crtc_enabled = old_crtc_state->base.active;
 	bool is_crtc_enabled = crtc_state->base.active;
 	bool turn_off, turn_on, visible, was_visible;
-	struct drm_framebuffer *fb = plane_state->base.fb;
 	int ret;
 
 	if (INTEL_GEN(dev_priv) >= 9 && plane->id != PLANE_CURSOR) {
@@ -11616,18 +11615,11 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat
 	if (!was_visible && !visible)
 		return 0;
 
-	if (fb != old_plane_state->base.fb)
-		crtc_state->fb_changed = true;
-
 	turn_off = was_visible && (!visible || mode_changed);
 	turn_on = visible && (!was_visible || mode_changed);
 
-	DRM_DEBUG_ATOMIC("[CRTC:%d:%s] has [PLANE:%d:%s] with fb %i\n",
+	DRM_DEBUG_ATOMIC("[CRTC:%d:%s] with [PLANE:%d:%s] visible %i -> %i, off %i, on %i, ms %i\n",
 			 crtc->base.base.id, crtc->base.name,
-			 plane->base.base.id, plane->base.name,
-			 fb ? fb->base.id : -1);
-
-	DRM_DEBUG_ATOMIC("[PLANE:%d:%s] visible %i -> %i, off %i, on %i, ms %i\n",
 			 plane->base.base.id, plane->base.name,
 			 was_visible, visible,
 			 turn_off, turn_on, mode_changed);
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 6b0a646f0170..a33644f12af1 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -766,7 +766,6 @@ struct intel_crtc_state {
 	bool update_pipe; /* can a fast modeset be performed? */
 	bool disable_cxsr;
 	bool update_wm_pre, update_wm_post; /* watermarks are updated */
-	bool fb_changed; /* fb on any of the planes is changed */
 	bool fifo_changed; /* FIFO split is changed */
 
 	/* Pipe source size (ie. panel fitter input size)
-- 
cgit v1.2.3


From c47b7ddbcb29fca51515294a6fd2ed1d7d861939 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Fri, 20 Sep 2019 13:42:20 +0200
Subject: drm/i915: Rename planar linked plane variables

Rename linked_plane to planar_linked_plane and slave to planar_slave,
this will make it easier to keep apart bigjoiner linking and planar plane
linking.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920114235.22411-8-maarten.lankhorst@linux.intel.com
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/i915/display/intel_atomic.c        |  7 +++++--
 drivers/gpu/drm/i915/display/intel_atomic_plane.c  |  4 ++--
 drivers/gpu/drm/i915/display/intel_display.c       | 22 +++++++++++-----------
 drivers/gpu/drm/i915/display/intel_display_types.h |  8 ++++----
 drivers/gpu/drm/i915/display/intel_sprite.c        |  4 ++--
 drivers/gpu/drm/i915/intel_pm.c                    | 12 ++++++------
 6 files changed, 30 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c
index f7a981ff6812..99f4f83de280 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic.c
@@ -263,10 +263,13 @@ static void intel_atomic_setup_scaler(struct intel_crtc_scaler_state *scaler_sta
 			 */
 			mode = PS_SCALER_MODE_NORMAL;
 		} else {
+			struct intel_plane *linked =
+				plane_state->planar_linked_plane;
+
 			mode = PS_SCALER_MODE_PLANAR;
 
-			if (plane_state->linked_plane)
-				mode |= PS_PLANE_Y_SEL(plane_state->linked_plane->id);
+			if (linked)
+				mode |= PS_PLANE_Y_SEL(linked->id);
 		}
 	} else if (INTEL_GEN(dev_priv) > 9 || IS_GEMINILAKE(dev_priv)) {
 		mode = PS_SCALER_MODE_NORMAL;
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index 476ef0906ba0..98b7766eaa7a 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -321,9 +321,9 @@ void skl_update_planes_on_crtc(struct intel_atomic_state *state,
 
 		if (new_plane_state->base.visible) {
 			intel_update_plane(plane, new_crtc_state, new_plane_state);
-		} else if (new_plane_state->slave) {
+		} else if (new_plane_state->planar_slave) {
 			struct intel_plane *master =
-				new_plane_state->linked_plane;
+				new_plane_state->planar_linked_plane;
 
 			/*
 			 * We update the slave plane from this function because
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 292be4b71a82..8f125f1624bd 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -11729,7 +11729,7 @@ static int icl_add_linked_planes(struct intel_atomic_state *state)
 	int i;
 
 	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
-		linked = plane_state->linked_plane;
+		linked = plane_state->planar_linked_plane;
 
 		if (!linked)
 			continue;
@@ -11738,8 +11738,8 @@ static int icl_add_linked_planes(struct intel_atomic_state *state)
 		if (IS_ERR(linked_plane_state))
 			return PTR_ERR(linked_plane_state);
 
-		WARN_ON(linked_plane_state->linked_plane != plane);
-		WARN_ON(linked_plane_state->slave == plane_state->slave);
+		WARN_ON(linked_plane_state->planar_linked_plane != plane);
+		WARN_ON(linked_plane_state->planar_slave == plane_state->planar_slave);
 	}
 
 	return 0;
@@ -11762,16 +11762,16 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state)
 	 * in the crtc_state->active_planes mask.
 	 */
 	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
-		if (plane->pipe != crtc->pipe || !plane_state->linked_plane)
+		if (plane->pipe != crtc->pipe || !plane_state->planar_linked_plane)
 			continue;
 
-		plane_state->linked_plane = NULL;
-		if (plane_state->slave && !plane_state->base.visible) {
+		plane_state->planar_linked_plane = NULL;
+		if (plane_state->planar_slave && !plane_state->base.visible) {
 			crtc_state->active_planes &= ~BIT(plane->id);
 			crtc_state->update_planes |= BIT(plane->id);
 		}
 
-		plane_state->slave = false;
+		plane_state->planar_slave = false;
 	}
 
 	if (!crtc_state->nv12_planes)
@@ -11805,10 +11805,10 @@ static int icl_check_nv12_planes(struct intel_crtc_state *crtc_state)
 			return -EINVAL;
 		}
 
-		plane_state->linked_plane = linked;
+		plane_state->planar_linked_plane = linked;
 
-		linked_state->slave = true;
-		linked_state->linked_plane = plane;
+		linked_state->planar_slave = true;
+		linked_state->planar_linked_plane = plane;
 		crtc_state->active_planes |= BIT(linked->id);
 		crtc_state->update_planes |= BIT(linked->id);
 		DRM_DEBUG_KMS("Using %s as Y plane for %s\n", linked->base.name, plane->base.name);
@@ -13257,7 +13257,7 @@ intel_verify_planes(struct intel_atomic_state *state)
 
 	for_each_new_intel_plane_in_state(state, plane,
 					  plane_state, i)
-		assert_plane(plane, plane_state->slave ||
+		assert_plane(plane, plane_state->planar_slave ||
 			     plane_state->base.visible);
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index a33644f12af1..976669f01a8c 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -559,24 +559,24 @@ struct intel_plane_state {
 	int scaler_id;
 
 	/*
-	 * linked_plane:
+	 * planar_linked_plane:
 	 *
 	 * ICL planar formats require 2 planes that are updated as pairs.
 	 * This member is used to make sure the other plane is also updated
 	 * when required, and for update_slave() to find the correct
 	 * plane_state to pass as argument.
 	 */
-	struct intel_plane *linked_plane;
+	struct intel_plane *planar_linked_plane;
 
 	/*
-	 * slave:
+	 * planar_slave:
 	 * If set don't update use the linked plane's state for updating
 	 * this plane during atomic commit with the update_slave() callback.
 	 *
 	 * It's also used by the watermark code to ignore wm calculations on
 	 * this plane. They're calculated by the linked plane's wm code.
 	 */
-	u32 slave;
+	u32 planar_slave;
 
 	struct drm_intel_sprite_colorkey ckey;
 };
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index 7a7078d0ba23..3d56db32291b 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -542,7 +542,7 @@ skl_program_plane(struct intel_plane *plane,
 	u32 y = plane_state->color_plane[color_plane].y;
 	u32 src_w = drm_rect_width(&plane_state->base.src) >> 16;
 	u32 src_h = drm_rect_height(&plane_state->base.src) >> 16;
-	struct intel_plane *linked = plane_state->linked_plane;
+	struct intel_plane *linked = plane_state->planar_linked_plane;
 	const struct drm_framebuffer *fb = plane_state->base.fb;
 	u8 alpha = plane_state->base.alpha >> 8;
 	u32 plane_color_ctl = 0;
@@ -641,7 +641,7 @@ skl_update_plane(struct intel_plane *plane,
 {
 	int color_plane = 0;
 
-	if (plane_state->linked_plane) {
+	if (plane_state->planar_linked_plane) {
 		/* Program the UV plane */
 		color_plane = 1;
 	}
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 6aa40f546226..6bed2ed14574 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4293,7 +4293,7 @@ icl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
 		enum plane_id plane_id = to_intel_plane(plane)->id;
 		u64 rate;
 
-		if (!plane_state->linked_plane) {
+		if (!plane_state->planar_linked_plane) {
 			rate = skl_plane_relative_data_rate(crtc_state, plane_state, 0);
 			plane_data_rate[plane_id] = rate;
 			total_data_rate += rate;
@@ -4307,12 +4307,12 @@ icl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
 			 * NULL if we try get_new_plane_state(), so we
 			 * always calculate from the master.
 			 */
-			if (plane_state->slave)
+			if (plane_state->planar_slave)
 				continue;
 
 			/* Y plane rate is calculated on the slave */
 			rate = skl_plane_relative_data_rate(crtc_state, plane_state, 0);
-			y_plane_id = plane_state->linked_plane->id;
+			y_plane_id = plane_state->planar_linked_plane->id;
 			plane_data_rate[y_plane_id] = rate;
 			total_data_rate += rate;
 
@@ -5051,12 +5051,12 @@ static int icl_build_plane_wm(struct intel_crtc_state *crtc_state,
 	int ret;
 
 	/* Watermarks calculated in master */
-	if (plane_state->slave)
+	if (plane_state->planar_slave)
 		return 0;
 
-	if (plane_state->linked_plane) {
+	if (plane_state->planar_linked_plane) {
 		const struct drm_framebuffer *fb = plane_state->base.fb;
-		enum plane_id y_plane_id = plane_state->linked_plane->id;
+		enum plane_id y_plane_id = plane_state->planar_linked_plane->id;
 
 		WARN_ON(!intel_wm_plane_visible(crtc_state, plane_state));
 		WARN_ON(!fb->format->is_yuv ||
-- 
cgit v1.2.3


From c750c22b2456bcd8c50067424ccabf2686306cda Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Fri, 20 Sep 2019 13:42:21 +0200
Subject: drm/i915: Do not add all planes when checking scalers on glk+

We cannot switch between HQ and normal mode on GLK+, so only
add planes on platforms where it makes sense.

We could probably restrict it even more to only add when scaler
users toggles between 1 and 2, but lets just leave it for now.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920114235.22411-9-maarten.lankhorst@linux.intel.com
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/i915/display/intel_atomic.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c
index 99f4f83de280..c5a552a69752 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic.c
@@ -373,6 +373,15 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 			 */
 			if (!plane) {
 				struct drm_plane_state *state;
+
+				/*
+				 * GLK+ scalers don't have a HQ mode so it
+				 * isn't necessary to change between HQ and dyn mode
+				 * on those platforms.
+				 */
+				if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+					continue;
+
 				plane = drm_plane_from_index(&dev_priv->drm, i);
 				state = drm_atomic_get_plane_state(drm_state, plane);
 				if (IS_ERR(state)) {
-- 
cgit v1.2.3


From 8ad8041b98c665b6147e607b749586d6e20ba73a Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 24 Sep 2019 09:25:52 -0700
Subject: ARM: OMAP2+: Fix missing reset done flag for am3 and am43

For ti,sysc-omap4 compatible devices with no sysstatus register, we do have
reset done status available in the SOFTRESET bit that clears when the reset
is done. This is documented for example in am437x TRM for DMTIMER_TIOCP_CFG
register. The am335x TRM just says that SOFTRESET bit value 1 means reset is
ongoing, but it behaves the same way clearing after reset is done.

With the ti-sysc driver handling this automatically based on no sysstatus
register defined, we see warnings if SYSC_HAS_RESET_STATUS is missing in the
legacy platform data:

ti-sysc 48042000.target-module: sysc_flags 00000222 != 00000022
ti-sysc 48044000.target-module: sysc_flags 00000222 != 00000022
ti-sysc 48046000.target-module: sysc_flags 00000222 != 00000022
...

Let's fix these warnings by adding SYSC_HAS_RESET_STATUS. Let's also
remove the useless parentheses while at it.

If it turns out we do have ti,sysc-omap4 compatible devices without a
working SOFTRESET bit we can set up additional quirk handling for it.

Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
index adb6271f819b..7773876d165f 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_43xx_ipblock_data.c
@@ -811,7 +811,8 @@ static struct omap_hwmod_class_sysconfig am33xx_timer_sysc = {
 	.rev_offs	= 0x0000,
 	.sysc_offs	= 0x0010,
 	.syss_offs	= 0x0014,
-	.sysc_flags	= (SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET),
+	.sysc_flags	= SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET |
+			  SYSC_HAS_RESET_STATUS,
 	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
 			  SIDLE_SMART_WKUP),
 	.sysc_fields	= &omap_hwmod_sysc_type2,
-- 
cgit v1.2.3


From 17529d43b21c72466e9109d602c6f5c360a1a9e8 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 24 Sep 2019 09:25:51 -0700
Subject: ARM: OMAP2+: Add missing LCDC midlemode for am335x

TRM "Table 13-34. SYSCONFIG Register Field Descriptions" lists both
standbymode and idlemode that should be just the sidle and midle
registers where midle is currently unconfigured for lcdc_sysc. As
the dts data has been generated based on lcdc_sysc, we now have an
empty "ti,sysc-midle" property.

And so we currently get a warning for lcdc because of a difference
with dts provided configuration compared to the legacy platform
data. This is because lcdc has SYSC_HAS_MIDLEMODE configured in
the platform data without configuring the modes.

Let's fix the issue by adding the missing midlemode to lcdc_sysc,
and configuring the "ti,sysc-midle" property based on the TRM
values.

Fixes: f711c575cfec ("ARM: dts: am335x: Add l4 interconnect hierarchy and ti-sysc data")
Cc: Jyri Sarha <jsarha@ti.com>
Cc: Keerthy <j-keerthy@ti.com>
Cc: Robert Nelson <robertcnelson@gmail.com>
Cc: Suman Anna <s-anna@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/boot/dts/am33xx-l4.dtsi           | 4 +++-
 arch/arm/mach-omap2/omap_hwmod_33xx_data.c | 5 +++--
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi
index 1515f4f91499..3287cf695b5a 100644
--- a/arch/arm/boot/dts/am33xx-l4.dtsi
+++ b/arch/arm/boot/dts/am33xx-l4.dtsi
@@ -2038,7 +2038,9 @@
 			reg = <0xe000 0x4>,
 			      <0xe054 0x4>;
 			reg-names = "rev", "sysc";
-			ti,sysc-midle ;
+			ti,sysc-midle = <SYSC_IDLE_FORCE>,
+					<SYSC_IDLE_NO>,
+					<SYSC_IDLE_SMART>;
 			ti,sysc-sidle = <SYSC_IDLE_FORCE>,
 					<SYSC_IDLE_NO>,
 					<SYSC_IDLE_SMART>;
diff --git a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
index c965af275e34..81d9912f17c8 100644
--- a/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_33xx_data.c
@@ -231,8 +231,9 @@ static struct omap_hwmod am33xx_control_hwmod = {
 static struct omap_hwmod_class_sysconfig lcdc_sysc = {
 	.rev_offs	= 0x0,
 	.sysc_offs	= 0x54,
-	.sysc_flags	= (SYSC_HAS_SIDLEMODE | SYSC_HAS_MIDLEMODE),
-	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
+	.sysc_flags	= SYSC_HAS_SIDLEMODE | SYSC_HAS_MIDLEMODE,
+	.idlemodes	= SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
+			  MSTANDBY_FORCE | MSTANDBY_NO | MSTANDBY_SMART,
 	.sysc_fields	= &omap_hwmod_sysc_type2,
 };
 
-- 
cgit v1.2.3


From cf395f7ddb9ebc6b2d28d83b53d18aa4e7c19701 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 24 Sep 2019 16:19:00 -0700
Subject: ARM: OMAP2+: Fix warnings with broken omap2_set_init_voltage()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This code is currently unable to find the dts opp tables as ti-cpufreq
needs to set them up first based on speed binning.

We stopped initializing the opp tables with platform code years ago for
device tree based booting with commit 92d51856d740 ("ARM: OMAP3+: do not
register non-dt OPP tables for device tree boot"), and all of mach-omap2
is now booting using device tree.

We currently get the following errors on init:

omap2_set_init_voltage: unable to find boot up OPP for vdd_mpu
omap2_set_init_voltage: unable to set vdd_mpu
omap2_set_init_voltage: unable to find boot up OPP for vdd_core
omap2_set_init_voltage: unable to set vdd_core
omap2_set_init_voltage: unable to find boot up OPP for vdd_iva
omap2_set_init_voltage: unable to set vdd_iva

Let's just drop the unused code. Nowadays ti-cpufreq should be used to
to initialize things properly.

Cc: Adam Ford <aford173@gmail.com>
Cc: André Roth <neolynx@gmail.com>
Cc: "H. Nikolaus Schaller" <hns@goldelico.com>
Cc: Nishanth Menon <nm@ti.com>
Cc: Tero Kristo <t-kristo@ti.com>
Tested-by: Adam Ford <aford173@gmail.com> #logicpd-torpedo-37xx-devkit
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/mach-omap2/pm.c | 100 -----------------------------------------------
 1 file changed, 100 deletions(-)

diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 1fde1bf53fb6..7ac9af56762d 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -74,83 +74,6 @@ int omap_pm_clkdms_setup(struct clockdomain *clkdm, void *unused)
 	return 0;
 }
 
-/*
- * This API is to be called during init to set the various voltage
- * domains to the voltage as per the opp table. Typically we boot up
- * at the nominal voltage. So this function finds out the rate of
- * the clock associated with the voltage domain, finds out the correct
- * opp entry and sets the voltage domain to the voltage specified
- * in the opp entry
- */
-static int __init omap2_set_init_voltage(char *vdd_name, char *clk_name,
-					 const char *oh_name)
-{
-	struct voltagedomain *voltdm;
-	struct clk *clk;
-	struct dev_pm_opp *opp;
-	unsigned long freq, bootup_volt;
-	struct device *dev;
-
-	if (!vdd_name || !clk_name || !oh_name) {
-		pr_err("%s: invalid parameters\n", __func__);
-		goto exit;
-	}
-
-	if (!strncmp(oh_name, "mpu", 3))
-		/* 
-		 * All current OMAPs share voltage rail and clock
-		 * source, so CPU0 is used to represent the MPU-SS.
-		 */
-		dev = get_cpu_device(0);
-	else
-		dev = omap_device_get_by_hwmod_name(oh_name);
-
-	if (IS_ERR(dev)) {
-		pr_err("%s: Unable to get dev pointer for hwmod %s\n",
-			__func__, oh_name);
-		goto exit;
-	}
-
-	voltdm = voltdm_lookup(vdd_name);
-	if (!voltdm) {
-		pr_err("%s: unable to get vdd pointer for vdd_%s\n",
-			__func__, vdd_name);
-		goto exit;
-	}
-
-	clk =  clk_get(NULL, clk_name);
-	if (IS_ERR(clk)) {
-		pr_err("%s: unable to get clk %s\n", __func__, clk_name);
-		goto exit;
-	}
-
-	freq = clk_get_rate(clk);
-	clk_put(clk);
-
-	opp = dev_pm_opp_find_freq_ceil(dev, &freq);
-	if (IS_ERR(opp)) {
-		pr_err("%s: unable to find boot up OPP for vdd_%s\n",
-			__func__, vdd_name);
-		goto exit;
-	}
-
-	bootup_volt = dev_pm_opp_get_voltage(opp);
-	dev_pm_opp_put(opp);
-
-	if (!bootup_volt) {
-		pr_err("%s: unable to find voltage corresponding to the bootup OPP for vdd_%s\n",
-		       __func__, vdd_name);
-		goto exit;
-	}
-
-	voltdm_scale(voltdm, bootup_volt);
-	return 0;
-
-exit:
-	pr_err("%s: unable to set vdd_%s\n", __func__, vdd_name);
-	return -EINVAL;
-}
-
 #ifdef CONFIG_SUSPEND
 static int omap_pm_enter(suspend_state_t suspend_state)
 {
@@ -208,25 +131,6 @@ void omap_common_suspend_init(void *pm_suspend)
 }
 #endif /* CONFIG_SUSPEND */
 
-static void __init omap3_init_voltages(void)
-{
-	if (!soc_is_omap34xx())
-		return;
-
-	omap2_set_init_voltage("mpu_iva", "dpll1_ck", "mpu");
-	omap2_set_init_voltage("core", "l3_ick", "l3_main");
-}
-
-static void __init omap4_init_voltages(void)
-{
-	if (!soc_is_omap44xx())
-		return;
-
-	omap2_set_init_voltage("mpu", "dpll_mpu_ck", "mpu");
-	omap2_set_init_voltage("core", "l3_div_ck", "l3_main_1");
-	omap2_set_init_voltage("iva", "dpll_iva_m5x2_ck", "iva");
-}
-
 int __maybe_unused omap_pm_nop_init(void)
 {
 	return 0;
@@ -246,10 +150,6 @@ int __init omap2_common_pm_late_init(void)
 	omap4_twl_init();
 	omap_voltage_late_init();
 
-	/* Initialize the voltages */
-	omap3_init_voltages();
-	omap4_init_voltages();
-
 	/* Smartreflex device init */
 	omap_devinit_smartreflex();
 
-- 
cgit v1.2.3


From f9d4eae25d93a76f8ed52b1519cc27c5b3cb1dcb Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 25 Sep 2019 14:08:45 +0100
Subject: drm/i915/execlists: Simplify gen12_csb_parse

Having decided that we only care about the promotion predicate, we can
simplify gen12_csb_parse to simply check whether we need to jump to a
new queue.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190925130845.17952-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index caac091b3eb9..ab725a6ca0ac 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1801,9 +1801,6 @@ gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
 	bool ctx_away_valid = GEN12_CSB_CTX_VALID(upper_dw);
 	bool new_queue = lower_dw & GEN12_CTX_STATUS_SWITCHED_TO_NEW_QUEUE;
 
-	if (!ctx_away_valid && ctx_to_valid)
-		return true;
-
 	/*
 	 * The context switch detail is not guaranteed to be 5 when a preemption
 	 * occurs, so we can't just check for that. The check below works for
@@ -1811,8 +1808,10 @@ gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
 	 * instructions and lite-restore. Preempt-to-idle via the CTRL register
 	 * would require some extra handling, but we don't support that.
 	 */
-	if (new_queue && ctx_away_valid)
+	if (!ctx_away_valid || new_queue) {
+		GEM_BUG_ON(!ctx_to_valid);
 		return true;
+	}
 
 	/*
 	 * switch detail = 5 is covered by the case above and we do not expect a
@@ -1820,7 +1819,6 @@ gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
 	 * use polling mode.
 	 */
 	GEM_BUG_ON(GEN12_CTX_SWITCH_DETAIL(upper_dw));
-
 	return false;
 }
 
-- 
cgit v1.2.3


From 1e225a2c7477f114f271403ce48b26dd7bc1da2c Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Tue, 24 Sep 2019 14:00:35 -0700
Subject: drm/i915/tgl: Add initial dkl pll support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The disable function can be the same as for MG phy since the same
registers are used. The others are different as registers changed,
also adding a empty dkl_pll_write() to be implemented later.

v2:
Setting the right HIP_INDEX_REG bits (José)

v3:
Masking non-computed registers of mg_pll_tdc_coldst_bias
when getting hardware state
Sharing mg_pll_enable() with TGL

Reviewed-by: Imre Deak <imre.deak@intel.com>
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190924210040.142075-1-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_dpll_mgr.c | 96 ++++++++++++++++++++++++++-
 1 file changed, 94 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 84e734d44828..1d56027be12c 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -3086,6 +3086,78 @@ out:
 	return ret;
 }
 
+static bool dkl_pll_get_hw_state(struct drm_i915_private *dev_priv,
+				 struct intel_shared_dpll *pll,
+				 struct intel_dpll_hw_state *hw_state)
+{
+	const enum intel_dpll_id id = pll->info->id;
+	enum tc_port tc_port = icl_pll_id_to_tc_port(id);
+	intel_wakeref_t wakeref;
+	bool ret = false;
+	u32 val;
+
+	wakeref = intel_display_power_get_if_enabled(dev_priv,
+						     POWER_DOMAIN_DISPLAY_CORE);
+	if (!wakeref)
+		return false;
+
+	val = I915_READ(MG_PLL_ENABLE(tc_port));
+	if (!(val & PLL_ENABLE))
+		goto out;
+
+	/*
+	 * All registers read here have the same HIP_INDEX_REG even though
+	 * they are on different building blocks
+	 */
+	I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, 0x2));
+
+	hw_state->mg_refclkin_ctl = I915_READ(DKL_REFCLKIN_CTL(tc_port));
+	hw_state->mg_refclkin_ctl &= MG_REFCLKIN_CTL_OD_2_MUX_MASK;
+
+	hw_state->mg_clktop2_hsclkctl =
+		I915_READ(DKL_CLKTOP2_HSCLKCTL(tc_port));
+	hw_state->mg_clktop2_hsclkctl &=
+		MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK |
+		MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK |
+		MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK |
+		MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK;
+
+	hw_state->mg_clktop2_coreclkctl1 =
+		I915_READ(DKL_CLKTOP2_CORECLKCTL1(tc_port));
+	hw_state->mg_clktop2_coreclkctl1 &=
+		MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
+
+	hw_state->mg_pll_div0 = I915_READ(DKL_PLL_DIV0(tc_port));
+	hw_state->mg_pll_div0 &= (DKL_PLL_DIV0_INTEG_COEFF_MASK |
+				  DKL_PLL_DIV0_PROP_COEFF_MASK |
+				  DKL_PLL_DIV0_FBPREDIV_MASK |
+				  DKL_PLL_DIV0_FBDIV_INT_MASK);
+
+	hw_state->mg_pll_div1 = I915_READ(DKL_PLL_DIV1(tc_port));
+	hw_state->mg_pll_div1 &= (DKL_PLL_DIV1_IREF_TRIM_MASK |
+				  DKL_PLL_DIV1_TDC_TARGET_CNT_MASK);
+
+	hw_state->mg_pll_ssc = I915_READ(DKL_PLL_SSC(tc_port));
+	hw_state->mg_pll_ssc &= (DKL_PLL_SSC_IREF_NDIV_RATIO_MASK |
+				 DKL_PLL_SSC_STEP_LEN_MASK |
+				 DKL_PLL_SSC_STEP_NUM_MASK |
+				 DKL_PLL_SSC_EN);
+
+	hw_state->mg_pll_bias = I915_READ(DKL_PLL_BIAS(tc_port));
+	hw_state->mg_pll_bias &= (DKL_PLL_BIAS_FRAC_EN_H |
+				  DKL_PLL_BIAS_FBDIV_FRAC_MASK);
+
+	hw_state->mg_pll_tdc_coldst_bias =
+		I915_READ(DKL_PLL_TDC_COLDST_BIAS(tc_port));
+	hw_state->mg_pll_tdc_coldst_bias &= (DKL_PLL_TDC_SSC_STEP_SIZE_MASK |
+					     DKL_PLL_TDC_FEED_FWD_GAIN_MASK);
+
+	ret = true;
+out:
+	intel_display_power_put(dev_priv, POWER_DOMAIN_DISPLAY_CORE, wakeref);
+	return ret;
+}
+
 static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 				 struct intel_shared_dpll *pll,
 				 struct intel_dpll_hw_state *hw_state,
@@ -3220,6 +3292,12 @@ static void icl_mg_pll_write(struct drm_i915_private *dev_priv,
 	POSTING_READ(MG_PLL_TDC_COLDST_BIAS(tc_port));
 }
 
+static void dkl_pll_write(struct drm_i915_private *dev_priv,
+			  struct intel_shared_dpll *pll)
+{
+	/* TODO */
+}
+
 static void icl_pll_power_enable(struct drm_i915_private *dev_priv,
 				 struct intel_shared_dpll *pll,
 				 i915_reg_t enable_reg)
@@ -3312,7 +3390,10 @@ static void mg_pll_enable(struct drm_i915_private *dev_priv,
 
 	icl_pll_power_enable(dev_priv, pll, enable_reg);
 
-	icl_mg_pll_write(dev_priv, pll);
+	if (INTEL_GEN(dev_priv) >= 12)
+		dkl_pll_write(dev_priv, pll);
+	else
+		icl_mg_pll_write(dev_priv, pll);
 
 	/*
 	 * DVFS pre sequence would be here, but in our driver the cdclk code
@@ -3467,11 +3548,22 @@ static const struct intel_dpll_mgr ehl_pll_mgr = {
 	.dump_hw_state = icl_dump_hw_state,
 };
 
+static const struct intel_shared_dpll_funcs dkl_pll_funcs = {
+	.enable = mg_pll_enable,
+	.disable = mg_pll_disable,
+	.get_hw_state = dkl_pll_get_hw_state,
+};
+
 static const struct dpll_info tgl_plls[] = {
 	{ "DPLL 0", &combo_pll_funcs, DPLL_ID_ICL_DPLL0,  0 },
 	{ "DPLL 1", &combo_pll_funcs, DPLL_ID_ICL_DPLL1,  0 },
 	{ "TBT PLL",  &tbt_pll_funcs, DPLL_ID_ICL_TBTPLL, 0 },
-	/* TODO: Add typeC plls */
+	{ "TC PLL 1", &dkl_pll_funcs, DPLL_ID_ICL_MGPLL1, 0 },
+	{ "TC PLL 2", &dkl_pll_funcs, DPLL_ID_ICL_MGPLL2, 0 },
+	{ "TC PLL 3", &dkl_pll_funcs, DPLL_ID_ICL_MGPLL3, 0 },
+	{ "TC PLL 4", &dkl_pll_funcs, DPLL_ID_ICL_MGPLL4, 0 },
+	{ "TC PLL 5", &dkl_pll_funcs, DPLL_ID_TGL_MGPLL5, 0 },
+	{ "TC PLL 6", &dkl_pll_funcs, DPLL_ID_TGL_MGPLL6, 0 },
 	{ },
 };
 
-- 
cgit v1.2.3


From e87b9b05104f5dc2d1529d2b8fb2574e332d43e5 Mon Sep 17 00:00:00 2001
From: Vandita Kulkarni <vandita.kulkarni@intel.com>
Date: Tue, 24 Sep 2019 14:00:36 -0700
Subject: drm/i915/tgl: Add support for dkl pll write
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a new function to write to dkl phy pll registers. As per the
bspec all the registers are read modify write.

Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Vandita Kulkarni <vandita.kulkarni@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190924210040.142075-2-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_dpll_mgr.c | 65 ++++++++++++++++++++++++++-
 1 file changed, 64 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 1d56027be12c..114116cdbf49 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -3295,7 +3295,70 @@ static void icl_mg_pll_write(struct drm_i915_private *dev_priv,
 static void dkl_pll_write(struct drm_i915_private *dev_priv,
 			  struct intel_shared_dpll *pll)
 {
-	/* TODO */
+	struct intel_dpll_hw_state *hw_state = &pll->state.hw_state;
+	enum tc_port tc_port = icl_pll_id_to_tc_port(pll->info->id);
+	u32 val;
+
+	/*
+	 * All registers programmed here have the same HIP_INDEX_REG even
+	 * though on different building block
+	 */
+	I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, 0x2));
+
+	/* All the registers are RMW */
+	val = I915_READ(DKL_REFCLKIN_CTL(tc_port));
+	val &= ~MG_REFCLKIN_CTL_OD_2_MUX_MASK;
+	val |= hw_state->mg_refclkin_ctl;
+	I915_WRITE(DKL_REFCLKIN_CTL(tc_port), val);
+
+	val = I915_READ(DKL_CLKTOP2_CORECLKCTL1(tc_port));
+	val &= ~MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
+	val |= hw_state->mg_clktop2_coreclkctl1;
+	I915_WRITE(DKL_CLKTOP2_CORECLKCTL1(tc_port), val);
+
+	val = I915_READ(DKL_CLKTOP2_HSCLKCTL(tc_port));
+	val &= ~(MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK |
+		 MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK |
+		 MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK |
+		 MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK);
+	val |= hw_state->mg_clktop2_hsclkctl;
+	I915_WRITE(DKL_CLKTOP2_HSCLKCTL(tc_port), val);
+
+	val = I915_READ(DKL_PLL_DIV0(tc_port));
+	val &= ~(DKL_PLL_DIV0_INTEG_COEFF_MASK |
+		 DKL_PLL_DIV0_PROP_COEFF_MASK |
+		 DKL_PLL_DIV0_FBPREDIV_MASK |
+		 DKL_PLL_DIV0_FBDIV_INT_MASK);
+	val |= hw_state->mg_pll_div0;
+	I915_WRITE(DKL_PLL_DIV0(tc_port), val);
+
+	val = I915_READ(DKL_PLL_DIV1(tc_port));
+	val &= ~(DKL_PLL_DIV1_IREF_TRIM_MASK |
+		 DKL_PLL_DIV1_TDC_TARGET_CNT_MASK);
+	val |= hw_state->mg_pll_div1;
+	I915_WRITE(DKL_PLL_DIV1(tc_port), val);
+
+	val = I915_READ(DKL_PLL_SSC(tc_port));
+	val &= ~(DKL_PLL_SSC_IREF_NDIV_RATIO_MASK |
+		 DKL_PLL_SSC_STEP_LEN_MASK |
+		 DKL_PLL_SSC_STEP_NUM_MASK |
+		 DKL_PLL_SSC_EN);
+	val |= hw_state->mg_pll_ssc;
+	I915_WRITE(DKL_PLL_SSC(tc_port), val);
+
+	val = I915_READ(DKL_PLL_BIAS(tc_port));
+	val &= ~(DKL_PLL_BIAS_FRAC_EN_H |
+		 DKL_PLL_BIAS_FBDIV_FRAC_MASK);
+	val |= hw_state->mg_pll_bias;
+	I915_WRITE(DKL_PLL_BIAS(tc_port), val);
+
+	val = I915_READ(DKL_PLL_TDC_COLDST_BIAS(tc_port));
+	val &= ~(DKL_PLL_TDC_SSC_STEP_SIZE_MASK |
+		 DKL_PLL_TDC_FEED_FWD_GAIN_MASK);
+	val |= hw_state->mg_pll_tdc_coldst_bias;
+	I915_WRITE(DKL_PLL_TDC_COLDST_BIAS(tc_port), val);
+
+	POSTING_READ(DKL_PLL_TDC_COLDST_BIAS(tc_port));
 }
 
 static void icl_pll_power_enable(struct drm_i915_private *dev_priv,
-- 
cgit v1.2.3


From 1a5c6aa43a3ae95bb4756c8a906a32519a6d291d Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Tue, 24 Sep 2019 14:00:38 -0700
Subject: drm/i915/tgl: re-indent code to prepare for DKL changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The final save operation into pll_state of the calculations done will
be different for DKL PHY. Prepare for that by reindenting code so it's
easier to check for correctness. This one has no change in behavior.

Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190924210040.142075-4-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_dpll_mgr.c | 119 ++++++++++++++------------
 1 file changed, 66 insertions(+), 53 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 114116cdbf49..ce2dee38c956 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -2786,60 +2786,73 @@ static bool icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state,
 	}
 	ssc_steplog = 4;
 
-	pll_state->mg_pll_div0 = (m2div_rem > 0 ? MG_PLL_DIV0_FRACNEN_H : 0) |
-				  MG_PLL_DIV0_FBDIV_FRAC(m2div_frac) |
-				  MG_PLL_DIV0_FBDIV_INT(m2div_int);
-
-	pll_state->mg_pll_div1 = MG_PLL_DIV1_IREF_NDIVRATIO(iref_ndiv) |
-				 MG_PLL_DIV1_DITHER_DIV_2 |
-				 MG_PLL_DIV1_NDIVRATIO(1) |
-				 MG_PLL_DIV1_FBPREDIV(m1div);
-
-	pll_state->mg_pll_lf = MG_PLL_LF_TDCTARGETCNT(tdc_targetcnt) |
-			       MG_PLL_LF_AFCCNTSEL_512 |
-			       MG_PLL_LF_GAINCTRL(1) |
-			       MG_PLL_LF_INT_COEFF(int_coeff) |
-			       MG_PLL_LF_PROP_COEFF(prop_coeff);
-
-	pll_state->mg_pll_frac_lock = MG_PLL_FRAC_LOCK_TRUELOCK_CRIT_32 |
-				      MG_PLL_FRAC_LOCK_EARLYLOCK_CRIT_32 |
-				      MG_PLL_FRAC_LOCK_LOCKTHRESH(10) |
-				      MG_PLL_FRAC_LOCK_DCODITHEREN |
-				      MG_PLL_FRAC_LOCK_FEEDFWRDGAIN(feedfwgain);
-	if (use_ssc || m2div_rem > 0)
-		pll_state->mg_pll_frac_lock |= MG_PLL_FRAC_LOCK_FEEDFWRDCAL_EN;
-
-	pll_state->mg_pll_ssc = (use_ssc ? MG_PLL_SSC_EN : 0) |
-				MG_PLL_SSC_TYPE(2) |
-				MG_PLL_SSC_STEPLENGTH(ssc_steplen) |
-				MG_PLL_SSC_STEPNUM(ssc_steplog) |
-				MG_PLL_SSC_FLLEN |
-				MG_PLL_SSC_STEPSIZE(ssc_stepsize);
-
-	pll_state->mg_pll_tdc_coldst_bias = MG_PLL_TDC_COLDST_COLDSTART |
-					    MG_PLL_TDC_COLDST_IREFINT_EN |
-					    MG_PLL_TDC_COLDST_REFBIAS_START_PULSE_W(iref_pulse_w) |
-					    MG_PLL_TDC_TDCOVCCORR_EN |
-					    MG_PLL_TDC_TDCSEL(3);
-
-	pll_state->mg_pll_bias = MG_PLL_BIAS_BIAS_GB_SEL(3) |
-				 MG_PLL_BIAS_INIT_DCOAMP(0x3F) |
-				 MG_PLL_BIAS_BIAS_BONUS(10) |
-				 MG_PLL_BIAS_BIASCAL_EN |
-				 MG_PLL_BIAS_CTRIM(12) |
-				 MG_PLL_BIAS_VREF_RDAC(4) |
-				 MG_PLL_BIAS_IREFTRIM(iref_trim);
-
-	if (refclk_khz == 38400) {
-		pll_state->mg_pll_tdc_coldst_bias_mask = MG_PLL_TDC_COLDST_COLDSTART;
-		pll_state->mg_pll_bias_mask = 0;
-	} else {
-		pll_state->mg_pll_tdc_coldst_bias_mask = -1U;
-		pll_state->mg_pll_bias_mask = -1U;
-	}
+	/* write pll_state calculations */
+	{
+		pll_state->mg_pll_div0 =
+			(m2div_rem > 0 ? MG_PLL_DIV0_FRACNEN_H : 0) |
+			MG_PLL_DIV0_FBDIV_FRAC(m2div_frac) |
+			MG_PLL_DIV0_FBDIV_INT(m2div_int);
+
+		pll_state->mg_pll_div1 =
+			MG_PLL_DIV1_IREF_NDIVRATIO(iref_ndiv) |
+			MG_PLL_DIV1_DITHER_DIV_2 |
+			MG_PLL_DIV1_NDIVRATIO(1) |
+			MG_PLL_DIV1_FBPREDIV(m1div);
+
+		pll_state->mg_pll_lf =
+			MG_PLL_LF_TDCTARGETCNT(tdc_targetcnt) |
+			MG_PLL_LF_AFCCNTSEL_512 |
+			MG_PLL_LF_GAINCTRL(1) |
+			MG_PLL_LF_INT_COEFF(int_coeff) |
+			MG_PLL_LF_PROP_COEFF(prop_coeff);
+
+		pll_state->mg_pll_frac_lock =
+			MG_PLL_FRAC_LOCK_TRUELOCK_CRIT_32 |
+			MG_PLL_FRAC_LOCK_EARLYLOCK_CRIT_32 |
+			MG_PLL_FRAC_LOCK_LOCKTHRESH(10) |
+			MG_PLL_FRAC_LOCK_DCODITHEREN |
+			MG_PLL_FRAC_LOCK_FEEDFWRDGAIN(feedfwgain);
+		if (use_ssc || m2div_rem > 0)
+			pll_state->mg_pll_frac_lock |=
+				MG_PLL_FRAC_LOCK_FEEDFWRDCAL_EN;
+
+		pll_state->mg_pll_ssc =
+			(use_ssc ? MG_PLL_SSC_EN : 0) |
+			MG_PLL_SSC_TYPE(2) |
+			MG_PLL_SSC_STEPLENGTH(ssc_steplen) |
+			MG_PLL_SSC_STEPNUM(ssc_steplog) |
+			MG_PLL_SSC_FLLEN |
+			MG_PLL_SSC_STEPSIZE(ssc_stepsize);
+
+		pll_state->mg_pll_tdc_coldst_bias =
+			MG_PLL_TDC_COLDST_COLDSTART |
+			MG_PLL_TDC_COLDST_IREFINT_EN |
+			MG_PLL_TDC_COLDST_REFBIAS_START_PULSE_W(iref_pulse_w) |
+			MG_PLL_TDC_TDCOVCCORR_EN |
+			MG_PLL_TDC_TDCSEL(3);
+
+		pll_state->mg_pll_bias =
+			MG_PLL_BIAS_BIAS_GB_SEL(3) |
+			MG_PLL_BIAS_INIT_DCOAMP(0x3F) |
+			MG_PLL_BIAS_BIAS_BONUS(10) |
+			MG_PLL_BIAS_BIASCAL_EN |
+			MG_PLL_BIAS_CTRIM(12) |
+			MG_PLL_BIAS_VREF_RDAC(4) |
+			MG_PLL_BIAS_IREFTRIM(iref_trim);
+
+		if (refclk_khz == 38400) {
+			pll_state->mg_pll_tdc_coldst_bias_mask =
+				MG_PLL_TDC_COLDST_COLDSTART;
+			pll_state->mg_pll_bias_mask = 0;
+		} else {
+			pll_state->mg_pll_tdc_coldst_bias_mask = -1U;
+			pll_state->mg_pll_bias_mask = -1U;
+		}
 
-	pll_state->mg_pll_tdc_coldst_bias &= pll_state->mg_pll_tdc_coldst_bias_mask;
-	pll_state->mg_pll_bias &= pll_state->mg_pll_bias_mask;
+		pll_state->mg_pll_tdc_coldst_bias &=
+			pll_state->mg_pll_tdc_coldst_bias_mask;
+		pll_state->mg_pll_bias &= pll_state->mg_pll_bias_mask;
+	}
 
 	return true;
 }
-- 
cgit v1.2.3


From ee7de6ad382d8d0fcf5bdb7443c7bc1f55e9d0f5 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Tue, 24 Sep 2019 14:00:39 -0700
Subject: drm/i915/tgl: Add dkl phy pll calculations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extending ICL mg calculations to also support dkl calculations.

v3:
Fixing iref_trim calculation for 38400 refclock

BSpec: 49204

Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Vandita Kulkarni <vandita.kulkarni@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190924210040.142075-5-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c      | 29 ++++++++++++++---
 drivers/gpu/drm/i915/display/intel_dpll_mgr.c | 45 ++++++++++++++++++++++-----
 2 files changed, 62 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 14fe987888a6..c06353ae0d12 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -1413,11 +1413,30 @@ static int icl_calc_mg_pll_link(struct drm_i915_private *dev_priv,
 
 	ref_clock = dev_priv->cdclk.hw.ref;
 
-	m1 = pll_state->mg_pll_div1 & MG_PLL_DIV1_FBPREDIV_MASK;
-	m2_int = pll_state->mg_pll_div0 & MG_PLL_DIV0_FBDIV_INT_MASK;
-	m2_frac = (pll_state->mg_pll_div0 & MG_PLL_DIV0_FRACNEN_H) ?
-		(pll_state->mg_pll_div0 & MG_PLL_DIV0_FBDIV_FRAC_MASK) >>
-		MG_PLL_DIV0_FBDIV_FRAC_SHIFT : 0;
+	if (INTEL_GEN(dev_priv) >= 12) {
+		m1 = pll_state->mg_pll_div0 & DKL_PLL_DIV0_FBPREDIV_MASK;
+		m1 = m1 >> DKL_PLL_DIV0_FBPREDIV_SHIFT;
+		m2_int = pll_state->mg_pll_div0 & DKL_PLL_DIV0_FBDIV_INT_MASK;
+
+		if (pll_state->mg_pll_bias & DKL_PLL_BIAS_FRAC_EN_H) {
+			m2_frac = pll_state->mg_pll_bias &
+				  DKL_PLL_BIAS_FBDIV_FRAC_MASK;
+			m2_frac = m2_frac >> DKL_PLL_BIAS_FBDIV_SHIFT;
+		} else {
+			m2_frac = 0;
+		}
+	} else {
+		m1 = pll_state->mg_pll_div1 & MG_PLL_DIV1_FBPREDIV_MASK;
+		m2_int = pll_state->mg_pll_div0 & MG_PLL_DIV0_FBDIV_INT_MASK;
+
+		if (pll_state->mg_pll_div0 & MG_PLL_DIV0_FRACNEN_H) {
+			m2_frac = pll_state->mg_pll_div0 &
+				  MG_PLL_DIV0_FBDIV_FRAC_MASK;
+			m2_frac = m2_frac >> MG_PLL_DIV0_FBDIV_FRAC_SHIFT;
+		} else {
+			m2_frac = 0;
+		}
+	}
 
 	switch (pll_state->mg_clktop2_hsclkctl &
 		MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK) {
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index ce2dee38c956..69abafa45ce9 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -2607,7 +2607,8 @@ enum intel_dpll_id icl_tc_port_to_pll_id(enum tc_port tc_port)
 
 static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc,
 				     u32 *target_dco_khz,
-				     struct intel_dpll_hw_state *state)
+				     struct intel_dpll_hw_state *state,
+				     bool is_dkl)
 {
 	u32 dco_min_freq, dco_max_freq;
 	int div1_vals[] = {7, 5, 3, 2};
@@ -2629,8 +2630,13 @@ static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc,
 				continue;
 
 			if (div2 >= 2) {
-				a_divratio = is_dp ? 10 : 5;
-				tlinedrv = 2;
+				if (is_dkl) {
+					a_divratio = 5;
+					tlinedrv = 1;
+				} else {
+					a_divratio = is_dp ? 10 : 5;
+					tlinedrv = 2;
+				}
 			} else {
 				a_divratio = 5;
 				tlinedrv = 0;
@@ -2693,11 +2699,12 @@ static bool icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state,
 	u64 tmp;
 	bool use_ssc = false;
 	bool is_dp = !intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI);
+	bool is_dkl = INTEL_GEN(dev_priv) >= 12;
 
 	memset(pll_state, 0, sizeof(*pll_state));
 
 	if (!icl_mg_pll_find_divisors(clock, is_dp, use_ssc, &dco_khz,
-				      pll_state)) {
+				      pll_state, is_dkl)) {
 		DRM_DEBUG_KMS("Failed to find divisors for clock %d\n", clock);
 		return false;
 	}
@@ -2705,8 +2712,11 @@ static bool icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state,
 	m1div = 2;
 	m2div_int = dco_khz / (refclk_khz * m1div);
 	if (m2div_int > 255) {
-		m1div = 4;
-		m2div_int = dco_khz / (refclk_khz * m1div);
+		if (!is_dkl) {
+			m1div = 4;
+			m2div_int = dco_khz / (refclk_khz * m1div);
+		}
+
 		if (m2div_int > 255) {
 			DRM_DEBUG_KMS("Failed to find mdiv for clock %d\n",
 				      clock);
@@ -2787,7 +2797,28 @@ static bool icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state,
 	ssc_steplog = 4;
 
 	/* write pll_state calculations */
-	{
+	if (is_dkl) {
+		pll_state->mg_pll_div0 = DKL_PLL_DIV0_INTEG_COEFF(int_coeff) |
+					 DKL_PLL_DIV0_PROP_COEFF(prop_coeff) |
+					 DKL_PLL_DIV0_FBPREDIV(m1div) |
+					 DKL_PLL_DIV0_FBDIV_INT(m2div_int);
+
+		pll_state->mg_pll_div1 = DKL_PLL_DIV1_IREF_TRIM(iref_trim) |
+					 DKL_PLL_DIV1_TDC_TARGET_CNT(tdc_targetcnt);
+
+		pll_state->mg_pll_ssc = DKL_PLL_SSC_IREF_NDIV_RATIO(iref_ndiv) |
+					DKL_PLL_SSC_STEP_LEN(ssc_steplen) |
+					DKL_PLL_SSC_STEP_NUM(ssc_steplog) |
+					(use_ssc ? DKL_PLL_SSC_EN : 0);
+
+		pll_state->mg_pll_bias = (m2div_frac ? DKL_PLL_BIAS_FRAC_EN_H : 0) |
+					  DKL_PLL_BIAS_FBDIV_FRAC(m2div_frac);
+
+		pll_state->mg_pll_tdc_coldst_bias =
+				DKL_PLL_TDC_SSC_STEP_SIZE(ssc_stepsize) |
+				DKL_PLL_TDC_FEED_FWD_GAIN(feedfwgain);
+
+	} else {
 		pll_state->mg_pll_div0 =
 			(m2div_rem > 0 ? MG_PLL_DIV0_FRACNEN_H : 0) |
 			MG_PLL_DIV0_FBDIV_FRAC(m2div_frac) |
-- 
cgit v1.2.3


From 6677c3b167b3ba9fa183015f6244e2db28d99f29 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Tue, 24 Sep 2019 14:00:40 -0700
Subject: drm/i915/tgl: Return the mg/dkl pll as DDI clock for new TC ports
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

TGL added 2 more TC ports that currently are not being handled by
icl_pll_to_ddi_clk_sel(), so adding those.

Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Reported-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190924210040.142075-6-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index c06353ae0d12..aa470c70a198 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -1049,6 +1049,8 @@ static u32 icl_pll_to_ddi_clk_sel(struct intel_encoder *encoder,
 	case DPLL_ID_ICL_MGPLL2:
 	case DPLL_ID_ICL_MGPLL3:
 	case DPLL_ID_ICL_MGPLL4:
+	case DPLL_ID_TGL_MGPLL5:
+	case DPLL_ID_TGL_MGPLL6:
 		return DDI_CLK_SEL_MG;
 	}
 }
-- 
cgit v1.2.3


From ddef29578a81a1d4d8f2b26a7adbfe21407ee3ea Mon Sep 17 00:00:00 2001
From: "Wunderlich, Mark" <mark.wunderlich@intel.com>
Date: Wed, 18 Sep 2019 23:36:37 +0000
Subject: nvme-tcp: fix wrong stop condition in io_work

Allow the do/while statement to continue if current time
is not after the proposed time 'deadline'. Intent is to
allow loop to proceed for a specific time period. Currently
the loop, as coded, will exit after first pass.

Signed-off-by: Mark Wunderlich <mark.wunderlich@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/tcp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 4ffd5957637a..385a5212c10f 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1042,7 +1042,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
 {
 	struct nvme_tcp_queue *queue =
 		container_of(w, struct nvme_tcp_queue, io_work);
-	unsigned long start = jiffies + msecs_to_jiffies(1);
+	unsigned long deadline = jiffies + msecs_to_jiffies(1);
 
 	do {
 		bool pending = false;
@@ -1067,7 +1067,7 @@ static void nvme_tcp_io_work(struct work_struct *w)
 		if (!pending)
 			return;
 
-	} while (time_after(jiffies, start)); /* quota is exhausted */
+	} while (!time_after(jiffies, deadline)); /* quota is exhausted */
 
 	queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
 }
-- 
cgit v1.2.3


From 7cbb5c6f9aa7cfda7175d82a9cf77a92965b0c5e Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@dell.com>
Date: Wed, 18 Sep 2019 13:15:55 -0500
Subject: nvme-pci: Save PCI state before putting drive into deepest state

The action of saving the PCI state will cause numerous PCI configuration
space reads which depending upon the vendor implementation may cause
the drive to exit the deepest NVMe state.

In these cases ASPM will typically resolve the PCIe link state and APST
may resolve the NVMe power state.  However it has also been observed
that this register access after quiesced will cause PC10 failure
on some device combinations.

To resolve this, move the PCI state saving to before SetFeatures has been
called.  This has been proven to resolve the issue across a 5000 sample
test on previously failing disk/system combinations.

Signed-off-by: Mario Limonciello <mario.limonciello@dell.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/pci.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 6b4d7b064b38..d3f63f0c212a 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2944,11 +2944,21 @@ static int nvme_suspend(struct device *dev)
 	if (ret < 0)
 		goto unfreeze;
 
+	/*
+	 * A saved state prevents pci pm from generically controlling the
+	 * device's power. If we're using protocol specific settings, we don't
+	 * want pci interfering.
+	 */
+	pci_save_state(pdev);
+
 	ret = nvme_set_power_state(ctrl, ctrl->npss);
 	if (ret < 0)
 		goto unfreeze;
 
 	if (ret) {
+		/* discard the saved state */
+		pci_load_saved_state(pdev, NULL);
+
 		/*
 		 * Clearing npss forces a controller reset on resume. The
 		 * correct value will be resdicovered then.
@@ -2956,14 +2966,7 @@ static int nvme_suspend(struct device *dev)
 		nvme_dev_disable(ndev, true);
 		ctrl->npss = 0;
 		ret = 0;
-		goto unfreeze;
 	}
-	/*
-	 * A saved state prevents pci pm from generically controlling the
-	 * device's power. If we're using protocol specific settings, we don't
-	 * want pci interfering.
-	 */
-	pci_save_state(pdev);
 unfreeze:
 	nvme_unfreeze(ctrl);
 	return ret;
-- 
cgit v1.2.3


From bc4f6e06a90ea016855fc67212b4d500145f0b8a Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 23 Sep 2019 17:18:36 +0300
Subject: nvme: fix an error code in nvme_init_subsystem()

"ret" should be a negative error code here, but it's either success or
possibly uninitialized.

Fixes: 32fd90c40768 ("nvme: change locking for the per-subsystem controller list")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/core.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 0c385b1994fe..d3c9df62a9d5 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2543,8 +2543,9 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 		list_add_tail(&subsys->entry, &nvme_subsystems);
 	}
 
-	if (sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
-			dev_name(ctrl->device))) {
+	ret = sysfs_create_link(&subsys->dev.kobj, &ctrl->device->kobj,
+				dev_name(ctrl->device));
+	if (ret) {
 		dev_err(ctrl->device,
 			"failed to create sysfs link from subsystem.\n");
 		goto out_put_subsystem;
-- 
cgit v1.2.3


From ff13c1b87c97275b82b2af99044b4abf6861b28f Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <maxg@mellanox.com>
Date: Sat, 21 Sep 2019 23:58:19 +0300
Subject: nvme-rdma: Fix max_hw_sectors calculation

By default, the NVMe/RDMA driver should support max io_size of 1MiB (or
upto the maximum supported size by the HCA). Currently, one will see that
/sys/class/block/<bdev>/queue/max_hw_sectors_kb is 1020 instead of 1024.

A non power of 2 value can cause performance degradation due to
unnecessary splitting of IO requests and unoptimized allocation units.

The number of pages per MR has been fixed here, so there is no longer any
need to reduce max_sectors by 1.

Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/rdma.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index dfa07bb9dfeb..9d16dfc29368 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -427,7 +427,7 @@ static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
 static int nvme_rdma_get_max_fr_pages(struct ib_device *ibdev)
 {
 	return min_t(u32, NVME_RDMA_MAX_SEGMENTS,
-		     ibdev->attrs.max_fast_reg_page_list_len);
+		     ibdev->attrs.max_fast_reg_page_list_len - 1);
 }
 
 static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
@@ -437,7 +437,7 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
 	const int cq_factor = send_wr_factor + 1;	/* + RECV */
 	int comp_vector, idx = nvme_rdma_queue_idx(queue);
 	enum ib_poll_context poll_ctx;
-	int ret;
+	int ret, pages_per_mr;
 
 	queue->device = nvme_rdma_find_get_device(queue->cm_id);
 	if (!queue->device) {
@@ -479,10 +479,16 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
 		goto out_destroy_qp;
 	}
 
+	/*
+	 * Currently we don't use SG_GAPS MR's so if the first entry is
+	 * misaligned we'll end up using two entries for a single data page,
+	 * so one additional entry is required.
+	 */
+	pages_per_mr = nvme_rdma_get_max_fr_pages(ibdev) + 1;
 	ret = ib_mr_pool_init(queue->qp, &queue->qp->rdma_mrs,
 			      queue->queue_size,
 			      IB_MR_TYPE_MEM_REG,
-			      nvme_rdma_get_max_fr_pages(ibdev), 0);
+			      pages_per_mr, 0);
 	if (ret) {
 		dev_err(queue->ctrl->ctrl.device,
 			"failed to initialize MR pool sized %d for QID %d\n",
@@ -820,8 +826,8 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
 	if (error)
 		goto out_stop_queue;
 
-	ctrl->ctrl.max_hw_sectors =
-		(ctrl->max_fr_pages - 1) << (ilog2(SZ_4K) - 9);
+	ctrl->ctrl.max_segments = ctrl->max_fr_pages;
+	ctrl->ctrl.max_hw_sectors = ctrl->max_fr_pages << (ilog2(SZ_4K) - 9);
 
 	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 
-- 
cgit v1.2.3


From f03e42c6af60f778a6d1ccfb857db9b2ec835279 Mon Sep 17 00:00:00 2001
From: Gabriel Craciunescu <nix.or.die@gmail.com>
Date: Mon, 23 Sep 2019 20:22:56 +0200
Subject: Added QUIRKs for ADATA XPG SX8200 Pro 512GB

Booting with default_ps_max_latency_us >6000 makes the device fail.
Also SUBNQN is NULL and gives a warning on each boot/resume.
 $ nvme id-ctrl /dev/nvme0 | grep ^subnqn
   subnqn    : (null)

I use this device with an Acer Nitro 5 (AN515-43-R8BF) Laptop.
To be sure is not a Laptop issue only, I tested the device on
my server board  with the same results.
( with 2x,4x link on the board and 4x link on a PCI-E card ).

Signed-off-by: Gabriel Craciunescu <nix.or.die@gmail.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/pci.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index d3f63f0c212a..7ab07f4dce83 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3091,6 +3091,9 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE(0x10ec, 0x5762),   /* ADATA SX6000LNP */
 		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+	{ PCI_DEVICE(0x1cc1, 0x8201),   /* ADATA SX8200PNP 512GB */
+		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
-- 
cgit v1.2.3


From 30f27d57c06e0199a9d3e0775113e13e2ae9078e Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Fri, 13 Sep 2019 10:36:40 -0700
Subject: nvmet-tcp: remove superflous check on request sgl

Now that sgl_free is null safe, drop the superflous check.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/target/tcp.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index bf4f03474e89..d535080b781f 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -348,8 +348,7 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
 
 	return 0;
 err:
-	if (cmd->req.sg_cnt)
-		sgl_free(cmd->req.sg);
+	sgl_free(cmd->req.sg);
 	return NVME_SC_INTERNAL;
 }
 
@@ -554,8 +553,7 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd)
 
 	if (queue->nvme_sq.sqhd_disabled) {
 		kfree(cmd->iov);
-		if (cmd->req.sg_cnt)
-			sgl_free(cmd->req.sg);
+		sgl_free(cmd->req.sg);
 	}
 
 	return 1;
@@ -586,8 +584,7 @@ static int nvmet_try_send_response(struct nvmet_tcp_cmd *cmd,
 		return -EAGAIN;
 
 	kfree(cmd->iov);
-	if (cmd->req.sg_cnt)
-		sgl_free(cmd->req.sg);
+	sgl_free(cmd->req.sg);
 	cmd->queue->snd_cmd = NULL;
 	nvmet_tcp_put_cmd(cmd);
 	return 1;
@@ -1310,8 +1307,7 @@ static void nvmet_tcp_finish_cmd(struct nvmet_tcp_cmd *cmd)
 	nvmet_req_uninit(&cmd->req);
 	nvmet_tcp_unmap_pdu_iovec(cmd);
 	kfree(cmd->iov);
-	if (cmd->req.sg_cnt)
-		sgl_free(cmd->req.sg);
+	sgl_free(cmd->req.sg);
 }
 
 static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
-- 
cgit v1.2.3


From 19ea025e1d28c629b369c3532a85b3df478cc5c6 Mon Sep 17 00:00:00 2001
From: Jian-Hong Pan <jian-hong@endlessm.com>
Date: Tue, 24 Sep 2019 17:42:41 +0800
Subject: nvme: Add quirk for Kingston NVME SSD running FW E8FK11.T

Kingston NVME SSD with firmware version E8FK11.T has no interrupt after
resume with actions related to suspend to idle. This patch applied
NVME_QUIRK_SIMPLE_SUSPEND quirk to fix this issue.

Fixes: d916b1be94b6 ("nvme-pci: use host managed power state for suspend")
Buglink: https://bugzilla.kernel.org/show_bug.cgi?id=204887
Signed-off-by: Jian-Hong Pan <jian-hong@endlessm.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/core.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index d3c9df62a9d5..adff57ea149e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2292,6 +2292,16 @@ static const struct nvme_core_quirk_entry core_quirks[] = {
 		.vid = 0x14a4,
 		.fr = "22301111",
 		.quirks = NVME_QUIRK_SIMPLE_SUSPEND,
+	},
+	{
+		/*
+		 * This Kingston E8FK11.T firmware version has no interrupt
+		 * after resume with actions related to suspend to idle
+		 * https://bugzilla.kernel.org/show_bug.cgi?id=204887
+		 */
+		.vid = 0x2646,
+		.fr = "E8FK11.T",
+		.quirks = NVME_QUIRK_SIMPLE_SUSPEND,
 	}
 };
 
-- 
cgit v1.2.3


From 65e68edce0db433aa0c2b26d7dc14fbbbeb89fbb Mon Sep 17 00:00:00 2001
From: Marta Rybczynska <mrybczyn@kalray.eu>
Date: Tue, 24 Sep 2019 15:14:52 +0200
Subject: nvme: allow 64-bit results in passthru commands

It is not possible to get 64-bit results from the passthru commands,
what prevents from getting for the Capabilities (CAP) property value.

As a result, it is not possible to implement IOL's NVMe Conformance
test 4.3 Case 1 for Fabrics targets [1] (page 123).

This issue has been already discussed [2], but without a solution.

This patch solves the problem by adding new ioctls with a new
passthru structure, including 64-bit results. The older ioctls stay
unchanged.

[1] https://www.iol.unh.edu/sites/default/files/testsuites/nvme/UNH-IOL_NVMe_Conformance_Test_Suite_v11.0.pdf
[2] http://lists.infradead.org/pipermail/linux-nvme/2018-June/018791.html

Signed-off-by: Marta Rybczynska <marta.rybczynska@kalray.eu>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/core.c        | 108 ++++++++++++++++++++++++++++++++++------
 include/uapi/linux/nvme_ioctl.h |  23 +++++++++
 2 files changed, 115 insertions(+), 16 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index adff57ea149e..87ed437a46b8 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -850,7 +850,7 @@ out:
 static int nvme_submit_user_cmd(struct request_queue *q,
 		struct nvme_command *cmd, void __user *ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
-		u32 meta_seed, u32 *result, unsigned timeout)
+		u32 meta_seed, u64 *result, unsigned timeout)
 {
 	bool write = nvme_is_write(cmd);
 	struct nvme_ns *ns = q->queuedata;
@@ -891,7 +891,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	else
 		ret = nvme_req(req)->status;
 	if (result)
-		*result = le32_to_cpu(nvme_req(req)->result.u32);
+		*result = le64_to_cpu(nvme_req(req)->result.u64);
 	if (meta && !ret && !write) {
 		if (copy_to_user(meta_buffer, meta, meta_len))
 			ret = -EFAULT;
@@ -1338,6 +1338,54 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	struct nvme_command c;
 	unsigned timeout = 0;
 	u32 effects;
+	u64 result;
+	int status;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
+		return -EFAULT;
+	if (cmd.flags)
+		return -EINVAL;
+
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = cmd.opcode;
+	c.common.flags = cmd.flags;
+	c.common.nsid = cpu_to_le32(cmd.nsid);
+	c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
+	c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
+	c.common.cdw10 = cpu_to_le32(cmd.cdw10);
+	c.common.cdw11 = cpu_to_le32(cmd.cdw11);
+	c.common.cdw12 = cpu_to_le32(cmd.cdw12);
+	c.common.cdw13 = cpu_to_le32(cmd.cdw13);
+	c.common.cdw14 = cpu_to_le32(cmd.cdw14);
+	c.common.cdw15 = cpu_to_le32(cmd.cdw15);
+
+	if (cmd.timeout_ms)
+		timeout = msecs_to_jiffies(cmd.timeout_ms);
+
+	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
+	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
+			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
+			(void __user *)(uintptr_t)cmd.metadata,
+			cmd.metadata_len, 0, &result, timeout);
+	nvme_passthru_end(ctrl, effects);
+
+	if (status >= 0) {
+		if (put_user(result, &ucmd->result))
+			return -EFAULT;
+	}
+
+	return status;
+}
+
+static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
+			struct nvme_passthru_cmd64 __user *ucmd)
+{
+	struct nvme_passthru_cmd64 cmd;
+	struct nvme_command c;
+	unsigned timeout = 0;
+	u32 effects;
 	int status;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -1408,6 +1456,41 @@ static void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx)
 		srcu_read_unlock(&head->srcu, idx);
 }
 
+static bool is_ctrl_ioctl(unsigned int cmd)
+{
+	if (cmd == NVME_IOCTL_ADMIN_CMD || cmd == NVME_IOCTL_ADMIN64_CMD)
+		return true;
+	if (is_sed_ioctl(cmd))
+		return true;
+	return false;
+}
+
+static int nvme_handle_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
+				  void __user *argp,
+				  struct nvme_ns_head *head,
+				  int srcu_idx)
+{
+	struct nvme_ctrl *ctrl = ns->ctrl;
+	int ret;
+
+	nvme_get_ctrl(ns->ctrl);
+	nvme_put_ns_from_disk(head, srcu_idx);
+
+	switch (cmd) {
+	case NVME_IOCTL_ADMIN_CMD:
+		ret = nvme_user_cmd(ctrl, NULL, argp);
+		break;
+	case NVME_IOCTL_ADMIN64_CMD:
+		ret = nvme_user_cmd64(ctrl, NULL, argp);
+		break;
+	default:
+		ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
+		break;
+	}
+	nvme_put_ctrl(ctrl);
+	return ret;
+}
+
 static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
 		unsigned int cmd, unsigned long arg)
 {
@@ -1425,20 +1508,8 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
 	 * seperately and drop the ns SRCU reference early.  This avoids a
 	 * deadlock when deleting namespaces using the passthrough interface.
 	 */
-	if (cmd == NVME_IOCTL_ADMIN_CMD || is_sed_ioctl(cmd)) {
-		struct nvme_ctrl *ctrl = ns->ctrl;
-
-		nvme_get_ctrl(ns->ctrl);
-		nvme_put_ns_from_disk(head, srcu_idx);
-
-		if (cmd == NVME_IOCTL_ADMIN_CMD)
-			ret = nvme_user_cmd(ctrl, NULL, argp);
-		else
-			ret = sed_ioctl(ctrl->opal_dev, cmd, argp);
-
-		nvme_put_ctrl(ctrl);
-		return ret;
-	}
+	if (is_ctrl_ioctl(cmd))
+		return nvme_handle_ctrl_ioctl(ns, cmd, argp, head, srcu_idx);
 
 	switch (cmd) {
 	case NVME_IOCTL_ID:
@@ -1451,6 +1522,9 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
 	case NVME_IOCTL_SUBMIT_IO:
 		ret = nvme_submit_io(ns, argp);
 		break;
+	case NVME_IOCTL_IO64_CMD:
+		ret = nvme_user_cmd64(ns->ctrl, ns, argp);
+		break;
 	default:
 		if (ns->ndev)
 			ret = nvme_nvm_ioctl(ns, cmd, arg);
@@ -2852,6 +2926,8 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
 	switch (cmd) {
 	case NVME_IOCTL_ADMIN_CMD:
 		return nvme_user_cmd(ctrl, NULL, argp);
+	case NVME_IOCTL_ADMIN64_CMD:
+		return nvme_user_cmd64(ctrl, NULL, argp);
 	case NVME_IOCTL_IO_CMD:
 		return nvme_dev_user_cmd(ctrl, argp);
 	case NVME_IOCTL_RESET:
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index 1c215ea1798e..e168dc59e9a0 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -45,6 +45,27 @@ struct nvme_passthru_cmd {
 	__u32	result;
 };
 
+struct nvme_passthru_cmd64 {
+	__u8	opcode;
+	__u8	flags;
+	__u16	rsvd1;
+	__u32	nsid;
+	__u32	cdw2;
+	__u32	cdw3;
+	__u64	metadata;
+	__u64	addr;
+	__u32	metadata_len;
+	__u32	data_len;
+	__u32	cdw10;
+	__u32	cdw11;
+	__u32	cdw12;
+	__u32	cdw13;
+	__u32	cdw14;
+	__u32	cdw15;
+	__u32	timeout_ms;
+	__u64	result;
+};
+
 #define nvme_admin_cmd nvme_passthru_cmd
 
 #define NVME_IOCTL_ID		_IO('N', 0x40)
@@ -54,5 +75,7 @@ struct nvme_passthru_cmd {
 #define NVME_IOCTL_RESET	_IO('N', 0x44)
 #define NVME_IOCTL_SUBSYS_RESET	_IO('N', 0x45)
 #define NVME_IOCTL_RESCAN	_IO('N', 0x46)
+#define NVME_IOCTL_ADMIN64_CMD	_IOWR('N', 0x47, struct nvme_passthru_cmd64)
+#define NVME_IOCTL_IO64_CMD	_IOWR('N', 0x48, struct nvme_passthru_cmd64)
 
 #endif /* _UAPI_LINUX_NVME_IOCTL_H */
-- 
cgit v1.2.3


From 2b1ff255d2d043aa4e6d62f50c478b283f9943ac Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 24 Sep 2019 14:22:08 -0700
Subject: nvme: Add ctrl attributes for queue_count and sqsize

Current controller interrogation requires a lot of guesswork
on how many io queues were created and what the io sq size is.
The numbers are dependent upon core/fabric defaults, connect
arguments, and target responses.

Add sysfs attributes for queue_count and sqsize.

Signed-off-by: James Smart <jsmart2021@gmail.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 87ed437a46b8..fd7dea36c3b6 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3135,6 +3135,8 @@ static DEVICE_ATTR(field, S_IRUGO, field##_show, NULL);
 
 nvme_show_int_function(cntlid);
 nvme_show_int_function(numa_node);
+nvme_show_int_function(queue_count);
+nvme_show_int_function(sqsize);
 
 static ssize_t nvme_sysfs_delete(struct device *dev,
 				struct device_attribute *attr, const char *buf,
@@ -3215,6 +3217,8 @@ static struct attribute *nvme_dev_attrs[] = {
 	&dev_attr_address.attr,
 	&dev_attr_state.attr,
 	&dev_attr_numa_node.attr,
+	&dev_attr_queue_count.attr,
+	&dev_attr_sqsize.attr,
 	NULL
 };
 
-- 
cgit v1.2.3


From c1f2b8124bdf2d7812a759f83a36a6d6178b5c94 Mon Sep 17 00:00:00 2001
From: James Ausmus <james.ausmus@intel.com>
Date: Tue, 24 Sep 2019 15:28:29 -0700
Subject: drm/i915/tgl: Add memory type decoding for bandwidth checking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The memory type values have changed in TGL, so we need to translate them
differently than ICL. While we're moving it, fix up the ICL translation
for LPDDR4.

BSpec: 53998

v2: Fix up ICL LPDDR4 entry (Ville); Drop unused values from TGL (Ville)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Signed-off-by: James Ausmus <james.ausmus@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190924222829.13142-1-james.ausmus@intel.com
---
 drivers/gpu/drm/i915/display/intel_bw.c | 55 +++++++++++++++++++++++----------
 1 file changed, 39 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c
index cd58e47ab7b2..22e83f857de8 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.c
+++ b/drivers/gpu/drm/i915/display/intel_bw.c
@@ -35,22 +35,45 @@ static int icl_pcode_read_mem_global_info(struct drm_i915_private *dev_priv,
 	if (ret)
 		return ret;
 
-	switch (val & 0xf) {
-	case 0:
-		qi->dram_type = INTEL_DRAM_DDR4;
-		break;
-	case 1:
-		qi->dram_type = INTEL_DRAM_DDR3;
-		break;
-	case 2:
-		qi->dram_type = INTEL_DRAM_LPDDR3;
-		break;
-	case 3:
-		qi->dram_type = INTEL_DRAM_LPDDR3;
-		break;
-	default:
-		MISSING_CASE(val & 0xf);
-		break;
+	if (IS_GEN(dev_priv, 12)) {
+		switch (val & 0xf) {
+		case 0:
+			qi->dram_type = INTEL_DRAM_DDR4;
+			break;
+		case 3:
+			qi->dram_type = INTEL_DRAM_LPDDR4;
+			break;
+		case 4:
+			qi->dram_type = INTEL_DRAM_DDR3;
+			break;
+		case 5:
+			qi->dram_type = INTEL_DRAM_LPDDR3;
+			break;
+		default:
+			MISSING_CASE(val & 0xf);
+			break;
+		}
+	} else if (IS_GEN(dev_priv, 11)) {
+		switch (val & 0xf) {
+		case 0:
+			qi->dram_type = INTEL_DRAM_DDR4;
+			break;
+		case 1:
+			qi->dram_type = INTEL_DRAM_DDR3;
+			break;
+		case 2:
+			qi->dram_type = INTEL_DRAM_LPDDR3;
+			break;
+		case 3:
+			qi->dram_type = INTEL_DRAM_LPDDR4;
+			break;
+		default:
+			MISSING_CASE(val & 0xf);
+			break;
+		}
+	} else {
+		MISSING_CASE(INTEL_GEN(dev_priv));
+		qi->dram_type = INTEL_DRAM_LPDDR3; /* Conservative default */
 	}
 
 	qi->num_channels = (val & 0xf0) >> 4;
-- 
cgit v1.2.3


From a0f0037e908c656573d165aadbfae6c05fc4dd75 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <wanpengli@tencent.com>
Date: Thu, 26 Sep 2019 08:54:03 +0800
Subject: KVM: LAPIC: Loosen filter for adaptive tuning of
 lapic_timer_advance_ns

5000 guest cycles delta is easy to encounter on desktop, per-vCPU
lapic_timer_advance_ns always keeps at 1000ns initial value, let's
loosen the filter a bit to let adaptive tuning make progress.

Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/lapic.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 3a3a6854dcca..87b0fcc23ef8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -66,9 +66,10 @@
 #define X2APIC_BROADCAST		0xFFFFFFFFul
 
 static bool lapic_timer_advance_dynamic __read_mostly;
-#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100
-#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 5000
-#define LAPIC_TIMER_ADVANCE_ADJUST_INIT 1000
+#define LAPIC_TIMER_ADVANCE_ADJUST_MIN	100	/* clock cycles */
+#define LAPIC_TIMER_ADVANCE_ADJUST_MAX	10000	/* clock cycles */
+#define LAPIC_TIMER_ADVANCE_NS_INIT	1000
+#define LAPIC_TIMER_ADVANCE_NS_MAX     5000
 /* step-by-step approximation to mitigate fluctuation */
 #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
 
@@ -1504,8 +1505,8 @@ static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu,
 		timer_advance_ns += ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP;
 	}
 
-	if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_ADJUST_MAX))
-		timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
+	if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_NS_MAX))
+		timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
 	apic->lapic_timer.timer_advance_ns = timer_advance_ns;
 }
 
@@ -2302,7 +2303,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 		     HRTIMER_MODE_ABS_HARD);
 	apic->lapic_timer.timer.function = apic_timer_fn;
 	if (timer_advance_ns == -1) {
-		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
+		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
 		lapic_timer_advance_dynamic = true;
 	} else {
 		apic->lapic_timer.timer_advance_ns = timer_advance_ns;
-- 
cgit v1.2.3


From a1a640b8c0cd8a2a7f84ab694f04bc64dc6988af Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Wed, 25 Sep 2019 11:17:14 -0700
Subject: kvm: x86: Fix a spurious -E2BIG in __do_cpuid_func

Don't return -E2BIG from __do_cpuid_func when processing function 0BH
or 1FH and the last interesting subleaf occupies the last allocated
entry in the result array.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Fixes: 831bf664e9c1fc ("KVM: Refactor and simplify kvm_dev_ioctl_get_supported_cpuid")
Signed-off-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/cpuid.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 63316036f85a..6bf4a261b308 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -618,16 +618,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
 	 */
 	case 0x1f:
 	case 0xb: {
-		int i, level_type;
+		int i;
 
-		/* read more entries until level_type is zero */
-		for (i = 1; ; ++i) {
+		/*
+		 * We filled in entry[0] for CPUID(EAX=<function>,
+		 * ECX=00H) above.  If its level type (ECX[15:8]) is
+		 * zero, then the leaf is unimplemented, and we're
+		 * done.  Otherwise, continue to populate entries
+		 * until the level type (ECX[15:8]) of the previously
+		 * added entry is zero.
+		 */
+		for (i = 1; entry[i - 1].ecx & 0xff00; ++i) {
 			if (*nent >= maxnent)
 				goto out;
 
-			level_type = entry[i - 1].ecx & 0xff00;
-			if (!level_type)
-				break;
 			do_host_cpuid(&entry[i], function, i);
 			++*nent;
 		}
-- 
cgit v1.2.3


From 3ca94192278ca8de169d78c085396c424be123b3 Mon Sep 17 00:00:00 2001
From: Wanpeng Li <wanpengli@tencent.com>
Date: Wed, 18 Sep 2019 17:50:10 +0800
Subject: KVM: X86: Fix userspace set invalid CR4

Reported by syzkaller:

	WARNING: CPU: 0 PID: 6544 at /home/kernel/data/kvm/arch/x86/kvm//vmx/vmx.c:4689 handle_desc+0x37/0x40 [kvm_intel]
	CPU: 0 PID: 6544 Comm: a.out Tainted: G           OE     5.3.0-rc4+ #4
	RIP: 0010:handle_desc+0x37/0x40 [kvm_intel]
	Call Trace:
	 vmx_handle_exit+0xbe/0x6b0 [kvm_intel]
	 vcpu_enter_guest+0x4dc/0x18d0 [kvm]
	 kvm_arch_vcpu_ioctl_run+0x407/0x660 [kvm]
	 kvm_vcpu_ioctl+0x3ad/0x690 [kvm]
	 do_vfs_ioctl+0xa2/0x690
	 ksys_ioctl+0x6d/0x80
	 __x64_sys_ioctl+0x1a/0x20
	 do_syscall_64+0x74/0x720
	 entry_SYSCALL_64_after_hwframe+0x49/0xbe

When CR4.UMIP is set, guest should have UMIP cpuid flag. Current
kvm set_sregs function doesn't have such check when userspace inputs
sregs values. SECONDARY_EXEC_DESC is enabled on writes to CR4.UMIP
in vmx_set_cr4 though guest doesn't have UMIP cpuid flag. The testcast
triggers handle_desc warning when executing ltr instruction since
guest architectural CR4 doesn't set UMIP. This patch fixes it by
adding valid CR4 and CPUID combination checking in __set_sregs.

syzkaller source: https://syzkaller.appspot.com/x/repro.c?x=138efb99600000

Reported-by: syzbot+0f1819555fbdce992df9@syzkaller.appspotmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Reviewed-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 38 +++++++++++++++++++++-----------------
 1 file changed, 21 insertions(+), 17 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0ed07d8d2caa..180c7e88577a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -885,34 +885,42 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 }
 EXPORT_SYMBOL_GPL(kvm_set_xcr);
 
-int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	unsigned long old_cr4 = kvm_read_cr4(vcpu);
-	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
-				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
-
 	if (cr4 & CR4_RESERVED_BITS)
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP))
+		return -EINVAL;
+
+	return 0;
+}
+
+int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+	unsigned long old_cr4 = kvm_read_cr4(vcpu);
+	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
+
+	if (kvm_valid_cr4(vcpu, cr4))
 		return 1;
 
 	if (is_long_mode(vcpu)) {
@@ -8714,10 +8722,6 @@ EXPORT_SYMBOL_GPL(kvm_task_switch);
 
 static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-			(sregs->cr4 & X86_CR4_OSXSAVE))
-		return  -EINVAL;
-
 	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
 		/*
 		 * When EFER.LME and CR0.PG are set, the processor is in
@@ -8736,7 +8740,7 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 			return -EINVAL;
 	}
 
-	return 0;
+	return kvm_valid_cr4(vcpu, sregs->cr4);
 }
 
 static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
-- 
cgit v1.2.3


From 43561123ab3759eb6ff47693aec1a307af0aef83 Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Wed, 25 Sep 2019 17:04:17 -0700
Subject: kvm: x86: Improve emulation of CPUID leaves 0BH and 1FH

For these CPUID leaves, the EDX output is not dependent on the ECX
input (i.e. the SIGNIFCANT_INDEX flag doesn't apply to
EDX). Furthermore, the low byte of the ECX output is always identical
to the low byte of the ECX input. KVM does not produce the correct ECX
and EDX outputs for any undefined subleaves beyond the first.

Special-case these CPUID leaves in kvm_cpuid, so that the ECX and EDX
outputs are properly generated for all undefined subleaves.

Fixes: 0771671749b59a ("KVM: Enhance guest cpuid management")
Fixes: a87f2d3a6eadab ("KVM: x86: Add Intel CPUID.1F cpuid emulation support")
Signed-off-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Marc Orr <marcorr@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Reviewed-by: Jacob Xu <jacobhxu@google.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/cpuid.c | 83 +++++++++++++++++++++++++++++-----------------------
 1 file changed, 47 insertions(+), 36 deletions(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 6bf4a261b308..a26a1ae03145 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -973,53 +973,64 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);
 
 /*
- * If no match is found, check whether we exceed the vCPU's limit
- * and return the content of the highest valid _standard_ leaf instead.
- * This is to satisfy the CPUID specification.
+ * If the basic or extended CPUID leaf requested is higher than the
+ * maximum supported basic or extended leaf, respectively, then it is
+ * out of range.
  */
-static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu,
-                                                  u32 function, u32 index)
+static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function)
 {
-	struct kvm_cpuid_entry2 *maxlevel;
-
-	maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
-	if (!maxlevel || maxlevel->eax >= function)
-		return NULL;
-	if (function & 0x80000000) {
-		maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0);
-		if (!maxlevel)
-			return NULL;
-	}
-	return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index);
+	struct kvm_cpuid_entry2 *max;
+
+	max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
+	return max && function <= max->eax;
 }
 
 bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
 	       u32 *ecx, u32 *edx, bool check_limit)
 {
 	u32 function = *eax, index = *ecx;
-	struct kvm_cpuid_entry2 *best;
-	bool entry_found = true;
-
-	best = kvm_find_cpuid_entry(vcpu, function, index);
-
-	if (!best) {
-		entry_found = false;
-		if (!check_limit)
-			goto out;
+	struct kvm_cpuid_entry2 *entry;
+	struct kvm_cpuid_entry2 *max;
+	bool found;
 
-		best = check_cpuid_limit(vcpu, function, index);
+	entry = kvm_find_cpuid_entry(vcpu, function, index);
+	found = entry;
+	/*
+	 * Intel CPUID semantics treats any query for an out-of-range
+	 * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were
+	 * requested.
+	 */
+	if (!entry && check_limit && !cpuid_function_in_range(vcpu, function)) {
+		max = kvm_find_cpuid_entry(vcpu, 0, 0);
+		if (max) {
+			function = max->eax;
+			entry = kvm_find_cpuid_entry(vcpu, function, index);
+		}
 	}
-
-out:
-	if (best) {
-		*eax = best->eax;
-		*ebx = best->ebx;
-		*ecx = best->ecx;
-		*edx = best->edx;
-	} else
+	if (entry) {
+		*eax = entry->eax;
+		*ebx = entry->ebx;
+		*ecx = entry->ecx;
+		*edx = entry->edx;
+	} else {
 		*eax = *ebx = *ecx = *edx = 0;
-	trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, entry_found);
-	return entry_found;
+		/*
+		 * When leaf 0BH or 1FH is defined, CL is pass-through
+		 * and EDX is always the x2APIC ID, even for undefined
+		 * subleaves. Index 1 will exist iff the leaf is
+		 * implemented, so we pass through CL iff leaf 1
+		 * exists. EDX can be copied from any existing index.
+		 */
+		if (function == 0xb || function == 0x1f) {
+			entry = kvm_find_cpuid_entry(vcpu, function, 1);
+			if (entry) {
+				*ecx = index & 0xff;
+				*edx = entry->edx;
+			}
+		}
+	}
+	trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found);
+	return found;
 }
 EXPORT_SYMBOL_GPL(kvm_cpuid);
 
-- 
cgit v1.2.3


From 5f41a37b151f6459e0b650a2f4d1d59b6c02d1ab Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Wed, 25 Sep 2019 17:04:18 -0700
Subject: kvm: x86: Use AMD CPUID semantics for AMD vCPUs

When the guest CPUID information represents an AMD vCPU, return all
zeroes for queries of undefined CPUID leaves, whether or not they are
in range.

Signed-off-by: Jim Mattson <jmattson@google.com>
Fixes: bd22f5cfcfe8f6 ("KVM: move and fix substitue search for missing CPUID entries")
Reviewed-by: Marc Orr <marcorr@google.com>
Reviewed-by: Peter Shier <pshier@google.com>
Reviewed-by: Jacob Xu <jacobhxu@google.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/cpuid.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a26a1ae03145..ce4a1b3cc3e8 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -998,9 +998,11 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
 	/*
 	 * Intel CPUID semantics treats any query for an out-of-range
 	 * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were
-	 * requested.
+	 * requested. AMD CPUID semantics returns all zeroes for any
+	 * undefined leaf, whether or not the leaf is in range.
 	 */
-	if (!entry && check_limit && !cpuid_function_in_range(vcpu, function)) {
+	if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) &&
+	    !cpuid_function_in_range(vcpu, function)) {
 		max = kvm_find_cpuid_entry(vcpu, 0, 0);
 		if (max) {
 			function = max->eax;
-- 
cgit v1.2.3


From 40bc47b08b6efc8b64fef77cb46974f634215425 Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Tue, 24 Sep 2019 13:51:08 -0700
Subject: kvm: x86: Enumerate support for CLZERO instruction

CLZERO is available to the guest if it is supported on the
host. Therefore, enumerate support for the instruction in
KVM_GET_SUPPORTED_CPUID whenever it is supported on the host.

Signed-off-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/cpuid.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index ce4a1b3cc3e8..34d9f9f481a3 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -485,8 +485,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
 
 	/* cpuid 0x80000008.ebx */
 	const u32 kvm_cpuid_8000_0008_ebx_x86_features =
-		F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) |
-		F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON);
+		F(CLZERO) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) |
+		F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) | F(AMD_SSBD) |
+		F(VIRT_SSBD) | F(AMD_SSB_NO);
 
 	/* cpuid 0xC0000001.edx */
 	const u32 kvm_cpuid_C000_0001_edx_x86_features =
-- 
cgit v1.2.3


From 504ce1954fba888936c9d13ccc1e3db9b8f613d5 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 25 Sep 2019 23:37:21 +0200
Subject: KVM: x86: Expose XSAVEERPTR to the guest

I was surprised to see that the guest reported `fxsave_leak' while the
host did not. After digging deeper I noticed that the bits are simply
masked out during enumeration.

The XSAVEERPTR feature is actually a bug fix on AMD which means the
kernel can disable a workaround.

Pass XSAVEERPTR to the guest if available on the host.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/cpuid.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 34d9f9f481a3..9c5029cf6f3f 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -485,9 +485,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
 
 	/* cpuid 0x80000008.ebx */
 	const u32 kvm_cpuid_8000_0008_ebx_x86_features =
-		F(CLZERO) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) |
-		F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) | F(AMD_SSBD) |
-		F(VIRT_SSBD) | F(AMD_SSB_NO);
+		F(CLZERO) | F(XSAVEERPTR) |
+		F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) |
+		F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON);
 
 	/* cpuid 0xC0000001.edx */
 	const u32 kvm_cpuid_C000_0001_edx_x86_features =
-- 
cgit v1.2.3


From 45d3c5cd5233258ffa9326b33ae4af59fb127dfb Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Wed, 25 Sep 2019 16:45:42 -0700
Subject: drm/i915: Small joiner RAM buffer size is platform-specific

According to the bspec, GLK/CNL have a smaller small joiner RAM buffer
than ICL+.  This feels like something that could easily change again on
future platforms, so let's just add a function to return the proper
per-platform buffer size.  That may also slightly simplify the upcoming
bigjoiner enabling.

Since we have to change intel_dp_dsc_get_output_bpp()'s signature to
pass the dev_priv down for the platform check, let's take the
opportunity to also make that function static since it isn't used
outside the intel_dp file.

v2: Minor rebase on top of Maarten's changes.

Bspec: 20388
Bspec: 49259
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190925234542.24289-1-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 893c9807755c..14a5c661f710 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -68,9 +68,6 @@
 
 #define DP_DPRX_ESI_LEN 14
 
-/* DP DSC small joiner has 2 FIFOs each of 640 x 6 bytes */
-#define DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER	61440
-
 /* DP DSC throughput values used for slice count calculations KPixels/s */
 #define DP_DSC_PEAK_PIXEL_RATE			2720000
 #define DP_DSC_MAX_ENC_THROUGHPUT_0		340000
@@ -498,7 +495,17 @@ u32 intel_dp_mode_to_fec_clock(u32 mode_clock)
 		       DP_DSC_FEC_OVERHEAD_FACTOR);
 }
 
-static u16 intel_dp_dsc_get_output_bpp(u32 link_clock, u32 lane_count,
+static int
+small_joiner_ram_size_bits(struct drm_i915_private *i915)
+{
+	if (INTEL_GEN(i915) >= 11)
+		return 7680 * 8;
+	else
+		return 6144 * 8;
+}
+
+static u16 intel_dp_dsc_get_output_bpp(struct drm_i915_private *i915,
+				       u32 link_clock, u32 lane_count,
 				       u32 mode_clock, u32 mode_hdisplay)
 {
 	u32 bits_per_pixel, max_bpp_small_joiner_ram;
@@ -515,7 +522,8 @@ static u16 intel_dp_dsc_get_output_bpp(u32 link_clock, u32 lane_count,
 	DRM_DEBUG_KMS("Max link bpp: %u\n", bits_per_pixel);
 
 	/* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */
-	max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER / mode_hdisplay;
+	max_bpp_small_joiner_ram = small_joiner_ram_size_bits(i915) /
+		mode_hdisplay;
 	DRM_DEBUG_KMS("Max small joiner bpp: %u\n", max_bpp_small_joiner_ram);
 
 	/*
@@ -632,7 +640,8 @@ intel_dp_mode_valid(struct drm_connector *connector,
 								true);
 		} else if (drm_dp_sink_supports_fec(intel_dp->fec_capable)) {
 			dsc_max_output_bpp =
-				intel_dp_dsc_get_output_bpp(max_link_clock,
+				intel_dp_dsc_get_output_bpp(dev_priv,
+							    max_link_clock,
 							    max_lanes,
 							    target_clock,
 							    mode->hdisplay) >> 4;
@@ -2059,7 +2068,8 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 		u8 dsc_dp_slice_count;
 
 		dsc_max_output_bpp =
-			intel_dp_dsc_get_output_bpp(pipe_config->port_clock,
+			intel_dp_dsc_get_output_bpp(dev_priv,
+						    pipe_config->port_clock,
 						    pipe_config->lane_count,
 						    adjusted_mode->crtc_clock,
 						    adjusted_mode->crtc_hdisplay);
-- 
cgit v1.2.3


From 5311f5171e98e6958fe5cf1c424a6196115baeb6 Mon Sep 17 00:00:00 2001
From: Michał Winiarski <michal.winiarski@intel.com>
Date: Thu, 26 Sep 2019 14:31:40 +0100
Subject: drm/i915: Define explicit wedged on init reset state
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We're currently using scratch presence as a way of identifying that we
entered wedged state at driver initialization time.
Let's use a separate flag rather than rely on scratch.

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190926133142.2838-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_reset.c       | 11 ++++++++++-
 drivers/gpu/drm/i915/gt/intel_reset.h       |  9 +++++++++
 drivers/gpu/drm/i915/gt/intel_reset_types.h |  6 ++++++
 drivers/gpu/drm/i915/i915_gem.c             |  2 +-
 4 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index ae68c3786f63..ec978b4d1be3 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -811,7 +811,8 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	if (!test_bit(I915_WEDGED, &gt->reset.flags))
 		return true;
 
-	if (!gt->scratch) /* Never full initialised, recovery impossible */
+	/* Never fully initialised, recovery impossible */
+	if (test_bit(I915_WEDGED_ON_INIT, &gt->reset.flags))
 		return false;
 
 	GEM_TRACE("start\n");
@@ -1279,6 +1280,14 @@ int intel_gt_terminally_wedged(struct intel_gt *gt)
 	return intel_gt_is_wedged(gt) ? -EIO : 0;
 }
 
+void intel_gt_set_wedged_on_init(struct intel_gt *gt)
+{
+	BUILD_BUG_ON(I915_RESET_ENGINE + I915_NUM_ENGINES >
+		     I915_WEDGED_ON_INIT);
+	intel_gt_set_wedged(gt);
+	set_bit(I915_WEDGED_ON_INIT, &gt->reset.flags);
+}
+
 void intel_gt_init_reset(struct intel_gt *gt)
 {
 	init_waitqueue_head(&gt->reset.queue);
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h
index 52c00199e069..0b6ff1ee7f06 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.h
+++ b/drivers/gpu/drm/i915/gt/intel_reset.h
@@ -45,6 +45,12 @@ void intel_gt_set_wedged(struct intel_gt *gt);
 bool intel_gt_unset_wedged(struct intel_gt *gt);
 int intel_gt_terminally_wedged(struct intel_gt *gt);
 
+/*
+ * There's no unset_wedged_on_init paired with this one.
+ * Once we're wedged on init, there's no going back.
+ */
+void intel_gt_set_wedged_on_init(struct intel_gt *gt);
+
 int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask);
 
 int intel_reset_guc(struct intel_gt *gt);
@@ -68,6 +74,9 @@ void __intel_fini_wedge(struct intel_wedge_me *w);
 
 static inline bool __intel_reset_failed(const struct intel_reset *reset)
 {
+	GEM_BUG_ON(test_bit(I915_WEDGED_ON_INIT, &reset->flags) ?
+		   !test_bit(I915_WEDGED, &reset->flags) : false);
+
 	return unlikely(test_bit(I915_WEDGED, &reset->flags));
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_reset_types.h b/drivers/gpu/drm/i915/gt/intel_reset_types.h
index 31968356e0c0..f43bc3a0fe4f 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_reset_types.h
@@ -29,11 +29,17 @@ struct intel_reset {
 	 * we set the #I915_WEDGED bit. Prior to command submission, e.g.
 	 * i915_request_alloc(), this bit is checked and the sequence
 	 * aborted (with -EIO reported to userspace) if set.
+	 *
+	 * #I915_WEDGED_ON_INIT - If we fail to initialize the GPU we can no
+	 * longer use the GPU - similar to #I915_WEDGED bit. The difference in
+	 * in the way we're handling "forced" unwedged (e.g. through debugfs),
+	 * which is not allowed in case we failed to initialize.
 	 */
 	unsigned long flags;
 #define I915_RESET_BACKOFF	0
 #define I915_RESET_MODESET	1
 #define I915_RESET_ENGINE	2
+#define I915_WEDGED_ON_INIT	(BITS_PER_LONG - 2)
 #define I915_WEDGED		(BITS_PER_LONG - 1)
 
 	struct mutex mutex; /* serialises wedging/unwedging */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 2da9544fa9a4..e2897a666225 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1411,7 +1411,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 err_gt:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
-	intel_gt_set_wedged(&dev_priv->gt);
+	intel_gt_set_wedged_on_init(&dev_priv->gt);
 	i915_gem_suspend(dev_priv);
 	i915_gem_suspend_late(dev_priv);
 
-- 
cgit v1.2.3


From e1237523749e342d9ffb499a636ab6860a554cba Mon Sep 17 00:00:00 2001
From: Michał Winiarski <michal.winiarski@intel.com>
Date: Thu, 26 Sep 2019 14:31:41 +0100
Subject: drm/i915/execlists: Use per-process HWSP as scratch
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some of our commands (MI_FLUSH_DW / PIPE_CONTROL) require a post-sync write
operation to be performed. Currently we're using dedicated VMA for
PIPE_CONTROL and global HWSP for MI_FLUSH_DW.
On execlists platforms, each of our contexts has an area that can be
used as scratch space. Let's use that instead.

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190926133142.2838-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_gt_types.h |  3 ---
 drivers/gpu/drm/i915/gt/intel_lrc.c      | 45 +++++++++-----------------------
 drivers/gpu/drm/i915/gt/intel_lrc.h      |  4 +++
 3 files changed, 17 insertions(+), 35 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index 3039cef64b11..e64db4c13df6 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -89,9 +89,6 @@ enum intel_gt_scratch_field {
 	/* 8 bytes */
 	INTEL_GT_SCRATCH_FIELD_DEFAULT = 0,
 
-	/* 8 bytes */
-	INTEL_GT_SCRATCH_FIELD_CLEAR_SLM_WA = 128,
-
 	/* 8 bytes */
 	INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH = 128,
 
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index ab725a6ca0ac..fa385218ce92 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2308,12 +2308,6 @@ gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch)
 	return batch;
 }
 
-static u32 slm_offset(struct intel_engine_cs *engine)
-{
-	return intel_gt_scratch_offset(engine->gt,
-				       INTEL_GT_SCRATCH_FIELD_CLEAR_SLM_WA);
-}
-
 /*
  * Typically we only have one indirect_ctx and per_ctx batch buffer which are
  * initialized at the beginning and shared across all contexts but this field
@@ -2342,10 +2336,10 @@ static u32 *gen8_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
 	/* Actual scratch location is at 128 bytes offset */
 	batch = gen8_emit_pipe_control(batch,
 				       PIPE_CONTROL_FLUSH_L3 |
-				       PIPE_CONTROL_GLOBAL_GTT_IVB |
+				       PIPE_CONTROL_STORE_DATA_INDEX |
 				       PIPE_CONTROL_CS_STALL |
 				       PIPE_CONTROL_QW_WRITE,
-				       slm_offset(engine));
+				       LRC_PPHWSP_SCRATCH_ADDR);
 
 	*batch++ = MI_ARB_ON_OFF | MI_ARB_ENABLE;
 
@@ -3052,7 +3046,7 @@ static int gen8_emit_flush(struct i915_request *request, u32 mode)
 	}
 
 	*cs++ = cmd;
-	*cs++ = I915_GEM_HWS_SCRATCH_ADDR | MI_FLUSH_DW_USE_GTT;
+	*cs++ = LRC_PPHWSP_SCRATCH_ADDR;
 	*cs++ = 0; /* upper addr */
 	*cs++ = 0; /* value */
 	intel_ring_advance(request, cs);
@@ -3063,10 +3057,6 @@ static int gen8_emit_flush(struct i915_request *request, u32 mode)
 static int gen8_emit_flush_render(struct i915_request *request,
 				  u32 mode)
 {
-	struct intel_engine_cs *engine = request->engine;
-	u32 scratch_addr =
-		intel_gt_scratch_offset(engine->gt,
-					INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH);
 	bool vf_flush_wa = false, dc_flush_wa = false;
 	u32 *cs, flags = 0;
 	int len;
@@ -3088,7 +3078,7 @@ static int gen8_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_QW_WRITE;
-		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 
 		/*
 		 * On GEN9: before VF_CACHE_INVALIDATE we need to emit a NULL
@@ -3121,7 +3111,7 @@ static int gen8_emit_flush_render(struct i915_request *request,
 		cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_DC_FLUSH_ENABLE,
 					    0);
 
-	cs = gen8_emit_pipe_control(cs, flags, scratch_addr);
+	cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 
 	if (dc_flush_wa)
 		cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_CS_STALL, 0);
@@ -3134,11 +3124,6 @@ static int gen8_emit_flush_render(struct i915_request *request,
 static int gen11_emit_flush_render(struct i915_request *request,
 				   u32 mode)
 {
-	struct intel_engine_cs *engine = request->engine;
-	const u32 scratch_addr =
-		intel_gt_scratch_offset(engine->gt,
-					INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH);
-
 	if (mode & EMIT_FLUSH) {
 		u32 *cs;
 		u32 flags = 0;
@@ -3151,13 +3136,13 @@ static int gen11_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_DC_FLUSH_ENABLE;
 		flags |= PIPE_CONTROL_FLUSH_ENABLE;
 		flags |= PIPE_CONTROL_QW_WRITE;
-		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 
 		cs = intel_ring_begin(request, 6);
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
-		cs = gen8_emit_pipe_control(cs, flags, scratch_addr);
+		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 		intel_ring_advance(request, cs);
 	}
 
@@ -3175,13 +3160,13 @@ static int gen11_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_QW_WRITE;
-		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 
 		cs = intel_ring_begin(request, 6);
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
-		cs = gen8_emit_pipe_control(cs, flags, scratch_addr);
+		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 		intel_ring_advance(request, cs);
 	}
 
@@ -3196,10 +3181,6 @@ static u32 preparser_disable(bool state)
 static int gen12_emit_flush_render(struct i915_request *request,
 				   u32 mode)
 {
-	const u32 scratch_addr =
-		intel_gt_scratch_offset(request->engine->gt,
-					INTEL_GT_SCRATCH_FIELD_RENDER_FLUSH);
-
 	if (mode & EMIT_FLUSH) {
 		u32 flags = 0;
 		u32 *cs;
@@ -3210,7 +3191,7 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_DC_FLUSH_ENABLE;
 		flags |= PIPE_CONTROL_FLUSH_ENABLE;
 
-		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 		flags |= PIPE_CONTROL_QW_WRITE;
 
 		flags |= PIPE_CONTROL_CS_STALL;
@@ -3219,7 +3200,7 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		if (IS_ERR(cs))
 			return PTR_ERR(cs);
 
-		cs = gen8_emit_pipe_control(cs, flags, scratch_addr);
+		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 		intel_ring_advance(request, cs);
 	}
 
@@ -3235,7 +3216,7 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
 
-		flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 		flags |= PIPE_CONTROL_QW_WRITE;
 
 		flags |= PIPE_CONTROL_CS_STALL;
@@ -3251,7 +3232,7 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		 */
 		*cs++ = preparser_disable(true);
 
-		cs = gen8_emit_pipe_control(cs, flags, scratch_addr);
+		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 
 		*cs++ = preparser_disable(false);
 		intel_ring_advance(request, cs);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index dc0252e0589e..66ac616361c1 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -104,6 +104,10 @@ int intel_execlists_submission_init(struct intel_engine_cs *engine);
  */
 #define LRC_HEADER_PAGES LRC_PPHWSP_PN
 
+/* Space within PPHWSP reserved to be used as scratch */
+#define LRC_PPHWSP_SCRATCH		0x34
+#define LRC_PPHWSP_SCRATCH_ADDR		(LRC_PPHWSP_SCRATCH * sizeof(u32))
+
 void intel_execlists_set_default_submission(struct intel_engine_cs *engine);
 
 void intel_lr_context_reset(struct intel_engine_cs *engine,
-- 
cgit v1.2.3


From 7d5255e0ced46a10131175bf65789a0c1a7806a4 Mon Sep 17 00:00:00 2001
From: Michał Winiarski <michal.winiarski@intel.com>
Date: Thu, 26 Sep 2019 14:31:42 +0100
Subject: drm/i915: Adjust length of MI_LOAD_REGISTER_REG
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Default length value of MI_LOAD_REGISTER_REG is 1.
Also move it out of cmd-parser-only registers since we're going to use
it in i915.

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190926133142.2838-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index f78b13d74e17..9211b1ad401b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -152,6 +152,7 @@
 #define   MI_FLUSH_DW_USE_PPGTT		(0<<2)
 #define MI_LOAD_REGISTER_MEM	   MI_INSTR(0x29, 1)
 #define MI_LOAD_REGISTER_MEM_GEN8  MI_INSTR(0x29, 2)
+#define MI_LOAD_REGISTER_REG    MI_INSTR(0x2A, 1)
 #define MI_BATCH_BUFFER		MI_INSTR(0x30, 1)
 #define   MI_BATCH_NON_SECURE		(1)
 /* for snb/ivb/vlv this also means "batch in ppgtt" when ppgtt is enabled. */
@@ -256,7 +257,6 @@
 #define MI_CLFLUSH              MI_INSTR(0x27, 0)
 #define MI_REPORT_PERF_COUNT    MI_INSTR(0x28, 0)
 #define   MI_REPORT_PERF_COUNT_GGTT (1<<0)
-#define MI_LOAD_REGISTER_REG    MI_INSTR(0x2A, 0)
 #define MI_RS_STORE_DATA_IMM    MI_INSTR(0x2B, 0)
 #define MI_LOAD_URB_MEM         MI_INSTR(0x2C, 0)
 #define MI_STORE_URB_MEM        MI_INSTR(0x2D, 0)
-- 
cgit v1.2.3


From 132dfc78d3eb51b6fc8e667183b3572d41e3fe9f Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 26 Sep 2019 12:56:44 +0200
Subject: drm/i915: Drop the IRQ-off asserts

The lockdep_assert_irqs_disabled() check is needless. The previous
lockdep_assert_held() check ensures that the lock is acquired and while
the lock is acquired lockdep also prints a warning if the interrupts are
not disabled if they have to be.
These IRQ-off asserts trigger on PREEMPT_RT because the locks become
sleeping locks and do not really disable interrupts.

Remove lockdep_assert_irqs_disabled().

Reported-by: Clark Williams <williams@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190926105644.16703-3-bigeasy@linutronix.de
---
 drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 09c68dda2098..0c6a1b11e259 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -120,7 +120,6 @@ __dma_fence_signal__notify(struct dma_fence *fence,
 	struct dma_fence_cb *cur, *tmp;
 
 	lockdep_assert_held(fence->lock);
-	lockdep_assert_irqs_disabled();
 
 	list_for_each_entry_safe(cur, tmp, list, node) {
 		INIT_LIST_HEAD(&cur->node);
@@ -275,7 +274,6 @@ void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine)
 bool i915_request_enable_breadcrumb(struct i915_request *rq)
 {
 	lockdep_assert_held(&rq->lock);
-	lockdep_assert_irqs_disabled();
 
 	if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) {
 		struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
@@ -325,7 +323,6 @@ void i915_request_cancel_breadcrumb(struct i915_request *rq)
 	struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
 
 	lockdep_assert_held(&rq->lock);
-	lockdep_assert_irqs_disabled();
 
 	/*
 	 * We must wait for b->irq_lock so that we know the interrupt handler
-- 
cgit v1.2.3


From e3792238c1dde5059e44e0f14899497ac875443d Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 26 Sep 2019 12:56:43 +0200
Subject: drm/i915: Don't disable interrupts for intel_engine_breadcrumbs_irq()

The function intel_engine_breadcrumbs_irq() is always invoked from an interrupt
handler and for that reason it invokes (as an optimisation) only spin_lock()
for locking assuming that the interrupts are already disabled. The
function intel_engine_signal_breadcrumbs() is provided to disable
interrupts while the former function is invoked so that assumption is
also true for callers from preemptible context.

On PREEMPT_RT local_irq_disable() really disables interrupts and this
forbids to invoke spin_lock() which becomes a sleeping spinlock.

This is also problematic with `threadirqs' in conjunction with
irq_work. With force threading the interrupt handler, the handler is
invoked with disabled BH but with interrupts enabled. This is okay and
the lock itself is never acquired in IRQ context. This changes with
irq_work (signal_irq_work()) which _still_ invokes
intel_engine_breadcrumbs_irq() from IRQ context. Lockdep should see this
and complain.

Acquire the locks in intel_engine_breadcrumbs_irq() with _irqsave()
suffix and let all callers invoke intel_engine_breadcrumbs_irq()
directly instead using intel_engine_signal_breadcrumbs().

Reported-by: Clark Williams <williams@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190926105644.16703-2-bigeasy@linutronix.de
---
 drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 16 +++++-----------
 drivers/gpu/drm/i915/gt/intel_engine.h      |  1 -
 drivers/gpu/drm/i915/gt/intel_hangcheck.c   |  2 +-
 drivers/gpu/drm/i915/gt/intel_reset.c       |  2 +-
 4 files changed, 7 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 0c6a1b11e259..55317081d48b 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -133,9 +133,10 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 	const ktime_t timestamp = ktime_get();
 	struct intel_context *ce, *cn;
 	struct list_head *pos, *next;
+	unsigned long flags;
 	LIST_HEAD(signal);
 
-	spin_lock(&b->irq_lock);
+	spin_lock_irqsave(&b->irq_lock, flags);
 
 	if (b->irq_armed && list_empty(&b->signalers))
 		__intel_breadcrumbs_disarm_irq(b);
@@ -181,30 +182,23 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 		}
 	}
 
-	spin_unlock(&b->irq_lock);
+	spin_unlock_irqrestore(&b->irq_lock, flags);
 
 	list_for_each_safe(pos, next, &signal) {
 		struct i915_request *rq =
 			list_entry(pos, typeof(*rq), signal_link);
 		struct list_head cb_list;
 
-		spin_lock(&rq->lock);
+		spin_lock_irqsave(&rq->lock, flags);
 		list_replace(&rq->fence.cb_list, &cb_list);
 		__dma_fence_signal__timestamp(&rq->fence, timestamp);
 		__dma_fence_signal__notify(&rq->fence, &cb_list);
-		spin_unlock(&rq->lock);
+		spin_unlock_irqrestore(&rq->lock, flags);
 
 		i915_request_put(rq);
 	}
 }
 
-void intel_engine_signal_breadcrumbs(struct intel_engine_cs *engine)
-{
-	local_irq_disable();
-	intel_engine_breadcrumbs_irq(engine);
-	local_irq_enable();
-}
-
 static void signal_irq_work(struct irq_work *work)
 {
 	struct intel_engine_cs *engine =
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index d3c6993f4f46..c9e8c8ccbd47 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -335,7 +335,6 @@ void intel_engine_init_execlists(struct intel_engine_cs *engine);
 void intel_engine_init_breadcrumbs(struct intel_engine_cs *engine);
 void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
 
-void intel_engine_signal_breadcrumbs(struct intel_engine_cs *engine);
 void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine);
 
 static inline void
diff --git a/drivers/gpu/drm/i915/gt/intel_hangcheck.c b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
index 40f62f780be5..9814b18b32ad 100644
--- a/drivers/gpu/drm/i915/gt/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
@@ -284,7 +284,7 @@ static void hangcheck_elapsed(struct work_struct *work)
 	for_each_engine(engine, gt->i915, id) {
 		struct hangcheck hc;
 
-		intel_engine_signal_breadcrumbs(engine);
+		intel_engine_breadcrumbs_irq(engine);
 
 		hangcheck_load_sample(engine, &hc);
 		hangcheck_accumulate_sample(engine, &hc);
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index ec978b4d1be3..d08226f5bea5 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -711,7 +711,7 @@ static void reset_finish_engine(struct intel_engine_cs *engine)
 	engine->reset.finish(engine);
 	intel_uncore_forcewake_put(engine->uncore, FORCEWAKE_ALL);
 
-	intel_engine_signal_breadcrumbs(engine);
+	intel_engine_breadcrumbs_irq(engine);
 }
 
 static void reset_finish(struct intel_gt *gt, intel_engine_mask_t awake)
-- 
cgit v1.2.3


From 56316cbc9c986ce907bfcf4f3762f2494e44f439 Mon Sep 17 00:00:00 2001
From: Anna Karas <anna.karas@intel.com>
Date: Thu, 26 Sep 2019 15:21:58 +0300
Subject: drm/i915/perf: Fix use of kernel-doc format in structure members

Insert structure members names into their descriptions to follow
kernel-doc format.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Anna Karas <anna.karas@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190926122158.13028-1-anna.karas@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index fcf7423075ef..b3c7dbc1832a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1134,7 +1134,7 @@ struct i915_perf_stream {
 	struct i915_oa_config *oa_config;
 
 	/**
-	 * The OA context specific information.
+	 * @pinned_ctx: The OA context specific information.
 	 */
 	struct intel_context *pinned_ctx;
 	u32 specific_ctx_id;
@@ -1148,7 +1148,7 @@ struct i915_perf_stream {
 	int period_exponent;
 
 	/**
-	 * State of the OA buffer.
+	 * @oa_buffer: State of the OA buffer.
 	 */
 	struct {
 		struct i915_vma *vma;
@@ -1159,7 +1159,7 @@ struct i915_perf_stream {
 		int size_exponent;
 
 		/**
-		 * Locks reads and writes to all head/tail state
+		 * @ptr_lock: Locks reads and writes to all head/tail state
 		 *
 		 * Consider: the head and tail pointer state needs to be read
 		 * consistently from a hrtimer callback (atomic context) and
@@ -1181,7 +1181,7 @@ struct i915_perf_stream {
 		spinlock_t ptr_lock;
 
 		/**
-		 * One 'aging' tail pointer and one 'aged' tail pointer ready to
+		 * @tails: One 'aging' tail pointer and one 'aged' tail pointer ready to
 		 * used for reading.
 		 *
 		 * Initial values of 0xffffffff are invalid and imply that an
@@ -1193,18 +1193,18 @@ struct i915_perf_stream {
 		} tails[2];
 
 		/**
-		 * Index for the aged tail ready to read() data up to.
+		 * @aged_tail_idx: Index for the aged tail ready to read() data up to.
 		 */
 		unsigned int aged_tail_idx;
 
 		/**
-		 * A monotonic timestamp for when the current aging tail pointer
+		 * @aging_timestamp: A monotonic timestamp for when the current aging tail pointer
 		 * was read; used to determine when it is old enough to trust.
 		 */
 		u64 aging_timestamp;
 
 		/**
-		 * Although we can always read back the head pointer register,
+		 * @head: Although we can always read back the head pointer register,
 		 * we prefer to avoid trusting the HW state, just to avoid any
 		 * risk that some hardware condition could * somehow bump the
 		 * head pointer unpredictably and cause us to forward the wrong
-- 
cgit v1.2.3


From f968688f44f529f96a64c9853fb2fb5d0a329aff Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 26 Sep 2019 12:44:39 +0900
Subject: nvme: Move ctrl sqsize to generic space

This isn't specific to fabrics.

Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/nvme.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b5013c101b35..38a83ef5bcd3 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -221,6 +221,7 @@ struct nvme_ctrl {
 	u16 oacs;
 	u16 nssa;
 	u16 nr_streams;
+	u16 sqsize;
 	u32 max_namespaces;
 	atomic_t abort_limit;
 	u8 vwc;
@@ -269,7 +270,6 @@ struct nvme_ctrl {
 	u16 hmmaxd;
 
 	/* Fabrics only */
-	u16 sqsize;
 	u32 ioccsz;
 	u32 iorcsz;
 	u16 icdoff;
-- 
cgit v1.2.3


From 74b2089a105f43c33d2f2124bd03d1085fe7c9fc Mon Sep 17 00:00:00 2001
From: Michał Winiarski <michal.winiarski@intel.com>
Date: Thu, 26 Sep 2019 12:06:33 +0200
Subject: drm/i915: Add definitions for MI_MATH command
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We can use it in i915 for updating parts of unmasked registers from
within a batch. We're also adding Gen8+ versions of CS_GPR registers
(aka MI_MATH_REG in the coprocessor).

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190926100635.9416-4-michal.winiarski@intel.com
---
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 23 +++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_reg.h              |  4 ++++
 2 files changed, 27 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 9211b1ad401b..b0227ab2fe1b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -241,6 +241,29 @@
 #define   PIPE_CONTROL_DEPTH_CACHE_FLUSH		(1<<0)
 #define   PIPE_CONTROL_GLOBAL_GTT (1<<2) /* in addr dword */
 
+#define MI_MATH(x)			MI_INSTR(0x1a, (x) - 1)
+#define MI_MATH_INSTR(opcode, op1, op2) ((opcode) << 20 | (op1) << 10 | (op2))
+/* Opcodes for MI_MATH_INSTR */
+#define   MI_MATH_NOOP			MI_MATH_INSTR(0x000, 0x0, 0x0)
+#define   MI_MATH_LOAD(op1, op2)	MI_MATH_INSTR(0x080, op1, op2)
+#define   MI_MATH_LOADINV(op1, op2)	MI_MATH_INSTR(0x480, op1, op2)
+#define   MI_MATH_LOAD0(op1)		MI_MATH_INSTR(0x081, op1)
+#define   MI_MATH_LOAD1(op1)		MI_MATH_INSTR(0x481, op1)
+#define   MI_MATH_ADD			MI_MATH_INSTR(0x100, 0x0, 0x0)
+#define   MI_MATH_SUB			MI_MATH_INSTR(0x101, 0x0, 0x0)
+#define   MI_MATH_AND			MI_MATH_INSTR(0x102, 0x0, 0x0)
+#define   MI_MATH_OR			MI_MATH_INSTR(0x103, 0x0, 0x0)
+#define   MI_MATH_XOR			MI_MATH_INSTR(0x104, 0x0, 0x0)
+#define   MI_MATH_STORE(op1, op2)	MI_MATH_INSTR(0x180, op1, op2)
+#define   MI_MATH_STOREINV(op1, op2)	MI_MATH_INSTR(0x580, op1, op2)
+/* Registers used as operands in MI_MATH_INSTR */
+#define   MI_MATH_REG(x)		(x)
+#define   MI_MATH_REG_SRCA		0x20
+#define   MI_MATH_REG_SRCB		0x21
+#define   MI_MATH_REG_ACCU		0x31
+#define   MI_MATH_REG_ZF		0x32
+#define   MI_MATH_REG_CF		0x33
+
 /*
  * Commands used only by the command parser
  */
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index e752de9470bd..5e30f1a14624 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2483,6 +2483,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   RING_WAIT		(1 << 11) /* gen3+, PRBx_CTL */
 #define   RING_WAIT_SEMAPHORE	(1 << 10) /* gen6+ */
 
+/* There are 16 64-bit CS General Purpose Registers per-engine on Gen8+ */
+#define GEN8_RING_CS_GPR(base, n)	_MMIO((base) + 0x600 + (n) * 8)
+#define GEN8_RING_CS_GPR_UDW(base, n)	_MMIO((base) + 0x600 + (n) * 8 + 4)
+
 #define RING_FORCE_TO_NONPRIV(base, i) _MMIO(((base) + 0x4D0) + (i) * 4)
 #define   RING_FORCE_TO_NONPRIV_ACCESS_RW	(0 << 28)    /* CFL+ & Gen11+ */
 #define   RING_FORCE_TO_NONPRIV_ACCESS_RD	(1 << 28)
-- 
cgit v1.2.3


From a0ecd6fdbf5d648123a7315c695fb6850d702835 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Tue, 24 Sep 2019 23:30:30 -0500
Subject: drm/komeda: prevent memory leak in komeda_wb_connector_add

In komeda_wb_connector_add if drm_writeback_connector_init fails the
allocated memory for kwb_conn should be released.

Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Reviewed-by: James Qian Wang (Arm Technology China) <james.qian.wang@arm.com>
Signed-off-by: james qian wang (Arm Technology China) <james.qian.wang@arm.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190925043031.32308-1-navid.emamdoost@gmail.com
---
 drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
index 23fbee268119..b72840c06ab7 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c
@@ -165,8 +165,10 @@ static int komeda_wb_connector_add(struct komeda_kms_dev *kms,
 					   &komeda_wb_encoder_helper_funcs,
 					   formats, n_formats);
 	komeda_put_fourcc_list(formats);
-	if (err)
+	if (err) {
+		kfree(kwb_conn);
 		return err;
+	}
 
 	drm_connector_helper_add(&wb_conn->base, &komeda_wb_conn_helper_funcs);
 
-- 
cgit v1.2.3


From a3f56e7da5231c902925711940835b6716f63f73 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 25 Sep 2019 20:34:46 +0100
Subject: drm/i915/selftests: Exercise concurrent submission to all engines

The simplest and most maximal submission we can do, a thread to submit
requests unto each engine.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190925193446.26007-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_request.c | 125 ++++++++++++++++++++++++++
 1 file changed, 125 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index b3688543ed7d..57cd4180d06c 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -1062,6 +1062,130 @@ out_unlock:
 	return err;
 }
 
+static int __live_parallel_engine1(void *arg)
+{
+	struct intel_engine_cs *engine = arg;
+	IGT_TIMEOUT(end_time);
+	unsigned long count;
+
+	count = 0;
+	do {
+		struct i915_request *rq;
+		int err;
+
+		mutex_lock(&engine->i915->drm.struct_mutex);
+		rq = i915_request_create(engine->kernel_context);
+		if (IS_ERR(rq)) {
+			mutex_unlock(&engine->i915->drm.struct_mutex);
+			return PTR_ERR(rq);
+		}
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+		mutex_unlock(&engine->i915->drm.struct_mutex);
+
+		err = 0;
+		if (i915_request_wait(rq, 0, HZ / 5) < 0)
+			err = -ETIME;
+		i915_request_put(rq);
+		if (err)
+			return err;
+
+		count++;
+	} while (!__igt_timeout(end_time, NULL));
+
+	pr_info("%s: %lu request + sync\n", engine->name, count);
+	return 0;
+}
+
+static int __live_parallel_engineN(void *arg)
+{
+	struct intel_engine_cs *engine = arg;
+	IGT_TIMEOUT(end_time);
+	unsigned long count;
+
+	count = 0;
+	do {
+		struct i915_request *rq;
+
+		mutex_lock(&engine->i915->drm.struct_mutex);
+		rq = i915_request_create(engine->kernel_context);
+		if (IS_ERR(rq)) {
+			mutex_unlock(&engine->i915->drm.struct_mutex);
+			return PTR_ERR(rq);
+		}
+
+		i915_request_add(rq);
+		mutex_unlock(&engine->i915->drm.struct_mutex);
+
+		count++;
+	} while (!__igt_timeout(end_time, NULL));
+
+	pr_info("%s: %lu requests\n", engine->name, count);
+	return 0;
+}
+
+static int live_parallel_engines(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	static int (* const func[])(void *arg) = {
+		__live_parallel_engine1,
+		__live_parallel_engineN,
+		NULL,
+	};
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int (* const *fn)(void *arg);
+	int err = 0;
+
+	/*
+	 * Check we can submit requests to all engines concurrently. This
+	 * tests that we load up the system maximally.
+	 */
+
+	for (fn = func; !err && *fn; fn++) {
+		struct task_struct *tsk[I915_NUM_ENGINES] = {};
+		struct igt_live_test t;
+
+		mutex_lock(&i915->drm.struct_mutex);
+		err = igt_live_test_begin(&t, i915, __func__, "");
+		mutex_unlock(&i915->drm.struct_mutex);
+		if (err)
+			break;
+
+		for_each_engine(engine, i915, id) {
+			tsk[id] = kthread_run(*fn, engine,
+					      "igt/parallel:%s",
+					      engine->name);
+			if (IS_ERR(tsk[id])) {
+				err = PTR_ERR(tsk[id]);
+				break;
+			}
+			get_task_struct(tsk[id]);
+		}
+
+		for_each_engine(engine, i915, id) {
+			int status;
+
+			if (IS_ERR_OR_NULL(tsk[id]))
+				continue;
+
+			status = kthread_stop(tsk[id]);
+			if (status && !err)
+				err = status;
+
+			put_task_struct(tsk[id]);
+		}
+
+		mutex_lock(&i915->drm.struct_mutex);
+		if (igt_live_test_end(&t))
+			err = -EIO;
+		mutex_unlock(&i915->drm.struct_mutex);
+	}
+
+	return err;
+}
+
 static int
 max_batches(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 {
@@ -1240,6 +1364,7 @@ int i915_request_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_nop_request),
 		SUBTEST(live_all_engines),
 		SUBTEST(live_sequential_engines),
+		SUBTEST(live_parallel_engines),
 		SUBTEST(live_empty_request),
 		SUBTEST(live_breadcrumbs_smoketest),
 	};
-- 
cgit v1.2.3


From 6eeb4ef049e7cd89783e8ebe1ea2f1dac276f82c Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Tue, 24 Sep 2019 12:43:08 +0200
Subject: KVM: x86: assign two bits to track SPTE kinds

Currently, we are overloading SPTE_SPECIAL_MASK to mean both
"A/D bits unavailable" and MMIO, where the difference between the
two is determined by mio_mask and mmio_value.

However, the next patch will need two bits to distinguish
availability of A/D bits from write protection.  So, while at
it give MMIO its own bit pattern, and move the two bits from
bit 62 to bits 52..53 since Intel is allocating EPT page table
bits from the top.

Reviewed-by: Junaid Shahid <junaids@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |  7 -------
 arch/x86/kvm/mmu.c              | 28 ++++++++++++++++++----------
 2 files changed, 18 insertions(+), 17 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 23edf56cf577..50eb430b0ad8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -219,13 +219,6 @@ enum {
 				 PFERR_WRITE_MASK |		\
 				 PFERR_PRESENT_MASK)
 
-/*
- * The mask used to denote special SPTEs, which can be either MMIO SPTEs or
- * Access Tracking SPTEs. We use bit 62 instead of bit 63 to avoid conflicting
- * with the SVE bit in EPT PTEs.
- */
-#define SPTE_SPECIAL_MASK (1ULL << 62)
-
 /* apic attention bits */
 #define KVM_APIC_CHECK_VAPIC	0
 /*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 5269aa057dfa..bac8d228d82b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -83,7 +83,16 @@ module_param(dbg, bool, 0644);
 #define PTE_PREFETCH_NUM		8
 
 #define PT_FIRST_AVAIL_BITS_SHIFT 10
-#define PT64_SECOND_AVAIL_BITS_SHIFT 52
+#define PT64_SECOND_AVAIL_BITS_SHIFT 54
+
+/*
+ * The mask used to denote special SPTEs, which can be either MMIO SPTEs or
+ * Access Tracking SPTEs.
+ */
+#define SPTE_SPECIAL_MASK (3ULL << 52)
+#define SPTE_AD_ENABLED_MASK (0ULL << 52)
+#define SPTE_AD_DISABLED_MASK (1ULL << 52)
+#define SPTE_MMIO_MASK (3ULL << 52)
 
 #define PT64_LEVEL_BITS 9
 
@@ -219,12 +228,11 @@ static u64 __read_mostly shadow_present_mask;
 static u64 __read_mostly shadow_me_mask;
 
 /*
- * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value.
- * Non-present SPTEs with shadow_acc_track_value set are in place for access
- * tracking.
+ * SPTEs used by MMUs without A/D bits are marked with SPTE_AD_DISABLED_MASK;
+ * shadow_acc_track_mask is the set of bits to be cleared in non-accessed
+ * pages.
  */
 static u64 __read_mostly shadow_acc_track_mask;
-static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK;
 
 /*
  * The mask/shift to use for saving the original R/X bits when marking the PTE
@@ -304,7 +312,7 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask)
 {
 	BUG_ON((u64)(unsigned)access_mask != access_mask);
 	BUG_ON((mmio_mask & mmio_value) != mmio_value);
-	shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK;
+	shadow_mmio_value = mmio_value | SPTE_MMIO_MASK;
 	shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK;
 	shadow_mmio_access_mask = access_mask;
 }
@@ -323,7 +331,7 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
 static inline bool spte_ad_enabled(u64 spte)
 {
 	MMU_WARN_ON(is_mmio_spte(spte));
-	return !(spte & shadow_acc_track_value);
+	return (spte & SPTE_SPECIAL_MASK) == SPTE_AD_ENABLED_MASK;
 }
 
 static inline u64 spte_shadow_accessed_mask(u64 spte)
@@ -461,7 +469,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 {
 	BUG_ON(!dirty_mask != !accessed_mask);
 	BUG_ON(!accessed_mask && !acc_track_mask);
-	BUG_ON(acc_track_mask & shadow_acc_track_value);
+	BUG_ON(acc_track_mask & SPTE_SPECIAL_MASK);
 
 	shadow_user_mask = user_mask;
 	shadow_accessed_mask = accessed_mask;
@@ -2622,7 +2630,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
 	       shadow_user_mask | shadow_x_mask | shadow_me_mask;
 
 	if (sp_ad_disabled(sp))
-		spte |= shadow_acc_track_value;
+		spte |= SPTE_AD_DISABLED_MASK;
 	else
 		spte |= shadow_accessed_mask;
 
@@ -2968,7 +2976,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 
 	sp = page_header(__pa(sptep));
 	if (sp_ad_disabled(sp))
-		spte |= shadow_acc_track_value;
+		spte |= SPTE_AD_DISABLED_MASK;
 
 	/*
 	 * For the EPT case, shadow_present_mask is 0 if hardware
-- 
cgit v1.2.3


From 1f4e5fc83a4217fc61b23370b07573827329d7bd Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 26 Sep 2019 18:47:59 +0200
Subject: KVM: x86: fix nested guest live migration with PML

Shadow paging is fundamentally incompatible with the page-modification
log, because the GPAs in the log come from the wrong memory map.
In particular, for the EPT page-modification log, the GPAs in the log come
from L2 rather than L1.  (If there was a non-EPT page-modification log,
we couldn't use it for shadow paging because it would log GVAs rather
than GPAs).

Therefore, we need to rely on write protection to record dirty pages.
This has the side effect of bypassing PML, since writes now result in an
EPT violation vmexit.

This is relatively easy to add to KVM, because pretty much the only place
that needs changing is spte_clear_dirty.  The first access to the page
already goes through the page fault path and records the correct GPA;
it's only subsequent accesses that are wrong.  Therefore, we can equip
set_spte (where the first access happens) to record that the SPTE will
have to be write protected, and then spte_clear_dirty will use this
information to do the right thing.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu.c | 39 ++++++++++++++++++++++++++++++++-------
 1 file changed, 32 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index bac8d228d82b..24c23c66b226 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -92,6 +92,7 @@ module_param(dbg, bool, 0644);
 #define SPTE_SPECIAL_MASK (3ULL << 52)
 #define SPTE_AD_ENABLED_MASK (0ULL << 52)
 #define SPTE_AD_DISABLED_MASK (1ULL << 52)
+#define SPTE_AD_WRPROT_ONLY_MASK (2ULL << 52)
 #define SPTE_MMIO_MASK (3ULL << 52)
 
 #define PT64_LEVEL_BITS 9
@@ -328,10 +329,27 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
 	return sp->role.ad_disabled;
 }
 
+static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * When using the EPT page-modification log, the GPAs in the log
+	 * would come from L2 rather than L1.  Therefore, we need to rely
+	 * on write protection to record dirty pages.  This also bypasses
+	 * PML, since writes now result in a vmexit.
+	 */
+	return vcpu->arch.mmu == &vcpu->arch.guest_mmu;
+}
+
 static inline bool spte_ad_enabled(u64 spte)
 {
 	MMU_WARN_ON(is_mmio_spte(spte));
-	return (spte & SPTE_SPECIAL_MASK) == SPTE_AD_ENABLED_MASK;
+	return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_DISABLED_MASK;
+}
+
+static inline bool spte_ad_need_write_protect(u64 spte)
+{
+	MMU_WARN_ON(is_mmio_spte(spte));
+	return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK;
 }
 
 static inline u64 spte_shadow_accessed_mask(u64 spte)
@@ -1597,16 +1615,16 @@ static bool spte_clear_dirty(u64 *sptep)
 
 	rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep);
 
+	MMU_WARN_ON(!spte_ad_enabled(spte));
 	spte &= ~shadow_dirty_mask;
-
 	return mmu_spte_update(sptep, spte);
 }
 
-static bool wrprot_ad_disabled_spte(u64 *sptep)
+static bool spte_wrprot_for_clear_dirty(u64 *sptep)
 {
 	bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT,
 					       (unsigned long *)sptep);
-	if (was_writable)
+	if (was_writable && !spte_ad_enabled(*sptep))
 		kvm_set_pfn_dirty(spte_to_pfn(*sptep));
 
 	return was_writable;
@@ -1625,10 +1643,10 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
 	bool flush = false;
 
 	for_each_rmap_spte(rmap_head, &iter, sptep)
-		if (spte_ad_enabled(*sptep))
-			flush |= spte_clear_dirty(sptep);
+		if (spte_ad_need_write_protect(*sptep))
+			flush |= spte_wrprot_for_clear_dirty(sptep);
 		else
-			flush |= wrprot_ad_disabled_spte(sptep);
+			flush |= spte_clear_dirty(sptep);
 
 	return flush;
 }
@@ -1639,6 +1657,11 @@ static bool spte_set_dirty(u64 *sptep)
 
 	rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep);
 
+	/*
+	 * Similar to the !kvm_x86_ops->slot_disable_log_dirty case,
+	 * do not bother adding back write access to pages marked
+	 * SPTE_AD_WRPROT_ONLY_MASK.
+	 */
 	spte |= shadow_dirty_mask;
 
 	return mmu_spte_update(sptep, spte);
@@ -2977,6 +3000,8 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	sp = page_header(__pa(sptep));
 	if (sp_ad_disabled(sp))
 		spte |= SPTE_AD_DISABLED_MASK;
+	else if (kvm_vcpu_ad_need_write_protect(vcpu))
+		spte |= SPTE_AD_WRPROT_ONLY_MASK;
 
 	/*
 	 * For the EPT case, shadow_present_mask is 0 if hardware
-- 
cgit v1.2.3


From 094444204570a5420d9e6ce3d4558877c3487856 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Thu, 26 Sep 2019 15:01:15 +0200
Subject: selftests: kvm: add test for dirty logging inside nested guests

Check that accesses by nested guests are logged according to the
L1 physical addresses rather than L2.

Most of the patch is really adding EPT support to the testing
framework.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile               |   1 +
 .../selftests/kvm/include/x86_64/processor.h       |   3 +
 tools/testing/selftests/kvm/include/x86_64/vmx.h   |  14 ++
 tools/testing/selftests/kvm/lib/kvm_util.c         |   2 +-
 .../testing/selftests/kvm/lib/kvm_util_internal.h  |   3 +
 tools/testing/selftests/kvm/lib/x86_64/vmx.c       | 201 ++++++++++++++++++++-
 .../selftests/kvm/x86_64/vmx_dirty_log_test.c      | 156 ++++++++++++++++
 7 files changed, 377 insertions(+), 3 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 62c591f87dab..fd84b7a78dcf 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -22,6 +22,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/smm_test
 TEST_GEN_PROGS_x86_64 += x86_64/state_test
 TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
+TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 0c17f2ee685e..ff234018219c 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -1083,6 +1083,9 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits);
 #define VMX_BASIC_MEM_TYPE_WB	6LLU
 #define VMX_BASIC_INOUT		0x0040000000000000LLU
 
+/* VMX_EPT_VPID_CAP bits */
+#define VMX_EPT_VPID_CAP_AD_BITS	(1ULL << 21)
+
 /* MSR_IA32_VMX_MISC bits */
 #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
 #define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE   0x1F
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 69b17055f63d..6ae5a47fe067 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -569,6 +569,10 @@ struct vmx_pages {
 	void *enlightened_vmcs_hva;
 	uint64_t enlightened_vmcs_gpa;
 	void *enlightened_vmcs;
+
+	void *eptp_hva;
+	uint64_t eptp_gpa;
+	void *eptp;
 };
 
 struct vmx_pages *vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva);
@@ -576,4 +580,14 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx);
 void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
 bool load_vmcs(struct vmx_pages *vmx);
 
+void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		   uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot);
+void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		 uint64_t nested_paddr, uint64_t paddr, uint64_t size,
+		 uint32_t eptp_memslot);
+void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
+			uint32_t memslot, uint32_t eptp_memslot);
+void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
+		  uint32_t eptp_memslot);
+
 #endif /* SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 80a338b5403c..41cf45416060 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -705,7 +705,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
  *   on error (e.g. currently no memory region using memslot as a KVM
  *   memory slot ID).
  */
-static struct userspace_mem_region *
+struct userspace_mem_region *
 memslot2region(struct kvm_vm *vm, uint32_t memslot)
 {
 	struct userspace_mem_region *region;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
index f36262e0f655..ac50c42750cf 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -68,4 +68,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
 void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent);
 void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent);
 
+struct userspace_mem_region *
+memslot2region(struct kvm_vm *vm, uint32_t memslot);
+
 #endif /* SELFTEST_KVM_UTIL_INTERNAL_H */
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index 9cef0455b819..fab8f6b0bf52 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -7,11 +7,39 @@
 
 #include "test_util.h"
 #include "kvm_util.h"
+#include "../kvm_util_internal.h"
 #include "processor.h"
 #include "vmx.h"
 
+#define PAGE_SHIFT_4K  12
+
+#define KVM_EPT_PAGE_TABLE_MIN_PADDR 0x1c0000
+
 bool enable_evmcs;
 
+struct eptPageTableEntry {
+	uint64_t readable:1;
+	uint64_t writable:1;
+	uint64_t executable:1;
+	uint64_t memory_type:3;
+	uint64_t ignore_pat:1;
+	uint64_t page_size:1;
+	uint64_t accessed:1;
+	uint64_t dirty:1;
+	uint64_t ignored_11_10:2;
+	uint64_t address:40;
+	uint64_t ignored_62_52:11;
+	uint64_t suppress_ve:1;
+};
+
+struct eptPageTablePointer {
+	uint64_t memory_type:3;
+	uint64_t page_walk_length:3;
+	uint64_t ad_enabled:1;
+	uint64_t reserved_11_07:5;
+	uint64_t address:40;
+	uint64_t reserved_63_52:12;
+};
 int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id)
 {
 	uint16_t evmcs_ver;
@@ -174,15 +202,35 @@ bool load_vmcs(struct vmx_pages *vmx)
  */
 static inline void init_vmcs_control_fields(struct vmx_pages *vmx)
 {
+	uint32_t sec_exec_ctl = 0;
+
 	vmwrite(VIRTUAL_PROCESSOR_ID, 0);
 	vmwrite(POSTED_INTR_NV, 0);
 
 	vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PINBASED_CTLS));
-	if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, 0))
+
+	if (vmx->eptp_gpa) {
+		uint64_t ept_paddr;
+		struct eptPageTablePointer eptp = {
+			.memory_type = VMX_BASIC_MEM_TYPE_WB,
+			.page_walk_length = 3, /* + 1 */
+			.ad_enabled = !!(rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & VMX_EPT_VPID_CAP_AD_BITS),
+			.address = vmx->eptp_gpa >> PAGE_SHIFT_4K,
+		};
+
+		memcpy(&ept_paddr, &eptp, sizeof(ept_paddr));
+		vmwrite(EPT_POINTER, ept_paddr);
+		sec_exec_ctl |= SECONDARY_EXEC_ENABLE_EPT;
+	}
+
+	if (!vmwrite(SECONDARY_VM_EXEC_CONTROL, sec_exec_ctl))
 		vmwrite(CPU_BASED_VM_EXEC_CONTROL,
 			rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS);
-	else
+	else {
 		vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS));
+		GUEST_ASSERT(!sec_exec_ctl);
+	}
+
 	vmwrite(EXCEPTION_BITMAP, 0);
 	vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0);
 	vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */
@@ -327,3 +375,152 @@ void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp)
 	init_vmcs_host_state();
 	init_vmcs_guest_state(guest_rip, guest_rsp);
 }
+
+void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+	 	   uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot)
+{
+	uint16_t index[4];
+	struct eptPageTableEntry *pml4e;
+
+	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
+		    "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+	TEST_ASSERT((nested_paddr % vm->page_size) == 0,
+		    "Nested physical address not on page boundary,\n"
+		    "  nested_paddr: 0x%lx vm->page_size: 0x%x",
+		    nested_paddr, vm->page_size);
+	TEST_ASSERT((nested_paddr >> vm->page_shift) <= vm->max_gfn,
+		    "Physical address beyond beyond maximum supported,\n"
+		    "  nested_paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+		    paddr, vm->max_gfn, vm->page_size);
+	TEST_ASSERT((paddr % vm->page_size) == 0,
+		    "Physical address not on page boundary,\n"
+		    "  paddr: 0x%lx vm->page_size: 0x%x",
+		    paddr, vm->page_size);
+	TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+		    "Physical address beyond beyond maximum supported,\n"
+		    "  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+		    paddr, vm->max_gfn, vm->page_size);
+
+	index[0] = (nested_paddr >> 12) & 0x1ffu;
+	index[1] = (nested_paddr >> 21) & 0x1ffu;
+	index[2] = (nested_paddr >> 30) & 0x1ffu;
+	index[3] = (nested_paddr >> 39) & 0x1ffu;
+
+	/* Allocate page directory pointer table if not present. */
+	pml4e = vmx->eptp_hva;
+	if (!pml4e[index[3]].readable) {
+		pml4e[index[3]].address = vm_phy_page_alloc(vm,
+			  KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot)
+			>> vm->page_shift;
+		pml4e[index[3]].writable = true;
+		pml4e[index[3]].readable = true;
+		pml4e[index[3]].executable = true;
+	}
+
+	/* Allocate page directory table if not present. */
+	struct eptPageTableEntry *pdpe;
+	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+	if (!pdpe[index[2]].readable) {
+		pdpe[index[2]].address = vm_phy_page_alloc(vm,
+			  KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot)
+			>> vm->page_shift;
+		pdpe[index[2]].writable = true;
+		pdpe[index[2]].readable = true;
+		pdpe[index[2]].executable = true;
+	}
+
+	/* Allocate page table if not present. */
+	struct eptPageTableEntry *pde;
+	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+	if (!pde[index[1]].readable) {
+		pde[index[1]].address = vm_phy_page_alloc(vm,
+			  KVM_EPT_PAGE_TABLE_MIN_PADDR, eptp_memslot)
+			>> vm->page_shift;
+		pde[index[1]].writable = true;
+		pde[index[1]].readable = true;
+		pde[index[1]].executable = true;
+	}
+
+	/* Fill in page table entry. */
+	struct eptPageTableEntry *pte;
+	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+	pte[index[0]].address = paddr >> vm->page_shift;
+	pte[index[0]].writable = true;
+	pte[index[0]].readable = true;
+	pte[index[0]].executable = true;
+
+	/*
+	 * For now mark these as accessed and dirty because the only
+	 * testcase we have needs that.  Can be reconsidered later.
+	 */
+	pte[index[0]].accessed = true;
+	pte[index[0]].dirty = true;
+}
+
+/*
+ * Map a range of EPT guest physical addresses to the VM's physical address
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   nested_paddr - Nested guest physical address to map
+ *   paddr - VM Physical Address
+ *   size - The size of the range to map
+ *   eptp_memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Within the VM given by vm, creates a nested guest translation for the
+ * page range starting at nested_paddr to the page range starting at paddr.
+ */
+void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		uint64_t nested_paddr, uint64_t paddr, uint64_t size,
+		uint32_t eptp_memslot)
+{
+	size_t page_size = vm->page_size;
+	size_t npages = size / page_size;
+
+	TEST_ASSERT(nested_paddr + size > nested_paddr, "Vaddr overflow");
+	TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
+
+	while (npages--) {
+		nested_pg_map(vmx, vm, nested_paddr, paddr, eptp_memslot);
+		nested_paddr += page_size;
+		paddr += page_size;
+	}
+}
+
+/* Prepare an identity extended page table that maps all the
+ * physical pages in VM.
+ */
+void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
+			uint32_t memslot, uint32_t eptp_memslot)
+{
+	sparsebit_idx_t i, last;
+	struct userspace_mem_region *region =
+		memslot2region(vm, memslot);
+
+	i = (region->region.guest_phys_addr >> vm->page_shift) - 1;
+	last = i + (region->region.memory_size >> vm->page_shift);
+	for (;;) {
+		i = sparsebit_next_clear(region->unused_phy_pages, i);
+		if (i > last)
+			break;
+
+		nested_map(vmx, vm,
+			   (uint64_t)i << vm->page_shift,
+			   (uint64_t)i << vm->page_shift,
+			   1 << vm->page_shift,
+			   eptp_memslot);
+	}
+}
+
+void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
+		  uint32_t eptp_memslot)
+{
+	vmx->eptp = (void *)vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+	vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp);
+	vmx->eptp_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->eptp);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
new file mode 100644
index 000000000000..0bca1cfe2c1e
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM dirty page logging test
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "vmx.h"
+
+#define VCPU_ID				1
+
+/* The memory slot index to track dirty pages */
+#define TEST_MEM_SLOT_INDEX		1
+#define TEST_MEM_SIZE			3
+
+/* L1 guest test virtual memory offset */
+#define GUEST_TEST_MEM			0xc0000000
+
+/* L2 guest test virtual memory offset */
+#define NESTED_TEST_MEM1		0xc0001000
+#define NESTED_TEST_MEM2		0xc0002000
+
+static void l2_guest_code(void)
+{
+	*(volatile uint64_t *)NESTED_TEST_MEM1;
+	*(volatile uint64_t *)NESTED_TEST_MEM1 = 1;
+	GUEST_SYNC(true);
+	GUEST_SYNC(false);
+
+	*(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+	GUEST_SYNC(true);
+	*(volatile uint64_t *)NESTED_TEST_MEM2 = 1;
+	GUEST_SYNC(true);
+	GUEST_SYNC(false);
+
+	/* Exit to L1 and never come back.  */
+	vmcall();
+}
+
+void l1_guest_code(struct vmx_pages *vmx)
+{
+#define L2_GUEST_STACK_SIZE 64
+	unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+	GUEST_ASSERT(vmx->vmcs_gpa);
+	GUEST_ASSERT(prepare_for_vmx_operation(vmx));
+	GUEST_ASSERT(load_vmcs(vmx));
+
+	prepare_vmcs(vmx, l2_guest_code,
+		     &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+	GUEST_SYNC(false);
+	GUEST_ASSERT(!vmlaunch());
+	GUEST_SYNC(false);
+	GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+	GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+	vm_vaddr_t vmx_pages_gva = 0;
+	struct vmx_pages *vmx;
+	unsigned long *bmap;
+	uint64_t *host_test_mem;
+
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	struct ucall uc;
+	bool done = false;
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, l1_guest_code);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+	vmx = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+	vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+	run = vcpu_state(vm, VCPU_ID);
+
+	/* Add an extra memory slot for testing dirty logging */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    GUEST_TEST_MEM,
+				    TEST_MEM_SLOT_INDEX,
+				    TEST_MEM_SIZE,
+				    KVM_MEM_LOG_DIRTY_PAGES);
+
+	/*
+	 * Add an identity map for GVA range [0xc0000000, 0xc0002000).  This
+	 * affects both L1 and L2.  However...
+	 */
+	virt_map(vm, GUEST_TEST_MEM, GUEST_TEST_MEM,
+		 TEST_MEM_SIZE * 4096, 0);
+
+	/*
+	 * ... pages in the L2 GPA range [0xc0001000, 0xc0003000) will map to
+	 * 0xc0000000.
+	 *
+	 * Note that prepare_eptp should be called only L1's GPA map is done,
+	 * meaning after the last call to virt_map.
+	 */
+	prepare_eptp(vmx, vm, 0);
+	nested_map_memslot(vmx, vm, 0, 0);
+	nested_map(vmx, vm, NESTED_TEST_MEM1, GUEST_TEST_MEM, 4096, 0);
+	nested_map(vmx, vm, NESTED_TEST_MEM2, GUEST_TEST_MEM, 4096, 0);
+
+	bmap = bitmap_alloc(TEST_MEM_SIZE);
+	host_test_mem = addr_gpa2hva(vm, GUEST_TEST_MEM);
+
+	while (!done) {
+		memset(host_test_mem, 0xaa, TEST_MEM_SIZE * 4096);
+		_vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Unexpected exit reason: %u (%s),\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
+				    __FILE__, uc.args[1]);
+			/* NOT REACHED */
+		case UCALL_SYNC:
+			/*
+			 * The nested guest wrote at offset 0x1000 in the memslot, but the
+			 * dirty bitmap must be filled in according to L1 GPA, not L2.
+			 */
+			kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
+			if (uc.args[1]) {
+				TEST_ASSERT(test_bit(0, bmap), "Page 0 incorrectly reported clean\n");
+				TEST_ASSERT(host_test_mem[0] == 1, "Page 0 not written by guest\n");
+			} else {
+				TEST_ASSERT(!test_bit(0, bmap), "Page 0 incorrectly reported dirty\n");
+				TEST_ASSERT(host_test_mem[0] == 0xaaaaaaaaaaaaaaaaULL, "Page 0 written by guest\n");
+			}
+
+			TEST_ASSERT(!test_bit(1, bmap), "Page 1 incorrectly reported dirty\n");
+			TEST_ASSERT(host_test_mem[4096 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 1 written by guest\n");
+			TEST_ASSERT(!test_bit(2, bmap), "Page 2 incorrectly reported dirty\n");
+			TEST_ASSERT(host_test_mem[8192 / 8] == 0xaaaaaaaaaaaaaaaaULL, "Page 2 written by guest\n");
+			break;
+		case UCALL_DONE:
+			done = true;
+			break;
+		default:
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
+		}
+	}
+}
-- 
cgit v1.2.3


From c113236718e89561f309705f1a78126b3df93a21 Mon Sep 17 00:00:00 2001
From: Andi Shyti <andi.shyti@intel.com>
Date: Fri, 27 Sep 2019 12:08:49 +0100
Subject: drm/i915: Extract GT render sleep (rc6) management

Continuing the theme of breaking intel_pm.c up in a reasonable chunk of
powermanagement utilities, pull out the rc6 setup into its GT handler.

Based on a patch by Chris Wilson.

Signed-off-by: Andi Shyti <andi.shyti@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919143840.20384-1-andi.shyti@intel.com
Link: https://patchwork.freedesktop.org/patch/msgid/20190927110849.28734-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/Makefile                      |   1 +
 drivers/gpu/drm/i915/gem/i915_gem_pm.c             |   2 +-
 drivers/gpu/drm/i915/gt/intel_engine_pm.c          |   1 +
 drivers/gpu/drm/i915/gt/intel_gt.c                 |   5 +-
 drivers/gpu/drm/i915/gt/intel_gt_pm.c              |  92 ++-
 drivers/gpu/drm/i915/gt/intel_gt_pm.h              |  11 +-
 drivers/gpu/drm/i915/gt/intel_gt_types.h           |   3 +
 drivers/gpu/drm/i915/gt/intel_rc6.c                | 712 ++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_rc6.h                |  25 +
 drivers/gpu/drm/i915/gt/intel_rc6_types.h          |  28 +
 drivers/gpu/drm/i915/gt/selftest_gt_pm.c           |  50 ++
 drivers/gpu/drm/i915/i915_debugfs.c                |  11 +-
 drivers/gpu/drm/i915/i915_drv.h                    |   7 -
 drivers/gpu/drm/i915/i915_pmu.c                    |   9 +-
 drivers/gpu/drm/i915/i915_sysfs.c                  |   4 +-
 drivers/gpu/drm/i915/intel_pm.c                    | 794 +--------------------
 drivers/gpu/drm/i915/intel_pm.h                    |   3 -
 .../gpu/drm/i915/selftests/i915_live_selftests.h   |   1 +
 18 files changed, 916 insertions(+), 843 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/gt/intel_rc6.c
 create mode 100644 drivers/gpu/drm/i915/gt/intel_rc6.h
 create mode 100644 drivers/gpu/drm/i915/gt/intel_rc6_types.h
 create mode 100644 drivers/gpu/drm/i915/gt/selftest_gt_pm.c

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 6313e7b4bd78..8d407ff7d59d 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -85,6 +85,7 @@ gt-y += \
 	gt/intel_gt_pm_irq.o \
 	gt/intel_hangcheck.o \
 	gt/intel_lrc.o \
+	gt/intel_rc6.o \
 	gt/intel_renderstate.o \
 	gt/intel_reset.o \
 	gt/intel_ringbuffer.o \
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index a11ad4d914ca..cca192ecff8b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -137,7 +137,6 @@ static bool switch_to_kernel_context_sync(struct intel_gt *gt)
 
 bool i915_gem_load_power_context(struct drm_i915_private *i915)
 {
-	intel_gt_pm_enable(&i915->gt);
 	return switch_to_kernel_context_sync(&i915->gt);
 }
 
@@ -188,6 +187,7 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	i915_gem_drain_freed_objects(i915);
 
 	intel_uc_suspend(&i915->gt.uc);
+	intel_gt_suspend(&i915->gt);
 }
 
 static struct drm_i915_gem_object *first_mm_object(struct list_head *list)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index ce61c83d68e9..66fc49b76ea8 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -11,6 +11,7 @@
 #include "intel_engine_pool.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
+#include "intel_rc6.h"
 
 static int __engine_unpark(struct intel_wakeref *wf)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index eef9bdae8ebb..0e5909ee0657 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -7,6 +7,7 @@
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_mocs.h"
+#include "intel_rc6.h"
 #include "intel_uncore.h"
 #include "intel_pm.h"
 
@@ -369,6 +370,8 @@ int intel_gt_init(struct intel_gt *gt)
 	if (err)
 		return err;
 
+	intel_gt_pm_init(gt);
+
 	return 0;
 }
 
@@ -387,8 +390,8 @@ void intel_gt_driver_release(struct intel_gt *gt)
 {
 	/* Paranoia: make sure we have disabled everything before we exit. */
 	intel_gt_pm_disable(gt);
+	intel_gt_pm_fini(gt);
 
-	intel_cleanup_gt_powersave(gt->i915);
 	intel_gt_fini_scratch(gt);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 2ccf8cacaa0a..42f175d9b98c 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -11,6 +11,7 @@
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_pm.h"
+#include "intel_rc6.h"
 #include "intel_wakeref.h"
 
 static void pm_notify(struct intel_gt *gt, int state)
@@ -90,6 +91,16 @@ void intel_gt_pm_init_early(struct intel_gt *gt)
 	BLOCKING_INIT_NOTIFIER_HEAD(&gt->pm_notifications);
 }
 
+void intel_gt_pm_init(struct intel_gt *gt)
+{
+	/*
+	 * Enabling power-management should be "self-healing". If we cannot
+	 * enable a feature, simply leave it disabled with a notice to the
+	 * user.
+	 */
+	intel_rc6_init(&gt->rc6);
+}
+
 static bool reset_engines(struct intel_gt *gt)
 {
 	if (INTEL_INFO(gt->i915)->gpu_reset_clobbers_display)
@@ -124,40 +135,14 @@ void intel_gt_sanitize(struct intel_gt *gt, bool force)
 		__intel_engine_reset(engine, false);
 }
 
-static bool is_mock_device(const struct intel_gt *gt)
-{
-	return I915_SELFTEST_ONLY(gt->awake == -1);
-}
-
-void intel_gt_pm_enable(struct intel_gt *gt)
+void intel_gt_pm_disable(struct intel_gt *gt)
 {
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-
-	/* Powersaving is controlled by the host when inside a VM */
-	if (intel_vgpu_active(gt->i915))
-		return;
-
-	if (is_mock_device(gt))
-		return;
-
-	intel_gt_pm_get(gt);
-
-	for_each_engine(engine, gt->i915, id) {
-		intel_engine_pm_get(engine);
-		engine->serial++; /* force kernel context reload */
-		intel_engine_pm_put(engine);
-	}
-
-	intel_gt_pm_put(gt);
+	intel_sanitize_gt_powersave(gt->i915);
 }
 
-void intel_gt_pm_disable(struct intel_gt *gt)
+void intel_gt_pm_fini(struct intel_gt *gt)
 {
-	if (is_mock_device(gt))
-		return;
-
-	intel_sanitize_gt_powersave(gt->i915);
+	intel_rc6_fini(&gt->rc6);
 }
 
 int intel_gt_resume(struct intel_gt *gt)
@@ -173,6 +158,9 @@ int intel_gt_resume(struct intel_gt *gt)
 	 * allowing us to fixup the user contexts on their first pin.
 	 */
 	intel_gt_pm_get(gt);
+	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
+	intel_rc6_sanitize(&gt->rc6);
+
 	for_each_engine(engine, gt->i915, id) {
 		struct intel_context *ce;
 
@@ -197,11 +185,51 @@ int intel_gt_resume(struct intel_gt *gt)
 			break;
 		}
 	}
+
+	intel_rc6_enable(&gt->rc6);
+	intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
 	intel_gt_pm_put(gt);
 
 	return err;
 }
 
+static void wait_for_idle(struct intel_gt *gt)
+{
+	mutex_lock(&gt->i915->drm.struct_mutex); /* XXX */
+	do {
+		if (i915_gem_wait_for_idle(gt->i915,
+					   I915_WAIT_LOCKED,
+					   I915_GEM_IDLE_TIMEOUT) == -ETIME) {
+			/* XXX hide warning from gem_eio */
+			if (i915_modparams.reset) {
+				dev_err(gt->i915->drm.dev,
+					"Failed to idle engines, declaring wedged!\n");
+				GEM_TRACE_DUMP();
+			}
+
+			/*
+			 * Forcibly cancel outstanding work and leave
+			 * the gpu quiet.
+			 */
+			intel_gt_set_wedged(gt);
+		}
+	} while (i915_retire_requests(gt->i915));
+	mutex_unlock(&gt->i915->drm.struct_mutex);
+
+	intel_gt_pm_wait_for_idle(gt);
+}
+
+void intel_gt_suspend(struct intel_gt *gt)
+{
+	intel_wakeref_t wakeref;
+
+	/* We expect to be idle already; but also want to be independent */
+	wait_for_idle(gt);
+
+	with_intel_runtime_pm(&gt->i915->runtime_pm, wakeref)
+		intel_rc6_disable(&gt->rc6);
+}
+
 void intel_gt_runtime_suspend(struct intel_gt *gt)
 {
 	intel_uc_runtime_suspend(&gt->uc);
@@ -213,3 +241,7 @@ int intel_gt_runtime_resume(struct intel_gt *gt)
 
 	return intel_uc_runtime_resume(&gt->uc);
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_gt_pm.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
index d1f3e2e23937..ab794e853356 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
@@ -43,12 +43,21 @@ static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt)
 }
 
 void intel_gt_pm_init_early(struct intel_gt *gt);
-void intel_gt_pm_enable(struct intel_gt *gt);
+void intel_gt_pm_init(struct intel_gt *gt);
 void intel_gt_pm_disable(struct intel_gt *gt);
+void intel_gt_pm_fini(struct intel_gt *gt);
 
 void intel_gt_sanitize(struct intel_gt *gt, bool force);
+
 int intel_gt_resume(struct intel_gt *gt);
+void intel_gt_suspend(struct intel_gt *gt);
+
 void intel_gt_runtime_suspend(struct intel_gt *gt);
 int intel_gt_runtime_resume(struct intel_gt *gt);
 
+static inline bool is_mock_gt(const struct intel_gt *gt)
+{
+	return I915_SELFTEST_ONLY(gt->awake == -1);
+}
+
 #endif /* INTEL_GT_PM_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index e64db4c13df6..7134f1319bbe 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -18,6 +18,7 @@
 #include "i915_vma.h"
 #include "intel_engine_types.h"
 #include "intel_reset_types.h"
+#include "intel_rc6_types.h"
 #include "intel_wakeref.h"
 
 struct drm_i915_private;
@@ -67,6 +68,8 @@ struct intel_gt {
 	 */
 	intel_wakeref_t awake;
 
+	struct intel_rc6 rc6;
+
 	struct blocking_notifier_head pm_notifications;
 
 	ktime_t last_init_time;
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
new file mode 100644
index 000000000000..d6167dd592e9
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -0,0 +1,712 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/pm_runtime.h>
+
+#include "i915_drv.h"
+#include "intel_gt.h"
+#include "intel_gt_pm.h"
+#include "intel_rc6.h"
+#include "intel_sideband.h"
+
+/**
+ * DOC: RC6
+ *
+ * RC6 is a special power stage which allows the GPU to enter an very
+ * low-voltage mode when idle, using down to 0V while at this stage.  This
+ * stage is entered automatically when the GPU is idle when RC6 support is
+ * enabled, and as soon as new workload arises GPU wakes up automatically as
+ * well.
+ *
+ * There are different RC6 modes available in Intel GPU, which differentiate
+ * among each other with the latency required to enter and leave RC6 and
+ * voltage consumed by the GPU in different states.
+ *
+ * The combination of the following flags define which states GPU is allowed
+ * to enter, while RC6 is the normal RC6 state, RC6p is the deep RC6, and
+ * RC6pp is deepest RC6. Their support by hardware varies according to the
+ * GPU, BIOS, chipset and platform. RC6 is usually the safest one and the one
+ * which brings the most power savings; deeper states save more power, but
+ * require higher latency to switch to and wake up.
+ */
+
+static struct intel_gt *rc6_to_gt(struct intel_rc6 *rc6)
+{
+	return container_of(rc6, struct intel_gt, rc6);
+}
+
+static struct intel_uncore *rc6_to_uncore(struct intel_rc6 *rc)
+{
+	return rc6_to_gt(rc)->uncore;
+}
+
+static struct drm_i915_private *rc6_to_i915(struct intel_rc6 *rc)
+{
+	return rc6_to_gt(rc)->i915;
+}
+
+static inline void set(struct intel_uncore *uncore, i915_reg_t reg, u32 val)
+{
+	intel_uncore_write_fw(uncore, reg, val);
+}
+
+static void gen11_rc6_enable(struct intel_rc6 *rc6)
+{
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	/* 2b: Program RC6 thresholds.*/
+	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
+	set(uncore, GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
+
+	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+	for_each_engine(engine, rc6_to_gt(rc6)->i915, id)
+		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+
+	set(uncore, GUC_MAX_IDLE_COUNT, 0xA);
+
+	set(uncore, GEN6_RC_SLEEP, 0);
+
+	set(uncore, GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
+
+	/*
+	 * 2c: Program Coarse Power Gating Policies.
+	 *
+	 * Bspec's guidance is to use 25us (really 25 * 1280ns) here. What we
+	 * use instead is a more conservative estimate for the maximum time
+	 * it takes us to service a CS interrupt and submit a new ELSP - that
+	 * is the time which the GPU is idle waiting for the CPU to select the
+	 * next request to execute. If the idle hysteresis is less than that
+	 * interrupt service latency, the hardware will automatically gate
+	 * the power well and we will then incur the wake up cost on top of
+	 * the service latency. A similar guide from plane_state is that we
+	 * do not want the enable hysteresis to less than the wakeup latency.
+	 *
+	 * igt/gem_exec_nop/sequential provides a rough estimate for the
+	 * service latency, and puts it around 10us for Broadwell (and other
+	 * big core) and around 40us for Broxton (and other low power cores).
+	 * [Note that for legacy ringbuffer submission, this is less than 1us!]
+	 * However, the wakeup latency on Broxton is closer to 100us. To be
+	 * conservative, we have to factor in a context switch on top (due
+	 * to ksoftirqd).
+	 */
+	set(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 250);
+	set(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 250);
+
+	/* 3a: Enable RC6 */
+	set(uncore, GEN6_RC_CONTROL,
+	    GEN6_RC_CTL_HW_ENABLE |
+	    GEN6_RC_CTL_RC6_ENABLE |
+	    GEN6_RC_CTL_EI_MODE(1));
+
+	set(uncore, GEN9_PG_ENABLE,
+	    GEN9_RENDER_PG_ENABLE |
+	    GEN9_MEDIA_PG_ENABLE |
+	    GEN11_MEDIA_SAMPLER_PG_ENABLE);
+}
+
+static void gen9_rc6_enable(struct intel_rc6 *rc6)
+{
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	u32 rc6_mode;
+
+	/* 2b: Program RC6 thresholds.*/
+	if (INTEL_GEN(rc6_to_i915(rc6)) >= 10) {
+		set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
+		set(uncore, GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
+	} else if (IS_SKYLAKE(rc6_to_i915(rc6))) {
+		/*
+		 * WaRsDoubleRc6WrlWithCoarsePowerGating:skl Doubling WRL only
+		 * when CPG is enabled
+		 */
+		set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 108 << 16);
+	} else {
+		set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16);
+	}
+
+	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+	for_each_engine(engine, rc6_to_gt(rc6)->i915, id)
+		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+
+	set(uncore, GUC_MAX_IDLE_COUNT, 0xA);
+
+	set(uncore, GEN6_RC_SLEEP, 0);
+
+	/*
+	 * 2c: Program Coarse Power Gating Policies.
+	 *
+	 * Bspec's guidance is to use 25us (really 25 * 1280ns) here. What we
+	 * use instead is a more conservative estimate for the maximum time
+	 * it takes us to service a CS interrupt and submit a new ELSP - that
+	 * is the time which the GPU is idle waiting for the CPU to select the
+	 * next request to execute. If the idle hysteresis is less than that
+	 * interrupt service latency, the hardware will automatically gate
+	 * the power well and we will then incur the wake up cost on top of
+	 * the service latency. A similar guide from plane_state is that we
+	 * do not want the enable hysteresis to less than the wakeup latency.
+	 *
+	 * igt/gem_exec_nop/sequential provides a rough estimate for the
+	 * service latency, and puts it around 10us for Broadwell (and other
+	 * big core) and around 40us for Broxton (and other low power cores).
+	 * [Note that for legacy ringbuffer submission, this is less than 1us!]
+	 * However, the wakeup latency on Broxton is closer to 100us. To be
+	 * conservative, we have to factor in a context switch on top (due
+	 * to ksoftirqd).
+	 */
+	set(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 250);
+	set(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 250);
+
+	/* 3a: Enable RC6 */
+	set(uncore, GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */
+
+	/* WaRsUseTimeoutMode:cnl (pre-prod) */
+	if (IS_CNL_REVID(rc6_to_i915(rc6), CNL_REVID_A0, CNL_REVID_C0))
+		rc6_mode = GEN7_RC_CTL_TO_MODE;
+	else
+		rc6_mode = GEN6_RC_CTL_EI_MODE(1);
+
+	set(uncore, GEN6_RC_CONTROL,
+	    GEN6_RC_CTL_HW_ENABLE |
+	    GEN6_RC_CTL_RC6_ENABLE |
+	    rc6_mode);
+
+	set(uncore, GEN9_PG_ENABLE,
+	    GEN9_RENDER_PG_ENABLE | GEN9_MEDIA_PG_ENABLE);
+}
+
+static void gen8_rc6_enable(struct intel_rc6 *rc6)
+{
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	/* 2b: Program RC6 thresholds.*/
+	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
+	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+	for_each_engine(engine, rc6_to_gt(rc6)->i915, id)
+		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+	set(uncore, GEN6_RC_SLEEP, 0);
+	set(uncore, GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */
+
+	/* 3: Enable RC6 */
+	set(uncore, GEN6_RC_CONTROL,
+	    GEN6_RC_CTL_HW_ENABLE |
+	    GEN7_RC_CTL_TO_MODE |
+	    GEN6_RC_CTL_RC6_ENABLE);
+}
+
+static void gen6_rc6_enable(struct intel_rc6 *rc6)
+{
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+	struct drm_i915_private *i915 = rc6_to_i915(rc6);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	u32 rc6vids, rc6_mask;
+	int ret;
+
+	set(uncore, GEN6_RC1_WAKE_RATE_LIMIT, 1000 << 16);
+	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16 | 30);
+	set(uncore, GEN6_RC6pp_WAKE_RATE_LIMIT, 30);
+	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000);
+	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25);
+
+	for_each_engine(engine, i915, id)
+		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+
+	set(uncore, GEN6_RC_SLEEP, 0);
+	set(uncore, GEN6_RC1e_THRESHOLD, 1000);
+	if (IS_IVYBRIDGE(i915))
+		set(uncore, GEN6_RC6_THRESHOLD, 125000);
+	else
+		set(uncore, GEN6_RC6_THRESHOLD, 50000);
+	set(uncore, GEN6_RC6p_THRESHOLD, 150000);
+	set(uncore, GEN6_RC6pp_THRESHOLD, 64000); /* unused */
+
+	/* We don't use those on Haswell */
+	rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
+	if (HAS_RC6p(i915))
+		rc6_mask |= GEN6_RC_CTL_RC6p_ENABLE;
+	if (HAS_RC6pp(i915))
+		rc6_mask |= GEN6_RC_CTL_RC6pp_ENABLE;
+	set(uncore, GEN6_RC_CONTROL,
+	    rc6_mask |
+	    GEN6_RC_CTL_EI_MODE(1) |
+	    GEN6_RC_CTL_HW_ENABLE);
+
+	rc6vids = 0;
+	ret = sandybridge_pcode_read(i915, GEN6_PCODE_READ_RC6VIDS,
+				     &rc6vids, NULL);
+	if (IS_GEN(i915, 6) && ret) {
+		DRM_DEBUG_DRIVER("Couldn't check for BIOS workaround\n");
+	} else if (IS_GEN(i915, 6) &&
+		   (GEN6_DECODE_RC6_VID(rc6vids & 0xff) < 450)) {
+		DRM_DEBUG_DRIVER("You should update your BIOS. Correcting minimum rc6 voltage (%dmV->%dmV)\n",
+				 GEN6_DECODE_RC6_VID(rc6vids & 0xff), 450);
+		rc6vids &= 0xffff00;
+		rc6vids |= GEN6_ENCODE_RC6_VID(450);
+		ret = sandybridge_pcode_write(i915, GEN6_PCODE_WRITE_RC6VIDS, rc6vids);
+		if (ret)
+			DRM_ERROR("Couldn't fix incorrect rc6 voltage\n");
+	}
+}
+
+/* Check that the pcbr address is not empty. */
+static int chv_rc6_init(struct intel_rc6 *rc6)
+{
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+	resource_size_t pctx_paddr, paddr;
+	resource_size_t pctx_size = 32 * SZ_1K;
+	u32 pcbr;
+
+	pcbr = intel_uncore_read(uncore, VLV_PCBR);
+	if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
+		DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n");
+		paddr = rc6_to_i915(rc6)->dsm.end + 1 - pctx_size;
+		GEM_BUG_ON(paddr > U32_MAX);
+
+		pctx_paddr = (paddr & ~4095);
+		intel_uncore_write(uncore, VLV_PCBR, pctx_paddr);
+	}
+
+	return 0;
+}
+
+static int vlv_rc6_init(struct intel_rc6 *rc6)
+{
+	struct drm_i915_private *i915 = rc6_to_i915(rc6);
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+	struct drm_i915_gem_object *pctx;
+	resource_size_t pctx_paddr;
+	resource_size_t pctx_size = 24 * SZ_1K;
+	u32 pcbr;
+
+	pcbr = intel_uncore_read(uncore, VLV_PCBR);
+	if (pcbr) {
+		/* BIOS set it up already, grab the pre-alloc'd space */
+		resource_size_t pcbr_offset;
+
+		pcbr_offset = (pcbr & ~4095) - i915->dsm.start;
+		pctx = i915_gem_object_create_stolen_for_preallocated(i915,
+								      pcbr_offset,
+								      I915_GTT_OFFSET_NONE,
+								      pctx_size);
+		if (!pctx)
+			return -ENOMEM;
+
+		goto out;
+	}
+
+	DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n");
+
+	/*
+	 * From the Gunit register HAS:
+	 * The Gfx driver is expected to program this register and ensure
+	 * proper allocation within Gfx stolen memory.  For example, this
+	 * register should be programmed such than the PCBR range does not
+	 * overlap with other ranges, such as the frame buffer, protected
+	 * memory, or any other relevant ranges.
+	 */
+	pctx = i915_gem_object_create_stolen(i915, pctx_size);
+	if (!pctx) {
+		DRM_DEBUG("not enough stolen space for PCTX, disabling\n");
+		return -ENOMEM;
+	}
+
+	GEM_BUG_ON(range_overflows_t(u64,
+				     i915->dsm.start,
+				     pctx->stolen->start,
+				     U32_MAX));
+	pctx_paddr = i915->dsm.start + pctx->stolen->start;
+	intel_uncore_write(uncore, VLV_PCBR, pctx_paddr);
+
+out:
+	rc6->pctx = pctx;
+	return 0;
+}
+
+static void chv_rc6_enable(struct intel_rc6 *rc6)
+{
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	/* 2a: Program RC6 thresholds.*/
+	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
+	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+
+	for_each_engine(engine, rc6_to_gt(rc6)->i915, id)
+		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+	set(uncore, GEN6_RC_SLEEP, 0);
+
+	/* TO threshold set to 500 us (0x186 * 1.28 us) */
+	set(uncore, GEN6_RC6_THRESHOLD, 0x186);
+
+	/* Allows RC6 residency counter to work */
+	set(uncore, VLV_COUNTER_CONTROL,
+	    _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
+			       VLV_MEDIA_RC6_COUNT_EN |
+			       VLV_RENDER_RC6_COUNT_EN));
+
+	/* 3: Enable RC6 */
+	set(uncore, GEN6_RC_CONTROL, GEN7_RC_CTL_TO_MODE);
+}
+
+static void vlv_rc6_enable(struct intel_rc6 *rc6)
+{
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 0x00280000);
+	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000);
+	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25);
+
+	for_each_engine(engine, rc6_to_gt(rc6)->i915, id)
+		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+
+	set(uncore, GEN6_RC6_THRESHOLD, 0x557);
+
+	/* Allows RC6 residency counter to work */
+	set(uncore, VLV_COUNTER_CONTROL,
+	    _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
+			       VLV_MEDIA_RC0_COUNT_EN |
+			       VLV_RENDER_RC0_COUNT_EN |
+			       VLV_MEDIA_RC6_COUNT_EN |
+			       VLV_RENDER_RC6_COUNT_EN));
+
+	set(uncore, GEN6_RC_CONTROL,
+	    GEN7_RC_CTL_TO_MODE | VLV_RC_CTL_CTX_RST_PARALLEL);
+}
+
+static bool bxt_check_bios_rc6_setup(struct intel_rc6 *rc6)
+{
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+	struct drm_i915_private *i915 = rc6_to_i915(rc6);
+	u32 rc6_ctx_base, rc_ctl, rc_sw_target;
+	bool enable_rc6 = true;
+
+	rc_ctl = intel_uncore_read(uncore, GEN6_RC_CONTROL);
+	rc_sw_target = intel_uncore_read(uncore, GEN6_RC_STATE);
+	rc_sw_target &= RC_SW_TARGET_STATE_MASK;
+	rc_sw_target >>= RC_SW_TARGET_STATE_SHIFT;
+	DRM_DEBUG_DRIVER("BIOS enabled RC states: "
+			 "HW_CTRL %s HW_RC6 %s SW_TARGET_STATE %x\n",
+			 onoff(rc_ctl & GEN6_RC_CTL_HW_ENABLE),
+			 onoff(rc_ctl & GEN6_RC_CTL_RC6_ENABLE),
+			 rc_sw_target);
+
+	if (!(intel_uncore_read(uncore, RC6_LOCATION) & RC6_CTX_IN_DRAM)) {
+		DRM_DEBUG_DRIVER("RC6 Base location not set properly.\n");
+		enable_rc6 = false;
+	}
+
+	/*
+	 * The exact context size is not known for BXT, so assume a page size
+	 * for this check.
+	 */
+	rc6_ctx_base =
+		intel_uncore_read(uncore, RC6_CTX_BASE) & RC6_CTX_BASE_MASK;
+	if (!(rc6_ctx_base >= i915->dsm_reserved.start &&
+	      rc6_ctx_base + PAGE_SIZE < i915->dsm_reserved.end)) {
+		DRM_DEBUG_DRIVER("RC6 Base address not as expected.\n");
+		enable_rc6 = false;
+	}
+
+	if (!((intel_uncore_read(uncore, PWRCTX_MAXCNT_RCSUNIT) & IDLE_TIME_MASK) > 1 &&
+	      (intel_uncore_read(uncore, PWRCTX_MAXCNT_VCSUNIT0) & IDLE_TIME_MASK) > 1 &&
+	      (intel_uncore_read(uncore, PWRCTX_MAXCNT_BCSUNIT) & IDLE_TIME_MASK) > 1 &&
+	      (intel_uncore_read(uncore, PWRCTX_MAXCNT_VECSUNIT) & IDLE_TIME_MASK) > 1)) {
+		DRM_DEBUG_DRIVER("Engine Idle wait time not set properly.\n");
+		enable_rc6 = false;
+	}
+
+	if (!intel_uncore_read(uncore, GEN8_PUSHBUS_CONTROL) ||
+	    !intel_uncore_read(uncore, GEN8_PUSHBUS_ENABLE) ||
+	    !intel_uncore_read(uncore, GEN8_PUSHBUS_SHIFT)) {
+		DRM_DEBUG_DRIVER("Pushbus not setup properly.\n");
+		enable_rc6 = false;
+	}
+
+	if (!intel_uncore_read(uncore, GEN6_GFXPAUSE)) {
+		DRM_DEBUG_DRIVER("GFX pause not setup properly.\n");
+		enable_rc6 = false;
+	}
+
+	if (!intel_uncore_read(uncore, GEN8_MISC_CTRL0)) {
+		DRM_DEBUG_DRIVER("GPM control not setup properly.\n");
+		enable_rc6 = false;
+	}
+
+	return enable_rc6;
+}
+
+static bool rc6_supported(struct intel_rc6 *rc6)
+{
+	struct drm_i915_private *i915 = rc6_to_i915(rc6);
+
+	if (!HAS_RC6(i915))
+		return false;
+
+	if (intel_vgpu_active(i915))
+		return false;
+
+	if (is_mock_gt(rc6_to_gt(rc6)))
+		return false;
+
+	if (IS_GEN9_LP(i915) && !bxt_check_bios_rc6_setup(rc6)) {
+		dev_notice(i915->drm.dev,
+			   "RC6 and powersaving disabled by BIOS\n");
+		return false;
+	}
+
+	return true;
+}
+
+static void rpm_get(struct intel_rc6 *rc6)
+{
+	GEM_BUG_ON(rc6->wakeref);
+	pm_runtime_get_sync(&rc6_to_i915(rc6)->drm.pdev->dev);
+	rc6->wakeref = true;
+}
+
+static void rpm_put(struct intel_rc6 *rc6)
+{
+	GEM_BUG_ON(!rc6->wakeref);
+	pm_runtime_put(&rc6_to_i915(rc6)->drm.pdev->dev);
+	rc6->wakeref = false;
+}
+
+static void __intel_rc6_disable(struct intel_rc6 *rc6)
+{
+	struct drm_i915_private *i915 = rc6_to_i915(rc6);
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+
+	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
+	if (INTEL_GEN(i915) >= 9)
+		set(uncore, GEN9_PG_ENABLE, 0);
+	set(uncore, GEN6_RC_CONTROL, 0);
+	set(uncore, GEN6_RC_STATE, 0);
+	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
+}
+
+void intel_rc6_init(struct intel_rc6 *rc6)
+{
+	struct drm_i915_private *i915 = rc6_to_i915(rc6);
+	int err;
+
+	/* Disable runtime-pm until we can save the GPU state with rc6 pctx */
+	rpm_get(rc6);
+
+	if (!rc6_supported(rc6))
+		return;
+
+	if (IS_CHERRYVIEW(i915))
+		err = chv_rc6_init(rc6);
+	else if (IS_VALLEYVIEW(i915))
+		err = vlv_rc6_init(rc6);
+	else
+		err = 0;
+
+	/* Sanitize rc6, ensure it is disabled before we are ready. */
+	__intel_rc6_disable(rc6);
+
+	rc6->supported = err == 0;
+}
+
+void intel_rc6_sanitize(struct intel_rc6 *rc6)
+{
+	if (rc6->supported)
+		__intel_rc6_disable(rc6);
+}
+
+void intel_rc6_enable(struct intel_rc6 *rc6)
+{
+	struct drm_i915_private *i915 = rc6_to_i915(rc6);
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+
+	if (!rc6->supported)
+		return;
+
+	GEM_BUG_ON(rc6->enabled);
+
+	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
+
+	if (IS_CHERRYVIEW(i915))
+		chv_rc6_enable(rc6);
+	else if (IS_VALLEYVIEW(i915))
+		vlv_rc6_enable(rc6);
+	else if (INTEL_GEN(i915) >= 11)
+		gen11_rc6_enable(rc6);
+	else if (INTEL_GEN(i915) >= 9)
+		gen9_rc6_enable(rc6);
+	else if (IS_BROADWELL(i915))
+		gen8_rc6_enable(rc6);
+	else if (INTEL_GEN(i915) >= 6)
+		gen6_rc6_enable(rc6);
+
+	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
+
+	/* rc6 is ready, runtime-pm is go! */
+	rpm_put(rc6);
+	rc6->enabled = true;
+}
+
+void intel_rc6_disable(struct intel_rc6 *rc6)
+{
+	if (!rc6->enabled)
+		return;
+
+	rpm_get(rc6);
+	rc6->enabled = false;
+
+	__intel_rc6_disable(rc6);
+}
+
+void intel_rc6_fini(struct intel_rc6 *rc6)
+{
+	struct drm_i915_gem_object *pctx;
+
+	intel_rc6_disable(rc6);
+
+	pctx = fetch_and_zero(&rc6->pctx);
+	if (pctx)
+		i915_gem_object_put(pctx);
+
+	if (rc6->wakeref)
+		rpm_put(rc6);
+}
+
+static u64 vlv_residency_raw(struct intel_uncore *uncore, const i915_reg_t reg)
+{
+	u32 lower, upper, tmp;
+	int loop = 2;
+
+	/*
+	 * The register accessed do not need forcewake. We borrow
+	 * uncore lock to prevent concurrent access to range reg.
+	 */
+	lockdep_assert_held(&uncore->lock);
+
+	/*
+	 * vlv and chv residency counters are 40 bits in width.
+	 * With a control bit, we can choose between upper or lower
+	 * 32bit window into this counter.
+	 *
+	 * Although we always use the counter in high-range mode elsewhere,
+	 * userspace may attempt to read the value before rc6 is initialised,
+	 * before we have set the default VLV_COUNTER_CONTROL value. So always
+	 * set the high bit to be safe.
+	 */
+	set(uncore, VLV_COUNTER_CONTROL,
+	    _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH));
+	upper = intel_uncore_read_fw(uncore, reg);
+	do {
+		tmp = upper;
+
+		set(uncore, VLV_COUNTER_CONTROL,
+		    _MASKED_BIT_DISABLE(VLV_COUNT_RANGE_HIGH));
+		lower = intel_uncore_read_fw(uncore, reg);
+
+		set(uncore, VLV_COUNTER_CONTROL,
+		    _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH));
+		upper = intel_uncore_read_fw(uncore, reg);
+	} while (upper != tmp && --loop);
+
+	/*
+	 * Everywhere else we always use VLV_COUNTER_CONTROL with the
+	 * VLV_COUNT_RANGE_HIGH bit set - so it is safe to leave it set
+	 * now.
+	 */
+
+	return lower | (u64)upper << 8;
+}
+
+u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, const i915_reg_t reg)
+{
+	struct drm_i915_private *i915 = rc6_to_i915(rc6);
+	struct intel_uncore *uncore = rc6_to_uncore(rc6);
+	u64 time_hw, prev_hw, overflow_hw;
+	unsigned int fw_domains;
+	unsigned long flags;
+	unsigned int i;
+	u32 mul, div;
+
+	if (!rc6->supported)
+		return 0;
+
+	/*
+	 * Store previous hw counter values for counter wrap-around handling.
+	 *
+	 * There are only four interesting registers and they live next to each
+	 * other so we can use the relative address, compared to the smallest
+	 * one as the index into driver storage.
+	 */
+	i = (i915_mmio_reg_offset(reg) -
+	     i915_mmio_reg_offset(GEN6_GT_GFX_RC6_LOCKED)) / sizeof(u32);
+	if (WARN_ON_ONCE(i >= ARRAY_SIZE(rc6->cur_residency)))
+		return 0;
+
+	fw_domains = intel_uncore_forcewake_for_reg(uncore, reg, FW_REG_READ);
+
+	spin_lock_irqsave(&uncore->lock, flags);
+	intel_uncore_forcewake_get__locked(uncore, fw_domains);
+
+	/* On VLV and CHV, residency time is in CZ units rather than 1.28us */
+	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
+		mul = 1000000;
+		div = i915->czclk_freq;
+		overflow_hw = BIT_ULL(40);
+		time_hw = vlv_residency_raw(uncore, reg);
+	} else {
+		/* 833.33ns units on Gen9LP, 1.28us elsewhere. */
+		if (IS_GEN9_LP(i915)) {
+			mul = 10000;
+			div = 12;
+		} else {
+			mul = 1280;
+			div = 1;
+		}
+
+		overflow_hw = BIT_ULL(32);
+		time_hw = intel_uncore_read_fw(uncore, reg);
+	}
+
+	/*
+	 * Counter wrap handling.
+	 *
+	 * But relying on a sufficient frequency of queries otherwise counters
+	 * can still wrap.
+	 */
+	prev_hw = rc6->prev_hw_residency[i];
+	rc6->prev_hw_residency[i] = time_hw;
+
+	/* RC6 delta from last sample. */
+	if (time_hw >= prev_hw)
+		time_hw -= prev_hw;
+	else
+		time_hw += overflow_hw - prev_hw;
+
+	/* Add delta to RC6 extended raw driver copy. */
+	time_hw += rc6->cur_residency[i];
+	rc6->cur_residency[i] = time_hw;
+
+	intel_uncore_forcewake_put__locked(uncore, fw_domains);
+	spin_unlock_irqrestore(&uncore->lock, flags);
+
+	return mul_u64_u32_div(time_hw, mul, div);
+}
+
+u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg)
+{
+	return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(rc6, reg), 1000);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.h b/drivers/gpu/drm/i915/gt/intel_rc6.h
new file mode 100644
index 000000000000..5e6711f36457
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.h
@@ -0,0 +1,25 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_RC6_H
+#define INTEL_RC6_H
+
+#include "i915_reg.h"
+
+struct intel_engine_cs;
+struct intel_rc6;
+
+void intel_rc6_init(struct intel_rc6 *rc6);
+void intel_rc6_fini(struct intel_rc6 *rc6);
+
+void intel_rc6_sanitize(struct intel_rc6 *rc6);
+void intel_rc6_enable(struct intel_rc6 *rc6);
+void intel_rc6_disable(struct intel_rc6 *rc6);
+
+u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, i915_reg_t reg);
+u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg);
+
+#endif /* INTEL_RC6_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6_types.h b/drivers/gpu/drm/i915/gt/intel_rc6_types.h
new file mode 100644
index 000000000000..214f354d6ae4
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_rc6_types.h
@@ -0,0 +1,28 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_RC6_TYPES_H
+#define INTEL_RC6_TYPES_H
+
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include "intel_engine_types.h"
+
+struct drm_i915_gem_object;
+
+struct intel_rc6 {
+	u64 prev_hw_residency[4];
+	u64 cur_residency[4];
+
+	struct drm_i915_gem_object *pctx;
+
+	bool supported : 1;
+	bool enabled : 1;
+	bool wakeref : 1;
+};
+
+#endif /* INTEL_RC6_TYPES_H */
diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
new file mode 100644
index 000000000000..87985bd46423
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
@@ -0,0 +1,50 @@
+
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+static int live_gt_resume(void *arg)
+{
+	struct intel_gt *gt = arg;
+	IGT_TIMEOUT(end_time);
+	int err;
+
+	/* Do several suspend/resume cycles to check we don't explode! */
+	do {
+		intel_gt_suspend(gt);
+
+		if (gt->rc6.enabled) {
+			pr_err("rc6 still enabled after suspend!\n");
+			intel_gt_set_wedged_on_init(gt);
+			err = -EINVAL;
+			break;
+		}
+
+		err = intel_gt_resume(gt);
+		if (err)
+			break;
+
+		if (gt->rc6.supported && !gt->rc6.enabled) {
+			pr_err("rc6 not enabled upon resume!\n");
+			intel_gt_set_wedged_on_init(gt);
+			err = -EINVAL;
+			break;
+		}
+	} while (!__igt_timeout(end_time, NULL));
+
+	return err;
+}
+
+int intel_gt_pm_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_gt_resume),
+	};
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return intel_gt_live_subtests(tests, &i915->gt);
+}
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index b5b449a88cf1..fec9fb7cc384 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -42,6 +42,7 @@
 #include "gem/i915_gem_context.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_reset.h"
+#include "gt/intel_rc6.h"
 #include "gt/uc/intel_guc_submission.h"
 
 #include "i915_debugfs.h"
@@ -1168,11 +1169,13 @@ static void print_rc6_res(struct seq_file *m,
 			  const char *title,
 			  const i915_reg_t reg)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
+	struct drm_i915_private *i915 = node_to_i915(m->private);
+	intel_wakeref_t wakeref;
 
-	seq_printf(m, "%s %u (%llu us)\n",
-		   title, I915_READ(reg),
-		   intel_rc6_residency_us(dev_priv, reg));
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+		seq_printf(m, "%s %u (%llu us)\n", title,
+			   intel_uncore_read(&i915->uncore, reg),
+			   intel_rc6_residency_us(&i915->gt.rc6, reg));
 }
 
 static int vlv_drpc_info(struct seq_file *m)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b3c7dbc1832a..0e4e77373ee5 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -599,19 +599,12 @@ struct intel_rps {
 	struct intel_rps_ei ei;
 };
 
-struct intel_rc6 {
-	bool enabled;
-	u64 prev_hw_residency[4];
-	u64 cur_residency[4];
-};
-
 struct intel_llc_pstate {
 	bool enabled;
 };
 
 struct intel_gen6_power_mgmt {
 	struct intel_rps rps;
-	struct intel_rc6 rc6;
 	struct intel_llc_pstate llc_pstate;
 };
 
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 3310353890fb..d0508719492e 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -11,6 +11,7 @@
 #include "gt/intel_engine_pm.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt_pm.h"
+#include "gt/intel_rc6.h"
 
 #include "i915_drv.h"
 #include "i915_pmu.h"
@@ -116,21 +117,21 @@ static bool pmu_needs_timer(struct i915_pmu *pmu, bool gpu_active)
 	return enable;
 }
 
-static u64 __get_rc6(const struct intel_gt *gt)
+static u64 __get_rc6(struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
 	u64 val;
 
-	val = intel_rc6_residency_ns(i915,
+	val = intel_rc6_residency_ns(&gt->rc6,
 				     IS_VALLEYVIEW(i915) ?
 				     VLV_GT_RENDER_RC6 :
 				     GEN6_GT_GFX_RC6);
 
 	if (HAS_RC6p(i915))
-		val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6p);
+		val += intel_rc6_residency_ns(&gt->rc6, GEN6_GT_GFX_RC6p);
 
 	if (HAS_RC6pp(i915))
-		val += intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6pp);
+		val += intel_rc6_residency_ns(&gt->rc6, GEN6_GT_GFX_RC6pp);
 
 	return val;
 }
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index d8a3b180c084..034b8abc5062 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -30,6 +30,8 @@
 #include <linux/stat.h>
 #include <linux/sysfs.h>
 
+#include "gt/intel_rc6.h"
+
 #include "i915_drv.h"
 #include "i915_sysfs.h"
 #include "intel_pm.h"
@@ -49,7 +51,7 @@ static u32 calc_residency(struct drm_i915_private *dev_priv,
 	u64 res = 0;
 
 	with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref)
-		res = intel_rc6_residency_us(dev_priv, reg);
+		res = intel_rc6_residency_us(&dev_priv->gt.rc6, reg);
 
 	return DIV_ROUND_CLOSEST_ULL(res, 1000);
 }
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 6bed2ed14574..bfcf03ab5245 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -45,26 +45,6 @@
 #include "intel_sideband.h"
 #include "../../../platform/x86/intel_ips.h"
 
-/**
- * DOC: RC6
- *
- * RC6 is a special power stage which allows the GPU to enter an very
- * low-voltage mode when idle, using down to 0V while at this stage.  This
- * stage is entered automatically when the GPU is idle when RC6 support is
- * enabled, and as soon as new workload arises GPU wakes up automatically as well.
- *
- * There are different RC6 modes available in Intel GPU, which differentiate
- * among each other with the latency required to enter and leave RC6 and
- * voltage consumed by the GPU in different states.
- *
- * The combination of the following flags define which states GPU is allowed
- * to enter, while RC6 is the normal RC6 state, RC6p is the deep RC6, and
- * RC6pp is deepest RC6. Their support by hardware varies according to the
- * GPU, BIOS, chipset and platform. RC6 is usually the safest one and the one
- * which brings the most power savings; deeper states save more power, but
- * require higher latency to switch to and wake up.
- */
-
 static void gen9_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	if (HAS_LLC(dev_priv)) {
@@ -6918,142 +6898,27 @@ int intel_set_rps(struct drm_i915_private *dev_priv, u8 val)
 	return err;
 }
 
-static void gen9_disable_rc6(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE(GEN6_RC_CONTROL, 0);
-	I915_WRITE(GEN9_PG_ENABLE, 0);
-}
-
 static void gen9_disable_rps(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE(GEN6_RP_CONTROL, 0);
 }
 
-static void gen6_disable_rc6(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE(GEN6_RC_CONTROL, 0);
-}
-
 static void gen6_disable_rps(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
 	I915_WRITE(GEN6_RP_CONTROL, 0);
 }
 
-static void cherryview_disable_rc6(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE(GEN6_RC_CONTROL, 0);
-}
-
 static void cherryview_disable_rps(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE(GEN6_RP_CONTROL, 0);
 }
 
-static void valleyview_disable_rc6(struct drm_i915_private *dev_priv)
-{
-	/* We're doing forcewake before Disabling RC6,
-	 * This what the BIOS expects when going into suspend */
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
-	I915_WRITE(GEN6_RC_CONTROL, 0);
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-}
-
 static void valleyview_disable_rps(struct drm_i915_private *dev_priv)
 {
 	I915_WRITE(GEN6_RP_CONTROL, 0);
 }
 
-static bool bxt_check_bios_rc6_setup(struct drm_i915_private *dev_priv)
-{
-	bool enable_rc6 = true;
-	unsigned long rc6_ctx_base;
-	u32 rc_ctl;
-	int rc_sw_target;
-
-	rc_ctl = I915_READ(GEN6_RC_CONTROL);
-	rc_sw_target = (I915_READ(GEN6_RC_STATE) & RC_SW_TARGET_STATE_MASK) >>
-		       RC_SW_TARGET_STATE_SHIFT;
-	DRM_DEBUG_DRIVER("BIOS enabled RC states: "
-			 "HW_CTRL %s HW_RC6 %s SW_TARGET_STATE %x\n",
-			 onoff(rc_ctl & GEN6_RC_CTL_HW_ENABLE),
-			 onoff(rc_ctl & GEN6_RC_CTL_RC6_ENABLE),
-			 rc_sw_target);
-
-	if (!(I915_READ(RC6_LOCATION) & RC6_CTX_IN_DRAM)) {
-		DRM_DEBUG_DRIVER("RC6 Base location not set properly.\n");
-		enable_rc6 = false;
-	}
-
-	/*
-	 * The exact context size is not known for BXT, so assume a page size
-	 * for this check.
-	 */
-	rc6_ctx_base = I915_READ(RC6_CTX_BASE) & RC6_CTX_BASE_MASK;
-	if (!((rc6_ctx_base >= dev_priv->dsm_reserved.start) &&
-	      (rc6_ctx_base + PAGE_SIZE < dev_priv->dsm_reserved.end))) {
-		DRM_DEBUG_DRIVER("RC6 Base address not as expected.\n");
-		enable_rc6 = false;
-	}
-
-	if (!(((I915_READ(PWRCTX_MAXCNT_RCSUNIT) & IDLE_TIME_MASK) > 1) &&
-	      ((I915_READ(PWRCTX_MAXCNT_VCSUNIT0) & IDLE_TIME_MASK) > 1) &&
-	      ((I915_READ(PWRCTX_MAXCNT_BCSUNIT) & IDLE_TIME_MASK) > 1) &&
-	      ((I915_READ(PWRCTX_MAXCNT_VECSUNIT) & IDLE_TIME_MASK) > 1))) {
-		DRM_DEBUG_DRIVER("Engine Idle wait time not set properly.\n");
-		enable_rc6 = false;
-	}
-
-	if (!I915_READ(GEN8_PUSHBUS_CONTROL) ||
-	    !I915_READ(GEN8_PUSHBUS_ENABLE) ||
-	    !I915_READ(GEN8_PUSHBUS_SHIFT)) {
-		DRM_DEBUG_DRIVER("Pushbus not setup properly.\n");
-		enable_rc6 = false;
-	}
-
-	if (!I915_READ(GEN6_GFXPAUSE)) {
-		DRM_DEBUG_DRIVER("GFX pause not setup properly.\n");
-		enable_rc6 = false;
-	}
-
-	if (!I915_READ(GEN8_MISC_CTRL0)) {
-		DRM_DEBUG_DRIVER("GPM control not setup properly.\n");
-		enable_rc6 = false;
-	}
-
-	return enable_rc6;
-}
-
-static bool sanitize_rc6(struct drm_i915_private *i915)
-{
-	struct intel_device_info *info = mkwrite_device_info(i915);
-
-	/* Powersaving is controlled by the host when inside a VM */
-	if (intel_vgpu_active(i915)) {
-		info->has_rc6 = 0;
-		info->has_rps = false;
-	}
-
-	if (info->has_rc6 &&
-	    IS_GEN9_LP(i915) && !bxt_check_bios_rc6_setup(i915)) {
-		DRM_INFO("RC6 disabled by BIOS\n");
-		info->has_rc6 = 0;
-	}
-
-	/*
-	 * We assume that we do not have any deep rc6 levels if we don't have
-	 * have the previous rc6 level supported, i.e. we use HAS_RC6()
-	 * as the initial coarse check for rc6 in general, moving on to
-	 * progressively finer/deeper levels.
-	 */
-	if (!info->has_rc6 && info->has_rc6p)
-		info->has_rc6p = 0;
-
-	return info->has_rc6;
-}
-
 static void gen6_init_rps_frequencies(struct drm_i915_private *dev_priv)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
@@ -7140,203 +7005,6 @@ static void gen9_enable_rps(struct drm_i915_private *dev_priv)
 	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
 }
 
-static void gen11_enable_rc6(struct drm_i915_private *dev_priv)
-{
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-
-	/* 1a: Software RC state - RC0 */
-	I915_WRITE(GEN6_RC_STATE, 0);
-
-	/*
-	 * 1b: Get forcewake during program sequence. Although the driver
-	 * hasn't enabled a state yet where we need forcewake, BIOS may have.
-	 */
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
-	/* 2a: Disable RC states. */
-	I915_WRITE(GEN6_RC_CONTROL, 0);
-
-	/* 2b: Program RC6 thresholds.*/
-	I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
-	I915_WRITE(GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
-
-	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
-	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-	for_each_engine(engine, dev_priv, id)
-		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
-
-	if (HAS_GT_UC(dev_priv))
-		I915_WRITE(GUC_MAX_IDLE_COUNT, 0xA);
-
-	I915_WRITE(GEN6_RC_SLEEP, 0);
-
-	I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
-
-	/*
-	 * 2c: Program Coarse Power Gating Policies.
-	 *
-	 * Bspec's guidance is to use 25us (really 25 * 1280ns) here. What we
-	 * use instead is a more conservative estimate for the maximum time
-	 * it takes us to service a CS interrupt and submit a new ELSP - that
-	 * is the time which the GPU is idle waiting for the CPU to select the
-	 * next request to execute. If the idle hysteresis is less than that
-	 * interrupt service latency, the hardware will automatically gate
-	 * the power well and we will then incur the wake up cost on top of
-	 * the service latency. A similar guide from plane_state is that we
-	 * do not want the enable hysteresis to less than the wakeup latency.
-	 *
-	 * igt/gem_exec_nop/sequential provides a rough estimate for the
-	 * service latency, and puts it around 10us for Broadwell (and other
-	 * big core) and around 40us for Broxton (and other low power cores).
-	 * [Note that for legacy ringbuffer submission, this is less than 1us!]
-	 * However, the wakeup latency on Broxton is closer to 100us. To be
-	 * conservative, we have to factor in a context switch on top (due
-	 * to ksoftirqd).
-	 */
-	I915_WRITE(GEN9_MEDIA_PG_IDLE_HYSTERESIS, 250);
-	I915_WRITE(GEN9_RENDER_PG_IDLE_HYSTERESIS, 250);
-
-	/* 3a: Enable RC6 */
-	I915_WRITE(GEN6_RC_CONTROL,
-		   GEN6_RC_CTL_HW_ENABLE |
-		   GEN6_RC_CTL_RC6_ENABLE |
-		   GEN6_RC_CTL_EI_MODE(1));
-
-	/* 3b: Enable Coarse Power Gating only when RC6 is enabled. */
-	I915_WRITE(GEN9_PG_ENABLE,
-		   GEN9_RENDER_PG_ENABLE |
-		   GEN9_MEDIA_PG_ENABLE |
-		   GEN11_MEDIA_SAMPLER_PG_ENABLE);
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-}
-
-static void gen9_enable_rc6(struct drm_i915_private *dev_priv)
-{
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	u32 rc6_mode;
-
-	/* 1a: Software RC state - RC0 */
-	I915_WRITE(GEN6_RC_STATE, 0);
-
-	/* 1b: Get forcewake during program sequence. Although the driver
-	 * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
-	/* 2a: Disable RC states. */
-	I915_WRITE(GEN6_RC_CONTROL, 0);
-
-	/* 2b: Program RC6 thresholds.*/
-	if (INTEL_GEN(dev_priv) >= 10) {
-		I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
-		I915_WRITE(GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
-	} else if (IS_SKYLAKE(dev_priv)) {
-		/*
-		 * WaRsDoubleRc6WrlWithCoarsePowerGating:skl Doubling WRL only
-		 * when CPG is enabled
-		 */
-		I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 108 << 16);
-	} else {
-		I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16);
-	}
-
-	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
-	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-	for_each_engine(engine, dev_priv, id)
-		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
-
-	if (HAS_GT_UC(dev_priv))
-		I915_WRITE(GUC_MAX_IDLE_COUNT, 0xA);
-
-	I915_WRITE(GEN6_RC_SLEEP, 0);
-
-	/*
-	 * 2c: Program Coarse Power Gating Policies.
-	 *
-	 * Bspec's guidance is to use 25us (really 25 * 1280ns) here. What we
-	 * use instead is a more conservative estimate for the maximum time
-	 * it takes us to service a CS interrupt and submit a new ELSP - that
-	 * is the time which the GPU is idle waiting for the CPU to select the
-	 * next request to execute. If the idle hysteresis is less than that
-	 * interrupt service latency, the hardware will automatically gate
-	 * the power well and we will then incur the wake up cost on top of
-	 * the service latency. A similar guide from plane_state is that we
-	 * do not want the enable hysteresis to less than the wakeup latency.
-	 *
-	 * igt/gem_exec_nop/sequential provides a rough estimate for the
-	 * service latency, and puts it around 10us for Broadwell (and other
-	 * big core) and around 40us for Broxton (and other low power cores).
-	 * [Note that for legacy ringbuffer submission, this is less than 1us!]
-	 * However, the wakeup latency on Broxton is closer to 100us. To be
-	 * conservative, we have to factor in a context switch on top (due
-	 * to ksoftirqd).
-	 */
-	I915_WRITE(GEN9_MEDIA_PG_IDLE_HYSTERESIS, 250);
-	I915_WRITE(GEN9_RENDER_PG_IDLE_HYSTERESIS, 250);
-
-	/* 3a: Enable RC6 */
-	I915_WRITE(GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */
-
-	/* WaRsUseTimeoutMode:cnl (pre-prod) */
-	if (IS_CNL_REVID(dev_priv, CNL_REVID_A0, CNL_REVID_C0))
-		rc6_mode = GEN7_RC_CTL_TO_MODE;
-	else
-		rc6_mode = GEN6_RC_CTL_EI_MODE(1);
-
-	I915_WRITE(GEN6_RC_CONTROL,
-		   GEN6_RC_CTL_HW_ENABLE |
-		   GEN6_RC_CTL_RC6_ENABLE |
-		   rc6_mode);
-
-	/*
-	 * 3b: Enable Coarse Power Gating only when RC6 is enabled.
-	 * WaRsDisableCoarsePowerGating:skl,cnl - Render/Media PG need to be disabled with RC6.
-	 */
-	if (NEEDS_WaRsDisableCoarsePowerGating(dev_priv))
-		I915_WRITE(GEN9_PG_ENABLE, 0);
-	else
-		I915_WRITE(GEN9_PG_ENABLE,
-			   GEN9_RENDER_PG_ENABLE | GEN9_MEDIA_PG_ENABLE);
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-}
-
-static void gen8_enable_rc6(struct drm_i915_private *dev_priv)
-{
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-
-	/* 1a: Software RC state - RC0 */
-	I915_WRITE(GEN6_RC_STATE, 0);
-
-	/* 1b: Get forcewake during program sequence. Although the driver
-	 * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
-	/* 2a: Disable RC states. */
-	I915_WRITE(GEN6_RC_CONTROL, 0);
-
-	/* 2b: Program RC6 thresholds.*/
-	I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
-	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
-	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-	for_each_engine(engine, dev_priv, id)
-		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
-	I915_WRITE(GEN6_RC_SLEEP, 0);
-	I915_WRITE(GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */
-
-	/* 3: Enable RC6 */
-
-	I915_WRITE(GEN6_RC_CONTROL,
-		   GEN6_RC_CTL_HW_ENABLE |
-		   GEN7_RC_CTL_TO_MODE |
-		   GEN6_RC_CTL_RC6_ENABLE);
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-}
-
 static void gen8_enable_rps(struct drm_i915_private *dev_priv)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
@@ -7377,75 +7045,6 @@ static void gen8_enable_rps(struct drm_i915_private *dev_priv)
 	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
 }
 
-static void gen6_enable_rc6(struct drm_i915_private *dev_priv)
-{
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	u32 rc6vids, rc6_mask;
-	u32 gtfifodbg;
-	int ret;
-
-	I915_WRITE(GEN6_RC_STATE, 0);
-
-	/* Clear the DBG now so we don't confuse earlier errors */
-	gtfifodbg = I915_READ(GTFIFODBG);
-	if (gtfifodbg) {
-		DRM_ERROR("GT fifo had a previous error %x\n", gtfifodbg);
-		I915_WRITE(GTFIFODBG, gtfifodbg);
-	}
-
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
-	/* disable the counters and set deterministic thresholds */
-	I915_WRITE(GEN6_RC_CONTROL, 0);
-
-	I915_WRITE(GEN6_RC1_WAKE_RATE_LIMIT, 1000 << 16);
-	I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16 | 30);
-	I915_WRITE(GEN6_RC6pp_WAKE_RATE_LIMIT, 30);
-	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000);
-	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25);
-
-	for_each_engine(engine, dev_priv, id)
-		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
-
-	I915_WRITE(GEN6_RC_SLEEP, 0);
-	I915_WRITE(GEN6_RC1e_THRESHOLD, 1000);
-	if (IS_IVYBRIDGE(dev_priv))
-		I915_WRITE(GEN6_RC6_THRESHOLD, 125000);
-	else
-		I915_WRITE(GEN6_RC6_THRESHOLD, 50000);
-	I915_WRITE(GEN6_RC6p_THRESHOLD, 150000);
-	I915_WRITE(GEN6_RC6pp_THRESHOLD, 64000); /* unused */
-
-	/* We don't use those on Haswell */
-	rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
-	if (HAS_RC6p(dev_priv))
-		rc6_mask |= GEN6_RC_CTL_RC6p_ENABLE;
-	if (HAS_RC6pp(dev_priv))
-		rc6_mask |= GEN6_RC_CTL_RC6pp_ENABLE;
-	I915_WRITE(GEN6_RC_CONTROL,
-		   rc6_mask |
-		   GEN6_RC_CTL_EI_MODE(1) |
-		   GEN6_RC_CTL_HW_ENABLE);
-
-	rc6vids = 0;
-	ret = sandybridge_pcode_read(dev_priv, GEN6_PCODE_READ_RC6VIDS,
-				     &rc6vids, NULL);
-	if (IS_GEN(dev_priv, 6) && ret) {
-		DRM_DEBUG_DRIVER("Couldn't check for BIOS workaround\n");
-	} else if (IS_GEN(dev_priv, 6) && (GEN6_DECODE_RC6_VID(rc6vids & 0xff) < 450)) {
-		DRM_DEBUG_DRIVER("You should update your BIOS. Correcting minimum rc6 voltage (%dmV->%dmV)\n",
-			  GEN6_DECODE_RC6_VID(rc6vids & 0xff), 450);
-		rc6vids &= 0xffff00;
-		rc6vids |= GEN6_ENCODE_RC6_VID(450);
-		ret = sandybridge_pcode_write(dev_priv, GEN6_PCODE_WRITE_RC6VIDS, rc6vids);
-		if (ret)
-			DRM_ERROR("Couldn't fix incorrect rc6 voltage\n");
-	}
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-}
-
 static void gen6_enable_rps(struct drm_i915_private *dev_priv)
 {
 	/* Here begins a magic sequence of register writes to enable
@@ -7662,100 +7261,6 @@ static int valleyview_rps_min_freq(struct drm_i915_private *dev_priv)
 	return max_t(u32, val, 0xc0);
 }
 
-/* Check that the pctx buffer wasn't move under us. */
-static void valleyview_check_pctx(struct drm_i915_private *dev_priv)
-{
-	unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
-
-	WARN_ON(pctx_addr != dev_priv->dsm.start +
-			     dev_priv->vlv_pctx->stolen->start);
-}
-
-
-/* Check that the pcbr address is not empty. */
-static void cherryview_check_pctx(struct drm_i915_private *dev_priv)
-{
-	unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
-
-	WARN_ON((pctx_addr >> VLV_PCBR_ADDR_SHIFT) == 0);
-}
-
-static void cherryview_setup_pctx(struct drm_i915_private *dev_priv)
-{
-	resource_size_t pctx_paddr, paddr;
-	resource_size_t pctx_size = 32*1024;
-	u32 pcbr;
-
-	pcbr = I915_READ(VLV_PCBR);
-	if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
-		DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n");
-		paddr = dev_priv->dsm.end + 1 - pctx_size;
-		GEM_BUG_ON(paddr > U32_MAX);
-
-		pctx_paddr = (paddr & (~4095));
-		I915_WRITE(VLV_PCBR, pctx_paddr);
-	}
-
-	DRM_DEBUG_DRIVER("PCBR: 0x%08x\n", I915_READ(VLV_PCBR));
-}
-
-static void valleyview_setup_pctx(struct drm_i915_private *dev_priv)
-{
-	struct drm_i915_gem_object *pctx;
-	resource_size_t pctx_paddr;
-	resource_size_t pctx_size = 24*1024;
-	u32 pcbr;
-
-	pcbr = I915_READ(VLV_PCBR);
-	if (pcbr) {
-		/* BIOS set it up already, grab the pre-alloc'd space */
-		resource_size_t pcbr_offset;
-
-		pcbr_offset = (pcbr & (~4095)) - dev_priv->dsm.start;
-		pctx = i915_gem_object_create_stolen_for_preallocated(dev_priv,
-								      pcbr_offset,
-								      I915_GTT_OFFSET_NONE,
-								      pctx_size);
-		goto out;
-	}
-
-	DRM_DEBUG_DRIVER("BIOS didn't set up PCBR, fixing up\n");
-
-	/*
-	 * From the Gunit register HAS:
-	 * The Gfx driver is expected to program this register and ensure
-	 * proper allocation within Gfx stolen memory.  For example, this
-	 * register should be programmed such than the PCBR range does not
-	 * overlap with other ranges, such as the frame buffer, protected
-	 * memory, or any other relevant ranges.
-	 */
-	pctx = i915_gem_object_create_stolen(dev_priv, pctx_size);
-	if (!pctx) {
-		DRM_DEBUG("not enough stolen space for PCTX, disabling\n");
-		goto out;
-	}
-
-	GEM_BUG_ON(range_overflows_t(u64,
-				     dev_priv->dsm.start,
-				     pctx->stolen->start,
-				     U32_MAX));
-	pctx_paddr = dev_priv->dsm.start + pctx->stolen->start;
-	I915_WRITE(VLV_PCBR, pctx_paddr);
-
-out:
-	DRM_DEBUG_DRIVER("PCBR: 0x%08x\n", I915_READ(VLV_PCBR));
-	dev_priv->vlv_pctx = pctx;
-}
-
-static void valleyview_cleanup_pctx(struct drm_i915_private *dev_priv)
-{
-	struct drm_i915_gem_object *pctx;
-
-	pctx = fetch_and_zero(&dev_priv->vlv_pctx);
-	if (pctx)
-		i915_gem_object_put(pctx);
-}
-
 static void vlv_init_gpll_ref_freq(struct drm_i915_private *dev_priv)
 {
 	dev_priv->gt_pm.rps.gpll_ref_freq =
@@ -7772,8 +7277,6 @@ static void valleyview_init_gt_powersave(struct drm_i915_private *dev_priv)
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	u32 val;
 
-	valleyview_setup_pctx(dev_priv);
-
 	vlv_iosf_sb_get(dev_priv,
 			BIT(VLV_IOSF_SB_PUNIT) |
 			BIT(VLV_IOSF_SB_NC) |
@@ -7828,8 +7331,6 @@ static void cherryview_init_gt_powersave(struct drm_i915_private *dev_priv)
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	u32 val;
 
-	cherryview_setup_pctx(dev_priv);
-
 	vlv_iosf_sb_get(dev_priv,
 			BIT(VLV_IOSF_SB_PUNIT) |
 			BIT(VLV_IOSF_SB_NC) |
@@ -7880,64 +7381,6 @@ static void cherryview_init_gt_powersave(struct drm_i915_private *dev_priv)
 		  "Odd GPU freq values\n");
 }
 
-static void valleyview_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
-{
-	valleyview_cleanup_pctx(dev_priv);
-}
-
-static void cherryview_enable_rc6(struct drm_i915_private *dev_priv)
-{
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	u32 gtfifodbg, rc6_mode, pcbr;
-
-	gtfifodbg = I915_READ(GTFIFODBG) & ~(GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV |
-					     GT_FIFO_FREE_ENTRIES_CHV);
-	if (gtfifodbg) {
-		DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
-				 gtfifodbg);
-		I915_WRITE(GTFIFODBG, gtfifodbg);
-	}
-
-	cherryview_check_pctx(dev_priv);
-
-	/* 1a & 1b: Get forcewake during program sequence. Although the driver
-	 * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
-	/*  Disable RC states. */
-	I915_WRITE(GEN6_RC_CONTROL, 0);
-
-	/* 2a: Program RC6 thresholds.*/
-	I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
-	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
-	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-
-	for_each_engine(engine, dev_priv, id)
-		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
-	I915_WRITE(GEN6_RC_SLEEP, 0);
-
-	/* TO threshold set to 500 us ( 0x186 * 1.28 us) */
-	I915_WRITE(GEN6_RC6_THRESHOLD, 0x186);
-
-	/* Allows RC6 residency counter to work */
-	I915_WRITE(VLV_COUNTER_CONTROL,
-		   _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
-				      VLV_MEDIA_RC6_COUNT_EN |
-				      VLV_RENDER_RC6_COUNT_EN));
-
-	/* For now we assume BIOS is allocating and populating the PCBR  */
-	pcbr = I915_READ(VLV_PCBR);
-
-	/* 3: Enable RC6 */
-	rc6_mode = 0;
-	if (pcbr >> VLV_PCBR_ADDR_SHIFT)
-		rc6_mode = GEN7_RC_CTL_TO_MODE;
-	I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-}
-
 static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
 {
 	u32 val;
@@ -7982,49 +7425,6 @@ static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
 	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
 }
 
-static void valleyview_enable_rc6(struct drm_i915_private *dev_priv)
-{
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	u32 gtfifodbg;
-
-	valleyview_check_pctx(dev_priv);
-
-	gtfifodbg = I915_READ(GTFIFODBG);
-	if (gtfifodbg) {
-		DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
-				 gtfifodbg);
-		I915_WRITE(GTFIFODBG, gtfifodbg);
-	}
-
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
-	/*  Disable RC states. */
-	I915_WRITE(GEN6_RC_CONTROL, 0);
-
-	I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 0x00280000);
-	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000);
-	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25);
-
-	for_each_engine(engine, dev_priv, id)
-		I915_WRITE(RING_MAX_IDLE(engine->mmio_base), 10);
-
-	I915_WRITE(GEN6_RC6_THRESHOLD, 0x557);
-
-	/* Allows RC6 residency counter to work */
-	I915_WRITE(VLV_COUNTER_CONTROL,
-		   _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
-				      VLV_MEDIA_RC0_COUNT_EN |
-				      VLV_RENDER_RC0_COUNT_EN |
-				      VLV_MEDIA_RC6_COUNT_EN |
-				      VLV_RENDER_RC6_COUNT_EN));
-
-	I915_WRITE(GEN6_RC_CONTROL,
-		   GEN7_RC_CTL_TO_MODE | VLV_RC_CTL_CTX_RST_PARALLEL);
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-}
-
 static void valleyview_enable_rps(struct drm_i915_private *dev_priv)
 {
 	u32 val;
@@ -8551,14 +7951,9 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 
-	/*
-	 * RPM depends on RC6 to save restore the GT HW context, so make RC6 a
-	 * requirement.
-	 */
-	if (!sanitize_rc6(dev_priv)) {
-		DRM_INFO("RC6 disabled, disabling runtime PM support\n");
-		pm_runtime_get(&dev_priv->drm.pdev->dev);
-	}
+	/* Powersaving is controlled by the host when inside a VM */
+	if (intel_vgpu_active(dev_priv))
+		mkwrite_device_info(dev_priv)->has_rps = false;
 
 	/* Initialize RPS limits (for userspace) */
 	if (IS_CHERRYVIEW(dev_priv))
@@ -8593,19 +7988,9 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
 	rps->cur_freq = rps->idle_freq;
 }
 
-void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
-{
-	if (IS_VALLEYVIEW(dev_priv))
-		valleyview_cleanup_gt_powersave(dev_priv);
-
-	if (!HAS_RC6(dev_priv))
-		pm_runtime_put(&dev_priv->drm.pdev->dev);
-}
-
 void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv)
 {
 	dev_priv->gt_pm.rps.enabled = true; /* force RPS disabling */
-	dev_priv->gt_pm.rc6.enabled = true; /* force RC6 disabling */
 	intel_disable_gt_powersave(dev_priv);
 
 	if (INTEL_GEN(dev_priv) >= 11)
@@ -8626,25 +8011,6 @@ static inline void intel_disable_llc_pstate(struct drm_i915_private *i915)
 	i915->gt_pm.llc_pstate.enabled = false;
 }
 
-static void intel_disable_rc6(struct drm_i915_private *dev_priv)
-{
-	lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
-
-	if (!dev_priv->gt_pm.rc6.enabled)
-		return;
-
-	if (INTEL_GEN(dev_priv) >= 9)
-		gen9_disable_rc6(dev_priv);
-	else if (IS_CHERRYVIEW(dev_priv))
-		cherryview_disable_rc6(dev_priv);
-	else if (IS_VALLEYVIEW(dev_priv))
-		valleyview_disable_rc6(dev_priv);
-	else if (INTEL_GEN(dev_priv) >= 6)
-		gen6_disable_rc6(dev_priv);
-
-	dev_priv->gt_pm.rc6.enabled = false;
-}
-
 static void intel_disable_rps(struct drm_i915_private *dev_priv)
 {
 	lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
@@ -8670,8 +8036,6 @@ void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
 {
 	mutex_lock(&dev_priv->gt_pm.rps.lock);
 
-	intel_disable_rc6(dev_priv);
-
 	intel_disable_rps(dev_priv);
 	if (HAS_LLC(dev_priv))
 		intel_disable_llc_pstate(dev_priv);
@@ -8691,29 +8055,6 @@ static inline void intel_enable_llc_pstate(struct drm_i915_private *i915)
 	i915->gt_pm.llc_pstate.enabled = true;
 }
 
-static void intel_enable_rc6(struct drm_i915_private *dev_priv)
-{
-	lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
-
-	if (dev_priv->gt_pm.rc6.enabled)
-		return;
-
-	if (IS_CHERRYVIEW(dev_priv))
-		cherryview_enable_rc6(dev_priv);
-	else if (IS_VALLEYVIEW(dev_priv))
-		valleyview_enable_rc6(dev_priv);
-	else if (INTEL_GEN(dev_priv) >= 11)
-		gen11_enable_rc6(dev_priv);
-	else if (INTEL_GEN(dev_priv) >= 9)
-		gen9_enable_rc6(dev_priv);
-	else if (IS_BROADWELL(dev_priv))
-		gen8_enable_rc6(dev_priv);
-	else if (INTEL_GEN(dev_priv) >= 6)
-		gen6_enable_rc6(dev_priv);
-
-	dev_priv->gt_pm.rc6.enabled = true;
-}
-
 static void intel_enable_rps(struct drm_i915_private *dev_priv)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
@@ -8755,8 +8096,6 @@ void intel_enable_gt_powersave(struct drm_i915_private *dev_priv)
 
 	mutex_lock(&dev_priv->gt_pm.rps.lock);
 
-	if (HAS_RC6(dev_priv))
-		intel_enable_rc6(dev_priv);
 	if (HAS_RPS(dev_priv))
 		intel_enable_rps(dev_priv);
 	if (HAS_LLC(dev_priv))
@@ -9818,133 +9157,6 @@ void intel_pm_setup(struct drm_i915_private *dev_priv)
 	atomic_set(&dev_priv->runtime_pm.wakeref_count, 0);
 }
 
-static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
-			     const i915_reg_t reg)
-{
-	u32 lower, upper, tmp;
-	int loop = 2;
-
-	/*
-	 * The register accessed do not need forcewake. We borrow
-	 * uncore lock to prevent concurrent access to range reg.
-	 */
-	lockdep_assert_held(&dev_priv->uncore.lock);
-
-	/*
-	 * vlv and chv residency counters are 40 bits in width.
-	 * With a control bit, we can choose between upper or lower
-	 * 32bit window into this counter.
-	 *
-	 * Although we always use the counter in high-range mode elsewhere,
-	 * userspace may attempt to read the value before rc6 is initialised,
-	 * before we have set the default VLV_COUNTER_CONTROL value. So always
-	 * set the high bit to be safe.
-	 */
-	I915_WRITE_FW(VLV_COUNTER_CONTROL,
-		      _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH));
-	upper = I915_READ_FW(reg);
-	do {
-		tmp = upper;
-
-		I915_WRITE_FW(VLV_COUNTER_CONTROL,
-			      _MASKED_BIT_DISABLE(VLV_COUNT_RANGE_HIGH));
-		lower = I915_READ_FW(reg);
-
-		I915_WRITE_FW(VLV_COUNTER_CONTROL,
-			      _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH));
-		upper = I915_READ_FW(reg);
-	} while (upper != tmp && --loop);
-
-	/*
-	 * Everywhere else we always use VLV_COUNTER_CONTROL with the
-	 * VLV_COUNT_RANGE_HIGH bit set - so it is safe to leave it set
-	 * now.
-	 */
-
-	return lower | (u64)upper << 8;
-}
-
-u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
-			   const i915_reg_t reg)
-{
-	struct intel_uncore *uncore = &dev_priv->uncore;
-	u64 time_hw, prev_hw, overflow_hw;
-	unsigned int fw_domains;
-	unsigned long flags;
-	unsigned int i;
-	u32 mul, div;
-
-	if (!HAS_RC6(dev_priv))
-		return 0;
-
-	/*
-	 * Store previous hw counter values for counter wrap-around handling.
-	 *
-	 * There are only four interesting registers and they live next to each
-	 * other so we can use the relative address, compared to the smallest
-	 * one as the index into driver storage.
-	 */
-	i = (i915_mmio_reg_offset(reg) -
-	     i915_mmio_reg_offset(GEN6_GT_GFX_RC6_LOCKED)) / sizeof(u32);
-	if (WARN_ON_ONCE(i >= ARRAY_SIZE(dev_priv->gt_pm.rc6.cur_residency)))
-		return 0;
-
-	fw_domains = intel_uncore_forcewake_for_reg(uncore, reg, FW_REG_READ);
-
-	spin_lock_irqsave(&uncore->lock, flags);
-	intel_uncore_forcewake_get__locked(uncore, fw_domains);
-
-	/* On VLV and CHV, residency time is in CZ units rather than 1.28us */
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		mul = 1000000;
-		div = dev_priv->czclk_freq;
-		overflow_hw = BIT_ULL(40);
-		time_hw = vlv_residency_raw(dev_priv, reg);
-	} else {
-		/* 833.33ns units on Gen9LP, 1.28us elsewhere. */
-		if (IS_GEN9_LP(dev_priv)) {
-			mul = 10000;
-			div = 12;
-		} else {
-			mul = 1280;
-			div = 1;
-		}
-
-		overflow_hw = BIT_ULL(32);
-		time_hw = intel_uncore_read_fw(uncore, reg);
-	}
-
-	/*
-	 * Counter wrap handling.
-	 *
-	 * But relying on a sufficient frequency of queries otherwise counters
-	 * can still wrap.
-	 */
-	prev_hw = dev_priv->gt_pm.rc6.prev_hw_residency[i];
-	dev_priv->gt_pm.rc6.prev_hw_residency[i] = time_hw;
-
-	/* RC6 delta from last sample. */
-	if (time_hw >= prev_hw)
-		time_hw -= prev_hw;
-	else
-		time_hw += overflow_hw - prev_hw;
-
-	/* Add delta to RC6 extended raw driver copy. */
-	time_hw += dev_priv->gt_pm.rc6.cur_residency[i];
-	dev_priv->gt_pm.rc6.cur_residency[i] = time_hw;
-
-	intel_uncore_forcewake_put__locked(uncore, fw_domains);
-	spin_unlock_irqrestore(&uncore->lock, flags);
-
-	return mul_u64_u32_div(time_hw, mul, div);
-}
-
-u64 intel_rc6_residency_us(struct drm_i915_private *dev_priv,
-			   i915_reg_t reg)
-{
-	return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(dev_priv, reg), 1000);
-}
-
 u32 intel_get_cagf(struct drm_i915_private *dev_priv, u32 rpstat)
 {
 	u32 cagf;
diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h
index e3573e1e16e3..93d192d0610a 100644
--- a/drivers/gpu/drm/i915/intel_pm.h
+++ b/drivers/gpu/drm/i915/intel_pm.h
@@ -32,7 +32,6 @@ void intel_pm_setup(struct drm_i915_private *dev_priv);
 void intel_gpu_ips_init(struct drm_i915_private *dev_priv);
 void intel_gpu_ips_teardown(void);
 void intel_init_gt_powersave(struct drm_i915_private *dev_priv);
-void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_enable_gt_powersave(struct drm_i915_private *dev_priv);
 void intel_disable_gt_powersave(struct drm_i915_private *dev_priv);
@@ -72,8 +71,6 @@ void intel_enable_ipc(struct drm_i915_private *dev_priv);
 
 int intel_gpu_freq(struct drm_i915_private *dev_priv, int val);
 int intel_freq_opcode(struct drm_i915_private *dev_priv, int val);
-u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv, i915_reg_t reg);
-u64 intel_rc6_residency_us(struct drm_i915_private *dev_priv, i915_reg_t reg);
 
 u32 intel_get_cagf(struct drm_i915_private *dev_priv, u32 rpstat1);
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index 66d83c1390c1..6713efea350b 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -16,6 +16,7 @@ selftest(gt_engines, intel_engine_live_selftests)
 selftest(gt_timelines, intel_timeline_live_selftests)
 selftest(gt_contexts, intel_context_live_selftests)
 selftest(gt_lrc, intel_lrc_live_selftests)
+selftest(gt_pm, intel_gt_pm_live_selftests)
 selftest(requests, i915_request_live_selftests)
 selftest(active, i915_active_live_selftests)
 selftest(objects, i915_gem_object_live_selftests)
-- 
cgit v1.2.3


From 9cd6c339e34ab13479fb139b0b9f5ffc9743bfc1 Mon Sep 17 00:00:00 2001
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Date: Fri, 27 Sep 2019 15:25:54 +0300
Subject: drm/i915: Update DRIVER_DATE to 20190927

Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0e4e77373ee5..c0f6c1f72b62 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -106,8 +106,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20190822"
-#define DRIVER_TIMESTAMP	1566477988
+#define DRIVER_DATE		"20190927"
+#define DRIVER_TIMESTAMP	1569587154
 
 struct drm_i915_gem_object;
 
-- 
cgit v1.2.3


From 4b0b2b096da9d296e0e5668cdfba8613bd6f5bc8 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 25 Sep 2019 12:59:23 -0700
Subject: libsubcmd: Make _FORTIFY_SOURCE defines dependent on the feature

Unconditionally defining _FORTIFY_SOURCE can break tools that don't work
with it, such as memory sanitizers:

  https://github.com/google/sanitizers/wiki/AddressSanitizer#faq

Fixes: 4b6ab94eabe4 ("perf subcmd: Create subcmd library")
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20190925195924.152834-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/lib/subcmd/Makefile | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index ed61fb3a46c0..5b2cd5e58df0 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -20,7 +20,13 @@ MAKEFLAGS += --no-print-directory
 LIBFILE = $(OUTPUT)libsubcmd.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -fPIC
+
+ifeq ($(DEBUG),0)
+  ifeq ($(feature-fortify-source), 1)
+    CFLAGS += -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2
+  endif
+endif
 
 ifeq ($(CC_NO_CLANG), 0)
   CFLAGS += -O3
-- 
cgit v1.2.3


From e3e2cf3d5b1fe800b032e14c0fdcd9a6fb20cf3b Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Wed, 25 Sep 2019 12:59:24 -0700
Subject: perf tests: Avoid raising SEGV using an obvious NULL dereference

An optimized build such as:

  make -C tools/perf CLANG=1 CC=clang EXTRA_CFLAGS="-O3

will turn the dereference operation into a ud2 instruction, raising a
SIGILL rather than a SIGSEGV. Use raise(..) for correctness and clarity.

Similar issues were addressed in Numfor Mbiziwo-Tiapo's patch:

  https://lkml.org/lkml/2019/7/8/1234

Committer testing:

Before:

  [root@quaco ~]# perf test hooks
  55: perf hooks                                            : Ok
  [root@quaco ~]# perf test -v hooks
  55: perf hooks                                            :
  --- start ---
  test child forked, pid 17092
  SIGSEGV is observed as expected, try to recover.
  Fatal error (SEGFAULT) in perf hook 'test'
  test child finished with 0
  ---- end ----
  perf hooks: Ok
  [root@quaco ~]#

After:

  [root@quaco ~]# perf test hooks
  55: perf hooks                                            : Ok
  [root@quaco ~]# perf test -v hooks
  55: perf hooks                                            :
  --- start ---
  test child forked, pid 17909
  SIGSEGV is observed as expected, try to recover.
  Fatal error (SEGFAULT) in perf hook 'test'
  test child finished with 0
  ---- end ----
  perf hooks: Ok
  [root@quaco ~]#

Fixes: a074865e60ed ("perf tools: Introduce perf hooks")
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lore.kernel.org/lkml/20190925195924.152834-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/perf-hooks.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/perf/tests/perf-hooks.c b/tools/perf/tests/perf-hooks.c
index dbc27199c65e..dd865e0bea12 100644
--- a/tools/perf/tests/perf-hooks.c
+++ b/tools/perf/tests/perf-hooks.c
@@ -19,12 +19,11 @@ static void sigsegv_handler(int sig __maybe_unused)
 static void the_hook(void *_hook_flags)
 {
 	int *hook_flags = _hook_flags;
-	int *p = NULL;
 
 	*hook_flags = 1234;
 
 	/* Generate a segfault, test perf_hooks__recover */
-	*p = 0;
+	raise(SIGSEGV);
 }
 
 int test__perf_hooks(struct test *test __maybe_unused, int subtest __maybe_unused)
-- 
cgit v1.2.3


From d586ac10ce56b2381b8e1d8ed74660c1b2b8ab0d Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Fri, 20 Sep 2019 21:13:27 -0700
Subject: perf docs: Allow man page date to be specified

With this change if a perf_date parameter is provided to asciidoc then
it will override the default date written to the man page metadata.

Without this change, or if the perf_date isn't specified, then the
current date is written to the metadata.

Having this parameter allows the metadata to be constant if builds
happen on different dates.

The name of the parameter is intended to be consistent with the existing
perf_version parameter.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20190921041327.155054-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/asciidoc.conf | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/perf/Documentation/asciidoc.conf b/tools/perf/Documentation/asciidoc.conf
index 356b23a40339..2b62ba1e72b7 100644
--- a/tools/perf/Documentation/asciidoc.conf
+++ b/tools/perf/Documentation/asciidoc.conf
@@ -71,6 +71,9 @@ ifdef::backend-docbook[]
 [header]
 template::[header-declarations]
 <refentry>
+ifdef::perf_date[]
+<refentryinfo><date>{perf_date}</date></refentryinfo>
+endif::perf_date[]
 <refmeta>
 <refentrytitle>{mantitle}</refentrytitle>
 <manvolnum>{manvolnum}</manvolnum>
-- 
cgit v1.2.3


From 08a96a31474a732fd654575ced843b94bc3212e1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 27 Sep 2019 09:28:11 -0300
Subject: tools headers uapi: Sync drm/i915_drm.h with the kernel sources

To pick the change in:

  bf73fc0fa9cf ("drm/i915: Show support for accurate sw PMU busyness tracking")

That don't result in any changes in tooling, just silences this perf
build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/drm/i915_drm.h' differs from latest version at 'include/uapi/drm/i915_drm.h'
  diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-o651nt7vpz93tu3nmx4f3xql@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/drm/i915_drm.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 328d05e77d9f..469dc512cca3 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -521,6 +521,7 @@ typedef struct drm_i915_irq_wait {
 #define   I915_SCHEDULER_CAP_PRIORITY	(1ul << 1)
 #define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
 #define   I915_SCHEDULER_CAP_SEMAPHORES	(1ul << 3)
+#define   I915_SCHEDULER_CAP_ENGINE_BUSY_STATS	(1ul << 4)
 
 #define I915_PARAM_HUC_STATUS		 42
 
-- 
cgit v1.2.3


From b9023b91dd020ad7e093baa5122b6968c48cc9e0 Mon Sep 17 00:00:00 2001
From: Balasubramani Vivekanandan <balasubramani_vivekanandan@mentor.com>
Date: Thu, 26 Sep 2019 15:51:01 +0200
Subject: tick: broadcast-hrtimer: Fix a race in bc_set_next

When a cpu requests broadcasting, before starting the tick broadcast
hrtimer, bc_set_next() checks if the timer callback (bc_handler) is active
using hrtimer_try_to_cancel(). But hrtimer_try_to_cancel() does not provide
the required synchronization when the callback is active on other core.

The callback could have already executed tick_handle_oneshot_broadcast()
and could have also returned. But still there is a small time window where
the hrtimer_try_to_cancel() returns -1. In that case bc_set_next() returns
without doing anything, but the next_event of the tick broadcast clock
device is already set to a timeout value.

In the race condition diagram below, CPU #1 is running the timer callback
and CPU #2 is entering idle state and so calls bc_set_next().

In the worst case, the next_event will contain an expiry time, but the
hrtimer will not be started which happens when the racing callback returns
HRTIMER_NORESTART. The hrtimer might never recover if all further requests
from the CPUs to subscribe to tick broadcast have timeout greater than the
next_event of tick broadcast clock device. This leads to cascading of
failures and finally noticed as rcu stall warnings

Here is a depiction of the race condition

CPU #1 (Running timer callback)                   CPU #2 (Enter idle
                                                  and subscribe to
                                                  tick broadcast)
---------------------                             ---------------------

__run_hrtimer()                                   tick_broadcast_enter()

  bc_handler()                                      __tick_broadcast_oneshot_control()

    tick_handle_oneshot_broadcast()

      raw_spin_lock(&tick_broadcast_lock);

      dev->next_event = KTIME_MAX;                  //wait for tick_broadcast_lock
      //next_event for tick broadcast clock
      set to KTIME_MAX since no other cores
      subscribed to tick broadcasting

      raw_spin_unlock(&tick_broadcast_lock);

    if (dev->next_event == KTIME_MAX)
      return HRTIMER_NORESTART
    // callback function exits without
       restarting the hrtimer                      //tick_broadcast_lock acquired
                                                   raw_spin_lock(&tick_broadcast_lock);

                                                   tick_broadcast_set_event()

                                                     clockevents_program_event()

                                                       dev->next_event = expires;

                                                       bc_set_next()

                                                         hrtimer_try_to_cancel()
                                                         //returns -1 since the timer
                                                         callback is active. Exits without
                                                         restarting the timer
  cpu_base->running = NULL;

The comment that hrtimer cannot be armed from within the callback is
wrong. It is fine to start the hrtimer from within the callback. Also it is
safe to start the hrtimer from the enter/exit idle code while the broadcast
handler is active. The enter/exit idle code and the broadcast handler are
synchronized using tick_broadcast_lock. So there is no need for the
existing try to cancel logic. All this can be removed which will eliminate
the race condition as well.

Fixes: 5d1638acb9f6 ("tick: Introduce hrtimer based broadcast")
Originally-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Balasubramani Vivekanandan <balasubramani_vivekanandan@mentor.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20190926135101.12102-2-balasubramani_vivekanandan@mentor.com
---
 kernel/time/tick-broadcast-hrtimer.c | 62 +++++++++++++++++-------------------
 1 file changed, 29 insertions(+), 33 deletions(-)

diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index c1f5bb590b5e..b5a65e212df2 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -42,39 +42,39 @@ static int bc_shutdown(struct clock_event_device *evt)
  */
 static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
 {
-	int bc_moved;
 	/*
-	 * We try to cancel the timer first. If the callback is on
-	 * flight on some other cpu then we let it handle it. If we
-	 * were able to cancel the timer nothing can rearm it as we
-	 * own broadcast_lock.
+	 * This is called either from enter/exit idle code or from the
+	 * broadcast handler. In all cases tick_broadcast_lock is held.
 	 *
-	 * However we can also be called from the event handler of
-	 * ce_broadcast_hrtimer itself when it expires. We cannot
-	 * restart the timer because we are in the callback, but we
-	 * can set the expiry time and let the callback return
-	 * HRTIMER_RESTART.
+	 * hrtimer_cancel() cannot be called here neither from the
+	 * broadcast handler nor from the enter/exit idle code. The idle
+	 * code can run into the problem described in bc_shutdown() and the
+	 * broadcast handler cannot wait for itself to complete for obvious
+	 * reasons.
 	 *
-	 * Since we are in the idle loop at this point and because
-	 * hrtimer_{start/cancel} functions call into tracing,
-	 * calls to these functions must be bound within RCU_NONIDLE.
+	 * Each caller tries to arm the hrtimer on its own CPU, but if the
+	 * hrtimer callbback function is currently running, then
+	 * hrtimer_start() cannot move it and the timer stays on the CPU on
+	 * which it is assigned at the moment.
+	 *
+	 * As this can be called from idle code, the hrtimer_start()
+	 * invocation has to be wrapped with RCU_NONIDLE() as
+	 * hrtimer_start() can call into tracing.
 	 */
-	RCU_NONIDLE(
-		{
-			bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0;
-			if (bc_moved) {
-				hrtimer_start(&bctimer, expires,
-					      HRTIMER_MODE_ABS_PINNED_HARD);
-			}
-		}
-	);
-
-	if (bc_moved) {
-		/* Bind the "device" to the cpu */
-		bc->bound_on = smp_processor_id();
-	} else if (bc->bound_on == smp_processor_id()) {
-		hrtimer_set_expires(&bctimer, expires);
-	}
+	RCU_NONIDLE( {
+		hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED_HARD);
+		/*
+		 * The core tick broadcast mode expects bc->bound_on to be set
+		 * correctly to prevent a CPU which has the broadcast hrtimer
+		 * armed from going deep idle.
+		 *
+		 * As tick_broadcast_lock is held, nothing can change the cpu
+		 * base which was just established in hrtimer_start() above. So
+		 * the below access is safe even without holding the hrtimer
+		 * base lock.
+		 */
+		bc->bound_on = bctimer.base->cpu_base->cpu;
+	} );
 	return 0;
 }
 
@@ -100,10 +100,6 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t)
 {
 	ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
 
-	if (clockevent_state_oneshot(&ce_broadcast_hrtimer))
-		if (ce_broadcast_hrtimer.next_event != KTIME_MAX)
-			return HRTIMER_RESTART;
-
 	return HRTIMER_NORESTART;
 }
 
-- 
cgit v1.2.3


From 19a36d329f5b1e5d3d06f7093de992693d0fdee6 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Mon, 26 Aug 2019 15:30:23 -0400
Subject: KVM: VMX: Set VMENTER_L1D_FLUSH_NOT_REQUIRED if !X86_BUG_L1TF

The l1tf_vmx_mitigation is only set to VMENTER_L1D_FLUSH_NOT_REQUIRED
when the ARCH_CAPABILITIES MSR indicates that L1D flush is not required.
However, if the CPU is not affected by L1TF, l1tf_vmx_mitigation will
still be set to VMENTER_L1D_FLUSH_AUTO. This is certainly not the best
option for a !X86_BUG_L1TF CPU.

So force l1tf_vmx_mitigation to VMENTER_L1D_FLUSH_NOT_REQUIRED to make it
more explicit in case users are checking the vmentry_l1d_flush parameter.

Signed-off-by: Waiman Long <longman@redhat.com>
[Patch rewritten accoring to Borislav Petkov's suggestion. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/vmx.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d4575ffb3cec..e7970a2e8eae 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -209,6 +209,11 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 	struct page *page;
 	unsigned int i;
 
+	if (!boot_cpu_has_bug(X86_BUG_L1TF)) {
+		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
+		return 0;
+	}
+
 	if (!enable_ept) {
 		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
 		return 0;
@@ -7995,12 +8000,10 @@ static int __init vmx_init(void)
 	 * contain 'auto' which will be turned into the default 'cond'
 	 * mitigation mode.
 	 */
-	if (boot_cpu_has(X86_BUG_L1TF)) {
-		r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
-		if (r) {
-			vmx_exit();
-			return r;
-		}
+	r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
+	if (r) {
+		vmx_exit();
+		return r;
 	}
 
 #ifdef CONFIG_KEXEC_CORE
-- 
cgit v1.2.3


From 2e4a75976dfb88ee6ce019b1d4fa507aabd02c14 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Fri, 27 Sep 2019 17:54:13 +0200
Subject: KVM: selftests: x86: clarify what is reported on KVM_GET_MSRS failure

When KVM_GET_MSRS fail the report looks like

==== Test Assertion Failure ====
  lib/x86_64/processor.c:1089: r == nmsrs
  pid=28775 tid=28775 - Argument list too long
     1	0x000000000040a55f: vcpu_save_state at processor.c:1088 (discriminator 3)
     2	0x00000000004010e3: main at state_test.c:171 (discriminator 4)
     3	0x00007fb8e69223d4: ?? ??:0
     4	0x0000000000401287: _start at ??:?
  Unexpected result from KVM_GET_MSRS, r: 36 (failed at 194)

and it's not obvious that '194' here is the failed MSR index and that
it's printed in hex. Change that.

Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/x86_64/processor.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index c53dbc6bc568..6698cb741e10 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1085,7 +1085,7 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
 	for (i = 0; i < nmsrs; i++)
 		state->msrs.entries[i].index = list->indices[i];
 	r = ioctl(vcpu->fd, KVM_GET_MSRS, &state->msrs);
-        TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed at %x)",
+        TEST_ASSERT(r == nmsrs, "Unexpected result from KVM_GET_MSRS, r: %i (failed MSR was 0x%x)",
                 r, r == nmsrs ? -1 : list->indices[r]);
 
 	r = ioctl(vcpu->fd, KVM_GET_DEBUGREGS, &state->debugregs);
-- 
cgit v1.2.3


From 901045c3f0f43566f9a8a2f5716c2c0a497979e6 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Wed, 25 Sep 2019 15:21:21 -0700
Subject: drm/i915/huc: fix version parsing from CSS header

The HuC FW has silently switched to encoding the version the same way as
the GuC FW does, i.e. major.minor.patch instead of just major.minor. All
the current blobs follow the new scheme, but since minor and patch are
both zero there is no difference in the end results and we happily load
them. New binaries, however, will have non-zero values in there, so we
need to make sure to parse them correctly.

Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Acked-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190925222121.4000-1-daniele.ceraolospurio@intel.com
---
 drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c     | 23 ++++-------------------
 drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h |  8 +++-----
 2 files changed, 7 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index ea9a807abd4f..bb878119f06c 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -339,25 +339,10 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw, struct drm_i915_private *i915)
 	}
 
 	/* Get version numbers from the CSS header */
-	switch (uc_fw->type) {
-	case INTEL_UC_FW_TYPE_GUC:
-		uc_fw->major_ver_found = FIELD_GET(CSS_SW_VERSION_GUC_MAJOR,
-						   css->sw_version);
-		uc_fw->minor_ver_found = FIELD_GET(CSS_SW_VERSION_GUC_MINOR,
-						   css->sw_version);
-		break;
-
-	case INTEL_UC_FW_TYPE_HUC:
-		uc_fw->major_ver_found = FIELD_GET(CSS_SW_VERSION_HUC_MAJOR,
-						   css->sw_version);
-		uc_fw->minor_ver_found = FIELD_GET(CSS_SW_VERSION_HUC_MINOR,
-						   css->sw_version);
-		break;
-
-	default:
-		MISSING_CASE(uc_fw->type);
-		break;
-	}
+	uc_fw->major_ver_found = FIELD_GET(CSS_SW_VERSION_UC_MAJOR,
+					   css->sw_version);
+	uc_fw->minor_ver_found = FIELD_GET(CSS_SW_VERSION_UC_MINOR,
+					   css->sw_version);
 
 	if (uc_fw->major_ver_found != uc_fw->major_ver_wanted ||
 	    uc_fw->minor_ver_found < uc_fw->minor_ver_wanted) {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h
index ae58e8a8c53b..f8f6c91a0df6 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h
@@ -69,11 +69,9 @@ struct uc_css_header {
 	char username[8];
 	char buildnumber[12];
 	u32 sw_version;
-#define CSS_SW_VERSION_GUC_MAJOR	(0xFF << 16)
-#define CSS_SW_VERSION_GUC_MINOR	(0xFF << 8)
-#define CSS_SW_VERSION_GUC_PATCH	(0xFF << 0)
-#define CSS_SW_VERSION_HUC_MAJOR	(0xFFFF << 16)
-#define CSS_SW_VERSION_HUC_MINOR	(0xFFFF << 0)
+#define CSS_SW_VERSION_UC_MAJOR		(0xFF << 16)
+#define CSS_SW_VERSION_UC_MINOR		(0xFF << 8)
+#define CSS_SW_VERSION_UC_PATCH		(0xFF << 0)
 	u32 reserved[14];
 	u32 header_info;
 } __packed;
-- 
cgit v1.2.3


From 283a4095af9dd95e5d6d9f3e7f8b66a4b9f84082 Mon Sep 17 00:00:00 2001
From: Anusha Srivatsa <anusha.srivatsa@intel.com>
Date: Wed, 25 Sep 2019 13:12:50 -0700
Subject: drm/i915/dmc: Update ICL DMC version to v1.09
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We have a new version of DMC for ICL - v1.09.

This version adds the Half Refresh Rate capability
into DMC.

Cc: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190925201250.18136-1-daniele.ceraolospurio@intel.com
---
 drivers/gpu/drm/i915/intel_csr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 546577e39b4e..09870a31b4f0 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -44,8 +44,8 @@
 #define TGL_CSR_MAX_FW_SIZE		0x6000
 MODULE_FIRMWARE(TGL_CSR_PATH);
 
-#define ICL_CSR_PATH			"i915/icl_dmc_ver1_07.bin"
-#define ICL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 7)
+#define ICL_CSR_PATH			"i915/icl_dmc_ver1_09.bin"
+#define ICL_CSR_VERSION_REQUIRED	CSR_VERSION(1, 9)
 #define ICL_CSR_MAX_FW_SIZE		0x6000
 MODULE_FIRMWARE(ICL_CSR_PATH);
 
-- 
cgit v1.2.3


From 67b483dd03c4cd9e90e4c3943132dce514ea4e88 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Tue, 24 Sep 2019 11:27:05 -0700
Subject: nvme-rdma: fix possible use-after-free in connect timeout

If the connect times out, we may have already destroyed the
queue in the timeout handler, so test if the queue is still
allocated in the connect error handler.

Reported-by: Yi Zhang <yi.zhang@redhat.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/rdma.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 9d16dfc29368..4d280160dd3f 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -620,7 +620,8 @@ static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx)
 	if (!ret) {
 		set_bit(NVME_RDMA_Q_LIVE, &queue->flags);
 	} else {
-		__nvme_rdma_stop_queue(queue);
+		if (test_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags))
+			__nvme_rdma_stop_queue(queue);
 		dev_info(ctrl->ctrl.device,
 			"failed to connect queue: %d ret=%d\n", idx, ret);
 	}
-- 
cgit v1.2.3


From a12de1d42d74ef3c80e9fb9a2da94daaef747869 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Fri, 27 Sep 2019 15:24:30 +0800
Subject: blk-mq: honor IO scheduler for multiqueue devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If a device is using multiple queues, the IO scheduler may be bypassed.
This may hurt performance for some slow MQ devices, and it also breaks
zoned devices which depend on mq-deadline for respecting the write order
in one zone.

Don't bypass io scheduler if we have one setup.

This patch can double sequential write performance basically on MQ
scsi_debug when mq-deadline is applied.

Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Javier González <javier@javigon.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 6e3b15f70cd7..5d4bef3c378d 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2012,6 +2012,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		}
 
 		blk_add_rq_to_plug(plug, rq);
+	} else if (q->elevator) {
+		blk_mq_sched_insert_request(rq, false, true, true);
 	} else if (plug && !blk_queue_nomerges(q)) {
 		/*
 		 * We do limited plugging. If the bio can be merged, do that.
@@ -2035,8 +2037,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
 					&cookie);
 		}
-	} else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
-			!data.hctx->dispatch_busy)) {
+	} else if ((q->nr_hw_queues > 1 && is_sync) ||
+			!data.hctx->dispatch_busy) {
 		blk_mq_try_issue_directly(data.hctx, rq, &cookie);
 	} else {
 		blk_mq_sched_insert_request(rq, false, true, true);
-- 
cgit v1.2.3


From 3b51be4e4061bd5e0f1b73f56cfecaa879c76d51 Mon Sep 17 00:00:00 2001
From: Clinton A Taylor <clinton.a.taylor@intel.com>
Date: Thu, 26 Sep 2019 14:06:56 -0700
Subject: drm/i915/tc: Update DP_MODE programming
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

BSpec was updated(r146548) with a new MG_DP_MODE Programming table,
now taking in consideration the pin assignment and allowing us to
optimize power by shutting down available but not needed lanes.

It was tested on ICL and TGL, with adaptors that used pin assignment
C and B, reversing the connector and going to different modes testing
the not needed lane shutdown.

v5:
Using crtc_state->lane_count instead of dp.lane_count

BSpec: 21735
BSpec: 49292

Cc: Imre Deak <imre.deak@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Clinton A Taylor <clinton.a.taylor@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190926210659.56317-1-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 92 ++++++++++++++++++--------------
 drivers/gpu/drm/i915/display/intel_tc.c  | 15 ++++++
 drivers/gpu/drm/i915/display/intel_tc.h  |  1 +
 drivers/gpu/drm/i915/i915_reg.h          |  5 ++
 4 files changed, 72 insertions(+), 41 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index aa470c70a198..20393d39a29a 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3091,11 +3091,14 @@ icl_phy_set_clock_gating(struct intel_digital_port *dig_port, bool enable)
 	I915_WRITE(MG_MISC_SUS0(tc_port), val);
 }
 
-static void icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port)
+static void
+icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port,
+		       const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
 	enum port port = intel_dig_port->base.port;
-	u32 ln0, ln1, lane_mask;
+	u32 ln0, ln1, pin_assignment;
+	u8 width;
 
 	if (intel_dig_port->tc_mode == TC_PORT_TBT_ALT)
 		return;
@@ -3103,50 +3106,57 @@ static void icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port)
 	ln0 = I915_READ(MG_DP_MODE(0, port));
 	ln1 = I915_READ(MG_DP_MODE(1, port));
 
-	switch (intel_dig_port->tc_mode) {
-	case TC_PORT_DP_ALT:
-		ln0 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X2_MODE);
-		ln1 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X2_MODE);
+	ln0 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X1_MODE);
+	ln1 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X2_MODE);
 
-		lane_mask = intel_tc_port_get_lane_mask(intel_dig_port);
+	/* DPPATC */
+	pin_assignment = intel_tc_port_get_pin_assignment_mask(intel_dig_port);
+	width = crtc_state->lane_count;
 
-		switch (lane_mask) {
-		case 0x1:
-		case 0x4:
-			break;
-		case 0x2:
+	switch (pin_assignment) {
+	case 0x0:
+		WARN_ON(intel_dig_port->tc_mode != TC_PORT_LEGACY);
+		if (width == 1) {
+			ln1 |= MG_DP_MODE_CFG_DP_X1_MODE;
+		} else {
+			ln0 |= MG_DP_MODE_CFG_DP_X2_MODE;
+			ln1 |= MG_DP_MODE_CFG_DP_X2_MODE;
+		}
+		break;
+	case 0x1:
+		if (width == 4) {
+			ln0 |= MG_DP_MODE_CFG_DP_X2_MODE;
+			ln1 |= MG_DP_MODE_CFG_DP_X2_MODE;
+		}
+		break;
+	case 0x2:
+		if (width == 2) {
+			ln0 |= MG_DP_MODE_CFG_DP_X2_MODE;
+			ln1 |= MG_DP_MODE_CFG_DP_X2_MODE;
+		}
+		break;
+	case 0x3:
+	case 0x5:
+		if (width == 1) {
 			ln0 |= MG_DP_MODE_CFG_DP_X1_MODE;
-			break;
-		case 0x3:
-			ln0 |= MG_DP_MODE_CFG_DP_X1_MODE |
-			       MG_DP_MODE_CFG_DP_X2_MODE;
-			break;
-		case 0x8:
 			ln1 |= MG_DP_MODE_CFG_DP_X1_MODE;
-			break;
-		case 0xC:
-			ln1 |= MG_DP_MODE_CFG_DP_X1_MODE |
-			       MG_DP_MODE_CFG_DP_X2_MODE;
-			break;
-		case 0xF:
-			ln0 |= MG_DP_MODE_CFG_DP_X1_MODE |
-			       MG_DP_MODE_CFG_DP_X2_MODE;
-			ln1 |= MG_DP_MODE_CFG_DP_X1_MODE |
-			       MG_DP_MODE_CFG_DP_X2_MODE;
-			break;
-		default:
-			MISSING_CASE(lane_mask);
+		} else {
+			ln0 |= MG_DP_MODE_CFG_DP_X2_MODE;
+			ln1 |= MG_DP_MODE_CFG_DP_X2_MODE;
 		}
 		break;
-
-	case TC_PORT_LEGACY:
-		ln0 |= MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X2_MODE;
-		ln1 |= MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X2_MODE;
+	case 0x4:
+	case 0x6:
+		if (width == 1) {
+			ln0 |= MG_DP_MODE_CFG_DP_X1_MODE;
+			ln1 |= MG_DP_MODE_CFG_DP_X1_MODE;
+		} else {
+			ln0 |= MG_DP_MODE_CFG_DP_X2_MODE;
+			ln1 |= MG_DP_MODE_CFG_DP_X2_MODE;
+		}
 		break;
-
 	default:
-		MISSING_CASE(intel_dig_port->tc_mode);
-		return;
+		MISSING_CASE(pin_assignment);
 	}
 
 	I915_WRITE(MG_DP_MODE(0, port), ln0);
@@ -3239,7 +3249,7 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 					dig_port->ddi_io_power_domain);
 
 	/* 6. */
-	icl_program_mg_dp_mode(dig_port);
+	icl_program_mg_dp_mode(dig_port, crtc_state);
 
 	/*
 	 * 7.a - Steps in this function should only be executed over MST
@@ -3321,7 +3331,7 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 		intel_display_power_get(dev_priv,
 					dig_port->ddi_io_power_domain);
 
-	icl_program_mg_dp_mode(dig_port);
+	icl_program_mg_dp_mode(dig_port, crtc_state);
 	icl_phy_set_clock_gating(dig_port, false);
 
 	if (INTEL_GEN(dev_priv) >= 11)
@@ -3391,7 +3401,7 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 
 	intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain);
 
-	icl_program_mg_dp_mode(dig_port);
+	icl_program_mg_dp_mode(dig_port, crtc_state);
 	icl_phy_set_clock_gating(dig_port, false);
 
 	if (INTEL_GEN(dev_priv) >= 11)
diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c
index f923f9cbd33c..7773169b7331 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.c
+++ b/drivers/gpu/drm/i915/display/intel_tc.c
@@ -67,6 +67,21 @@ u32 intel_tc_port_get_lane_mask(struct intel_digital_port *dig_port)
 	return lane_mask >> DP_LANE_ASSIGNMENT_SHIFT(dig_port->tc_phy_fia_idx);
 }
 
+u32 intel_tc_port_get_pin_assignment_mask(struct intel_digital_port *dig_port)
+{
+	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
+	struct intel_uncore *uncore = &i915->uncore;
+	u32 pin_mask;
+
+	pin_mask = intel_uncore_read(uncore,
+				     PORT_TX_DFLEXPA1(dig_port->tc_phy_fia));
+
+	WARN_ON(pin_mask == 0xffffffff);
+
+	return (pin_mask & DP_PIN_ASSIGNMENT_MASK(dig_port->tc_phy_fia_idx)) >>
+	       DP_PIN_ASSIGNMENT_SHIFT(dig_port->tc_phy_fia_idx);
+}
+
 int intel_tc_port_fia_max_lane_count(struct intel_digital_port *dig_port)
 {
 	struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev);
diff --git a/drivers/gpu/drm/i915/display/intel_tc.h b/drivers/gpu/drm/i915/display/intel_tc.h
index 783d75531435..463f1b3c836f 100644
--- a/drivers/gpu/drm/i915/display/intel_tc.h
+++ b/drivers/gpu/drm/i915/display/intel_tc.h
@@ -13,6 +13,7 @@ struct intel_digital_port;
 
 bool intel_tc_port_connected(struct intel_digital_port *dig_port);
 u32 intel_tc_port_get_lane_mask(struct intel_digital_port *dig_port);
+u32 intel_tc_port_get_pin_assignment_mask(struct intel_digital_port *dig_port);
 int intel_tc_port_fia_max_lane_count(struct intel_digital_port *dig_port);
 void intel_tc_port_set_fia_lane_count(struct intel_digital_port *dig_port,
 				      int required_lanes);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 5e30f1a14624..014fa5dbde83 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -11861,6 +11861,11 @@ enum skl_power_gate {
 #define PORT_TX_DFLEXDPCSSS(fia)		_MMIO_FIA((fia), 0x00894)
 #define   DP_PHY_MODE_STATUS_NOT_SAFE(idx)	(1 << (idx))
 
+#define PORT_TX_DFLEXPA1(fia)			_MMIO_FIA((fia), 0x00880)
+#define   DP_PIN_ASSIGNMENT_SHIFT(idx)		((idx) * 4)
+#define   DP_PIN_ASSIGNMENT_MASK(idx)		(0xf << ((idx) * 4))
+#define   DP_PIN_ASSIGNMENT(idx, x)		((x) << ((idx) * 4))
+
 /* This register controls the Display State Buffer (DSB) engines. */
 #define _DSBSL_INSTANCE_BASE		0x70B00
 #define DSBSL_INSTANCE(pipe, id)	(_DSBSL_INSTANCE_BASE + \
-- 
cgit v1.2.3


From 978c3e539be210268b6c6cfeef0c97e18c00d7a7 Mon Sep 17 00:00:00 2001
From: Clinton A Taylor <clinton.a.taylor@intel.com>
Date: Thu, 26 Sep 2019 14:06:57 -0700
Subject: drm/i915/tgl: Add dkl phy programming sequences
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Added DKL Phy sequences and helpers functions to program voltage
swing, clock gating and dp mode.

It is not written in DP enabling sequence but "PHY Clockgating
programming" states that clock gating should be enabled after the
link training but doing so causes all the following trainings to fail
so not enabling it for.

v2:
Setting the right HIP_INDEX_REG bits (José)

v3:
Adding the meaning of each column of tgl_dkl_phy_ddi_translations
Adding if gen >= 12 on intel_ddi_hdmi_level() and
intel_ddi_pre_enable_hdmi() instead of reuse part of gen >= 11 if

v4:
Moved the DP_MODE lane programing to another patch as ICL also
needed it
Sharing icl_phy_set_clock_gating() and icl_program_mg_dp_mode() with
TGL as bits and programing as now it almost identical to ICL

BSpec: 49292
BSpec: 49190

Cc: Imre Deak <imre.deak@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Clinton A Taylor <clinton.a.taylor@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190926210659.56317-2-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 174 +++++++++++++++++++++++++++----
 drivers/gpu/drm/i915/i915_reg.h          |   8 --
 2 files changed, 154 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 20393d39a29a..b463e51f8b45 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -586,6 +586,26 @@ static const struct icl_mg_phy_ddi_buf_trans icl_mg_phy_ddi_translations[] = {
 	{ 0x0, 0x00, 0x00 },	/* 3              0   */
 };
 
+struct tgl_dkl_phy_ddi_buf_trans {
+	u32 dkl_vswing_control;
+	u32 dkl_preshoot_control;
+	u32 dkl_de_emphasis_control;
+};
+
+static const struct tgl_dkl_phy_ddi_buf_trans tgl_dkl_phy_ddi_translations[] = {
+				/* VS	pre-emp	Non-trans mV	Pre-emph dB */
+	{ 0x7, 0x0, 0x00 },	/* 0	0	400mV		0 dB */
+	{ 0x5, 0x0, 0x03 },	/* 0	1	400mV		3.5 dB */
+	{ 0x2, 0x0, 0x0b },	/* 0	2	400mV		6 dB */
+	{ 0x0, 0x0, 0x19 },	/* 0	3	400mV		9.5 dB */
+	{ 0x5, 0x0, 0x00 },	/* 1	0	600mV		0 dB */
+	{ 0x2, 0x0, 0x03 },	/* 1	1	600mV		3.5 dB */
+	{ 0x0, 0x0, 0x14 },	/* 1	2	600mV		6 dB */
+	{ 0x2, 0x0, 0x00 },	/* 2	0	800mV		0 dB */
+	{ 0x0, 0x0, 0x0B },	/* 2	1	800mV		3.5 dB */
+	{ 0x0, 0x0, 0x00 },	/* 3	0	1200mV		0 dB HDMI default */
+};
+
 static const struct ddi_buf_trans *
 bdw_get_buf_trans_edp(struct drm_i915_private *dev_priv, int *n_entries)
 {
@@ -872,7 +892,14 @@ static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port por
 
 	level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift;
 
-	if (INTEL_GEN(dev_priv) >= 11) {
+	if (INTEL_GEN(dev_priv) >= 12) {
+		if (intel_phy_is_combo(dev_priv, phy))
+			icl_get_combo_buf_trans(dev_priv, INTEL_OUTPUT_HDMI,
+						0, &n_entries);
+		else
+			n_entries = ARRAY_SIZE(tgl_dkl_phy_ddi_translations);
+		default_entry = n_entries - 1;
+	} else if (INTEL_GEN(dev_priv) == 11) {
 		if (intel_phy_is_combo(dev_priv, phy))
 			icl_get_combo_buf_trans(dev_priv, INTEL_OUTPUT_HDMI,
 						0, &n_entries);
@@ -2334,7 +2361,13 @@ u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder)
 	enum phy phy = intel_port_to_phy(dev_priv, port);
 	int n_entries;
 
-	if (INTEL_GEN(dev_priv) >= 11) {
+	if (INTEL_GEN(dev_priv) >= 12) {
+		if (intel_phy_is_combo(dev_priv, phy))
+			icl_get_combo_buf_trans(dev_priv, encoder->type,
+						intel_dp->link_rate, &n_entries);
+		else
+			n_entries = ARRAY_SIZE(tgl_dkl_phy_ddi_translations);
+	} else if (INTEL_GEN(dev_priv) == 11) {
 		if (intel_phy_is_combo(dev_priv, phy))
 			icl_get_combo_buf_trans(dev_priv, encoder->type,
 						intel_dp->link_rate, &n_entries);
@@ -2776,6 +2809,62 @@ static void icl_ddi_vswing_sequence(struct intel_encoder *encoder,
 		icl_mg_phy_ddi_vswing_sequence(encoder, link_clock, level);
 }
 
+static void
+tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder, int link_clock,
+				u32 level)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum tc_port tc_port = intel_port_to_tc(dev_priv, encoder->port);
+	const struct tgl_dkl_phy_ddi_buf_trans *ddi_translations;
+	u32 n_entries, val, ln, dpcnt_mask, dpcnt_val;
+
+	n_entries = ARRAY_SIZE(tgl_dkl_phy_ddi_translations);
+	ddi_translations = tgl_dkl_phy_ddi_translations;
+
+	if (level >= n_entries)
+		level = n_entries - 1;
+
+	dpcnt_mask = (DKL_TX_PRESHOOT_COEFF_MASK |
+		      DKL_TX_DE_EMPAHSIS_COEFF_MASK |
+		      DKL_TX_VSWING_CONTROL_MASK);
+	dpcnt_val = DKL_TX_VSWING_CONTROL(ddi_translations[level].dkl_vswing_control);
+	dpcnt_val |= DKL_TX_DE_EMPHASIS_COEFF(ddi_translations[level].dkl_de_emphasis_control);
+	dpcnt_val |= DKL_TX_PRESHOOT_COEFF(ddi_translations[level].dkl_preshoot_control);
+
+	for (ln = 0; ln < 2; ln++) {
+		I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, ln));
+
+		/* All the registers are RMW */
+		val = I915_READ(DKL_TX_DPCNTL0(tc_port));
+		val &= ~dpcnt_mask;
+		val |= dpcnt_val;
+		I915_WRITE(DKL_TX_DPCNTL0(tc_port), val);
+
+		val = I915_READ(DKL_TX_DPCNTL1(tc_port));
+		val &= ~dpcnt_mask;
+		val |= dpcnt_val;
+		I915_WRITE(DKL_TX_DPCNTL1(tc_port), val);
+
+		val = I915_READ(DKL_TX_DPCNTL2(tc_port));
+		val &= ~DKL_TX_DP20BITMODE;
+		I915_WRITE(DKL_TX_DPCNTL2(tc_port), val);
+	}
+}
+
+static void tgl_ddi_vswing_sequence(struct intel_encoder *encoder,
+				    int link_clock,
+				    u32 level,
+				    enum intel_output_type type)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum phy phy = intel_port_to_phy(dev_priv, encoder->port);
+
+	if (intel_phy_is_combo(dev_priv, phy))
+		icl_combo_phy_ddi_vswing_sequence(encoder, level, type);
+	else
+		tgl_dkl_phy_ddi_vswing_sequence(encoder, link_clock, level);
+}
+
 static u32 translate_signal_level(int signal_levels)
 {
 	int i;
@@ -2807,7 +2896,10 @@ u32 bxt_signal_levels(struct intel_dp *intel_dp)
 	struct intel_encoder *encoder = &dport->base;
 	int level = intel_ddi_dp_level(intel_dp);
 
-	if (INTEL_GEN(dev_priv) >= 11)
+	if (INTEL_GEN(dev_priv) >= 12)
+		tgl_ddi_vswing_sequence(encoder, intel_dp->link_rate,
+					level, encoder->type);
+	else if (INTEL_GEN(dev_priv) >= 11)
 		icl_ddi_vswing_sequence(encoder, intel_dp->link_rate,
 					level, encoder->type);
 	else if (IS_CANNONLAKE(dev_priv))
@@ -3071,24 +3163,39 @@ icl_phy_set_clock_gating(struct intel_digital_port *dig_port, bool enable)
 	       MG_DP_MODE_CFG_GAONPWR_GATING;
 
 	for (ln = 0; ln < 2; ln++) {
-		val = I915_READ(MG_DP_MODE(ln, port));
+		if (INTEL_GEN(dev_priv) >= 12) {
+			I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, ln));
+			val = I915_READ(DKL_DP_MODE(tc_port));
+		} else {
+			val = I915_READ(MG_DP_MODE(ln, port));
+		}
+
 		if (enable)
 			val |= bits;
 		else
 			val &= ~bits;
-		I915_WRITE(MG_DP_MODE(ln, port), val);
+
+		if (INTEL_GEN(dev_priv) >= 12)
+			I915_WRITE(DKL_DP_MODE(tc_port), val);
+		else
+			I915_WRITE(MG_DP_MODE(ln, port), val);
 	}
 
-	bits = MG_MISC_SUS0_CFG_TR2PWR_GATING | MG_MISC_SUS0_CFG_CL2PWR_GATING |
-	       MG_MISC_SUS0_CFG_GAONPWR_GATING | MG_MISC_SUS0_CFG_TRPWR_GATING |
-	       MG_MISC_SUS0_CFG_CL1PWR_GATING | MG_MISC_SUS0_CFG_DGPWR_GATING;
+	if (INTEL_GEN(dev_priv) == 11) {
+		bits = MG_MISC_SUS0_CFG_TR2PWR_GATING |
+		       MG_MISC_SUS0_CFG_CL2PWR_GATING |
+		       MG_MISC_SUS0_CFG_GAONPWR_GATING |
+		       MG_MISC_SUS0_CFG_TRPWR_GATING |
+		       MG_MISC_SUS0_CFG_CL1PWR_GATING |
+		       MG_MISC_SUS0_CFG_DGPWR_GATING;
 
-	val = I915_READ(MG_MISC_SUS0(tc_port));
-	if (enable)
-		val |= (bits | MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE(3));
-	else
-		val &= ~(bits | MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE_MASK);
-	I915_WRITE(MG_MISC_SUS0(tc_port), val);
+		val = I915_READ(MG_MISC_SUS0(tc_port));
+		if (enable)
+			val |= (bits | MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE(3));
+		else
+			val &= ~(bits | MG_MISC_SUS0_SUSCLK_DYNCLKGATE_MODE_MASK);
+		I915_WRITE(MG_MISC_SUS0(tc_port), val);
+	}
 }
 
 static void
@@ -3097,14 +3204,22 @@ icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port,
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
 	enum port port = intel_dig_port->base.port;
+	enum tc_port tc_port = intel_port_to_tc(dev_priv, port);
 	u32 ln0, ln1, pin_assignment;
 	u8 width;
 
 	if (intel_dig_port->tc_mode == TC_PORT_TBT_ALT)
 		return;
 
-	ln0 = I915_READ(MG_DP_MODE(0, port));
-	ln1 = I915_READ(MG_DP_MODE(1, port));
+	if (INTEL_GEN(dev_priv) >= 12) {
+		I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, 0x0));
+		ln0 = I915_READ(DKL_DP_MODE(tc_port));
+		I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, 0x1));
+		ln1 = I915_READ(DKL_DP_MODE(tc_port));
+	} else {
+		ln0 = I915_READ(MG_DP_MODE(0, port));
+		ln1 = I915_READ(MG_DP_MODE(1, port));
+	}
 
 	ln0 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X1_MODE);
 	ln1 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X2_MODE);
@@ -3159,8 +3274,15 @@ icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port,
 		MISSING_CASE(pin_assignment);
 	}
 
-	I915_WRITE(MG_DP_MODE(0, port), ln0);
-	I915_WRITE(MG_DP_MODE(1, port), ln1);
+	if (INTEL_GEN(dev_priv) >= 12) {
+		I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, 0x0));
+		I915_WRITE(DKL_DP_MODE(tc_port), ln0);
+		I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, 0x1));
+		I915_WRITE(DKL_DP_MODE(tc_port), ln1);
+	} else {
+		I915_WRITE(MG_DP_MODE(0, port), ln0);
+		I915_WRITE(MG_DP_MODE(1, port), ln1);
+	}
 }
 
 static void intel_dp_sink_set_fec_ready(struct intel_dp *intel_dp,
@@ -3265,7 +3387,7 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	icl_phy_set_clock_gating(dig_port, false);
 
 	/* 7.e */
-	icl_ddi_vswing_sequence(encoder, crtc_state->port_clock, level,
+	tgl_ddi_vswing_sequence(encoder, crtc_state->port_clock, level,
 				encoder->type);
 
 	/* 7.f */
@@ -3297,6 +3419,15 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	/* 7.k */
 	intel_dp_stop_link_train(intel_dp);
 
+	/*
+	 * TODO: enable clock gating
+	 *
+	 * It is not written in DP enabling sequence but "PHY Clockgating
+	 * programming" states that clock gating should be enabled after the
+	 * link training but doing so causes all the following trainings to fail
+	 * so not enabling it for now.
+	 */
+
 	/* 7.l */
 	intel_ddi_enable_fec(encoder, crtc_state);
 	intel_dsc_enable(encoder, crtc_state);
@@ -3404,7 +3535,10 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 	icl_program_mg_dp_mode(dig_port, crtc_state);
 	icl_phy_set_clock_gating(dig_port, false);
 
-	if (INTEL_GEN(dev_priv) >= 11)
+	if (INTEL_GEN(dev_priv) >= 12)
+		tgl_ddi_vswing_sequence(encoder, crtc_state->port_clock,
+					level, INTEL_OUTPUT_HDMI);
+	else if (INTEL_GEN(dev_priv) == 11)
 		icl_ddi_vswing_sequence(encoder, crtc_state->port_clock,
 					level, INTEL_OUTPUT_HDMI);
 	else if (IS_CANNONLAKE(dev_priv))
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 014fa5dbde83..058aa5ca8b73 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -10249,14 +10249,6 @@ enum skl_power_gate {
 						     _DKL_TX_DW18)
 
 #define _DKL_DP_MODE					0xA0
-#define  DKL_DP_MODE_CFG_GAONPWR_GATING		(1 << 1)
-#define  DKL_DP_MODE_CFG_DIGPWR_GATING		(1 << 2)
-#define  DKL_DP_MODE_CFG_CLNPWR_GATING		(1 << 3)
-#define  DKL_DP_MODE_CFG_TRPWR_GATING		(1 << 4)
-#define  DKL_DP_MODE_CFG_TR2PWR_GATING		(1 << 5)
-#define  DKL_DP_MODE_CFG_GATING_CTRL_MASK	(0x1f << 1)
-#define  DKL_DP_MODE_CFG_DP_X1_MODE			(1 << 6)
-#define  DKL_DP_MODE_CFG_DP_X2_MODE			(1 << 7)
 #define DKL_DP_MODE(tc_port) _MMIO(_PORT(tc_port, \
 						     _DKL_PHY1_BASE, \
 						     _DKL_PHY2_BASE) + \
-- 
cgit v1.2.3


From a839136ca47f79dcdb403cd7a0c5f4798466ac48 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Thu, 26 Sep 2019 14:06:58 -0700
Subject: drm/i915/tgl: Fix dkl link training
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Link training is failling when running link at 2.7GHz and 1.62GHz and
following BSpec pll algorithm.

Comparing the values calculated and the ones from the reference table
it looks like MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO should not always set
to 5. For DP ports ICL mg pll algorithm sets it to 10 or 5 based on
div2 value, that matches with dkl hardcoded table.

So implementing this way as it proved to work in HW and leaving a
comment so we know why it do not match BSpec.

v4:
Using the same is_dp check as ICL, need testing on HDMI over tc port

Issue reported on BSpec 49204.

Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190926210659.56317-3-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_dpll_mgr.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 69abafa45ce9..be69a2344294 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -2630,13 +2630,13 @@ static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc,
 				continue;
 
 			if (div2 >= 2) {
-				if (is_dkl) {
-					a_divratio = 5;
-					tlinedrv = 1;
-				} else {
-					a_divratio = is_dp ? 10 : 5;
-					tlinedrv = 2;
-				}
+				/*
+				 * Note: a_divratio not matching TGL BSpec
+				 * algorithm but matching hardcoded values and
+				 * working on HW for DP alt-mode at least
+				 */
+				a_divratio = is_dp ? 10 : 5;
+				tlinedrv = is_dkl ? 1 : 2;
 			} else {
 				a_divratio = 5;
 				tlinedrv = 0;
-- 
cgit v1.2.3


From f663769a5eefbeb304a7b4749fdd28c24944d9a7 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 26 Sep 2019 14:06:59 -0700
Subject: drm/i915/tgl: initialize TC and TBT ports
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that TC support was added, initialize DDIs.

Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190926210659.56317-4-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 8f125f1624bd..bbe088b9d057 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -15340,9 +15340,14 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 		return;
 
 	if (INTEL_GEN(dev_priv) >= 12) {
-		/* TODO: initialize TC ports as well */
 		intel_ddi_init(dev_priv, PORT_A);
 		intel_ddi_init(dev_priv, PORT_B);
+		intel_ddi_init(dev_priv, PORT_D);
+		intel_ddi_init(dev_priv, PORT_E);
+		intel_ddi_init(dev_priv, PORT_F);
+		intel_ddi_init(dev_priv, PORT_G);
+		intel_ddi_init(dev_priv, PORT_H);
+		intel_ddi_init(dev_priv, PORT_I);
 		icl_dsi_init(dev_priv);
 	} else if (IS_ELKHARTLAKE(dev_priv)) {
 		intel_ddi_init(dev_priv, PORT_A);
-- 
cgit v1.2.3


From 3154df262db52f1d27e01020e871f4345ec2f9a8 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Fri, 27 Sep 2019 15:24:31 +0800
Subject: blk-mq: apply normal plugging for HDD

Some HDD drive may expose multiple hardware queues, such as MegraRaid.
Let's apply the normal plugging for such devices because sequential IO
may benefit a lot from plug merging.

Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 5d4bef3c378d..ec791156e9cc 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1992,10 +1992,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		/* bypass scheduler for flush rq */
 		blk_insert_flush(rq);
 		blk_mq_run_hw_queue(data.hctx, true);
-	} else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs)) {
+	} else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs ||
+				!blk_queue_nonrot(q))) {
 		/*
 		 * Use plugging if we have a ->commit_rqs() hook as well, as
 		 * we know the driver uses bd->last in a smart fashion.
+		 *
+		 * Use normal plugging if this disk is slow HDD, as sequential
+		 * IO may benefit a lot from plug merging.
 		 */
 		unsigned int request_count = plug->rq_count;
 		struct request *last = NULL;
-- 
cgit v1.2.3


From b178a3f68128383a1ad2988464f0e964712563f6 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 27 Sep 2019 18:33:48 +0100
Subject: drm/i915: check for kernel_context

Explosions during early driver init on the error path. Make sure we fail
gracefully.

[ 9547.672258] BUG: kernel NULL pointer dereference, address: 000000000000007c
[ 9547.672288] #PF: supervisor read access in kernel mode
[ 9547.672292] #PF: error_code(0x0000) - not-present page
[ 9547.672296] PGD 8000000846b41067 P4D 8000000846b41067 PUD 797034067 PMD 0
[ 9547.672303] Oops: 0000 [#1] SMP PTI
[ 9547.672307] CPU: 1 PID: 25634 Comm: i915_selftest Tainted: G     U            5.3.0-rc8+ #73
[ 9547.672313] Hardware name:  /NUC6i7KYB, BIOS KYSKLi70.86A.0050.2017.0831.1924 08/31/2017
[ 9547.672395] RIP: 0010:intel_context_unpin+0x9/0x100 [i915]
[ 9547.672400] Code: 6b 60 00 e9 17 ff ff ff bd fc ff ff ff e9 7c ff ff ff 66 66 2e 0f 1f 84 00 00 00 00
 00 0f 1f 40 00 0f 1f 44 00 00 41 54 55 53 <8b> 47 7c 83 f8 01 74 26 8d 48 ff f0 0f b1 4f 7c 48 8d 57 7c
 75 05
[ 9547.672413] RSP: 0018:ffffae8ac24ff878 EFLAGS: 00010246
[ 9547.672417] RAX: ffff944a1b7842d0 RBX: ffff944a1b784000 RCX: ffff944a12dd6fa8
[ 9547.672422] RDX: ffff944a1b7842c0 RSI: ffff944a12dd5328 RDI: 0000000000000000
[ 9547.672428] RBP: 0000000000000000 R08: ffff944a11e5d840 R09: 0000000000000000
[ 9547.672433] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
[ 9547.672438] R13: ffffffffc11aaf00 R14: 00000000ffffffe4 R15: ffff944a0e29bf38
[ 9547.672443] FS:  00007fc259b88ac0(0000) GS:ffff944a1f880000(0000) knlGS:0000000000000000
[ 9547.672449] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 9547.672454] CR2: 000000000000007c CR3: 0000000853346003 CR4: 00000000003606e0
[ 9547.672459] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 9547.672464] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 9547.672469] Call Trace:
[ 9547.672518]  intel_engine_cleanup_common+0xe3/0x270 [i915]
[ 9547.672567]  execlists_destroy+0xe/0x30 [i915]
[ 9547.672669]  intel_engines_init+0x94/0xf0 [i915]
[ 9547.672749]  i915_gem_init+0x191/0x950 [i915]

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190927173409.31175-2-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index f451d5076bde..80fd072ac719 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -820,8 +820,10 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 	if (engine->default_state)
 		i915_gem_object_put(engine->default_state);
 
-	intel_context_unpin(engine->kernel_context);
-	intel_context_put(engine->kernel_context);
+	if (engine->kernel_context) {
+		intel_context_unpin(engine->kernel_context);
+		intel_context_put(engine->kernel_context);
+	}
 	GEM_BUG_ON(!llist_empty(&engine->barrier_tasks));
 
 	intel_wa_list_free(&engine->ctx_wa_list);
-- 
cgit v1.2.3


From a3f356b273f9b860cd28be1d4ec25cd2782cda0c Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 27 Sep 2019 18:33:49 +0100
Subject: drm/i915: simplify i915_gem_init_early

i915_gem_init_early doesn't need to return anything.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190927173409.31175-3-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/i915_drv.c | 5 +----
 drivers/gpu/drm/i915/i915_drv.h | 2 +-
 drivers/gpu/drm/i915/i915_gem.c | 4 +---
 3 files changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index dd9613e45723..364f7d0b7e31 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -614,9 +614,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
 
 	intel_gt_init_early(&dev_priv->gt, dev_priv);
 
-	ret = i915_gem_init_early(dev_priv);
-	if (ret < 0)
-		goto err_gt;
+	i915_gem_init_early(dev_priv);
 
 	/* This must be called before any calls to HAS_PCH_* */
 	intel_detect_pch(dev_priv);
@@ -638,7 +636,6 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
 
 err_gem:
 	i915_gem_cleanup_early(dev_priv);
-err_gt:
 	intel_gt_driver_late_release(&dev_priv->gt);
 	vlv_free_s0ix_state(dev_priv);
 err_workqueues:
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c0f6c1f72b62..337d8306416a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2243,7 +2243,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 int i915_gem_init_userptr(struct drm_i915_private *dev_priv);
 void i915_gem_cleanup_userptr(struct drm_i915_private *dev_priv);
 void i915_gem_sanitize(struct drm_i915_private *i915);
-int i915_gem_init_early(struct drm_i915_private *dev_priv);
+void i915_gem_init_early(struct drm_i915_private *dev_priv);
 void i915_gem_cleanup_early(struct drm_i915_private *dev_priv);
 int i915_gem_freeze(struct drm_i915_private *dev_priv);
 int i915_gem_freeze_late(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index e2897a666225..3d3fda4cae99 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1533,7 +1533,7 @@ static void i915_gem_init__mm(struct drm_i915_private *i915)
 	i915_gem_init__objects(i915);
 }
 
-int i915_gem_init_early(struct drm_i915_private *dev_priv)
+void i915_gem_init_early(struct drm_i915_private *dev_priv)
 {
 	int err;
 
@@ -1545,8 +1545,6 @@ int i915_gem_init_early(struct drm_i915_private *dev_priv)
 	err = i915_gemfs_init(dev_priv);
 	if (err)
 		DRM_NOTE("Unable to create a private tmpfs mount, hugepage support will be disabled(%d).\n", err);
-
-	return 0;
 }
 
 void i915_gem_cleanup_early(struct drm_i915_private *dev_priv)
-- 
cgit v1.2.3


From 6402939ec86eaf226c8b8ae00ed983936b164908 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Tue, 17 Sep 2019 17:47:12 -0500
Subject: ieee802154: ca8210: prevent memory leak

In ca8210_probe the allocated pdata needs to be assigned to
spi_device->dev.platform_data before calling ca8210_get_platform_data.
Othrwise when ca8210_get_platform_data fails pdata cannot be released.

Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Link: https://lore.kernel.org/r/20190917224713.26371-1-navid.emamdoost@gmail.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 drivers/net/ieee802154/ca8210.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
index b188fce3f641..658b399ac9ea 100644
--- a/drivers/net/ieee802154/ca8210.c
+++ b/drivers/net/ieee802154/ca8210.c
@@ -3152,12 +3152,12 @@ static int ca8210_probe(struct spi_device *spi_device)
 		goto error;
 	}
 
+	priv->spi->dev.platform_data = pdata;
 	ret = ca8210_get_platform_data(priv->spi, pdata);
 	if (ret) {
 		dev_crit(&spi_device->dev, "ca8210_get_platform_data failed\n");
 		goto error;
 	}
-	priv->spi->dev.platform_data = pdata;
 
 	ret = ca8210_dev_com_init(priv);
 	if (ret) {
-- 
cgit v1.2.3


From 42b899fb9a3fe40e7b59e8815247a34973729d9a Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 27 Sep 2019 22:06:46 +0100
Subject: drm/i915/selftests: Do not try to sanitize mock HW

If we are mocking the device, skip trying to sanitize the pm HW state.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190927210646.29664-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_gt_pm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 42f175d9b98c..29fa1dabbc2e 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -137,7 +137,8 @@ void intel_gt_sanitize(struct intel_gt *gt, bool force)
 
 void intel_gt_pm_disable(struct intel_gt *gt)
 {
-	intel_sanitize_gt_powersave(gt->i915);
+	if (!is_mock_gt(gt))
+		intel_sanitize_gt_powersave(gt->i915);
 }
 
 void intel_gt_pm_fini(struct intel_gt *gt)
-- 
cgit v1.2.3


From 260e6b712769d74304093a699796ebf134aef095 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 27 Sep 2019 22:17:47 +0100
Subject: drm/i915: Pass intel_gt to has-reset?

As we execute GPU resets on a gt/ basis, and use the intel_gt as the
primary for all other reset functions, also use it for the has-reset?
predicates. Gradually simplifying the churn of pointers.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190927211749.2181-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/display/intel_display.c   |  2 +-
 drivers/gpu/drm/i915/gt/intel_reset.c          | 21 +++++++++++++--------
 drivers/gpu/drm/i915/gt/intel_reset.h          |  5 ++---
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c   | 12 ++++++------
 drivers/gpu/drm/i915/gt/selftest_lrc.c         |  2 +-
 drivers/gpu/drm/i915/gt/selftest_reset.c       |  4 ++--
 drivers/gpu/drm/i915/gt/selftest_workarounds.c |  8 ++++----
 drivers/gpu/drm/i915/i915_getparam.c           |  4 ++--
 8 files changed, 31 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index bbe088b9d057..f1328c08f4ad 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -4273,7 +4273,7 @@ __intel_display_resume(struct drm_device *dev,
 static bool gpu_reset_clobbers_display(struct drm_i915_private *dev_priv)
 {
 	return (INTEL_INFO(dev_priv)->gpu_reset_clobbers_display &&
-		intel_has_gpu_reset(dev_priv));
+		intel_has_gpu_reset(&dev_priv->gt));
 }
 
 void intel_prepare_reset(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index d08226f5bea5..ea5cf3a28fbe 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -546,8 +546,10 @@ typedef int (*reset_func)(struct intel_gt *,
 			  intel_engine_mask_t engine_mask,
 			  unsigned int retry);
 
-static reset_func intel_get_gpu_reset(struct drm_i915_private *i915)
+static reset_func intel_get_gpu_reset(const struct intel_gt *gt)
 {
+	struct drm_i915_private *i915 = gt->i915;
+
 	if (INTEL_GEN(i915) >= 8)
 		return gen8_reset_engines;
 	else if (INTEL_GEN(i915) >= 6)
@@ -571,7 +573,7 @@ int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask)
 	int ret = -ETIMEDOUT;
 	int retry;
 
-	reset = intel_get_gpu_reset(gt->i915);
+	reset = intel_get_gpu_reset(gt);
 	if (!reset)
 		return -ENODEV;
 
@@ -591,17 +593,20 @@ int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask)
 	return ret;
 }
 
-bool intel_has_gpu_reset(struct drm_i915_private *i915)
+bool intel_has_gpu_reset(const struct intel_gt *gt)
 {
 	if (!i915_modparams.reset)
 		return NULL;
 
-	return intel_get_gpu_reset(i915);
+	return intel_get_gpu_reset(gt);
 }
 
-bool intel_has_reset_engine(struct drm_i915_private *i915)
+bool intel_has_reset_engine(const struct intel_gt *gt)
 {
-	return INTEL_INFO(i915)->has_reset_engine && i915_modparams.reset >= 2;
+	if (i915_modparams.reset < 2)
+		return false;
+
+	return INTEL_INFO(gt->i915)->has_reset_engine;
 }
 
 int intel_reset_guc(struct intel_gt *gt)
@@ -958,7 +963,7 @@ void intel_gt_reset(struct intel_gt *gt,
 
 	awake = reset_prepare(gt);
 
-	if (!intel_has_gpu_reset(gt->i915)) {
+	if (!intel_has_gpu_reset(gt)) {
 		if (i915_modparams.reset)
 			dev_err(gt->i915->drm.dev, "GPU reset not supported\n");
 		else
@@ -1179,7 +1184,7 @@ void intel_gt_handle_error(struct intel_gt *gt,
 	 * Try engine reset when available. We fall back to full reset if
 	 * single reset fails.
 	 */
-	if (intel_has_reset_engine(gt->i915) && !intel_gt_is_wedged(gt)) {
+	if (intel_has_reset_engine(gt) && !intel_gt_is_wedged(gt)) {
 		for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
 			BUILD_BUG_ON(I915_RESET_MODESET >= I915_RESET_ENGINE);
 			if (test_and_set_bit(I915_RESET_ENGINE + engine->id,
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h
index 0b6ff1ee7f06..8e8d5f761166 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.h
+++ b/drivers/gpu/drm/i915/gt/intel_reset.h
@@ -14,7 +14,6 @@
 #include "intel_engine_types.h"
 #include "intel_reset_types.h"
 
-struct drm_i915_private;
 struct i915_request;
 struct intel_engine_cs;
 struct intel_gt;
@@ -80,7 +79,7 @@ static inline bool __intel_reset_failed(const struct intel_reset *reset)
 	return unlikely(test_bit(I915_WEDGED, &reset->flags));
 }
 
-bool intel_has_gpu_reset(struct drm_i915_private *i915);
-bool intel_has_reset_engine(struct drm_i915_private *i915);
+bool intel_has_gpu_reset(const struct intel_gt *gt);
+bool intel_has_reset_engine(const struct intel_gt *gt);
 
 #endif /* I915_RESET_H */
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index a0098fc35921..9c0c8441c22a 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -458,7 +458,7 @@ static int igt_reset_nop_engine(void *arg)
 
 	/* Check that we can engine-reset during non-user portions */
 
-	if (!intel_has_reset_engine(gt->i915))
+	if (!intel_has_reset_engine(gt))
 		return 0;
 
 	file = mock_file(gt->i915);
@@ -559,7 +559,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 
 	/* Check that we can issue an engine reset on an idle engine (no-op) */
 
-	if (!intel_has_reset_engine(gt->i915))
+	if (!intel_has_reset_engine(gt))
 		return 0;
 
 	if (active) {
@@ -791,7 +791,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 	 * with any other engine.
 	 */
 
-	if (!intel_has_reset_engine(gt->i915))
+	if (!intel_has_reset_engine(gt))
 		return 0;
 
 	if (flags & TEST_ACTIVE) {
@@ -1547,7 +1547,7 @@ static int igt_handle_error(void *arg)
 
 	/* Check that we can issue a global GPU and engine reset */
 
-	if (!intel_has_reset_engine(gt->i915))
+	if (!intel_has_reset_engine(gt))
 		return 0;
 
 	if (!engine || !intel_engine_can_store_dword(engine))
@@ -1689,7 +1689,7 @@ static int igt_reset_engines_atomic(void *arg)
 
 	/* Check that the engines resets are usable from atomic context */
 
-	if (!intel_has_reset_engine(gt->i915))
+	if (!intel_has_reset_engine(gt))
 		return 0;
 
 	if (USES_GUC_SUBMISSION(gt->i915))
@@ -1746,7 +1746,7 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 	bool saved_hangcheck;
 	int err;
 
-	if (!intel_has_gpu_reset(gt->i915))
+	if (!intel_has_gpu_reset(gt))
 		return 0;
 
 	if (intel_gt_is_wedged(gt))
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 22ea2e747064..93f2fcdc49bf 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -1310,7 +1310,7 @@ static int live_preempt_hang(void *arg)
 	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
 		return 0;
 
-	if (!intel_has_reset_engine(i915))
+	if (!intel_has_reset_engine(&i915->gt))
 		return 0;
 
 	mutex_lock(&i915->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c
index 00a4f60cdfd5..d79482db7fe8 100644
--- a/drivers/gpu/drm/i915/gt/selftest_reset.c
+++ b/drivers/gpu/drm/i915/gt/selftest_reset.c
@@ -112,7 +112,7 @@ static int igt_atomic_engine_reset(void *arg)
 
 	/* Check that the resets are usable from atomic context */
 
-	if (!intel_has_reset_engine(gt->i915))
+	if (!intel_has_reset_engine(gt))
 		return 0;
 
 	if (USES_GUC_SUBMISSION(gt->i915))
@@ -170,7 +170,7 @@ int intel_reset_live_selftests(struct drm_i915_private *i915)
 	};
 	struct intel_gt *gt = &i915->gt;
 
-	if (!intel_has_gpu_reset(gt->i915))
+	if (!intel_has_gpu_reset(gt))
 		return 0;
 
 	if (intel_gt_is_wedged(gt))
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 999a98f00494..d40ce0709bff 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -747,7 +747,7 @@ static int live_reset_whitelist(void *arg)
 
 	igt_global_reset_lock(&i915->gt);
 
-	if (intel_has_reset_engine(i915)) {
+	if (intel_has_reset_engine(&i915->gt)) {
 		err = check_whitelist_across_reset(engine,
 						   do_engine_reset,
 						   "engine");
@@ -755,7 +755,7 @@ static int live_reset_whitelist(void *arg)
 			goto out;
 	}
 
-	if (intel_has_gpu_reset(i915)) {
+	if (intel_has_gpu_reset(&i915->gt)) {
 		err = check_whitelist_across_reset(engine,
 						   do_device_reset,
 						   "device");
@@ -1131,7 +1131,7 @@ live_gpu_reset_workarounds(void *arg)
 	struct wa_lists lists;
 	bool ok;
 
-	if (!intel_has_gpu_reset(i915))
+	if (!intel_has_gpu_reset(&i915->gt))
 		return 0;
 
 	ctx = kernel_context(i915);
@@ -1178,7 +1178,7 @@ live_engine_reset_workarounds(void *arg)
 	struct wa_lists lists;
 	int ret = 0;
 
-	if (!intel_has_reset_engine(i915))
+	if (!intel_has_reset_engine(&i915->gt))
 		return 0;
 
 	ctx = kernel_context(i915);
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index 5d9101376a3d..f4b3cbb1adce 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -79,8 +79,8 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		break;
 	case I915_PARAM_HAS_GPU_RESET:
 		value = i915_modparams.enable_hangcheck &&
-			intel_has_gpu_reset(i915);
-		if (value && intel_has_reset_engine(i915))
+			intel_has_gpu_reset(&i915->gt);
+		if (value && intel_has_reset_engine(&i915->gt))
 			value = 2;
 		break;
 	case I915_PARAM_HAS_RESOURCE_STREAMER:
-- 
cgit v1.2.3


From 4e18ca703f2167d8bcb7f736271744131e3c390b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 27 Sep 2019 22:17:48 +0100
Subject: drm/i915/selftests: Distinguish mock device from no wakeref

On systems that have no runtime-pm, we mark the wakeref as being -1. We
therefore cannot use that value for the mock-gt indicator, so opt for
-ENODEV instead. The wakeref should never be an error value -- one
hopes!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190927211749.2181-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_gt_pm.h            | 2 +-
 drivers/gpu/drm/i915/selftests/mock_gem_device.c | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
index ab794e853356..997770d3a968 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
@@ -57,7 +57,7 @@ int intel_gt_runtime_resume(struct intel_gt *gt);
 
 static inline bool is_mock_gt(const struct intel_gt *gt)
 {
-	return I915_SELFTEST_ONLY(gt->awake == -1);
+	return I915_SELFTEST_ONLY(gt->awake == -ENODEV);
 }
 
 #endif /* INTEL_GT_PM_H */
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 91f15fa728cd..2448067822af 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -182,6 +182,7 @@ struct drm_i915_private *mock_gem_device(void)
 	i915_gem_init__mm(i915);
 	intel_gt_init_early(&i915->gt, i915);
 	atomic_inc(&i915->gt.wakeref.count); /* disable; no hw support */
+	i915->gt.awake = -ENODEV;
 
 	i915->wq = alloc_ordered_workqueue("mock", 0);
 	if (!i915->wq)
@@ -192,8 +193,6 @@ struct drm_i915_private *mock_gem_device(void)
 	INIT_DELAYED_WORK(&i915->gem.retire_work, mock_retire_work_handler);
 	INIT_WORK(&i915->gem.idle_work, mock_idle_work_handler);
 
-	i915->gt.awake = -1;
-
 	intel_timelines_init(i915);
 
 	mutex_lock(&i915->drm.struct_mutex);
-- 
cgit v1.2.3


From 4abc6e7c917b1929d8fad2c2364b270cae5ed4ca Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 27 Sep 2019 22:17:49 +0100
Subject: drm/i915/selftests: Provide a mock GPU reset routine

For those mock tests that may wish to pretend triggering a GPU reset and
processing the cleanup.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190927211749.2181-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_reset.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index ea5cf3a28fbe..76938fa3a1b9 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -542,6 +542,13 @@ skip_reset:
 	return ret;
 }
 
+static int mock_reset(struct intel_gt *gt,
+		      intel_engine_mask_t mask,
+		      unsigned int retry)
+{
+	return 0;
+}
+
 typedef int (*reset_func)(struct intel_gt *,
 			  intel_engine_mask_t engine_mask,
 			  unsigned int retry);
@@ -550,7 +557,9 @@ static reset_func intel_get_gpu_reset(const struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
 
-	if (INTEL_GEN(i915) >= 8)
+	if (is_mock_gt(gt))
+		return mock_reset;
+	else if (INTEL_GEN(i915) >= 8)
 		return gen8_reset_engines;
 	else if (INTEL_GEN(i915) >= 6)
 		return gen6_reset_engines;
-- 
cgit v1.2.3


From 55d554f5d14071f7c2c5dbd88d0a2eb695c97d16 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Thu, 26 Sep 2019 19:13:44 -0600
Subject: tools: bpf: Use !building_out_of_srctree to determine srctree

make TARGETS=bpf kselftest fails with:

Makefile:127: tools/build/Makefile.include: No such file or directory

When the bpf tool make is invoked from tools Makefile, srctree is
cleared and the current logic check for srctree equals to empty
string to determine srctree location from CURDIR.

When the build in invoked from selftests/bpf Makefile, the srctree
is set to "." and the same logic used for srctree equals to empty is
needed to determine srctree.

Check building_out_of_srctree undefined as the condition for both
cases to fix "make TARGETS=bpf kselftest" build failure.

Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20190927011344.4695-1-skhan@linuxfoundation.org
---
 tools/bpf/Makefile     | 6 +++++-
 tools/lib/bpf/Makefile | 6 +++++-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index fbf5e4a0cb9c..5d1995fd369c 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -12,7 +12,11 @@ INSTALL ?= install
 CFLAGS += -Wall -O2
 CFLAGS += -D__EXPORTED_HEADERS__ -I$(srctree)/include/uapi -I$(srctree)/include
 
-ifeq ($(srctree),)
+# This will work when bpf is built in tools env. where srctree
+# isn't set and when invoked from selftests build, where srctree
+# is set to ".". building_out_of_srctree is undefined for in srctree
+# builds
+ifndef building_out_of_srctree
 srctree := $(patsubst %/,%,$(dir $(CURDIR)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))
 endif
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index c6f94cffe06e..20772663d3e1 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -8,7 +8,11 @@ LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION)))
 
 MAKEFLAGS += --no-print-directory
 
-ifeq ($(srctree),)
+# This will work when bpf is built in tools env. where srctree
+# isn't set and when invoked from selftests build, where srctree
+# is a ".". building_out_of_srctree is undefined for in srctree
+# builds
+ifndef building_out_of_srctree
 srctree := $(patsubst %/,%,$(dir $(CURDIR)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))
-- 
cgit v1.2.3


From d7d44b6fe40a98e960be92ea8617954c2596d140 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 9 Sep 2019 22:33:57 +0200
Subject: drm/tilcdc: include linux/pinctrl/consumer.h again

This was apparently dropped by accident in a recent
cleanup, causing a build failure in some configurations now:

drivers/gpu/drm/tilcdc/tilcdc_tfp410.c:296:12: error: implicit declaration of function 'devm_pinctrl_get_select_default' [-Werror,-Wimplicit-function-declaration]

Fixes: fcb57664172e ("drm/tilcdc: drop use of drmP.h")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Jyri Sarha <jsarha@ti.com>
Link: https://patchwork.freedesktop.org/patch/msgid/02b03f74cf941f52a941a36bdc8dabb4a69fd87e.1569852588.git.jsarha@ti.com
Acked-by: Sam Ravnborg <sam@ravnborg.org>
---
 drivers/gpu/drm/tilcdc/tilcdc_tfp410.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index 525dc1c0f1c1..530edb3b51cc 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -7,6 +7,7 @@
 #include <linux/gpio.h>
 #include <linux/mod_devicetable.h>
 #include <linux/of_gpio.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 
 #include <drm/drm_atomic_helper.h>
-- 
cgit v1.2.3


From f90ec6cdf674248dcad85bf9af6e064bf472b841 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Mon, 30 Sep 2019 11:54:50 +0300
Subject: ARM: dts: am4372: Set memory bandwidth limit for DISPC

Set memory bandwidth limit to filter out resolutions above 720p@60Hz to
avoid underflow errors due to the bandwidth needs of higher resolutions.

am43xx can not provide enough bandwidth to DISPC to correctly handle
'high' resolutions.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
---
 arch/arm/boot/dts/am4372.dtsi | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index 848e2a8884e2..14bbc438055f 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -337,6 +337,8 @@
 				ti,hwmods = "dss_dispc";
 				clocks = <&disp_clk>;
 				clock-names = "fck";
+
+				max-memory-bandwidth = <230000000>;
 			};
 
 			rfbi: rfbi@4832a800 {
-- 
cgit v1.2.3


From 50d16d44cce45f172bc4b27dcd353b1107aa7429 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 30 Sep 2019 15:49:19 +0100
Subject: drm/i915/selftests: Exercise context switching in parallel

We currently test context switching on each engine as a basic stress
test (just verifying that nothing explodes if we execute 2 requests from
different contexts sequentially). What we have not tested is what
happens if we try and do so on all available engines simultaneously,
putting our SW and the HW under the maximal stress.

v2: Clone the set of engines from the first context into the secondary
contexts.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190930144919.27992-1-chris@chris-wilson.co.uk
---
 .../gpu/drm/i915/gem/selftests/i915_gem_context.c  | 225 +++++++++++++++++++++
 1 file changed, 225 insertions(+)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index dc25bcc3e372..0f4d0644a480 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -156,6 +156,230 @@ out_unlock:
 	return err;
 }
 
+struct parallel_switch {
+	struct task_struct *tsk;
+	struct intel_context *ce[2];
+};
+
+static int __live_parallel_switch1(void *data)
+{
+	struct parallel_switch *arg = data;
+	struct drm_i915_private *i915 = arg->ce[0]->engine->i915;
+	IGT_TIMEOUT(end_time);
+	unsigned long count;
+
+	count = 0;
+	do {
+		struct i915_request *rq = NULL;
+		int err, n;
+
+		for (n = 0; n < ARRAY_SIZE(arg->ce); n++) {
+			i915_request_put(rq);
+
+			mutex_lock(&i915->drm.struct_mutex);
+			rq = i915_request_create(arg->ce[n]);
+			if (IS_ERR(rq)) {
+				mutex_unlock(&i915->drm.struct_mutex);
+				return PTR_ERR(rq);
+			}
+
+			i915_request_get(rq);
+			i915_request_add(rq);
+			mutex_unlock(&i915->drm.struct_mutex);
+		}
+
+		err = 0;
+		if (i915_request_wait(rq, 0, HZ / 5) < 0)
+			err = -ETIME;
+		i915_request_put(rq);
+		if (err)
+			return err;
+
+		count++;
+	} while (!__igt_timeout(end_time, NULL));
+
+	pr_info("%s: %lu switches (sync)\n", arg->ce[0]->engine->name, count);
+	return 0;
+}
+
+static int __live_parallel_switchN(void *data)
+{
+	struct parallel_switch *arg = data;
+	struct drm_i915_private *i915 = arg->ce[0]->engine->i915;
+	IGT_TIMEOUT(end_time);
+	unsigned long count;
+	int n;
+
+	count = 0;
+	do {
+		for (n = 0; n < ARRAY_SIZE(arg->ce); n++) {
+			struct i915_request *rq;
+
+			mutex_lock(&i915->drm.struct_mutex);
+			rq = i915_request_create(arg->ce[n]);
+			if (IS_ERR(rq)) {
+				mutex_unlock(&i915->drm.struct_mutex);
+				return PTR_ERR(rq);
+			}
+
+			i915_request_add(rq);
+			mutex_unlock(&i915->drm.struct_mutex);
+		}
+
+		count++;
+	} while (!__igt_timeout(end_time, NULL));
+
+	pr_info("%s: %lu switches (many)\n", arg->ce[0]->engine->name, count);
+	return 0;
+}
+
+static int live_parallel_switch(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	static int (* const func[])(void *arg) = {
+		__live_parallel_switch1,
+		__live_parallel_switchN,
+		NULL,
+	};
+	struct parallel_switch *data = NULL;
+	struct i915_gem_engines *engines;
+	struct i915_gem_engines_iter it;
+	int (* const *fn)(void *arg);
+	struct i915_gem_context *ctx;
+	struct intel_context *ce;
+	struct drm_file *file;
+	int n, m, count;
+	int err = 0;
+
+	/*
+	 * Check we can process switches on all engines simultaneously.
+	 */
+
+	if (!DRIVER_CAPS(i915)->has_logical_contexts)
+		return 0;
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	mutex_lock(&i915->drm.struct_mutex);
+
+	ctx = live_context(i915, file);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out_locked;
+	}
+
+	engines = i915_gem_context_lock_engines(ctx);
+	count = engines->num_engines;
+
+	data = kcalloc(count, sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		i915_gem_context_unlock_engines(ctx);
+		err = -ENOMEM;
+		goto out_locked;
+	}
+
+	m = 0; /* Use the first context as our template for the engines */
+	for_each_gem_engine(ce, engines, it) {
+		err = intel_context_pin(ce);
+		if (err) {
+			i915_gem_context_unlock_engines(ctx);
+			goto out_locked;
+		}
+		data[m++].ce[0] = intel_context_get(ce);
+	}
+	i915_gem_context_unlock_engines(ctx);
+
+	/* Clone the same set of engines into the other contexts */
+	for (n = 1; n < ARRAY_SIZE(data->ce); n++) {
+		ctx = live_context(i915, file);
+		if (IS_ERR(ctx)) {
+			err = PTR_ERR(ctx);
+			goto out_locked;
+		}
+
+		for (m = 0; m < count; m++) {
+			if (!data[m].ce[0])
+				continue;
+
+			ce = intel_context_create(ctx, data[m].ce[0]->engine);
+			if (IS_ERR(ce))
+				goto out_locked;
+
+			err = intel_context_pin(ce);
+			if (err) {
+				intel_context_put(ce);
+				goto out_locked;
+			}
+
+			data[m].ce[n] = ce;
+		}
+	}
+
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	for (fn = func; !err && *fn; fn++) {
+		struct igt_live_test t;
+		int n;
+
+		mutex_lock(&i915->drm.struct_mutex);
+		err = igt_live_test_begin(&t, i915, __func__, "");
+		mutex_unlock(&i915->drm.struct_mutex);
+		if (err)
+			break;
+
+		for (n = 0; n < count; n++) {
+			if (!data[n].ce[0])
+				continue;
+
+			data[n].tsk = kthread_run(*fn, &data[n],
+						  "igt/parallel:%s",
+						  data[n].ce[0]->engine->name);
+			if (IS_ERR(data[n].tsk)) {
+				err = PTR_ERR(data[n].tsk);
+				break;
+			}
+			get_task_struct(data[n].tsk);
+		}
+
+		for (n = 0; n < count; n++) {
+			int status;
+
+			if (IS_ERR_OR_NULL(data[n].tsk))
+				continue;
+
+			status = kthread_stop(data[n].tsk);
+			if (status && !err)
+				err = status;
+
+			put_task_struct(data[n].tsk);
+			data[n].tsk = NULL;
+		}
+
+		mutex_lock(&i915->drm.struct_mutex);
+		if (igt_live_test_end(&t))
+			err = -EIO;
+		mutex_unlock(&i915->drm.struct_mutex);
+	}
+
+	mutex_lock(&i915->drm.struct_mutex);
+out_locked:
+	for (n = 0; n < count; n++) {
+		for (m = 0; m < ARRAY_SIZE(data->ce); m++) {
+			if (!data[n].ce[m])
+				continue;
+
+			intel_context_unpin(data[n].ce[m]);
+			intel_context_put(data[n].ce[m]);
+		}
+	}
+	mutex_unlock(&i915->drm.struct_mutex);
+	kfree(data);
+	mock_file_free(i915, file);
+	return err;
+}
+
 static unsigned long real_page_count(struct drm_i915_gem_object *obj)
 {
 	return huge_gem_object_phys_size(obj) >> PAGE_SHIFT;
@@ -1681,6 +1905,7 @@ int i915_gem_context_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(live_nop_switch),
+		SUBTEST(live_parallel_switch),
 		SUBTEST(igt_ctx_exec),
 		SUBTEST(igt_ctx_readonly),
 		SUBTEST(igt_ctx_sseu),
-- 
cgit v1.2.3


From 1d6f1d16d3a36351a6718378790497f1ba3b5378 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 27 Sep 2019 17:03:35 +0100
Subject: drm/i915/gt: Only unwedge if we can reset first
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unwedging the GPU requires a successful GPU reset before we restore the
default submission, or else we may see residual context switch events
that we were not expecting.

v2: Pull in the special-case reset_clobbers_display, and explain why it
should be safe in the context of unwedging.

v3: Just forget all about resets before unwedging if it will clobber the
display; risk it all.

Reported-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> #v1
Link: https://patchwork.freedesktop.org/patch/msgid/20190927160335.10622-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_reset.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 76938fa3a1b9..e189897e8797 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -821,6 +821,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	struct intel_gt_timelines *timelines = &gt->timelines;
 	struct intel_timeline *tl;
 	unsigned long flags;
+	bool ok;
 
 	if (!test_bit(I915_WEDGED, &gt->reset.flags))
 		return true;
@@ -867,7 +868,12 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	}
 	spin_unlock_irqrestore(&timelines->lock, flags);
 
-	intel_gt_sanitize(gt, false);
+	/* We must reset pending GPU events before restoring our submission */
+	ok = !HAS_EXECLISTS(gt->i915); /* XXX better agnosticism desired */
+	if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display)
+		ok = __intel_gt_reset(gt, ALL_ENGINES) == 0;
+	if (!ok)
+		return false;
 
 	/*
 	 * Undo nop_submit_request. We prevent all new i915 requests from
-- 
cgit v1.2.3


From 833b45de69a6016c4b0cebe6765d526a31a81580 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 30 Sep 2019 18:48:44 +0200
Subject: kvm: x86, powerpc: do not allow clearing largepages debugfs entry

The largepages debugfs entry is incremented/decremented as shadow
pages are created or destroyed.  Clearing it will result in an
underflow, which is harmless to KVM but ugly (and could be
misinterpreted by tools that use debugfs information), so make
this particular statistic read-only.

Cc: kvm-ppc@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/powerpc/kvm/book3s.c |  8 ++++----
 arch/x86/kvm/x86.c        |  6 +++---
 include/linux/kvm_host.h  |  2 ++
 virt/kvm/kvm_main.c       | 10 +++++++---
 4 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index d7fcdfa7fee4..ec2547cc5ecb 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -36,8 +36,8 @@
 #include "book3s.h"
 #include "trace.h"
 
-#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
-#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
+#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
 
 /* #define EXIT_DEBUG */
 
@@ -69,8 +69,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "pthru_all",       VCPU_STAT(pthru_all) },
 	{ "pthru_host",      VCPU_STAT(pthru_host) },
 	{ "pthru_bad_aff",   VCPU_STAT(pthru_bad_aff) },
-	{ "largepages_2M",    VM_STAT(num_2M_pages) },
-	{ "largepages_1G",    VM_STAT(num_1G_pages) },
+	{ "largepages_2M",    VM_STAT(num_2M_pages, .mode = 0444) },
+	{ "largepages_1G",    VM_STAT(num_1G_pages, .mode = 0444) },
 	{ NULL }
 };
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 180c7e88577a..8072acaaf028 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -92,8 +92,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA));
 static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 #endif
 
-#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
-#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
+#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
 
 #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \
                                     KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
@@ -212,7 +212,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
 	{ "mmu_unsync", VM_STAT(mmu_unsync) },
 	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
-	{ "largepages", VM_STAT(lpages) },
+	{ "largepages", VM_STAT(lpages, .mode = 0444) },
 	{ "max_mmu_page_hash_collisions",
 		VM_STAT(max_mmu_page_hash_collisions) },
 	{ NULL }
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index fcb46b3374c6..719fc3e15ea4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1090,6 +1090,7 @@ enum kvm_stat_kind {
 
 struct kvm_stat_data {
 	int offset;
+	int mode;
 	struct kvm *kvm;
 };
 
@@ -1097,6 +1098,7 @@ struct kvm_stats_debugfs_item {
 	const char *name;
 	int offset;
 	enum kvm_stat_kind kind;
+	int mode;
 };
 extern struct kvm_stats_debugfs_item debugfs_entries[];
 extern struct dentry *kvm_debugfs_dir;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e6de3159e682..fd68fbe0a75d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -617,8 +617,9 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 
 		stat_data->kvm = kvm;
 		stat_data->offset = p->offset;
+		stat_data->mode = p->mode ? p->mode : 0644;
 		kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
-		debugfs_create_file(p->name, 0644, kvm->debugfs_dentry,
+		debugfs_create_file(p->name, stat_data->mode, kvm->debugfs_dentry,
 				    stat_data, stat_fops_per_vm[p->kind]);
 	}
 	return 0;
@@ -3929,7 +3930,9 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file,
 	if (!refcount_inc_not_zero(&stat_data->kvm->users_count))
 		return -ENOENT;
 
-	if (simple_attr_open(inode, file, get, set, fmt)) {
+	if (simple_attr_open(inode, file, get,
+			     stat_data->mode & S_IWUGO ? set : NULL,
+			     fmt)) {
 		kvm_put_kvm(stat_data->kvm);
 		return -ENOMEM;
 	}
@@ -4177,7 +4180,8 @@ static void kvm_init_debug(void)
 
 	kvm_debugfs_num_entries = 0;
 	for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
-		debugfs_create_file(p->name, 0644, kvm_debugfs_dir,
+		int mode = p->mode ? p->mode : 0644;
+		debugfs_create_file(p->name, mode, kvm_debugfs_dir,
 				    (void *)(long)p->offset,
 				    stat_fops[p->kind]);
 	}
-- 
cgit v1.2.3


From 7ae6d93c8f052b7a77ba56ed0f654e22a2876739 Mon Sep 17 00:00:00 2001
From: Michal Vokáč <michal.vokac@ysoft.com>
Date: Thu, 26 Sep 2019 10:59:17 +0200
Subject: net: dsa: qca8k: Use up to 7 ports for all operations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The QCA8K family supports up to 7 ports. So use the existing
QCA8K_NUM_PORTS define to allocate the switch structure and limit all
operations with the switch ports.

This was not an issue until commit 0394a63acfe2 ("net: dsa: enable and
disable all ports") disabled all unused ports. Since the unused ports 7-11
are outside of the correct register range on this switch some registers
were rewritten with invalid content.

Fixes: 6b93fb46480a ("net-next: dsa: add new driver for qca8xxx family")
Fixes: a0c02161ecfc ("net: dsa: variable number of ports")
Fixes: 0394a63acfe2 ("net: dsa: enable and disable all ports")
Signed-off-by: Michal Vokáč <michal.vokac@ysoft.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/qca8k.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index 684aa51684db..b00274caae4f 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -705,7 +705,7 @@ qca8k_setup(struct dsa_switch *ds)
 		    BIT(0) << QCA8K_GLOBAL_FW_CTRL1_UC_DP_S);
 
 	/* Setup connection between CPU port & user ports */
-	for (i = 0; i < DSA_MAX_PORTS; i++) {
+	for (i = 0; i < QCA8K_NUM_PORTS; i++) {
 		/* CPU port gets connected to all user ports of the switch */
 		if (dsa_is_cpu_port(ds, i)) {
 			qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(QCA8K_CPU_PORT),
@@ -1077,7 +1077,7 @@ qca8k_sw_probe(struct mdio_device *mdiodev)
 	if (id != QCA8K_ID_QCA8337)
 		return -ENODEV;
 
-	priv->ds = dsa_switch_alloc(&mdiodev->dev, DSA_MAX_PORTS);
+	priv->ds = dsa_switch_alloc(&mdiodev->dev, QCA8K_NUM_PORTS);
 	if (!priv->ds)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From e9789c7cc182484fc031fd88097eb14cb26c4596 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 26 Sep 2019 18:24:43 -0700
Subject: sch_cbq: validate TCA_CBQ_WRROPT to avoid crash

syzbot reported a crash in cbq_normalize_quanta() caused
by an out of range cl->priority.

iproute2 enforces this check, but malicious users do not.

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN PTI
Modules linked in:
CPU: 1 PID: 26447 Comm: syz-executor.1 Not tainted 5.3+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:cbq_normalize_quanta.part.0+0x1fd/0x430 net/sched/sch_cbq.c:902
RSP: 0018:ffff8801a5c333b0 EFLAGS: 00010206
RAX: 0000000020000003 RBX: 00000000fffffff8 RCX: ffffc9000712f000
RDX: 00000000000043bf RSI: ffffffff83be8962 RDI: 0000000100000018
RBP: ffff8801a5c33420 R08: 000000000000003a R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 00000000000002ef
R13: ffff88018da95188 R14: dffffc0000000000 R15: 0000000000000015
FS:  00007f37d26b1700(0000) GS:ffff8801dad00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004c7cec CR3: 00000001bcd0a006 CR4: 00000000001626f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 [<ffffffff83be9d57>] cbq_normalize_quanta include/net/pkt_sched.h:27 [inline]
 [<ffffffff83be9d57>] cbq_addprio net/sched/sch_cbq.c:1097 [inline]
 [<ffffffff83be9d57>] cbq_set_wrr+0x2d7/0x450 net/sched/sch_cbq.c:1115
 [<ffffffff83bee8a7>] cbq_change_class+0x987/0x225b net/sched/sch_cbq.c:1537
 [<ffffffff83b96985>] tc_ctl_tclass+0x555/0xcd0 net/sched/sch_api.c:2329
 [<ffffffff83a84655>] rtnetlink_rcv_msg+0x485/0xc10 net/core/rtnetlink.c:5248
 [<ffffffff83cadf0a>] netlink_rcv_skb+0x17a/0x460 net/netlink/af_netlink.c:2510
 [<ffffffff83a7db6d>] rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5266
 [<ffffffff83cac2c6>] netlink_unicast_kernel net/netlink/af_netlink.c:1324 [inline]
 [<ffffffff83cac2c6>] netlink_unicast+0x536/0x720 net/netlink/af_netlink.c:1350
 [<ffffffff83cacd4a>] netlink_sendmsg+0x89a/0xd50 net/netlink/af_netlink.c:1939
 [<ffffffff8399d46e>] sock_sendmsg_nosec net/socket.c:673 [inline]
 [<ffffffff8399d46e>] sock_sendmsg+0x12e/0x170 net/socket.c:684
 [<ffffffff8399f1fd>] ___sys_sendmsg+0x81d/0x960 net/socket.c:2359
 [<ffffffff839a2d05>] __sys_sendmsg+0x105/0x1d0 net/socket.c:2397
 [<ffffffff839a2df9>] SYSC_sendmsg net/socket.c:2406 [inline]
 [<ffffffff839a2df9>] SyS_sendmsg+0x29/0x30 net/socket.c:2404
 [<ffffffff8101ccc8>] do_syscall_64+0x528/0x770 arch/x86/entry/common.c:305
 [<ffffffff84400091>] entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbq.c | 43 +++++++++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 14 deletions(-)

diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 06c7a2da21bc..39b427dc7512 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1127,6 +1127,33 @@ static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = {
 	[TCA_CBQ_POLICE]	= { .len = sizeof(struct tc_cbq_police) },
 };
 
+static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1],
+			 struct nlattr *opt,
+			 struct netlink_ext_ack *extack)
+{
+	int err;
+
+	if (!opt) {
+		NL_SET_ERR_MSG(extack, "CBQ options are required for this operation");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt,
+					  cbq_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (tb[TCA_CBQ_WRROPT]) {
+		const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]);
+
+		if (wrr->priority > TC_CBQ_MAXPRIO) {
+			NL_SET_ERR_MSG(extack, "priority is bigger than TC_CBQ_MAXPRIO");
+			err = -EINVAL;
+		}
+	}
+	return err;
+}
+
 static int cbq_init(struct Qdisc *sch, struct nlattr *opt,
 		    struct netlink_ext_ack *extack)
 {
@@ -1139,13 +1166,7 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt,
 	hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
 	q->delay_timer.function = cbq_undelay;
 
-	if (!opt) {
-		NL_SET_ERR_MSG(extack, "CBQ options are required for this operation");
-		return -EINVAL;
-	}
-
-	err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy,
-					  extack);
+	err = cbq_opt_parse(tb, opt, extack);
 	if (err < 0)
 		return err;
 
@@ -1464,13 +1485,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 	struct cbq_class *parent;
 	struct qdisc_rate_table *rtab = NULL;
 
-	if (!opt) {
-		NL_SET_ERR_MSG(extack, "Mandatory qdisc options missing");
-		return -EINVAL;
-	}
-
-	err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, cbq_policy,
-					  extack);
+	err = cbq_opt_parse(tb, opt, extack);
 	if (err < 0)
 		return err;
 
-- 
cgit v1.2.3


From 0e141f757b2c78c983df893e9993313e2dc21e38 Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Fri, 27 Sep 2019 14:58:20 +0800
Subject: erspan: remove the incorrect mtu limit for erspan

erspan driver calls ether_setup(), after commit 61e84623ace3
("net: centralize net_device min/max MTU checking"), the range
of mtu is [min_mtu, max_mtu], which is [68, 1500] by default.

It causes the dev mtu of the erspan device to not be greater
than 1500, this limit value is not correct for ipgre tap device.

Tested:
Before patch:
# ip link set erspan0 mtu 1600
Error: mtu greater than device maximum.
After patch:
# ip link set erspan0 mtu 1600
# ip -d link show erspan0
21: erspan0@NONE: <BROADCAST,MULTICAST> mtu 1600 qdisc noop state DOWN
mode DEFAULT group default qlen 1000
    link/ether 00:00:00:00:00:00 brd ff:ff:ff:ff:ff:ff promiscuity 0 minmtu 68 maxmtu 0

Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking")
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index a53a543fe055..52690bb3e40f 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1446,6 +1446,7 @@ static void erspan_setup(struct net_device *dev)
 	struct ip_tunnel *t = netdev_priv(dev);
 
 	ether_setup(dev);
+	dev->max_mtu = 0;
 	dev->netdev_ops = &erspan_netdev_ops;
 	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
-- 
cgit v1.2.3


From a304c0a60252fde9daccd9f8a07a598021f6956a Mon Sep 17 00:00:00 2001
From: Keerthy <j-keerthy@ti.com>
Date: Fri, 20 Sep 2019 13:29:46 +0530
Subject: arm64/ARM: configs: Change CONFIG_REMOTEPROC from m to y

Commit 6334150e9a36 ("remoteproc: don't allow modular build")
changes CONFIG_REMOTEPROC to a boolean from a tristate config
option which inhibits all defconfigs marking CONFIG_REMOTEPROC as
a module in compiling the remoteproc and dependent config options.

So fix the configs to have CONFIG_REMOTEPROC built in.

Link: https://lore.kernel.org/r/20190920075946.13282-5-j-keerthy@ti.com
Fixes: 6334150e9a36 ("remoteproc: don't allow modular build")
Signed-off-by: Keerthy <j-keerthy@ti.com>
Acked-by: Will Deacon <will@kernel.org>
[olof: Fixed up all 4 occurrances in this one commit]
Signed-off-by: Olof Johansson <olof@lixom.net>
---
 arch/arm/configs/davinci_all_defconfig | 2 +-
 arch/arm/configs/multi_v7_defconfig    | 2 +-
 arch/arm/configs/omap2plus_defconfig   | 2 +-
 arch/arm64/configs/defconfig           | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig
index b34970ce6b31..01e3c0f4be92 100644
--- a/arch/arm/configs/davinci_all_defconfig
+++ b/arch/arm/configs/davinci_all_defconfig
@@ -228,7 +228,7 @@ CONFIG_RTC_DRV_OMAP=m
 CONFIG_DMADEVICES=y
 CONFIG_TI_EDMA=y
 CONFIG_COMMON_CLK_PWM=m
-CONFIG_REMOTEPROC=m
+CONFIG_REMOTEPROC=y
 CONFIG_DA8XX_REMOTEPROC=m
 CONFIG_MEMORY=y
 CONFIG_TI_AEMIF=m
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 13ba53286901..198de8e36d92 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -933,7 +933,7 @@ CONFIG_BCM2835_MBOX=y
 CONFIG_ROCKCHIP_IOMMU=y
 CONFIG_TEGRA_IOMMU_GART=y
 CONFIG_TEGRA_IOMMU_SMMU=y
-CONFIG_REMOTEPROC=m
+CONFIG_REMOTEPROC=y
 CONFIG_ST_REMOTEPROC=m
 CONFIG_RPMSG_VIRTIO=m
 CONFIG_ASPEED_LPC_CTRL=m
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 64eb896907bf..af4069476582 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -481,7 +481,7 @@ CONFIG_RTC_DRV_OMAP=m
 CONFIG_RTC_DRV_CPCAP=m
 CONFIG_DMADEVICES=y
 CONFIG_OMAP_IOMMU=y
-CONFIG_REMOTEPROC=m
+CONFIG_REMOTEPROC=y
 CONFIG_OMAP_REMOTEPROC=m
 CONFIG_WKUP_M3_RPROC=m
 CONFIG_SOC_TI=y
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 8e05c39eab08..c9a867ac32d4 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -723,7 +723,7 @@ CONFIG_TEGRA_IOMMU_SMMU=y
 CONFIG_ARM_SMMU=y
 CONFIG_ARM_SMMU_V3=y
 CONFIG_QCOM_IOMMU=y
-CONFIG_REMOTEPROC=m
+CONFIG_REMOTEPROC=y
 CONFIG_QCOM_Q6V5_MSS=m
 CONFIG_QCOM_Q6V5_PAS=m
 CONFIG_QCOM_SYSMON=m
-- 
cgit v1.2.3


From b1ba55cf1cfb9f3e0e00d743534684a25bf66d28 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 27 Sep 2019 11:30:30 -0300
Subject: tools headers uapi: Sync asm-generic/mman-common.h with the kernel
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To pick the changes from:

  1a4e58cce84e ("mm: introduce MADV_PAGEOUT")
  9c276cc65a58 ("mm: introduce MADV_COLD")

That result in these changes in the tools:

  $ tools/perf/trace/beauty/madvise_behavior.sh > before
  $ cp include/uapi/asm-generic/mman-common.h tools/include/uapi/asm-generic/mman-common.h
  $ git diff
  diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
  index 63b1f506ea67..c160a5354eb6 100644
  --- a/tools/include/uapi/asm-generic/mman-common.h
  +++ b/tools/include/uapi/asm-generic/mman-common.h
  @@ -67,6 +67,9 @@
   #define MADV_WIPEONFORK 18             /* Zero memory on fork, child only */
   #define MADV_KEEPONFORK 19             /* Undo MADV_WIPEONFORK */

  +#define MADV_COLD      20              /* deactivate these pages */
  +#define MADV_PAGEOUT   21              /* reclaim these pages */
  +
   /* compatibility flags */
   #define MAP_FILE       0

  $ tools/perf/trace/beauty/madvise_behavior.sh > after
  $ diff -u before after
  --- before	2019-09-27 11:29:43.346320100 -0300
  +++ after	2019-09-27 11:30:03.838570439 -0300
  @@ -16,6 +16,8 @@
   	[17] = "DODUMP",
   	[18] = "WIPEONFORK",
   	[19] = "KEEPONFORK",
  +	[20] = "COLD",
  +	[21] = "PAGEOUT",
   	[100] = "HWPOISON",
   	[101] = "SOFT_OFFLINE",
   };
  $

I.e. now when madvise gets those behaviours as args, it will be able to
translate from the number to a human readable string.

This addresses the following perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/mman-common.h' differs from latest version at 'include/uapi/asm-generic/mman-common.h'
  diff -u tools/include/uapi/asm-generic/mman-common.h include/uapi/asm-generic/mman-common.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-n40y6c4sa49p29q6sl8w3ufx@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/asm-generic/mman-common.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 63b1f506ea67..c160a5354eb6 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -67,6 +67,9 @@
 #define MADV_WIPEONFORK 18		/* Zero memory on fork, child only */
 #define MADV_KEEPONFORK 19		/* Undo MADV_WIPEONFORK */
 
+#define MADV_COLD	20		/* deactivate these pages */
+#define MADV_PAGEOUT	21		/* reclaim these pages */
+
 /* compatibility flags */
 #define MAP_FILE	0
 
-- 
cgit v1.2.3


From 05f371f8c55d69e4c04db4473085303291e4e734 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 27 Sep 2019 11:42:26 -0300
Subject: tools headers uapi: Sync linux/usbdevice_fs.h with the kernel sources
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To pick up the changes from:

  4ed3350539aa ("USB: usbfs: Add a capability flag for runtime suspend")
  7794f486ed0b ("usbfs: Add ioctls for runtime power management")

This triggers these changes in the kernel sources, automagically
supporting these new ioctls in the 'perf trace' beautifiers.

Soon this will be used in things like filter expressions for tracepoints
in 'perf record', 'perf trace', 'perf top', i.e. filter expressions will
do a lookup to turn things like USBDEVFS_WAIT_FOR_RESUME into _IO('U',
35) before associating the tracepoint expression to tracepoint perf
event.

  $ tools/perf/trace/beauty/usbdevfs_ioctl.sh  > before
  $ cp include/uapi/linux/usbdevice_fs.h tools/include/uapi/linux/usbdevice_fs.h
  $ git diff
  diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h
  index 78efe870c2b7..cf525cddeb94 100644
  --- a/tools/include/uapi/linux/usbdevice_fs.h
  +++ b/tools/include/uapi/linux/usbdevice_fs.h
  @@ -158,6 +158,7 @@ struct usbdevfs_hub_portinfo {
   #define USBDEVFS_CAP_MMAP                      0x20
   #define USBDEVFS_CAP_DROP_PRIVILEGES           0x40
   #define USBDEVFS_CAP_CONNINFO_EX               0x80
  +#define USBDEVFS_CAP_SUSPEND                   0x100

   /* USBDEVFS_DISCONNECT_CLAIM flags & struct */

  @@ -223,5 +224,8 @@ struct usbdevfs_streams {
    * extending size of the data returned.
    */
   #define USBDEVFS_CONNINFO_EX(len)  _IOC(_IOC_READ, 'U', 32, len)
  +#define USBDEVFS_FORBID_SUSPEND    _IO('U', 33)
  +#define USBDEVFS_ALLOW_SUSPEND     _IO('U', 34)
  +#define USBDEVFS_WAIT_FOR_RESUME   _IO('U', 35)

   #endif /* _UAPI_LINUX_USBDEVICE_FS_H */
  $ tools/perf/trace/beauty/usbdevfs_ioctl.sh  > after
  $ diff -u before after
  --- before	2019-09-27 11:41:50.634867620 -0300
  +++ after	2019-09-27 11:42:07.453102978 -0300
  @@ -24,6 +24,9 @@
   	[30] = "DROP_PRIVILEGES",
   	[31] = "GET_SPEED",
   	[32] = "CONNINFO_EX",
  +	[33] = "FORBID_SUSPEND",
  +	[34] = "ALLOW_SUSPEND",
  +	[35] = "WAIT_FOR_RESUME",
   	[3] = "RESETEP",
   	[4] = "SETINTERFACE",
   	[5] = "SETCONFIGURATION",
  $

This addresses the following perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/usbdevice_fs.h' differs from latest version at 'include/uapi/linux/usbdevice_fs.h'
  diff -u tools/include/uapi/linux/usbdevice_fs.h include/uapi/linux/usbdevice_fs.h

Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-x1rb109b9nfi7pukota82xhj@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/usbdevice_fs.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/include/uapi/linux/usbdevice_fs.h
index 78efe870c2b7..cf525cddeb94 100644
--- a/tools/include/uapi/linux/usbdevice_fs.h
+++ b/tools/include/uapi/linux/usbdevice_fs.h
@@ -158,6 +158,7 @@ struct usbdevfs_hub_portinfo {
 #define USBDEVFS_CAP_MMAP			0x20
 #define USBDEVFS_CAP_DROP_PRIVILEGES		0x40
 #define USBDEVFS_CAP_CONNINFO_EX		0x80
+#define USBDEVFS_CAP_SUSPEND			0x100
 
 /* USBDEVFS_DISCONNECT_CLAIM flags & struct */
 
@@ -223,5 +224,8 @@ struct usbdevfs_streams {
  * extending size of the data returned.
  */
 #define USBDEVFS_CONNINFO_EX(len)  _IOC(_IOC_READ, 'U', 32, len)
+#define USBDEVFS_FORBID_SUSPEND    _IO('U', 33)
+#define USBDEVFS_ALLOW_SUSPEND     _IO('U', 34)
+#define USBDEVFS_WAIT_FOR_RESUME   _IO('U', 35)
 
 #endif /* _UAPI_LINUX_USBDEVICE_FS_H */
-- 
cgit v1.2.3


From 0ae4061223a3d097222cbec6599370e54db17731 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 27 Sep 2019 12:01:26 -0300
Subject: tools headers uapi: Sync linux/fs.h with the kernel sources

To pick the changes from:

  78a1b96bcf7a ("fscrypt: add FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS ioctl")
  23c688b54016 ("fscrypt: allow unprivileged users to add/remove keys for v2 policies")
  5dae460c2292 ("fscrypt: v2 encryption policy support")
  5a7e29924dac ("fscrypt: add FS_IOC_GET_ENCRYPTION_KEY_STATUS ioctl")
  b1c0ec3599f4 ("fscrypt: add FS_IOC_REMOVE_ENCRYPTION_KEY ioctl")
  22d94f493bfb ("fscrypt: add FS_IOC_ADD_ENCRYPTION_KEY ioctl")
  3b6df59bc4d2 ("fscrypt: use FSCRYPT_* definitions, not FS_*")
  2336d0deb2d4 ("fscrypt: use FSCRYPT_ prefix for uapi constants")
  7af0ab0d3aab ("fs, fscrypt: move uapi definitions to new header <linux/fscrypt.h>")

That don't trigger any changes in tooling, as it so far is used only
for:

  $ grep -l 'fs\.h' tools/perf/trace/beauty/*.sh | xargs grep regex=
  tools/perf/trace/beauty/rename_flags.sh:regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+RENAME_([[:alnum:]_]+)[[:space:]]+\(1[[:space:]]*<<[[:space:]]*([[:xdigit:]]+)[[:space:]]*\)[[:space:]]*.*'
  tools/perf/trace/beauty/sync_file_range.sh:regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+SYNC_FILE_RANGE_([[:alnum:]_]+)[[:space:]]+([[:xdigit:]]+)[[:space:]]*.*'
  tools/perf/trace/beauty/usbdevfs_ioctl.sh:regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)(\(\w+\))?[[:space:]]+_IO[CWR]{0,2}\([[:space:]]*(_IOC_\w+,[[:space:]]*)?'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*"
  tools/perf/trace/beauty/usbdevfs_ioctl.sh:regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)[[:space:]]+_IO[WR]{0,2}\([[:space:]]*'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*"
  $

This silences this perf build warning:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/fs.h' differs from latest version at 'include/uapi/linux/fs.h'
  diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-44g48exl9br9ba0t64chqb4i@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/fs.h      |  55 +----------
 tools/include/uapi/linux/fscrypt.h | 181 +++++++++++++++++++++++++++++++++++++
 tools/perf/check-headers.sh        |   1 +
 3 files changed, 186 insertions(+), 51 deletions(-)
 create mode 100644 tools/include/uapi/linux/fscrypt.h

diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index 2a616aa3f686..379a612f8f1d 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -13,6 +13,9 @@
 #include <linux/limits.h>
 #include <linux/ioctl.h>
 #include <linux/types.h>
+#ifndef __KERNEL__
+#include <linux/fscrypt.h>
+#endif
 
 /* Use of MS_* flags within the kernel is restricted to core mount(2) code. */
 #if !defined(__KERNEL__)
@@ -212,57 +215,6 @@ struct fsxattr {
 #define FS_IOC_GETFSLABEL		_IOR(0x94, 49, char[FSLABEL_MAX])
 #define FS_IOC_SETFSLABEL		_IOW(0x94, 50, char[FSLABEL_MAX])
 
-/*
- * File system encryption support
- */
-/* Policy provided via an ioctl on the topmost directory */
-#define FS_KEY_DESCRIPTOR_SIZE	8
-
-#define FS_POLICY_FLAGS_PAD_4		0x00
-#define FS_POLICY_FLAGS_PAD_8		0x01
-#define FS_POLICY_FLAGS_PAD_16		0x02
-#define FS_POLICY_FLAGS_PAD_32		0x03
-#define FS_POLICY_FLAGS_PAD_MASK	0x03
-#define FS_POLICY_FLAG_DIRECT_KEY	0x04	/* use master key directly */
-#define FS_POLICY_FLAGS_VALID		0x07
-
-/* Encryption algorithms */
-#define FS_ENCRYPTION_MODE_INVALID		0
-#define FS_ENCRYPTION_MODE_AES_256_XTS		1
-#define FS_ENCRYPTION_MODE_AES_256_GCM		2
-#define FS_ENCRYPTION_MODE_AES_256_CBC		3
-#define FS_ENCRYPTION_MODE_AES_256_CTS		4
-#define FS_ENCRYPTION_MODE_AES_128_CBC		5
-#define FS_ENCRYPTION_MODE_AES_128_CTS		6
-#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7 /* Removed, do not use. */
-#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8 /* Removed, do not use. */
-#define FS_ENCRYPTION_MODE_ADIANTUM		9
-
-struct fscrypt_policy {
-	__u8 version;
-	__u8 contents_encryption_mode;
-	__u8 filenames_encryption_mode;
-	__u8 flags;
-	__u8 master_key_descriptor[FS_KEY_DESCRIPTOR_SIZE];
-};
-
-#define FS_IOC_SET_ENCRYPTION_POLICY	_IOR('f', 19, struct fscrypt_policy)
-#define FS_IOC_GET_ENCRYPTION_PWSALT	_IOW('f', 20, __u8[16])
-#define FS_IOC_GET_ENCRYPTION_POLICY	_IOW('f', 21, struct fscrypt_policy)
-
-/* Parameters for passing an encryption key into the kernel keyring */
-#define FS_KEY_DESC_PREFIX		"fscrypt:"
-#define FS_KEY_DESC_PREFIX_SIZE		8
-
-/* Structure that userspace passes to the kernel keyring */
-#define FS_MAX_KEY_SIZE			64
-
-struct fscrypt_key {
-	__u32 mode;
-	__u8 raw[FS_MAX_KEY_SIZE];
-	__u32 size;
-};
-
 /*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
  *
@@ -306,6 +258,7 @@ struct fscrypt_key {
 #define FS_TOPDIR_FL			0x00020000 /* Top of directory hierarchies*/
 #define FS_HUGE_FILE_FL			0x00040000 /* Reserved for ext4 */
 #define FS_EXTENT_FL			0x00080000 /* Extents */
+#define FS_VERITY_FL			0x00100000 /* Verity protected inode */
 #define FS_EA_INODE_FL			0x00200000 /* Inode used for large EA */
 #define FS_EOFBLOCKS_FL			0x00400000 /* Reserved for ext4 */
 #define FS_NOCOW_FL			0x00800000 /* Do not cow file */
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
new file mode 100644
index 000000000000..39ccfe9311c3
--- /dev/null
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -0,0 +1,181 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * fscrypt user API
+ *
+ * These ioctls can be used on filesystems that support fscrypt.  See the
+ * "User API" section of Documentation/filesystems/fscrypt.rst.
+ */
+#ifndef _UAPI_LINUX_FSCRYPT_H
+#define _UAPI_LINUX_FSCRYPT_H
+
+#include <linux/types.h>
+
+/* Encryption policy flags */
+#define FSCRYPT_POLICY_FLAGS_PAD_4		0x00
+#define FSCRYPT_POLICY_FLAGS_PAD_8		0x01
+#define FSCRYPT_POLICY_FLAGS_PAD_16		0x02
+#define FSCRYPT_POLICY_FLAGS_PAD_32		0x03
+#define FSCRYPT_POLICY_FLAGS_PAD_MASK		0x03
+#define FSCRYPT_POLICY_FLAG_DIRECT_KEY		0x04
+#define FSCRYPT_POLICY_FLAGS_VALID		0x07
+
+/* Encryption algorithms */
+#define FSCRYPT_MODE_AES_256_XTS		1
+#define FSCRYPT_MODE_AES_256_CTS		4
+#define FSCRYPT_MODE_AES_128_CBC		5
+#define FSCRYPT_MODE_AES_128_CTS		6
+#define FSCRYPT_MODE_ADIANTUM			9
+#define __FSCRYPT_MODE_MAX			9
+
+/*
+ * Legacy policy version; ad-hoc KDF and no key verification.
+ * For new encrypted directories, use fscrypt_policy_v2 instead.
+ *
+ * Careful: the .version field for this is actually 0, not 1.
+ */
+#define FSCRYPT_POLICY_V1		0
+#define FSCRYPT_KEY_DESCRIPTOR_SIZE	8
+struct fscrypt_policy_v1 {
+	__u8 version;
+	__u8 contents_encryption_mode;
+	__u8 filenames_encryption_mode;
+	__u8 flags;
+	__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+};
+#define fscrypt_policy	fscrypt_policy_v1
+
+/*
+ * Process-subscribed "logon" key description prefix and payload format.
+ * Deprecated; prefer FS_IOC_ADD_ENCRYPTION_KEY instead.
+ */
+#define FSCRYPT_KEY_DESC_PREFIX		"fscrypt:"
+#define FSCRYPT_KEY_DESC_PREFIX_SIZE	8
+#define FSCRYPT_MAX_KEY_SIZE		64
+struct fscrypt_key {
+	__u32 mode;
+	__u8 raw[FSCRYPT_MAX_KEY_SIZE];
+	__u32 size;
+};
+
+/*
+ * New policy version with HKDF and key verification (recommended).
+ */
+#define FSCRYPT_POLICY_V2		2
+#define FSCRYPT_KEY_IDENTIFIER_SIZE	16
+struct fscrypt_policy_v2 {
+	__u8 version;
+	__u8 contents_encryption_mode;
+	__u8 filenames_encryption_mode;
+	__u8 flags;
+	__u8 __reserved[4];
+	__u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+};
+
+/* Struct passed to FS_IOC_GET_ENCRYPTION_POLICY_EX */
+struct fscrypt_get_policy_ex_arg {
+	__u64 policy_size; /* input/output */
+	union {
+		__u8 version;
+		struct fscrypt_policy_v1 v1;
+		struct fscrypt_policy_v2 v2;
+	} policy; /* output */
+};
+
+/*
+ * v1 policy keys are specified by an arbitrary 8-byte key "descriptor",
+ * matching fscrypt_policy_v1::master_key_descriptor.
+ */
+#define FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR	1
+
+/*
+ * v2 policy keys are specified by a 16-byte key "identifier" which the kernel
+ * calculates as a cryptographic hash of the key itself,
+ * matching fscrypt_policy_v2::master_key_identifier.
+ */
+#define FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER	2
+
+/*
+ * Specifies a key, either for v1 or v2 policies.  This doesn't contain the
+ * actual key itself; this is just the "name" of the key.
+ */
+struct fscrypt_key_specifier {
+	__u32 type;	/* one of FSCRYPT_KEY_SPEC_TYPE_* */
+	__u32 __reserved;
+	union {
+		__u8 __reserved[32]; /* reserve some extra space */
+		__u8 descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+		__u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+	} u;
+};
+
+/* Struct passed to FS_IOC_ADD_ENCRYPTION_KEY */
+struct fscrypt_add_key_arg {
+	struct fscrypt_key_specifier key_spec;
+	__u32 raw_size;
+	__u32 __reserved[9];
+	__u8 raw[];
+};
+
+/* Struct passed to FS_IOC_REMOVE_ENCRYPTION_KEY */
+struct fscrypt_remove_key_arg {
+	struct fscrypt_key_specifier key_spec;
+#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_FILES_BUSY	0x00000001
+#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS	0x00000002
+	__u32 removal_status_flags;	/* output */
+	__u32 __reserved[5];
+};
+
+/* Struct passed to FS_IOC_GET_ENCRYPTION_KEY_STATUS */
+struct fscrypt_get_key_status_arg {
+	/* input */
+	struct fscrypt_key_specifier key_spec;
+	__u32 __reserved[6];
+
+	/* output */
+#define FSCRYPT_KEY_STATUS_ABSENT		1
+#define FSCRYPT_KEY_STATUS_PRESENT		2
+#define FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED	3
+	__u32 status;
+#define FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF   0x00000001
+	__u32 status_flags;
+	__u32 user_count;
+	__u32 __out_reserved[13];
+};
+
+#define FS_IOC_SET_ENCRYPTION_POLICY		_IOR('f', 19, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_PWSALT		_IOW('f', 20, __u8[16])
+#define FS_IOC_GET_ENCRYPTION_POLICY		_IOW('f', 21, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_POLICY_EX		_IOWR('f', 22, __u8[9]) /* size + version */
+#define FS_IOC_ADD_ENCRYPTION_KEY		_IOWR('f', 23, struct fscrypt_add_key_arg)
+#define FS_IOC_REMOVE_ENCRYPTION_KEY		_IOWR('f', 24, struct fscrypt_remove_key_arg)
+#define FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS	_IOWR('f', 25, struct fscrypt_remove_key_arg)
+#define FS_IOC_GET_ENCRYPTION_KEY_STATUS	_IOWR('f', 26, struct fscrypt_get_key_status_arg)
+
+/**********************************************************************/
+
+/* old names; don't add anything new here! */
+#ifndef __KERNEL__
+#define FS_KEY_DESCRIPTOR_SIZE		FSCRYPT_KEY_DESCRIPTOR_SIZE
+#define FS_POLICY_FLAGS_PAD_4		FSCRYPT_POLICY_FLAGS_PAD_4
+#define FS_POLICY_FLAGS_PAD_8		FSCRYPT_POLICY_FLAGS_PAD_8
+#define FS_POLICY_FLAGS_PAD_16		FSCRYPT_POLICY_FLAGS_PAD_16
+#define FS_POLICY_FLAGS_PAD_32		FSCRYPT_POLICY_FLAGS_PAD_32
+#define FS_POLICY_FLAGS_PAD_MASK	FSCRYPT_POLICY_FLAGS_PAD_MASK
+#define FS_POLICY_FLAG_DIRECT_KEY	FSCRYPT_POLICY_FLAG_DIRECT_KEY
+#define FS_POLICY_FLAGS_VALID		FSCRYPT_POLICY_FLAGS_VALID
+#define FS_ENCRYPTION_MODE_INVALID	0	/* never used */
+#define FS_ENCRYPTION_MODE_AES_256_XTS	FSCRYPT_MODE_AES_256_XTS
+#define FS_ENCRYPTION_MODE_AES_256_GCM	2	/* never used */
+#define FS_ENCRYPTION_MODE_AES_256_CBC	3	/* never used */
+#define FS_ENCRYPTION_MODE_AES_256_CTS	FSCRYPT_MODE_AES_256_CTS
+#define FS_ENCRYPTION_MODE_AES_128_CBC	FSCRYPT_MODE_AES_128_CBC
+#define FS_ENCRYPTION_MODE_AES_128_CTS	FSCRYPT_MODE_AES_128_CTS
+#define FS_ENCRYPTION_MODE_SPECK128_256_XTS	7	/* removed */
+#define FS_ENCRYPTION_MODE_SPECK128_256_CTS	8	/* removed */
+#define FS_ENCRYPTION_MODE_ADIANTUM	FSCRYPT_MODE_ADIANTUM
+#define FS_KEY_DESC_PREFIX		FSCRYPT_KEY_DESC_PREFIX
+#define FS_KEY_DESC_PREFIX_SIZE		FSCRYPT_KEY_DESC_PREFIX_SIZE
+#define FS_MAX_KEY_SIZE			FSCRYPT_MAX_KEY_SIZE
+#endif /* !__KERNEL__ */
+
+#endif /* _UAPI_LINUX_FSCRYPT_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index e2e0f06c97d0..cea13cb987d0 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -8,6 +8,7 @@ include/uapi/drm/i915_drm.h
 include/uapi/linux/fadvise.h
 include/uapi/linux/fcntl.h
 include/uapi/linux/fs.h
+include/uapi/linux/fscrypt.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
-- 
cgit v1.2.3


From b7ad6108484221f431372b94763b74e550d16c93 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Fri, 27 Sep 2019 12:18:21 -0300
Subject: tools headers kvm: Sync kvm headers with the kernel sources

To pick the changes in:

  200824f55eef ("KVM: s390: Disallow invalid bits in kvm_valid_regs and kvm_dirty_regs")
  4a53d99dd0c2 ("KVM: VMX: Introduce exit reason for receiving INIT signal on guest-mode")
  7396d337cfad ("KVM: x86: Return to userspace with internal error on unexpected exit reason")
  92f35b751c71 ("KVM: arm/arm64: vgic: Allow more than 256 vcpus for KVM_IRQ_LINE")

None of them trigger any changes in tooling, this time this is just to silence
these perf build warnings:

  Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h'
  diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h
  Warning: Kernel ABI header at 'tools/arch/x86/include/uapi/asm/vmx.h' differs from latest version at 'arch/x86/include/uapi/asm/vmx.h'
  diff -u tools/arch/x86/include/uapi/asm/vmx.h arch/x86/include/uapi/asm/vmx.h
  Warning: Kernel ABI header at 'tools/arch/s390/include/uapi/asm/kvm.h' differs from latest version at 'arch/s390/include/uapi/asm/kvm.h'
  diff -u tools/arch/s390/include/uapi/asm/kvm.h arch/s390/include/uapi/asm/kvm.h
  Warning: Kernel ABI header at 'tools/arch/arm/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm/include/uapi/asm/kvm.h'
  diff -u tools/arch/arm/include/uapi/asm/kvm.h arch/arm/include/uapi/asm/kvm.h
  Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h'
  diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Janosch Frank <frankja@linux.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Liran Alon <liran.alon@oracle.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Thomas Huth <thuth@redhat.com>
Link: https://lkml.kernel.org/n/tip-akuugvvjxte26kzv23zp5d2z@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/arm/include/uapi/asm/kvm.h   | 4 +++-
 tools/arch/arm64/include/uapi/asm/kvm.h | 4 +++-
 tools/arch/s390/include/uapi/asm/kvm.h  | 6 ++++++
 tools/arch/x86/include/uapi/asm/vmx.h   | 2 ++
 tools/include/uapi/linux/kvm.h          | 3 +++
 5 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index a4217c1a5d01..2769360f195c 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -266,8 +266,10 @@ struct kvm_vcpu_events {
 #define   KVM_DEV_ARM_ITS_CTRL_RESET		4
 
 /* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_VCPU2_SHIFT		28
+#define KVM_ARM_IRQ_VCPU2_MASK		0xf
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
-#define KVM_ARM_IRQ_TYPE_MASK		0xff
+#define KVM_ARM_IRQ_TYPE_MASK		0xf
 #define KVM_ARM_IRQ_VCPU_SHIFT		16
 #define KVM_ARM_IRQ_VCPU_MASK		0xff
 #define KVM_ARM_IRQ_NUM_SHIFT		0
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 9a507716ae2f..67c21f9bdbad 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -325,8 +325,10 @@ struct kvm_vcpu_events {
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
 
 /* KVM_IRQ_LINE irq field index values */
+#define KVM_ARM_IRQ_VCPU2_SHIFT		28
+#define KVM_ARM_IRQ_VCPU2_MASK		0xf
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
-#define KVM_ARM_IRQ_TYPE_MASK		0xff
+#define KVM_ARM_IRQ_TYPE_MASK		0xf
 #define KVM_ARM_IRQ_VCPU_SHIFT		16
 #define KVM_ARM_IRQ_VCPU_MASK		0xff
 #define KVM_ARM_IRQ_NUM_SHIFT		0
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 47104e5b47fd..436ec7636927 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -231,6 +231,12 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_GSCB   (1UL << 9)
 #define KVM_SYNC_BPBC   (1UL << 10)
 #define KVM_SYNC_ETOKEN (1UL << 11)
+
+#define KVM_SYNC_S390_VALID_FIELDS \
+	(KVM_SYNC_PREFIX | KVM_SYNC_GPRS | KVM_SYNC_ACRS | KVM_SYNC_CRS | \
+	 KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT | KVM_SYNC_VRS | KVM_SYNC_RICCB | \
+	 KVM_SYNC_FPRS | KVM_SYNC_GSCB | KVM_SYNC_BPBC | KVM_SYNC_ETOKEN)
+
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
 #define SDNXL (1UL << SDNXC)
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index f0b0c90dd398..f01950aa7fae 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -31,6 +31,7 @@
 #define EXIT_REASON_EXCEPTION_NMI       0
 #define EXIT_REASON_EXTERNAL_INTERRUPT  1
 #define EXIT_REASON_TRIPLE_FAULT        2
+#define EXIT_REASON_INIT_SIGNAL			3
 
 #define EXIT_REASON_PENDING_INTERRUPT   7
 #define EXIT_REASON_NMI_WINDOW          8
@@ -90,6 +91,7 @@
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
 	{ EXIT_REASON_EXTERNAL_INTERRUPT,    "EXTERNAL_INTERRUPT" }, \
 	{ EXIT_REASON_TRIPLE_FAULT,          "TRIPLE_FAULT" }, \
+	{ EXIT_REASON_INIT_SIGNAL,           "INIT_SIGNAL" }, \
 	{ EXIT_REASON_PENDING_INTERRUPT,     "PENDING_INTERRUPT" }, \
 	{ EXIT_REASON_NMI_WINDOW,            "NMI_WINDOW" }, \
 	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 5e3f12d5359e..233efbb1c81c 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -243,6 +243,8 @@ struct kvm_hyperv_exit {
 #define KVM_INTERNAL_ERROR_SIMUL_EX	2
 /* Encounter unexpected vm-exit due to delivery event. */
 #define KVM_INTERNAL_ERROR_DELIVERY_EV	3
+/* Encounter unexpected vm-exit reason */
+#define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON	4
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
@@ -996,6 +998,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
 #define KVM_CAP_ARM_PTRAUTH_GENERIC 172
 #define KVM_CAP_PMU_EVENT_FILTER 173
+#define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From 7d4c85b7035eb2f9ab217ce649dcd1bfaf0cacd3 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Thu, 26 Sep 2019 15:00:18 -0700
Subject: perf llvm: Don't access out-of-scope array

The 'test_dir' variable is assigned to the 'release' array which is
out-of-scope 3 lines later.

Extend the scope of the 'release' array so that an out-of-scope array
isn't accessed.

Bug detected by clang's address sanitizer.

Fixes: 07bc5c699a3d ("perf tools: Make fetch_kernel_version() publicly available")
Cc: stable@vger.kernel.org # v4.4+
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lore.kernel.org/lkml/20190926220018.25402-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/llvm-utils.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 8d04e3d070b1..8b14e4a7f1dc 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -233,14 +233,14 @@ static int detect_kbuild_dir(char **kbuild_dir)
 	const char *prefix_dir = "";
 	const char *suffix_dir = "";
 
+	/* _UTSNAME_LENGTH is 65 */
+	char release[128];
+
 	char *autoconf_path;
 
 	int err;
 
 	if (!test_dir) {
-		/* _UTSNAME_LENGTH is 65 */
-		char release[128];
-
 		err = fetch_kernel_version(NULL, release,
 					   sizeof(release));
 		if (err)
-- 
cgit v1.2.3


From 02d084792273e8a5f1813dcad988229a45be96ea Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 27 Sep 2019 10:11:46 +0200
Subject: perf vendor events s390: Add JSON transaction for machine type 8561

Add s390 transaction counter definition for machine 8561. This is the
same file as for the predecessor machine.

Fixes: 6e67d77d673d ("perf vendor events s390: Add JSON files for machine type 8561")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: http://lore.kernel.org/lkml/20190927081147.18345-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/s390/cf_m8561/transaction.json | 7 +++++++
 1 file changed, 7 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/s390/cf_m8561/transaction.json

diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/transaction.json b/tools/perf/pmu-events/arch/s390/cf_m8561/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_m8561/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
-- 
cgit v1.2.3


From 0d0e5ecec6116db6031829299e74cc71240c9ff3 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 27 Sep 2019 10:11:47 +0200
Subject: perf vendor events s390: Use s390 machine name instead of type 8561

In the pmu-events directory for JSON file definitions use the
official machine name IBM z15 instead of machine type number
8561. This is consistent with previous machines.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Link: http://lore.kernel.org/lkml/20190927081147.18345-2-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../perf/pmu-events/arch/s390/cf_m8561/basic.json  |  58 ----
 .../perf/pmu-events/arch/s390/cf_m8561/crypto.json | 114 -------
 .../pmu-events/arch/s390/cf_m8561/crypto6.json     |  30 --
 .../pmu-events/arch/s390/cf_m8561/extended.json    | 373 ---------------------
 .../pmu-events/arch/s390/cf_m8561/transaction.json |   7 -
 tools/perf/pmu-events/arch/s390/cf_z15/basic.json  |  58 ++++
 tools/perf/pmu-events/arch/s390/cf_z15/crypto.json | 114 +++++++
 .../perf/pmu-events/arch/s390/cf_z15/crypto6.json  |  30 ++
 .../perf/pmu-events/arch/s390/cf_z15/extended.json | 373 +++++++++++++++++++++
 .../pmu-events/arch/s390/cf_z15/transaction.json   |   7 +
 tools/perf/pmu-events/arch/s390/mapfile.csv        |   2 +-
 11 files changed, 583 insertions(+), 583 deletions(-)
 delete mode 100644 tools/perf/pmu-events/arch/s390/cf_m8561/basic.json
 delete mode 100644 tools/perf/pmu-events/arch/s390/cf_m8561/crypto.json
 delete mode 100644 tools/perf/pmu-events/arch/s390/cf_m8561/crypto6.json
 delete mode 100644 tools/perf/pmu-events/arch/s390/cf_m8561/extended.json
 delete mode 100644 tools/perf/pmu-events/arch/s390/cf_m8561/transaction.json
 create mode 100644 tools/perf/pmu-events/arch/s390/cf_z15/basic.json
 create mode 100644 tools/perf/pmu-events/arch/s390/cf_z15/crypto.json
 create mode 100644 tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
 create mode 100644 tools/perf/pmu-events/arch/s390/cf_z15/extended.json
 create mode 100644 tools/perf/pmu-events/arch/s390/cf_z15/transaction.json

diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/basic.json b/tools/perf/pmu-events/arch/s390/cf_m8561/basic.json
deleted file mode 100644
index 17fb5241928b..000000000000
--- a/tools/perf/pmu-events/arch/s390/cf_m8561/basic.json
+++ /dev/null
@@ -1,58 +0,0 @@
-[
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "0",
-		"EventName": "CPU_CYCLES",
-		"BriefDescription": "CPU Cycles",
-		"PublicDescription": "Cycle Count"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "1",
-		"EventName": "INSTRUCTIONS",
-		"BriefDescription": "Instructions",
-		"PublicDescription": "Instruction Count"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "2",
-		"EventName": "L1I_DIR_WRITES",
-		"BriefDescription": "L1I Directory Writes",
-		"PublicDescription": "Level-1 I-Cache Directory Write Count"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "3",
-		"EventName": "L1I_PENALTY_CYCLES",
-		"BriefDescription": "L1I Penalty Cycles",
-		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "4",
-		"EventName": "L1D_DIR_WRITES",
-		"BriefDescription": "L1D Directory Writes",
-		"PublicDescription": "Level-1 D-Cache Directory Write Count"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "5",
-		"EventName": "L1D_PENALTY_CYCLES",
-		"BriefDescription": "L1D Penalty Cycles",
-		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "32",
-		"EventName": "PROBLEM_STATE_CPU_CYCLES",
-		"BriefDescription": "Problem-State CPU Cycles",
-		"PublicDescription": "Problem-State Cycle Count"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "33",
-		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
-		"BriefDescription": "Problem-State Instructions",
-		"PublicDescription": "Problem-State Instruction Count"
-	},
-]
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/crypto.json b/tools/perf/pmu-events/arch/s390/cf_m8561/crypto.json
deleted file mode 100644
index db286f19e7b6..000000000000
--- a/tools/perf/pmu-events/arch/s390/cf_m8561/crypto.json
+++ /dev/null
@@ -1,114 +0,0 @@
-[
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "64",
-		"EventName": "PRNG_FUNCTIONS",
-		"BriefDescription": "PRNG Functions",
-		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "65",
-		"EventName": "PRNG_CYCLES",
-		"BriefDescription": "PRNG Cycles",
-		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "66",
-		"EventName": "PRNG_BLOCKED_FUNCTIONS",
-		"BriefDescription": "PRNG Blocked Functions",
-		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "67",
-		"EventName": "PRNG_BLOCKED_CYCLES",
-		"BriefDescription": "PRNG Blocked Cycles",
-		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "68",
-		"EventName": "SHA_FUNCTIONS",
-		"BriefDescription": "SHA Functions",
-		"PublicDescription": "Total number of SHA functions issued by the CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "69",
-		"EventName": "SHA_CYCLES",
-		"BriefDescription": "SHA Cycles",
-		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "70",
-		"EventName": "SHA_BLOCKED_FUNCTIONS",
-		"BriefDescription": "SHA Blocked Functions",
-		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "71",
-		"EventName": "SHA_BLOCKED_CYCLES",
-		"BriefDescription": "SHA Bloced Cycles",
-		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "72",
-		"EventName": "DEA_FUNCTIONS",
-		"BriefDescription": "DEA Functions",
-		"PublicDescription": "Total number of the DEA functions issued by the CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "73",
-		"EventName": "DEA_CYCLES",
-		"BriefDescription": "DEA Cycles",
-		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "74",
-		"EventName": "DEA_BLOCKED_FUNCTIONS",
-		"BriefDescription": "DEA Blocked Functions",
-		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "75",
-		"EventName": "DEA_BLOCKED_CYCLES",
-		"BriefDescription": "DEA Blocked Cycles",
-		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "76",
-		"EventName": "AES_FUNCTIONS",
-		"BriefDescription": "AES Functions",
-		"PublicDescription": "Total number of AES functions issued by the CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "77",
-		"EventName": "AES_CYCLES",
-		"BriefDescription": "AES Cycles",
-		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "78",
-		"EventName": "AES_BLOCKED_FUNCTIONS",
-		"BriefDescription": "AES Blocked Functions",
-		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "79",
-		"EventName": "AES_BLOCKED_CYCLES",
-		"BriefDescription": "AES Blocked Cycles",
-		"PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
-	},
-]
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/crypto6.json b/tools/perf/pmu-events/arch/s390/cf_m8561/crypto6.json
deleted file mode 100644
index 5e36bc2468d0..000000000000
--- a/tools/perf/pmu-events/arch/s390/cf_m8561/crypto6.json
+++ /dev/null
@@ -1,30 +0,0 @@
-[
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "80",
-		"EventName": "ECC_FUNCTION_COUNT",
-		"BriefDescription": "ECC Function Count",
-		"PublicDescription": "Long ECC function Count"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "81",
-		"EventName": "ECC_CYCLES_COUNT",
-		"BriefDescription": "ECC Cycles Count",
-		"PublicDescription": "Long ECC Function cycles count"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "82",
-		"EventName": "ECC_BLOCKED_FUNCTION_COUNT",
-		"BriefDescription": "Ecc Blocked Function Count",
-		"PublicDescription": "Long ECC blocked function count"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "83",
-		"EventName": "ECC_BLOCKED_CYCLES_COUNT",
-		"BriefDescription": "ECC Blocked Cycles Count",
-		"PublicDescription": "Long ECC blocked cycles count"
-	},
-]
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/extended.json b/tools/perf/pmu-events/arch/s390/cf_m8561/extended.json
deleted file mode 100644
index 89e070727e1b..000000000000
--- a/tools/perf/pmu-events/arch/s390/cf_m8561/extended.json
+++ /dev/null
@@ -1,373 +0,0 @@
-[
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "128",
-		"EventName": "L1D_RO_EXCL_WRITES",
-		"BriefDescription": "L1D Read-only Exclusive Writes",
-		"PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "129",
-		"EventName": "DTLB2_WRITES",
-		"BriefDescription": "DTLB2 Writes",
-		"PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "130",
-		"EventName": "DTLB2_MISSES",
-		"BriefDescription": "DTLB2 Misses",
-		"PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "131",
-		"EventName": "DTLB2_HPAGE_WRITES",
-		"BriefDescription": "DTLB2 One-Megabyte Page Writes",
-		"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "132",
-		"EventName": "DTLB2_GPAGE_WRITES",
-		"BriefDescription": "DTLB2 Two-Gigabyte Page Writes",
-		"PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "133",
-		"EventName": "L1D_L2D_SOURCED_WRITES",
-		"BriefDescription": "L1D L2D Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "134",
-		"EventName": "ITLB2_WRITES",
-		"BriefDescription": "ITLB2 Writes",
-		"PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "135",
-		"EventName": "ITLB2_MISSES",
-		"BriefDescription": "ITLB2 Misses",
-		"PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "136",
-		"EventName": "L1I_L2I_SOURCED_WRITES",
-		"BriefDescription": "L1I L2I Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "137",
-		"EventName": "TLB2_PTE_WRITES",
-		"BriefDescription": "TLB2 PTE Writes",
-		"PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "138",
-		"EventName": "TLB2_CRSTE_WRITES",
-		"BriefDescription": "TLB2 CRSTE Writes",
-		"PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "139",
-		"EventName": "TLB2_ENGINES_BUSY",
-		"BriefDescription": "TLB2 Engines Busy",
-		"PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "140",
-		"EventName": "TX_C_TEND",
-		"BriefDescription": "Completed TEND instructions in constrained TX mode",
-		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "141",
-		"EventName": "TX_NC_TEND",
-		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
-		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "143",
-		"EventName": "L1C_TLB2_MISSES",
-		"BriefDescription": "L1C TLB2 Misses",
-		"PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "144",
-		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
-		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "145",
-		"EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES",
-		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "146",
-		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
-		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "147",
-		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES",
-		"BriefDescription": "L1D On-Cluster L3 Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "148",
-		"EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES",
-		"BriefDescription": "L1D On-Cluster Memory Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "149",
-		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV",
-		"BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "150",
-		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES",
-		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "151",
-		"EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES",
-		"BriefDescription": "L1D Off-Cluster Memory Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "152",
-		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV",
-		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "153",
-		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES",
-		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "154",
-		"EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES",
-		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "155",
-		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV",
-		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "156",
-		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
-		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "157",
-		"EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES",
-		"BriefDescription": "L1D Off-Drawer L4 Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "158",
-		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO",
-		"BriefDescription": "L1D On-Chip L3 Sourced Writes read-only",
-		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "162",
-		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
-		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "163",
-		"EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES",
-		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "164",
-		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
-		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "165",
-		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES",
-		"BriefDescription": "L1I On-Cluster L3 Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "166",
-		"EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES",
-		"BriefDescription": "L1I On-Cluster Memory Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "167",
-		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV",
-		"BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "168",
-		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES",
-		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "169",
-		"EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES",
-		"BriefDescription": "L1I Off-Cluster Memory Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "170",
-		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV",
-		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "171",
-		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES",
-		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "172",
-		"EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES",
-		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "173",
-		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV",
-		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "174",
-		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
-		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "175",
-		"EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES",
-		"BriefDescription": "L1I Off-Drawer L4 Sourced Writes",
-		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "224",
-		"EventName": "BCD_DFP_EXECUTION_SLOTS",
-		"BriefDescription": "BCD DFP Execution Slots",
-		"PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "225",
-		"EventName": "VX_BCD_EXECUTION_SLOTS",
-		"BriefDescription": "VX BCD Execution Slots",
-		"PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "226",
-		"EventName": "DECIMAL_INSTRUCTIONS",
-		"BriefDescription": "Decimal Instructions",
-		"PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "232",
-		"EventName": "LAST_HOST_TRANSLATIONS",
-		"BriefDescription": "Last host translation done",
-		"PublicDescription": "Last Host Translation done"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "243",
-		"EventName": "TX_NC_TABORT",
-		"BriefDescription": "Aborted transactions in non-constrained TX mode",
-		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "244",
-		"EventName": "TX_C_TABORT_NO_SPECIAL",
-		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
-		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "245",
-		"EventName": "TX_C_TABORT_SPECIAL",
-		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
-		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "448",
-		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
-		"BriefDescription": "Cycle count with one thread active",
-		"PublicDescription": "Cycle count with one thread active"
-	},
-	{
-		"Unit": "CPU-M-CF",
-		"EventCode": "449",
-		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
-		"BriefDescription": "Cycle count with two threads active",
-		"PublicDescription": "Cycle count with two threads active"
-	},
-]
diff --git a/tools/perf/pmu-events/arch/s390/cf_m8561/transaction.json b/tools/perf/pmu-events/arch/s390/cf_m8561/transaction.json
deleted file mode 100644
index 1a0034f79f73..000000000000
--- a/tools/perf/pmu-events/arch/s390/cf_m8561/transaction.json
+++ /dev/null
@@ -1,7 +0,0 @@
-[
-  {
-    "BriefDescription": "Transaction count",
-    "MetricName": "transaction",
-    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
-  }
-]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/basic.json b/tools/perf/pmu-events/arch/s390/cf_z15/basic.json
new file mode 100644
index 000000000000..17fb5241928b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/basic.json
@@ -0,0 +1,58 @@
+[
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "0",
+		"EventName": "CPU_CYCLES",
+		"BriefDescription": "CPU Cycles",
+		"PublicDescription": "Cycle Count"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "1",
+		"EventName": "INSTRUCTIONS",
+		"BriefDescription": "Instructions",
+		"PublicDescription": "Instruction Count"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "2",
+		"EventName": "L1I_DIR_WRITES",
+		"BriefDescription": "L1I Directory Writes",
+		"PublicDescription": "Level-1 I-Cache Directory Write Count"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "3",
+		"EventName": "L1I_PENALTY_CYCLES",
+		"BriefDescription": "L1I Penalty Cycles",
+		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "4",
+		"EventName": "L1D_DIR_WRITES",
+		"BriefDescription": "L1D Directory Writes",
+		"PublicDescription": "Level-1 D-Cache Directory Write Count"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "5",
+		"EventName": "L1D_PENALTY_CYCLES",
+		"BriefDescription": "L1D Penalty Cycles",
+		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "32",
+		"EventName": "PROBLEM_STATE_CPU_CYCLES",
+		"BriefDescription": "Problem-State CPU Cycles",
+		"PublicDescription": "Problem-State Cycle Count"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "33",
+		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
+		"BriefDescription": "Problem-State Instructions",
+		"PublicDescription": "Problem-State Instruction Count"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json
new file mode 100644
index 000000000000..db286f19e7b6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/crypto.json
@@ -0,0 +1,114 @@
+[
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "64",
+		"EventName": "PRNG_FUNCTIONS",
+		"BriefDescription": "PRNG Functions",
+		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "65",
+		"EventName": "PRNG_CYCLES",
+		"BriefDescription": "PRNG Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "66",
+		"EventName": "PRNG_BLOCKED_FUNCTIONS",
+		"BriefDescription": "PRNG Blocked Functions",
+		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "67",
+		"EventName": "PRNG_BLOCKED_CYCLES",
+		"BriefDescription": "PRNG Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "68",
+		"EventName": "SHA_FUNCTIONS",
+		"BriefDescription": "SHA Functions",
+		"PublicDescription": "Total number of SHA functions issued by the CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "69",
+		"EventName": "SHA_CYCLES",
+		"BriefDescription": "SHA Cycles",
+		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "70",
+		"EventName": "SHA_BLOCKED_FUNCTIONS",
+		"BriefDescription": "SHA Blocked Functions",
+		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "71",
+		"EventName": "SHA_BLOCKED_CYCLES",
+		"BriefDescription": "SHA Bloced Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "72",
+		"EventName": "DEA_FUNCTIONS",
+		"BriefDescription": "DEA Functions",
+		"PublicDescription": "Total number of the DEA functions issued by the CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "73",
+		"EventName": "DEA_CYCLES",
+		"BriefDescription": "DEA Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "74",
+		"EventName": "DEA_BLOCKED_FUNCTIONS",
+		"BriefDescription": "DEA Blocked Functions",
+		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "75",
+		"EventName": "DEA_BLOCKED_CYCLES",
+		"BriefDescription": "DEA Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "76",
+		"EventName": "AES_FUNCTIONS",
+		"BriefDescription": "AES Functions",
+		"PublicDescription": "Total number of AES functions issued by the CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "77",
+		"EventName": "AES_CYCLES",
+		"BriefDescription": "AES Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "78",
+		"EventName": "AES_BLOCKED_FUNCTIONS",
+		"BriefDescription": "AES Blocked Functions",
+		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "79",
+		"EventName": "AES_BLOCKED_CYCLES",
+		"BriefDescription": "AES Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
new file mode 100644
index 000000000000..5e36bc2468d0
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/crypto6.json
@@ -0,0 +1,30 @@
+[
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "80",
+		"EventName": "ECC_FUNCTION_COUNT",
+		"BriefDescription": "ECC Function Count",
+		"PublicDescription": "Long ECC function Count"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "81",
+		"EventName": "ECC_CYCLES_COUNT",
+		"BriefDescription": "ECC Cycles Count",
+		"PublicDescription": "Long ECC Function cycles count"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "82",
+		"EventName": "ECC_BLOCKED_FUNCTION_COUNT",
+		"BriefDescription": "Ecc Blocked Function Count",
+		"PublicDescription": "Long ECC blocked function count"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "83",
+		"EventName": "ECC_BLOCKED_CYCLES_COUNT",
+		"BriefDescription": "ECC Blocked Cycles Count",
+		"PublicDescription": "Long ECC blocked cycles count"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/extended.json b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
new file mode 100644
index 000000000000..89e070727e1b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/extended.json
@@ -0,0 +1,373 @@
+[
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "128",
+		"EventName": "L1D_RO_EXCL_WRITES",
+		"BriefDescription": "L1D Read-only Exclusive Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "129",
+		"EventName": "DTLB2_WRITES",
+		"BriefDescription": "DTLB2 Writes",
+		"PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "130",
+		"EventName": "DTLB2_MISSES",
+		"BriefDescription": "DTLB2 Misses",
+		"PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "131",
+		"EventName": "DTLB2_HPAGE_WRITES",
+		"BriefDescription": "DTLB2 One-Megabyte Page Writes",
+		"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "132",
+		"EventName": "DTLB2_GPAGE_WRITES",
+		"BriefDescription": "DTLB2 Two-Gigabyte Page Writes",
+		"PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "133",
+		"EventName": "L1D_L2D_SOURCED_WRITES",
+		"BriefDescription": "L1D L2D Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "134",
+		"EventName": "ITLB2_WRITES",
+		"BriefDescription": "ITLB2 Writes",
+		"PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "135",
+		"EventName": "ITLB2_MISSES",
+		"BriefDescription": "ITLB2 Misses",
+		"PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "136",
+		"EventName": "L1I_L2I_SOURCED_WRITES",
+		"BriefDescription": "L1I L2I Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "137",
+		"EventName": "TLB2_PTE_WRITES",
+		"BriefDescription": "TLB2 PTE Writes",
+		"PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "138",
+		"EventName": "TLB2_CRSTE_WRITES",
+		"BriefDescription": "TLB2 CRSTE Writes",
+		"PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "139",
+		"EventName": "TLB2_ENGINES_BUSY",
+		"BriefDescription": "TLB2 Engines Busy",
+		"PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "140",
+		"EventName": "TX_C_TEND",
+		"BriefDescription": "Completed TEND instructions in constrained TX mode",
+		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "141",
+		"EventName": "TX_NC_TEND",
+		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
+		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "143",
+		"EventName": "L1C_TLB2_MISSES",
+		"BriefDescription": "L1C TLB2 Misses",
+		"PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "144",
+		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "145",
+		"EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "146",
+		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "147",
+		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Cluster L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "148",
+		"EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Cluster Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "149",
+		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "150",
+		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "151",
+		"EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Cluster Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "152",
+		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "153",
+		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "154",
+		"EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "155",
+		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "156",
+		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "157",
+		"EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Drawer L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "158",
+		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO",
+		"BriefDescription": "L1D On-Chip L3 Sourced Writes read-only",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "162",
+		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "163",
+		"EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "164",
+		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "165",
+		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Cluster L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "166",
+		"EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Cluster Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "167",
+		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "168",
+		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "169",
+		"EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Cluster Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "170",
+		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "171",
+		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "172",
+		"EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "173",
+		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "174",
+		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "175",
+		"EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Drawer L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "224",
+		"EventName": "BCD_DFP_EXECUTION_SLOTS",
+		"BriefDescription": "BCD DFP Execution Slots",
+		"PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "225",
+		"EventName": "VX_BCD_EXECUTION_SLOTS",
+		"BriefDescription": "VX BCD Execution Slots",
+		"PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "226",
+		"EventName": "DECIMAL_INSTRUCTIONS",
+		"BriefDescription": "Decimal Instructions",
+		"PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "232",
+		"EventName": "LAST_HOST_TRANSLATIONS",
+		"BriefDescription": "Last host translation done",
+		"PublicDescription": "Last Host Translation done"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "243",
+		"EventName": "TX_NC_TABORT",
+		"BriefDescription": "Aborted transactions in non-constrained TX mode",
+		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "244",
+		"EventName": "TX_C_TABORT_NO_SPECIAL",
+		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
+		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "245",
+		"EventName": "TX_C_TABORT_SPECIAL",
+		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
+		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "448",
+		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
+		"BriefDescription": "Cycle count with one thread active",
+		"PublicDescription": "Cycle count with one thread active"
+	},
+	{
+		"Unit": "CPU-M-CF",
+		"EventCode": "449",
+		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
+		"BriefDescription": "Cycle count with two threads active",
+		"PublicDescription": "Cycle count with two threads active"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z15/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv
index bd3fc577139c..61641a3480e0 100644
--- a/tools/perf/pmu-events/arch/s390/mapfile.csv
+++ b/tools/perf/pmu-events/arch/s390/mapfile.csv
@@ -4,4 +4,4 @@ Family-model,Version,Filename,EventType
 ^IBM.282[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_zec12,core
 ^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core
 ^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core
-^IBM.856[12].*3\.6.[[:xdigit:]]+$,3,cf_m8561,core
+^IBM.856[12].*3\.6.[[:xdigit:]]+$,3,cf_z15,core
-- 
cgit v1.2.3


From ee212d6ea20887c0ef352be8563ca13dbf965906 Mon Sep 17 00:00:00 2001
From: Steve MacLean <Steve.MacLean@microsoft.com>
Date: Sat, 28 Sep 2019 01:39:00 +0000
Subject: perf map: Fix overlapped map handling

Whenever an mmap/mmap2 event occurs, the map tree must be updated to add a new
entry. If a new map overlaps a previous map, the overlapped section of the
previous map is effectively unmapped, but the non-overlapping sections are
still valid.

maps__fixup_overlappings() is responsible for creating any new map entries from
the previously overlapped map. It optionally creates a before and an after map.

When creating the after map the existing code failed to adjust the map.pgoff.
This meant the new after map would incorrectly calculate the file offset
for the ip. This results in incorrect symbol name resolution for any ip in the
after region.

Make maps__fixup_overlappings() correctly populate map.pgoff.

Add an assert that new mapping matches old mapping at the beginning of
the after map.

Committer-testing:

Validated correct parsing of libcoreclr.so symbols from .NET Core 3.0 preview9
(which didn't strip symbols).

Preparation:

  ~/dotnet3.0-preview9/dotnet new webapi -o perfSymbol
  cd perfSymbol
  ~/dotnet3.0-preview9/dotnet publish
  perf record ~/dotnet3.0-preview9/dotnet \
      bin/Debug/netcoreapp3.0/publish/perfSymbol.dll
  ^C

Before:

  perf script --show-mmap-events 2>&1 | grep -e MMAP -e unknown |\
     grep libcoreclr.so | head -n 4
        dotnet  1907 373352.698780: PERF_RECORD_MMAP2 1907/1907: \
            [0x7fe615726000(0x768000) @ 0 08:02 5510620 765057155]: \
            r-xp .../3.0.0-preview9-19423-09/libcoreclr.so
        dotnet  1907 373352.701091: PERF_RECORD_MMAP2 1907/1907: \
            [0x7fe615974000(0x1000) @ 0x24e000 08:02 5510620 765057155]: \
            rwxp .../3.0.0-preview9-19423-09/libcoreclr.so
        dotnet  1907 373352.701241: PERF_RECORD_MMAP2 1907/1907: \
            [0x7fe615c42000(0x1000) @ 0x51c000 08:02 5510620 765057155]: \
            rwxp .../3.0.0-preview9-19423-09/libcoreclr.so
        dotnet  1907 373352.705249:     250000 cpu-clock: \
             7fe6159a1f99 [unknown] \
             (.../3.0.0-preview9-19423-09/libcoreclr.so)

After:

  perf script --show-mmap-events 2>&1 | grep -e MMAP -e unknown |\
     grep libcoreclr.so | head -n 4
        dotnet  1907 373352.698780: PERF_RECORD_MMAP2 1907/1907: \
            [0x7fe615726000(0x768000) @ 0 08:02 5510620 765057155]: \
            r-xp .../3.0.0-preview9-19423-09/libcoreclr.so
        dotnet  1907 373352.701091: PERF_RECORD_MMAP2 1907/1907: \
            [0x7fe615974000(0x1000) @ 0x24e000 08:02 5510620 765057155]: \
            rwxp .../3.0.0-preview9-19423-09/libcoreclr.so
        dotnet  1907 373352.701241: PERF_RECORD_MMAP2 1907/1907: \
            [0x7fe615c42000(0x1000) @ 0x51c000 08:02 5510620 765057155]: \
            rwxp .../3.0.0-preview9-19423-09/libcoreclr.so

All the [unknown] symbols were resolved.

Signed-off-by: Steve MacLean <Steve.MacLean@Microsoft.com>
Tested-by: Brian Robbins <brianrob@microsoft.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Eric Saint-Etienne <eric.saint.etienne@oracle.com>
Cc: John Keeping <john@metanate.com>
Cc: John Salem <josalem@microsoft.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom McDonald <thomas.mcdonald@microsoft.com>
Link: http://lore.kernel.org/lkml/BN8PR21MB136270949F22A6A02335C238F7800@BN8PR21MB1362.namprd21.prod.outlook.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/map.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 5b83ed1ebbd6..eec9b282c047 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "symbol.h"
+#include <assert.h>
 #include <errno.h>
 #include <inttypes.h>
 #include <limits.h>
@@ -850,6 +851,8 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			}
 
 			after->start = map->end;
+			after->pgoff += map->end - pos->start;
+			assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end));
 			__map_groups__insert(pos->groups, after);
 			if (verbose >= 2 && !use_browser)
 				map__fprintf(after, fp);
-- 
cgit v1.2.3


From b59711e9b0d22fd47abfa00602fd8c365cdd3ab7 Mon Sep 17 00:00:00 2001
From: Steve MacLean <Steve.MacLean@microsoft.com>
Date: Sat, 28 Sep 2019 01:41:18 +0000
Subject: perf inject jit: Fix JIT_CODE_MOVE filename

During perf inject --jit, JIT_CODE_MOVE records were injecting MMAP records
with an incorrect filename. Specifically it was missing the ".so" suffix.

Further the JIT_CODE_LOAD record were silently truncating the
jr->load.code_index field to 32 bits before generating the filename.

Make both records emit the same filename based on the full 64 bit
code_index field.

Fixes: 9b07e27f88b9 ("perf inject: Add jitdump mmap injection support")
Cc: stable@vger.kernel.org # v4.6+
Signed-off-by: Steve MacLean <Steve.MacLean@Microsoft.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Brian Robbins <brianrob@microsoft.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Eric Saint-Etienne <eric.saint.etienne@oracle.com>
Cc: John Keeping <john@metanate.com>
Cc: John Salem <josalem@microsoft.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom McDonald <thomas.mcdonald@microsoft.com>
Link: http://lore.kernel.org/lkml/BN8PR21MB1362FF8F127B31DBF4121528F7800@BN8PR21MB1362.namprd21.prod.outlook.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/jitdump.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index 1bdf4c6ea3e5..e3ccb0ce1938 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -395,7 +395,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 	size_t size;
 	u16 idr_size;
 	const char *sym;
-	uint32_t count;
+	uint64_t count;
 	int ret, csize, usize;
 	pid_t pid, tid;
 	struct {
@@ -418,7 +418,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 		return -1;
 
 	filename = event->mmap2.filename;
-	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so",
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
 			jd->dir,
 			pid,
 			count);
@@ -529,7 +529,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 		return -1;
 
 	filename = event->mmap2.filename;
-	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64,
+	size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%" PRIu64 ".so",
 	         jd->dir,
 	         pid,
 		 jr->move.code_index);
-- 
cgit v1.2.3


From 2657983b4c0d81632c6a73bae469951b0d341251 Mon Sep 17 00:00:00 2001
From: Steve MacLean <Steve.MacLean@microsoft.com>
Date: Sat, 28 Sep 2019 01:53:08 +0000
Subject: perf docs: Correct and clarify jitdump spec

Specification claims latest version of jitdump file format is 2. Current
jit dump reading code treats 1 as the latest version.

Correct spec to match code.

The original language made it unclear the value to be written in the
magic field.

Revise language that the writer always writes the same value. Specify
that the reader uses the value to detect endian mismatches.

Signed-off-by: Steve MacLean <Steve.MacLean@Microsoft.com>
Acked-by: Stephane Eranian <eranian@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Brian Robbins <brianrob@microsoft.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Eric Saint-Etienne <eric.saint.etienne@oracle.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: John Keeping <john@metanate.com>
Cc: John Salem <josalem@microsoft.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Tom McDonald <thomas.mcdonald@microsoft.com>
Link: http://lore.kernel.org/lkml/BN8PR21MB1362F63CDE7AC69736FC7F9EF7800@BN8PR21MB1362.namprd21.prod.outlook.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/jitdump-specification.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/Documentation/jitdump-specification.txt b/tools/perf/Documentation/jitdump-specification.txt
index 4c62b0713651..52152d156ad9 100644
--- a/tools/perf/Documentation/jitdump-specification.txt
+++ b/tools/perf/Documentation/jitdump-specification.txt
@@ -36,8 +36,8 @@ III/ Jitdump file header format
 Each jitdump file starts with a fixed size header containing the following fields in order:
 
 
-* uint32_t magic     : a magic number tagging the file type. The value is 4-byte long and represents the string "JiTD" in ASCII form. It is 0x4A695444 or 0x4454694a depending on the endianness. The field can be used to detect the endianness of the file
-* uint32_t version   : a 4-byte value representing the format version. It is currently set to 2
+* uint32_t magic     : a magic number tagging the file type. The value is 4-byte long and represents the string "JiTD" in ASCII form. It written is as 0x4A695444. The reader will detect an endian mismatch when it reads 0x4454694a.
+* uint32_t version   : a 4-byte value representing the format version. It is currently set to 1
 * uint32_t total_size: size in bytes of file header
 * uint32_t elf_mach  : ELF architecture encoding (ELF e_machine value as specified in /usr/include/elf.h)
 * uint32_t pad1      : padding. Reserved for future use
-- 
cgit v1.2.3


From e98df280bc2a499fd41d7f9e2d6733884de69902 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Fri, 27 Sep 2019 16:35:44 -0700
Subject: perf script brstackinsn: Fix recovery from LBR/binary mismatch

When the LBR data and the instructions in a binary do not match the loop
printing instructions could get confused and print a long stream of
bogus <bad> instructions.

The problem was that if the instruction decoder cannot decode an
instruction it ilen wasn't initialized, so the loop going through the
basic block would continue with the previous value.

Harden the code to avoid such problems:

- Make sure ilen is always freshly initialized and is 0 for bad
  instructions.

- Do not overrun the code buffer while printing instructions

- Print a warning message if the final jump is not on an instruction
  boundary.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20190927233546.11533-1-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-script.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 286fc70d7402..67be8d31afab 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1063,7 +1063,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 			continue;
 
 		insn = 0;
-		for (off = 0;; off += ilen) {
+		for (off = 0; off < (unsigned)len; off += ilen) {
 			uint64_t ip = start + off;
 
 			printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
@@ -1074,6 +1074,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 					printed += print_srccode(thread, x.cpumode, ip);
 				break;
 			} else {
+				ilen = 0;
 				printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip,
 						   dump_insn(&x, ip, buffer + off, len - off, &ilen));
 				if (ilen == 0)
@@ -1083,6 +1084,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 				insn++;
 			}
 		}
+		if (off != (unsigned)len)
+			printed += fprintf(fp, "\tmismatch of LBR data and executable\n");
 	}
 
 	/*
@@ -1123,6 +1126,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 		goto out;
 	}
 	for (off = 0; off <= end - start; off += ilen) {
+		ilen = 0;
 		printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", start + off,
 				   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
 		if (ilen == 0)
-- 
cgit v1.2.3


From 6bdfd9f118bd59cf0f85d3bf4b72b586adea17c1 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Fri, 27 Sep 2019 16:35:45 -0700
Subject: perf jevents: Fix period for Intel fixed counters

The Intel fixed counters use a special table to override the JSON
information.

During this override the period information from the JSON file got
dropped, which results in inst_retired.any and similar running with
frequency mode instead of a period.

Just specify the expected period in the table.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20190927233546.11533-2-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/jevents.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 9e37287da924..e2837260ca4d 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -450,12 +450,12 @@ static struct fixed {
 	const char *name;
 	const char *event;
 } fixed[] = {
-	{ "inst_retired.any", "event=0xc0" },
-	{ "inst_retired.any_p", "event=0xc0" },
-	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" },
-	{ "cpu_clk_unhalted.thread", "event=0x3c" },
-	{ "cpu_clk_unhalted.core", "event=0x3c" },
-	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" },
+	{ "inst_retired.any", "event=0xc0,period=2000003" },
+	{ "inst_retired.any_p", "event=0xc0,period=2000003" },
+	{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03,period=2000003" },
+	{ "cpu_clk_unhalted.thread", "event=0x3c,period=2000003" },
+	{ "cpu_clk_unhalted.core", "event=0x3c,period=2000003" },
+	{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1,period=2000003" },
 	{ NULL, NULL},
 };
 
-- 
cgit v1.2.3


From f67001a4a08eb124197ed4376941e1da9cf94b42 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 30 Sep 2019 10:55:34 -0300
Subject: perf tools: Propagate get_cpuid() error

For consistency, propagate the exact cause for get_cpuid() to have
failed.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-9ig269f7ktnhh99g4l15vpu2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/powerpc/util/header.c | 3 ++-
 tools/perf/arch/s390/util/header.c    | 9 +++++----
 tools/perf/arch/x86/util/header.c     | 3 ++-
 tools/perf/builtin-kvm.c              | 7 ++++---
 4 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index b6b7bc7e31a1..3b4cdfc5efd6 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
+#include <errno.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -30,7 +31,7 @@ get_cpuid(char *buffer, size_t sz)
 		buffer[nb-1] = '\0';
 		return 0;
 	}
-	return -1;
+	return ENOBUFS;
 }
 
 char *
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
index 8b0b018d896a..7933f6871c81 100644
--- a/tools/perf/arch/s390/util/header.c
+++ b/tools/perf/arch/s390/util/header.c
@@ -8,6 +8,7 @@
  */
 
 #include <sys/types.h>
+#include <errno.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <string.h>
@@ -54,7 +55,7 @@ int get_cpuid(char *buffer, size_t sz)
 
 	sysinfo = fopen(SYSINFO, "r");
 	if (sysinfo == NULL)
-		return -1;
+		return errno;
 
 	while ((read = getline(&line, &line_sz, sysinfo)) != -1) {
 		if (!strncmp(line, SYSINFO_MANU, strlen(SYSINFO_MANU))) {
@@ -89,7 +90,7 @@ int get_cpuid(char *buffer, size_t sz)
 
 	/* Missing manufacturer, type or model information should not happen */
 	if (!manufacturer[0] || !type[0] || !model[0])
-		return -1;
+		return EINVAL;
 
 	/*
 	 * Scan /proc/service_levels and return the CPU-MF counter facility
@@ -133,14 +134,14 @@ skip_sysinfo:
 	else
 		nbytes = snprintf(buffer, sz, "%s,%s,%s", manufacturer, type,
 				  model);
-	return (nbytes >= sz) ? -1 : 0;
+	return (nbytes >= sz) ? ENOBUFS : 0;
 }
 
 char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 {
 	char *buf = malloc(128);
 
-	if (buf && get_cpuid(buf, 128) < 0)
+	if (buf && get_cpuid(buf, 128))
 		zfree(&buf);
 	return buf;
 }
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index 662ecf84a421..aa6deb463bf3 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <sys/types.h>
+#include <errno.h>
 #include <unistd.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -58,7 +59,7 @@ __get_cpuid(char *buffer, size_t sz, const char *fmt)
 		buffer[nb-1] = '\0';
 		return 0;
 	}
-	return -1;
+	return ENOBUFS;
 }
 
 int
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 2227e2f42c09..58a9e0989491 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -705,14 +705,15 @@ static int process_sample_event(struct perf_tool *tool,
 
 static int cpu_isa_config(struct perf_kvm_stat *kvm)
 {
-	char buf[64], *cpuid;
+	char buf[128], *cpuid;
 	int err;
 
 	if (kvm->live) {
 		err = get_cpuid(buf, sizeof(buf));
 		if (err != 0) {
-			pr_err("Failed to look up CPU type\n");
-			return err;
+			pr_err("Failed to look up CPU type: %s\n",
+			       str_error_r(err, buf, sizeof(buf)));
+			return -err;
 		}
 		cpuid = buf;
 	} else
-- 
cgit v1.2.3


From 9db0e3635fb35b6695275774ab909c51221b66ad Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 30 Sep 2019 11:48:32 -0300
Subject: perf evsel: Fall back to global 'perf_env' in perf_evsel__env()

I.e. if evsel->evlist or evsel->evlist->env isn't set, return the
environment for the running machine, as that would be set if reading
from a perf.data file.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-uqq4grmhbi12rwb0lfpo6lfu@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c  | 3 ++-
 tools/perf/util/python.c | 6 ++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5591af81a070..abc7fda4a0fe 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -30,6 +30,7 @@
 #include "counts.h"
 #include "event.h"
 #include "evsel.h"
+#include "util/env.h"
 #include "util/evsel_config.h"
 #include "util/evsel_fprintf.h"
 #include "evlist.h"
@@ -2512,7 +2513,7 @@ struct perf_env *perf_evsel__env(struct evsel *evsel)
 {
 	if (evsel && evsel->evlist)
 		return evsel->evlist->env;
-	return NULL;
+	return &perf_env;
 }
 
 static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist)
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 53f31053a27a..02460362256d 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -14,6 +14,7 @@
 #include "thread_map.h"
 #include "trace-event.h"
 #include "mmap.h"
+#include "util/env.h"
 #include <internal/lib.h>
 #include "../perf-sys.h"
 
@@ -53,6 +54,11 @@ int parse_callchain_record(const char *arg __maybe_unused,
 	return 0;
 }
 
+/*
+ * Add this one here not to drag util/env.c
+ */
+struct perf_env perf_env;
+
 /*
  * Support debug printing even though util/debug.c is not linked.  That means
  * implementing 'verbose' and 'eprintf'.
-- 
cgit v1.2.3


From a66fa0619a0ae3585ef09e9c33ecfb5c7c6cb72b Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 30 Sep 2019 15:06:01 -0300
Subject: perf annotate: Propagate perf_env__arch() error

The callers of symbol__annotate2() use symbol__strerror_disassemble() to
convert its failure returns into a human readable string, so
propagate error values from functions it calls, starting with
perf_env__arch() that when fails the right thing to do is to look at
'errno' to see why its possible call to uname() failed.

Reported-by: Russell King - ARM Linux admin <linux@armlinux.org.uk>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/n/tip-it5d83kyusfhb1q1b0l4pxzs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e830eadfca2a..9b7b9176e713 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2071,7 +2071,7 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 	int err;
 
 	if (!arch_name)
-		return -1;
+		return errno;
 
 	args.arch = arch = arch__find(arch_name);
 	if (arch == NULL)
-- 
cgit v1.2.3


From 28f4417c3333940b242af03d90214f713bbef232 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 30 Sep 2019 15:11:47 -0300
Subject: perf annotate: Fix the signedness of failure returns

Callers of symbol__annotate() expect a errno value or some other
extended error value range in symbol__strerror_disassemble() to
convert to a proper error string, fix it when propagating a failure to
find the arch specific annotation routines via arch__find(arch_name).

Reported-by: Russell King - ARM Linux admin <linux@armlinux.org.uk>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/n/tip-o0k6dw7cas0vvmjjvgsyvu1i@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 9b7b9176e713..95109acf4808 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2075,7 +2075,7 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 
 	args.arch = arch = arch__find(arch_name);
 	if (arch == NULL)
-		return -ENOTSUP;
+		return ENOTSUP;
 
 	if (parch)
 		*parch = arch;
-- 
cgit v1.2.3


From 211f493b611eef012841f795166c38ec7528738d Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 30 Sep 2019 15:44:13 -0300
Subject: perf annotate: Propagate the symbol__annotate() error return

We were just returning -1 in symbol__annotate() when symbol__annotate()
failed, propagate its error as it is used later to pass to
symbol__strerror_disassemble() to present a error message to the user,
that in some cases were getting:

  "Invalid -1 error code"

Fix it to propagate the error.

Reported-by: Russell King - ARM Linux admin <linux@armlinux.org.uk>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/n/tip-0tj89rs9g7nbcyd5skadlvuu@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 95109acf4808..1de1a7091c48 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2997,7 +2997,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct evsel *evsel,
 
 out_free_offsets:
 	zfree(&notes->offsets);
-	return -1;
+	return err;
 }
 
 #define ANNOTATION__CFG(n) \
-- 
cgit v1.2.3


From 42d7a9107d83223a5fcecc6732d626a6c074cbc2 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 30 Sep 2019 15:48:12 -0300
Subject: perf annotate: Fix arch specific ->init() failure errors

They are called from symbol__annotate() and to propagate errors that can
help understand the problem make them return what
symbol__strerror_disassemble() known, i.e. errno codes and other
annotation specific errors in a special, out of errnos, range.

Reported-by: Russell King - ARM Linux admin <linux@armlinux.org.uk>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/n/tip-pqx7srcv7tixgid251aeboj6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm/annotate/instructions.c   | 4 ++--
 tools/perf/arch/arm64/annotate/instructions.c | 4 ++--
 tools/perf/arch/s390/annotate/instructions.c  | 6 ++++--
 tools/perf/arch/x86/annotate/instructions.c   | 6 ++++--
 tools/perf/util/annotate.c                    | 6 ++++++
 tools/perf/util/annotate.h                    | 2 ++
 6 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/tools/perf/arch/arm/annotate/instructions.c b/tools/perf/arch/arm/annotate/instructions.c
index e1d4b484cc4b..2ff6cedeb9c5 100644
--- a/tools/perf/arch/arm/annotate/instructions.c
+++ b/tools/perf/arch/arm/annotate/instructions.c
@@ -37,7 +37,7 @@ static int arm__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 
 	arm = zalloc(sizeof(*arm));
 	if (!arm)
-		return -1;
+		return ENOMEM;
 
 #define ARM_CONDS "(cc|cs|eq|ge|gt|hi|le|ls|lt|mi|ne|pl|vc|vs)"
 	err = regcomp(&arm->call_insn, "^blx?" ARM_CONDS "?$", REG_EXTENDED);
@@ -59,5 +59,5 @@ out_free_call:
 	regfree(&arm->call_insn);
 out_free_arm:
 	free(arm);
-	return -1;
+	return SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP;
 }
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index 43aa93ed8414..037e292ecd8e 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -95,7 +95,7 @@ static int arm64__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 
 	arm = zalloc(sizeof(*arm));
 	if (!arm)
-		return -1;
+		return ENOMEM;
 
 	/* bl, blr */
 	err = regcomp(&arm->call_insn, "^blr?$", REG_EXTENDED);
@@ -118,5 +118,5 @@ out_free_call:
 	regfree(&arm->call_insn);
 out_free_arm:
 	free(arm);
-	return -1;
+	return SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP;
 }
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index 89bb8f2c54ce..a50e70baf918 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -164,8 +164,10 @@ static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 	if (!arch->initialized) {
 		arch->initialized = true;
 		arch->associate_instruction_ops = s390__associate_ins_ops;
-		if (cpuid)
-			err = s390__cpuid_parse(arch, cpuid);
+		if (cpuid) {
+			if (s390__cpuid_parse(arch, cpuid))
+				err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING;
+		}
 	}
 
 	return err;
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 44f5aba78210..7eb5621c021d 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -196,8 +196,10 @@ static int x86__annotate_init(struct arch *arch, char *cpuid)
 	if (arch->initialized)
 		return 0;
 
-	if (cpuid)
-		err = x86__cpuid_parse(arch, cpuid);
+	if (cpuid) {
+		if (x86__cpuid_parse(arch, cpuid))
+			err = SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING;
+	}
 
 	arch->initialized = true;
 	return err;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 1de1a7091c48..dc15352924f9 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1631,6 +1631,12 @@ int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map *
 	case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
 		scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");
 		break;
+	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP:
+		scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions.");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING:
+		scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization.");
+		break;
 	default:
 		scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
 		break;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index d94be9140e31..116e21f49da6 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -370,6 +370,8 @@ enum symbol_disassemble_errno {
 
 	SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX	= __SYMBOL_ANNOTATE_ERRNO__START,
 	SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF,
+	SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING,
+	SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP,
 
 	__SYMBOL_ANNOTATE_ERRNO__END,
 };
-- 
cgit v1.2.3


From 16ed3c1e91159e28b02f11f71ff4ce4cbc6f99e4 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 30 Sep 2019 15:53:33 -0300
Subject: perf annotate: Return appropriate error code for allocation failures

We should return errno or the annotation extra range understood by
symbol__strerror_disassemble() instead of -1, fix it, returning ENOMEM
instead.

Reported-by: Russell King - ARM Linux admin <linux@armlinux.org.uk>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/n/tip-8of1cmj3rz0mppfcshc9bbqq@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index dc15352924f9..b49ecdd51188 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1668,7 +1668,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 
 	build_id_path = strdup(filename);
 	if (!build_id_path)
-		return -1;
+		return ENOMEM;
 
 	/*
 	 * old style build-id cache has name of XX/XXXXXXX.. while
@@ -2977,7 +2977,7 @@ int symbol__annotate2(struct symbol *sym, struct map *map, struct evsel *evsel,
 
 	notes->offsets = zalloc(size * sizeof(struct annotation_line *));
 	if (notes->offsets == NULL)
-		return -1;
+		return ENOMEM;
 
 	if (perf_evsel__is_group_event(evsel))
 		nr_pcnt = evsel->core.nr_members;
-- 
cgit v1.2.3


From 11aad897f6d1a28eae3b7e5b293647c522d65819 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Mon, 30 Sep 2019 16:04:21 -0300
Subject: perf annotate: Don't return -1 for error when doing BPF disassembly

Return errno when open_memstream() fails and add two new speciall error
codes for when an invalid, non BPF file or one without BTF is passed to
symbol__disassemble_bpf(), so that its callers can rely on
symbol__strerror_disassemble() to convert that to a human readable error
message that can help figure out what is wrong, with hints even.

Cc: Russell King - ARM Linux admin <linux@armlinux.org.uk>
Cc: Song Liu <songliubraving@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>,
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/n/tip-usevw9r2gcipfcrbpaueurw0@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/annotate.c | 19 +++++++++++++++----
 tools/perf/util/annotate.h |  2 ++
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index b49ecdd51188..4036c7f7b0fb 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1637,6 +1637,13 @@ int symbol__strerror_disassemble(struct symbol *sym __maybe_unused, struct map *
 	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING:
 		scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization.");
 		break;
+	case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE:
+		scnprintf(buf, buflen, "Invalid BPF file: %s.", dso->long_name);
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF:
+		scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.",
+			  dso->long_name);
+		break;
 	default:
 		scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
 		break;
@@ -1719,13 +1726,13 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	char tpath[PATH_MAX];
 	size_t buf_size;
 	int nr_skip = 0;
-	int ret = -1;
 	char *buf;
 	bfd *bfdf;
+	int ret;
 	FILE *s;
 
 	if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
-		return -1;
+		return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE;
 
 	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
 		  sym->name, sym->start, sym->end - sym->start);
@@ -1738,8 +1745,10 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	assert(bfd_check_format(bfdf, bfd_object));
 
 	s = open_memstream(&buf, &buf_size);
-	if (!s)
+	if (!s) {
+		ret = errno;
 		goto out;
+	}
 	init_disassemble_info(&info, s,
 			      (fprintf_ftype) fprintf);
 
@@ -1748,8 +1757,10 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 
 	info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
 						 dso->bpf_prog.id);
-	if (!info_node)
+	if (!info_node) {
+		return SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
 		goto out;
+	}
 	info_linear = info_node->info_linear;
 	sub_id = dso->bpf_prog.sub_id;
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 116e21f49da6..d76fd0e81f46 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -372,6 +372,8 @@ enum symbol_disassemble_errno {
 	SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF,
 	SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING,
 	SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP,
+	SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE,
+	SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF,
 
 	__SYMBOL_ANNOTATE_ERRNO__END,
 };
-- 
cgit v1.2.3


From 61129dd29f7962f278b618a2a3e8fdb986a66dc8 Mon Sep 17 00:00:00 2001
From: Seth Forshee <seth.forshee@canonical.com>
Date: Tue, 17 Sep 2019 09:18:53 +0200
Subject: sched: Add __ASSEMBLY__ guards around struct clone_args

The addition of struct clone_args to uapi/linux/sched.h is not protected
by __ASSEMBLY__ guards, causing a failure to build from source for glibc
on RISC-V. Add the guards to fix this.

Fixes: 7f192e3cd316 ("fork: add clone3")
Signed-off-by: Seth Forshee <seth.forshee@canonical.com>
Cc: <stable@vger.kernel.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20190917071853.12385-1-seth.forshee@canonical.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/uapi/linux/sched.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index b3105ac1381a..851ff1feadd5 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -33,6 +33,7 @@
 #define CLONE_NEWNET		0x40000000	/* New network namespace */
 #define CLONE_IO		0x80000000	/* Clone io context */
 
+#ifndef __ASSEMBLY__
 /*
  * Arguments for the clone3 syscall
  */
@@ -46,6 +47,7 @@ struct clone_args {
 	__aligned_u64 stack_size;
 	__aligned_u64 tls;
 };
+#endif
 
 /*
  * Scheduling policies
-- 
cgit v1.2.3


From 3969e76909d3aa06715997896184ee684f68d164 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Tue, 24 Sep 2019 13:52:37 -0600
Subject: selftests: pidfd: Fix undefined reference to pthread_create()

Fix build failure:

undefined reference to `pthread_create'
collect2: error: ld returned 1 exit status

Fix CFLAGS to include pthread correctly.

Fixes: 740378dc7834 ("pidfd: add polling selftests")
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20190924195237.30519-1-skhan@linuxfoundation.org
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 tools/testing/selftests/pidfd/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile
index 464c9b76148f..7550f08822a3 100644
--- a/tools/testing/selftests/pidfd/Makefile
+++ b/tools/testing/selftests/pidfd/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-CFLAGS += -g -I../../../../usr/include/ -lpthread
+CFLAGS += -g -I../../../../usr/include/ -pthread
 
 TEST_GEN_PROGS := pidfd_test pidfd_open_test pidfd_poll_test pidfd_wait
 
-- 
cgit v1.2.3


From 517d6b9c6f71bee15c729155445c42cc4ef77dda Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 18 Sep 2019 08:30:33 +0000
Subject: erofs: fix return value check in erofs_read_superblock()

In case of error, the function read_mapping_page() returns
ERR_PTR() not NULL. The NULL test in the return value check
should be replaced with IS_ERR().

Fixes: fe7c2423570d ("erofs: use read_mapping_page instead of sb_bread")
Reviewed-by: Gao Xiang <gaoxiang25@huawei.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Link: https://lore.kernel.org/r/20190918083033.47780-1-weiyongjun1@huawei.com
Signed-off-by: Gao Xiang <gaoxiang25@huawei.com>
---
 fs/erofs/super.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index caf9a95173b0..0e369494f2f2 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -105,9 +105,9 @@ static int erofs_read_superblock(struct super_block *sb)
 	int ret;
 
 	page = read_mapping_page(sb->s_bdev->bd_inode->i_mapping, 0, NULL);
-	if (!page) {
+	if (IS_ERR(page)) {
 		erofs_err(sb, "cannot read erofs superblock");
-		return -EIO;
+		return PTR_ERR(page);
 	}
 
 	sbi = EROFS_SB(sb);
-- 
cgit v1.2.3


From 6927cc05c2b067d4ca8ab6aeaa3b4544bea26ef8 Mon Sep 17 00:00:00 2001
From: Gao Xiang <gaoxiang25@huawei.com>
Date: Thu, 19 Sep 2019 14:28:38 +0800
Subject: MAINTAINERS: erofs: complete sub-entries for erofs

Add a formal git tree and missing files for erofs
after moving out of staging for everyone to blame
in order for better improvement.

Acked-by: Chao Yu <yuchao0@huawei.com>
Link: https://lore.kernel.org/r/20190919062838.106423-1-gaoxiang25@huawei.com
Signed-off-by: Gao Xiang <gaoxiang25@huawei.com>
---
 MAINTAINERS | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 296de2b51c83..30a5b4028d2f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6112,7 +6112,10 @@ M:	Gao Xiang <gaoxiang25@huawei.com>
 M:	Chao Yu <yuchao0@huawei.com>
 L:	linux-erofs@lists.ozlabs.org
 S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git
+F:	Documentation/filesystems/erofs.txt
 F:	fs/erofs/
+F:	include/trace/events/erofs.h
 
 ERRSEQ ERROR TRACKING INFRASTRUCTURE
 M:	Jeff Layton <jlayton@kernel.org>
-- 
cgit v1.2.3


From 55252ab72b774119afedfdc6d1f142ffa2a9b818 Mon Sep 17 00:00:00 2001
From: Gao Xiang <gaoxiang25@huawei.com>
Date: Sun, 22 Sep 2019 02:43:55 +0800
Subject: erofs: fix erofs_get_meta_page locking due to a cleanup

After doing more drop_caches stress test on
our products, I found the mistake introduced by
a very recent cleanup [1].

The current rule is that "erofs_get_meta_page"
should be returned with page locked (although
it's mostly unnecessary for read-only fs after
pages are PG_uptodate), but a fix should be
done for this.

[1] https://lore.kernel.org/r/20190904020912.63925-26-gaoxiang25@huawei.com
Fixes: 618f40ea026b ("erofs: use read_cache_page_gfp for erofs_get_meta_page")
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Link: https://lore.kernel.org/r/20190921184355.149928-1-gaoxiang25@huawei.com
Signed-off-by: Gao Xiang <gaoxiang25@huawei.com>
---
 fs/erofs/data.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 8a9fcbd0e8ac..fc3a8d8064f8 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -34,11 +34,15 @@ static void erofs_readendio(struct bio *bio)
 
 struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr)
 {
-	struct inode *const bd_inode = sb->s_bdev->bd_inode;
-	struct address_space *const mapping = bd_inode->i_mapping;
+	struct address_space *const mapping = sb->s_bdev->bd_inode->i_mapping;
+	struct page *page;
 
-	return read_cache_page_gfp(mapping, blkaddr,
+	page = read_cache_page_gfp(mapping, blkaddr,
 				   mapping_gfp_constraint(mapping, ~__GFP_FS));
+	/* should already be PageUptodate */
+	if (!IS_ERR(page))
+		lock_page(page);
+	return page;
 }
 
 static int erofs_map_blocks_flatmode(struct inode *inode,
-- 
cgit v1.2.3


From dc76ea8c1087b5c44235566ed4be2202d21a8504 Mon Sep 17 00:00:00 2001
From: Gao Xiang <gaoxiang25@huawei.com>
Date: Sun, 22 Sep 2019 18:04:34 +0800
Subject: erofs: fix mis-inplace determination related with noio chain

Fix a recent cleanup patch. noio (bypass) chain is
handled asynchronously against submit chain, therefore
inplace I/O or pagevec cannot be applied to such pages.
Add detailed comment for this as well.

Fixes: 97e86a858bc3 ("staging: erofs: tidy up decompression frontend")
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Link: https://lore.kernel.org/r/20190922100434.229340-1-gaoxiang25@huawei.com
Signed-off-by: Gao Xiang <gaoxiang25@huawei.com>
---
 fs/erofs/zdata.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 96e34c90f814..fad80c97d247 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -575,7 +575,7 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe,
 	struct erofs_map_blocks *const map = &fe->map;
 	struct z_erofs_collector *const clt = &fe->clt;
 	const loff_t offset = page_offset(page);
-	bool tight = (clt->mode >= COLLECT_PRIMARY_HOOKED);
+	bool tight = true;
 
 	enum z_erofs_cache_alloctype cache_strategy;
 	enum z_erofs_page_type page_type;
@@ -628,8 +628,16 @@ restart_now:
 	preload_compressed_pages(clt, MNGD_MAPPING(sbi),
 				 cache_strategy, pagepool);
 
-	tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED);
 hitted:
+	/*
+	 * Ensure the current partial page belongs to this submit chain rather
+	 * than other concurrent submit chains or the noio(bypass) chain since
+	 * those chains are handled asynchronously thus the page cannot be used
+	 * for inplace I/O or pagevec (should be processed in strict order.)
+	 */
+	tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED &&
+		  clt->mode != COLLECT_PRIMARY_FOLLOWED_NOINPLACE);
+
 	cur = end - min_t(unsigned int, offset + end - map->m_la, end);
 	if (!(map->m_flags & EROFS_MAP_MAPPED)) {
 		zero_user_segment(page, cur, end);
-- 
cgit v1.2.3


From 2b6509f42dc6c96ef0b625888d4aa56d2e140330 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Fri, 27 Sep 2019 18:27:42 +0800
Subject: MIPS: Loongson64: Fix boot failure after dropping boot_mem_map

From commit a94e4f24ec83 ("MIPS: init: Drop boot_mem_map") onwards,
add_memory_region() is handled by memblock_add()/memblock_reserve()
directly and all bootmem API should be converted to memblock API.
Otherwise it will lead to boot failure, especially in the NUMA case
because add_memory_region lose the node_id information.

Fixes: a94e4f24ec836c8984f83959 ("MIPS: init: Drop boot_mem_map")
Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
[paul.burton@mips.com:
  - Invert node_id check to de-indent the switch statement & avoid lines
    over 80 characters.
  - Fixup commit reference in commit message.]
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Cc: linux-mips@vger.kernel.org
Cc: Fuxin Zhang <zhangfx@lemote.com>
Cc: Zhangjin Wu <wuzhangjin@gmail.com>
Cc: Huacai Chen <chenhuacai@gmail.com>
---
 arch/mips/loongson64/common/mem.c      | 35 +++++++++++++++++-----------------
 arch/mips/loongson64/loongson-3/numa.c | 11 +----------
 2 files changed, 18 insertions(+), 28 deletions(-)

diff --git a/arch/mips/loongson64/common/mem.c b/arch/mips/loongson64/common/mem.c
index 4abb92e0fc39..4254ac4ec616 100644
--- a/arch/mips/loongson64/common/mem.c
+++ b/arch/mips/loongson64/common/mem.c
@@ -3,6 +3,7 @@
  */
 #include <linux/fs.h>
 #include <linux/fcntl.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 
 #include <asm/bootinfo.h>
@@ -64,24 +65,22 @@ void __init prom_init_memory(void)
 		node_id = loongson_memmap->map[i].node_id;
 		mem_type = loongson_memmap->map[i].mem_type;
 
-		if (node_id == 0) {
-			switch (mem_type) {
-			case SYSTEM_RAM_LOW:
-				add_memory_region(loongson_memmap->map[i].mem_start,
-					(u64)loongson_memmap->map[i].mem_size << 20,
-					BOOT_MEM_RAM);
-				break;
-			case SYSTEM_RAM_HIGH:
-				add_memory_region(loongson_memmap->map[i].mem_start,
-					(u64)loongson_memmap->map[i].mem_size << 20,
-					BOOT_MEM_RAM);
-				break;
-			case SYSTEM_RAM_RESERVED:
-				add_memory_region(loongson_memmap->map[i].mem_start,
-					(u64)loongson_memmap->map[i].mem_size << 20,
-					BOOT_MEM_RESERVED);
-				break;
-			}
+		if (node_id != 0)
+			continue;
+
+		switch (mem_type) {
+		case SYSTEM_RAM_LOW:
+			memblock_add(loongson_memmap->map[i].mem_start,
+				(u64)loongson_memmap->map[i].mem_size << 20);
+			break;
+		case SYSTEM_RAM_HIGH:
+			memblock_add(loongson_memmap->map[i].mem_start,
+				(u64)loongson_memmap->map[i].mem_size << 20);
+			break;
+		case SYSTEM_RAM_RESERVED:
+			memblock_reserve(loongson_memmap->map[i].mem_start,
+				(u64)loongson_memmap->map[i].mem_size << 20);
+			break;
 		}
 	}
 }
diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c
index 414e97de5dc0..8f20d2cb3767 100644
--- a/arch/mips/loongson64/loongson-3/numa.c
+++ b/arch/mips/loongson64/loongson-3/numa.c
@@ -142,8 +142,6 @@ static void __init szmem(unsigned int node)
 				(u32)node_id, mem_type, mem_start, mem_size);
 			pr_info("       start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
 				start_pfn, end_pfn, num_physpages);
-			add_memory_region((node_id << 44) + mem_start,
-				(u64)mem_size << 20, BOOT_MEM_RAM);
 			memblock_add_node(PFN_PHYS(start_pfn),
 				PFN_PHYS(end_pfn - start_pfn), node);
 			break;
@@ -156,16 +154,12 @@ static void __init szmem(unsigned int node)
 				(u32)node_id, mem_type, mem_start, mem_size);
 			pr_info("       start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
 				start_pfn, end_pfn, num_physpages);
-			add_memory_region((node_id << 44) + mem_start,
-				(u64)mem_size << 20, BOOT_MEM_RAM);
 			memblock_add_node(PFN_PHYS(start_pfn),
 				PFN_PHYS(end_pfn - start_pfn), node);
 			break;
 		case SYSTEM_RAM_RESERVED:
 			pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
 				(u32)node_id, mem_type, mem_start, mem_size);
-			add_memory_region((node_id << 44) + mem_start,
-				(u64)mem_size << 20, BOOT_MEM_RESERVED);
 			memblock_reserve(((node_id << 44) + mem_start),
 				mem_size << 20);
 			break;
@@ -191,8 +185,6 @@ static void __init node_mem_init(unsigned int node)
 	NODE_DATA(node)->node_start_pfn = start_pfn;
 	NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn;
 
-	free_bootmem_with_active_regions(node, end_pfn);
-
 	if (node == 0) {
 		/* kernel end address */
 		unsigned long kernel_end_pfn = PFN_UP(__pa_symbol(&_end));
@@ -209,8 +201,6 @@ static void __init node_mem_init(unsigned int node)
 			memblock_reserve((node_addrspace_offset | 0xfe000000),
 					 32 << 20);
 	}
-
-	sparse_memory_present_with_active_regions(node);
 }
 
 static __init void prom_meminit(void)
@@ -227,6 +217,7 @@ static __init void prom_meminit(void)
 			cpumask_clear(&__node_data[(node)]->cpumask);
 		}
 	}
+	memblocks_present();
 	max_low_pfn = PHYS_PFN(memblock_end_of_DRAM());
 
 	for (cpu = 0; cpu < loongson_sysconf.nr_cpus; cpu++) {
-- 
cgit v1.2.3


From 1bd63524593b964934a33afd442df16b8f90e2b5 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Mon, 30 Sep 2019 14:02:03 -0700
Subject: libbpf: handle symbol versioning properly for libbpf.a

bcc uses libbpf repo as a submodule. It brings in libbpf source
code and builds everything together to produce shared libraries.
With latest libbpf, I got the following errors:
  /bin/ld: libbcc_bpf.so.0.10.0: version node not found for symbol xsk_umem__create@LIBBPF_0.0.2
  /bin/ld: failed to set dynamic section sizes: Bad value
  collect2: error: ld returned 1 exit status
  make[2]: *** [src/cc/libbcc_bpf.so.0.10.0] Error 1

In xsk.c, we have
  asm(".symver xsk_umem__create_v0_0_2, xsk_umem__create@LIBBPF_0.0.2");
  asm(".symver xsk_umem__create_v0_0_4, xsk_umem__create@@LIBBPF_0.0.4");
The linker thinks the built is for LIBBPF but cannot find proper version
LIBBPF_0.0.2/4, so emit errors.

I also confirmed that using libbpf.a to produce a shared library also
has issues:
  -bash-4.4$ cat t.c
  extern void *xsk_umem__create;
  void * test() { return xsk_umem__create; }
  -bash-4.4$ gcc -c -fPIC t.c
  -bash-4.4$ gcc -shared t.o libbpf.a -o t.so
  /bin/ld: t.so: version node not found for symbol xsk_umem__create@LIBBPF_0.0.2
  /bin/ld: failed to set dynamic section sizes: Bad value
  collect2: error: ld returned 1 exit status
  -bash-4.4$

Symbol versioning does happens in commonly used libraries, e.g., elfutils
and glibc. For static libraries, for a versioned symbol, the old definitions
will be ignored, and the symbol will be an alias to the latest definition.
For example, glibc sched_setaffinity is versioned.
  -bash-4.4$ readelf -s /usr/lib64/libc.so.6 | grep sched_setaffinity
     756: 000000000013d3d0    13 FUNC    GLOBAL DEFAULT   13 sched_setaffinity@GLIBC_2.3.3
     757: 00000000000e2e70   455 FUNC    GLOBAL DEFAULT   13 sched_setaffinity@@GLIBC_2.3.4
    1800: 0000000000000000     0 FILE    LOCAL  DEFAULT  ABS sched_setaffinity.c
    4228: 00000000000e2e70   455 FUNC    LOCAL  DEFAULT   13 __sched_setaffinity_new
    4648: 000000000013d3d0    13 FUNC    LOCAL  DEFAULT   13 __sched_setaffinity_old
    7338: 000000000013d3d0    13 FUNC    GLOBAL DEFAULT   13 sched_setaffinity@GLIBC_2
    7380: 00000000000e2e70   455 FUNC    GLOBAL DEFAULT   13 sched_setaffinity@@GLIBC_
  -bash-4.4$
For static library, the definition of sched_setaffinity aliases to the new definition.
  -bash-4.4$ readelf -s /usr/lib64/libc.a | grep sched_setaffinity
  File: /usr/lib64/libc.a(sched_setaffinity.o)
     8: 0000000000000000   455 FUNC    GLOBAL DEFAULT    1 __sched_setaffinity_new
    12: 0000000000000000   455 FUNC    WEAK   DEFAULT    1 sched_setaffinity

For both elfutils and glibc, additional macros are used to control different handling
of symbol versioning w.r.t static and shared libraries.
For elfutils, the macro is SYMBOL_VERSIONING
(https://sourceware.org/git/?p=elfutils.git;a=blob;f=lib/eu-config.h).
For glibc, the macro is SHARED
(https://sourceware.org/git/?p=glibc.git;a=blob;f=include/shlib-compat.h;hb=refs/heads/master)

This patch used SHARED as the macro name. After this patch, the libbpf.a has
  -bash-4.4$ readelf -s libbpf.a | grep xsk_umem__create
     372: 0000000000017145  1190 FUNC    GLOBAL DEFAULT    1 xsk_umem__create_v0_0_4
     405: 0000000000017145  1190 FUNC    GLOBAL DEFAULT    1 xsk_umem__create
     499: 00000000000175eb   103 FUNC    GLOBAL DEFAULT    1 xsk_umem__create_v0_0_2
  -bash-4.4$
No versioned symbols for xsk_umem__create.
The libbpf.a can be used to build a shared library succesfully.
  -bash-4.4$ cat t.c
  extern void *xsk_umem__create;
  void * test() { return xsk_umem__create; }
  -bash-4.4$ gcc -c -fPIC t.c
  -bash-4.4$ gcc -shared t.o libbpf.a -o t.so
  -bash-4.4$

Fixes: 10d30e301732 ("libbpf: add flags to umem config")
Cc: Kevin Laatz <kevin.laatz@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andrii Nakryiko <andriin@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Makefile          | 27 ++++++++++++++++++---------
 tools/lib/bpf/libbpf_internal.h | 16 ++++++++++++++++
 tools/lib/bpf/xsk.c             |  4 ++--
 3 files changed, 36 insertions(+), 11 deletions(-)

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 20772663d3e1..56ce6292071b 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -114,6 +114,9 @@ override CFLAGS += $(INCLUDES)
 override CFLAGS += -fvisibility=hidden
 override CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 
+# flags specific for shared library
+SHLIB_FLAGS := -DSHARED
+
 ifeq ($(VERBOSE),1)
   Q =
 else
@@ -130,14 +133,17 @@ all:
 export srctree OUTPUT CC LD CFLAGS V
 include $(srctree)/tools/build/Makefile.include
 
-BPF_IN		:= $(OUTPUT)libbpf-in.o
+SHARED_OBJDIR	:= $(OUTPUT)sharedobjs/
+STATIC_OBJDIR	:= $(OUTPUT)staticobjs/
+BPF_IN_SHARED	:= $(SHARED_OBJDIR)libbpf-in.o
+BPF_IN_STATIC	:= $(STATIC_OBJDIR)libbpf-in.o
 VERSION_SCRIPT	:= libbpf.map
 
 LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
 LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
 PC_FILE		:= $(addprefix $(OUTPUT),$(PC_FILE))
 
-GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \
+GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \
 			   cut -d "@" -f1 | sed 's/_v[0-9]_[0-9]_[0-9].*//' | \
 			   awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$8}' | \
 			   sort -u | wc -l)
@@ -159,7 +165,7 @@ all: fixdep
 
 all_cmd: $(CMD_TARGETS) check
 
-$(BPF_IN): force elfdep bpfdep
+$(BPF_IN_SHARED): force elfdep bpfdep
 	@(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
 	(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true
@@ -175,17 +181,20 @@ $(BPF_IN): force elfdep bpfdep
 	@(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \
 	(diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
-	$(Q)$(MAKE) $(build)=libbpf
+	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)"
+
+$(BPF_IN_STATIC): force elfdep bpfdep
+	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
 
 $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
 
-$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN)
+$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED)
 	$(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(LIBBPF_MAJOR_VERSION) \
 				    -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
 	@ln -sf $(@F) $(OUTPUT)libbpf.so
 	@ln -sf $(@F) $(OUTPUT)libbpf.so.$(LIBBPF_MAJOR_VERSION)
 
-$(OUTPUT)libbpf.a: $(BPF_IN)
+$(OUTPUT)libbpf.a: $(BPF_IN_STATIC)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
 
 $(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a
@@ -201,7 +210,7 @@ check: check_abi
 
 check_abi: $(OUTPUT)libbpf.so
 	@if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then	 \
-		echo "Warning: Num of global symbols in $(BPF_IN)"	 \
+		echo "Warning: Num of global symbols in $(BPF_IN_SHARED)"	 \
 		     "($(GLOBAL_SYM_COUNT)) does NOT match with num of"	 \
 		     "versioned symbols in $^ ($(VERSIONED_SYM_COUNT))." \
 		     "Please make sure all LIBBPF_API symbols are"	 \
@@ -259,9 +268,9 @@ config-clean:
 	$(Q)$(MAKE) -C $(srctree)/tools/build/feature/ clean >/dev/null
 
 clean:
-	$(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \
+	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(TARGETS) $(CXX_TEST_TARGET) \
 		*.o *~ *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) .*.d .*.cmd \
-		*.pc LIBBPF-CFLAGS
+		*.pc LIBBPF-CFLAGS $(SHARED_OBJDIR) $(STATIC_OBJDIR)
 	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
 
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 2e83a34f8c79..98216a69c32f 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -34,6 +34,22 @@
 	(offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD))
 #endif
 
+/* Symbol versioning is different between static and shared library.
+ * Properly versioned symbols are needed for shared library, but
+ * only the symbol of the new version is needed for static library.
+ */
+#ifdef SHARED
+# define COMPAT_VERSION(internal_name, api_name, version) \
+	asm(".symver " #internal_name "," #api_name "@" #version);
+# define DEFAULT_VERSION(internal_name, api_name, version) \
+	asm(".symver " #internal_name "," #api_name "@@" #version);
+#else
+# define COMPAT_VERSION(internal_name, api_name, version)
+# define DEFAULT_VERSION(internal_name, api_name, version) \
+	extern typeof(internal_name) api_name \
+	__attribute__((alias(#internal_name)));
+#endif
+
 extern void libbpf_print(enum libbpf_print_level level,
 			 const char *format, ...)
 	__attribute__((format(printf, 2, 3)));
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 24fa313524fb..a902838f9fcc 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -261,8 +261,8 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area,
 	return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp,
 					&config);
 }
-asm(".symver xsk_umem__create_v0_0_2, xsk_umem__create@LIBBPF_0.0.2");
-asm(".symver xsk_umem__create_v0_0_4, xsk_umem__create@@LIBBPF_0.0.4");
+COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2)
+DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4)
 
 static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 {
-- 
cgit v1.2.3


From 0889d07f3e4b171c453b2aaf2b257f9074cdf624 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Mon, 30 Sep 2019 11:39:52 +0200
Subject: MIPS: dts: ar9331: fix interrupt-controller size

It is two registers each of 4 byte.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Pengutronix Kernel Team <kernel@pengutronix.de>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: devicetree@vger.kernel.org
Cc: linux-mips@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/boot/dts/qca/ar9331.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/boot/dts/qca/ar9331.dtsi b/arch/mips/boot/dts/qca/ar9331.dtsi
index 63a9f33aa43e..5cfc9d347826 100644
--- a/arch/mips/boot/dts/qca/ar9331.dtsi
+++ b/arch/mips/boot/dts/qca/ar9331.dtsi
@@ -99,7 +99,7 @@
 
 			miscintc: interrupt-controller@18060010 {
 				compatible = "qca,ar7240-misc-intc";
-				reg = <0x18060010 0x4>;
+				reg = <0x18060010 0x8>;
 
 				interrupt-parent = <&cpuintc>;
 				interrupts = <6>;
-- 
cgit v1.2.3


From 8c7138b33e5c690c308b2a7085f6313fdcb3f616 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Fri, 27 Sep 2019 16:00:31 -0700
Subject: net: Unpublish sk from sk_reuseport_cb before call_rcu

The "reuse->sock[]" array is shared by multiple sockets.  The going away
sk must unpublish itself from "reuse->sock[]" before making call_rcu()
call.  However, this unpublish-action is currently done after a grace
period and it may cause use-after-free.

The fix is to move reuseport_detach_sock() to sk_destruct().
Due to the above reason, any socket with sk_reuseport_cb has
to go through the rcu grace period before freeing it.

It is a rather old bug (~3 yrs).  The Fixes tag is not necessary
the right commit but it is the one that introduced the SOCK_RCU_FREE
logic and this fix is depending on it.

Fixes: a4298e4522d6 ("net: add SOCK_RCU_FREE socket flag")
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 07863edbe6fc..e23ec80a67bf 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1700,8 +1700,6 @@ static void __sk_destruct(struct rcu_head *head)
 		sk_filter_uncharge(sk, filter);
 		RCU_INIT_POINTER(sk->sk_filter, NULL);
 	}
-	if (rcu_access_pointer(sk->sk_reuseport_cb))
-		reuseport_detach_sock(sk);
 
 	sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
 
@@ -1728,7 +1726,14 @@ static void __sk_destruct(struct rcu_head *head)
 
 void sk_destruct(struct sock *sk)
 {
-	if (sock_flag(sk, SOCK_RCU_FREE))
+	bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
+
+	if (rcu_access_pointer(sk->sk_reuseport_cb)) {
+		reuseport_detach_sock(sk);
+		use_call_rcu = true;
+	}
+
+	if (use_call_rcu)
 		call_rcu(&sk->sk_rcu, __sk_destruct);
 	else
 		__sk_destruct(&sk->sk_rcu);
-- 
cgit v1.2.3


From 13dc8c029cabf52ba95f60c56eb104d4d95d5889 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Sat, 21 Sep 2019 15:49:54 +0900
Subject: kbuild: remove ar-option and KBUILD_ARFLAGS

Commit 40df759e2b9e ("kbuild: Fix build with binutils <= 2.19")
introduced ar-option and KBUILD_ARFLAGS to deal with old binutils.

According to Documentation/process/changes.rst, the current minimal
supported version of binutils is 2.21 so you can assume the 'D' option
is always supported. Not only GNU ar but also llvm-ar supports it.

With the 'D' option hard-coded, there is no more user of ar-option
or KBUILD_ARFLAGS.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Tested-by: Nick Desaulniers <ndesaulniers@google.com>
---
 Documentation/kbuild/makefiles.rst | 5 -----
 Makefile                           | 4 ----
 arch/powerpc/boot/Makefile         | 2 +-
 scripts/Kbuild.include             | 5 -----
 scripts/Makefile.build             | 2 +-
 scripts/Makefile.lib               | 2 +-
 6 files changed, 3 insertions(+), 17 deletions(-)

diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst
index 6ba9d5365ff3..b89c88168d6a 100644
--- a/Documentation/kbuild/makefiles.rst
+++ b/Documentation/kbuild/makefiles.rst
@@ -954,11 +954,6 @@ When kbuild executes, the following steps are followed (roughly):
 
 	From commandline LDFLAGS_MODULE shall be used (see kbuild.txt).
 
-    KBUILD_ARFLAGS   Options for $(AR) when creating archives
-
-	$(KBUILD_ARFLAGS) set by the top level Makefile to "D" (deterministic
-	mode) if this option is supported by $(AR).
-
     KBUILD_LDS
 
 	The linker script with full path. Assigned by the top-level Makefile.
diff --git a/Makefile b/Makefile
index 6f54f2f95743..7452174f5b21 100644
--- a/Makefile
+++ b/Makefile
@@ -498,7 +498,6 @@ export CFLAGS_KASAN CFLAGS_KASAN_NOSANITIZE CFLAGS_UBSAN
 export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE
 export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE
 export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL
-export KBUILD_ARFLAGS
 
 # Files to ignore in find ... statements
 
@@ -914,9 +913,6 @@ ifdef CONFIG_RETPOLINE
 KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none)
 endif
 
-# use the deterministic mode of AR if available
-KBUILD_ARFLAGS := $(call ar-option,D)
-
 include scripts/Makefile.kasan
 include scripts/Makefile.extrawarn
 include scripts/Makefile.ubsan
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 6841bd52738b..dfbd7f22eef5 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -50,7 +50,7 @@ endif
 
 BOOTAFLAGS	:= -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc
 
-BOOTARFLAGS	:= -cr$(KBUILD_ARFLAGS)
+BOOTARFLAGS	:= -crD
 
 ifdef CONFIG_CC_IS_CLANG
 BOOTCFLAGS += $(CLANG_FLAGS)
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 4b0432e095ae..10ba926ae292 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -143,11 +143,6 @@ cc-ifversion = $(shell [ $(CONFIG_GCC_VERSION)0 $(1) $(2)000 ] && echo $(3) || e
 # Usage: KBUILD_LDFLAGS += $(call ld-option, -X, -Y)
 ld-option = $(call try-run, $(LD) $(KBUILD_LDFLAGS) $(1) -v,$(1),$(2),$(3))
 
-# ar-option
-# Usage: KBUILD_ARFLAGS := $(call ar-option,D)
-# Important: no spaces around options
-ar-option = $(call try-run, $(AR) rc$(1) "$$TMP",$(1),$(2))
-
 # ld-version
 # Note this is mainly for HJ Lu's 3 number binutil versions
 ld-version = $(shell $(LD) --version | $(srctree)/scripts/ld-version.sh)
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index f72aba64d611..a9e47953ca53 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -389,7 +389,7 @@ $(sort $(subdir-obj-y)): $(subdir-ym) ;
 ifdef builtin-target
 
 quiet_cmd_ar_builtin = AR      $@
-      cmd_ar_builtin = rm -f $@; $(AR) rcSTP$(KBUILD_ARFLAGS) $@ $(real-prereqs)
+      cmd_ar_builtin = rm -f $@; $(AR) cDPrST $@ $(real-prereqs)
 
 $(builtin-target): $(real-obj-y) FORCE
 	$(call if_changed,ar_builtin)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 4a0cdd6f5909..179d55af5852 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -232,7 +232,7 @@ quiet_cmd_ld = LD      $@
 # ---------------------------------------------------------------------------
 
 quiet_cmd_ar = AR      $@
-      cmd_ar = rm -f $@; $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(real-prereqs)
+      cmd_ar = rm -f $@; $(AR) cDPrsT $@ $(real-prereqs)
 
 # Objcopy
 # ---------------------------------------------------------------------------
-- 
cgit v1.2.3


From b6f2494d311a19b33b19708543e7ef6dea1de459 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 29 Sep 2019 01:08:17 +0300
Subject: net: dsa: sja1105: Ensure PTP time for rxtstamp reconstruction is not
 in the past

Sometimes the PTP synchronization on the switch 'jumps':

  ptp4l[11241.155]: rms    8 max   16 freq -21732 +/-  11 delay   742 +/-   0
  ptp4l[11243.157]: rms    7 max   17 freq -21731 +/-  10 delay   744 +/-   0
  ptp4l[11245.160]: rms 33592410 max 134217731 freq +192422 +/- 8530253 delay   743 +/-   0
  ptp4l[11247.163]: rms 811631 max 964131 freq +10326 +/- 557785 delay   743 +/-   0
  ptp4l[11249.166]: rms 261936 max 533876 freq -304323 +/- 126371 delay   744 +/-   0
  ptp4l[11251.169]: rms 48700 max 57740 freq -20218 +/- 30532 delay   744 +/-   0
  ptp4l[11253.171]: rms 14570 max 30163 freq  -5568 +/- 7563 delay   742 +/-   0
  ptp4l[11255.174]: rms 2914 max 3440 freq -22001 +/- 1667 delay   744 +/-   1
  ptp4l[11257.177]: rms  811 max 1710 freq -22653 +/- 451 delay   744 +/-   1
  ptp4l[11259.180]: rms  177 max  218 freq -21695 +/-  89 delay   741 +/-   0
  ptp4l[11261.182]: rms   45 max   92 freq -21677 +/-  32 delay   742 +/-   0
  ptp4l[11263.186]: rms   14 max   32 freq -21733 +/-  11 delay   742 +/-   0
  ptp4l[11265.188]: rms    9 max   14 freq -21725 +/-  12 delay   742 +/-   0
  ptp4l[11267.191]: rms    9 max   16 freq -21727 +/-  13 delay   742 +/-   0
  ptp4l[11269.194]: rms    6 max   15 freq -21726 +/-   9 delay   743 +/-   0
  ptp4l[11271.197]: rms    8 max   15 freq -21728 +/-  11 delay   743 +/-   0
  ptp4l[11273.200]: rms    6 max   12 freq -21727 +/-   8 delay   743 +/-   0
  ptp4l[11275.202]: rms    9 max   17 freq -21720 +/-  11 delay   742 +/-   0
  ptp4l[11277.205]: rms    9 max   18 freq -21725 +/-  12 delay   742 +/-   0

Background: the switch only offers partial RX timestamps (24 bits) and
it is up to the driver to read the PTP clock to fill those timestamps up
to 64 bits. But the PTP clock readout needs to happen quickly enough (in
0.135 seconds, in fact), otherwise the PTP clock will wrap around 24
bits, condition which cannot be detected.

Looking at the 'max 134217731' value on output line 3, one can see that
in hex it is 0x8000003. Because the PTP clock resolution is 8 ns,
that means 0x1000000 in ticks, which is exactly 2^24. So indeed this is
a PTP clock wraparound, but the reason might be surprising.

What is going on is that sja1105_tstamp_reconstruct(priv, now, ts)
expects a "now" time that is later than the "ts" was snapshotted at.
This, of course, is obvious: we read the PTP time _after_ the partial RX
timestamp was received. However, the workqueue is processing frames from
a skb queue and reuses the same PTP time, read once at the beginning.
Normally the skb queue only contains one frame and all goes well. But
when the skb queue contains two frames, the second frame that gets
dequeued might have been partially timestamped by the RX MAC _after_ we
had read our PTP time initially.

The code was originally like that due to concerns that SPI access for
PTP time readout is a slow process, and we are time-constrained anyway
(aka: premature optimization). But some timing analysis reveals that the
time spent until the RX timestamp is completely reconstructed is 1 order
of magnitude lower than the 0.135 s deadline even under worst-case
conditions. So we can afford to read the PTP time for each frame in the
RX timestamping queue, which of course ensures that the full PTP time is
in the partial timestamp's future.

Fixes: f3097be21bf1 ("net: dsa: sja1105: Add a state machine for RX timestamping")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index b9def744bcb3..f3d38ff144c4 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2005,12 +2005,12 @@ static void sja1105_rxtstamp_work(struct work_struct *work)
 
 	mutex_lock(&priv->ptp_lock);
 
-	now = priv->tstamp_cc.read(&priv->tstamp_cc);
-
 	while ((skb = skb_dequeue(&data->skb_rxtstamp_queue)) != NULL) {
 		struct skb_shared_hwtstamps *shwt = skb_hwtstamps(skb);
 		u64 ts;
 
+		now = priv->tstamp_cc.read(&priv->tstamp_cc);
+
 		*shwt = (struct skb_shared_hwtstamps) {0};
 
 		ts = SJA1105_SKB_CB(skb)->meta_tstamp;
-- 
cgit v1.2.3


From 7e35b42591c058b91282f95ce3b2cf0c05ffe93d Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Sat, 21 Sep 2019 16:05:41 +0900
Subject: kbuild: remove SUBDIRS support

Linux 5.3 is out. Remove the SUBDIRS support.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Makefile | 20 ++------------------
 1 file changed, 2 insertions(+), 18 deletions(-)

diff --git a/Makefile b/Makefile
index 7452174f5b21..779c9c9b9820 100644
--- a/Makefile
+++ b/Makefile
@@ -206,24 +206,8 @@ ifndef KBUILD_CHECKSRC
   KBUILD_CHECKSRC = 0
 endif
 
-# Use make M=dir to specify directory of external module to build
-# Old syntax make ... SUBDIRS=$PWD is still supported
-# Setting the environment variable KBUILD_EXTMOD take precedence
-ifdef SUBDIRS
-  $(warning ================= WARNING ================)
-  $(warning 'SUBDIRS' will be removed after Linux 5.3)
-  $(warning )
-  $(warning If you are building an individual subdirectory)
-  $(warning in the kernel tree, you can do like this:)
-  $(warning $$ make path/to/dir/you/want/to/build/)
-  $(warning (Do not forget the trailing slash))
-  $(warning )
-  $(warning If you are building an external module,)
-  $(warning Please use 'M=' or 'KBUILD_EXTMOD' instead)
-  $(warning ==========================================)
-  KBUILD_EXTMOD ?= $(SUBDIRS)
-endif
-
+# Use make M=dir or set the environment variable KBUILD_EXTMOD to specify the
+# directory of external module to build. Setting M= takes precedence.
 ifeq ("$(origin M)", "command line")
   KBUILD_EXTMOD := $(M)
 endif
-- 
cgit v1.2.3


From 807f2105b87af20c4a582fb62111b16689f83bb8 Mon Sep 17 00:00:00 2001
From: Alex Gaynor <alex.gaynor@gmail.com>
Date: Sat, 21 Sep 2019 15:23:04 -0700
Subject: kbuild: correct formatting of header in kbuild module docs

Minor formatting fixup.

Fixes: cd238effefa2 ("docs: kbuild: convert docs to ReST and rename to *.rst")
Signed-off-by: Alex Gaynor <alex.gaynor@gmail.com>
Signed-off-by: Matthew Garrett <mjg59@google.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Documentation/kbuild/modules.rst | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/kbuild/modules.rst b/Documentation/kbuild/modules.rst
index d2ae799237fd..33a17121d11d 100644
--- a/Documentation/kbuild/modules.rst
+++ b/Documentation/kbuild/modules.rst
@@ -498,7 +498,8 @@ build.
 	will be written containing all exported symbols that were not
 	defined in the kernel.
 
---- 6.3 Symbols From Another External Module
+6.3 Symbols From Another External Module
+----------------------------------------
 
 	Sometimes, an external module uses exported symbols from
 	another external module. kbuild needs to have full knowledge of
-- 
cgit v1.2.3


From 47346e96f004eca07720e1e2b24fc7f0b0df4092 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Tue, 24 Sep 2019 21:07:40 +0900
Subject: modpost: fix static EXPORT_SYMBOL warnings for UML build

Johannes Berg reports lots of modpost warnings on ARCH=um builds:

WARNING: "rename" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "lseek" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "ftruncate64" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "getuid" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "lseek64" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "unlink" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "pwrite64" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "close" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "opendir" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "pread64" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "syscall" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "readdir" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "readdir64" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "futimes" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "__lxstat" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "write" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "closedir" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "__xstat" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "fsync" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "__lxstat64" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "__fxstat64" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "telldir" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "printf" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "readlink" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "__sprintf_chk" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "link" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "rmdir" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "fdatasync" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "truncate" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "statfs" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "__errno_location" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "__xmknod" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "open64" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "truncate64" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "open" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "read" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "chown" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "chmod" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "utime" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "fchmod" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "seekdir" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "ioctl" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "dup2" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "statfs64" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "utimes" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "mkdir" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "fchown" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "__guard" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "symlink" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "access" [vmlinux] is a static EXPORT_SYMBOL
WARNING: "__stack_smash_handler" [vmlinux] is a static EXPORT_SYMBOL

When you run "make", the modpost is run twice; before linking vmlinux,
and before building modules. All the warnings above are from the second
modpost.

The offending symbols are defined not in vmlinux, but in the C library.
The first modpost is run against the relocatable vmlinux.o, and those
warnings are nicely suppressed because the SH_UNDEF entries from the
symbol table clear the ->is_static flag.

The second modpost is run against the executable vmlinux (+ modules),
where those symbols have been resolved, but the definitions do not
exist.

This commit fixes it in a straightforward way; suppress the static
EXPORT_SYMBOL warnings from "vmlinux".

Without this commit, we see valid warnings twice anyway. For example,
ARCH=arm64 defconfig shows the following warning twice:

WARNING: "HYPERVISOR_platform_op" [vmlinux] is a static EXPORT_SYMBOL_GPL

So, it is reasonable to suppress the second one.

Fixes: 15bfc2348d54 ("modpost: check for static EXPORT_SYMBOL* functions")
Reported-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Tested-by: Johannes Berg <johannes@sipsolutions.net>
Tested-by: Denis Efremov <efremov@linux.com>
---
 scripts/mod/modpost.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 3961941e8e7a..442d5e2ad688 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -2652,15 +2652,20 @@ int main(int argc, char **argv)
 		fatal("modpost: Section mismatches detected.\n"
 		      "Set CONFIG_SECTION_MISMATCH_WARN_ONLY=y to allow them.\n");
 	for (n = 0; n < SYMBOL_HASH_SIZE; n++) {
-		struct symbol *s = symbolhash[n];
+		struct symbol *s;
+
+		for (s = symbolhash[n]; s; s = s->next) {
+			/*
+			 * Do not check "vmlinux". This avoids the same warnings
+			 * shown twice, and false-positives for ARCH=um.
+			 */
+			if (is_vmlinux(s->module->name) && !s->module->is_dot_o)
+				continue;
 
-		while (s) {
 			if (s->is_static)
 				warn("\"%s\" [%s] is a static %s\n",
 				     s->name, s->module->name,
 				     export_str(s->export));
-
-			s = s->next;
 		}
 	}
 
-- 
cgit v1.2.3


From 68501df92d116b760777a2cfda314789f926476f Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Sun, 29 Sep 2019 01:43:39 +0300
Subject: net: dsa: sja1105: Prevent leaking memory

In sja1105_static_config_upload, in two cases memory is leaked: when
static_config_buf_prepare_for_upload fails and when sja1105_inhibit_tx
fails. In both cases config_buf should be released.

Fixes: 8aa9ebccae87 ("net: dsa: Introduce driver for NXP SJA1105 5-port L2 switch")
Fixes: 1a4c69406cc1 ("net: dsa: sja1105: Prevent PHY jabbering during switch reset")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_spi.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c
index 84dc603138cf..58dd37ecde17 100644
--- a/drivers/net/dsa/sja1105/sja1105_spi.c
+++ b/drivers/net/dsa/sja1105/sja1105_spi.c
@@ -409,7 +409,8 @@ int sja1105_static_config_upload(struct sja1105_private *priv)
 	rc = static_config_buf_prepare_for_upload(priv, config_buf, buf_len);
 	if (rc < 0) {
 		dev_err(dev, "Invalid config, cannot upload\n");
-		return -EINVAL;
+		rc = -EINVAL;
+		goto out;
 	}
 	/* Prevent PHY jabbering during switch reset by inhibiting
 	 * Tx on all ports and waiting for current packet to drain.
@@ -418,7 +419,8 @@ int sja1105_static_config_upload(struct sja1105_private *priv)
 	rc = sja1105_inhibit_tx(priv, port_bitmap, true);
 	if (rc < 0) {
 		dev_err(dev, "Failed to inhibit Tx on ports\n");
-		return -ENXIO;
+		rc = -ENXIO;
+		goto out;
 	}
 	/* Wait for an eventual egress packet to finish transmission
 	 * (reach IFG). It is guaranteed that a second one will not
-- 
cgit v1.2.3


From 68ce6688a5baefde30914fc07fc27292dbbe8320 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 29 Sep 2019 02:01:39 +0300
Subject: net: sched: taprio: Fix potential integer overflow in
 taprio_set_picos_per_byte

The speed divisor is used in a context expecting an s64, but it is
evaluated using 32-bit arithmetic.

To avoid that happening, instead of multiplying by 1,000,000 in the
first place, simplify the fraction and do a standard 32 bit division
instead.

Fixes: f04b514c0ce2 ("taprio: Set default link speed to 10 Mbps in taprio_set_picos_per_byte")
Reported-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 2f7b34205c82..2aab46ada94f 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1048,8 +1048,7 @@ static void taprio_set_picos_per_byte(struct net_device *dev,
 		speed = ecmd.base.speed;
 
 skip:
-	picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8,
-				   speed * 1000 * 1000);
+	picos_per_byte = (USEC_PER_SEC * 8) / speed;
 
 	atomic64_set(&q->picos_per_byte, picos_per_byte);
 	netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n",
-- 
cgit v1.2.3


From 21e3d6c81179bbdfa279efc8de456c34b814cfd2 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Tue, 3 Sep 2019 12:18:39 +0200
Subject: scsi: sd: Ignore a failure to sync cache due to lack of authorization

I've got a report about a UAS drive enclosure reporting back Sense: Logical
unit access not authorized if the drive it holds is password protected.
While the drive is obviously unusable in that state as a mass storage
device, it still exists as a sd device and when the system is asked to
perform a suspend of the drive, it will be sent a SYNCHRONIZE CACHE. If
that fails due to password protection, the error must be ignored.

Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20190903101840.16483-1-oneukum@suse.com
Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 91af598f2f53..0f96eb0ddbfa 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1655,7 +1655,8 @@ static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
 		/* we need to evaluate the error return  */
 		if (scsi_sense_valid(sshdr) &&
 			(sshdr->asc == 0x3a ||	/* medium not present */
-			 sshdr->asc == 0x20))	/* invalid command */
+			 sshdr->asc == 0x20 ||	/* invalid command */
+			 (sshdr->asc == 0x74 && sshdr->ascq == 0x71)))	/* drive is password locked */
 				/* this is no error here */
 				return 0;
 
-- 
cgit v1.2.3


From 9bc6157f5fd0e898c94f3018d088a3419bde0d8f Mon Sep 17 00:00:00 2001
From: Daniel Wagner <dwagner@suse.de>
Date: Fri, 27 Sep 2019 09:30:31 +0200
Subject: scsi: qla2xxx: Remove WARN_ON_ONCE in qla2x00_status_cont_entry()

Commit 88263208dd23 ("scsi: qla2xxx: Complain if sp->done() is not called
from the completion path") introduced the WARN_ON_ONCE in
qla2x00_status_cont_entry(). The assumption was that there is only one
status continuations element. According to the firmware documentation it is
possible that multiple status continuations are emitted by the firmware.

Fixes: 88263208dd23 ("scsi: qla2xxx: Complain if sp->done() is not called from the completion path")
Link: https://lore.kernel.org/r/20190927073031.62296-1-dwagner@suse.de
Cc: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_isr.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 4c26630c1c3e..009fd5a33fcd 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -2837,8 +2837,6 @@ qla2x00_status_cont_entry(struct rsp_que *rsp, sts_cont_entry_t *pkt)
 	if (sense_len == 0) {
 		rsp->status_srb = NULL;
 		sp->done(sp, cp->result);
-	} else {
-		WARN_ON_ONCE(true);
 	}
 }
 
-- 
cgit v1.2.3


From ec1db1be106101c24f6f24efbb5eb3176f66cb50 Mon Sep 17 00:00:00 2001
From: Michael Straube <straube.linux@gmail.com>
Date: Tue, 17 Sep 2019 21:07:55 +0200
Subject: staging: exfat: add missing SPDX line to Kconfig

Add SPDX identifier to Kconfig.

Signed-off-by: Michael Straube <straube.linux@gmail.com>
Link: https://lore.kernel.org/r/20190917190755.21723-1-straube.linux@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/exfat/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/staging/exfat/Kconfig b/drivers/staging/exfat/Kconfig
index 290dbfc7ace1..59e07afe249c 100644
--- a/drivers/staging/exfat/Kconfig
+++ b/drivers/staging/exfat/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 config EXFAT_FS
 	tristate "exFAT fs support"
 	depends on BLOCK
-- 
cgit v1.2.3


From a358eea07c78d9d0c246738ed1c6349d72d41920 Mon Sep 17 00:00:00 2001
From: Valdis Klētnieks <valdis.kletnieks@vt.edu>
Date: Wed, 18 Sep 2019 20:38:08 -0400
Subject: staging: exfat - fix SPDX tags..

The copyright notices as I got them said "GPLv2 or later", which I
screwed up when putting in the SPDX tags.  Fix them to match the
license I got the code under.

Signed-off-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>

Link: https://lore.kernel.org/r/122590.1568853488@turing-police
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/exfat/Makefile       | 2 +-
 drivers/staging/exfat/exfat.h        | 2 +-
 drivers/staging/exfat/exfat_blkdev.c | 2 +-
 drivers/staging/exfat/exfat_cache.c  | 2 +-
 drivers/staging/exfat/exfat_core.c   | 2 +-
 drivers/staging/exfat/exfat_nls.c    | 2 +-
 drivers/staging/exfat/exfat_super.c  | 2 +-
 drivers/staging/exfat/exfat_upcase.c | 2 +-
 8 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/staging/exfat/Makefile b/drivers/staging/exfat/Makefile
index 84944dfbae28..6c90aec83feb 100644
--- a/drivers/staging/exfat/Makefile
+++ b/drivers/staging/exfat/Makefile
@@ -1,4 +1,4 @@
-# SPDX-License-Identifier: GPL-2.0
+# SPDX-License-Identifier: GPL-2.0-or-later
 
 obj-$(CONFIG_EXFAT_FS) += exfat.o
 
diff --git a/drivers/staging/exfat/exfat.h b/drivers/staging/exfat/exfat.h
index 6c12f2d79f4d..3abab33e932c 100644
--- a/drivers/staging/exfat/exfat.h
+++ b/drivers/staging/exfat/exfat.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  Copyright (C) 2012-2013 Samsung Electronics Co., Ltd.
  */
diff --git a/drivers/staging/exfat/exfat_blkdev.c b/drivers/staging/exfat/exfat_blkdev.c
index f086c75e7076..81d20e6241c6 100644
--- a/drivers/staging/exfat/exfat_blkdev.c
+++ b/drivers/staging/exfat/exfat_blkdev.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 2012-2013 Samsung Electronics Co., Ltd.
  */
diff --git a/drivers/staging/exfat/exfat_cache.c b/drivers/staging/exfat/exfat_cache.c
index 1565ce65d39f..e1b001718709 100644
--- a/drivers/staging/exfat/exfat_cache.c
+++ b/drivers/staging/exfat/exfat_cache.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 2012-2013 Samsung Electronics Co., Ltd.
  */
diff --git a/drivers/staging/exfat/exfat_core.c b/drivers/staging/exfat/exfat_core.c
index b3e9cf725cf5..79174e5c4145 100644
--- a/drivers/staging/exfat/exfat_core.c
+++ b/drivers/staging/exfat/exfat_core.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 2012-2013 Samsung Electronics Co., Ltd.
  */
diff --git a/drivers/staging/exfat/exfat_nls.c b/drivers/staging/exfat/exfat_nls.c
index 03cb8290b5d2..a5c4b68925fb 100644
--- a/drivers/staging/exfat/exfat_nls.c
+++ b/drivers/staging/exfat/exfat_nls.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 2012-2013 Samsung Electronics Co., Ltd.
  */
diff --git a/drivers/staging/exfat/exfat_super.c b/drivers/staging/exfat/exfat_super.c
index 5f6caee819a6..229ecabe7a93 100644
--- a/drivers/staging/exfat/exfat_super.c
+++ b/drivers/staging/exfat/exfat_super.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 2012-2013 Samsung Electronics Co., Ltd.
  */
diff --git a/drivers/staging/exfat/exfat_upcase.c b/drivers/staging/exfat/exfat_upcase.c
index 366082fb3dab..b91a1faa0e50 100644
--- a/drivers/staging/exfat/exfat_upcase.c
+++ b/drivers/staging/exfat/exfat_upcase.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  Copyright (C) 2012-2013 Samsung Electronics Co., Ltd.
  */
-- 
cgit v1.2.3


From 89d5f78fab48844d750f6f3a419e26f7f828bac8 Mon Sep 17 00:00:00 2001
From: Masanari Iida <standby24x7@gmail.com>
Date: Mon, 30 Sep 2019 22:05:04 +0900
Subject: staging: exfat: Fix a typo in Kconfig

This patch fix a spelling typo in Kconfig.

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Link: https://lore.kernel.org/r/20190930130504.21994-1-standby24x7@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/exfat/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/exfat/Kconfig b/drivers/staging/exfat/Kconfig
index 59e07afe249c..ce32dfe33bec 100644
--- a/drivers/staging/exfat/Kconfig
+++ b/drivers/staging/exfat/Kconfig
@@ -7,7 +7,7 @@ config EXFAT_FS
 	  This adds support for the exFAT file system.
 
 config EXFAT_DONT_MOUNT_VFAT
-	bool "Prohibit mounting of fat/vfat filesysems by exFAT"
+	bool "Prohibit mounting of fat/vfat filesystems by exFAT"
 	depends on EXFAT_FS
 	default y
 	help
-- 
cgit v1.2.3


From 7d4dea95f8281fc7f14766a6040e3504d3f658fc Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 19 Sep 2019 11:50:22 +0200
Subject: staging: octeon: Use "(uintptr_t)" to cast from pointer to int
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On 32-bit:

    In file included from drivers/staging/octeon/octeon-ethernet.h:41,
		     from drivers/staging/octeon/ethernet-tx.c:25:
    drivers/staging/octeon/octeon-stubs.h: In function ‘cvmx_phys_to_ptr’:
    drivers/staging/octeon/octeon-stubs.h:1205:9: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
      return (void *)(physical_address);
	     ^
    drivers/staging/octeon/ethernet-tx.c: In function ‘cvm_oct_xmit’:
    drivers/staging/octeon/ethernet-tx.c:264:37: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
       hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)skb->data);
					 ^
    drivers/staging/octeon/octeon-stubs.h:2:30: note: in definition of macro ‘XKPHYS_TO_PHYS’
     #define XKPHYS_TO_PHYS(p)   (p)
				  ^
    drivers/staging/octeon/ethernet-tx.c:268:37: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
       hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)skb->data);
					 ^
    drivers/staging/octeon/octeon-stubs.h:2:30: note: in definition of macro ‘XKPHYS_TO_PHYS’
     #define XKPHYS_TO_PHYS(p)   (p)
				  ^
    drivers/staging/octeon/ethernet-tx.c:276:20: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
	 XKPHYS_TO_PHYS((u64)skb_frag_address(fs));
			^
    drivers/staging/octeon/octeon-stubs.h:2:30: note: in definition of macro ‘XKPHYS_TO_PHYS’
     #define XKPHYS_TO_PHYS(p)   (p)
				  ^
    drivers/staging/octeon/ethernet-tx.c:280:37: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
       hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)CVM_OCT_SKB_CB(skb));
					 ^
    drivers/staging/octeon/octeon-stubs.h:2:30: note: in definition of macro ‘XKPHYS_TO_PHYS’
     #define XKPHYS_TO_PHYS(p)   (p)
				  ^

Fix this by replacing casts to "u64" by casts to "uintptr_t", which is
either 32-bit or 64-bit, and adding an intermediate cast to "uintptr_t"
where needed.

Exposed by commit 171a9bae68c72f2d ("staging/octeon: Allow test build on
!MIPS").

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Link: https://lore.kernel.org/r/20190919095022.29099-1-geert@linux-m68k.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/octeon/ethernet-tx.c  | 9 +++++----
 drivers/staging/octeon/octeon-stubs.h | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c
index c64728fc21f2..7021ff07ba2a 100644
--- a/drivers/staging/octeon/ethernet-tx.c
+++ b/drivers/staging/octeon/ethernet-tx.c
@@ -261,11 +261,11 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Build the PKO buffer pointer */
 	hw_buffer.u64 = 0;
 	if (skb_shinfo(skb)->nr_frags == 0) {
-		hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)skb->data);
+		hw_buffer.s.addr = XKPHYS_TO_PHYS((uintptr_t)skb->data);
 		hw_buffer.s.pool = 0;
 		hw_buffer.s.size = skb->len;
 	} else {
-		hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)skb->data);
+		hw_buffer.s.addr = XKPHYS_TO_PHYS((uintptr_t)skb->data);
 		hw_buffer.s.pool = 0;
 		hw_buffer.s.size = skb_headlen(skb);
 		CVM_OCT_SKB_CB(skb)[0] = hw_buffer.u64;
@@ -273,11 +273,12 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 			skb_frag_t *fs = skb_shinfo(skb)->frags + i;
 
 			hw_buffer.s.addr =
-				XKPHYS_TO_PHYS((u64)skb_frag_address(fs));
+				XKPHYS_TO_PHYS((uintptr_t)skb_frag_address(fs));
 			hw_buffer.s.size = skb_frag_size(fs);
 			CVM_OCT_SKB_CB(skb)[i + 1] = hw_buffer.u64;
 		}
-		hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)CVM_OCT_SKB_CB(skb));
+		hw_buffer.s.addr =
+			XKPHYS_TO_PHYS((uintptr_t)CVM_OCT_SKB_CB(skb));
 		hw_buffer.s.size = skb_shinfo(skb)->nr_frags + 1;
 		pko_command.s.segs = skb_shinfo(skb)->nr_frags + 1;
 		pko_command.s.gather = 1;
diff --git a/drivers/staging/octeon/octeon-stubs.h b/drivers/staging/octeon/octeon-stubs.h
index a4ac3bfb62a8..b78ce9eaab85 100644
--- a/drivers/staging/octeon/octeon-stubs.h
+++ b/drivers/staging/octeon/octeon-stubs.h
@@ -1202,7 +1202,7 @@ static inline int cvmx_wqe_get_grp(cvmx_wqe_t *work)
 
 static inline void *cvmx_phys_to_ptr(uint64_t physical_address)
 {
-	return (void *)(physical_address);
+	return (void *)(uintptr_t)(physical_address);
 }
 
 static inline uint64_t cvmx_ptr_to_phys(void *ptr)
-- 
cgit v1.2.3


From 63f2b1677fba11c5bd02089f25c13421948905f5 Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Tue, 17 Sep 2019 19:18:41 +0200
Subject: staging/fbtft: Depend on OF
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit c440eee1a7a1 ("Staging: fbtft: Switch to the gpio descriptor
interface") removed setting gpios via platform data. This means that
fbtft will now only work with Device Tree so set the dependency.

This also prevents a NULL pointer deref on non-DT platform because
fbtftops.request_gpios is not set in that case anymore.

Fixes: c440eee1a7a1 ("Staging: fbtft: Switch to the gpio descriptor interface")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Link: https://lore.kernel.org/r/20190917171843.10334-1-noralf@tronnes.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/fbtft/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/fbtft/Kconfig b/drivers/staging/fbtft/Kconfig
index 8ec524a95ec8..4e5d860fd788 100644
--- a/drivers/staging/fbtft/Kconfig
+++ b/drivers/staging/fbtft/Kconfig
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 menuconfig FB_TFT
 	tristate "Support for small TFT LCD display modules"
-	depends on FB && SPI
+	depends on FB && SPI && OF
 	depends on GPIOLIB || COMPILE_TEST
 	select FB_SYS_FILLRECT
 	select FB_SYS_COPYAREA
-- 
cgit v1.2.3


From 2962db71c7030868b6859d09b2138b55297df95e Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Tue, 17 Sep 2019 19:18:42 +0200
Subject: staging/fbtft: Remove fbtft_device
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit c440eee1a7a1 ("Staging: fbtft: Switch to the gpio descriptor
interface") removed the gpio code from fbtft_device rendering it useless.

fbtft_device is a module that was used on the Raspberry Pi to dynamically
add fbtft devices when the Pi didn't have Device Tree support.
Just remove the module since it's the responsibility of Device Tree, ACPI
or platform code to add devices.

Fixes: c440eee1a7a1 ("Staging: fbtft: Switch to the gpio descriptor interface")
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Link: https://lore.kernel.org/r/20190917171843.10334-2-noralf@tronnes.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/fbtft/Kconfig        |    4 -
 drivers/staging/fbtft/Makefile       |    3 -
 drivers/staging/fbtft/fbtft_device.c | 1261 ----------------------------------
 3 files changed, 1268 deletions(-)
 delete mode 100644 drivers/staging/fbtft/fbtft_device.c

diff --git a/drivers/staging/fbtft/Kconfig b/drivers/staging/fbtft/Kconfig
index 4e5d860fd788..4c37d087e25c 100644
--- a/drivers/staging/fbtft/Kconfig
+++ b/drivers/staging/fbtft/Kconfig
@@ -205,7 +205,3 @@ config FB_FLEX
 	depends on FB_TFT
 	help
 	  Generic Framebuffer support for TFT LCD displays.
-
-config FB_TFT_FBTFT_DEVICE
-	tristate "Module to for adding FBTFT devices"
-	depends on FB_TFT
diff --git a/drivers/staging/fbtft/Makefile b/drivers/staging/fbtft/Makefile
index 6bc03311c9c7..925ec17e318d 100644
--- a/drivers/staging/fbtft/Makefile
+++ b/drivers/staging/fbtft/Makefile
@@ -37,6 +37,3 @@ obj-$(CONFIG_FB_TFT_UC1701)      += fb_uc1701.o
 obj-$(CONFIG_FB_TFT_UPD161704)   += fb_upd161704.o
 obj-$(CONFIG_FB_TFT_WATTEROTT)   += fb_watterott.o
 obj-$(CONFIG_FB_FLEX)            += flexfb.o
-
-# Device modules
-obj-$(CONFIG_FB_TFT_FBTFT_DEVICE) += fbtft_device.o
diff --git a/drivers/staging/fbtft/fbtft_device.c b/drivers/staging/fbtft/fbtft_device.c
deleted file mode 100644
index 44e1410eb3fe..000000000000
--- a/drivers/staging/fbtft/fbtft_device.c
+++ /dev/null
@@ -1,1261 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- *
- * Copyright (C) 2013, Noralf Tronnes
- */
-
-#define pr_fmt(fmt) "fbtft_device: " fmt
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/gpio/consumer.h>
-#include <linux/spi/spi.h>
-#include <video/mipi_display.h>
-
-#include "fbtft.h"
-
-#define MAX_GPIOS 32
-
-static struct spi_device *spi_device;
-static struct platform_device *p_device;
-
-static char *name;
-module_param(name, charp, 0000);
-MODULE_PARM_DESC(name,
-		 "Devicename (required). name=list => list all supported devices.");
-
-static unsigned int rotate;
-module_param(rotate, uint, 0000);
-MODULE_PARM_DESC(rotate,
-		 "Angle to rotate display counter clockwise: 0, 90, 180, 270");
-
-static unsigned int busnum;
-module_param(busnum, uint, 0000);
-MODULE_PARM_DESC(busnum, "SPI bus number (default=0)");
-
-static unsigned int cs;
-module_param(cs, uint, 0000);
-MODULE_PARM_DESC(cs, "SPI chip select (default=0)");
-
-static unsigned int speed;
-module_param(speed, uint, 0000);
-MODULE_PARM_DESC(speed, "SPI speed (override device default)");
-
-static int mode = -1;
-module_param(mode, int, 0000);
-MODULE_PARM_DESC(mode, "SPI mode (override device default)");
-
-static unsigned int fps;
-module_param(fps, uint, 0000);
-MODULE_PARM_DESC(fps, "Frames per second (override driver default)");
-
-static char *gamma;
-module_param(gamma, charp, 0000);
-MODULE_PARM_DESC(gamma,
-		 "String representation of Gamma Curve(s). Driver specific.");
-
-static int txbuflen;
-module_param(txbuflen, int, 0000);
-MODULE_PARM_DESC(txbuflen, "txbuflen (override driver default)");
-
-static int bgr = -1;
-module_param(bgr, int, 0000);
-MODULE_PARM_DESC(bgr,
-		 "BGR bit (supported by some drivers).");
-
-static unsigned int startbyte;
-module_param(startbyte, uint, 0000);
-MODULE_PARM_DESC(startbyte, "Sets the Start byte used by some SPI displays.");
-
-static bool custom;
-module_param(custom, bool, 0000);
-MODULE_PARM_DESC(custom, "Add a custom display device. Use speed= argument to make it a SPI device, else platform_device");
-
-static unsigned int width;
-module_param(width, uint, 0000);
-MODULE_PARM_DESC(width, "Display width, used with the custom argument");
-
-static unsigned int height;
-module_param(height, uint, 0000);
-MODULE_PARM_DESC(height, "Display height, used with the custom argument");
-
-static unsigned int buswidth = 8;
-module_param(buswidth, uint, 0000);
-MODULE_PARM_DESC(buswidth, "Display bus width, used with the custom argument");
-
-static s16 init[FBTFT_MAX_INIT_SEQUENCE];
-static int init_num;
-module_param_array(init, short, &init_num, 0000);
-MODULE_PARM_DESC(init, "Init sequence, used with the custom argument");
-
-static unsigned long debug;
-module_param(debug, ulong, 0000);
-MODULE_PARM_DESC(debug,
-		 "level: 0-7 (the remaining 29 bits is for advanced usage)");
-
-static unsigned int verbose = 3;
-module_param(verbose, uint, 0000);
-MODULE_PARM_DESC(verbose,
-		 "0 silent, >1 show devices, >2 show devices before (default=3)");
-
-struct fbtft_device_display {
-	char *name;
-	struct spi_board_info *spi;
-	struct platform_device *pdev;
-};
-
-static void fbtft_device_pdev_release(struct device *dev);
-
-static int write_gpio16_wr_slow(struct fbtft_par *par, void *buf, size_t len);
-static void adafruit18_green_tab_set_addr_win(struct fbtft_par *par,
-					      int xs, int ys, int xe, int ye);
-
-#define ADAFRUIT18_GAMMA \
-		"02 1c 07 12 37 32 29 2d 29 25 2B 39 00 01 03 10\n" \
-		"03 1d 07 06 2E 2C 29 2D 2E 2E 37 3F 00 00 02 10"
-
-#define CBERRY28_GAMMA \
-		"D0 00 14 15 13 2C 42 43 4E 09 16 14 18 21\n" \
-		"D0 00 14 15 13 0B 43 55 53 0C 17 14 23 20"
-
-static const s16 cberry28_init_sequence[] = {
-	/* turn off sleep mode */
-	-1, MIPI_DCS_EXIT_SLEEP_MODE,
-	-2, 120,
-
-	/* set pixel format to RGB-565 */
-	-1, MIPI_DCS_SET_PIXEL_FORMAT, MIPI_DCS_PIXEL_FMT_16BIT,
-
-	-1, 0xB2, 0x0C, 0x0C, 0x00, 0x33, 0x33,
-
-	/*
-	 * VGH = 13.26V
-	 * VGL = -10.43V
-	 */
-	-1, 0xB7, 0x35,
-
-	/*
-	 * VDV and VRH register values come from command write
-	 * (instead of NVM)
-	 */
-	-1, 0xC2, 0x01, 0xFF,
-
-	/*
-	 * VAP =  4.7V + (VCOM + VCOM offset + 0.5 * VDV)
-	 * VAN = -4.7V + (VCOM + VCOM offset + 0.5 * VDV)
-	 */
-	-1, 0xC3, 0x17,
-
-	/* VDV = 0V */
-	-1, 0xC4, 0x20,
-
-	/* VCOM = 0.675V */
-	-1, 0xBB, 0x17,
-
-	/* VCOM offset = 0V */
-	-1, 0xC5, 0x20,
-
-	/*
-	 * AVDD = 6.8V
-	 * AVCL = -4.8V
-	 * VDS = 2.3V
-	 */
-	-1, 0xD0, 0xA4, 0xA1,
-
-	-1, MIPI_DCS_SET_DISPLAY_ON,
-
-	-3,
-};
-
-static const s16 hy28b_init_sequence[] = {
-	-1, 0x00e7, 0x0010, -1, 0x0000, 0x0001,
-	-1, 0x0001, 0x0100, -1, 0x0002, 0x0700,
-	-1, 0x0003, 0x1030, -1, 0x0004, 0x0000,
-	-1, 0x0008, 0x0207, -1, 0x0009, 0x0000,
-	-1, 0x000a, 0x0000, -1, 0x000c, 0x0001,
-	-1, 0x000d, 0x0000, -1, 0x000f, 0x0000,
-	-1, 0x0010, 0x0000, -1, 0x0011, 0x0007,
-	-1, 0x0012, 0x0000, -1, 0x0013, 0x0000,
-	-2, 50, -1, 0x0010, 0x1590, -1, 0x0011,
-	0x0227, -2, 50, -1, 0x0012, 0x009c, -2, 50,
-	-1, 0x0013, 0x1900, -1, 0x0029, 0x0023,
-	-1, 0x002b, 0x000e, -2, 50,
-	-1, 0x0020, 0x0000, -1, 0x0021, 0x0000,
-	-2, 50, -1, 0x0050, 0x0000,
-	-1, 0x0051, 0x00ef, -1, 0x0052, 0x0000,
-	-1, 0x0053, 0x013f, -1, 0x0060, 0xa700,
-	-1, 0x0061, 0x0001, -1, 0x006a, 0x0000,
-	-1, 0x0080, 0x0000, -1, 0x0081, 0x0000,
-	-1, 0x0082, 0x0000, -1, 0x0083, 0x0000,
-	-1, 0x0084, 0x0000, -1, 0x0085, 0x0000,
-	-1, 0x0090, 0x0010, -1, 0x0092, 0x0000,
-	-1, 0x0093, 0x0003, -1, 0x0095, 0x0110,
-	-1, 0x0097, 0x0000, -1, 0x0098, 0x0000,
-	-1, 0x0007, 0x0133, -1, 0x0020, 0x0000,
-	-1, 0x0021, 0x0000, -2, 100, -3 };
-
-#define HY28B_GAMMA \
-	"04 1F 4 7 7 0 7 7 6 0\n" \
-	"0F 00 1 7 4 0 0 0 6 7"
-
-static const s16 pitft_init_sequence[] = {
-	-1, MIPI_DCS_SOFT_RESET,
-	-2, 5,
-	-1, MIPI_DCS_SET_DISPLAY_OFF,
-	-1, 0xEF, 0x03, 0x80, 0x02,
-	-1, 0xCF, 0x00, 0xC1, 0x30,
-	-1, 0xED, 0x64, 0x03, 0x12, 0x81,
-	-1, 0xE8, 0x85, 0x00, 0x78,
-	-1, 0xCB, 0x39, 0x2C, 0x00, 0x34, 0x02,
-	-1, 0xF7, 0x20,
-	-1, 0xEA, 0x00, 0x00,
-	-1, 0xC0, 0x23,
-	-1, 0xC1, 0x10,
-	-1, 0xC5, 0x3E, 0x28,
-	-1, 0xC7, 0x86,
-	-1, MIPI_DCS_SET_PIXEL_FORMAT, 0x55,
-	-1, 0xB1, 0x00, 0x18,
-	-1, 0xB6, 0x08, 0x82, 0x27,
-	-1, 0xF2, 0x00,
-	-1, MIPI_DCS_SET_GAMMA_CURVE, 0x01,
-	-1, 0xE0, 0x0F, 0x31, 0x2B, 0x0C, 0x0E, 0x08, 0x4E,
-		0xF1, 0x37, 0x07, 0x10, 0x03, 0x0E, 0x09, 0x00,
-	-1, 0xE1, 0x00, 0x0E, 0x14, 0x03, 0x11, 0x07, 0x31,
-		0xC1, 0x48, 0x08, 0x0F, 0x0C, 0x31, 0x36, 0x0F,
-	-1, MIPI_DCS_EXIT_SLEEP_MODE,
-	-2, 100,
-	-1, MIPI_DCS_SET_DISPLAY_ON,
-	-2, 20,
-	-3
-};
-
-static const s16 waveshare32b_init_sequence[] = {
-	-1, 0xCB, 0x39, 0x2C, 0x00, 0x34, 0x02,
-	-1, 0xCF, 0x00, 0xC1, 0x30,
-	-1, 0xE8, 0x85, 0x00, 0x78,
-	-1, 0xEA, 0x00, 0x00,
-	-1, 0xED, 0x64, 0x03, 0x12, 0x81,
-	-1, 0xF7, 0x20,
-	-1, 0xC0, 0x23,
-	-1, 0xC1, 0x10,
-	-1, 0xC5, 0x3E, 0x28,
-	-1, 0xC7, 0x86,
-	-1, MIPI_DCS_SET_ADDRESS_MODE, 0x28,
-	-1, MIPI_DCS_SET_PIXEL_FORMAT, 0x55,
-	-1, 0xB1, 0x00, 0x18,
-	-1, 0xB6, 0x08, 0x82, 0x27,
-	-1, 0xF2, 0x00,
-	-1, MIPI_DCS_SET_GAMMA_CURVE, 0x01,
-	-1, 0xE0, 0x0F, 0x31, 0x2B, 0x0C, 0x0E, 0x08, 0x4E,
-		0xF1, 0x37, 0x07, 0x10, 0x03, 0x0E, 0x09, 0x00,
-	-1, 0xE1, 0x00, 0x0E, 0x14, 0x03, 0x11, 0x07, 0x31,
-		0xC1, 0x48, 0x08, 0x0F, 0x0C, 0x31, 0x36, 0x0F,
-	-1, MIPI_DCS_EXIT_SLEEP_MODE,
-	-2, 120,
-	-1, MIPI_DCS_SET_DISPLAY_ON,
-	-1, MIPI_DCS_WRITE_MEMORY_START,
-	-3
-};
-
-#define PIOLED_GAMMA	"0 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 " \
-			"2 2 2 2 2 2 2 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 " \
-			"3 3 3 4 4 4 4 4 4 4 4 4 4 4 4"
-
-/* Supported displays in alphabetical order */
-static struct fbtft_device_display displays[] = {
-	{
-		.name = "adafruit18",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_st7735r",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.gamma = ADAFRUIT18_GAMMA,
-			}
-		}
-	}, {
-		.name = "adafruit18_green",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_st7735r",
-			.max_speed_hz = 4000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-					.fbtftops.set_addr_win =
-					    adafruit18_green_tab_set_addr_win,
-				},
-				.bgr = true,
-				.gamma = ADAFRUIT18_GAMMA,
-			}
-		}
-	}, {
-		.name = "adafruit22",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_hx8340bn",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 9,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "adafruit22a",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9340",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "adafruit28",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9341",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "adafruit13m",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ssd1306",
-			.max_speed_hz = 16000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-				},
-			}
-		}
-	}, {
-		.name = "admatec_c-berry28",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_st7789v",
-			.max_speed_hz = 48000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-					.init_sequence = cberry28_init_sequence,
-				},
-				.gamma = CBERRY28_GAMMA,
-			}
-		}
-	}, {
-		.name = "agm1264k-fl",
-		.pdev = &(struct platform_device) {
-			.name = "fb_agm1264k-fl",
-			.id = 0,
-			.dev = {
-			.release = fbtft_device_pdev_release,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = FBTFT_ONBOARD_BACKLIGHT,
-				},
-			},
-			}
-		}
-	}, {
-		.name = "dogs102",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_uc1701",
-			.max_speed_hz = 8000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "er_tftm050_2",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ra8875",
-			.max_speed_hz = 5000000,
-			.mode = SPI_MODE_3,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-					.width = 480,
-					.height = 272,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "er_tftm070_5",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ra8875",
-			.max_speed_hz = 5000000,
-			.mode = SPI_MODE_3,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-					.width = 800,
-					.height = 480,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "ew24ha0",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_uc1611",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_3,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-				},
-			}
-		}
-	}, {
-		.name = "ew24ha0_9bit",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_uc1611",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_3,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 9,
-				},
-			}
-		}
-	}, {
-		.name = "flexfb",
-		.spi = &(struct spi_board_info) {
-			.modalias = "flexfb",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-		}
-	}, {
-		.name = "flexpfb",
-		.pdev = &(struct platform_device) {
-			.name = "flexpfb",
-			.id = 0,
-			.dev = {
-			.release = fbtft_device_pdev_release,
-			}
-		}
-	}, {
-		.name = "freetronicsoled128",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ssd1351",
-			.max_speed_hz = 20000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = FBTFT_ONBOARD_BACKLIGHT,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "hx8353d",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_hx8353d",
-			.max_speed_hz = 16000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-			}
-		}
-	}, {
-		.name = "hy28a",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9320",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_3,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.startbyte = 0x70,
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "hy28b",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9325",
-			.max_speed_hz = 48000000,
-			.mode = SPI_MODE_3,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-					.init_sequence = hy28b_init_sequence,
-				},
-				.startbyte = 0x70,
-				.bgr = true,
-				.fps = 50,
-				.gamma = HY28B_GAMMA,
-			}
-		}
-	}, {
-		.name = "ili9481",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9481",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.regwidth = 16,
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "itdb24",
-		.pdev = &(struct platform_device) {
-			.name = "fb_s6d1121",
-			.id = 0,
-			.dev = {
-			.release = fbtft_device_pdev_release,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = false,
-			},
-			}
-		}
-	}, {
-		.name = "itdb28",
-		.pdev = &(struct platform_device) {
-			.name = "fb_ili9325",
-			.id = 0,
-			.dev = {
-			.release = fbtft_device_pdev_release,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			},
-			}
-		}
-	}, {
-		.name = "itdb28_spi",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9325",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "mi0283qt-2",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_hx8347d",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.startbyte = 0x70,
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "mi0283qt-9a",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9341",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 9,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "mi0283qt-v2",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_watterott",
-			.max_speed_hz = 4000000,
-			.mode = SPI_MODE_3,
-			.platform_data = &(struct fbtft_platform_data) {
-			}
-		}
-	}, {
-		.name = "nokia3310",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_pcd8544",
-			.max_speed_hz = 400000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-				},
-			}
-		}
-	}, {
-		.name = "nokia3310a",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_tls8204",
-			.max_speed_hz = 1000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-				},
-			}
-		}
-	}, {
-		.name = "nokia5110",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9163",
-			.max_speed_hz = 12000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "piscreen",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9486",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.regwidth = 16,
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "pitft",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9340",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.chip_select = 0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-					.init_sequence = pitft_init_sequence,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "pioled",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ssd1351",
-			.max_speed_hz = 20000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-				},
-				.bgr = true,
-				.gamma = PIOLED_GAMMA
-			}
-		}
-	}, {
-		.name = "rpi-display",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9341",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "s6d02a1",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_s6d02a1",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "sainsmart18",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_st7735r",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-				},
-			}
-		}
-	}, {
-		.name = "sainsmart32",
-		.pdev = &(struct platform_device) {
-			.name = "fb_ssd1289",
-			.id = 0,
-			.dev = {
-			.release = fbtft_device_pdev_release,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 16,
-					.txbuflen = -2, /* disable buffer */
-					.backlight = 1,
-					.fbtftops.write = write_gpio16_wr_slow,
-				},
-				.bgr = true,
-			},
-		},
-		}
-	}, {
-		.name = "sainsmart32_fast",
-		.pdev = &(struct platform_device) {
-			.name = "fb_ssd1289",
-			.id = 0,
-			.dev = {
-			.release = fbtft_device_pdev_release,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 16,
-					.txbuflen = -2, /* disable buffer */
-					.backlight = 1,
-				},
-				.bgr = true,
-			},
-		},
-		}
-	}, {
-		.name = "sainsmart32_latched",
-		.pdev = &(struct platform_device) {
-			.name = "fb_ssd1289",
-			.id = 0,
-			.dev = {
-			.release = fbtft_device_pdev_release,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 16,
-					.txbuflen = -2, /* disable buffer */
-					.backlight = 1,
-					.fbtftops.write =
-						fbtft_write_gpio16_wr_latched,
-				},
-				.bgr = true,
-			},
-		},
-		}
-	}, {
-		.name = "sainsmart32_spi",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ssd1289",
-			.max_speed_hz = 16000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "spidev",
-		.spi = &(struct spi_board_info) {
-			.modalias = "spidev",
-			.max_speed_hz = 500000,
-			.bus_num = 0,
-			.chip_select = 0,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-			}
-		}
-	}, {
-		.name = "ssd1331",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ssd1331",
-			.max_speed_hz = 20000000,
-			.mode = SPI_MODE_3,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-				},
-			}
-		}
-	}, {
-		.name = "tinylcd35",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_tinylcd",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "tm022hdh26",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9341",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "tontec35_9481", /* boards before 02 July 2014 */
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9481",
-			.max_speed_hz = 128000000,
-			.mode = SPI_MODE_3,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "tontec35_9486", /* boards after 02 July 2014 */
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9486",
-			.max_speed_hz = 128000000,
-			.mode = SPI_MODE_3,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "upd161704",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_upd161704",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-				},
-			}
-		}
-	}, {
-		.name = "waveshare32b",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_ili9340",
-			.max_speed_hz = 48000000,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-					.backlight = 1,
-					.init_sequence =
-						waveshare32b_init_sequence,
-				},
-				.bgr = true,
-			}
-		}
-	}, {
-		.name = "waveshare22",
-		.spi = &(struct spi_board_info) {
-			.modalias = "fb_bd663474",
-			.max_speed_hz = 32000000,
-			.mode = SPI_MODE_3,
-			.platform_data = &(struct fbtft_platform_data) {
-				.display = {
-					.buswidth = 8,
-				},
-			}
-		}
-	}, {
-		/* This should be the last item.
-		 * Used with the custom argument
-		 */
-		.name = "",
-		.spi = &(struct spi_board_info) {
-			.modalias = "",
-			.max_speed_hz = 0,
-			.mode = SPI_MODE_0,
-			.platform_data = &(struct fbtft_platform_data) {
-			}
-		},
-		.pdev = &(struct platform_device) {
-			.name = "",
-			.id = 0,
-			.dev = {
-				.release = fbtft_device_pdev_release,
-				.platform_data = &(struct fbtft_platform_data) {
-				},
-			},
-		},
-	}
-};
-
-static int write_gpio16_wr_slow(struct fbtft_par *par, void *buf, size_t len)
-{
-	u16 data;
-	int i;
-#ifndef DO_NOT_OPTIMIZE_FBTFT_WRITE_GPIO
-	static u16 prev_data;
-#endif
-
-	fbtft_par_dbg_hex(DEBUG_WRITE, par, par->info->device, u8, buf, len,
-			  "%s(len=%zu): ", __func__, len);
-
-	while (len) {
-		data = *(u16 *)buf;
-
-		/* Start writing by pulling down /WR */
-		gpiod_set_value(par->gpio.wr, 0);
-
-		/* Set data */
-#ifndef DO_NOT_OPTIMIZE_FBTFT_WRITE_GPIO
-		if (data == prev_data) {
-			gpiod_set_value(par->gpio.wr, 0); /* used as delay */
-		} else {
-			for (i = 0; i < 16; i++) {
-				if ((data & 1) != (prev_data & 1))
-					gpiod_set_value(par->gpio.db[i],
-							data & 1);
-				data >>= 1;
-				prev_data >>= 1;
-			}
-		}
-#else
-		for (i = 0; i < 16; i++) {
-			gpiod_set_value(par->gpio.db[i], data & 1);
-			data >>= 1;
-		}
-#endif
-
-		/* Pullup /WR */
-		gpiod_set_value(par->gpio.wr, 1);
-
-#ifndef DO_NOT_OPTIMIZE_FBTFT_WRITE_GPIO
-		prev_data = *(u16 *)buf;
-#endif
-		buf += 2;
-		len -= 2;
-	}
-
-	return 0;
-}
-
-static void adafruit18_green_tab_set_addr_win(struct fbtft_par *par,
-					      int xs, int ys, int xe, int ye)
-{
-	write_reg(par, 0x2A, 0, xs + 2, 0, xe + 2);
-	write_reg(par, 0x2B, 0, ys + 1, 0, ye + 1);
-	write_reg(par, 0x2C);
-}
-
-static void fbtft_device_pdev_release(struct device *dev)
-{
-/* Needed to silence this message:
- * Device 'xxx' does not have a release() function,
- * it is broken and must be fixed
- */
-}
-
-static int spi_device_found(struct device *dev, void *data)
-{
-	struct spi_device *spi = to_spi_device(dev);
-
-	dev_info(dev, "%s %s %dkHz %d bits mode=0x%02X\n", spi->modalias,
-		 dev_name(dev), spi->max_speed_hz / 1000, spi->bits_per_word,
-		 spi->mode);
-
-	return 0;
-}
-
-static void pr_spi_devices(void)
-{
-	pr_debug("SPI devices registered:\n");
-	bus_for_each_dev(&spi_bus_type, NULL, NULL, spi_device_found);
-}
-
-static int p_device_found(struct device *dev, void *data)
-{
-	struct platform_device
-	*pdev = to_platform_device(dev);
-
-	if (strstr(pdev->name, "fb"))
-		dev_info(dev, "%s id=%d pdata? %s\n", pdev->name, pdev->id,
-			 pdev->dev.platform_data ? "yes" : "no");
-
-	return 0;
-}
-
-static void pr_p_devices(void)
-{
-	pr_debug("'fb' Platform devices registered:\n");
-	bus_for_each_dev(&platform_bus_type, NULL, NULL, p_device_found);
-}
-
-#ifdef MODULE
-static void fbtft_device_spi_delete(struct spi_master *master, unsigned int cs)
-{
-	struct device *dev;
-	char str[32];
-
-	snprintf(str, sizeof(str), "%s.%u", dev_name(&master->dev), cs);
-
-	dev = bus_find_device_by_name(&spi_bus_type, NULL, str);
-	if (dev) {
-		if (verbose)
-			dev_info(dev, "Deleting %s\n", str);
-		device_del(dev);
-	}
-}
-
-static int fbtft_device_spi_device_register(struct spi_board_info *spi)
-{
-	struct spi_master *master;
-
-	master = spi_busnum_to_master(spi->bus_num);
-	if (!master) {
-		pr_err("spi_busnum_to_master(%d) returned NULL\n",
-		       spi->bus_num);
-		return -EINVAL;
-	}
-	/* make sure it's available */
-	fbtft_device_spi_delete(master, spi->chip_select);
-	spi_device = spi_new_device(master, spi);
-	put_device(&master->dev);
-	if (!spi_device) {
-		dev_err(&master->dev, "spi_new_device() returned NULL\n");
-		return -EPERM;
-	}
-	return 0;
-}
-#else
-static int fbtft_device_spi_device_register(struct spi_board_info *spi)
-{
-	return spi_register_board_info(spi, 1);
-}
-#endif
-
-static int __init fbtft_device_init(void)
-{
-	struct spi_board_info *spi = NULL;
-	struct fbtft_platform_data *pdata;
-	bool found = false;
-	int i = 0;
-	int ret = 0;
-
-	if (!name) {
-#ifdef MODULE
-		pr_err("missing module parameter: 'name'\n");
-		return -EINVAL;
-#else
-		return 0;
-#endif
-	}
-
-	if (init_num > FBTFT_MAX_INIT_SEQUENCE) {
-		pr_err("init parameter: exceeded max array size: %d\n",
-		       FBTFT_MAX_INIT_SEQUENCE);
-		return -EINVAL;
-	}
-
-	if (verbose > 2) {
-		pr_spi_devices(); /* print list of registered SPI devices */
-		pr_p_devices(); /* print list of 'fb' platform devices */
-	}
-
-	pr_debug("name='%s', busnum=%d, cs=%d\n", name, busnum, cs);
-
-	if (rotate > 0 && rotate < 4) {
-		rotate = (4 - rotate) * 90;
-		pr_warn("argument 'rotate' should be an angle. Values 1-3 is deprecated. Setting it to %d.\n",
-			rotate);
-	}
-	if (rotate != 0 && rotate != 90 && rotate != 180 && rotate != 270) {
-		pr_warn("argument 'rotate' illegal value: %d. Setting it to 0.\n",
-			rotate);
-		rotate = 0;
-	}
-
-	/* name=list lists all supported displays */
-	if (strcmp(name, "list") == 0) {
-		pr_info("Supported displays:\n");
-
-		for (i = 0; i < ARRAY_SIZE(displays); i++)
-			pr_info("%s\n", displays[i].name);
-		return -ECANCELED;
-	}
-
-	if (custom) {
-		i = ARRAY_SIZE(displays) - 1;
-		displays[i].name = name;
-		if (speed == 0) {
-			displays[i].pdev->name = name;
-			displays[i].spi = NULL;
-		} else {
-			size_t len;
-
-			len = strlcpy(displays[i].spi->modalias, name,
-				      SPI_NAME_SIZE);
-			if (len >= SPI_NAME_SIZE)
-				pr_warn("modalias (name) truncated to: %s\n",
-					displays[i].spi->modalias);
-			displays[i].pdev = NULL;
-		}
-	}
-
-	for (i = 0; i < ARRAY_SIZE(displays); i++) {
-		if (strncmp(name, displays[i].name, SPI_NAME_SIZE) == 0) {
-			if (displays[i].spi) {
-				spi = displays[i].spi;
-				spi->chip_select = cs;
-				spi->bus_num = busnum;
-				if (speed)
-					spi->max_speed_hz = speed;
-				if (mode != -1)
-					spi->mode = mode;
-				pdata = (void *)spi->platform_data;
-			} else if (displays[i].pdev) {
-				p_device = displays[i].pdev;
-				pdata = p_device->dev.platform_data;
-			} else {
-				pr_err("broken displays array\n");
-				return -EINVAL;
-			}
-
-			pdata->rotate = rotate;
-			if (bgr == 0)
-				pdata->bgr = false;
-			else if (bgr == 1)
-				pdata->bgr = true;
-			if (startbyte)
-				pdata->startbyte = startbyte;
-			if (gamma)
-				pdata->gamma = gamma;
-			pdata->display.debug = debug;
-			if (fps)
-				pdata->fps = fps;
-			if (txbuflen)
-				pdata->txbuflen = txbuflen;
-			if (init_num)
-				pdata->display.init_sequence = init;
-			if (custom) {
-				pdata->display.width = width;
-				pdata->display.height = height;
-				pdata->display.buswidth = buswidth;
-				pdata->display.backlight = 1;
-			}
-
-			if (displays[i].spi) {
-				ret = fbtft_device_spi_device_register(spi);
-				if (ret) {
-					pr_err("failed to register SPI device\n");
-					return ret;
-				}
-			} else {
-				ret = platform_device_register(p_device);
-				if (ret < 0) {
-					pr_err("platform_device_register() returned %d\n",
-					       ret);
-					return ret;
-				}
-			}
-			found = true;
-			break;
-		}
-	}
-
-	if (!found) {
-		pr_err("display not supported: '%s'\n", name);
-		return -EINVAL;
-	}
-
-	if (spi_device && (verbose > 1))
-		pr_spi_devices();
-	if (p_device && (verbose > 1))
-		pr_p_devices();
-
-	return 0;
-}
-
-static void __exit fbtft_device_exit(void)
-{
-	if (spi_device) {
-		device_del(&spi_device->dev);
-		kfree(spi_device);
-	}
-
-	if (p_device)
-		platform_device_unregister(p_device);
-}
-
-arch_initcall(fbtft_device_init);
-module_exit(fbtft_device_exit);
-
-MODULE_DESCRIPTION("Add a FBTFT device.");
-MODULE_AUTHOR("Noralf Tronnes");
-MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From cc2965091914d50330ad86911ac4306777fbf4c7 Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Tue, 17 Sep 2019 19:18:43 +0200
Subject: staging/fbtft: Remove flexfb
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

flexfb was an attempt to write a generic fbtft driver that was abandoned.
All the displays it supports are supported by other fbtft drivers.

Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Link: https://lore.kernel.org/r/20190917171843.10334-3-noralf@tronnes.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/fbtft/Kconfig  |   6 -
 drivers/staging/fbtft/Makefile |   1 -
 drivers/staging/fbtft/flexfb.c | 851 -----------------------------------------
 3 files changed, 858 deletions(-)
 delete mode 100644 drivers/staging/fbtft/flexfb.c

diff --git a/drivers/staging/fbtft/Kconfig b/drivers/staging/fbtft/Kconfig
index 4c37d087e25c..cb61c2a772bd 100644
--- a/drivers/staging/fbtft/Kconfig
+++ b/drivers/staging/fbtft/Kconfig
@@ -199,9 +199,3 @@ config FB_TFT_WATTEROTT
 	depends on FB_TFT
 	help
 	  Generic Framebuffer support for WATTEROTT
-
-config FB_FLEX
-	tristate "Generic FB driver for TFT LCD displays"
-	depends on FB_TFT
-	help
-	  Generic Framebuffer support for TFT LCD displays.
diff --git a/drivers/staging/fbtft/Makefile b/drivers/staging/fbtft/Makefile
index 925ec17e318d..27af43f32f81 100644
--- a/drivers/staging/fbtft/Makefile
+++ b/drivers/staging/fbtft/Makefile
@@ -36,4 +36,3 @@ obj-$(CONFIG_FB_TFT_UC1611)      += fb_uc1611.o
 obj-$(CONFIG_FB_TFT_UC1701)      += fb_uc1701.o
 obj-$(CONFIG_FB_TFT_UPD161704)   += fb_upd161704.o
 obj-$(CONFIG_FB_TFT_WATTEROTT)   += fb_watterott.o
-obj-$(CONFIG_FB_FLEX)            += flexfb.o
diff --git a/drivers/staging/fbtft/flexfb.c b/drivers/staging/fbtft/flexfb.c
deleted file mode 100644
index 3747321011fa..000000000000
--- a/drivers/staging/fbtft/flexfb.c
+++ /dev/null
@@ -1,851 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * Generic FB driver for TFT LCD displays
- *
- * Copyright (C) 2013 Noralf Tronnes
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/vmalloc.h>
-#include <linux/gpio/consumer.h>
-#include <linux/spi/spi.h>
-#include <linux/delay.h>
-
-#include "fbtft.h"
-
-#define DRVNAME	    "flexfb"
-
-static char *chip;
-module_param(chip, charp, 0000);
-MODULE_PARM_DESC(chip, "LCD controller");
-
-static unsigned int width;
-module_param(width, uint, 0000);
-MODULE_PARM_DESC(width, "Display width");
-
-static unsigned int height;
-module_param(height, uint, 0000);
-MODULE_PARM_DESC(height, "Display height");
-
-static s16 init[512];
-static int init_num;
-module_param_array(init, short, &init_num, 0000);
-MODULE_PARM_DESC(init, "Init sequence");
-
-static unsigned int setaddrwin;
-module_param(setaddrwin, uint, 0000);
-MODULE_PARM_DESC(setaddrwin, "Which set_addr_win() implementation to use");
-
-static unsigned int buswidth = 8;
-module_param(buswidth, uint, 0000);
-MODULE_PARM_DESC(buswidth, "Width of databus (default: 8)");
-
-static unsigned int regwidth = 8;
-module_param(regwidth, uint, 0000);
-MODULE_PARM_DESC(regwidth, "Width of controller register (default: 8)");
-
-static bool nobacklight;
-module_param(nobacklight, bool, 0000);
-MODULE_PARM_DESC(nobacklight, "Turn off backlight functionality.");
-
-static bool latched;
-module_param(latched, bool, 0000);
-MODULE_PARM_DESC(latched, "Use with latched 16-bit databus");
-
-static const s16 *initp;
-static int initp_num;
-
-/* default init sequences */
-static const s16 st7735r_init[] = {
-	-1, 0x01,
-	-2, 150,
-	-1, 0x11,
-	-2, 500,
-	-1, 0xB1, 0x01, 0x2C, 0x2D,
-	-1, 0xB2, 0x01, 0x2C, 0x2D,
-	-1, 0xB3, 0x01, 0x2C, 0x2D, 0x01, 0x2C, 0x2D,
-	-1, 0xB4, 0x07,
-	-1, 0xC0, 0xA2, 0x02, 0x84,
-	-1, 0xC1, 0xC5,
-	-1, 0xC2, 0x0A, 0x00,
-	-1, 0xC3, 0x8A, 0x2A,
-	-1, 0xC4, 0x8A, 0xEE,
-	-1, 0xC5, 0x0E,
-	-1, 0x20,
-	-1, 0x36, 0xC0,
-	-1, 0x3A, 0x05,
-	-1, 0xE0, 0x0f, 0x1a, 0x0f, 0x18, 0x2f, 0x28, 0x20, 0x22,
-	    0x1f, 0x1b, 0x23, 0x37, 0x00, 0x07, 0x02, 0x10,
-	-1, 0xE1, 0x0f, 0x1b, 0x0f, 0x17, 0x33, 0x2c, 0x29, 0x2e,
-	    0x30, 0x30, 0x39, 0x3f, 0x00, 0x07, 0x03, 0x10,
-	-1, 0x29,
-	-2, 100,
-	-1, 0x13,
-	-2, 10,
-	-3
-};
-
-static const s16 ssd1289_init[] = {
-	-1, 0x00, 0x0001,
-	-1, 0x03, 0xA8A4,
-	-1, 0x0C, 0x0000,
-	-1, 0x0D, 0x080C,
-	-1, 0x0E, 0x2B00,
-	-1, 0x1E, 0x00B7,
-	-1, 0x01, 0x2B3F,
-	-1, 0x02, 0x0600,
-	-1, 0x10, 0x0000,
-	-1, 0x11, 0x6070,
-	-1, 0x05, 0x0000,
-	-1, 0x06, 0x0000,
-	-1, 0x16, 0xEF1C,
-	-1, 0x17, 0x0003,
-	-1, 0x07, 0x0233,
-	-1, 0x0B, 0x0000,
-	-1, 0x0F, 0x0000,
-	-1, 0x41, 0x0000,
-	-1, 0x42, 0x0000,
-	-1, 0x48, 0x0000,
-	-1, 0x49, 0x013F,
-	-1, 0x4A, 0x0000,
-	-1, 0x4B, 0x0000,
-	-1, 0x44, 0xEF00,
-	-1, 0x45, 0x0000,
-	-1, 0x46, 0x013F,
-	-1, 0x30, 0x0707,
-	-1, 0x31, 0x0204,
-	-1, 0x32, 0x0204,
-	-1, 0x33, 0x0502,
-	-1, 0x34, 0x0507,
-	-1, 0x35, 0x0204,
-	-1, 0x36, 0x0204,
-	-1, 0x37, 0x0502,
-	-1, 0x3A, 0x0302,
-	-1, 0x3B, 0x0302,
-	-1, 0x23, 0x0000,
-	-1, 0x24, 0x0000,
-	-1, 0x25, 0x8000,
-	-1, 0x4f, 0x0000,
-	-1, 0x4e, 0x0000,
-	-1, 0x22,
-	-3
-};
-
-static const s16 hx8340bn_init[] = {
-	-1, 0xC1, 0xFF, 0x83, 0x40,
-	-1, 0x11,
-	-2, 150,
-	-1, 0xCA, 0x70, 0x00, 0xD9,
-	-1, 0xB0, 0x01, 0x11,
-	-1, 0xC9, 0x90, 0x49, 0x10, 0x28, 0x28, 0x10, 0x00, 0x06,
-	-2, 20,
-	-1, 0xC2, 0x60, 0x71, 0x01, 0x0E, 0x05, 0x02, 0x09, 0x31, 0x0A,
-	-1, 0xC3, 0x67, 0x30, 0x61, 0x17, 0x48, 0x07, 0x05, 0x33,
-	-2, 10,
-	-1, 0xB5, 0x35, 0x20, 0x45,
-	-1, 0xB4, 0x33, 0x25, 0x4C,
-	-2, 10,
-	-1, 0x3A, 0x05,
-	-1, 0x29,
-	-2, 10,
-	-3
-};
-
-static const s16 ili9225_init[] = {
-	-1, 0x0001, 0x011C,
-	-1, 0x0002, 0x0100,
-	-1, 0x0003, 0x1030,
-	-1, 0x0008, 0x0808,
-	-1, 0x000C, 0x0000,
-	-1, 0x000F, 0x0A01,
-	-1, 0x0020, 0x0000,
-	-1, 0x0021, 0x0000,
-	-2, 50,
-	-1, 0x0010, 0x0A00,
-	-1, 0x0011, 0x1038,
-	-2, 50,
-	-1, 0x0012, 0x1121,
-	-1, 0x0013, 0x004E,
-	-1, 0x0014, 0x676F,
-	-1, 0x0030, 0x0000,
-	-1, 0x0031, 0x00DB,
-	-1, 0x0032, 0x0000,
-	-1, 0x0033, 0x0000,
-	-1, 0x0034, 0x00DB,
-	-1, 0x0035, 0x0000,
-	-1, 0x0036, 0x00AF,
-	-1, 0x0037, 0x0000,
-	-1, 0x0038, 0x00DB,
-	-1, 0x0039, 0x0000,
-	-1, 0x0050, 0x0000,
-	-1, 0x0051, 0x060A,
-	-1, 0x0052, 0x0D0A,
-	-1, 0x0053, 0x0303,
-	-1, 0x0054, 0x0A0D,
-	-1, 0x0055, 0x0A06,
-	-1, 0x0056, 0x0000,
-	-1, 0x0057, 0x0303,
-	-1, 0x0058, 0x0000,
-	-1, 0x0059, 0x0000,
-	-2, 50,
-	-1, 0x0007, 0x1017,
-	-2, 50,
-	-3
-};
-
-static const s16 ili9320_init[] = {
-	-1, 0x00E5, 0x8000,
-	-1, 0x0000, 0x0001,
-	-1, 0x0001, 0x0100,
-	-1, 0x0002, 0x0700,
-	-1, 0x0003, 0x1030,
-	-1, 0x0004, 0x0000,
-	-1, 0x0008, 0x0202,
-	-1, 0x0009, 0x0000,
-	-1, 0x000A, 0x0000,
-	-1, 0x000C, 0x0000,
-	-1, 0x000D, 0x0000,
-	-1, 0x000F, 0x0000,
-	-1, 0x0010, 0x0000,
-	-1, 0x0011, 0x0007,
-	-1, 0x0012, 0x0000,
-	-1, 0x0013, 0x0000,
-	-2, 200,
-	-1, 0x0010, 0x17B0,
-	-1, 0x0011, 0x0031,
-	-2, 50,
-	-1, 0x0012, 0x0138,
-	-2, 50,
-	-1, 0x0013, 0x1800,
-	-1, 0x0029, 0x0008,
-	-2, 50,
-	-1, 0x0020, 0x0000,
-	-1, 0x0021, 0x0000,
-	-1, 0x0030, 0x0000,
-	-1, 0x0031, 0x0505,
-	-1, 0x0032, 0x0004,
-	-1, 0x0035, 0x0006,
-	-1, 0x0036, 0x0707,
-	-1, 0x0037, 0x0105,
-	-1, 0x0038, 0x0002,
-	-1, 0x0039, 0x0707,
-	-1, 0x003C, 0x0704,
-	-1, 0x003D, 0x0807,
-	-1, 0x0050, 0x0000,
-	-1, 0x0051, 0x00EF,
-	-1, 0x0052, 0x0000,
-	-1, 0x0053, 0x013F,
-	-1, 0x0060, 0x2700,
-	-1, 0x0061, 0x0001,
-	-1, 0x006A, 0x0000,
-	-1, 0x0080, 0x0000,
-	-1, 0x0081, 0x0000,
-	-1, 0x0082, 0x0000,
-	-1, 0x0083, 0x0000,
-	-1, 0x0084, 0x0000,
-	-1, 0x0085, 0x0000,
-	-1, 0x0090, 0x0010,
-	-1, 0x0092, 0x0000,
-	-1, 0x0093, 0x0003,
-	-1, 0x0095, 0x0110,
-	-1, 0x0097, 0x0000,
-	-1, 0x0098, 0x0000,
-	-1, 0x0007, 0x0173,
-	-3
-};
-
-static const s16 ili9325_init[] = {
-	-1, 0x00E3, 0x3008,
-	-1, 0x00E7, 0x0012,
-	-1, 0x00EF, 0x1231,
-	-1, 0x0001, 0x0100,
-	-1, 0x0002, 0x0700,
-	-1, 0x0003, 0x1030,
-	-1, 0x0004, 0x0000,
-	-1, 0x0008, 0x0207,
-	-1, 0x0009, 0x0000,
-	-1, 0x000A, 0x0000,
-	-1, 0x000C, 0x0000,
-	-1, 0x000D, 0x0000,
-	-1, 0x000F, 0x0000,
-	-1, 0x0010, 0x0000,
-	-1, 0x0011, 0x0007,
-	-1, 0x0012, 0x0000,
-	-1, 0x0013, 0x0000,
-	-2, 200,
-	-1, 0x0010, 0x1690,
-	-1, 0x0011, 0x0223,
-	-2, 50,
-	-1, 0x0012, 0x000D,
-	-2, 50,
-	-1, 0x0013, 0x1200,
-	-1, 0x0029, 0x000A,
-	-1, 0x002B, 0x000C,
-	-2, 50,
-	-1, 0x0020, 0x0000,
-	-1, 0x0021, 0x0000,
-	-1, 0x0030, 0x0000,
-	-1, 0x0031, 0x0506,
-	-1, 0x0032, 0x0104,
-	-1, 0x0035, 0x0207,
-	-1, 0x0036, 0x000F,
-	-1, 0x0037, 0x0306,
-	-1, 0x0038, 0x0102,
-	-1, 0x0039, 0x0707,
-	-1, 0x003C, 0x0702,
-	-1, 0x003D, 0x1604,
-	-1, 0x0050, 0x0000,
-	-1, 0x0051, 0x00EF,
-	-1, 0x0052, 0x0000,
-	-1, 0x0053, 0x013F,
-	-1, 0x0060, 0xA700,
-	-1, 0x0061, 0x0001,
-	-1, 0x006A, 0x0000,
-	-1, 0x0080, 0x0000,
-	-1, 0x0081, 0x0000,
-	-1, 0x0082, 0x0000,
-	-1, 0x0083, 0x0000,
-	-1, 0x0084, 0x0000,
-	-1, 0x0085, 0x0000,
-	-1, 0x0090, 0x0010,
-	-1, 0x0092, 0x0600,
-	-1, 0x0007, 0x0133,
-	-3
-};
-
-static const s16 ili9341_init[] = {
-	-1, 0x28,
-	-2, 20,
-	-1, 0xCF, 0x00, 0x83, 0x30,
-	-1, 0xED, 0x64, 0x03, 0x12, 0x81,
-	-1, 0xE8, 0x85, 0x01, 0x79,
-	-1, 0xCB, 0x39, 0x2c, 0x00, 0x34, 0x02,
-	-1, 0xF7, 0x20,
-	-1, 0xEA, 0x00, 0x00,
-	-1, 0xC0, 0x26,
-	-1, 0xC1, 0x11,
-	-1, 0xC5, 0x35, 0x3E,
-	-1, 0xC7, 0xBE,
-	-1, 0xB1, 0x00, 0x1B,
-	-1, 0xB6, 0x0a, 0x82, 0x27, 0x00,
-	-1, 0xB7, 0x07,
-	-1, 0x3A, 0x55,
-	-1, 0x36, 0x48,
-	-1, 0x11,
-	-2, 120,
-	-1, 0x29,
-	-2, 20,
-	-3
-};
-
-static const s16 ssd1351_init[] = {
-	-1, 0xfd, 0x12,
-	-1, 0xfd, 0xb1,
-	-1, 0xae,
-	-1, 0xb3, 0xf1,
-	-1, 0xca, 0x7f,
-	-1, 0xa0, 0x74,
-	-1, 0x15, 0x00, 0x7f,
-	-1, 0x75, 0x00, 0x7f,
-	-1, 0xa1, 0x00,
-	-1, 0xa2, 0x00,
-	-1, 0xb5, 0x00,
-	-1, 0xab, 0x01,
-	-1, 0xb1, 0x32,
-	-1, 0xb4, 0xa0, 0xb5, 0x55,
-	-1, 0xbb, 0x17,
-	-1, 0xbe, 0x05,
-	-1, 0xc1, 0xc8, 0x80, 0xc8,
-	-1, 0xc7, 0x0f,
-	-1, 0xb6, 0x01,
-	-1, 0xa6,
-	-1, 0xaf,
-	-3
-};
-
-/**
- * struct flexfb_lcd_controller - Describes the LCD controller properties
- * @name: Model name of the chip
- * @width: Width of display in pixels
- * @height: Height of display in pixels
- * @setaddrwin: Which set_addr_win() implementation to use
- * @regwidth: LCD Controller Register width in bits
- * @init_seq: LCD initialization sequence
- * @init_seq_sz: Size of LCD initialization sequence
- */
-struct flexfb_lcd_controller {
-	const char *name;
-	unsigned int width;
-	unsigned int height;
-	unsigned int setaddrwin;
-	unsigned int regwidth;
-	const s16 *init_seq;
-	int init_seq_sz;
-};
-
-static const struct flexfb_lcd_controller flexfb_chip_table[] = {
-	{
-		.name = "st7735r",
-		.width = 120,
-		.height = 160,
-		.init_seq = st7735r_init,
-		.init_seq_sz = ARRAY_SIZE(st7735r_init),
-	},
-	{
-		.name = "hx8340bn",
-		.width = 176,
-		.height = 220,
-		.init_seq = hx8340bn_init,
-		.init_seq_sz = ARRAY_SIZE(hx8340bn_init),
-	},
-	{
-		.name = "ili9225",
-		.width = 176,
-		.height = 220,
-		.regwidth = 16,
-		.init_seq = ili9225_init,
-		.init_seq_sz = ARRAY_SIZE(ili9225_init),
-	},
-	{
-		.name = "ili9320",
-		.width = 240,
-		.height = 320,
-		.setaddrwin = 1,
-		.regwidth = 16,
-		.init_seq = ili9320_init,
-		.init_seq_sz = ARRAY_SIZE(ili9320_init),
-	},
-	{
-		.name = "ili9325",
-		.width = 240,
-		.height = 320,
-		.setaddrwin = 1,
-		.regwidth = 16,
-		.init_seq = ili9325_init,
-		.init_seq_sz = ARRAY_SIZE(ili9325_init),
-	},
-	{
-		.name = "ili9341",
-		.width = 240,
-		.height = 320,
-		.init_seq = ili9341_init,
-		.init_seq_sz = ARRAY_SIZE(ili9341_init),
-	},
-	{
-		.name = "ssd1289",
-		.width = 240,
-		.height = 320,
-		.setaddrwin = 2,
-		.regwidth = 16,
-		.init_seq = ssd1289_init,
-		.init_seq_sz = ARRAY_SIZE(ssd1289_init),
-	},
-	{
-		.name = "ssd1351",
-		.width = 128,
-		.height = 128,
-		.setaddrwin = 3,
-		.init_seq = ssd1351_init,
-		.init_seq_sz = ARRAY_SIZE(ssd1351_init),
-	},
-};
-
-/* ili9320, ili9325 */
-static void flexfb_set_addr_win_1(struct fbtft_par *par,
-				  int xs, int ys, int xe, int ye)
-{
-	switch (par->info->var.rotate) {
-	/* R20h = Horizontal GRAM Start Address */
-	/* R21h = Vertical GRAM Start Address */
-	case 0:
-		write_reg(par, 0x0020, xs);
-		write_reg(par, 0x0021, ys);
-		break;
-	case 180:
-		write_reg(par, 0x0020, width - 1 - xs);
-		write_reg(par, 0x0021, height - 1 - ys);
-		break;
-	case 270:
-		write_reg(par, 0x0020, width - 1 - ys);
-		write_reg(par, 0x0021, xs);
-		break;
-	case 90:
-		write_reg(par, 0x0020, ys);
-		write_reg(par, 0x0021, height - 1 - xs);
-		break;
-	}
-	write_reg(par, 0x0022); /* Write Data to GRAM */
-}
-
-/* ssd1289 */
-static void flexfb_set_addr_win_2(struct fbtft_par *par,
-				  int xs, int ys, int xe, int ye)
-{
-	switch (par->info->var.rotate) {
-	/* R4Eh - Set GDDRAM X address counter */
-	/* R4Fh - Set GDDRAM Y address counter */
-	case 0:
-		write_reg(par, 0x4e, xs);
-		write_reg(par, 0x4f, ys);
-		break;
-	case 180:
-		write_reg(par, 0x4e, par->info->var.xres - 1 - xs);
-		write_reg(par, 0x4f, par->info->var.yres - 1 - ys);
-		break;
-	case 270:
-		write_reg(par, 0x4e, par->info->var.yres - 1 - ys);
-		write_reg(par, 0x4f, xs);
-		break;
-	case 90:
-		write_reg(par, 0x4e, ys);
-		write_reg(par, 0x4f, par->info->var.xres - 1 - xs);
-		break;
-	}
-
-	/* R22h - RAM data write */
-	write_reg(par, 0x22, 0);
-}
-
-/* ssd1351 */
-static void set_addr_win_3(struct fbtft_par *par,
-			   int xs, int ys, int xe, int ye)
-{
-	write_reg(par, 0x15, xs, xe);
-	write_reg(par, 0x75, ys, ye);
-	write_reg(par, 0x5C);
-}
-
-static int flexfb_verify_gpios_dc(struct fbtft_par *par)
-{
-	fbtft_par_dbg(DEBUG_VERIFY_GPIOS, par, "%s()\n", __func__);
-
-	if (!par->gpio.dc) {
-		dev_err(par->info->device,
-			"Missing info about 'dc' gpio. Aborting.\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int flexfb_verify_gpios_db(struct fbtft_par *par)
-{
-	int i;
-	int num_db = buswidth;
-
-	fbtft_par_dbg(DEBUG_VERIFY_GPIOS, par, "%s()\n", __func__);
-
-	if (!par->gpio.dc) {
-		dev_err(par->info->device, "Missing info about 'dc' gpio. Aborting.\n");
-		return -EINVAL;
-	}
-	if (!par->gpio.wr) {
-		dev_err(par->info->device, "Missing info about 'wr' gpio. Aborting.\n");
-		return -EINVAL;
-	}
-	if (latched && !par->gpio.latch) {
-		dev_err(par->info->device, "Missing info about 'latch' gpio. Aborting.\n");
-		return -EINVAL;
-	}
-	if (latched)
-		num_db = buswidth / 2;
-	for (i = 0; i < num_db; i++) {
-		if (!par->gpio.db[i]) {
-			dev_err(par->info->device,
-				"Missing info about 'db%02d' gpio. Aborting.\n",
-				i);
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
-
-static void flexfb_chip_load_param(const struct flexfb_lcd_controller *chip)
-{
-	if (!width)
-		width = chip->width;
-	if (!height)
-		height = chip->height;
-	setaddrwin = chip->setaddrwin;
-	if (chip->regwidth)
-		regwidth = chip->regwidth;
-	if (!init_num) {
-		initp = chip->init_seq;
-		initp_num = chip->init_seq_sz;
-	}
-}
-
-static struct fbtft_display flex_display = { };
-
-static int flexfb_chip_init(const struct device *dev)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(flexfb_chip_table); i++)
-		if (!strcmp(chip, flexfb_chip_table[i].name)) {
-			flexfb_chip_load_param(&flexfb_chip_table[i]);
-			return 0;
-		}
-
-	dev_err(dev, "chip=%s is not supported\n", chip);
-
-	return -EINVAL;
-}
-
-static int flexfb_probe_common(struct spi_device *sdev,
-			       struct platform_device *pdev)
-{
-	struct device *dev;
-	struct fb_info *info;
-	struct fbtft_par *par;
-	int ret;
-
-	initp = init;
-	initp_num = init_num;
-
-	if (sdev)
-		dev = &sdev->dev;
-	else
-		dev = &pdev->dev;
-
-	fbtft_init_dbg(dev, "%s(%s)\n", __func__,
-		       sdev ? "'SPI device'" : "'Platform device'");
-
-	if (chip) {
-		ret = flexfb_chip_init(dev);
-		if (ret)
-			return ret;
-	}
-
-	if (width == 0 || height == 0) {
-		dev_err(dev, "argument(s) missing: width and height has to be set.\n");
-		return -EINVAL;
-	}
-	flex_display.width = width;
-	flex_display.height = height;
-	fbtft_init_dbg(dev, "Display resolution: %dx%d\n", width, height);
-	fbtft_init_dbg(dev, "chip = %s\n", chip ? chip : "not set");
-	fbtft_init_dbg(dev, "setaddrwin = %d\n", setaddrwin);
-	fbtft_init_dbg(dev, "regwidth = %d\n", regwidth);
-	fbtft_init_dbg(dev, "buswidth = %d\n", buswidth);
-
-	info = fbtft_framebuffer_alloc(&flex_display, dev, dev->platform_data);
-	if (!info)
-		return -ENOMEM;
-
-	par = info->par;
-	if (sdev)
-		par->spi = sdev;
-	else
-		par->pdev = pdev;
-	if (!par->init_sequence)
-		par->init_sequence = initp;
-	par->fbtftops.init_display = fbtft_init_display;
-
-	/* registerwrite functions */
-	switch (regwidth) {
-	case 8:
-		par->fbtftops.write_register = fbtft_write_reg8_bus8;
-		break;
-	case 16:
-		par->fbtftops.write_register = fbtft_write_reg16_bus8;
-		break;
-	default:
-		dev_err(dev,
-			"argument 'regwidth': %d is not supported.\n",
-			regwidth);
-		return -EINVAL;
-	}
-
-	/* bus functions */
-	if (sdev) {
-		par->fbtftops.write = fbtft_write_spi;
-		switch (buswidth) {
-		case 8:
-			par->fbtftops.write_vmem = fbtft_write_vmem16_bus8;
-			if (!par->startbyte)
-				par->fbtftops.verify_gpios = flexfb_verify_gpios_dc;
-			break;
-		case 9:
-			if (regwidth == 16) {
-				dev_err(dev, "argument 'regwidth': %d is not supported with buswidth=%d and SPI.\n",
-					regwidth, buswidth);
-				return -EINVAL;
-			}
-			par->fbtftops.write_register = fbtft_write_reg8_bus9;
-			par->fbtftops.write_vmem = fbtft_write_vmem16_bus9;
-			if (par->spi->master->bits_per_word_mask
-			    & SPI_BPW_MASK(9)) {
-				par->spi->bits_per_word = 9;
-				break;
-			}
-
-			dev_warn(dev,
-				 "9-bit SPI not available, emulating using 8-bit.\n");
-			/* allocate buffer with room for dc bits */
-			par->extra = devm_kzalloc(par->info->device,
-						  par->txbuf.len
-						  + (par->txbuf.len / 8) + 8,
-						  GFP_KERNEL);
-			if (!par->extra) {
-				ret = -ENOMEM;
-				goto out_release;
-			}
-			par->fbtftops.write = fbtft_write_spi_emulate_9;
-
-			break;
-		default:
-			dev_err(dev,
-				"argument 'buswidth': %d is not supported with SPI.\n",
-				buswidth);
-			return -EINVAL;
-		}
-	} else {
-		par->fbtftops.verify_gpios = flexfb_verify_gpios_db;
-		switch (buswidth) {
-		case 8:
-			par->fbtftops.write = fbtft_write_gpio8_wr;
-			par->fbtftops.write_vmem = fbtft_write_vmem16_bus8;
-			break;
-		case 16:
-			par->fbtftops.write_register = fbtft_write_reg16_bus16;
-			if (latched)
-				par->fbtftops.write = fbtft_write_gpio16_wr_latched;
-			else
-				par->fbtftops.write = fbtft_write_gpio16_wr;
-			par->fbtftops.write_vmem = fbtft_write_vmem16_bus16;
-			break;
-		default:
-			dev_err(dev,
-				"argument 'buswidth': %d is not supported with parallel.\n",
-				buswidth);
-			return -EINVAL;
-		}
-	}
-
-	/* set_addr_win function */
-	switch (setaddrwin) {
-	case 0:
-		/* use default */
-		break;
-	case 1:
-		par->fbtftops.set_addr_win = flexfb_set_addr_win_1;
-		break;
-	case 2:
-		par->fbtftops.set_addr_win = flexfb_set_addr_win_2;
-		break;
-	case 3:
-		par->fbtftops.set_addr_win = set_addr_win_3;
-		break;
-	default:
-		dev_err(dev, "argument 'setaddrwin': unknown value %d.\n",
-			setaddrwin);
-		return -EINVAL;
-	}
-
-	if (!nobacklight)
-		par->fbtftops.register_backlight = fbtft_register_backlight;
-
-	ret = fbtft_register_framebuffer(info);
-	if (ret < 0)
-		goto out_release;
-
-	return 0;
-
-out_release:
-	fbtft_framebuffer_release(info);
-
-	return ret;
-}
-
-static int flexfb_remove_common(struct device *dev, struct fb_info *info)
-{
-	struct fbtft_par *par;
-
-	if (!info)
-		return -EINVAL;
-	par = info->par;
-	if (par)
-		fbtft_par_dbg(DEBUG_DRIVER_INIT_FUNCTIONS, par, "%s()\n",
-			      __func__);
-	fbtft_unregister_framebuffer(info);
-	fbtft_framebuffer_release(info);
-
-	return 0;
-}
-
-static int flexfb_probe_spi(struct spi_device *spi)
-{
-	return flexfb_probe_common(spi, NULL);
-}
-
-static int flexfb_remove_spi(struct spi_device *spi)
-{
-	struct fb_info *info = spi_get_drvdata(spi);
-
-	return flexfb_remove_common(&spi->dev, info);
-}
-
-static int flexfb_probe_pdev(struct platform_device *pdev)
-{
-	return flexfb_probe_common(NULL, pdev);
-}
-
-static int flexfb_remove_pdev(struct platform_device *pdev)
-{
-	struct fb_info *info = platform_get_drvdata(pdev);
-
-	return flexfb_remove_common(&pdev->dev, info);
-}
-
-static struct spi_driver flexfb_spi_driver = {
-	.driver = {
-		.name   = DRVNAME,
-	},
-	.probe  = flexfb_probe_spi,
-	.remove = flexfb_remove_spi,
-};
-
-static const struct platform_device_id flexfb_platform_ids[] = {
-	{ "flexpfb", 0 },
-	{ },
-};
-MODULE_DEVICE_TABLE(platform, flexfb_platform_ids);
-
-static struct platform_driver flexfb_platform_driver = {
-	.driver = {
-		.name   = DRVNAME,
-	},
-	.id_table = flexfb_platform_ids,
-	.probe  = flexfb_probe_pdev,
-	.remove = flexfb_remove_pdev,
-};
-
-static int __init flexfb_init(void)
-{
-	int ret, ret2;
-
-	ret = spi_register_driver(&flexfb_spi_driver);
-	ret2 = platform_driver_register(&flexfb_platform_driver);
-	if (ret < 0)
-		return ret;
-	return ret2;
-}
-
-static void __exit flexfb_exit(void)
-{
-	spi_unregister_driver(&flexfb_spi_driver);
-	platform_driver_unregister(&flexfb_platform_driver);
-}
-
-/* ------------------------------------------------------------------------- */
-
-module_init(flexfb_init);
-module_exit(flexfb_exit);
-
-MODULE_DESCRIPTION("Generic FB driver for TFT LCD displays");
-MODULE_AUTHOR("Noralf Tronnes");
-MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 2eed19b99c8e95ff87afe6c140ed895c3fac5937 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Sat, 14 Sep 2019 17:24:05 +0200
Subject: staging: bcm2835-audio: Fix draining behavior regression

The PCM draining behavior got broken since the recent refactoring, and
this turned out to be the incorrect expectation of the firmware
behavior regarding "draining".  While I expected the "drain" flag at
the stop operation would do processing the queued samples, it seems
rather dropping the samples.

As a quick fix, just drop the SNDRV_PCM_INFO_DRAIN_TRIGGER flag, so
that the driver uses the normal PCM draining procedure.  Also, put
some caution comment to the function for future readers not to fall
into the same pitfall.

Fixes: d7ca3a71545b ("staging: bcm2835-audio: Operate non-atomic PCM ops")
BugLink: https://github.com/raspberrypi/linux/issues/2983
Cc: stable@vger.kernel.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Acked-by: Stefan Wahren <wahrenst@gmx.net>
Link: https://lore.kernel.org/r/20190914152405.7416-1-tiwai@suse.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vc04_services/bcm2835-audio/bcm2835-pcm.c   | 4 ++--
 drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/vc04_services/bcm2835-audio/bcm2835-pcm.c b/drivers/staging/vc04_services/bcm2835-audio/bcm2835-pcm.c
index bc1eaa3a0773..826016c3431a 100644
--- a/drivers/staging/vc04_services/bcm2835-audio/bcm2835-pcm.c
+++ b/drivers/staging/vc04_services/bcm2835-audio/bcm2835-pcm.c
@@ -12,7 +12,7 @@
 static const struct snd_pcm_hardware snd_bcm2835_playback_hw = {
 	.info = (SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_BLOCK_TRANSFER |
 		 SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_MMAP_VALID |
-		 SNDRV_PCM_INFO_DRAIN_TRIGGER | SNDRV_PCM_INFO_SYNC_APPLPTR),
+		 SNDRV_PCM_INFO_SYNC_APPLPTR),
 	.formats = SNDRV_PCM_FMTBIT_U8 | SNDRV_PCM_FMTBIT_S16_LE,
 	.rates = SNDRV_PCM_RATE_CONTINUOUS | SNDRV_PCM_RATE_8000_48000,
 	.rate_min = 8000,
@@ -29,7 +29,7 @@ static const struct snd_pcm_hardware snd_bcm2835_playback_hw = {
 static const struct snd_pcm_hardware snd_bcm2835_playback_spdif_hw = {
 	.info = (SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_BLOCK_TRANSFER |
 		 SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_MMAP_VALID |
-		 SNDRV_PCM_INFO_DRAIN_TRIGGER | SNDRV_PCM_INFO_SYNC_APPLPTR),
+		 SNDRV_PCM_INFO_SYNC_APPLPTR),
 	.formats = SNDRV_PCM_FMTBIT_S16_LE,
 	.rates = SNDRV_PCM_RATE_CONTINUOUS | SNDRV_PCM_RATE_44100 |
 	SNDRV_PCM_RATE_48000,
diff --git a/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c b/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c
index 23fba01107b9..c6f9cf1913d2 100644
--- a/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c
+++ b/drivers/staging/vc04_services/bcm2835-audio/bcm2835-vchiq.c
@@ -289,6 +289,7 @@ int bcm2835_audio_stop(struct bcm2835_alsa_stream *alsa_stream)
 					 VC_AUDIO_MSG_TYPE_STOP, false);
 }
 
+/* FIXME: this doesn't seem working as expected for "draining" */
 int bcm2835_audio_drain(struct bcm2835_alsa_stream *alsa_stream)
 {
 	struct vc_audio_msg m = {
-- 
cgit v1.2.3


From 955c1532a34305f2f780b47f0c40cc7c65500810 Mon Sep 17 00:00:00 2001
From: Connor Kuehl <connor.kuehl@canonical.com>
Date: Fri, 27 Sep 2019 14:44:15 -0700
Subject: staging: rtl8188eu: fix null dereference when kzalloc fails

If kzalloc() returns NULL, the error path doesn't stop the flow of
control from entering rtw_hal_read_chip_version() which dereferences the
null pointer. Fix this by adding a 'goto' to the error path to more
gracefully handle the issue and avoid proceeding with initialization
steps that we're no longer prepared to handle.

Also update the debug message to be more consistent with the other debug
messages in this function.

Addresses-Coverity: ("Dereference after null check")

Signed-off-by: Connor Kuehl <connor.kuehl@canonical.com>
Link: https://lore.kernel.org/r/20190927214415.899-1-connor.kuehl@canonical.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8188eu/os_dep/usb_intf.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
index 664d93a7f90d..4fac9dca798e 100644
--- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c
+++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
@@ -348,8 +348,10 @@ static struct adapter *rtw_usb_if1_init(struct dvobj_priv *dvobj,
 	}
 
 	padapter->HalData = kzalloc(sizeof(struct hal_data_8188e), GFP_KERNEL);
-	if (!padapter->HalData)
-		DBG_88E("cant not alloc memory for HAL DATA\n");
+	if (!padapter->HalData) {
+		DBG_88E("Failed to allocate memory for HAL data\n");
+		goto free_adapter;
+	}
 
 	/* step read_chip_version */
 	rtw_hal_read_chip_version(padapter);
-- 
cgit v1.2.3


From 22d67a01d8d89552b989c9651419824bb4111200 Mon Sep 17 00:00:00 2001
From: Denis Efremov <efremov@linux.com>
Date: Thu, 26 Sep 2019 10:31:38 +0300
Subject: staging: rtl8188eu: fix HighestRate check in odm_ARFBRefresh_8188E()

It's incorrect to compare HighestRate with 0x0b twice in the following
manner "if (HighestRate > 0x0b) ... else if (HighestRate > 0x0b) ...". The
"else if" branch is constantly false. The second comparision should be
with 0x03 according to the max_rate_idx in ODM_RAInfo_Init().

Cc: Michael Straube <straube.linux@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Denis Efremov <efremov@linux.com>
Acked-by: Larry Finger <Larry.Finger@lwfinger.net>
Link: https://lore.kernel.org/r/20190926073138.12109-1-efremov@linux.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/rtl8188eu/hal/hal8188e_rate_adaptive.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8188eu/hal/hal8188e_rate_adaptive.c b/drivers/staging/rtl8188eu/hal/hal8188e_rate_adaptive.c
index 9ddd51685063..5792f491b59a 100644
--- a/drivers/staging/rtl8188eu/hal/hal8188e_rate_adaptive.c
+++ b/drivers/staging/rtl8188eu/hal/hal8188e_rate_adaptive.c
@@ -409,7 +409,7 @@ static int odm_ARFBRefresh_8188E(struct odm_dm_struct *dm_odm, struct odm_ra_inf
 		pRaInfo->PTModeSS = 3;
 	else if (pRaInfo->HighestRate > 0x0b)
 		pRaInfo->PTModeSS = 2;
-	else if (pRaInfo->HighestRate > 0x0b)
+	else if (pRaInfo->HighestRate > 0x03)
 		pRaInfo->PTModeSS = 1;
 	else
 		pRaInfo->PTModeSS = 0;
-- 
cgit v1.2.3


From df359f0d09dc029829b66322707a2f558cb720f7 Mon Sep 17 00:00:00 2001
From: Ross Lagerwall <ross.lagerwall@citrix.com>
Date: Fri, 27 Sep 2019 16:49:20 +0100
Subject: xen/efi: Set nonblocking callbacks

Other parts of the kernel expect these nonblocking EFI callbacks to
exist and crash when running under Xen. Since the implementations of
xen_efi_set_variable() and xen_efi_query_variable_info() do not take any
locks, use them for the nonblocking callbacks too.

Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
---
 arch/arm/xen/efi.c | 2 ++
 arch/x86/xen/efi.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/arch/arm/xen/efi.c b/arch/arm/xen/efi.c
index d687a73044bf..cb2aaf98e243 100644
--- a/arch/arm/xen/efi.c
+++ b/arch/arm/xen/efi.c
@@ -19,7 +19,9 @@ void __init xen_efi_runtime_setup(void)
 	efi.get_variable             = xen_efi_get_variable;
 	efi.get_next_variable        = xen_efi_get_next_variable;
 	efi.set_variable             = xen_efi_set_variable;
+	efi.set_variable_nonblocking = xen_efi_set_variable;
 	efi.query_variable_info      = xen_efi_query_variable_info;
+	efi.query_variable_info_nonblocking = xen_efi_query_variable_info;
 	efi.update_capsule           = xen_efi_update_capsule;
 	efi.query_capsule_caps       = xen_efi_query_capsule_caps;
 	efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index 0d3365cb64de..7e3eb70f411a 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -65,7 +65,9 @@ static efi_system_table_t __init *xen_efi_probe(void)
 	efi.get_variable             = xen_efi_get_variable;
 	efi.get_next_variable        = xen_efi_get_next_variable;
 	efi.set_variable             = xen_efi_set_variable;
+	efi.set_variable_nonblocking = xen_efi_set_variable;
 	efi.query_variable_info      = xen_efi_query_variable_info;
+	efi.query_variable_info_nonblocking = xen_efi_query_variable_info;
 	efi.update_capsule           = xen_efi_update_capsule;
 	efi.query_capsule_caps       = xen_efi_query_capsule_caps;
 	efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
-- 
cgit v1.2.3


From 851345828095f1e40d383ec1a1e91767a2051976 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Mon, 23 Sep 2019 07:56:47 +0200
Subject: s390/cpumf: Use consistant debug print format

Use consistant debug print format of the form variable
blank value.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/perf_cpum_cf_diag.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index 5f1fd1581330..2654e348801a 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -390,7 +390,7 @@ static size_t cf_diag_getctrset(struct cf_ctrset_entry *ctrdata, int ctrset,
 
 	debug_sprintf_event(cf_diag_dbg, 6,
 			    "%s ctrset %d ctrset_size %zu cfvn %d csvn %d"
-			    " need %zd rc:%d\n",
+			    " need %zd rc %d\n",
 			    __func__, ctrset, ctrset_size, cpuhw->info.cfvn,
 			    cpuhw->info.csvn, need, rc);
 	return need;
@@ -567,7 +567,7 @@ static int cf_diag_add(struct perf_event *event, int flags)
 	int err = 0;
 
 	debug_sprintf_event(cf_diag_dbg, 5,
-			    "%s event %p cpu %d flags %#x cpuhw:%p\n",
+			    "%s event %p cpu %d flags %#x cpuhw %p\n",
 			    __func__, event, event->cpu, flags, cpuhw);
 
 	if (cpuhw->flags & PMU_F_IN_USE) {
-- 
cgit v1.2.3


From 932bfc5aae08f3cb20c1c9f051542f5933710151 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Fri, 20 Sep 2019 11:57:43 +0200
Subject: s390/cpumsf: Check for CPU Measurement sampling

s390 IBM z15 introduces a check if the CPU Mesurement Facility
sampling is temporarily unavailable. If this is the case return -EBUSY
and abort the setup of CPU Measuement facility sampling.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/cpu_mf.h  | 5 ++++-
 arch/s390/kernel/perf_cpum_sf.c | 6 ++++++
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index ceeb552d3472..753669bfbe99 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -28,6 +28,8 @@ asm(".include \"asm/cpu_mf-insn.h\"\n");
 				 CPU_MF_INT_SF_PRA|CPU_MF_INT_SF_SACA|	\
 				 CPU_MF_INT_SF_LSDA)
 
+#define CPU_MF_SF_RIBM_NOTAV	0x1		/* Sampling unavailable */
+
 /* CPU measurement facility support */
 static inline int cpum_cf_avail(void)
 {
@@ -69,7 +71,8 @@ struct hws_qsi_info_block {	    /* Bit(s) */
 	unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/
 	unsigned long tear;	    /* 24-31: TEAR contents		 */
 	unsigned long dear;	    /* 32-39: DEAR contents		 */
-	unsigned int rsvrd0;	    /* 40-43: reserved			 */
+	unsigned int rsvrd0:24;	    /* 40-42: reserved			 */
+	unsigned int ribm:8;	    /* 43: Reserved by IBM		 */
 	unsigned int cpu_speed;     /* 44-47: CPU speed			 */
 	unsigned long long rsvrd1;  /* 48-55: reserved			 */
 	unsigned long long rsvrd2;  /* 56-63: reserved			 */
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 544a02e944c6..2421f0b62630 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -803,6 +803,12 @@ static int __hw_perf_event_init(struct perf_event *event)
 		goto out;
 	}
 
+	if (si.ribm & CPU_MF_SF_RIBM_NOTAV) {
+		pr_warn("CPU Measurement Facility sampling is temporarily not available\n");
+		err = -EBUSY;
+		goto out;
+	}
+
 	/* Always enable basic sampling */
 	SAMPL_FLAGS(hwc) = PERF_CPUM_SF_BASIC_MODE;
 
-- 
cgit v1.2.3


From e14e59c125f6d81c08f2c598eb17ada3fc3ba21f Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 24 Sep 2019 09:31:13 +0200
Subject: s390/cpumf: Fix indentation in sampling device driver

Fix indentation in the s390 CPU Measuement Facility
sampling device dirver.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/perf_cpum_sf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 2421f0b62630..3d8b12a9a6ff 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -901,7 +901,7 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
 
 	/* Check online status of the CPU to which the event is pinned */
 	if (event->cpu >= 0 && !cpu_online(event->cpu))
-			return -ENODEV;
+		return -ENODEV;
 
 	/* Force reset of idle/hv excludes regardless of what the
 	 * user requested.
-- 
cgit v1.2.3


From 9f494438d4bc4746831cb5289b9836c18e4bbf96 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Fri, 20 Sep 2019 10:17:09 +0200
Subject: s390/qdio: clarify size of the QIB parm area

The QIB parm area is 128 bytes long. Current code consistently misuses
an _entirely unrelated_ QDIO constant, merely because it has the same
value. Stop doing so.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Reviewed-by: Benjamin Block <bblock@linux.ibm.com>
Reviewed-by: Jens Remus <jremus@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/qdio.h      | 2 +-
 drivers/s390/cio/qdio_setup.c     | 2 +-
 drivers/s390/net/qeth_core_main.c | 3 +--
 3 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index 78e8a888306d..e3f238e8c611 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -111,7 +111,7 @@ struct qib {
 	/* private: */
 	u8 res[88];
 	/* public: */
-	u8 parm[QDIO_MAX_BUFFERS_PER_Q];
+	u8 parm[128];
 } __attribute__ ((packed, aligned(256)));
 
 /**
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index f4ca1d29d61b..cd164886132f 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -113,7 +113,7 @@ static void set_impl_params(struct qdio_irq *irq_ptr,
 	irq_ptr->qib.pfmt = qib_param_field_format;
 	if (qib_param_field)
 		memcpy(irq_ptr->qib.parm, qib_param_field,
-		       QDIO_MAX_BUFFERS_PER_Q);
+		       sizeof(irq_ptr->qib.parm));
 
 	if (!input_slib_elements)
 		goto output;
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index a7868c8133ee..dda274351c21 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -4715,8 +4715,7 @@ static int qeth_qdio_establish(struct qeth_card *card)
 
 	QETH_CARD_TEXT(card, 2, "qdioest");
 
-	qib_param_field = kzalloc(QDIO_MAX_BUFFERS_PER_Q,
-				  GFP_KERNEL);
+	qib_param_field = kzalloc(FIELD_SIZEOF(struct qib, parm), GFP_KERNEL);
 	if (!qib_param_field) {
 		rc =  -ENOMEM;
 		goto out_free_nothing;
-- 
cgit v1.2.3


From e735244e2cf068f98b6384681a38993e0517a838 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Tue, 1 Oct 2019 11:44:53 +0200
Subject: gpiolib: don't clear FLAG_IS_OUT when emulating
 open-drain/open-source

When emulating open-drain/open-source by not actively driving the output
lines - we're simply changing their mode to input. This is wrong as it
will then make it impossible to change the value of such line - it's now
considered to actually be in input mode. If we want to still use the
direction_input() callback for simplicity then we need to set FLAG_IS_OUT
manually in gpiod_direction_output() and not clear it in
gpio_set_open_drain_value_commit() and
gpio_set_open_source_value_commit().

Fixes: c663e5f56737 ("gpio: support native single-ended hardware drivers")
Cc: stable@vger.kernel.org
Reported-by: Kent Gibson <warthog618@gmail.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 drivers/gpio/gpiolib.c | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index bdbc1649eafa..5833e4f380d6 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3070,8 +3070,10 @@ int gpiod_direction_output(struct gpio_desc *desc, int value)
 		if (!ret)
 			goto set_output_value;
 		/* Emulate open drain by not actively driving the line high */
-		if (value)
-			return gpiod_direction_input(desc);
+		if (value) {
+			ret = gpiod_direction_input(desc);
+			goto set_output_flag;
+		}
 	}
 	else if (test_bit(FLAG_OPEN_SOURCE, &desc->flags)) {
 		ret = gpio_set_config(gc, gpio_chip_hwgpio(desc),
@@ -3079,8 +3081,10 @@ int gpiod_direction_output(struct gpio_desc *desc, int value)
 		if (!ret)
 			goto set_output_value;
 		/* Emulate open source by not actively driving the line low */
-		if (!value)
-			return gpiod_direction_input(desc);
+		if (!value) {
+			ret = gpiod_direction_input(desc);
+			goto set_output_flag;
+		}
 	} else {
 		gpio_set_config(gc, gpio_chip_hwgpio(desc),
 				PIN_CONFIG_DRIVE_PUSH_PULL);
@@ -3088,6 +3092,17 @@ int gpiod_direction_output(struct gpio_desc *desc, int value)
 
 set_output_value:
 	return gpiod_direction_output_raw_commit(desc, value);
+
+set_output_flag:
+	/*
+	 * When emulating open-source or open-drain functionalities by not
+	 * actively driving the line (setting mode to input) we still need to
+	 * set the IS_OUT flag or otherwise we won't be able to set the line
+	 * value anymore.
+	 */
+	if (ret == 0)
+		set_bit(FLAG_IS_OUT, &desc->flags);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(gpiod_direction_output);
 
@@ -3448,8 +3463,6 @@ static void gpio_set_open_drain_value_commit(struct gpio_desc *desc, bool value)
 
 	if (value) {
 		ret = chip->direction_input(chip, offset);
-		if (!ret)
-			clear_bit(FLAG_IS_OUT, &desc->flags);
 	} else {
 		ret = chip->direction_output(chip, offset, 0);
 		if (!ret)
@@ -3479,8 +3492,6 @@ static void gpio_set_open_source_value_commit(struct gpio_desc *desc, bool value
 			set_bit(FLAG_IS_OUT, &desc->flags);
 	} else {
 		ret = chip->direction_input(chip, offset);
-		if (!ret)
-			clear_bit(FLAG_IS_OUT, &desc->flags);
 	}
 	trace_gpio_direction(desc_to_gpio(desc), !value, ret);
 	if (ret < 0)
-- 
cgit v1.2.3


From be7ae45cfea97e787234e00e1a9eb341acacd84e Mon Sep 17 00:00:00 2001
From: Marco Felsch <m.felsch@pengutronix.de>
Date: Tue, 1 Oct 2019 11:49:21 +0200
Subject: gpio: fix getting nonexclusive gpiods from DT

Since commit ec757001c818 ("gpio: Enable nonexclusive gpiods from DT
nodes") we are able to get GPIOD_FLAGS_BIT_NONEXCLUSIVE marked gpios.
Currently the gpiolib uses the wrong flags variable for the check. We
need to check the gpiod_flags instead of the of_gpio_flags else we
return -EBUSY for GPIOD_FLAGS_BIT_NONEXCLUSIVE marked and requested
gpiod's.

Fixes: ec757001c818 gpio: Enable nonexclusive gpiods from DT nodes
Cc: stable@vger.kernel.org
Signed-off-by: Marco Felsch <m.felsch@pengutronix.de>
[Bartosz: the function was moved to gpiolib-of.c so updated the patch]
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 drivers/gpio/gpiolib-of.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 1eea2c6c2e1d..80ea49f570f4 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -317,7 +317,7 @@ struct gpio_desc *gpiod_get_from_of_node(struct device_node *node,
 	transitory = flags & OF_GPIO_TRANSITORY;
 
 	ret = gpiod_request(desc, label);
-	if (ret == -EBUSY && (flags & GPIOD_FLAGS_BIT_NONEXCLUSIVE))
+	if (ret == -EBUSY && (dflags & GPIOD_FLAGS_BIT_NONEXCLUSIVE))
 		return desc;
 	if (ret)
 		return ERR_PTR(ret);
-- 
cgit v1.2.3


From e91aafcb51f3c5001ae76c3ee027beb0b8506447 Mon Sep 17 00:00:00 2001
From: Bruce Chen <bruce.chen@unisoc.com>
Date: Mon, 16 Sep 2019 17:56:56 +0800
Subject: gpio: eic: sprd: Fix the incorrect EIC offset when toggling

When toggling the level trigger to emulate the edge trigger, the
EIC offset is incorrect without adding the corresponding bank index,
thus fix it.

Fixes: 7bf0d7f62282 ("gpio: eic: Add edge trigger emulation for EIC")
Cc: stable@vger.kernel.org
Signed-off-by: Bruce Chen <bruce.chen@unisoc.com>
Signed-off-by: Baolin Wang <baolin.wang@linaro.org>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
---
 drivers/gpio/gpio-eic-sprd.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c
index fe7a73f52329..bb287f35cf40 100644
--- a/drivers/gpio/gpio-eic-sprd.c
+++ b/drivers/gpio/gpio-eic-sprd.c
@@ -530,11 +530,12 @@ static void sprd_eic_handle_one_type(struct gpio_chip *chip)
 		}
 
 		for_each_set_bit(n, &reg, SPRD_EIC_PER_BANK_NR) {
-			girq = irq_find_mapping(chip->irq.domain,
-					bank * SPRD_EIC_PER_BANK_NR + n);
+			u32 offset = bank * SPRD_EIC_PER_BANK_NR + n;
+
+			girq = irq_find_mapping(chip->irq.domain, offset);
 
 			generic_handle_irq(girq);
-			sprd_eic_toggle_trigger(chip, girq, n);
+			sprd_eic_toggle_trigger(chip, girq, offset);
 		}
 	}
 }
-- 
cgit v1.2.3


From f8db4d051b5eb8d6272b67d76cf79971d117a728 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 1 Oct 2019 11:35:18 +0100
Subject: drm/i915: Initialise breadcrumb lists on the virtual engine

With deferring the breadcrumb signalling to the virtual engine (thanks
preempt-to-busy) we need to make sure the lists and irq-worker are ready
to send a signal.

[41958.710544] BUG: kernel NULL pointer dereference, address: 0000000000000000
[41958.710553] #PF: supervisor write access in kernel mode
[41958.710556] #PF: error_code(0x0002) - not-present page
[41958.710558] PGD 0 P4D 0
[41958.710562] Oops: 0002 [#1] SMP
[41958.710565] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G     U            5.3.0+ #207
[41958.710568] Hardware name: Intel Corporation NUC7i5BNK/NUC7i5BNB, BIOS BNKBL357.86A.0052.2017.0918.1346 09/18/2017
[41958.710602] RIP: 0010:i915_request_enable_breadcrumb+0xe1/0x130 [i915]
[41958.710605] Code: 8b 44 24 30 48 89 41 08 48 89 08 48 8b 85 98 01 00 00 48 8d 8d 90 01 00 00 48 89 95 98 01 00 00 49 89 4c 24 28 49 89 44 24 30 <48> 89 10 f0 80 4b 30 10 c6 85 88 01 00 00 00 e9 1a ff ff ff 48 83
[41958.710609] RSP: 0018:ffffc90000003de0 EFLAGS: 00010046
[41958.710612] RAX: 0000000000000000 RBX: ffff888735424480 RCX: ffff8887cddb2190
[41958.710614] RDX: ffff8887cddb3570 RSI: ffff888850362190 RDI: ffff8887cddb2188
[41958.710617] RBP: ffff8887cddb2000 R08: ffff8888503624a8 R09: 0000000000000100
[41958.710619] R10: 0000000000000001 R11: 0000000000000000 R12: ffff8887cddb3548
[41958.710622] R13: 0000000000000000 R14: 0000000000000046 R15: ffff888850362070
[41958.710625] FS:  0000000000000000(0000) GS:ffff88885ea00000(0000) knlGS:0000000000000000
[41958.710628] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[41958.710630] CR2: 0000000000000000 CR3: 0000000002c09002 CR4: 00000000001606f0
[41958.710633] Call Trace:
[41958.710636]  <IRQ>
[41958.710668]  __i915_request_submit+0x12b/0x160 [i915]
[41958.710693]  virtual_submit_request+0x67/0x120 [i915]
[41958.710720]  __unwind_incomplete_requests+0x131/0x170 [i915]
[41958.710744]  execlists_dequeue+0xb40/0xe00 [i915]
[41958.710771]  execlists_submission_tasklet+0x10f/0x150 [i915]
[41958.710776]  tasklet_action_common.isra.17+0x41/0xa0
[41958.710781]  __do_softirq+0xc8/0x221
[41958.710785]  irq_exit+0xa6/0xb0
[41958.710788]  smp_apic_timer_interrupt+0x4d/0x80
[41958.710791]  apic_timer_interrupt+0xf/0x20
[41958.710794]  </IRQ>

Fixes: cb2377a919bb ("drm/i915: Fixup preempt-to-busy vs reset of a virtual request")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191001103518.9113-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index fa385218ce92..9877b6ba13df 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -4175,6 +4175,7 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 	snprintf(ve->base.name, sizeof(ve->base.name), "virtual");
 
 	intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
+	intel_engine_init_breadcrumbs(&ve->base);
 
 	intel_engine_init_execlists(&ve->base);
 
-- 
cgit v1.2.3


From 6db7bfb431220d78e34d2d0afdb7c12683323588 Mon Sep 17 00:00:00 2001
From: Liu Xiang <liuxiang_1999@126.com>
Date: Mon, 16 Sep 2019 21:53:00 +0800
Subject: iommu/arm-smmu: Free context bitmap in the err path of
 arm_smmu_init_domain_context

When alloc_io_pgtable_ops is failed, context bitmap which is just allocated
by __arm_smmu_alloc_bitmap should be freed to release the resource.

Signed-off-by: Liu Xiang <liuxiang_1999@126.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/arm-smmu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index b18aac4c105e..7c503a6bc585 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -812,6 +812,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	return 0;
 
 out_clear_smmu:
+	__arm_smmu_free_bitmap(smmu->context_map, cfg->cbndx);
 	smmu_domain->smmu = NULL;
 out_unlock:
 	mutex_unlock(&smmu_domain->init_mutex);
-- 
cgit v1.2.3


From 52f325f4eb321ea2e8a0779f49a3866be58bc694 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 30 Sep 2019 15:11:00 +0100
Subject: iommu/io-pgtable-arm: Correct Mali attributes

Whilst Midgard's MEMATTR follows a similar principle to the VMSA MAIR,
the actual attribute values differ, so although it currently appears to
work to some degree, we probably shouldn't be using our standard stage 1
MAIR for that. Instead, generate a reasonable MEMATTR with attribute
values borrowed from the kbase driver; at this point we'll be overriding
or ignoring pretty much all of the LPAE config, so just implement these
Mali details in a dedicated allocator instead of pretending to subclass
the standard VMSA format.

Fixes: d08d42de6432 ("iommu: io-pgtable: Add ARM Mali midgard MMU page table format")
Tested-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/io-pgtable-arm.c | 53 +++++++++++++++++++++++++++++++-----------
 1 file changed, 40 insertions(+), 13 deletions(-)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 4c91359057c5..90cb37af761c 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -166,6 +166,9 @@
 #define ARM_MALI_LPAE_TTBR_READ_INNER	BIT(2)
 #define ARM_MALI_LPAE_TTBR_SHARE_OUTER	BIT(4)
 
+#define ARM_MALI_LPAE_MEMATTR_IMP_DEF	0x88ULL
+#define ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC 0x8DULL
+
 /* IOPTE accessors */
 #define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d))
 
@@ -1015,27 +1018,51 @@ arm_32_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 static struct io_pgtable *
 arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 {
-	struct io_pgtable *iop;
+	struct arm_lpae_io_pgtable *data;
+
+	/* No quirks for Mali (hopefully) */
+	if (cfg->quirks)
+		return NULL;
 
 	if (cfg->ias != 48 || cfg->oas > 40)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
-	iop = arm_64_lpae_alloc_pgtable_s1(cfg, cookie);
-	if (iop) {
-		u64 mair, ttbr;
 
-		/* Copy values as union fields overlap */
-		mair = cfg->arm_lpae_s1_cfg.mair[0];
-		ttbr = cfg->arm_lpae_s1_cfg.ttbr[0];
+	data = arm_lpae_alloc_pgtable(cfg);
+	if (!data)
+		return NULL;
 
-		cfg->arm_mali_lpae_cfg.memattr = mair;
-		cfg->arm_mali_lpae_cfg.transtab = ttbr |
-			ARM_MALI_LPAE_TTBR_READ_INNER |
-			ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
-	}
+	/*
+	 * MEMATTR: Mali has no actual notion of a non-cacheable type, so the
+	 * best we can do is mimic the out-of-tree driver and hope that the
+	 * "implementation-defined caching policy" is good enough. Similarly,
+	 * we'll use it for the sake of a valid attribute for our 'device'
+	 * index, although callers should never request that in practice.
+	 */
+	cfg->arm_mali_lpae_cfg.memattr =
+		(ARM_MALI_LPAE_MEMATTR_IMP_DEF
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_NC)) |
+		(ARM_MALI_LPAE_MEMATTR_WRITE_ALLOC
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_CACHE)) |
+		(ARM_MALI_LPAE_MEMATTR_IMP_DEF
+		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
 
-	return iop;
+	data->pgd = __arm_lpae_alloc_pages(data->pgd_size, GFP_KERNEL, cfg);
+	if (!data->pgd)
+		goto out_free_data;
+
+	/* Ensure the empty pgd is visible before TRANSTAB can be written */
+	wmb();
+
+	cfg->arm_mali_lpae_cfg.transtab = virt_to_phys(data->pgd) |
+					  ARM_MALI_LPAE_TTBR_READ_INNER |
+					  ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
+	return &data->iop;
+
+out_free_data:
+	kfree(data);
+	return NULL;
 }
 
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {
-- 
cgit v1.2.3


From 1be08f458d1602275b02f5357ef069957058f3fd Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 30 Sep 2019 15:11:01 +0100
Subject: iommu/io-pgtable-arm: Support all Mali configurations

In principle, Midgard GPUs supporting smaller VA sizes should only
require 3-level pagetables, since level 0 only resolves bits 48:40 of
the address. However, the kbase driver does not appear to have any
notion of a variable start level, and empirically T720 and T820 rapidly
blow up with translation faults unless given a full 4-level table,
despite only supporting a 33-bit VA size.

The 'real' IAS value is still valuable in terms of validating addresses
on map/unmap, so tweak the allocator to allow smaller values while still
forcing the resultant tables to the full 4 levels. As far as I can test,
this should make all known Midgard variants happy.

Fixes: d08d42de6432 ("iommu: io-pgtable: Add ARM Mali midgard MMU page table format")
Tested-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/iommu/io-pgtable-arm.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 90cb37af761c..ca51036aa53c 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -1024,7 +1024,7 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 	if (cfg->quirks)
 		return NULL;
 
-	if (cfg->ias != 48 || cfg->oas > 40)
+	if (cfg->ias > 48 || cfg->oas > 40)
 		return NULL;
 
 	cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G);
@@ -1033,6 +1033,11 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 	if (!data)
 		return NULL;
 
+	/* Mali seems to need a full 4-level table regardless of IAS */
+	if (data->levels < ARM_LPAE_MAX_LEVELS) {
+		data->levels = ARM_LPAE_MAX_LEVELS;
+		data->pgd_size = sizeof(arm_lpae_iopte);
+	}
 	/*
 	 * MEMATTR: Mali has no actual notion of a non-cacheable type, so the
 	 * best we can do is mimic the out-of-tree driver and hope that the
-- 
cgit v1.2.3


From 99785b86eead0934dffc1b36f3e5820d0c87e69f Mon Sep 17 00:00:00 2001
From: Srinivasan S <srinivasan.s@intel.com>
Date: Wed, 25 Sep 2019 06:05:42 +0530
Subject: drm/i915/dp: Fix DP MST error after unplugging TypeC cable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch avoids DP MST payload error message in dmesg, as it is trying
to update the payload to the disconnected DP MST device. After DP MST
device is disconnected we should not be updating the payload and
hence remove the error.

v2: Removed the connector status check and converted from error to debug.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111632
Signed-off-by: Srinivasan S <srinivasan.s@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1569371742-109402-1-git-send-email-srinivasan.s@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp_mst.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index cf4d851a5139..df4f35c10a69 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -215,7 +215,7 @@ static void intel_mst_disable_dp(struct intel_encoder *encoder,
 
 	ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr);
 	if (ret) {
-		DRM_ERROR("failed to update payload %d\n", ret);
+		DRM_DEBUG_KMS("failed to update payload %d\n", ret);
 	}
 	if (old_crtc_state->has_audio)
 		intel_audio_codec_disable(encoder,
-- 
cgit v1.2.3


From 7a292b6c7c9c35afee01ce3b2248f705869d0ff1 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Mon, 23 Sep 2019 11:12:29 +0200
Subject: arm64: errata: Update stale comment

Commit 73f381660959 ("arm64: Advertise mitigation of Spectre-v2, or lack
thereof") renamed the caller of the install_bp_hardening_cb() function
but forgot to update a comment, which can be confusing when trying to
follow the code flow.

Fixes: 73f381660959 ("arm64: Advertise mitigation of Spectre-v2, or lack thereof")
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/cpu_errata.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 1e43ba5c79b7..f593f4cffc0d 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -128,8 +128,8 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 	int cpu, slot = -1;
 
 	/*
-	 * enable_smccc_arch_workaround_1() passes NULL for the hyp_vecs
-	 * start/end if we're a guest. Skip the hyp-vectors work.
+	 * detect_harden_bp_fw() passes NULL for the hyp_vecs start/end if
+	 * we're a guest. Skip the hyp-vectors work.
 	 */
 	if (!hyp_vecs_start) {
 		__this_cpu_write(bp_hardening_data.fn, fn);
-- 
cgit v1.2.3


From 4585fc59c0e813188d6a4c5de1f6976fce461fc2 Mon Sep 17 00:00:00 2001
From: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Date: Mon, 30 Sep 2019 16:56:00 -0400
Subject: arm64/sve: Fix wrong free for task->thread.sve_state

The system which has SVE feature crashed because of
the memory pointed by task->thread.sve_state was destroyed
by someone.

That is because sve_state is freed while the forking the
child process. The child process has the pointer of sve_state
which is same as the parent's because the child's task_struct
is copied from the parent's one. If the copy_process()
fails as an error on somewhere, for example, copy_creds(),
then the sve_state is freed even if the parent is alive.
The flow is as follows.

copy_process
        p = dup_task_struct
            => arch_dup_task_struct
                *dst = *src;  // copy the entire region.
:
        retval = copy_creds
        if (retval < 0)
                goto bad_fork_free;
:
bad_fork_free:
...
        delayed_free_task(p);
          => free_task
             => arch_release_task_struct
                => fpsimd_release_task
                   => __sve_free
                      => kfree(task->thread.sve_state);
                         // free the parent's sve_state

Move child's sve_state = NULL and clearing TIF_SVE flag
to arch_dup_task_struct() so that the child doesn't free the
parent's one.
There is no need to wait until copy_process() to clear TIF_SVE for
dst, because the thread flags for dst are initialized already by
copying the src task_struct.
This change simplifies the code, so get rid of comments that are no
longer needed.

As a note, arm64 used to have thread_info on the stack. So it
would not be possible to clear TIF_SVE until the stack is initialized.
From commit c02433dd6de3 ("arm64: split thread_info from task stack"),
the thread_info is part of the task, so it should be valid to modify
the flag from arch_dup_task_struct().

Cc: stable@vger.kernel.org # 4.15.x-
Fixes: bc0ee4760364 ("arm64/sve: Core task context handling")
Signed-off-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Reported-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Suggested-by: Dave Martin <Dave.Martin@arm.com>
Reviewed-by: Dave Martin <Dave.Martin@arm.com>
Tested-by: Julien Grall <julien.grall@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/process.c | 32 +++++++++++++++-----------------
 1 file changed, 15 insertions(+), 17 deletions(-)

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index a47462def04b..1fb2819fc048 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -332,22 +332,27 @@ void arch_release_task_struct(struct task_struct *tsk)
 	fpsimd_release_task(tsk);
 }
 
-/*
- * src and dst may temporarily have aliased sve_state after task_struct
- * is copied.  We cannot fix this properly here, because src may have
- * live SVE state and dst's thread_info may not exist yet, so tweaking
- * either src's or dst's TIF_SVE is not safe.
- *
- * The unaliasing is done in copy_thread() instead.  This works because
- * dst is not schedulable or traceable until both of these functions
- * have been called.
- */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	if (current->mm)
 		fpsimd_preserve_current_state();
 	*dst = *src;
 
+	/* We rely on the above assignment to initialize dst's thread_flags: */
+	BUILD_BUG_ON(!IS_ENABLED(CONFIG_THREAD_INFO_IN_TASK));
+
+	/*
+	 * Detach src's sve_state (if any) from dst so that it does not
+	 * get erroneously used or freed prematurely.  dst's sve_state
+	 * will be allocated on demand later on if dst uses SVE.
+	 * For consistency, also clear TIF_SVE here: this could be done
+	 * later in copy_process(), but to avoid tripping up future
+	 * maintainers it is best not to leave TIF_SVE and sve_state in
+	 * an inconsistent state, even temporarily.
+	 */
+	dst->thread.sve_state = NULL;
+	clear_tsk_thread_flag(dst, TIF_SVE);
+
 	return 0;
 }
 
@@ -360,13 +365,6 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
 
-	/*
-	 * Unalias p->thread.sve_state (if any) from the parent task
-	 * and disable discard SVE state for p:
-	 */
-	clear_tsk_thread_flag(p, TIF_SVE);
-	p->thread.sve_state = NULL;
-
 	/*
 	 * In case p was allocated the same task_struct pointer as some
 	 * other recently-exited task, make sure p is disassociated from
-- 
cgit v1.2.3


From a2b99dcac36c332d4a49184716fc2a67dc1bdbb1 Mon Sep 17 00:00:00 2001
From: Adam Zerella <adam.zerella@gmail.com>
Date: Sat, 28 Sep 2019 22:58:19 +1000
Subject: docs: arm64: Fix indentation and doc formatting

Sphinx generates the following warnings for the arm64 doc
pages:

Documentation/arm64/memory.rst:158: WARNING: Unexpected indentation.
Documentation/arm64/memory.rst:162: WARNING: Unexpected indentation.

These indentations warnings can be resolved by utilising code
hightlighting instead.

Signed-off-by: Adam Zerella <adam.zerella@gmail.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 Documentation/arm64/memory.rst | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/Documentation/arm64/memory.rst b/Documentation/arm64/memory.rst
index b040909e45f8..02e02175e6f5 100644
--- a/Documentation/arm64/memory.rst
+++ b/Documentation/arm64/memory.rst
@@ -154,11 +154,18 @@ return virtual addresses to userspace from a 48-bit range.
 
 Software can "opt-in" to receiving VAs from a 52-bit space by
 specifying an mmap hint parameter that is larger than 48-bit.
+
 For example:
-    maybe_high_address = mmap(~0UL, size, prot, flags,...);
+
+.. code-block:: c
+
+   maybe_high_address = mmap(~0UL, size, prot, flags,...);
 
 It is also possible to build a debug kernel that returns addresses
 from a 52-bit space by enabling the following kernel config options:
+
+.. code-block:: sh
+
    CONFIG_EXPERT=y && CONFIG_ARM64_FORCE_52BIT=y
 
 Note that this option is only intended for debugging applications
-- 
cgit v1.2.3


From 3aa6d4abd4ebf07c36e0a9a507af0311fcb267dc Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Tue, 17 Sep 2019 09:50:00 +0100
Subject: crypto: arm/aes-ce - build for v8 architecture explicitly

The NEON/Crypto Extensions based AES implementation for 32-bit ARM
can be built in a kernel that targets ARMv6 CPUs and higher, even
though the actual code will not be able to run on that generation,
but it allows for a portable image to be generated that can will
use the special instructions only when they are available.

Since those instructions are part of a FPU profile rather than a
CPU profile, we don't override the architecture in the assembler
code, and most of the scalar code is simple enough to be ARMv6
compatible. However, that changes with commit c61b1607ed4fbbf2,
which introduces calls to the movw/movt instructions, which are
v7+ only.

So override the architecture in the .S file to armv8-a, which
matches the architecture specification in the crypto-neon-fp-armv8
FPU specificier that we already using. Note that using armv7-a
here may trigger an issue with the upcoming Clang 10 release,
which no longer permits .arch/.fpu combinations it views as
incompatible.

Reported-by: kbuild test robot <lkp@intel.com>
Fixes: c61b1607ed4fbbf2 ("crypto: arm/aes-ce - implement ciphertext stealing ...")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm/crypto/aes-ce-core.S | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/crypto/aes-ce-core.S b/arch/arm/crypto/aes-ce-core.S
index b978cdf133af..4d1707388d94 100644
--- a/arch/arm/crypto/aes-ce-core.S
+++ b/arch/arm/crypto/aes-ce-core.S
@@ -9,6 +9,7 @@
 #include <asm/assembler.h>
 
 	.text
+	.arch		armv8-a
 	.fpu		crypto-neon-fp-armv8
 	.align		3
 
-- 
cgit v1.2.3


From f703964fc66804e6049f2670fc11045aa8359b1a Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Tue, 17 Sep 2019 09:50:01 +0100
Subject: crypto: arm/aes-ce - add dependency on AES library

The ARM accelerated AES driver depends on the new AES library for
its non-SIMD fallback so express this in its Kconfig declaration.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm/crypto/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index b24df84a1d7a..043b0b18bf7e 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -98,6 +98,7 @@ config CRYPTO_AES_ARM_CE
 	tristate "Accelerated AES using ARMv8 Crypto Extensions"
 	depends on KERNEL_MODE_NEON
 	select CRYPTO_BLKCIPHER
+	select CRYPTO_LIB_AES
 	select CRYPTO_SIMD
 	help
 	  Use an implementation of AES in CBC, CTR and XTS modes that uses
-- 
cgit v1.2.3


From e1fba49cc1e965a3dacd897367ba1e7b340cf0f4 Mon Sep 17 00:00:00 2001
From: Jim Mattson <jmattson@google.com>
Date: Mon, 30 Sep 2019 16:38:54 -0700
Subject: kvm: vmx: Limit guest PMCs to those supported on the host

KVM can only virtualize as many PMCs as the host supports.

Limit the number of generic counters and fixed counters to the number
of corresponding counters supported on the host, rather than to
INTEL_PMC_MAX_GENERIC and INTEL_PMC_MAX_FIXED, respectively.

Note that INTEL_PMC_MAX_GENERIC is currently 32, which exceeds the 18
contiguous MSR indices reserved by Intel for event selectors. Since
the existing code relies on a contiguous range of MSR indices for
event selectors, it can't possibly work for more than 18 general
purpose counters.

Fixes: f5132b01386b5a ("KVM: Expose a version 2 architectural PMU to a guests")
Signed-off-by: Jim Mattson <jmattson@google.com>
Reviewed-by: Marc Orr <marcorr@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/pmu_intel.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 4dea0e0e7e39..3e9c059099e9 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -262,6 +262,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct x86_pmu_capability x86_pmu;
 	struct kvm_cpuid_entry2 *entry;
 	union cpuid10_eax eax;
 	union cpuid10_edx edx;
@@ -283,8 +284,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	if (!pmu->version)
 		return;
 
+	perf_get_x86_pmu_capability(&x86_pmu);
+
 	pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
-					INTEL_PMC_MAX_GENERIC);
+					 x86_pmu.num_counters_gp);
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
 	pmu->available_event_types = ~entry->ebx &
 					((1ull << eax.split.mask_length) - 1);
@@ -294,7 +297,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	} else {
 		pmu->nr_arch_fixed_counters =
 			min_t(int, edx.split.num_counters_fixed,
-				INTEL_PMC_MAX_FIXED);
+			      x86_pmu.num_counters_fixed);
 		pmu->counter_bitmask[KVM_PMC_FIXED] =
 			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}
-- 
cgit v1.2.3


From f5a1a536fa14895ccff4e94e6a5af90901ce86aa Mon Sep 17 00:00:00 2001
From: Aleksa Sarai <cyphar@cyphar.com>
Date: Tue, 1 Oct 2019 11:10:52 +1000
Subject: lib: introduce copy_struct_from_user() helper

A common pattern for syscall extensions is increasing the size of a
struct passed from userspace, such that the zero-value of the new fields
result in the old kernel behaviour (allowing for a mix of userspace and
kernel vintages to operate on one another in most cases).

While this interface exists for communication in both directions, only
one interface is straightforward to have reasonable semantics for
(userspace passing a struct to the kernel). For kernel returns to
userspace, what the correct semantics are (whether there should be an
error if userspace is unaware of a new extension) is very
syscall-dependent and thus probably cannot be unified between syscalls
(a good example of this problem is [1]).

Previously there was no common lib/ function that implemented
the necessary extension-checking semantics (and different syscalls
implemented them slightly differently or incompletely[2]). Future
patches replace common uses of this pattern to make use of
copy_struct_from_user().

Some in-kernel selftests that insure that the handling of alignment and
various byte patterns are all handled identically to memchr_inv() usage.

[1]: commit 1251201c0d34 ("sched/core: Fix uclamp ABI bug, clean up and
     robustify sched_read_attr() ABI logic and code")

[2]: For instance {sched_setattr,perf_event_open,clone3}(2) all do do
     similar checks to copy_struct_from_user() while rt_sigprocmask(2)
     always rejects differently-sized struct arguments.

Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20191001011055.19283-2-cyphar@cyphar.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/linux/bitops.h  |   7 +++
 include/linux/uaccess.h |  70 +++++++++++++++++++++++++
 lib/strnlen_user.c      |   8 +--
 lib/test_user_copy.c    | 136 +++++++++++++++++++++++++++++++++++++++++++++---
 lib/usercopy.c          |  55 ++++++++++++++++++++
 5 files changed, 263 insertions(+), 13 deletions(-)

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index cf074bce3eb3..c94a9ff9f082 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -4,6 +4,13 @@
 #include <asm/types.h>
 #include <linux/bits.h>
 
+/* Set bits in the first 'n' bytes when loaded from memory */
+#ifdef __LITTLE_ENDIAN
+#  define aligned_byte_mask(n) ((1UL << 8*(n))-1)
+#else
+#  define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n)))
+#endif
+
 #define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
 
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 70bbdc38dc37..e47d0522a1f4 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -231,6 +231,76 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from,
 
 #endif		/* ARCH_HAS_NOCACHE_UACCESS */
 
+extern __must_check int check_zeroed_user(const void __user *from, size_t size);
+
+/**
+ * copy_struct_from_user: copy a struct from userspace
+ * @dst:   Destination address, in kernel space. This buffer must be @ksize
+ *         bytes long.
+ * @ksize: Size of @dst struct.
+ * @src:   Source address, in userspace.
+ * @usize: (Alleged) size of @src struct.
+ *
+ * Copies a struct from userspace to kernel space, in a way that guarantees
+ * backwards-compatibility for struct syscall arguments (as long as future
+ * struct extensions are made such that all new fields are *appended* to the
+ * old struct, and zeroed-out new fields have the same meaning as the old
+ * struct).
+ *
+ * @ksize is just sizeof(*dst), and @usize should've been passed by userspace.
+ * The recommended usage is something like the following:
+ *
+ *   SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize)
+ *   {
+ *      int err;
+ *      struct foo karg = {};
+ *
+ *      if (usize > PAGE_SIZE)
+ *        return -E2BIG;
+ *      if (usize < FOO_SIZE_VER0)
+ *        return -EINVAL;
+ *
+ *      err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize);
+ *      if (err)
+ *        return err;
+ *
+ *      // ...
+ *   }
+ *
+ * There are three cases to consider:
+ *  * If @usize == @ksize, then it's copied verbatim.
+ *  * If @usize < @ksize, then the userspace has passed an old struct to a
+ *    newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize)
+ *    are to be zero-filled.
+ *  * If @usize > @ksize, then the userspace has passed a new struct to an
+ *    older kernel. The trailing bytes unknown to the kernel (@usize - @ksize)
+ *    are checked to ensure they are zeroed, otherwise -E2BIG is returned.
+ *
+ * Returns (in all cases, some data may have been copied):
+ *  * -E2BIG:  (@usize > @ksize) and there are non-zero trailing bytes in @src.
+ *  * -EFAULT: access to userspace failed.
+ */
+static __always_inline __must_check int
+copy_struct_from_user(void *dst, size_t ksize, const void __user *src,
+		      size_t usize)
+{
+	size_t size = min(ksize, usize);
+	size_t rest = max(ksize, usize) - size;
+
+	/* Deal with trailing bytes. */
+	if (usize < ksize) {
+		memset(dst + size, 0, rest);
+	} else if (usize > ksize) {
+		int ret = check_zeroed_user(src + size, rest);
+		if (ret <= 0)
+			return ret ?: -E2BIG;
+	}
+	/* Copy the interoperable parts of the struct. */
+	if (copy_from_user(dst, src, size))
+		return -EFAULT;
+	return 0;
+}
+
 /*
  * probe_kernel_read(): safely attempt to read from a location
  * @dst: pointer to the buffer that shall take the data
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
index 28ff554a1be8..6c0005d5dd5c 100644
--- a/lib/strnlen_user.c
+++ b/lib/strnlen_user.c
@@ -3,16 +3,10 @@
 #include <linux/export.h>
 #include <linux/uaccess.h>
 #include <linux/mm.h>
+#include <linux/bitops.h>
 
 #include <asm/word-at-a-time.h>
 
-/* Set bits in the first 'n' bytes when loaded from memory */
-#ifdef __LITTLE_ENDIAN
-#  define aligned_byte_mask(n) ((1ul << 8*(n))-1)
-#else
-#  define aligned_byte_mask(n) (~0xfful << (BITS_PER_LONG - 8 - 8*(n)))
-#endif
-
 /*
  * Do a strnlen, return length of string *with* final '\0'.
  * 'count' is the user-supplied count, while 'max' is the
diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c
index 67bcd5dfd847..950ee88cd6ac 100644
--- a/lib/test_user_copy.c
+++ b/lib/test_user_copy.c
@@ -31,14 +31,133 @@
 # define TEST_U64
 #endif
 
-#define test(condition, msg)		\
-({					\
-	int cond = (condition);		\
-	if (cond)			\
-		pr_warn("%s\n", msg);	\
-	cond;				\
+#define test(condition, msg, ...)					\
+({									\
+	int cond = (condition);						\
+	if (cond)							\
+		pr_warn("[%d] " msg "\n", __LINE__, ##__VA_ARGS__);	\
+	cond;								\
 })
 
+static bool is_zeroed(void *from, size_t size)
+{
+	return memchr_inv(from, 0x0, size) == NULL;
+}
+
+static int test_check_nonzero_user(char *kmem, char __user *umem, size_t size)
+{
+	int ret = 0;
+	size_t start, end, i;
+	size_t zero_start = size / 4;
+	size_t zero_end = size - zero_start;
+
+	/*
+	 * We conduct a series of check_nonzero_user() tests on a block of memory
+	 * with the following byte-pattern (trying every possible [start,end]
+	 * pair):
+	 *
+	 *   [ 00 ff 00 ff ... 00 00 00 00 ... ff 00 ff 00 ]
+	 *
+	 * And we verify that check_nonzero_user() acts identically to memchr_inv().
+	 */
+
+	memset(kmem, 0x0, size);
+	for (i = 1; i < zero_start; i += 2)
+		kmem[i] = 0xff;
+	for (i = zero_end; i < size; i += 2)
+		kmem[i] = 0xff;
+
+	ret |= test(copy_to_user(umem, kmem, size),
+		    "legitimate copy_to_user failed");
+
+	for (start = 0; start <= size; start++) {
+		for (end = start; end <= size; end++) {
+			size_t len = end - start;
+			int retval = check_zeroed_user(umem + start, len);
+			int expected = is_zeroed(kmem + start, len);
+
+			ret |= test(retval != expected,
+				    "check_nonzero_user(=%d) != memchr_inv(=%d) mismatch (start=%zu, end=%zu)",
+				    retval, expected, start, end);
+		}
+	}
+
+	return ret;
+}
+
+static int test_copy_struct_from_user(char *kmem, char __user *umem,
+				      size_t size)
+{
+	int ret = 0;
+	char *umem_src = NULL, *expected = NULL;
+	size_t ksize, usize;
+
+	umem_src = kmalloc(size, GFP_KERNEL);
+	if (ret |= test(umem_src == NULL, "kmalloc failed"))
+		goto out_free;
+
+	expected = kmalloc(size, GFP_KERNEL);
+	if (ret |= test(expected == NULL, "kmalloc failed"))
+		goto out_free;
+
+	/* Fill umem with a fixed byte pattern. */
+	memset(umem_src, 0x3e, size);
+	ret |= test(copy_to_user(umem, umem_src, size),
+		    "legitimate copy_to_user failed");
+
+	/* Check basic case -- (usize == ksize). */
+	ksize = size;
+	usize = size;
+
+	memcpy(expected, umem_src, ksize);
+
+	memset(kmem, 0x0, size);
+	ret |= test(copy_struct_from_user(kmem, ksize, umem, usize),
+		    "copy_struct_from_user(usize == ksize) failed");
+	ret |= test(memcmp(kmem, expected, ksize),
+		    "copy_struct_from_user(usize == ksize) gives unexpected copy");
+
+	/* Old userspace case -- (usize < ksize). */
+	ksize = size;
+	usize = size / 2;
+
+	memcpy(expected, umem_src, usize);
+	memset(expected + usize, 0x0, ksize - usize);
+
+	memset(kmem, 0x0, size);
+	ret |= test(copy_struct_from_user(kmem, ksize, umem, usize),
+		    "copy_struct_from_user(usize < ksize) failed");
+	ret |= test(memcmp(kmem, expected, ksize),
+		    "copy_struct_from_user(usize < ksize) gives unexpected copy");
+
+	/* New userspace (-E2BIG) case -- (usize > ksize). */
+	ksize = size / 2;
+	usize = size;
+
+	memset(kmem, 0x0, size);
+	ret |= test(copy_struct_from_user(kmem, ksize, umem, usize) != -E2BIG,
+		    "copy_struct_from_user(usize > ksize) didn't give E2BIG");
+
+	/* New userspace (success) case -- (usize > ksize). */
+	ksize = size / 2;
+	usize = size;
+
+	memcpy(expected, umem_src, ksize);
+	ret |= test(clear_user(umem + ksize, usize - ksize),
+		    "legitimate clear_user failed");
+
+	memset(kmem, 0x0, size);
+	ret |= test(copy_struct_from_user(kmem, ksize, umem, usize),
+		    "copy_struct_from_user(usize > ksize) failed");
+	ret |= test(memcmp(kmem, expected, ksize),
+		    "copy_struct_from_user(usize > ksize) gives unexpected copy");
+
+out_free:
+	kfree(expected);
+	kfree(umem_src);
+	return ret;
+}
+
 static int __init test_user_copy_init(void)
 {
 	int ret = 0;
@@ -106,6 +225,11 @@ static int __init test_user_copy_init(void)
 #endif
 #undef test_legit
 
+	/* Test usage of check_nonzero_user(). */
+	ret |= test_check_nonzero_user(kmem, usermem, 2 * PAGE_SIZE);
+	/* Test usage of copy_struct_from_user(). */
+	ret |= test_copy_struct_from_user(kmem, usermem, 2 * PAGE_SIZE);
+
 	/*
 	 * Invalid usage: none of these copies should succeed.
 	 */
diff --git a/lib/usercopy.c b/lib/usercopy.c
index c2bfbcaeb3dc..cbb4d9ec00f2 100644
--- a/lib/usercopy.c
+++ b/lib/usercopy.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/uaccess.h>
+#include <linux/bitops.h>
 
 /* out-of-line parts */
 
@@ -31,3 +32,57 @@ unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n)
 }
 EXPORT_SYMBOL(_copy_to_user);
 #endif
+
+/**
+ * check_zeroed_user: check if a userspace buffer only contains zero bytes
+ * @from: Source address, in userspace.
+ * @size: Size of buffer.
+ *
+ * This is effectively shorthand for "memchr_inv(from, 0, size) == NULL" for
+ * userspace addresses (and is more efficient because we don't care where the
+ * first non-zero byte is).
+ *
+ * Returns:
+ *  * 0: There were non-zero bytes present in the buffer.
+ *  * 1: The buffer was full of zero bytes.
+ *  * -EFAULT: access to userspace failed.
+ */
+int check_zeroed_user(const void __user *from, size_t size)
+{
+	unsigned long val;
+	uintptr_t align = (uintptr_t) from % sizeof(unsigned long);
+
+	if (unlikely(size == 0))
+		return 1;
+
+	from -= align;
+	size += align;
+
+	if (!user_access_begin(from, size))
+		return -EFAULT;
+
+	unsafe_get_user(val, (unsigned long __user *) from, err_fault);
+	if (align)
+		val &= ~aligned_byte_mask(align);
+
+	while (size > sizeof(unsigned long)) {
+		if (unlikely(val))
+			goto done;
+
+		from += sizeof(unsigned long);
+		size -= sizeof(unsigned long);
+
+		unsafe_get_user(val, (unsigned long __user *) from, err_fault);
+	}
+
+	if (size < sizeof(unsigned long))
+		val &= aligned_byte_mask(size);
+
+done:
+	user_access_end();
+	return (val == 0);
+err_fault:
+	user_access_end();
+	return -EFAULT;
+}
+EXPORT_SYMBOL(check_zeroed_user);
-- 
cgit v1.2.3


From f14c234b4bc5184fd40d9a47830e5b32c3b36d49 Mon Sep 17 00:00:00 2001
From: Aleksa Sarai <cyphar@cyphar.com>
Date: Tue, 1 Oct 2019 11:10:53 +1000
Subject: clone3: switch to copy_struct_from_user()

Switch clone3() syscall from it's own copying struct clone_args from
userspace to the new dedicated copy_struct_from_user() helper.

The change is very straightforward, and helps unify the syscall
interface for struct-from-userspace syscalls. Additionally, explicitly
define CLONE_ARGS_SIZE_VER0 to match the other users of the
struct-extension pattern.

Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
[christian.brauner@ubuntu.com: improve commit message]
Link: https://lore.kernel.org/r/20191001011055.19283-3-cyphar@cyphar.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/uapi/linux/sched.h |  2 ++
 kernel/fork.c              | 34 +++++++---------------------------
 2 files changed, 9 insertions(+), 27 deletions(-)

diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index b3105ac1381a..0945805982b4 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -47,6 +47,8 @@ struct clone_args {
 	__aligned_u64 tls;
 };
 
+#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
+
 /*
  * Scheduling policies
  */
diff --git a/kernel/fork.c b/kernel/fork.c
index f9572f416126..2ef529869c64 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2525,39 +2525,19 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 #ifdef __ARCH_WANT_SYS_CLONE3
 noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 					      struct clone_args __user *uargs,
-					      size_t size)
+					      size_t usize)
 {
+	int err;
 	struct clone_args args;
 
-	if (unlikely(size > PAGE_SIZE))
+	if (unlikely(usize > PAGE_SIZE))
 		return -E2BIG;
-
-	if (unlikely(size < sizeof(struct clone_args)))
+	if (unlikely(usize < CLONE_ARGS_SIZE_VER0))
 		return -EINVAL;
 
-	if (unlikely(!access_ok(uargs, size)))
-		return -EFAULT;
-
-	if (size > sizeof(struct clone_args)) {
-		unsigned char __user *addr;
-		unsigned char __user *end;
-		unsigned char val;
-
-		addr = (void __user *)uargs + sizeof(struct clone_args);
-		end = (void __user *)uargs + size;
-
-		for (; addr < end; addr++) {
-			if (get_user(val, addr))
-				return -EFAULT;
-			if (val)
-				return -E2BIG;
-		}
-
-		size = sizeof(struct clone_args);
-	}
-
-	if (copy_from_user(&args, uargs, size))
-		return -EFAULT;
+	err = copy_struct_from_user(&args, sizeof(args), uargs, usize);
+	if (err)
+		return err;
 
 	/*
 	 * Verify that higher 32bits of exit_signal are unset and that
-- 
cgit v1.2.3


From dff3a85feceade213daf153556fd32a3b0a73c63 Mon Sep 17 00:00:00 2001
From: Aleksa Sarai <cyphar@cyphar.com>
Date: Tue, 1 Oct 2019 11:10:54 +1000
Subject: sched_setattr: switch to copy_struct_from_user()

Switch sched_setattr() syscall from it's own copying struct sched_attr
from userspace to the new dedicated copy_struct_from_user() helper.

The change is very straightforward, and helps unify the syscall
interface for struct-from-userspace syscalls. Ideally we could also
unify sched_getattr(2)-style syscalls as well, but unfortunately the
correct semantics for such syscalls are much less clear (see [1] for
more detail). In future we could come up with a more sane idea for how
the syscall interface should look.

[1]: commit 1251201c0d34 ("sched/core: Fix uclamp ABI bug, clean up and
     robustify sched_read_attr() ABI logic and code")

Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
[christian.brauner@ubuntu.com: improve commit message]
Link: https://lore.kernel.org/r/20191001011055.19283-4-cyphar@cyphar.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 kernel/sched/core.c | 43 +++++++------------------------------------
 1 file changed, 7 insertions(+), 36 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7880f4f64d0e..dd05a378631a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5106,9 +5106,6 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
 	u32 size;
 	int ret;
 
-	if (!access_ok(uattr, SCHED_ATTR_SIZE_VER0))
-		return -EFAULT;
-
 	/* Zero the full structure, so that a short copy will be nice: */
 	memset(attr, 0, sizeof(*attr));
 
@@ -5116,45 +5113,19 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
 	if (ret)
 		return ret;
 
-	/* Bail out on silly large: */
-	if (size > PAGE_SIZE)
-		goto err_size;
-
 	/* ABI compatibility quirk: */
 	if (!size)
 		size = SCHED_ATTR_SIZE_VER0;
-
-	if (size < SCHED_ATTR_SIZE_VER0)
+	if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE)
 		goto err_size;
 
-	/*
-	 * If we're handed a bigger struct than we know of,
-	 * ensure all the unknown bits are 0 - i.e. new
-	 * user-space does not rely on any kernel feature
-	 * extensions we dont know about yet.
-	 */
-	if (size > sizeof(*attr)) {
-		unsigned char __user *addr;
-		unsigned char __user *end;
-		unsigned char val;
-
-		addr = (void __user *)uattr + sizeof(*attr);
-		end  = (void __user *)uattr + size;
-
-		for (; addr < end; addr++) {
-			ret = get_user(val, addr);
-			if (ret)
-				return ret;
-			if (val)
-				goto err_size;
-		}
-		size = sizeof(*attr);
+	ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
+	if (ret) {
+		if (ret == -E2BIG)
+			goto err_size;
+		return ret;
 	}
 
-	ret = copy_from_user(attr, uattr, size);
-	if (ret)
-		return -EFAULT;
-
 	if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) &&
 	    size < SCHED_ATTR_SIZE_VER1)
 		return -EINVAL;
@@ -5354,7 +5325,7 @@ sched_attr_copy_to_user(struct sched_attr __user *uattr,
  * sys_sched_getattr - similar to sched_getparam, but with sched_attr
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
- * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility.
+ * @usize: sizeof(attr) for fwd/bwd comp.
  * @flags: for future extension.
  */
 SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
-- 
cgit v1.2.3


From c2ba8f41ad366dc12840dd87d8f1565185845126 Mon Sep 17 00:00:00 2001
From: Aleksa Sarai <cyphar@cyphar.com>
Date: Tue, 1 Oct 2019 11:10:55 +1000
Subject: perf_event_open: switch to copy_struct_from_user()

Switch perf_event_open() syscall from it's own copying
struct perf_event_attr from userspace to the new dedicated
copy_struct_from_user() helper.

The change is very straightforward, and helps unify the syscall
interface for struct-from-userspace syscalls.

Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
[christian.brauner@ubuntu.com: improve commit message]
Link: https://lore.kernel.org/r/20191001011055.19283-5-cyphar@cyphar.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 kernel/events/core.c | 47 +++++++++--------------------------------------
 1 file changed, 9 insertions(+), 38 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4655adbbae10..3f0cb82e4fbc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10586,55 +10586,26 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	u32 size;
 	int ret;
 
-	if (!access_ok(uattr, PERF_ATTR_SIZE_VER0))
-		return -EFAULT;
-
-	/*
-	 * zero the full structure, so that a short copy will be nice.
-	 */
+	/* Zero the full structure, so that a short copy will be nice. */
 	memset(attr, 0, sizeof(*attr));
 
 	ret = get_user(size, &uattr->size);
 	if (ret)
 		return ret;
 
-	if (size > PAGE_SIZE)	/* silly large */
-		goto err_size;
-
-	if (!size)		/* abi compat */
+	/* ABI compatibility quirk: */
+	if (!size)
 		size = PERF_ATTR_SIZE_VER0;
-
-	if (size < PERF_ATTR_SIZE_VER0)
+	if (size < PERF_ATTR_SIZE_VER0 || size > PAGE_SIZE)
 		goto err_size;
 
-	/*
-	 * If we're handed a bigger struct than we know of,
-	 * ensure all the unknown bits are 0 - i.e. new
-	 * user-space does not rely on any kernel feature
-	 * extensions we dont know about yet.
-	 */
-	if (size > sizeof(*attr)) {
-		unsigned char __user *addr;
-		unsigned char __user *end;
-		unsigned char val;
-
-		addr = (void __user *)uattr + sizeof(*attr);
-		end  = (void __user *)uattr + size;
-
-		for (; addr < end; addr++) {
-			ret = get_user(val, addr);
-			if (ret)
-				return ret;
-			if (val)
-				goto err_size;
-		}
-		size = sizeof(*attr);
+	ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
+	if (ret) {
+		if (ret == -E2BIG)
+			goto err_size;
+		return ret;
 	}
 
-	ret = copy_from_user(attr, uattr, size);
-	if (ret)
-		return -EFAULT;
-
 	attr->size = size;
 
 	if (attr->__reserved_1)
-- 
cgit v1.2.3


From 18545e8b6871d21aa3386dc42867138da9948a33 Mon Sep 17 00:00:00 2001
From: Adit Ranadive <aditr@vmware.com>
Date: Wed, 18 Sep 2019 23:08:00 +0000
Subject: RDMA/vmw_pvrdma: Free SRQ only once

An extra kfree cleanup was missed since these are now deallocated by core.

Link: https://lore.kernel.org/r/1568848066-12449-1-git-send-email-aditr@vmware.com
Cc: <stable@vger.kernel.org>
Fixes: 68e326dea1db ("RDMA: Handle SRQ allocations by IB/core")
Signed-off-by: Adit Ranadive <aditr@vmware.com>
Reviewed-by: Vishnu Dasa <vdasa@vmware.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
index 6cac0c88cf39..36cdfbdbd325 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c
@@ -230,8 +230,6 @@ static void pvrdma_free_srq(struct pvrdma_dev *dev, struct pvrdma_srq *srq)
 
 	pvrdma_page_dir_cleanup(dev, &srq->pdir);
 
-	kfree(srq);
-
 	atomic_dec(&dev->num_srqs);
 }
 
-- 
cgit v1.2.3


From df791c54d627bae53c9be3be40a69594c55de487 Mon Sep 17 00:00:00 2001
From: Krishnamraju Eraparaju <krishna2@chelsio.com>
Date: Mon, 23 Sep 2019 15:41:12 +0530
Subject: RDMA/siw: Fix serialization issue in write_space()

In siw_qp_llp_write_space(), 'sock' members should be accessed with
sk_callback_lock held, otherwise, it could race with
siw_sk_restore_upcalls(). And this could cause "NULL deref" panic.  Below
panic is due to the NULL cep returned from sk_to_cep(sk):

  Call Trace:
   <IRQ>    siw_qp_llp_write_space+0x11/0x40 [siw]
   tcp_check_space+0x4c/0xf0
   tcp_rcv_established+0x52b/0x630
   tcp_v4_do_rcv+0xf4/0x1e0
   tcp_v4_rcv+0x9b8/0xab0
   ip_protocol_deliver_rcu+0x2c/0x1c0
   ip_local_deliver_finish+0x44/0x50
   ip_local_deliver+0x6b/0xf0
   ? ip_protocol_deliver_rcu+0x1c0/0x1c0
   ip_rcv+0x52/0xd0
   ? ip_rcv_finish_core.isra.14+0x390/0x390
   __netif_receive_skb_one_core+0x83/0xa0
   netif_receive_skb_internal+0x73/0xb0
   napi_gro_frags+0x1ff/0x2b0
   t4_ethrx_handler+0x4a7/0x740 [cxgb4]
   process_responses+0x2c9/0x590 [cxgb4]
   ? t4_sge_intr_msix+0x1d/0x30 [cxgb4]
   ? handle_irq_event_percpu+0x51/0x70
   ? handle_irq_event+0x41/0x60
   ? handle_edge_irq+0x97/0x1a0
   napi_rx_handler+0x14/0xe0 [cxgb4]
   net_rx_action+0x2af/0x410
   __do_softirq+0xda/0x2a8
   do_softirq_own_stack+0x2a/0x40
   </IRQ>
   do_softirq+0x50/0x60
   __local_bh_enable_ip+0x50/0x60
   ip_finish_output2+0x18f/0x520
   ip_output+0x6e/0xf0
   ? __ip_finish_output+0x1f0/0x1f0
   __ip_queue_xmit+0x14f/0x3d0
   ? __slab_alloc+0x4b/0x58
   __tcp_transmit_skb+0x57d/0xa60
   tcp_write_xmit+0x23b/0xfd0
   __tcp_push_pending_frames+0x2e/0xf0
   tcp_sendmsg_locked+0x939/0xd50
   tcp_sendmsg+0x27/0x40
   sock_sendmsg+0x57/0x80
   siw_tx_hdt+0x894/0xb20 [siw]
   ? find_busiest_group+0x3e/0x5b0
   ? common_interrupt+0xa/0xf
   ? common_interrupt+0xa/0xf
   ? common_interrupt+0xa/0xf
   siw_qp_sq_process+0xf1/0xe60 [siw]
   ? __wake_up_common_lock+0x87/0xc0
   siw_sq_resume+0x33/0xe0 [siw]
   siw_run_sq+0xac/0x190 [siw]
   ? remove_wait_queue+0x60/0x60
   kthread+0xf8/0x130
   ? siw_sq_resume+0xe0/0xe0 [siw]
   ? kthread_bind+0x10/0x10
   ret_from_fork+0x35/0x40

Fixes: f29dd55b0236 ("rdma/siw: queue pair methods")
Link: https://lore.kernel.org/r/20190923101112.32685-1-krishna2@chelsio.com
Signed-off-by: Krishnamraju Eraparaju <krishna2@chelsio.com>
Reviewed-by: Bernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/sw/siw/siw_qp.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/sw/siw/siw_qp.c b/drivers/infiniband/sw/siw/siw_qp.c
index 430314c8abd9..52d402f39df9 100644
--- a/drivers/infiniband/sw/siw/siw_qp.c
+++ b/drivers/infiniband/sw/siw/siw_qp.c
@@ -182,12 +182,19 @@ void siw_qp_llp_close(struct siw_qp *qp)
  */
 void siw_qp_llp_write_space(struct sock *sk)
 {
-	struct siw_cep *cep = sk_to_cep(sk);
+	struct siw_cep *cep;
 
-	cep->sk_write_space(sk);
+	read_lock(&sk->sk_callback_lock);
+
+	cep  = sk_to_cep(sk);
+	if (cep) {
+		cep->sk_write_space(sk);
 
-	if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
-		(void)siw_sq_start(cep->qp);
+		if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
+			(void)siw_sq_start(cep->qp);
+	}
+
+	read_unlock(&sk->sk_callback_lock);
 }
 
 static int siw_qp_readq_init(struct siw_qp *qp, int irq_size, int orq_size)
-- 
cgit v1.2.3


From 390d3fdcae2da52755b31aa44fcf19ecb5a2488b Mon Sep 17 00:00:00 2001
From: Michal Kalderon <michal.kalderon@marvell.com>
Date: Wed, 25 Sep 2019 15:33:32 +0300
Subject: RDMA/core: Fix use after free and refcnt leak on ndev in_device in
 iwarp_query_port

If an iWARP driver is probed and removed while there are no ips set for
the device, it will lead to a reference count leak on the inet device of
the netdevice.

In addition, the netdevice was accessed after already calling netdev_put,
which could lead to using the netdev after already freed.

Fixes: 4929116bdf72 ("RDMA/core: Add common iWARP query port")
Link: https://lore.kernel.org/r/20190925123332.10746-1-michal.kalderon@marvell.com
Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
Reviewed-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/device.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 99c4a55545cf..2dd2cfe9b561 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1987,8 +1987,6 @@ static int iw_query_port(struct ib_device *device,
 	if (!netdev)
 		return -ENODEV;
 
-	dev_put(netdev);
-
 	port_attr->max_mtu = IB_MTU_4096;
 	port_attr->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
 
@@ -1996,19 +1994,22 @@ static int iw_query_port(struct ib_device *device,
 		port_attr->state = IB_PORT_DOWN;
 		port_attr->phys_state = IB_PORT_PHYS_STATE_DISABLED;
 	} else {
-		inetdev = in_dev_get(netdev);
+		rcu_read_lock();
+		inetdev = __in_dev_get_rcu(netdev);
 
 		if (inetdev && inetdev->ifa_list) {
 			port_attr->state = IB_PORT_ACTIVE;
 			port_attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
-			in_dev_put(inetdev);
 		} else {
 			port_attr->state = IB_PORT_INIT;
 			port_attr->phys_state =
 				IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING;
 		}
+
+		rcu_read_unlock();
 	}
 
+	dev_put(netdev);
 	err = device->ops.query_port(device, port_num, port_attr);
 	if (err)
 		return err;
-- 
cgit v1.2.3


From 34b3be18a04ecdc610aae4c48e5d1b799d8689f6 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Wed, 25 Sep 2019 09:45:42 -0500
Subject: RDMA/hfi1: Prevent memory leak in sdma_init

In sdma_init if rhashtable_init fails the allocated memory for
tmp_sdma_rht should be released.

Fixes: 5a52a7acf7e2 ("IB/hfi1: NULL pointer dereference when freeing rhashtable")
Link: https://lore.kernel.org/r/20190925144543.10141-1-navid.emamdoost@gmail.com
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Acked-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/hfi1/sdma.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index 2395fd4233a7..2ed7bfd5feea 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -1526,8 +1526,11 @@ int sdma_init(struct hfi1_devdata *dd, u8 port)
 	}
 
 	ret = rhashtable_init(tmp_sdma_rht, &sdma_rht_params);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(tmp_sdma_rht);
 		goto bail;
+	}
+
 	dd->sdma_rht = tmp_sdma_rht;
 
 	dd_dev_info(dd, "SDMA num_sdma: %u\n", dd->num_sdma);
-- 
cgit v1.2.3


From 91724c1e5afe45b64970036170659726e7dc5cff Mon Sep 17 00:00:00 2001
From: Potnuri Bharat Teja <bharat@chelsio.com>
Date: Mon, 30 Sep 2019 13:11:19 +0530
Subject: RDMA/iw_cxgb4: fix SRQ access from dump_qp()

dump_qp() is wrongly trying to dump SRQ structures as QP when SRQ is used
by the application. This patch matches the QPID before dumping them.  Also
removes unwanted SRQ id addition to QP id xarray.

Fixes: 2f43129127e6 ("cxgb4: Convert qpidr to XArray")
Link: https://lore.kernel.org/r/20190930074119.20046-1-bharat@chelsio.com
Signed-off-by: Rahul Kundu <rahul.kundu@chelsio.com>
Signed-off-by: Potnuri Bharat Teja <bharat@chelsio.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/cxgb4/device.c |  7 +++++--
 drivers/infiniband/hw/cxgb4/qp.c     | 10 +---------
 2 files changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index a8b9548bd1a2..599340c1f0b8 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -242,10 +242,13 @@ static void set_ep_sin6_addrs(struct c4iw_ep *ep,
 	}
 }
 
-static int dump_qp(struct c4iw_qp *qp, struct c4iw_debugfs_data *qpd)
+static int dump_qp(unsigned long id, struct c4iw_qp *qp,
+		   struct c4iw_debugfs_data *qpd)
 {
 	int space;
 	int cc;
+	if (id != qp->wq.sq.qid)
+		return 0;
 
 	space = qpd->bufsize - qpd->pos - 1;
 	if (space == 0)
@@ -350,7 +353,7 @@ static int qp_open(struct inode *inode, struct file *file)
 
 	xa_lock_irq(&qpd->devp->qps);
 	xa_for_each(&qpd->devp->qps, index, qp)
-		dump_qp(qp, qpd);
+		dump_qp(index, qp, qpd);
 	xa_unlock_irq(&qpd->devp->qps);
 
 	qpd->buf[qpd->pos++] = 0;
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index eb9368be28c1..bbcac539777a 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -2737,15 +2737,11 @@ int c4iw_create_srq(struct ib_srq *ib_srq, struct ib_srq_init_attr *attrs,
 	if (CHELSIO_CHIP_VERSION(rhp->rdev.lldi.adapter_type) > CHELSIO_T6)
 		srq->flags = T4_SRQ_LIMIT_SUPPORT;
 
-	ret = xa_insert_irq(&rhp->qps, srq->wq.qid, srq, GFP_KERNEL);
-	if (ret)
-		goto err_free_queue;
-
 	if (udata) {
 		srq_key_mm = kmalloc(sizeof(*srq_key_mm), GFP_KERNEL);
 		if (!srq_key_mm) {
 			ret = -ENOMEM;
-			goto err_remove_handle;
+			goto err_free_queue;
 		}
 		srq_db_key_mm = kmalloc(sizeof(*srq_db_key_mm), GFP_KERNEL);
 		if (!srq_db_key_mm) {
@@ -2789,8 +2785,6 @@ err_free_srq_db_key_mm:
 	kfree(srq_db_key_mm);
 err_free_srq_key_mm:
 	kfree(srq_key_mm);
-err_remove_handle:
-	xa_erase_irq(&rhp->qps, srq->wq.qid);
 err_free_queue:
 	free_srq_queue(srq, ucontext ? &ucontext->uctx : &rhp->rdev.uctx,
 		       srq->wr_waitp);
@@ -2813,8 +2807,6 @@ void c4iw_destroy_srq(struct ib_srq *ibsrq, struct ib_udata *udata)
 	rhp = srq->rhp;
 
 	pr_debug("%s id %d\n", __func__, srq->wq.qid);
-
-	xa_erase_irq(&rhp->qps, srq->wq.qid);
 	ucontext = rdma_udata_to_drv_context(udata, struct c4iw_ucontext,
 					     ibucontext);
 	free_srq_queue(srq, ucontext ? &ucontext->uctx : &rhp->rdev.uctx,
-- 
cgit v1.2.3


From b66f31efbdad95ec274345721d99d1d835e6de01 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Mon, 30 Sep 2019 16:16:54 -0700
Subject: RDMA/iwcm: Fix a lock inversion issue

This patch fixes the lock inversion complaint:

============================================
WARNING: possible recursive locking detected
5.3.0-rc7-dbg+ #1 Not tainted
--------------------------------------------
kworker/u16:6/171 is trying to acquire lock:
00000000035c6e6c (&id_priv->handler_mutex){+.+.}, at: rdma_destroy_id+0x78/0x4a0 [rdma_cm]

but task is already holding lock:
00000000bc7c307d (&id_priv->handler_mutex){+.+.}, at: iw_conn_req_handler+0x151/0x680 [rdma_cm]

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&id_priv->handler_mutex);
  lock(&id_priv->handler_mutex);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

3 locks held by kworker/u16:6/171:
 #0: 00000000e2eaa773 ((wq_completion)iw_cm_wq){+.+.}, at: process_one_work+0x472/0xac0
 #1: 000000001efd357b ((work_completion)(&work->work)#3){+.+.}, at: process_one_work+0x476/0xac0
 #2: 00000000bc7c307d (&id_priv->handler_mutex){+.+.}, at: iw_conn_req_handler+0x151/0x680 [rdma_cm]

stack backtrace:
CPU: 3 PID: 171 Comm: kworker/u16:6 Not tainted 5.3.0-rc7-dbg+ #1
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
Workqueue: iw_cm_wq cm_work_handler [iw_cm]
Call Trace:
 dump_stack+0x8a/0xd6
 __lock_acquire.cold+0xe1/0x24d
 lock_acquire+0x106/0x240
 __mutex_lock+0x12e/0xcb0
 mutex_lock_nested+0x1f/0x30
 rdma_destroy_id+0x78/0x4a0 [rdma_cm]
 iw_conn_req_handler+0x5c9/0x680 [rdma_cm]
 cm_work_handler+0xe62/0x1100 [iw_cm]
 process_one_work+0x56d/0xac0
 worker_thread+0x7a/0x5d0
 kthread+0x1bc/0x210
 ret_from_fork+0x24/0x30

This is not a bug as there are actually two lock classes here.

Link: https://lore.kernel.org/r/20190930231707.48259-3-bvanassche@acm.org
Fixes: de910bd92137 ("RDMA/cma: Simplify locking needed for serialization of callbacks")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/cma.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 0e3cf3461999..d78f67623f24 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2396,9 +2396,10 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
 		conn_id->cm_id.iw = NULL;
 		cma_exch(conn_id, RDMA_CM_DESTROYING);
 		mutex_unlock(&conn_id->handler_mutex);
+		mutex_unlock(&listen_id->handler_mutex);
 		cma_deref_id(conn_id);
 		rdma_destroy_id(&conn_id->id);
-		goto out;
+		return ret;
 	}
 
 	mutex_unlock(&conn_id->handler_mutex);
-- 
cgit v1.2.3


From 85560117d00f5d528e928918b8f61cadcefff98b Mon Sep 17 00:00:00 2001
From: Martijn Coenen <maco@android.com>
Date: Wed, 4 Sep 2019 21:49:01 +0200
Subject: loop: change queue block size to match when using DIO

The loop driver assumes that if the passed in fd is opened with
O_DIRECT, the caller wants to use direct I/O on the loop device.
However, if the underlying block device has a different block size than
the loop block queue, direct I/O can't be enabled. Instead of requiring
userspace to manually change the blocksize and re-enable direct I/O,
just change the queue block sizes to match, as well as the io_min size.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martijn Coenen <maco@android.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 1410fa893653..f6f77eaa7217 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -994,6 +994,16 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
 		blk_queue_write_cache(lo->lo_queue, true, false);
 
+	if (io_is_direct(lo->lo_backing_file) && inode->i_sb->s_bdev) {
+		/* In case of direct I/O, match underlying block size */
+		unsigned short bsize = bdev_logical_block_size(
+			inode->i_sb->s_bdev);
+
+		blk_queue_logical_block_size(lo->lo_queue, bsize);
+		blk_queue_physical_block_size(lo->lo_queue, bsize);
+		blk_queue_io_min(lo->lo_queue, bsize);
+	}
+
 	loop_update_rotational(lo);
 	loop_update_dio(lo);
 	set_capacity(lo->lo_disk, size);
-- 
cgit v1.2.3


From bdf200731145f07a6127cb16753e2e8fdc159cf4 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 1 Oct 2019 09:53:29 -0600
Subject: io_uring: use __kernel_timespec in timeout ABI

All system calls use struct __kernel_timespec instead of the old struct
timespec, but this one was just added with the old-style ABI. Change it
now to enforce the use of __kernel_timespec, avoiding ABI confusion and
the need for compat handlers on 32-bit architectures.

Any user space caller will have to use __kernel_timespec now, but this
is unambiguous and works for any C library regardless of the time_t
definition. A nicer way to specify the timeout would have been a less
ambiguous 64-bit nanosecond value, but I suppose it's too late now to
change that as this would impact both 32-bit and 64-bit users.

Fixes: 5262f567987d ("io_uring: IORING_OP_TIMEOUT support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index dd094b387cab..0bc167aca46d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1892,15 +1892,15 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	unsigned count, req_dist, tail_index;
 	struct io_ring_ctx *ctx = req->ctx;
 	struct list_head *entry;
-	struct timespec ts;
+	struct timespec64 ts;
 
 	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
 		return -EINVAL;
 	if (sqe->flags || sqe->ioprio || sqe->buf_index || sqe->timeout_flags ||
 	    sqe->len != 1)
 		return -EINVAL;
-	if (copy_from_user(&ts, (void __user *) (unsigned long) sqe->addr,
-	    sizeof(ts)))
+
+	if (get_timespec64(&ts, u64_to_user_ptr(sqe->addr)))
 		return -EFAULT;
 
 	/*
@@ -1934,7 +1934,7 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 
 	hrtimer_init(&req->timeout.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	req->timeout.timer.function = io_timeout_fn;
-	hrtimer_start(&req->timeout.timer, timespec_to_ktime(ts),
+	hrtimer_start(&req->timeout.timer, timespec64_to_ktime(ts),
 			HRTIMER_MODE_REL);
 	return 0;
 }
-- 
cgit v1.2.3


From dd45483981ac62f432e073fea6e5e11200b9070d Mon Sep 17 00:00:00 2001
From: Jan Höppner <hoeppner@linux.ibm.com>
Date: Tue, 1 Oct 2019 17:34:38 +0200
Subject: s390/dasd: Fix error handling during online processing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It is possible that the CCW commands for reading volume and extent pool
information are not supported, either by the storage server (for
dedicated DASDs) or by z/VM (for virtual devices, such as MDISKs).

As a command reject will occur in such a case, the current error
handling leads to a failing online processing and thus the DASD can't be
used at all.

Since the data being read is not essential for an fully operational
DASD, the error handling can be removed. Information about the failing
command is sent to the s390dbf debug feature.

Fixes: c729696bcf8b ("s390/dasd: Recognise data for ESE volumes")
Cc: <stable@vger.kernel.org> # 5.3
Reported-by: Frank Heimes <frank.heimes@canonical.com>
Signed-off-by: Jan Höppner <hoeppner@linux.ibm.com>
Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/s390/block/dasd_eckd.c | 24 ++++++++----------------
 1 file changed, 8 insertions(+), 16 deletions(-)

diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index fc53e1e221f0..b213c40d1a51 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1553,8 +1553,8 @@ static int dasd_eckd_read_vol_info(struct dasd_device *device)
 	if (rc == 0) {
 		memcpy(&private->vsq, vsq, sizeof(*vsq));
 	} else {
-		dev_warn(&device->cdev->dev,
-			 "Reading the volume storage information failed with rc=%d\n", rc);
+		DBF_EVENT_DEVID(DBF_WARNING, device->cdev,
+				"Reading the volume storage information failed with rc=%d", rc);
 	}
 
 	if (useglobal)
@@ -1737,8 +1737,8 @@ static int dasd_eckd_read_ext_pool_info(struct dasd_device *device)
 	if (rc == 0) {
 		dasd_eckd_cpy_ext_pool_data(device, lcq);
 	} else {
-		dev_warn(&device->cdev->dev,
-			 "Reading the logical configuration failed with rc=%d\n", rc);
+		DBF_EVENT_DEVID(DBF_WARNING, device->cdev,
+				"Reading the logical configuration failed with rc=%d", rc);
 	}
 
 	dasd_sfree_request(cqr, cqr->memdev);
@@ -2020,14 +2020,10 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
 	dasd_eckd_read_features(device);
 
 	/* Read Volume Information */
-	rc = dasd_eckd_read_vol_info(device);
-	if (rc)
-		goto out_err3;
+	dasd_eckd_read_vol_info(device);
 
 	/* Read Extent Pool Information */
-	rc = dasd_eckd_read_ext_pool_info(device);
-	if (rc)
-		goto out_err3;
+	dasd_eckd_read_ext_pool_info(device);
 
 	/* Read Device Characteristics */
 	rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC,
@@ -5663,14 +5659,10 @@ static int dasd_eckd_restore_device(struct dasd_device *device)
 	dasd_eckd_read_features(device);
 
 	/* Read Volume Information */
-	rc = dasd_eckd_read_vol_info(device);
-	if (rc)
-		goto out_err2;
+	dasd_eckd_read_vol_info(device);
 
 	/* Read Extent Pool Information */
-	rc = dasd_eckd_read_ext_pool_info(device);
-	if (rc)
-		goto out_err2;
+	dasd_eckd_read_ext_pool_info(device);
 
 	/* Read Device Characteristics */
 	rc = dasd_generic_read_dev_chars(device, DASD_ECKD_MAGIC,
-- 
cgit v1.2.3


From 964ce509e2ded52c1a61ad86044cc4d70abd9eb8 Mon Sep 17 00:00:00 2001
From: Stefan Haberland <sth@linux.ibm.com>
Date: Tue, 1 Oct 2019 17:34:39 +0200
Subject: Revert "s390/dasd: Add discard support for ESE volumes"

This reverts commit 7e64db1597fe114b83fe17d0ba96c6aa5fca419a.

The thin provisioning feature introduces an IOCTL and the discard support
to allow userspace tools and filesystems to release unused and previously
allocated space respectively.

During some internal performance improvements and further tests, the
release of allocated space revealed some issues that may lead to data
corruption in some configurations when filesystems are mounted with
discard support enabled.

While we're working on a fix and trying to clarify the situation,
this commit reverts the discard support for ESE volumes to prevent
potential data corruption.

Cc: <stable@vger.kernel.org> # 5.3
Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/s390/block/dasd_eckd.c | 57 +++---------------------------------------
 1 file changed, 3 insertions(+), 54 deletions(-)

diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index b213c40d1a51..c94184d080f8 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -2055,9 +2055,6 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
 	if (readonly)
 		set_bit(DASD_FLAG_DEVICE_RO, &device->flags);
 
-	if (dasd_eckd_is_ese(device))
-		dasd_set_feature(device->cdev, DASD_FEATURE_DISCARD, 1);
-
 	dev_info(&device->cdev->dev, "New DASD %04X/%02X (CU %04X/%02X) "
 		 "with %d cylinders, %d heads, %d sectors%s\n",
 		 private->rdc_data.dev_type,
@@ -3691,14 +3688,6 @@ static int dasd_eckd_release_space(struct dasd_device *device,
 		return -EINVAL;
 }
 
-static struct dasd_ccw_req *
-dasd_eckd_build_cp_discard(struct dasd_device *device, struct dasd_block *block,
-			   struct request *req, sector_t first_trk,
-			   sector_t last_trk)
-{
-	return dasd_eckd_dso_ras(device, block, req, first_trk, last_trk, 1);
-}
-
 static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single(
 					       struct dasd_device *startdev,
 					       struct dasd_block *block,
@@ -4443,10 +4432,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp(struct dasd_device *startdev,
 	cmdwtd = private->features.feature[12] & 0x40;
 	use_prefix = private->features.feature[8] & 0x01;
 
-	if (req_op(req) == REQ_OP_DISCARD)
-		return dasd_eckd_build_cp_discard(startdev, block, req,
-						  first_trk, last_trk);
-
 	cqr = NULL;
 	if (cdlspecial || dasd_page_cache) {
 		/* do nothing, just fall through to the cmd mode single case */
@@ -4725,14 +4710,12 @@ static struct dasd_ccw_req *dasd_eckd_build_alias_cp(struct dasd_device *base,
 						     struct dasd_block *block,
 						     struct request *req)
 {
-	struct dasd_device *startdev = NULL;
 	struct dasd_eckd_private *private;
-	struct dasd_ccw_req *cqr;
+	struct dasd_device *startdev;
 	unsigned long flags;
+	struct dasd_ccw_req *cqr;
 
-	/* Discard requests can only be processed on base devices */
-	if (req_op(req) != REQ_OP_DISCARD)
-		startdev = dasd_alias_get_start_dev(base);
+	startdev = dasd_alias_get_start_dev(base);
 	if (!startdev)
 		startdev = base;
 	private = startdev->private;
@@ -6513,20 +6496,8 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block)
 	unsigned int logical_block_size = block->bp_block;
 	struct request_queue *q = block->request_queue;
 	struct dasd_device *device = block->base;
-	struct dasd_eckd_private *private;
-	unsigned int max_discard_sectors;
-	unsigned int max_bytes;
-	unsigned int ext_bytes; /* Extent Size in Bytes */
-	int recs_per_trk;
-	int trks_per_cyl;
-	int ext_limit;
-	int ext_size; /* Extent Size in Cylinders */
 	int max;
 
-	private = device->private;
-	trks_per_cyl = private->rdc_data.trk_per_cyl;
-	recs_per_trk = recs_per_track(&private->rdc_data, 0, logical_block_size);
-
 	if (device->features & DASD_FEATURE_USERAW) {
 		/*
 		 * the max_blocks value for raw_track access is 256
@@ -6547,28 +6518,6 @@ static void dasd_eckd_setup_blk_queue(struct dasd_block *block)
 	/* With page sized segments each segment can be translated into one idaw/tidaw */
 	blk_queue_max_segment_size(q, PAGE_SIZE);
 	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
-
-	if (dasd_eckd_is_ese(device)) {
-		/*
-		 * Depending on the extent size, up to UINT_MAX bytes can be
-		 * accepted. However, neither DASD_ECKD_RAS_EXTS_MAX nor the
-		 * device limits should be exceeded.
-		 */
-		ext_size = dasd_eckd_ext_size(device);
-		ext_limit = min(private->real_cyl / ext_size, DASD_ECKD_RAS_EXTS_MAX);
-		ext_bytes = ext_size * trks_per_cyl * recs_per_trk *
-			logical_block_size;
-		max_bytes = UINT_MAX - (UINT_MAX % ext_bytes);
-		if (max_bytes / ext_bytes > ext_limit)
-			max_bytes = ext_bytes * ext_limit;
-
-		max_discard_sectors = max_bytes / 512;
-
-		blk_queue_max_discard_sectors(q, max_discard_sectors);
-		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
-		q->limits.discard_granularity = ext_bytes;
-		q->limits.discard_alignment = ext_bytes;
-	}
 }
 
 static struct ccw_driver dasd_eckd_driver = {
-- 
cgit v1.2.3


From f88eb7c0d002a67ef31aeb7850b42ff69abc46dc Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 20 Sep 2019 21:54:17 +0200
Subject: nl80211: validate beacon head

We currently don't validate the beacon head, i.e. the header,
fixed part and elements that are to go in front of the TIM
element. This means that the variable elements there can be
malformed, e.g. have a length exceeding the buffer size, but
most downstream code from this assumes that this has already
been checked.

Add the necessary checks to the netlink policy.

Cc: stable@vger.kernel.org
Fixes: ed1b6cc7f80f ("cfg80211/nl80211: add beacon settings")
Link: https://lore.kernel.org/r/1569009255-I7ac7fbe9436e9d8733439eab8acbbd35e55c74ef@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 37 +++++++++++++++++++++++++++++++++++--
 1 file changed, 35 insertions(+), 2 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d21b1581a665..7386421e2ad3 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -201,6 +201,38 @@ cfg80211_get_dev_from_info(struct net *netns, struct genl_info *info)
 	return __cfg80211_rdev_from_attrs(netns, info->attrs);
 }
 
+static int validate_beacon_head(const struct nlattr *attr,
+				struct netlink_ext_ack *extack)
+{
+	const u8 *data = nla_data(attr);
+	unsigned int len = nla_len(attr);
+	const struct element *elem;
+	const struct ieee80211_mgmt *mgmt = (void *)data;
+	unsigned int fixedlen = offsetof(struct ieee80211_mgmt,
+					 u.beacon.variable);
+
+	if (len < fixedlen)
+		goto err;
+
+	if (ieee80211_hdrlen(mgmt->frame_control) !=
+	    offsetof(struct ieee80211_mgmt, u.beacon))
+		goto err;
+
+	data += fixedlen;
+	len -= fixedlen;
+
+	for_each_element(elem, data, len) {
+		/* nothing */
+	}
+
+	if (for_each_element_completed(elem, data, len))
+		return 0;
+
+err:
+	NL_SET_ERR_MSG_ATTR(extack, attr, "malformed beacon head");
+	return -EINVAL;
+}
+
 static int validate_ie_attr(const struct nlattr *attr,
 			    struct netlink_ext_ack *extack)
 {
@@ -338,8 +370,9 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 
 	[NL80211_ATTR_BEACON_INTERVAL] = { .type = NLA_U32 },
 	[NL80211_ATTR_DTIM_PERIOD] = { .type = NLA_U32 },
-	[NL80211_ATTR_BEACON_HEAD] = { .type = NLA_BINARY,
-				       .len = IEEE80211_MAX_DATA_LEN },
+	[NL80211_ATTR_BEACON_HEAD] =
+		NLA_POLICY_VALIDATE_FN(NLA_BINARY, validate_beacon_head,
+				       IEEE80211_MAX_DATA_LEN),
 	[NL80211_ATTR_BEACON_TAIL] =
 		NLA_POLICY_VALIDATE_FN(NLA_BINARY, validate_ie_attr,
 				       IEEE80211_MAX_DATA_LEN),
-- 
cgit v1.2.3


From 242b0931c1918c56cd1dc5563fd250a3c39b996d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 20 Sep 2019 21:54:18 +0200
Subject: cfg80211: validate SSID/MBSSID element ordering assumption

The code copying the data assumes that the SSID element is
before the MBSSID element, but since the data is untrusted
from the AP, this cannot be guaranteed.

Validate that this is indeed the case and ignore the MBSSID
otherwise, to avoid having to deal with both cases for the
copy of data that should be between them.

Cc: stable@vger.kernel.org
Fixes: 0b8fb8235be8 ("cfg80211: Parsing of Multiple BSSID information in scanning")
Link: https://lore.kernel.org/r/1569009255-I1673911f5eae02964e21bdc11b2bf58e5e207e59@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/scan.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index d313c9befa23..ff1016607f0b 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1723,7 +1723,12 @@ cfg80211_update_notlisted_nontrans(struct wiphy *wiphy,
 		return;
 	new_ie_len -= trans_ssid[1];
 	mbssid = cfg80211_find_ie(WLAN_EID_MULTIPLE_BSSID, ie, ielen);
-	if (!mbssid)
+	/*
+	 * It's not valid to have the MBSSID element before SSID
+	 * ignore if that happens - the code below assumes it is
+	 * after (while copying things inbetween).
+	 */
+	if (!mbssid || mbssid < trans_ssid)
 		return;
 	new_ie_len -= mbssid[1];
 	rcu_read_lock();
-- 
cgit v1.2.3


From f43e5210c739fe76a4b0ed851559d6902f20ceb1 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 23 Sep 2019 13:51:16 +0200
Subject: cfg80211: initialize on-stack chandefs

In a few places we don't properly initialize on-stack chandefs,
resulting in EDMG data to be non-zero, which broke things.

Additionally, in a few places we rely on the driver to init the
data completely, but perhaps we shouldn't as non-EDMG drivers
may not initialize the EDMG data, also initialize it there.

Cc: stable@vger.kernel.org
Fixes: 2a38075cd0be ("nl80211: Add support for EDMG channels")
Reported-by: Dmitry Osipenko <digetx@gmail.com>
Tested-by: Dmitry Osipenko <digetx@gmail.com>
Link: https://lore.kernel.org/r/1569239475-I2dcce394ecf873376c386a78f31c2ec8b538fa25@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c     | 4 +++-
 net/wireless/reg.c         | 2 +-
 net/wireless/wext-compat.c | 2 +-
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 7386421e2ad3..10617566a117 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2669,6 +2669,8 @@ int nl80211_parse_chandef(struct cfg80211_registered_device *rdev,
 
 	control_freq = nla_get_u32(attrs[NL80211_ATTR_WIPHY_FREQ]);
 
+	memset(chandef, 0, sizeof(*chandef));
+
 	chandef->chan = ieee80211_get_channel(&rdev->wiphy, control_freq);
 	chandef->width = NL80211_CHAN_WIDTH_20_NOHT;
 	chandef->center_freq1 = control_freq;
@@ -3209,7 +3211,7 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag
 
 	if (rdev->ops->get_channel) {
 		int ret;
-		struct cfg80211_chan_def chandef;
+		struct cfg80211_chan_def chandef = {};
 
 		ret = rdev_get_channel(rdev, wdev, &chandef);
 		if (ret == 0) {
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 5311d0ae2454..420c4207ab59 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2108,7 +2108,7 @@ static void reg_call_notifier(struct wiphy *wiphy,
 
 static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev)
 {
-	struct cfg80211_chan_def chandef;
+	struct cfg80211_chan_def chandef = {};
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	enum nl80211_iftype iftype;
 
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 7b6529d81c61..cac9e28d852b 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -798,7 +798,7 @@ static int cfg80211_wext_giwfreq(struct net_device *dev,
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
-	struct cfg80211_chan_def chandef;
+	struct cfg80211_chan_def chandef = {};
 	int ret;
 
 	switch (wdev->iftype) {
-- 
cgit v1.2.3


From b501426cf86e70649c983c52f4c823b3c40d72a3 Mon Sep 17 00:00:00 2001
From: Miaoqing Pan <miaoqing@codeaurora.org>
Date: Thu, 26 Sep 2019 16:16:50 +0800
Subject: nl80211: fix null pointer dereference

If the interface is not in MESH mode, the command 'iw wlanx mpath del'
will cause kernel panic.

The root cause is null pointer access in mpp_flush_by_proxy(), as the
pointer 'sdata->u.mesh.mpp_paths' is NULL for non MESH interface.

Unable to handle kernel NULL pointer dereference at virtual address 00000068
[...]
PC is at _raw_spin_lock_bh+0x20/0x5c
LR is at mesh_path_del+0x1c/0x17c [mac80211]
[...]
Process iw (pid: 4537, stack limit = 0xd83e0238)
[...]
[<c021211c>] (_raw_spin_lock_bh) from [<bf8c7648>] (mesh_path_del+0x1c/0x17c [mac80211])
[<bf8c7648>] (mesh_path_del [mac80211]) from [<bf6cdb7c>] (extack_doit+0x20/0x68 [compat])
[<bf6cdb7c>] (extack_doit [compat]) from [<c05c309c>] (genl_rcv_msg+0x274/0x30c)
[<c05c309c>] (genl_rcv_msg) from [<c05c25d8>] (netlink_rcv_skb+0x58/0xac)
[<c05c25d8>] (netlink_rcv_skb) from [<c05c2e14>] (genl_rcv+0x20/0x34)
[<c05c2e14>] (genl_rcv) from [<c05c1f90>] (netlink_unicast+0x11c/0x204)
[<c05c1f90>] (netlink_unicast) from [<c05c2420>] (netlink_sendmsg+0x30c/0x370)
[<c05c2420>] (netlink_sendmsg) from [<c05886d0>] (sock_sendmsg+0x70/0x84)
[<c05886d0>] (sock_sendmsg) from [<c0589f4c>] (___sys_sendmsg.part.3+0x188/0x228)
[<c0589f4c>] (___sys_sendmsg.part.3) from [<c058add4>] (__sys_sendmsg+0x4c/0x70)
[<c058add4>] (__sys_sendmsg) from [<c0208c80>] (ret_fast_syscall+0x0/0x44)
Code: e2822c02 e2822001 e5832004 f590f000 (e1902f9f)
---[ end trace bbd717600f8f884d ]---

Signed-off-by: Miaoqing Pan <miaoqing@codeaurora.org>
Link: https://lore.kernel.org/r/1569485810-761-1-git-send-email-miaoqing@codeaurora.org
[trim useless data from commit message]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 10617566a117..141cdb171665 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6305,6 +6305,9 @@ static int nl80211_del_mpath(struct sk_buff *skb, struct genl_info *info)
 	if (!rdev->ops->del_mpath)
 		return -EOPNOTSUPP;
 
+	if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_MESH_POINT)
+		return -EOPNOTSUPP;
+
 	return rdev_del_mpath(rdev, dev, dst);
 }
 
-- 
cgit v1.2.3


From 8ed31a264065ae92058ce54aa3cc8da8d81dc6d7 Mon Sep 17 00:00:00 2001
From: Miaoqing Pan <miaoqing@codeaurora.org>
Date: Fri, 27 Sep 2019 10:03:16 +0800
Subject: mac80211: fix txq null pointer dereference
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If the interface type is P2P_DEVICE or NAN, read the file of
'/sys/kernel/debug/ieee80211/phyx/netdev:wlanx/aqm' will get a
NULL pointer dereference. As for those interface type, the
pointer sdata->vif.txq is NULL.

Unable to handle kernel NULL pointer dereference at virtual address 00000011
CPU: 1 PID: 30936 Comm: cat Not tainted 4.14.104 #1
task: ffffffc0337e4880 task.stack: ffffff800cd20000
PC is at ieee80211_if_fmt_aqm+0x34/0xa0 [mac80211]
LR is at ieee80211_if_fmt_aqm+0x34/0xa0 [mac80211]
[...]
Process cat (pid: 30936, stack limit = 0xffffff800cd20000)
[...]
[<ffffff8000b7cd00>] ieee80211_if_fmt_aqm+0x34/0xa0 [mac80211]
[<ffffff8000b7c414>] ieee80211_if_read+0x60/0xbc [mac80211]
[<ffffff8000b7ccc4>] ieee80211_if_read_aqm+0x28/0x30 [mac80211]
[<ffffff80082eff94>] full_proxy_read+0x2c/0x48
[<ffffff80081eef00>] __vfs_read+0x2c/0xd4
[<ffffff80081ef084>] vfs_read+0x8c/0x108
[<ffffff80081ef494>] SyS_read+0x40/0x7c

Signed-off-by: Miaoqing Pan <miaoqing@codeaurora.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/1569549796-8223-1-git-send-email-miaoqing@codeaurora.org
[trim useless data from commit message]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/debugfs_netdev.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index b1438fd4d876..64b544ae9966 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -487,9 +487,14 @@ static ssize_t ieee80211_if_fmt_aqm(
 	const struct ieee80211_sub_if_data *sdata, char *buf, int buflen)
 {
 	struct ieee80211_local *local = sdata->local;
-	struct txq_info *txqi = to_txq_info(sdata->vif.txq);
+	struct txq_info *txqi;
 	int len;
 
+	if (!sdata->vif.txq)
+		return 0;
+
+	txqi = to_txq_info(sdata->vif.txq);
+
 	spin_lock_bh(&local->fq.lock);
 	rcu_read_lock();
 
@@ -658,7 +663,9 @@ static void add_common_files(struct ieee80211_sub_if_data *sdata)
 	DEBUGFS_ADD(rc_rateidx_vht_mcs_mask_5ghz);
 	DEBUGFS_ADD(hw_queues);
 
-	if (sdata->local->ops->wake_tx_queue)
+	if (sdata->local->ops->wake_tx_queue &&
+	    sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE &&
+	    sdata->vif.type != NL80211_IFTYPE_NAN)
 		DEBUGFS_ADD(aqm);
 }
 
-- 
cgit v1.2.3


From d8dec42b5c2d2b273bc30b0e073cfbe832d69902 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 1 Oct 2019 13:19:23 +0200
Subject: mac80211: keep BHs disabled while calling drv_tx_wake_queue()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drivers typically expect this, as it's the case for almost all cases
where this is called (i.e. from the TX path). Also, the code in mac80211
itself (if the driver calls ieee80211_tx_dequeue()) expects this as it
uses this_cpu_ptr() without additional protection.

This should fix various reports of the problem:
https://bugzilla.kernel.org/show_bug.cgi?id=204127
https://lore.kernel.org/linux-wireless/CAN5HydrWb3o_FE6A1XDnP1E+xS66d5kiEuhHfiGKkLNQokx13Q@mail.gmail.com/
https://lore.kernel.org/lkml/nycvar.YFH.7.76.1909111238470.473@cbobk.fhfr.pm/

Cc: stable@vger.kernel.org
Reported-and-tested-by: Jiri Kosina <jkosina@suse.cz>
Reported-by: Aaron Hill <aa1ronham@gmail.com>
Reported-by: Lukas Redlinger <rel+kernel@agilox.net>
Reported-by: Oleksii Shevchuk <alxchk@gmail.com>
Fixes: 21a5d4c3a45c ("mac80211: add stop/start logic for software TXQs")
Link: https://lore.kernel.org/r/1569928763-I3e8838c5ecad878e59d4a94eb069a90f6641461a@changeid
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/util.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 051a02ddcb85..32a7a53833c0 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -247,7 +247,8 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac)
 	struct sta_info *sta;
 	int i;
 
-	spin_lock_bh(&fq->lock);
+	local_bh_disable();
+	spin_lock(&fq->lock);
 
 	if (sdata->vif.type == NL80211_IFTYPE_AP)
 		ps = &sdata->bss->ps;
@@ -273,9 +274,9 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac)
 						&txqi->flags))
 				continue;
 
-			spin_unlock_bh(&fq->lock);
+			spin_unlock(&fq->lock);
 			drv_wake_tx_queue(local, txqi);
-			spin_lock_bh(&fq->lock);
+			spin_lock(&fq->lock);
 		}
 	}
 
@@ -288,12 +289,14 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac)
 	    (ps && atomic_read(&ps->num_sta_ps)) || ac != vif->txq->ac)
 		goto out;
 
-	spin_unlock_bh(&fq->lock);
+	spin_unlock(&fq->lock);
 
 	drv_wake_tx_queue(local, txqi);
+	local_bh_enable();
 	return;
 out:
-	spin_unlock_bh(&fq->lock);
+	spin_unlock(&fq->lock);
+	local_bh_enable();
 }
 
 static void
-- 
cgit v1.2.3


From 55131dec2b1c7417d216f861ea7a29dc7c4d2d20 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 1 Oct 2019 10:33:51 +0200
Subject: net: socionext: netsec: always grab descriptor lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Always acquire tx descriptor spinlock even if a xdp program is not loaded
on the netsec device since ndo_xdp_xmit can run concurrently with
netsec_netdev_start_xmit and netsec_clean_tx_dring. This can happen
loading a xdp program on a different device (e.g virtio-net) and
xdp_do_redirect_map/xdp_do_redirect_slow can redirect to netsec even if
we do not have a xdp program on it.

Fixes: ba2b232108d3 ("net: netsec: add XDP support")
Tested-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 30 +++++++-----------------------
 1 file changed, 7 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 55db7fbd43cc..f9e6744d8fd6 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -282,7 +282,6 @@ struct netsec_desc_ring {
 	void *vaddr;
 	u16 head, tail;
 	u16 xdp_xmit; /* netsec_xdp_xmit packets */
-	bool is_xdp;
 	struct page_pool *page_pool;
 	struct xdp_rxq_info xdp_rxq;
 	spinlock_t lock; /* XDP tx queue locking */
@@ -634,8 +633,7 @@ static bool netsec_clean_tx_dring(struct netsec_priv *priv)
 	unsigned int bytes;
 	int cnt = 0;
 
-	if (dring->is_xdp)
-		spin_lock(&dring->lock);
+	spin_lock(&dring->lock);
 
 	bytes = 0;
 	entry = dring->vaddr + DESC_SZ * tail;
@@ -682,8 +680,8 @@ next:
 		entry = dring->vaddr + DESC_SZ * tail;
 		cnt++;
 	}
-	if (dring->is_xdp)
-		spin_unlock(&dring->lock);
+
+	spin_unlock(&dring->lock);
 
 	if (!cnt)
 		return false;
@@ -799,9 +797,6 @@ static void netsec_set_tx_de(struct netsec_priv *priv,
 	de->data_buf_addr_lw = lower_32_bits(desc->dma_addr);
 	de->buf_len_info = (tx_ctrl->tcp_seg_len << 16) | desc->len;
 	de->attr = attr;
-	/* under spin_lock if using XDP */
-	if (!dring->is_xdp)
-		dma_wmb();
 
 	dring->desc[idx] = *desc;
 	if (desc->buf_type == TYPE_NETSEC_SKB)
@@ -1123,12 +1118,10 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 	u16 tso_seg_len = 0;
 	int filled;
 
-	if (dring->is_xdp)
-		spin_lock_bh(&dring->lock);
+	spin_lock_bh(&dring->lock);
 	filled = netsec_desc_used(dring);
 	if (netsec_check_stop_tx(priv, filled)) {
-		if (dring->is_xdp)
-			spin_unlock_bh(&dring->lock);
+		spin_unlock_bh(&dring->lock);
 		net_warn_ratelimited("%s %s Tx queue full\n",
 				     dev_name(priv->dev), ndev->name);
 		return NETDEV_TX_BUSY;
@@ -1161,8 +1154,7 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 	tx_desc.dma_addr = dma_map_single(priv->dev, skb->data,
 					  skb_headlen(skb), DMA_TO_DEVICE);
 	if (dma_mapping_error(priv->dev, tx_desc.dma_addr)) {
-		if (dring->is_xdp)
-			spin_unlock_bh(&dring->lock);
+		spin_unlock_bh(&dring->lock);
 		netif_err(priv, drv, priv->ndev,
 			  "%s: DMA mapping failed\n", __func__);
 		ndev->stats.tx_dropped++;
@@ -1177,8 +1169,7 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 	netdev_sent_queue(priv->ndev, skb->len);
 
 	netsec_set_tx_de(priv, dring, &tx_ctrl, &tx_desc, skb);
-	if (dring->is_xdp)
-		spin_unlock_bh(&dring->lock);
+	spin_unlock_bh(&dring->lock);
 	netsec_write(priv, NETSEC_REG_NRM_TX_PKTCNT, 1); /* submit another tx */
 
 	return NETDEV_TX_OK;
@@ -1262,7 +1253,6 @@ err:
 static void netsec_setup_tx_dring(struct netsec_priv *priv)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_TX];
-	struct bpf_prog *xdp_prog = READ_ONCE(priv->xdp_prog);
 	int i;
 
 	for (i = 0; i < DESC_NUM; i++) {
@@ -1275,12 +1265,6 @@ static void netsec_setup_tx_dring(struct netsec_priv *priv)
 		 */
 		de->attr = 1U << NETSEC_TX_SHIFT_OWN_FIELD;
 	}
-
-	if (xdp_prog)
-		dring->is_xdp = true;
-	else
-		dring->is_xdp = false;
-
 }
 
 static int netsec_setup_rx_dring(struct netsec_priv *priv)
-- 
cgit v1.2.3


From 17eac6c2db8b2cdfe33d40229bdda2acd86b304a Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Thu, 26 Sep 2019 16:40:14 -0600
Subject: selftests: Add kselftest-all and kselftest-install targets

Add kselftest-all target to build tests from the top level
Makefile. This is to simplify kselftest use-cases for CI and
distributions where build and test systems are different.

Current kselftest target builds and runs tests on a development
system which is a developer use-case.

Add kselftest-install target to install tests from the top level
Makefile. This is to simplify kselftest use-cases for CI and
distributions where build and test systems are different.

This change addresses requests from developers and testers to add
support for installing kselftest from the main Makefile.

In addition, make the install directory the same when install is
run using "make kselftest-install" or by running kselftest_install.sh.
Also fix the INSTALL_PATH variable conflict between main Makefile and
selftests Makefile.

Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Acked-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 Makefile                                     | 5 ++---
 tools/testing/selftests/Makefile             | 8 ++++++--
 tools/testing/selftests/kselftest_install.sh | 4 ++--
 3 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/Makefile b/Makefile
index 6f54f2f95743..02f7ede2f344 100644
--- a/Makefile
+++ b/Makefile
@@ -1237,9 +1237,8 @@ PHONY += kselftest
 kselftest:
 	$(Q)$(MAKE) -C $(srctree)/tools/testing/selftests run_tests
 
-PHONY += kselftest-clean
-kselftest-clean:
-	$(Q)$(MAKE) -C $(srctree)/tools/testing/selftests clean
+kselftest-%: FORCE
+	$(Q)$(MAKE) -C $(srctree)/tools/testing/selftests $*
 
 PHONY += kselftest-merge
 kselftest-merge:
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index c3feccb99ff5..bad18145ed1a 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -171,9 +171,12 @@ run_pstore_crash:
 # 1. output_dir=kernel_src
 # 2. a separate output directory is specified using O= KBUILD_OUTPUT
 # 3. a separate output directory is specified using KBUILD_OUTPUT
+# Avoid conflict with INSTALL_PATH set by the main Makefile
 #
-INSTALL_PATH ?= $(BUILD)/install
-INSTALL_PATH := $(abspath $(INSTALL_PATH))
+KSFT_INSTALL_PATH ?= $(BUILD)/kselftest_install
+KSFT_INSTALL_PATH := $(abspath $(KSFT_INSTALL_PATH))
+# Avoid changing the rest of the logic here and lib.mk.
+INSTALL_PATH := $(KSFT_INSTALL_PATH)
 ALL_SCRIPT := $(INSTALL_PATH)/run_kselftest.sh
 
 install: all
@@ -203,6 +206,7 @@ ifdef INSTALL_PATH
 		echo "[ -w /dev/kmsg ] && echo \"kselftest: Running tests in $$TARGET\" >> /dev/kmsg" >> $(ALL_SCRIPT); \
 		echo "cd $$TARGET" >> $(ALL_SCRIPT); \
 		echo -n "run_many" >> $(ALL_SCRIPT); \
+		echo -n "Emit Tests for $$TARGET\n"; \
 		$(MAKE) -s --no-print-directory OUTPUT=$$BUILD_TARGET -C $$TARGET emit_tests >> $(ALL_SCRIPT); \
 		echo "" >> $(ALL_SCRIPT);	    \
 		echo "cd \$$ROOT" >> $(ALL_SCRIPT); \
diff --git a/tools/testing/selftests/kselftest_install.sh b/tools/testing/selftests/kselftest_install.sh
index ec304463883c..e2e1911d62d5 100755
--- a/tools/testing/selftests/kselftest_install.sh
+++ b/tools/testing/selftests/kselftest_install.sh
@@ -24,12 +24,12 @@ main()
 		echo "$0: Installing in specified location - $install_loc ..."
 	fi
 
-	install_dir=$install_loc/kselftest
+	install_dir=$install_loc/kselftest_install
 
 # Create install directory
 	mkdir -p $install_dir
 # Build tests
-	INSTALL_PATH=$install_dir make install
+	KSFT_INSTALL_PATH=$install_dir make install
 }
 
 main "$@"
-- 
cgit v1.2.3


From c5f75a14a081dc2289739f3958af39392943b1c6 Mon Sep 17 00:00:00 2001
From: Adam Zerella <adam.zerella@gmail.com>
Date: Tue, 1 Oct 2019 21:16:58 +1000
Subject: docs: networking: Add title caret and missing doc

Resolving a couple of Sphinx documentation warnings
that are generated in the networking section.

- WARNING: document isn't included in any toctree
- WARNING: Title underline too short.

Signed-off-by: Adam Zerella <adam.zerella@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/device_drivers/index.rst | 1 +
 Documentation/networking/j1939.rst                | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/device_drivers/index.rst b/Documentation/networking/device_drivers/index.rst
index f51f92571e39..c1f7f75e5fd9 100644
--- a/Documentation/networking/device_drivers/index.rst
+++ b/Documentation/networking/device_drivers/index.rst
@@ -23,6 +23,7 @@ Contents:
    intel/ice
    google/gve
    mellanox/mlx5
+   netronome/nfp
    pensando/ionic
 
 .. only::  subproject and html
diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst
index ce7e7a044e08..dc60b13fcd09 100644
--- a/Documentation/networking/j1939.rst
+++ b/Documentation/networking/j1939.rst
@@ -272,7 +272,7 @@ supported flags are:
 * MSG_DONTWAIT, i.e. non-blocking operation.
 
 recvmsg(2)
-^^^^^^^^^
+^^^^^^^^^^
 
 In most cases recvmsg(2) is needed if you want to extract more information than
 recvfrom(2) can provide. For example package priority and timestamp. The
-- 
cgit v1.2.3


From 6de6d18591b5781b7fdfb9d0ade0a4b5afacf882 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 1 Oct 2019 16:21:40 +0200
Subject: ionic: select CONFIG_NET_DEVLINK

When no other driver selects the devlink library code, ionic
produces a link failure:

drivers/net/ethernet/pensando/ionic/ionic_devlink.o: In function `ionic_devlink_alloc':
ionic_devlink.c:(.text+0xd): undefined reference to `devlink_alloc'
drivers/net/ethernet/pensando/ionic/ionic_devlink.o: In function `ionic_devlink_register':
ionic_devlink.c:(.text+0x71): undefined reference to `devlink_register'

Add the same 'select' statement that the other drivers use here.

Fixes: fbfb8031533c ("ionic: Add hardware init and device commands")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/pensando/Kconfig b/drivers/net/ethernet/pensando/Kconfig
index bd0583e409df..d25b88f53de4 100644
--- a/drivers/net/ethernet/pensando/Kconfig
+++ b/drivers/net/ethernet/pensando/Kconfig
@@ -20,6 +20,7 @@ if NET_VENDOR_PENSANDO
 config IONIC
 	tristate "Pensando Ethernet IONIC Support"
 	depends on 64BIT && PCI
+	select NET_DEVLINK
 	help
 	  This enables the support for the Pensando family of Ethernet
 	  adapters.  More specific information on this driver can be
-- 
cgit v1.2.3


From c67d970f0ea8dcc423e112137d34334fa0abb8ec Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 30 Sep 2019 10:20:25 +0100
Subject: Btrfs: fix memory leak due to concurrent append writes with fiemap

When we have a buffered write that starts at an offset greater than or
equals to the file's size happening concurrently with a full ranged
fiemap, we can end up leaking an extent state structure.

Suppose we have a file with a size of 1Mb, and before the buffered write
and fiemap are performed, it has a single extent state in its io tree
representing the range from 0 to 1Mb, with the EXTENT_DELALLOC bit set.

The following sequence diagram shows how the memory leak happens if a
fiemap a buffered write, starting at offset 1Mb and with a length of
4Kb, are performed concurrently.

          CPU 1                                                  CPU 2

  extent_fiemap()
    --> it's a full ranged fiemap
        range from 0 to LLONG_MAX - 1
        (9223372036854775807)

    --> locks range in the inode's
        io tree
      --> after this we have 2 extent
          states in the io tree:
          --> 1 for range [0, 1Mb[ with
              the bits EXTENT_LOCKED and
              EXTENT_DELALLOC_BITS set
          --> 1 for the range
              [1Mb, LLONG_MAX[ with
              the EXTENT_LOCKED bit set

                                                  --> start buffered write at offset
                                                      1Mb with a length of 4Kb

                                                  btrfs_file_write_iter()

                                                    btrfs_buffered_write()
                                                      --> cached_state is NULL

                                                      lock_and_cleanup_extent_if_need()
                                                        --> returns 0 and does not lock
                                                            range because it starts
                                                            at current i_size / eof

                                                      --> cached_state remains NULL

                                                      btrfs_dirty_pages()
                                                        btrfs_set_extent_delalloc()
                                                          (...)
                                                          __set_extent_bit()

                                                            --> splits extent state for range
                                                                [1Mb, LLONG_MAX[ and now we
                                                                have 2 extent states:

                                                                --> one for the range
                                                                    [1Mb, 1Mb + 4Kb[ with
                                                                    EXTENT_LOCKED set
                                                                --> another one for the range
                                                                    [1Mb + 4Kb, LLONG_MAX[ with
                                                                    EXTENT_LOCKED set as well

                                                            --> sets EXTENT_DELALLOC on the
                                                                extent state for the range
                                                                [1Mb, 1Mb + 4Kb[
                                                            --> caches extent state
                                                                [1Mb, 1Mb + 4Kb[ into
                                                                @cached_state because it has
                                                                the bit EXTENT_LOCKED set

                                                    --> btrfs_buffered_write() ends up
                                                        with a non-NULL cached_state and
                                                        never calls anything to release its
                                                        reference on it, resulting in a
                                                        memory leak

Fix this by calling free_extent_state() on cached_state if the range was
not locked by lock_and_cleanup_extent_if_need().

The same issue can happen if anything else other than fiemap locks a range
that covers eof and beyond.

This could be triggered, sporadically, by test case generic/561 from the
fstests suite, which makes duperemove run concurrently with fsstress, and
duperemove does plenty of calls to fiemap. When CONFIG_BTRFS_DEBUG is set
the leak is reported in dmesg/syslog when removing the btrfs module with
a message like the following:

  [77100.039461] BTRFS: state leak: start 6574080 end 6582271 state 16402 in tree 0 refs 1

Otherwise (CONFIG_BTRFS_DEBUG not set) detectable with kmemleak.

CC: stable@vger.kernel.org # 4.16+
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/file.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 8fe4eb7e5045..27e5b269e729 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1591,7 +1591,6 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct page **pages = NULL;
-	struct extent_state *cached_state = NULL;
 	struct extent_changeset *data_reserved = NULL;
 	u64 release_bytes = 0;
 	u64 lockstart;
@@ -1611,6 +1610,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
 		return -ENOMEM;
 
 	while (iov_iter_count(i) > 0) {
+		struct extent_state *cached_state = NULL;
 		size_t offset = offset_in_page(pos);
 		size_t sector_offset;
 		size_t write_bytes = min(iov_iter_count(i),
@@ -1758,9 +1758,20 @@ again:
 		if (copied > 0)
 			ret = btrfs_dirty_pages(inode, pages, dirty_pages,
 						pos, copied, &cached_state);
+
+		/*
+		 * If we have not locked the extent range, because the range's
+		 * start offset is >= i_size, we might still have a non-NULL
+		 * cached extent state, acquired while marking the extent range
+		 * as delalloc through btrfs_dirty_pages(). Therefore free any
+		 * possible cached extent state to avoid a memory leak.
+		 */
 		if (extents_locked)
 			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
 					     lockstart, lockend, &cached_state);
+		else
+			free_extent_state(cached_state);
+
 		btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes,
 					       true);
 		if (ret) {
-- 
cgit v1.2.3


From 4203e968947071586a98b5314fd7ffdea3b4f971 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Sep 2019 16:27:25 -0400
Subject: btrfs: fix incorrect updating of log root tree

We've historically had reports of being unable to mount file systems
because the tree log root couldn't be read.  Usually this is the "parent
transid failure", but could be any of the related errors, including
"fsid mismatch" or "bad tree block", depending on which block got
allocated.

The modification of the individual log root items are serialized on the
per-log root root_mutex.  This means that any modification to the
per-subvol log root_item is completely protected.

However we update the root item in the log root tree outside of the log
root tree log_mutex.  We do this in order to allow multiple subvolumes
to be updated in each log transaction.

This is problematic however because when we are writing the log root
tree out we update the super block with the _current_ log root node
information.  Since these two operations happen independently of each
other, you can end up updating the log root tree in between writing out
the dirty blocks and setting the super block to point at the current
root.

This means we'll point at the new root node that hasn't been written
out, instead of the one we should be pointing at.  Thus whatever garbage
or old block we end up pointing at complains when we mount the file
system later and try to replay the log.

Fix this by copying the log's root item into a local root item copy.
Then once we're safely under the log_root_tree->log_mutex we update the
root item in the log_root_tree.  This way we do not modify the
log_root_tree while we're committing it, fixing the problem.

CC: stable@vger.kernel.org # 4.4+
Reviewed-by: Chris Mason <clm@fb.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 36 +++++++++++++++++++++++++++---------
 1 file changed, 27 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 77b6797fcac3..2488eb4b70fc 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2932,7 +2932,8 @@ out:
  * in the tree of log roots
  */
 static int update_log_root(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *log)
+			   struct btrfs_root *log,
+			   struct btrfs_root_item *root_item)
 {
 	struct btrfs_fs_info *fs_info = log->fs_info;
 	int ret;
@@ -2940,10 +2941,10 @@ static int update_log_root(struct btrfs_trans_handle *trans,
 	if (log->log_transid == 1) {
 		/* insert root item on the first sync */
 		ret = btrfs_insert_root(trans, fs_info->log_root_tree,
-				&log->root_key, &log->root_item);
+				&log->root_key, root_item);
 	} else {
 		ret = btrfs_update_root(trans, fs_info->log_root_tree,
-				&log->root_key, &log->root_item);
+				&log->root_key, root_item);
 	}
 	return ret;
 }
@@ -3041,6 +3042,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_root *log = root->log_root;
 	struct btrfs_root *log_root_tree = fs_info->log_root_tree;
+	struct btrfs_root_item new_root_item;
 	int log_transid = 0;
 	struct btrfs_log_ctx root_log_ctx;
 	struct blk_plug plug;
@@ -3104,17 +3106,25 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
+	/*
+	 * We _must_ update under the root->log_mutex in order to make sure we
+	 * have a consistent view of the log root we are trying to commit at
+	 * this moment.
+	 *
+	 * We _must_ copy this into a local copy, because we are not holding the
+	 * log_root_tree->log_mutex yet.  This is important because when we
+	 * commit the log_root_tree we must have a consistent view of the
+	 * log_root_tree when we update the super block to point at the
+	 * log_root_tree bytenr.  If we update the log_root_tree here we'll race
+	 * with the commit and possibly point at the new block which we may not
+	 * have written out.
+	 */
 	btrfs_set_root_node(&log->root_item, log->node);
+	memcpy(&new_root_item, &log->root_item, sizeof(new_root_item));
 
 	root->log_transid++;
 	log->log_transid = root->log_transid;
 	root->log_start_pid = 0;
-	/*
-	 * Update or create log root item under the root's log_mutex to prevent
-	 * races with concurrent log syncs that can lead to failure to update
-	 * log root item because it was not created yet.
-	 */
-	ret = update_log_root(trans, log);
 	/*
 	 * IO has been started, blocks of the log tree have WRITTEN flag set
 	 * in their headers. new modifications of the log will be written to
@@ -3135,6 +3145,14 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	mutex_unlock(&log_root_tree->log_mutex);
 
 	mutex_lock(&log_root_tree->log_mutex);
+
+	/*
+	 * Now we are safe to update the log_root_tree because we're under the
+	 * log_mutex, and we're a current writer so we're holding the commit
+	 * open until we drop the log_mutex.
+	 */
+	ret = update_log_root(trans, log, &new_root_item);
+
 	if (atomic_dec_and_test(&log_root_tree->log_writers)) {
 		/* atomic_dec_and_test implies a barrier */
 		cond_wake_up_nomb(&log_root_tree->log_writer_wait);
-- 
cgit v1.2.3


From 895b5c9f206eb7d25dc1360a8ccfc5958895eb89 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Sun, 29 Sep 2019 20:54:03 +0200
Subject: netfilter: drop bridge nf reset from nf_reset

commit 174e23810cd31
("sk_buff: drop all skb extensions on free and skb scrubbing") made napi
recycle always drop skb extensions.  The additional skb_ext_del() that is
performed via nf_reset on napi skb recycle is not needed anymore.

Most nf_reset() calls in the stack are there so queued skb won't block
'rmmod nf_conntrack' indefinitely.

This removes the skb_ext_del from nf_reset, and renames it to a more
fitting nf_reset_ct().

In a few selected places, add a call to skb_ext_reset to make sure that
no active extensions remain.

I am submitting this for "net", because we're still early in the release
cycle.  The patch applies to net-next too, but I think the rename causes
needless divergence between those trees.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 drivers/net/ppp/pptp.c                | 4 ++--
 drivers/net/tun.c                     | 2 +-
 drivers/net/virtio_net.c              | 2 +-
 drivers/net/vrf.c                     | 8 ++++----
 drivers/net/wireless/mac80211_hwsim.c | 4 ++--
 drivers/staging/octeon/ethernet-tx.c  | 6 ++----
 include/linux/skbuff.h                | 5 +----
 net/batman-adv/soft-interface.c       | 2 +-
 net/core/skbuff.c                     | 2 +-
 net/dccp/ipv4.c                       | 2 +-
 net/ipv4/ip_input.c                   | 2 +-
 net/ipv4/ipmr.c                       | 4 ++--
 net/ipv4/netfilter/nf_dup_ipv4.c      | 2 +-
 net/ipv4/raw.c                        | 2 +-
 net/ipv4/tcp_ipv4.c                   | 2 +-
 net/ipv4/udp.c                        | 4 ++--
 net/ipv6/ip6_input.c                  | 2 +-
 net/ipv6/netfilter/nf_dup_ipv6.c      | 2 +-
 net/ipv6/raw.c                        | 2 +-
 net/l2tp/l2tp_core.c                  | 2 +-
 net/l2tp/l2tp_eth.c                   | 2 +-
 net/l2tp/l2tp_ip.c                    | 2 +-
 net/l2tp/l2tp_ip6.c                   | 2 +-
 net/netfilter/ipvs/ip_vs_xmit.c       | 2 +-
 net/openvswitch/vport-internal_dev.c  | 2 +-
 net/packet/af_packet.c                | 4 ++--
 net/sctp/input.c                      | 2 +-
 net/xfrm/xfrm_input.c                 | 2 +-
 net/xfrm/xfrm_interface.c             | 2 +-
 net/xfrm/xfrm_output.c                | 2 +-
 net/xfrm/xfrm_policy.c                | 2 +-
 31 files changed, 40 insertions(+), 45 deletions(-)

diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 734de7de03f7..e1fabb3e3246 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -238,7 +238,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	skb_dst_drop(skb);
 	skb_dst_set(skb, &rt->dst);
 
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	skb->ip_summed = CHECKSUM_NONE;
 	ip_select_ident(net, skb, NULL);
@@ -358,7 +358,7 @@ static int pptp_rcv(struct sk_buff *skb)
 	po = lookup_chan(htons(header->call_id), iph->saddr);
 	if (po) {
 		skb_dst_drop(skb);
-		nf_reset(skb);
+		nf_reset_ct(skb);
 		return sk_receive_skb(sk_pppox(po), skb, 0);
 	}
 drop:
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index aab0be40d443..812dc3a65efb 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1104,7 +1104,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	skb_orphan(skb);
 
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	if (ptr_ring_produce(&tfile->tx_ring, skb))
 		goto drop;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ba98e0971b84..5a635f028bdc 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1585,7 +1585,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Don't wait up for transmitted skbs to be freed. */
 	if (!use_napi) {
 		skb_orphan(skb);
-		nf_reset(skb);
+		nf_reset_ct(skb);
 	}
 
 	/* If running out of space, stop queue to avoid getting packets that we
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index a4b38a980c3c..ee52bde058df 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -366,7 +366,7 @@ static int vrf_finish_output6(struct net *net, struct sock *sk,
 	struct neighbour *neigh;
 	int ret;
 
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->dev = dev;
@@ -459,7 +459,7 @@ static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev,
 
 	/* reset skb device */
 	if (likely(err == 1))
-		nf_reset(skb);
+		nf_reset_ct(skb);
 	else
 		skb = NULL;
 
@@ -560,7 +560,7 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	bool is_v6gw = false;
 	int ret = -EINVAL;
 
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	/* Be paranoid, rather than too clever. */
 	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
@@ -670,7 +670,7 @@ static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev,
 
 	/* reset skb device */
 	if (likely(err == 1))
-		nf_reset(skb);
+		nf_reset_ct(skb);
 	else
 		skb = NULL;
 
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 635956024e88..45c73a6f09a1 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -1261,8 +1261,8 @@ static bool mac80211_hwsim_tx_frame_no_nl(struct ieee80211_hw *hw,
 	skb_orphan(skb);
 	skb_dst_drop(skb);
 	skb->mark = 0;
-	secpath_reset(skb);
-	nf_reset(skb);
+	skb_ext_reset(skb);
+	nf_reset_ct(skb);
 
 	/*
 	 * Get absolute mactime here so all HWs RX at the "same time", and
diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c
index c64728fc21f2..a62057555d1b 100644
--- a/drivers/staging/octeon/ethernet-tx.c
+++ b/drivers/staging/octeon/ethernet-tx.c
@@ -349,10 +349,8 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	dst_release(skb_dst(skb));
 	skb_dst_set(skb, NULL);
-#ifdef CONFIG_XFRM
-	secpath_reset(skb);
-#endif
-	nf_reset(skb);
+	skb_ext_reset(skb);
+	nf_reset_ct(skb);
 
 #ifdef CONFIG_NET_SCHED
 	skb->tc_index = 0;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e7d3b1a513ef..4351577b14d7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4160,15 +4160,12 @@ static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {}
 static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {}
 #endif /* CONFIG_SKB_EXTENSIONS */
 
-static inline void nf_reset(struct sk_buff *skb)
+static inline void nf_reset_ct(struct sk_buff *skb)
 {
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 	nf_conntrack_put(skb_nfct(skb));
 	skb->_nfct = 0;
 #endif
-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
-	skb_ext_del(skb, SKB_EXT_BRIDGE_NF);
-#endif
 }
 
 static inline void nf_reset_trace(struct sk_buff *skb)
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index a1146cb10919..9cbed6f5a85a 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -436,7 +436,7 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	/* clean the netfilter state now that the batman-adv header has been
 	 * removed
 	 */
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
 		goto dropped;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 01d65206f4fb..529133611ea2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5120,7 +5120,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->ignore_df = 0;
 	skb_dst_drop(skb);
 	skb_ext_reset(skb);
-	nf_reset(skb);
+	nf_reset_ct(skb);
 	nf_reset_trace(skb);
 
 #ifdef CONFIG_NET_SWITCHDEV
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index b685bc82f8d0..d9b4200ed12d 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -871,7 +871,7 @@ lookup:
 
 	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_and_relse;
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	return __sk_receive_skb(sk, skb, 1, dh->dccph_doff * 4, refcounted);
 
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 1e2392b7c64e..c59a78a267c3 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -199,7 +199,7 @@ resubmit:
 				kfree_skb(skb);
 				return;
 			}
-			nf_reset(skb);
+			nf_reset_ct(skb);
 		}
 		ret = INDIRECT_CALL_2(ipprot->handler, tcp_v4_rcv, udp_rcv,
 				      skb);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 313470f6bb14..716d5472c022 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1794,7 +1794,7 @@ static void ip_encap(struct net *net, struct sk_buff *skb,
 	ip_send_check(iph);
 
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
-	nf_reset(skb);
+	nf_reset_ct(skb);
 }
 
 static inline int ipmr_forward_finish(struct net *net, struct sock *sk,
@@ -2140,7 +2140,7 @@ int ip_mr_input(struct sk_buff *skb)
 
 			mroute_sk = rcu_dereference(mrt->mroute_sk);
 			if (mroute_sk) {
-				nf_reset(skb);
+				nf_reset_ct(skb);
 				raw_rcv(mroute_sk, skb);
 				return 0;
 			}
diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c
index af3fbf76dbd3..6cc5743c553a 100644
--- a/net/ipv4/netfilter/nf_dup_ipv4.c
+++ b/net/ipv4/netfilter/nf_dup_ipv4.c
@@ -65,7 +65,7 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum,
 
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	/* Avoid counting cloned packets towards the original connection. */
-	nf_reset(skb);
+	nf_reset_ct(skb);
 	nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
 #endif
 	/*
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 80da5a66d5d7..3183413ebc6c 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -332,7 +332,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb)
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	skb_push(skb, skb->data - skb_network_header(skb));
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2ee45e3755e9..bf124b1742df 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1916,7 +1916,7 @@ process:
 	if (tcp_v4_inbound_md5_hash(sk, skb))
 		goto discard_and_relse;
 
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	if (tcp_filter(sk, skb))
 		goto discard_and_relse;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index cf755156a684..e8443cc5c1ab 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1969,7 +1969,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto drop;
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) {
 		int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
@@ -2298,7 +2298,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 		goto drop;
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	/* No socket. Drop packet silently, if checksum is wrong */
 	if (udp_lib_checksum_complete(skb))
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index d432d0011c16..7e5df23cbe7b 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -371,7 +371,7 @@ resubmit_final:
 			/* Free reference early: we don't need it any more,
 			   and it may hold ip_conntrack module loaded
 			   indefinitely. */
-			nf_reset(skb);
+			nf_reset_ct(skb);
 
 			skb_postpull_rcsum(skb, skb_network_header(skb),
 					   skb_network_header_len(skb));
diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c
index e6c9da9866b1..a0a2de30be3e 100644
--- a/net/ipv6/netfilter/nf_dup_ipv6.c
+++ b/net/ipv6/netfilter/nf_dup_ipv6.c
@@ -54,7 +54,7 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum,
 		return;
 
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
-	nf_reset(skb);
+	nf_reset_ct(skb);
 	nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
 #endif
 	if (hooknum == NF_INET_PRE_ROUTING ||
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 6e1888ee4036..a77f6b7d3a7c 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -215,7 +215,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
 
 			/* Not releasing hash table! */
 			if (clone) {
-				nf_reset(clone);
+				nf_reset_ct(clone);
 				rawv6_rcv(sk, clone);
 			}
 		}
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 105e5a7092e7..f82ea12bac37 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1078,7 +1078,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
 	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
 			      IPSKB_REROUTED);
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index bd3f39349d40..fd5ac2788e45 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -151,7 +151,7 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb,
 	skb->ip_summed = CHECKSUM_NONE;
 
 	skb_dst_drop(skb);
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	rcu_read_lock();
 	dev = rcu_dereference(spriv->dev);
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 622833317dcb..0d7c887a2b75 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -193,7 +193,7 @@ pass_up:
 	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_put;
 
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	return sk_receive_skb(sk, skb, 1);
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 687e23a8b326..802f19aba7e3 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -206,7 +206,7 @@ pass_up:
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
 		goto discard_put;
 
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	return sk_receive_skb(sk, skb, 1);
 
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 9c464d24beec..888d3068a492 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -613,7 +613,7 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb,
 	if (unlikely(cp->flags & IP_VS_CONN_F_NFCT))
 		ret = ip_vs_confirm_conntrack(skb);
 	if (ret == NF_ACCEPT) {
-		nf_reset(skb);
+		nf_reset_ct(skb);
 		skb_forward_csum(skb);
 	}
 	return ret;
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index d2437b5b2f6a..21c90d3a7ebf 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -237,7 +237,7 @@ static netdev_tx_t internal_dev_recv(struct sk_buff *skb)
 	}
 
 	skb_dst_drop(skb);
-	nf_reset(skb);
+	nf_reset_ct(skb);
 	secpath_reset(skb);
 
 	skb->pkt_type = PACKET_HOST;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e2742b006d25..82a50e850245 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1821,7 +1821,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev,
 	skb_dst_drop(skb);
 
 	/* drop conntrack reference */
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	spkt = &PACKET_SKB_CB(skb)->sa.pkt;
 
@@ -2121,7 +2121,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 	skb_dst_drop(skb);
 
 	/* drop conntrack reference */
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	spin_lock(&sk->sk_receive_queue.lock);
 	po->stats.stats1.tp_packets++;
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 1008cdc44dd6..5a070fb5b278 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -201,7 +201,7 @@ int sctp_rcv(struct sk_buff *skb)
 
 	if (!xfrm_policy_check(sk, XFRM_POLICY_IN, skb, family))
 		goto discard_release;
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	if (sk_filter(sk, skb))
 		goto discard_release;
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 6088bc2dc11e..9b599ed66d97 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -706,7 +706,7 @@ resume:
 	if (err)
 		goto drop;
 
-	nf_reset(skb);
+	nf_reset_ct(skb);
 
 	if (decaps) {
 		sp = skb_sec_path(skb);
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 2ab4859df55a..0f5131bc3342 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -185,7 +185,7 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->skb_iif = 0;
 	skb->ignore_df = 0;
 	skb_dst_drop(skb);
-	nf_reset(skb);
+	nf_reset_ct(skb);
 	nf_reset_trace(skb);
 
 	if (!xnet)
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 9499b35feb92..b1db55b50ba1 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -502,7 +502,7 @@ int xfrm_output_resume(struct sk_buff *skb, int err)
 	struct net *net = xs_net(skb_dst(skb)->xfrm);
 
 	while (likely((err = xfrm_output_one(skb, err)) == 0)) {
-		nf_reset(skb);
+		nf_reset_ct(skb);
 
 		err = skb_dst(skb)->ops->local_out(net, skb->sk, skb);
 		if (unlikely(err != 1))
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 21e939235b39..f2d1e573ea55 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2808,7 +2808,7 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 			continue;
 		}
 
-		nf_reset(skb);
+		nf_reset_ct(skb);
 		skb_dst_drop(skb);
 		skb_dst_set(skb, dst);
 
-- 
cgit v1.2.3


From 34a4c95abd25ab41fb390b985a08a651b1fa0b0f Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Mon, 30 Sep 2019 11:05:49 +0200
Subject: netfilter: nft_connlimit: disable bh on garbage collection

BH must be disabled when invoking nf_conncount_gc_list() to perform
garbage collection, otherwise deadlock might happen.

  nf_conncount_add+0x1f/0x50 [nf_conncount]
  nft_connlimit_eval+0x4c/0xe0 [nft_connlimit]
  nft_dynset_eval+0xb5/0x100 [nf_tables]
  nft_do_chain+0xea/0x420 [nf_tables]
  ? sch_direct_xmit+0x111/0x360
  ? noqueue_init+0x10/0x10
  ? __qdisc_run+0x84/0x510
  ? tcp_packet+0x655/0x1610 [nf_conntrack]
  ? ip_finish_output2+0x1a7/0x430
  ? tcp_error+0x130/0x150 [nf_conntrack]
  ? nf_conntrack_in+0x1fc/0x4c0 [nf_conntrack]
  nft_do_chain_ipv4+0x66/0x80 [nf_tables]
  nf_hook_slow+0x44/0xc0
  ip_rcv+0xb5/0xd0
  ? ip_rcv_finish_core.isra.19+0x360/0x360
  __netif_receive_skb_one_core+0x52/0x70
  netif_receive_skb_internal+0x34/0xe0
  napi_gro_receive+0xba/0xe0
  e1000_clean_rx_irq+0x1e9/0x420 [e1000e]
  e1000e_poll+0xbe/0x290 [e1000e]
  net_rx_action+0x149/0x3b0
  __do_softirq+0xde/0x2d8
  irq_exit+0xba/0xc0
  do_IRQ+0x85/0xd0
  common_interrupt+0xf/0xf
  </IRQ>
  RIP: 0010:nf_conncount_gc_list+0x3b/0x130 [nf_conncount]

Fixes: 2f971a8f4255 ("netfilter: nf_conncount: move all list iterations under spinlock")
Reported-by: Laura Garcia Liebana <nevola@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_connlimit.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c
index af1497ab9464..69d6173f91e2 100644
--- a/net/netfilter/nft_connlimit.c
+++ b/net/netfilter/nft_connlimit.c
@@ -218,8 +218,13 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx,
 static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr)
 {
 	struct nft_connlimit *priv = nft_expr_priv(expr);
+	bool ret;
 
-	return nf_conncount_gc_list(net, &priv->list);
+	local_bh_disable();
+	ret = nf_conncount_gc_list(net, &priv->list);
+	local_bh_enable();
+
+	return ret;
 }
 
 static struct nft_expr_type nft_connlimit_type;
-- 
cgit v1.2.3


From 9a9251a3534745d08a92abfeca0ca467b912b5f6 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 29 Sep 2019 02:37:22 +0300
Subject: net: sched: taprio: Avoid division by zero on invalid link speed

The check in taprio_set_picos_per_byte is currently not robust enough
and will trigger this division by zero, due to e.g. PHYLINK not setting
kset->base.speed when there is no PHY connected:

[   27.109992] Division by zero in kernel.
[   27.113842] CPU: 1 PID: 198 Comm: tc Not tainted 5.3.0-rc5-01246-gc4006b8c2637-dirty #212
[   27.121974] Hardware name: Freescale LS1021A
[   27.126234] [<c03132e0>] (unwind_backtrace) from [<c030d8b8>] (show_stack+0x10/0x14)
[   27.133938] [<c030d8b8>] (show_stack) from [<c10b21b0>] (dump_stack+0xb0/0xc4)
[   27.141124] [<c10b21b0>] (dump_stack) from [<c10af97c>] (Ldiv0_64+0x8/0x18)
[   27.148052] [<c10af97c>] (Ldiv0_64) from [<c0700260>] (div64_u64+0xcc/0xf0)
[   27.154978] [<c0700260>] (div64_u64) from [<c07002d0>] (div64_s64+0x4c/0x68)
[   27.161993] [<c07002d0>] (div64_s64) from [<c0f3d890>] (taprio_set_picos_per_byte+0xe8/0xf4)
[   27.170388] [<c0f3d890>] (taprio_set_picos_per_byte) from [<c0f3f614>] (taprio_change+0x668/0xcec)
[   27.179302] [<c0f3f614>] (taprio_change) from [<c0f2bc24>] (qdisc_create+0x1fc/0x4f4)
[   27.187091] [<c0f2bc24>] (qdisc_create) from [<c0f2c0c8>] (tc_modify_qdisc+0x1ac/0x6f8)
[   27.195055] [<c0f2c0c8>] (tc_modify_qdisc) from [<c0ee9604>] (rtnetlink_rcv_msg+0x268/0x2dc)
[   27.203449] [<c0ee9604>] (rtnetlink_rcv_msg) from [<c0f4fef0>] (netlink_rcv_skb+0xe0/0x114)
[   27.211756] [<c0f4fef0>] (netlink_rcv_skb) from [<c0f4f6cc>] (netlink_unicast+0x1b4/0x22c)
[   27.219977] [<c0f4f6cc>] (netlink_unicast) from [<c0f4fa84>] (netlink_sendmsg+0x284/0x340)
[   27.228198] [<c0f4fa84>] (netlink_sendmsg) from [<c0eae5fc>] (sock_sendmsg+0x14/0x24)
[   27.235988] [<c0eae5fc>] (sock_sendmsg) from [<c0eaedf8>] (___sys_sendmsg+0x214/0x228)
[   27.243863] [<c0eaedf8>] (___sys_sendmsg) from [<c0eb015c>] (__sys_sendmsg+0x50/0x8c)
[   27.251652] [<c0eb015c>] (__sys_sendmsg) from [<c0301000>] (ret_fast_syscall+0x0/0x54)
[   27.259524] Exception stack(0xe8045fa8 to 0xe8045ff0)
[   27.264546] 5fa0:                   b6f608c8 000000f8 00000003 bed7e2f0 00000000 00000000
[   27.272681] 5fc0: b6f608c8 000000f8 004ce54c 00000128 5d3ce8c7 00000000 00000026 00505c9c
[   27.280812] 5fe0: 00000070 bed7e298 004ddd64 b6dd1e64

Russell King points out that the ethtool API says zero is a valid return
value of __ethtool_get_link_ksettings:

   * If it is enabled then they are read-only; if the link
   * is up they represent the negotiated link mode; if the link is down,
   * the speed is 0, %SPEED_UNKNOWN or the highest enabled speed and
   * @duplex is %DUPLEX_UNKNOWN or the best enabled duplex mode.

  So, it seems that taprio is not following the API... I'd suggest either
  fixing taprio, or getting agreement to change the ethtool API.

The chosen path was to fix taprio.

Fixes: 7b9eba7ba0c1 ("net/sched: taprio: fix picos_per_byte miscalculation")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_taprio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 2aab46ada94f..68b543f85a96 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1044,7 +1044,7 @@ static void taprio_set_picos_per_byte(struct net_device *dev,
 	if (err < 0)
 		goto skip;
 
-	if (ecmd.base.speed != SPEED_UNKNOWN)
+	if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN)
 		speed = ecmd.base.speed;
 
 skip:
-- 
cgit v1.2.3


From 83c8c3cf45163f0c823db37be6ab04dfcf8ac751 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Sun, 29 Sep 2019 02:39:48 +0300
Subject: net: sched: cbs: Avoid division by zero when calculating the port
 rate

As explained in the "net: sched: taprio: Avoid division by zero on
invalid link speed" commit, it is legal for the ethtool API to return
zero as a link speed. So guard against it to ensure we don't perform a
division by zero in kernel.

Fixes: e0a7683d30e9 ("net/sched: cbs: fix port_rate miscalculation")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 1bef152c5721..b2905b03a432 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -306,7 +306,7 @@ static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q)
 	if (err < 0)
 		goto skip;
 
-	if (ecmd.base.speed != SPEED_UNKNOWN)
+	if (ecmd.base.speed && ecmd.base.speed != SPEED_UNKNOWN)
 		speed = ecmd.base.speed;
 
 skip:
-- 
cgit v1.2.3


From d2c50b1cd94528aea8c8e9abb4cce81590f32cc4 Mon Sep 17 00:00:00 2001
From: Wen Yang <wenyang@linux.alibaba.com>
Date: Sun, 29 Sep 2019 14:54:24 +0800
Subject: net: mscc: ocelot: add missing of_node_put after calling
 of_get_child_by_name

of_node_put needs to be called when the device node which is got
from of_get_child_by_name finished using.
In both cases of success and failure, we need to release 'ports',
so clean up the code using goto.

fixes: a556c76adc05 ("net: mscc: Add initial Ocelot switch support")
Signed-off-by: Wen Yang <wenyang@linux.alibaba.com>
Cc: Alexandre Belloni <alexandre.belloni@bootlin.com>
Cc: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_board.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index b063eb78fa0c..aac115136720 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -388,13 +388,14 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 			continue;
 
 		phy = of_phy_find_device(phy_node);
+		of_node_put(phy_node);
 		if (!phy)
 			continue;
 
 		err = ocelot_probe_port(ocelot, port, regs, phy);
 		if (err) {
 			of_node_put(portnp);
-			return err;
+			goto out_put_ports;
 		}
 
 		phy_mode = of_get_phy_mode(portnp);
@@ -422,7 +423,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 				"invalid phy mode for port%d, (Q)SGMII only\n",
 				port);
 			of_node_put(portnp);
-			return -EINVAL;
+			err = -EINVAL;
+			goto out_put_ports;
 		}
 
 		serdes = devm_of_phy_get(ocelot->dev, portnp, NULL);
@@ -435,7 +437,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 					"missing SerDes phys for port%d\n",
 					port);
 
-			goto err_probe_ports;
+			of_node_put(portnp);
+			goto out_put_ports;
 		}
 
 		ocelot->ports[port]->serdes = serdes;
@@ -447,9 +450,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 
 	dev_info(&pdev->dev, "Ocelot switch probed\n");
 
-	return 0;
-
-err_probe_ports:
+out_put_ports:
+	of_node_put(ports);
 	return err;
 }
 
-- 
cgit v1.2.3


From f32eb9d80470dab05df26b6efd02d653c72e6a11 Mon Sep 17 00:00:00 2001
From: Wen Yang <wenyang@linux.alibaba.com>
Date: Sun, 29 Sep 2019 15:00:47 +0800
Subject: net: dsa: rtl8366rb: add missing of_node_put after calling
 of_get_child_by_name

of_node_put needs to be called when the device node which is got
from of_get_child_by_name finished using.
irq_domain_add_linear() also calls of_node_get() to increase refcount,
so irq_domain will not be affected when it is released.

Fixes: d8652956cf37 ("net: dsa: realtek-smi: Add Realtek SMI driver")
Signed-off-by: Wen Yang <wenyang@linux.alibaba.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Vivien Didelot <vivien.didelot@gmail.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rtl8366rb.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c
index a268085ffad2..f5cc8b0a7c74 100644
--- a/drivers/net/dsa/rtl8366rb.c
+++ b/drivers/net/dsa/rtl8366rb.c
@@ -507,7 +507,8 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi)
 	irq = of_irq_get(intc, 0);
 	if (irq <= 0) {
 		dev_err(smi->dev, "failed to get parent IRQ\n");
-		return irq ? irq : -EINVAL;
+		ret = irq ? irq : -EINVAL;
+		goto out_put_node;
 	}
 
 	/* This clears the IRQ status register */
@@ -515,7 +516,7 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi)
 			  &val);
 	if (ret) {
 		dev_err(smi->dev, "can't read interrupt status\n");
-		return ret;
+		goto out_put_node;
 	}
 
 	/* Fetch IRQ edge information from the descriptor */
@@ -537,7 +538,7 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi)
 				 val);
 	if (ret) {
 		dev_err(smi->dev, "could not configure IRQ polarity\n");
-		return ret;
+		goto out_put_node;
 	}
 
 	ret = devm_request_threaded_irq(smi->dev, irq, NULL,
@@ -545,7 +546,7 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi)
 					"RTL8366RB", smi);
 	if (ret) {
 		dev_err(smi->dev, "unable to request irq: %d\n", ret);
-		return ret;
+		goto out_put_node;
 	}
 	smi->irqdomain = irq_domain_add_linear(intc,
 					       RTL8366RB_NUM_INTERRUPT,
@@ -553,12 +554,15 @@ static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi)
 					       smi);
 	if (!smi->irqdomain) {
 		dev_err(smi->dev, "failed to create IRQ domain\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out_put_node;
 	}
 	for (i = 0; i < smi->num_ports; i++)
 		irq_set_parent(irq_create_mapping(smi->irqdomain, i), irq);
 
-	return 0;
+out_put_node:
+	of_node_put(intc);
+	return ret;
 }
 
 static int rtl8366rb_set_addr(struct realtek_smi *smi)
-- 
cgit v1.2.3


From 93c2fcb01ae919b6e882b0931383d33aaa9bf7a6 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Mon, 30 Sep 2019 11:52:21 +0530
Subject: devlink: Fix error handling in param and info_get dumpit cb

If any of the param or info_get op returns error, dumpit cb is
skipping to dump remaining params or info_get ops for all the
drivers.

Fix to not return if any of the param/info_get op returns error
as not supported and continue to dump remaining information.

v2: Modify the patch to return error, except for params/info_get
op that return -EOPNOTSUPP as suggested by Andrew Lunn. Also, modify
commit message to reflect the same.

Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Jiri Pirko <jiri@mellanox.com>
Cc: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/devlink.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/devlink.c b/net/core/devlink.c
index e48680efe54a..f80151eeaf51 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3172,7 +3172,7 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg,
 						    NETLINK_CB(cb->skb).portid,
 						    cb->nlh->nlmsg_seq,
 						    NLM_F_MULTI);
-			if (err) {
+			if (err && err != -EOPNOTSUPP) {
 				mutex_unlock(&devlink->lock);
 				goto out;
 			}
@@ -3432,7 +3432,7 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg,
 						NETLINK_CB(cb->skb).portid,
 						cb->nlh->nlmsg_seq,
 						NLM_F_MULTI);
-				if (err) {
+				if (err && err != -EOPNOTSUPP) {
 					mutex_unlock(&devlink->lock);
 					goto out;
 				}
@@ -4088,7 +4088,7 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg,
 					   cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					   cb->extack);
 		mutex_unlock(&devlink->lock);
-		if (err)
+		if (err && err != -EOPNOTSUPP)
 			break;
 		idx++;
 	}
-- 
cgit v1.2.3


From 9a2ae7b3960eb2426a8560cbc3251e3453230d21 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 30 Sep 2019 10:19:05 +0200
Subject: net: stmmac: xgmac: Not all Unicast addresses may be available

Some setups may not have all Unicast addresses filters available. Let's
check this before trying to setup filters.

Fixes: 0efedbf11f07 ("net: stmmac: xgmac: Fix XGMAC selftests")
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 2b277b2c586b..6d8ac2ef4fc2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -472,7 +472,7 @@ static void dwxgmac2_set_filter(struct mac_device_info *hw,
 	dwxgmac2_set_mchash(ioaddr, mc_filter, mcbitslog2);
 
 	/* Handle multiple unicast addresses */
-	if (netdev_uc_count(dev) > XGMAC_ADDR_MAX) {
+	if (netdev_uc_count(dev) > hw->unicast_filter_entries) {
 		value |= XGMAC_FILTER_PR;
 	} else {
 		struct netdev_hw_addr *ha;
-- 
cgit v1.2.3


From c11986b9fa74cd3ce218e0ca7e0de88d30e6f497 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 30 Sep 2019 10:19:06 +0200
Subject: net: stmmac: xgmac: Detect Hash Table size dinamically

Since commit b8ef7020d6e5 ("net: stmmac: add support for hash table size
128/256 in dwmac4"), we can detect the Hash Table dinamically.

Let's implement this feature in XGMAC cores and fix possible setups that
don't support the maximum size for Hash Table.

Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h     | 1 +
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 5923ca62d793..f7eb06f8fb37 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -122,6 +122,7 @@
 #define XGMAC_HWFEAT_GMIISEL		BIT(1)
 #define XGMAC_HW_FEATURE1		0x00000120
 #define XGMAC_HWFEAT_L3L4FNUM		GENMASK(30, 27)
+#define XGMAC_HWFEAT_HASHTBLSZ		GENMASK(25, 24)
 #define XGMAC_HWFEAT_RSSEN		BIT(20)
 #define XGMAC_HWFEAT_TSOEN		BIT(18)
 #define XGMAC_HWFEAT_SPHEN		BIT(17)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 53c4a40d8386..965cbe3e6f51 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -380,6 +380,7 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 	/* MAC HW feature 1 */
 	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1);
 	dma_cap->l3l4fnum = (hw_cap & XGMAC_HWFEAT_L3L4FNUM) >> 27;
+	dma_cap->hash_tb_sz = (hw_cap & XGMAC_HWFEAT_HASHTBLSZ) >> 24;
 	dma_cap->rssen = (hw_cap & XGMAC_HWFEAT_RSSEN) >> 20;
 	dma_cap->tsoen = (hw_cap & XGMAC_HWFEAT_TSOEN) >> 18;
 	dma_cap->sphen = (hw_cap & XGMAC_HWFEAT_SPHEN) >> 17;
-- 
cgit v1.2.3


From 432439fef933602cae51fb141f33014fb03f2b38 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 30 Sep 2019 10:19:07 +0200
Subject: net: stmmac: selftests: Always use max DMA size in Jumbo Test

Although some XGMAC setups support frames larger than DMA size, some of
them may not. As we can't know before-hand which ones support let's use
the maximum DMA buffer size in the Jumbo Tests.

User can always reconfigure the MTU to achieve larger frames.

Fixes: 427849e8c37f ("net: stmmac: selftests: Add Jumbo Frame tests")
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
index 5f66f6161629..cc76a42c7466 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -1564,10 +1564,6 @@ static int __stmmac_test_jumbo(struct stmmac_priv *priv, u16 queue)
 	struct stmmac_packet_attrs attr = { };
 	int size = priv->dma_buf_sz;
 
-	/* Only XGMAC has SW support for multiple RX descs in same packet */
-	if (priv->plat->has_xgmac)
-		size = priv->dev->max_mtu;
-
 	attr.dst = priv->dev->dev_addr;
 	attr.max_size = size - ETH_FCS_LEN;
 	attr.queue_mapping = queue;
-- 
cgit v1.2.3


From f79bfda3756c50a86c0ee65091935c42c5bbe0cb Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 30 Sep 2019 10:19:08 +0200
Subject: net: stmmac: dwmac4: Always update the MAC Hash Filter

We need to always update the MAC Hash Filter so that previous entries
are invalidated.

Found out while running stmmac selftests.

Fixes: b8ef7020d6e5 ("net: stmmac: add support for hash table size 128/256 in dwmac4")
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 9b4b5f69fc02..2cb9c53f93b8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -401,8 +401,11 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 	int numhashregs = (hw->multicast_filter_bins >> 5);
 	int mcbitslog2 = hw->mcast_bits_log2;
 	unsigned int value;
+	u32 mc_filter[8];
 	int i;
 
+	memset(mc_filter, 0, sizeof(mc_filter));
+
 	value = readl(ioaddr + GMAC_PACKET_FILTER);
 	value &= ~GMAC_PACKET_FILTER_HMC;
 	value &= ~GMAC_PACKET_FILTER_HPF;
@@ -416,16 +419,13 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 		/* Pass all multi */
 		value |= GMAC_PACKET_FILTER_PM;
 		/* Set all the bits of the HASH tab */
-		for (i = 0; i < numhashregs; i++)
-			writel(0xffffffff, ioaddr + GMAC_HASH_TAB(i));
+		memset(mc_filter, 0xff, sizeof(mc_filter));
 	} else if (!netdev_mc_empty(dev)) {
 		struct netdev_hw_addr *ha;
-		u32 mc_filter[8];
 
 		/* Hash filter for multicast */
 		value |= GMAC_PACKET_FILTER_HMC;
 
-		memset(mc_filter, 0, sizeof(mc_filter));
 		netdev_for_each_mc_addr(ha, dev) {
 			/* The upper n bits of the calculated CRC are used to
 			 * index the contents of the hash table. The number of
@@ -440,10 +440,11 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 			 */
 			mc_filter[bit_nr >> 5] |= (1 << (bit_nr & 0x1f));
 		}
-		for (i = 0; i < numhashregs; i++)
-			writel(mc_filter[i], ioaddr + GMAC_HASH_TAB(i));
 	}
 
+	for (i = 0; i < numhashregs; i++)
+		writel(mc_filter[i], ioaddr + GMAC_HASH_TAB(i));
+
 	value |= GMAC_PACKET_FILTER_HPF;
 
 	/* Handle multiple unicast addresses */
-- 
cgit v1.2.3


From 14f347334bf232074616e29e29103dd0c7c54dec Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 30 Sep 2019 10:19:09 +0200
Subject: net: stmmac: Correctly take timestamp for PTPv2

The case for PTPV2_EVENT requires event packets to be captured so add
this setting to the list of enabled captures.

Fixes: 891434b18ec0 ("stmmac: add IEEE PTPv1 and PTPv2 support.")
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d3232738fb25..31a237ec73bc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -629,6 +629,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
+			ts_event_en = PTP_TCR_TSEVNTENA;
 			ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA;
 			ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA;
 			ptp_over_ethernet = PTP_TCR_TSIPENA;
-- 
cgit v1.2.3


From 3e2bf04fb0447aa4b967b8000125178f55ae7800 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 30 Sep 2019 10:19:10 +0200
Subject: net: stmmac: Do not stop PHY if WoL is enabled

If WoL is enabled we can't really stop the PHY, otherwise we will not
receive the WoL packet. Fix this by telling phylink that only the MAC is
down and only stop the PHY if WoL is not enabled.

Fixes: 74371272f97f ("net: stmmac: Convert to phylink and remove phylib logic")
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 31a237ec73bc..843d53e084b7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4718,9 +4718,7 @@ int stmmac_suspend(struct device *dev)
 
 	mutex_lock(&priv->lock);
 
-	rtnl_lock();
-	phylink_stop(priv->phylink);
-	rtnl_unlock();
+	phylink_mac_change(priv->phylink, false);
 
 	netif_device_detach(ndev);
 	stmmac_stop_all_queues(priv);
@@ -4735,6 +4733,10 @@ int stmmac_suspend(struct device *dev)
 		stmmac_pmt(priv, priv->hw, priv->wolopts);
 		priv->irq_wake = 1;
 	} else {
+		rtnl_lock();
+		phylink_stop(priv->phylink);
+		rtnl_unlock();
+
 		stmmac_mac_set(priv, priv->ioaddr, false);
 		pinctrl_pm_select_sleep_state(priv->device);
 		/* Disable clock in case of PWM is off */
@@ -4825,9 +4827,13 @@ int stmmac_resume(struct device *dev)
 
 	stmmac_start_all_queues(priv);
 
-	rtnl_lock();
-	phylink_start(priv->phylink);
-	rtnl_unlock();
+	if (!device_may_wakeup(priv->device)) {
+		rtnl_lock();
+		phylink_start(priv->phylink);
+		rtnl_unlock();
+	}
+
+	phylink_mac_change(priv->phylink, true);
 
 	mutex_unlock(&priv->lock);
 
-- 
cgit v1.2.3


From 30300d9f9150e4673bbef68fcae40cf267b87293 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 30 Sep 2019 10:19:11 +0200
Subject: net: stmmac: xgmac: Disable the Timestamp interrupt by default

We don't use it anyway as XGMAC only supports polling for timestamp (in
current SW implementation). This greatly reduces the system load by
reducing the number of interrupts.

Fixes: 2142754f8b9c ("net: stmmac: Add MAC related callbacks for XGMAC2")
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index f7eb06f8fb37..99037386080a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -84,7 +84,7 @@
 #define XGMAC_TSIE			BIT(12)
 #define XGMAC_LPIIE			BIT(5)
 #define XGMAC_PMTIE			BIT(4)
-#define XGMAC_INT_DEFAULT_EN		(XGMAC_LPIIE | XGMAC_PMTIE | XGMAC_TSIE)
+#define XGMAC_INT_DEFAULT_EN		(XGMAC_LPIIE | XGMAC_PMTIE)
 #define XGMAC_Qx_TX_FLOW_CTRL(x)	(0x00000070 + (x) * 4)
 #define XGMAC_PT			GENMASK(31, 16)
 #define XGMAC_PT_SHIFT			16
-- 
cgit v1.2.3


From 3c72d4d33059cf84a23492e827731f12c023ab00 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 30 Sep 2019 10:19:12 +0200
Subject: net: stmmac: xgmac: Fix RSS not writing all Keys to HW

The sizeof(cfg->key) is != ARRAY_SIZE(cfg->key). Fix it. This warning is
triggered when running with cc flag -Wsizeof-array-div.

Reported-by: kbuild test robot <lkp@intel.com>
Reported-by: Nick Desaulniers <ndesaulniers@google.com>
Reported-by: Nathan Chancellor <natechancellor@gmail.com>
Fixes: 76067459c686 ("net: stmmac: Implement RSS and enable it in XGMAC core")
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 6d8ac2ef4fc2..4a1f52474dbc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -533,7 +533,7 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw,
 		return 0;
 	}
 
-	for (i = 0; i < (sizeof(cfg->key) / sizeof(u32)); i++) {
+	for (i = 0; i < (ARRAY_SIZE(cfg->key) / sizeof(u32)); i++) {
 		ret = dwxgmac2_rss_write_reg(ioaddr, true, i, cfg->key[i]);
 		if (ret)
 			return ret;
-- 
cgit v1.2.3


From 56627336b655494356a23e65200c21718a1c3b2b Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Mon, 30 Sep 2019 10:19:13 +0200
Subject: net: stmmac: xgmac: Fix RSS writing wrong keys

Commit b6b6cc9acd7b, changed the call to dwxgmac2_rss_write_reg()
passing it the variable cfg->key[i].

As key is an u8 but we write 32 bits at a time we need to cast it into
an u32 so that the correct key values are written. Notice that the for
loop already takes this into account so we don't try to write past the
keys size.

Fixes: b6b6cc9acd7b ("net: stmmac: selftest: avoid large stack usage")
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 4a1f52474dbc..5031398e612c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -523,8 +523,8 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw,
 				  struct stmmac_rss *cfg, u32 num_rxq)
 {
 	void __iomem *ioaddr = hw->pcsr;
+	u32 value, *key;
 	int i, ret;
-	u32 value;
 
 	value = readl(ioaddr + XGMAC_RSS_CTRL);
 	if (!cfg || !cfg->enable) {
@@ -533,8 +533,9 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw,
 		return 0;
 	}
 
+	key = (u32 *)cfg->key;
 	for (i = 0; i < (ARRAY_SIZE(cfg->key) / sizeof(u32)); i++) {
-		ret = dwxgmac2_rss_write_reg(ioaddr, true, i, cfg->key[i]);
+		ret = dwxgmac2_rss_write_reg(ioaddr, true, i, key[i]);
 		if (ret)
 			return ret;
 	}
-- 
cgit v1.2.3


From 569aad4fcd82cba64eb10ede235d330a00f0aa09 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Tue, 1 Oct 2019 08:41:47 +0200
Subject: net: ag71xx: fix mdio subnode support

This patch is syncing driver with actual devicetree documentation:
Documentation/devicetree/bindings/net/qca,ar71xx.txt
|Optional subnodes:
|- mdio : specifies the mdio bus, used as a container for phy nodes
|  according to phy.txt in the same directory

The driver was working with fixed phy without any noticeable issues. This bug
was uncovered by introducing dsa ar9331-switch driver.
Since no one reported this bug until now, I assume no body is using it
and this patch should not brake existing system.

Fixes: d51b6ce441d3 ("net: ethernet: add ag71xx driver")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/ag71xx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c
index 7548247455d7..1b1a09095c0d 100644
--- a/drivers/net/ethernet/atheros/ag71xx.c
+++ b/drivers/net/ethernet/atheros/ag71xx.c
@@ -526,7 +526,7 @@ static int ag71xx_mdio_probe(struct ag71xx *ag)
 	struct device *dev = &ag->pdev->dev;
 	struct net_device *ndev = ag->ndev;
 	static struct mii_bus *mii_bus;
-	struct device_node *np;
+	struct device_node *np, *mnp;
 	int err;
 
 	np = dev->of_node;
@@ -571,7 +571,9 @@ static int ag71xx_mdio_probe(struct ag71xx *ag)
 		msleep(200);
 	}
 
-	err = of_mdiobus_register(mii_bus, np);
+	mnp = of_get_child_by_name(np, "mdio");
+	err = of_mdiobus_register(mii_bus, mnp);
+	of_node_put(mnp);
 	if (err)
 		goto mdio_err_put_clk;
 
-- 
cgit v1.2.3


From 7a54789074a54f64addf5b49bf1994f478337a83 Mon Sep 17 00:00:00 2001
From: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Date: Thu, 12 Sep 2019 19:55:01 -0400
Subject: btrfs: fix balance convert to single on 32-bit host CPUs

Currently, the command:

	btrfs balance start -dconvert=single,soft .

on a Raspberry Pi produces the following kernel message:

	BTRFS error (device mmcblk0p2): balance: invalid convert data profile single

This fails because we use is_power_of_2(unsigned long) to validate
the new data profile, the constant for 'single' profile uses bit 48,
and there are only 32 bits in a long on ARM.

Fix by open-coding the check using u64 variables.

Tested by completing the original balance command on several Raspberry
Pis.

Fixes: 818255feece6 ("btrfs: use common helper instead of open coding a bit test")
CC: stable@vger.kernel.org # 4.20+
Signed-off-by: Zygo Blaxell <ce3g8jdj@umail.furryterror.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index cdd7af424033..bdfe4493e43a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3845,7 +3845,11 @@ static int alloc_profile_is_valid(u64 flags, int extended)
 		return !extended; /* "0" is valid for usual profiles */
 
 	/* true if exactly one bit set */
-	return is_power_of_2(flags);
+	/*
+	 * Don't use is_power_of_2(unsigned long) because it won't work
+	 * for the single profile (1ULL << 48) on 32-bit CPUs.
+	 */
+	return flags != 0 && (flags & (flags - 1)) == 0;
 }
 
 static inline int balance_need_close(struct btrfs_fs_info *fs_info)
-- 
cgit v1.2.3


From cdee3b60af594403bd389e6e8239bcd0b4a159fc Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 1 Oct 2019 09:46:28 +0200
Subject: ARM: dts: ux500: Fix up the CPU thermal zone

This fixes up the default ux500 CPU thermal zone:

- Set polling delay to 0 and explain why
- Set passive polling delay to 250
- Remove restrictions from the CPU cooling device,
  we should use all cpufreq steps to cool down if
  needed.

Link: https://lore.kernel.org/r/20191001074628.8122-1-linus.walleij@linaro.org
Fixes: b786a05f6ce4 ("ARM: dts: ux500: Update thermal zone")
Suggested-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Olof Johansson <olof@lixom.net>
---
 arch/arm/boot/dts/ste-dbx5x0.dtsi | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi
index a53657b83288..bda454d12150 100644
--- a/arch/arm/boot/dts/ste-dbx5x0.dtsi
+++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi
@@ -8,6 +8,7 @@
 #include <dt-bindings/mfd/dbx500-prcmu.h>
 #include <dt-bindings/arm/ux500_pm_domains.h>
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/thermal/thermal.h>
 
 / {
 	#address-cells = <1>;
@@ -59,8 +60,12 @@
 		 * cooling.
 		 */
 		cpu_thermal: cpu-thermal {
-			polling-delay-passive = <0>;
-			polling-delay = <1000>;
+			polling-delay-passive = <250>;
+			/*
+			 * This sensor fires interrupts to update the thermal
+			 * zone, so no polling is needed.
+			 */
+			polling-delay = <0>;
 
 			thermal-sensors = <&thermal>;
 
@@ -79,7 +84,7 @@
 
 			cooling-maps {
 				trip = <&cpu_alert>;
-				cooling-device = <&CPU0 0 2>;
+				cooling-device = <&CPU0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
 				contribution = <100>;
 			};
 		};
-- 
cgit v1.2.3


From 11a19a90870ea5496a8ded69b86f5b476b6d3355 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 9 Sep 2019 10:12:04 -0400
Subject: btrfs: allocate new inode in NOFS context

A user reported a lockdep splat

 ======================================================
 WARNING: possible circular locking dependency detected
 5.2.11-gentoo #2 Not tainted
 ------------------------------------------------------
 kswapd0/711 is trying to acquire lock:
 000000007777a663 (sb_internal){.+.+}, at: start_transaction+0x3a8/0x500

but task is already holding lock:
 000000000ba86300 (fs_reclaim){+.+.}, at: __fs_reclaim_acquire+0x0/0x30

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (fs_reclaim){+.+.}:
 kmem_cache_alloc+0x1f/0x1c0
 btrfs_alloc_inode+0x1f/0x260
 alloc_inode+0x16/0xa0
 new_inode+0xe/0xb0
 btrfs_new_inode+0x70/0x610
 btrfs_symlink+0xd0/0x420
 vfs_symlink+0x9c/0x100
 do_symlinkat+0x66/0xe0
 do_syscall_64+0x55/0x1c0
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

-> #0 (sb_internal){.+.+}:
 __sb_start_write+0xf6/0x150
 start_transaction+0x3a8/0x500
 btrfs_commit_inode_delayed_inode+0x59/0x110
 btrfs_evict_inode+0x19e/0x4c0
 evict+0xbc/0x1f0
 inode_lru_isolate+0x113/0x190
 __list_lru_walk_one.isra.4+0x5c/0x100
 list_lru_walk_one+0x32/0x50
 prune_icache_sb+0x36/0x80
 super_cache_scan+0x14a/0x1d0
 do_shrink_slab+0x131/0x320
 shrink_node+0xf7/0x380
 balance_pgdat+0x2d5/0x640
 kswapd+0x2ba/0x5e0
 kthread+0x147/0x160
 ret_from_fork+0x24/0x30

other info that might help us debug this:

 Possible unsafe locking scenario:

 CPU0 CPU1
 ---- ----
 lock(fs_reclaim);
 lock(sb_internal);
 lock(fs_reclaim);
 lock(sb_internal);
*** DEADLOCK ***

 3 locks held by kswapd0/711:
 #0: 000000000ba86300 (fs_reclaim){+.+.}, at: __fs_reclaim_acquire+0x0/0x30
 #1: 000000004a5100f8 (shrinker_rwsem){++++}, at: shrink_node+0x9a/0x380
 #2: 00000000f956fa46 (&type->s_umount_key#30){++++}, at: super_cache_scan+0x35/0x1d0

stack backtrace:
 CPU: 7 PID: 711 Comm: kswapd0 Not tainted 5.2.11-gentoo #2
 Hardware name: Dell Inc. Precision Tower 3620/0MWYPT, BIOS 2.4.2 09/29/2017
 Call Trace:
 dump_stack+0x85/0xc7
 print_circular_bug.cold.40+0x1d9/0x235
 __lock_acquire+0x18b1/0x1f00
 lock_acquire+0xa6/0x170
 ? start_transaction+0x3a8/0x500
 __sb_start_write+0xf6/0x150
 ? start_transaction+0x3a8/0x500
 start_transaction+0x3a8/0x500
 btrfs_commit_inode_delayed_inode+0x59/0x110
 btrfs_evict_inode+0x19e/0x4c0
 ? var_wake_function+0x20/0x20
 evict+0xbc/0x1f0
 inode_lru_isolate+0x113/0x190
 ? discard_new_inode+0xc0/0xc0
 __list_lru_walk_one.isra.4+0x5c/0x100
 ? discard_new_inode+0xc0/0xc0
 list_lru_walk_one+0x32/0x50
 prune_icache_sb+0x36/0x80
 super_cache_scan+0x14a/0x1d0
 do_shrink_slab+0x131/0x320
 shrink_node+0xf7/0x380
 balance_pgdat+0x2d5/0x640
 kswapd+0x2ba/0x5e0
 ? __wake_up_common_lock+0x90/0x90
 kthread+0x147/0x160
 ? balance_pgdat+0x640/0x640
 ? __kthread_create_on_node+0x160/0x160
 ret_from_fork+0x24/0x30

This is because btrfs_new_inode() calls new_inode() under the
transaction.  We could probably move the new_inode() outside of this but
for now just wrap it in memalloc_nofs_save().

Reported-by: Zdenek Sojka <zsojka@seznam.cz>
Fixes: 712e36c5f2a7 ("btrfs: use GFP_KERNEL in btrfs_alloc_inode")
CC: stable@vger.kernel.org # 4.16+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a0546401bc0a..0f2754eaa05b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6305,13 +6305,16 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	u32 sizes[2];
 	int nitems = name ? 2 : 1;
 	unsigned long ptr;
+	unsigned int nofs_flag;
 	int ret;
 
 	path = btrfs_alloc_path();
 	if (!path)
 		return ERR_PTR(-ENOMEM);
 
+	nofs_flag = memalloc_nofs_save();
 	inode = new_inode(fs_info->sb);
+	memalloc_nofs_restore(nofs_flag);
 	if (!inode) {
 		btrfs_free_path(path);
 		return ERR_PTR(-ENOMEM);
-- 
cgit v1.2.3


From 6184488a19be96d89cb6c36fb4bc277198309484 Mon Sep 17 00:00:00 2001
From: Nishad Kamdar <nishadkamdar@gmail.com>
Date: Tue, 16 Apr 2019 21:16:14 +0530
Subject: x86: Use the correct SPDX License Identifier in headers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Correct the SPDX License Identifier format in a couple of headers.

Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Nishad Kamdar <nishadkamdar@gmail.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Cc: Waiman Long <longman@redhat.com>
Cc: x86-ml <x86@kernel.org>
Link: https://lkml.kernel.org/r/697848ff866ade29e78e872525d7a3067642fd37.1555427420.git.nishadkamdar@gmail.com
---
 arch/x86/include/asm/cpu_entry_area.h | 2 +-
 arch/x86/include/asm/pti.h            | 2 +-
 arch/x86/kernel/process.h             | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index cff3f3f3bfe0..8348f7d69fd5 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 
 #ifndef _ASM_X86_CPU_ENTRY_AREA_H
 #define _ASM_X86_CPU_ENTRY_AREA_H
diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
index 5df09a0b80b8..07375b476c4f 100644
--- a/arch/x86/include/asm/pti.h
+++ b/arch/x86/include/asm/pti.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_PTI_H
 #define _ASM_X86_PTI_H
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/kernel/process.h b/arch/x86/kernel/process.h
index 320ab978fb1f..1d0797b2338a 100644
--- a/arch/x86/kernel/process.h
+++ b/arch/x86/kernel/process.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 //
 // Code shared between 32 and 64 bit
 
-- 
cgit v1.2.3


From 6a297c90efa68b2864483193b8bfb0d19478600c Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Tue, 20 Aug 2019 02:56:34 +0000
Subject: HID: hyperv: Use in-place iterator API in the channel callback

Simplify the ring buffer handling with the in-place API.

Also avoid the dynamic allocation and the memory leak in the channel
callback function.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/hid/hid-hyperv.c | 56 +++++++++---------------------------------------
 1 file changed, 10 insertions(+), 46 deletions(-)

diff --git a/drivers/hid/hid-hyperv.c b/drivers/hid/hid-hyperv.c
index cc5b09b87ab0..79a28fc91521 100644
--- a/drivers/hid/hid-hyperv.c
+++ b/drivers/hid/hid-hyperv.c
@@ -314,60 +314,24 @@ static void mousevsc_on_receive(struct hv_device *device,
 
 static void mousevsc_on_channel_callback(void *context)
 {
-	const int packet_size = 0x100;
-	int ret;
 	struct hv_device *device = context;
-	u32 bytes_recvd;
-	u64 req_id;
 	struct vmpacket_descriptor *desc;
-	unsigned char	*buffer;
-	int	bufferlen = packet_size;
-
-	buffer = kmalloc(bufferlen, GFP_ATOMIC);
-	if (!buffer)
-		return;
-
-	do {
-		ret = vmbus_recvpacket_raw(device->channel, buffer,
-					bufferlen, &bytes_recvd, &req_id);
-
-		switch (ret) {
-		case 0:
-			if (bytes_recvd <= 0) {
-				kfree(buffer);
-				return;
-			}
-			desc = (struct vmpacket_descriptor *)buffer;
-
-			switch (desc->type) {
-			case VM_PKT_COMP:
-				break;
-
-			case VM_PKT_DATA_INBAND:
-				mousevsc_on_receive(device, desc);
-				break;
-
-			default:
-				pr_err("unhandled packet type %d, tid %llx len %d\n",
-					desc->type, req_id, bytes_recvd);
-				break;
-			}
 
+	foreach_vmbus_pkt(desc, device->channel) {
+		switch (desc->type) {
+		case VM_PKT_COMP:
 			break;
 
-		case -ENOBUFS:
-			kfree(buffer);
-			/* Handle large packet */
-			bufferlen = bytes_recvd;
-			buffer = kmalloc(bytes_recvd, GFP_ATOMIC);
-
-			if (!buffer)
-				return;
+		case VM_PKT_DATA_INBAND:
+			mousevsc_on_receive(device, desc);
+			break;
 
+		default:
+			pr_err("Unhandled packet type %d, tid %llx len %d\n",
+			       desc->type, desc->trans_id, desc->len8 * 8);
 			break;
 		}
-	} while (1);
-
+	}
 }
 
 static int mousevsc_connect_to_vsp(struct hv_device *device)
-- 
cgit v1.2.3


From 83b50f83a96899f30c6369ef5988412fa2354ab2 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Thu, 19 Sep 2019 21:46:12 +0000
Subject: Drivers: hv: vmbus: Fix harmless building warnings without
 CONFIG_PM_SLEEP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If CONFIG_PM_SLEEP is not set, we can comment out these functions to avoid
the below warnings:

drivers/hv/vmbus_drv.c:2208:12: warning: ‘vmbus_bus_resume’ defined but not used [-Wunused-function]
drivers/hv/vmbus_drv.c:2128:12: warning: ‘vmbus_bus_suspend’ defined but not used [-Wunused-function]
drivers/hv/vmbus_drv.c:937:12: warning: ‘vmbus_resume’ defined but not used [-Wunused-function]
drivers/hv/vmbus_drv.c:918:12: warning: ‘vmbus_suspend’ defined but not used [-Wunused-function]

Fixes: 271b2224d42f ("Drivers: hv: vmbus: Implement suspend/resume for VSC drivers for hibernation")
Fixes: f53335e3289f ("Drivers: hv: vmbus: Suspend/resume the vmbus itself for hibernation")
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by:  Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/hv/vmbus_drv.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 391f0b225c9a..53a60c81e220 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -912,6 +912,7 @@ static void vmbus_shutdown(struct device *child_device)
 		drv->shutdown(dev);
 }
 
+#ifdef CONFIG_PM_SLEEP
 /*
  * vmbus_suspend - Suspend a vmbus device
  */
@@ -949,6 +950,7 @@ static int vmbus_resume(struct device *child_device)
 
 	return drv->resume(dev);
 }
+#endif /* CONFIG_PM_SLEEP */
 
 /*
  * vmbus_device_release - Final callback release of the vmbus child device
@@ -1070,6 +1072,7 @@ msg_handled:
 	vmbus_signal_eom(msg, message_type);
 }
 
+#ifdef CONFIG_PM_SLEEP
 /*
  * Fake RESCIND_CHANNEL messages to clean up hv_sock channels by force for
  * hibernation, because hv_sock connections can not persist across hibernation.
@@ -1105,6 +1108,7 @@ static void vmbus_force_channel_rescinded(struct vmbus_channel *channel)
 		      vmbus_connection.work_queue,
 		      &ctx->work);
 }
+#endif /* CONFIG_PM_SLEEP */
 
 /*
  * Direct callback for channels using other deferred processing
@@ -2125,6 +2129,7 @@ acpi_walk_err:
 	return ret_val;
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int vmbus_bus_suspend(struct device *dev)
 {
 	struct vmbus_channel *channel, *sc;
@@ -2247,6 +2252,7 @@ static int vmbus_bus_resume(struct device *dev)
 
 	return 0;
 }
+#endif /* CONFIG_PM_SLEEP */
 
 static const struct acpi_device_id vmbus_acpi_device_ids[] = {
 	{"VMBUS", 0},
-- 
cgit v1.2.3


From 3a24f7f6b610910ee328df11392e21925cefdecb Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 26 Sep 2019 18:52:18 +0100
Subject: kselftest: add capability to skip chosen TARGETS

Let the user specify an optional TARGETS skiplist through the new optional
SKIP_TARGETS Makefile variable.

It is easier to skip at will using a reduced and well defined list of
possibly problematic targets with SKIP_TARGETS than to provide a partially
stripped down list of good targets using the usual TARGETS variable.

Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 Documentation/dev-tools/kselftest.rst | 16 ++++++++++++++++
 tools/testing/selftests/Makefile      |  7 +++++++
 2 files changed, 23 insertions(+)

diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst
index 25604904fa6e..ecdfdc9d4b03 100644
--- a/Documentation/dev-tools/kselftest.rst
+++ b/Documentation/dev-tools/kselftest.rst
@@ -89,6 +89,22 @@ To build, save output files in a separate directory with KBUILD_OUTPUT ::
 
   $ export KBUILD_OUTPUT=/tmp/kselftest; make TARGETS="size timers" kselftest
 
+Additionally you can use the "SKIP_TARGETS" variable on the make command
+line to specify one or more targets to exclude from the TARGETS list.
+
+To run all tests but a single subsystem::
+
+  $ make -C tools/testing/selftests SKIP_TARGETS=ptrace run_tests
+
+You can specify multiple tests to skip::
+
+  $  make SKIP_TARGETS="size timers" kselftest
+
+You can also specify a restricted list of tests to run together with a
+dedicated skiplist::
+
+  $  make TARGETS="bpf breakpoints size timers" SKIP_TARGETS=bpf kselftest
+
 See the top-level tools/testing/selftests/Makefile for the list of all
 possible targets.
 
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index bad18145ed1a..e08f26ca4071 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -63,6 +63,13 @@ TARGETS += zram
 TARGETS_HOTPLUG = cpu-hotplug
 TARGETS_HOTPLUG += memory-hotplug
 
+# User can optionally provide a TARGETS skiplist.
+SKIP_TARGETS ?=
+ifneq ($(SKIP_TARGETS),)
+	TMP := $(filter-out $(SKIP_TARGETS), $(TARGETS))
+	override TARGETS := $(TMP)
+endif
+
 # Clear LDFLAGS and MAKEFLAGS if called from main
 # Makefile to avoid test build failures when test
 # Makefile doesn't have explicit build rules.
-- 
cgit v1.2.3


From 73956fc07dd7b25d4a33ab3fdd6247c60d0b237c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 1 Oct 2019 10:50:33 +0200
Subject: membarrier: Fix RCU locking bug caused by faulty merge

The following commit:

  227a4aadc75b ("sched/membarrier: Fix p->mm->membarrier_state racy load")

got fat fingered by me when merging it with other patches. It meant to move
the RCU section out of the for loop but ended up doing it partially, leaving
a superfluous rcu_read_lock() inside, causing havok.

Reported-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King - ARM Linux admin <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-tip-commits@vger.kernel.org
Fixes: 227a4aadc75b ("sched/membarrier: Fix p->mm->membarrier_state racy load")
Link: https://lkml.kernel.org/r/20191001085033.GP4519@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/membarrier.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index a39bed2c784f..168479a7d61b 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -174,7 +174,6 @@ static int membarrier_private_expedited(int flags)
 		 */
 		if (cpu == raw_smp_processor_id())
 			continue;
-		rcu_read_lock();
 		p = rcu_dereference(cpu_rq(cpu)->curr);
 		if (p && p->mm == mm)
 			__cpumask_set_cpu(cpu, tmpmask);
-- 
cgit v1.2.3


From 131b30c94fbc0adb15f911609884dd39dada8f00 Mon Sep 17 00:00:00 2001
From: Cristian Marussi <cristian.marussi@arm.com>
Date: Thu, 26 Sep 2019 18:52:19 +0100
Subject: kselftest: exclude failed TARGETS from runlist

A TARGET which failed to be built/installed should not be included in the
runlist generated inside the run_kselftest.sh script.

Signed-off-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/selftests/Makefile | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index e08f26ca4071..4cdbae6f4e61 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -208,8 +208,12 @@ ifdef INSTALL_PATH
 	echo "  cat /dev/null > \$$logfile" >> $(ALL_SCRIPT)
 	echo "fi" >> $(ALL_SCRIPT)
 
+	@# While building run_kselftest.sh skip also non-existent TARGET dirs:
+	@# they could be the result of a build failure and should NOT be
+	@# included in the generated runlist.
 	for TARGET in $(TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
+		[ ! -d $$INSTALL_PATH/$$TARGET ] && echo "Skipping non-existent dir: $$TARGET" && continue; \
 		echo "[ -w /dev/kmsg ] && echo \"kselftest: Running tests in $$TARGET\" >> /dev/kmsg" >> $(ALL_SCRIPT); \
 		echo "cd $$TARGET" >> $(ALL_SCRIPT); \
 		echo -n "run_many" >> $(ALL_SCRIPT); \
-- 
cgit v1.2.3


From 852c8cbf34d3b3130a05c38064dd98614f97d3a8 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 19 Sep 2019 11:06:44 -0700
Subject: selftests/kselftest/runner.sh: Add 45 second timeout per test

Commit a745f7af3cbd ("selftests/harness: Add 30 second timeout per
test") solves the problem of kselftest_harness.h-using binary tests
possibly hanging forever. However, scripts and other binaries can still
hang forever. This adds a global timeout to each test script run.

To make this configurable (e.g. as needed in the "rtc" test case),
include a new per-test-directory "settings" file (similar to "config")
that can contain kselftest-specific settings. The first recognized field
is "timeout".

Additionally, this splits the reporting for timeouts into a specific
"TIMEOUT" not-ok (and adds exit code reporting in the remaining case).

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/selftests/kselftest/runner.sh | 36 ++++++++++++++++++++++++++---
 tools/testing/selftests/rtc/settings        |  1 +
 2 files changed, 34 insertions(+), 3 deletions(-)
 create mode 100644 tools/testing/selftests/rtc/settings

diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh
index 00c9020bdda8..84de7bc74f2c 100644
--- a/tools/testing/selftests/kselftest/runner.sh
+++ b/tools/testing/selftests/kselftest/runner.sh
@@ -3,9 +3,14 @@
 #
 # Runs a set of tests in a given subdirectory.
 export skip_rc=4
+export timeout_rc=124
 export logfile=/dev/stdout
 export per_test_logging=
 
+# Defaults for "settings" file fields:
+# "timeout" how many seconds to let each test run before failing.
+export kselftest_default_timeout=45
+
 # There isn't a shell-agnostic way to find the path of a sourced file,
 # so we must rely on BASE_DIR being set to find other tools.
 if [ -z "$BASE_DIR" ]; then
@@ -24,6 +29,16 @@ tap_prefix()
 	fi
 }
 
+tap_timeout()
+{
+	# Make sure tests will time out if utility is available.
+	if [ -x /usr/bin/timeout ] ; then
+		/usr/bin/timeout "$kselftest_timeout" "$1"
+	else
+		"$1"
+	fi
+}
+
 run_one()
 {
 	DIR="$1"
@@ -32,6 +47,18 @@ run_one()
 
 	BASENAME_TEST=$(basename $TEST)
 
+	# Reset any "settings"-file variables.
+	export kselftest_timeout="$kselftest_default_timeout"
+	# Load per-test-directory kselftest "settings" file.
+	settings="$BASE_DIR/$DIR/settings"
+	if [ -r "$settings" ] ; then
+		while read line ; do
+			field=$(echo "$line" | cut -d= -f1)
+			value=$(echo "$line" | cut -d= -f2-)
+			eval "kselftest_$field"="$value"
+		done < "$settings"
+	fi
+
 	TEST_HDR_MSG="selftests: $DIR: $BASENAME_TEST"
 	echo "# $TEST_HDR_MSG"
 	if [ ! -x "$TEST" ]; then
@@ -44,14 +71,17 @@ run_one()
 		echo "not ok $test_num $TEST_HDR_MSG"
 	else
 		cd `dirname $TEST` > /dev/null
-		(((((./$BASENAME_TEST 2>&1; echo $? >&3) |
+		((((( tap_timeout ./$BASENAME_TEST 2>&1; echo $? >&3) |
 			tap_prefix >&4) 3>&1) |
 			(read xs; exit $xs)) 4>>"$logfile" &&
 		echo "ok $test_num $TEST_HDR_MSG") ||
-		(if [ $? -eq $skip_rc ]; then	\
+		(rc=$?;	\
+		if [ $rc -eq $skip_rc ]; then	\
 			echo "not ok $test_num $TEST_HDR_MSG # SKIP"
+		elif [ $rc -eq $timeout_rc ]; then \
+			echo "not ok $test_num $TEST_HDR_MSG # TIMEOUT"
 		else
-			echo "not ok $test_num $TEST_HDR_MSG"
+			echo "not ok $test_num $TEST_HDR_MSG # exit=$rc"
 		fi)
 		cd - >/dev/null
 	fi
diff --git a/tools/testing/selftests/rtc/settings b/tools/testing/selftests/rtc/settings
new file mode 100644
index 000000000000..ba4d85f74cd6
--- /dev/null
+++ b/tools/testing/selftests/rtc/settings
@@ -0,0 +1 @@
+timeout=90
-- 
cgit v1.2.3


From ade77a2da81efb5eaff1f7cc1b1bc14cd9380faa Mon Sep 17 00:00:00 2001
From: Stefano Stabellini <stefano.stabellini@xilinx.com>
Date: Tue, 1 Oct 2019 10:38:03 -0700
Subject: ARM: xen: unexport HYPERVISOR_platform_op function

HYPERVISOR_platform_op() is an inline function and should not
be exported. Since commit 15bfc2348d54 ("modpost: check for
static EXPORT_SYMBOL* functions"), this causes a warning:

WARNING: "HYPERVISOR_platform_op" [vmlinux] is a static EXPORT_SYMBOL_GPL

Instead, export the underlying function called by the static inline:
HYPERVISOR_platform_op_raw.

Fixes: 15bfc2348d54 ("modpost: check for static EXPORT_SYMBOL* functions")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Stefano Stabellini <stefano.stabellini@xilinx.com>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
---
 arch/arm/xen/enlighten.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 1e57692552d9..522c97d43ef8 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -437,7 +437,7 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
-EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op_raw);
 EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
 EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist);
 EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op);
-- 
cgit v1.2.3


From c5ad81eb029570c5ca5859539b0679f07a776d25 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 27 Sep 2019 17:46:28 +0200
Subject: xen/balloon: Set pages PageOffline() in balloon_add_region()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We are missing a __SetPageOffline(), which is why we can get
!PageOffline() pages onto the balloon list, where
alloc_xenballooned_pages() will complain:

page:ffffea0003e7ffc0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0
flags: 0xffffe00001000(reserved)
raw: 000ffffe00001000 dead000000000100 dead000000000200 0000000000000000
raw: 0000000000000000 0000000000000000 00000001ffffffff 0000000000000000
page dumped because: VM_BUG_ON_PAGE(!PageOffline(page))
------------[ cut here ]------------
kernel BUG at include/linux/page-flags.h:744!
invalid opcode: 0000 [#1] SMP NOPTI

Reported-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Tested-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Fixes: 77c4adf6a6df ("xen/balloon: mark inflated pages PG_offline")
Cc: stable@vger.kernel.org # v5.1+
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/balloon.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 4e11de6cde81..91cba70b69df 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -688,6 +688,7 @@ static void __init balloon_add_region(unsigned long start_pfn,
 		/* totalram_pages and totalhigh_pages do not
 		   include the boot-time balloon extension, so
 		   don't subtract from it. */
+		__SetPageOffline(page);
 		__balloon_append(page);
 	}
 
-- 
cgit v1.2.3


From dde3285ffa1a75dbd67c6a61e5f3eba2267c6593 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Tue, 1 Oct 2019 11:01:50 +0200
Subject: xen/balloon: Drop __balloon_append()

Let's simply use balloon_append() directly.

Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/balloon.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 91cba70b69df..37443c5fda99 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -156,7 +156,7 @@ static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
 	(GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC)
 
 /* balloon_append: add the given page to the balloon. */
-static void __balloon_append(struct page *page)
+static void balloon_append(struct page *page)
 {
 	/* Lowmem is re-populated first, so highmem pages go at list tail. */
 	if (PageHighMem(page)) {
@@ -169,11 +169,6 @@ static void __balloon_append(struct page *page)
 	wake_up(&balloon_wq);
 }
 
-static void balloon_append(struct page *page)
-{
-	__balloon_append(page);
-}
-
 /* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
 static struct page *balloon_retrieve(bool require_lowmem)
 {
@@ -378,7 +373,7 @@ static void xen_online_page(struct page *page, unsigned int order)
 		p = pfn_to_page(start_pfn + i);
 		__online_page_set_limits(p);
 		__SetPageOffline(p);
-		__balloon_append(p);
+		balloon_append(p);
 	}
 	mutex_unlock(&balloon_mutex);
 }
@@ -689,7 +684,7 @@ static void __init balloon_add_region(unsigned long start_pfn,
 		   include the boot-time balloon extension, so
 		   don't subtract from it. */
 		__SetPageOffline(page);
-		__balloon_append(page);
+		balloon_append(page);
 	}
 
 	balloon_stats.total_pages += extra_pfn_end - start_pfn;
-- 
cgit v1.2.3


From 59b52f105f23edebf497bf8f0e57660e649e3f17 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Tue, 1 Oct 2019 11:01:51 +0200
Subject: xen/balloon: Mark pages PG_offline in balloon_append()

Let's move the __SetPageOffline() call which all callers perform into
balloon_append().

In bp_state decrease_reservation(), pages are now marked PG_offline a
little later than before, however, this should not matter for XEN.

Suggested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/balloon.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 37443c5fda99..8c245e99bb06 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -158,6 +158,8 @@ static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
 /* balloon_append: add the given page to the balloon. */
 static void balloon_append(struct page *page)
 {
+	__SetPageOffline(page);
+
 	/* Lowmem is re-populated first, so highmem pages go at list tail. */
 	if (PageHighMem(page)) {
 		list_add_tail(&page->lru, &ballooned_pages);
@@ -372,7 +374,6 @@ static void xen_online_page(struct page *page, unsigned int order)
 	for (i = 0; i < size; i++) {
 		p = pfn_to_page(start_pfn + i);
 		__online_page_set_limits(p);
-		__SetPageOffline(p);
 		balloon_append(p);
 	}
 	mutex_unlock(&balloon_mutex);
@@ -466,7 +467,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 			state = BP_EAGAIN;
 			break;
 		}
-		__SetPageOffline(page);
 		adjust_managed_page_count(page, -1);
 		xenmem_reservation_scrub_page(page);
 		list_add(&page->lru, &pages);
@@ -648,10 +648,8 @@ void free_xenballooned_pages(int nr_pages, struct page **pages)
 	mutex_lock(&balloon_mutex);
 
 	for (i = 0; i < nr_pages; i++) {
-		if (pages[i]) {
-			__SetPageOffline(pages[i]);
+		if (pages[i])
 			balloon_append(pages[i]);
-		}
 	}
 
 	balloon_stats.target_unpopulated -= nr_pages;
@@ -669,7 +667,6 @@ static void __init balloon_add_region(unsigned long start_pfn,
 				      unsigned long pages)
 {
 	unsigned long pfn, extra_pfn_end;
-	struct page *page;
 
 	/*
 	 * If the amount of usable memory has been limited (e.g., with
@@ -679,12 +676,10 @@ static void __init balloon_add_region(unsigned long start_pfn,
 	extra_pfn_end = min(max_pfn, start_pfn + pages);
 
 	for (pfn = start_pfn; pfn < extra_pfn_end; pfn++) {
-		page = pfn_to_page(pfn);
 		/* totalram_pages and totalhigh_pages do not
 		   include the boot-time balloon extension, so
 		   don't subtract from it. */
-		__SetPageOffline(page);
-		balloon_append(page);
+		balloon_append(pfn_to_page(pfn));
 	}
 
 	balloon_stats.total_pages += extra_pfn_end - start_pfn;
-- 
cgit v1.2.3


From 04ccbdc390b14d8fdc4612abbf023ff49cdc5cd8 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Tue, 1 Oct 2019 11:01:52 +0200
Subject: xen/balloon: Clear PG_offline in balloon_retrieve()

Let's move the clearing to balloon_retrieve(). In
bp_state increase_reservation(), we now clear the flag a little earlier
than before, however, this should not matter for XEN.

Suggested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/balloon.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 8c245e99bb06..5bae515c8e25 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -189,6 +189,7 @@ static struct page *balloon_retrieve(bool require_lowmem)
 	else
 		balloon_stats.balloon_low--;
 
+	__ClearPageOffline(page);
 	return page;
 }
 
@@ -440,7 +441,6 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 		xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]);
 
 		/* Relinquish the page back to the allocator. */
-		__ClearPageOffline(page);
 		free_reserved_page(page);
 	}
 
@@ -606,7 +606,6 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages)
 	while (pgno < nr_pages) {
 		page = balloon_retrieve(true);
 		if (page) {
-			__ClearPageOffline(page);
 			pages[pgno++] = page;
 #ifdef CONFIG_XEN_HAVE_PVMMU
 			/*
-- 
cgit v1.2.3


From d345d9cad22532ac18afa70efa0506b1d8cface5 Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Fri, 27 Sep 2019 13:33:39 +0800
Subject: MIPS: cpu-bugs64: Mark inline functions as __always_inline

Commit ac7c3e4ff401 ("compiler: enable CONFIG_OPTIMIZE_INLINING
forcibly") allows compiler to uninline functions marked as 'inline'.
Leading to section mismatch in this case.

Since we're using const variables to pass assembly flags, 'inline's
can't be dropped. So we simply mark them as __always_inline.

Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: linux-mips@vger.kernel.org
[paul.burton@mips.com:
  - Annotate these functions with __init, even if it only serves to
    inform human readers when the code can be used.
  - Drop the __always_inline from check_daddi() & check_daddiu() which
    don't use arguments as immediates in inline asm.
  - Rewrap the commit message.]
Signed-off-by: Paul Burton <paul.burton@mips.com>
---
 arch/mips/kernel/cpu-bugs64.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/cpu-bugs64.c
index fa62cd1dff93..6a7afe7ef4d3 100644
--- a/arch/mips/kernel/cpu-bugs64.c
+++ b/arch/mips/kernel/cpu-bugs64.c
@@ -24,7 +24,8 @@ static char r4kwar[] __initdata =
 static char daddiwar[] __initdata =
 	"Enable CPU_DADDI_WORKAROUNDS to rectify.";
 
-static inline void align_mod(const int align, const int mod)
+static __always_inline __init
+void align_mod(const int align, const int mod)
 {
 	asm volatile(
 		".set	push\n\t"
@@ -38,8 +39,9 @@ static inline void align_mod(const int align, const int mod)
 		: "n"(align), "n"(mod));
 }
 
-static __always_inline void mult_sh_align_mod(long *v1, long *v2, long *w,
-					      const int align, const int mod)
+static __always_inline __init
+void mult_sh_align_mod(long *v1, long *v2, long *w,
+		       const int align, const int mod)
 {
 	unsigned long flags;
 	int m1, m2;
@@ -113,7 +115,7 @@ static __always_inline void mult_sh_align_mod(long *v1, long *v2, long *w,
 	*w = lw;
 }
 
-static inline void check_mult_sh(void)
+static __always_inline __init void check_mult_sh(void)
 {
 	long v1[8], v2[8], w[8];
 	int bug, fix, i;
@@ -176,7 +178,7 @@ asmlinkage void __init do_daddi_ov(struct pt_regs *regs)
 	exception_exit(prev_state);
 }
 
-static inline void check_daddi(void)
+static __init void check_daddi(void)
 {
 	extern asmlinkage void handle_daddi_ov(void);
 	unsigned long flags;
@@ -242,7 +244,7 @@ static inline void check_daddi(void)
 
 int daddiu_bug	= IS_ENABLED(CONFIG_CPU_MIPSR6) ? 0 : -1;
 
-static inline void check_daddiu(void)
+static __init void check_daddiu(void)
 {
 	long v, w, tmp;
 
-- 
cgit v1.2.3


From 18856604b3e7090ce42d533995173ee70c24b1c9 Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmer@sifive.com>
Date: Tue, 24 Sep 2019 17:15:56 -0700
Subject: RISC-V: Clear load reservations while restoring hart contexts

This is almost entirely a comment.  The bug is unlikely to manifest on
existing hardware because there is a timeout on load reservations, but
manifests on QEMU because there is no timeout.

Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
---
 arch/riscv/include/asm/asm.h |  1 +
 arch/riscv/kernel/entry.S    | 21 ++++++++++++++++++++-
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 5a02b7d50940..9c992a88d858 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -22,6 +22,7 @@
 
 #define REG_L		__REG_SEL(ld, lw)
 #define REG_S		__REG_SEL(sd, sw)
+#define REG_SC		__REG_SEL(sc.d, sc.w)
 #define SZREG		__REG_SEL(8, 4)
 #define LGREG		__REG_SEL(3, 2)
 
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index da7aa88113c2..2d592da1e776 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -98,7 +98,26 @@ _save_context:
  */
 	.macro RESTORE_ALL
 	REG_L a0, PT_SSTATUS(sp)
-	REG_L a2, PT_SEPC(sp)
+	/*
+	 * The current load reservation is effectively part of the processor's
+	 * state, in the sense that load reservations cannot be shared between
+	 * different hart contexts.  We can't actually save and restore a load
+	 * reservation, so instead here we clear any existing reservation --
+	 * it's always legal for implementations to clear load reservations at
+	 * any point (as long as the forward progress guarantee is kept, but
+	 * we'll ignore that here).
+	 *
+	 * Dangling load reservations can be the result of taking a trap in the
+	 * middle of an LR/SC sequence, but can also be the result of a taken
+	 * forward branch around an SC -- which is how we implement CAS.  As a
+	 * result we need to clear reservations between the last CAS and the
+	 * jump back to the new context.  While it is unlikely the store
+	 * completes, implementations are allowed to expand reservations to be
+	 * arbitrarily large.
+	 */
+	REG_L  a2, PT_SEPC(sp)
+	REG_SC x0, a2, PT_SEPC(sp)
+
 	csrw CSR_SSTATUS, a0
 	csrw CSR_SEPC, a2
 
-- 
cgit v1.2.3


From 922b0375fc93fb1a20c5617e37c389c26bbccb70 Mon Sep 17 00:00:00 2001
From: Albert Ou <aou@eecs.berkeley.edu>
Date: Fri, 27 Sep 2019 16:14:18 -0700
Subject: riscv: Fix memblock reservation for device tree blob

This fixes an error with how the FDT blob is reserved in memblock.
An incorrect physical address calculation exposed the FDT header to
unintended corruption, which typically manifested with of_fdt_raw_init()
faulting during late boot after fdt_totalsize() returned a wrong value.
Systems with smaller physical memory sizes more frequently trigger this
issue, as the kernel is more likely to allocate from the DMA32 zone
where bbl places the DTB after the kernel image.

Commit 671f9a3e2e24 ("RISC-V: Setup initial page tables in two stages")
changed the mapping of the DTB to reside in the fixmap area.
Consequently, early_init_fdt_reserve_self() cannot be used anymore in
setup_bootmem() since it relies on __pa() to derive a physical address,
which does not work with dtb_early_va that is no longer a valid kernel
logical address.

The reserved[0x1] region shows the effect of the pointer underflow
resulting from the __pa(initial_boot_params) offset subtraction:

[    0.000000] MEMBLOCK configuration:
[    0.000000]  memory size = 0x000000001fe00000 reserved size = 0x0000000000a2e514
[    0.000000]  memory.cnt  = 0x1
[    0.000000]  memory[0x0]     [0x0000000080200000-0x000000009fffffff], 0x000000001fe00000 bytes flags: 0x0
[    0.000000]  reserved.cnt  = 0x2
[    0.000000]  reserved[0x0]   [0x0000000080200000-0x0000000080c2dfeb], 0x0000000000a2dfec bytes flags: 0x0
[    0.000000]  reserved[0x1]   [0xfffffff080100000-0xfffffff080100527], 0x0000000000000528 bytes flags: 0x0

With the fix applied:

[    0.000000] MEMBLOCK configuration:
[    0.000000]  memory size = 0x000000001fe00000 reserved size = 0x0000000000a2e514
[    0.000000]  memory.cnt  = 0x1
[    0.000000]  memory[0x0]     [0x0000000080200000-0x000000009fffffff], 0x000000001fe00000 bytes flags: 0x0
[    0.000000]  reserved.cnt  = 0x2
[    0.000000]  reserved[0x0]   [0x0000000080200000-0x0000000080c2dfeb], 0x0000000000a2dfec bytes flags: 0x0
[    0.000000]  reserved[0x1]   [0x0000000080e00000-0x0000000080e00527], 0x0000000000000528 bytes flags: 0x0

Fixes: 671f9a3e2e24 ("RISC-V: Setup initial page tables in two stages")
Signed-off-by: Albert Ou <aou@eecs.berkeley.edu>
Tested-by: Bin Meng <bmeng.cn@gmail.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
---
 arch/riscv/mm/init.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index f0ba71304b6e..83f7d12042fb 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -11,6 +11,7 @@
 #include <linux/swap.h>
 #include <linux/sizes.h>
 #include <linux/of_fdt.h>
+#include <linux/libfdt.h>
 
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
@@ -82,6 +83,8 @@ disable:
 }
 #endif /* CONFIG_BLK_DEV_INITRD */
 
+static phys_addr_t dtb_early_pa __initdata;
+
 void __init setup_bootmem(void)
 {
 	struct memblock_region *reg;
@@ -117,7 +120,12 @@ void __init setup_bootmem(void)
 	setup_initrd();
 #endif /* CONFIG_BLK_DEV_INITRD */
 
-	early_init_fdt_reserve_self();
+	/*
+	 * Avoid using early_init_fdt_reserve_self() since __pa() does
+	 * not work for DTB pointers that are fixmap addresses
+	 */
+	memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va));
+
 	early_init_fdt_scan_reserved_mem();
 	memblock_allow_resize();
 	memblock_dump_all();
@@ -393,6 +401,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 
 	/* Save pointer to DTB for early FDT parsing */
 	dtb_early_va = (void *)fix_to_virt(FIX_FDT) + (dtb_pa & ~PAGE_MASK);
+	/* Save physical address for memblock reservation */
+	dtb_early_pa = dtb_pa;
 }
 
 static void __init setup_vm_final(void)
-- 
cgit v1.2.3


From 86c1aea84b97120a6d428ce17a2ebd55be677f56 Mon Sep 17 00:00:00 2001
From: Brian Vazquez <brianvv@google.com>
Date: Tue, 1 Oct 2019 10:37:27 -0700
Subject: selftests/bpf: test_progs: Don't leak server_fd in tcp_rtt

server_fd needs to be closed if pthread can't be created.

Fixes: 8a03222f508b ("selftests/bpf: test_progs: fix client/server race in tcp_rtt")
Signed-off-by: Brian Vazquez <brianvv@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20191001173728.149786-2-brianvv@google.com
---
 tools/testing/selftests/bpf/prog_tests/tcp_rtt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index a82da555b1b0..f4cd60d6fba2 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -260,13 +260,14 @@ void test_tcp_rtt(void)
 
 	if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread,
 				      (void *)&server_fd)))
-		goto close_cgroup_fd;
+		goto close_server_fd;
 
 	pthread_mutex_lock(&server_started_mtx);
 	pthread_cond_wait(&server_started, &server_started_mtx);
 	pthread_mutex_unlock(&server_started_mtx);
 
 	CHECK_FAIL(run_test(cgroup_fd, server_fd));
+close_server_fd:
 	close(server_fd);
 close_cgroup_fd:
 	close(cgroup_fd);
-- 
cgit v1.2.3


From a2d074e4c6e81ec9ab359d54f0b88273c738de37 Mon Sep 17 00:00:00 2001
From: Brian Vazquez <brianvv@google.com>
Date: Tue, 1 Oct 2019 10:37:28 -0700
Subject: selftests/bpf: test_progs: Don't leak server_fd in
 test_sockopt_inherit

server_fd needs to be closed if pthread can't be created.

Fixes: e3e02e1d9c24 ("selftests/bpf: test_progs: convert test_sockopt_inherit")
Signed-off-by: Brian Vazquez <brianvv@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/bpf/20191001173728.149786-3-brianvv@google.com
---
 tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
index 6cbeea7b4bf1..8547ecbdc61f 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
@@ -195,7 +195,7 @@ static void run_test(int cgroup_fd)
 
 	if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread,
 				      (void *)&server_fd)))
-		goto close_bpf_object;
+		goto close_server_fd;
 
 	pthread_mutex_lock(&server_started_mtx);
 	pthread_cond_wait(&server_started, &server_started_mtx);
-- 
cgit v1.2.3


From 8353da9fa69722b54cba82b2ec740afd3d438748 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 30 Sep 2019 17:12:41 +0200
Subject: hso: fix NULL-deref on tty open

Fix NULL-pointer dereference on tty open due to a failure to handle a
missing interrupt-in endpoint when probing modem ports:

	BUG: kernel NULL pointer dereference, address: 0000000000000006
	...
	RIP: 0010:tiocmget_submit_urb+0x1c/0xe0 [hso]
	...
	Call Trace:
	hso_start_serial_device+0xdc/0x140 [hso]
	hso_serial_open+0x118/0x1b0 [hso]
	tty_open+0xf1/0x490

Fixes: 542f54823614 ("tty: Modem functions for the HSO driver")
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/hso.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index ce78714f536f..a505b2ab88b8 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -2620,14 +2620,18 @@ static struct hso_device *hso_create_bulk_serial_device(
 		 */
 		if (serial->tiocmget) {
 			tiocmget = serial->tiocmget;
+			tiocmget->endp = hso_get_ep(interface,
+						    USB_ENDPOINT_XFER_INT,
+						    USB_DIR_IN);
+			if (!tiocmget->endp) {
+				dev_err(&interface->dev, "Failed to find INT IN ep\n");
+				goto exit;
+			}
+
 			tiocmget->urb = usb_alloc_urb(0, GFP_KERNEL);
 			if (tiocmget->urb) {
 				mutex_init(&tiocmget->mutex);
 				init_waitqueue_head(&tiocmget->waitq);
-				tiocmget->endp = hso_get_ep(
-					interface,
-					USB_ENDPOINT_XFER_INT,
-					USB_DIR_IN);
 			} else
 				hso_free_tiomget(serial);
 		}
-- 
cgit v1.2.3


From 0d9138ffac24cf8b75366ede3a68c951e6dcc575 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <decui@microsoft.com>
Date: Mon, 30 Sep 2019 18:43:50 +0000
Subject: vsock: Fix a lockdep warning in __vsock_release()

Lockdep is unhappy if two locks from the same class are held.

Fix the below warning for hyperv and virtio sockets (vmci socket code
doesn't have the issue) by using lock_sock_nested() when __vsock_release()
is called recursively:

============================================
WARNING: possible recursive locking detected
5.3.0+ #1 Not tainted
--------------------------------------------
server/1795 is trying to acquire lock:
ffff8880c5158990 (sk_lock-AF_VSOCK){+.+.}, at: hvs_release+0x10/0x120 [hv_sock]

but task is already holding lock:
ffff8880c5158150 (sk_lock-AF_VSOCK){+.+.}, at: __vsock_release+0x2e/0xf0 [vsock]

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(sk_lock-AF_VSOCK);
  lock(sk_lock-AF_VSOCK);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

2 locks held by server/1795:
 #0: ffff8880c5d05ff8 (&sb->s_type->i_mutex_key#10){+.+.}, at: __sock_release+0x2d/0xa0
 #1: ffff8880c5158150 (sk_lock-AF_VSOCK){+.+.}, at: __vsock_release+0x2e/0xf0 [vsock]

stack backtrace:
CPU: 5 PID: 1795 Comm: server Not tainted 5.3.0+ #1
Call Trace:
 dump_stack+0x67/0x90
 __lock_acquire.cold.67+0xd2/0x20b
 lock_acquire+0xb5/0x1c0
 lock_sock_nested+0x6d/0x90
 hvs_release+0x10/0x120 [hv_sock]
 __vsock_release+0x24/0xf0 [vsock]
 __vsock_release+0xa0/0xf0 [vsock]
 vsock_release+0x12/0x30 [vsock]
 __sock_release+0x37/0xa0
 sock_close+0x14/0x20
 __fput+0xc1/0x250
 task_work_run+0x98/0xc0
 do_exit+0x344/0xc60
 do_group_exit+0x47/0xb0
 get_signal+0x15c/0xc50
 do_signal+0x30/0x720
 exit_to_usermode_loop+0x50/0xa0
 do_syscall_64+0x24e/0x270
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7f4184e85f31

Tested-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/af_vsock.c                | 16 ++++++++++++----
 net/vmw_vsock/hyperv_transport.c        |  2 +-
 net/vmw_vsock/virtio_transport_common.c |  2 +-
 3 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index ab47bf3ab66e..2ab43b2bba31 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -638,7 +638,7 @@ struct sock *__vsock_create(struct net *net,
 }
 EXPORT_SYMBOL_GPL(__vsock_create);
 
-static void __vsock_release(struct sock *sk)
+static void __vsock_release(struct sock *sk, int level)
 {
 	if (sk) {
 		struct sk_buff *skb;
@@ -648,9 +648,17 @@ static void __vsock_release(struct sock *sk)
 		vsk = vsock_sk(sk);
 		pending = NULL;	/* Compiler warning. */
 
+		/* The release call is supposed to use lock_sock_nested()
+		 * rather than lock_sock(), if a sock lock should be acquired.
+		 */
 		transport->release(vsk);
 
-		lock_sock(sk);
+		/* When "level" is SINGLE_DEPTH_NESTING, use the nested
+		 * version to avoid the warning "possible recursive locking
+		 * detected". When "level" is 0, lock_sock_nested(sk, level)
+		 * is the same as lock_sock(sk).
+		 */
+		lock_sock_nested(sk, level);
 		sock_orphan(sk);
 		sk->sk_shutdown = SHUTDOWN_MASK;
 
@@ -659,7 +667,7 @@ static void __vsock_release(struct sock *sk)
 
 		/* Clean up any sockets that never were accepted. */
 		while ((pending = vsock_dequeue_accept(sk)) != NULL) {
-			__vsock_release(pending);
+			__vsock_release(pending, SINGLE_DEPTH_NESTING);
 			sock_put(pending);
 		}
 
@@ -708,7 +716,7 @@ EXPORT_SYMBOL_GPL(vsock_stream_has_space);
 
 static int vsock_release(struct socket *sock)
 {
-	__vsock_release(sock->sk);
+	__vsock_release(sock->sk, 0);
 	sock->sk = NULL;
 	sock->state = SS_FREE;
 
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 261521d286d6..c443db7af8d4 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -559,7 +559,7 @@ static void hvs_release(struct vsock_sock *vsk)
 	struct sock *sk = sk_vsock(vsk);
 	bool remove_sock;
 
-	lock_sock(sk);
+	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 	remove_sock = hvs_close_lock_held(vsk);
 	release_sock(sk);
 	if (remove_sock)
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 5bb70c692b1e..a666ef8fc54e 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -820,7 +820,7 @@ void virtio_transport_release(struct vsock_sock *vsk)
 	struct sock *sk = &vsk->sk;
 	bool remove_sock = true;
 
-	lock_sock(sk);
+	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 	if (sk->sk_type == SOCK_STREAM)
 		remove_sock = virtio_transport_close(vsk);
 
-- 
cgit v1.2.3


From 3256a2d6ab1f71f9a1bd2d7f6f18eb8108c48d17 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 30 Sep 2019 15:44:44 -0700
Subject: tcp: adjust rto_base in retransmits_timed_out()

The cited commit exposed an old retransmits_timed_out() bug
which assumed it could call tcp_model_timeout() with
TCP_RTO_MIN as rto_base for all states.

But flows in SYN_SENT or SYN_RECV state uses a different
RTO base (1 sec instead of 200 ms, unless BPF choses
another value)

This caused a reduction of SYN retransmits from 6 to 4 with
the default /proc/sys/net/ipv4/tcp_syn_retries value.

Fixes: a41e8a88b06e ("tcp: better handle TCP_USER_TIMEOUT in SYN_SENT state")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 40de2d2364a1..05be564414e9 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -198,8 +198,13 @@ static bool retransmits_timed_out(struct sock *sk,
 		return false;
 
 	start_ts = tcp_sk(sk)->retrans_stamp;
-	if (likely(timeout == 0))
-		timeout = tcp_model_timeout(sk, boundary, TCP_RTO_MIN);
+	if (likely(timeout == 0)) {
+		unsigned int rto_base = TCP_RTO_MIN;
+
+		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
+			rto_base = tcp_timeout_init(sk);
+		timeout = tcp_model_timeout(sk, boundary, rto_base);
+	}
 
 	return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0;
 }
-- 
cgit v1.2.3


From a3ce2a21bb8969ae27917281244fa91bf5f286d7 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 30 Sep 2019 20:28:34 -0700
Subject: ipv6: Handle race in addrconf_dad_work

Rajendra reported a kernel panic when a link was taken down:

[ 6870.263084] BUG: unable to handle kernel NULL pointer dereference at 00000000000000a8
[ 6870.271856] IP: [<ffffffff8efc5764>] __ipv6_ifa_notify+0x154/0x290

<snip>

[ 6870.570501] Call Trace:
[ 6870.573238] [<ffffffff8efc58c6>] ? ipv6_ifa_notify+0x26/0x40
[ 6870.579665] [<ffffffff8efc98ec>] ? addrconf_dad_completed+0x4c/0x2c0
[ 6870.586869] [<ffffffff8efe70c6>] ? ipv6_dev_mc_inc+0x196/0x260
[ 6870.593491] [<ffffffff8efc9c6a>] ? addrconf_dad_work+0x10a/0x430
[ 6870.600305] [<ffffffff8f01ade4>] ? __switch_to_asm+0x34/0x70
[ 6870.606732] [<ffffffff8ea93a7a>] ? process_one_work+0x18a/0x430
[ 6870.613449] [<ffffffff8ea93d6d>] ? worker_thread+0x4d/0x490
[ 6870.619778] [<ffffffff8ea93d20>] ? process_one_work+0x430/0x430
[ 6870.626495] [<ffffffff8ea99dd9>] ? kthread+0xd9/0xf0
[ 6870.632145] [<ffffffff8f01ade4>] ? __switch_to_asm+0x34/0x70
[ 6870.638573] [<ffffffff8ea99d00>] ? kthread_park+0x60/0x60
[ 6870.644707] [<ffffffff8f01ae77>] ? ret_from_fork+0x57/0x70
[ 6870.650936] Code: 31 c0 31 d2 41 b9 20 00 08 02 b9 09 00 00 0

addrconf_dad_work is kicked to be scheduled when a device is brought
up. There is a race between addrcond_dad_work getting scheduled and
taking the rtnl lock and a process taking the link down (under rtnl).
The latter removes the host route from the inet6_addr as part of
addrconf_ifdown which is run for NETDEV_DOWN. The former attempts
to use the host route in ipv6_ifa_notify. If the down event removes
the host route due to the race to the rtnl, then the BUG listed above
occurs.

This scenario does not occur when the ipv6 address is not kept
(net.ipv6.conf.all.keep_addr_on_down = 0) as addrconf_ifdown sets the
state of the ifp to DEAD. Handle when the addresses are kept by checking
IF_READY which is reset by addrconf_ifdown.

The 'dead' flag for an inet6_addr is set only under rtnl, in
addrconf_ifdown and it means the device is getting removed (or IPv6 is
disabled). The interesting cases for changing the idev flag are
addrconf_notify (NETDEV_UP and NETDEV_CHANGE) and addrconf_ifdown
(reset the flag). The former does not have the idev lock - only rtnl;
the latter has both. Based on that the existing dead + IF_READY check
can be moved to right after the rtnl_lock in addrconf_dad_work.

Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Reported-by: Rajendra Dendukuri <rajendra.dendukuri@broadcom.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 6a576ff92c39..dd3be06d5a06 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4032,6 +4032,12 @@ static void addrconf_dad_work(struct work_struct *w)
 
 	rtnl_lock();
 
+	/* check if device was taken down before this delayed work
+	 * function could be canceled
+	 */
+	if (idev->dead || !(idev->if_flags & IF_READY))
+		goto out;
+
 	spin_lock_bh(&ifp->lock);
 	if (ifp->state == INET6_IFADDR_STATE_PREDAD) {
 		action = DAD_BEGIN;
@@ -4077,11 +4083,6 @@ static void addrconf_dad_work(struct work_struct *w)
 		goto out;
 
 	write_lock_bh(&idev->lock);
-	if (idev->dead || !(idev->if_flags & IF_READY)) {
-		write_unlock_bh(&idev->lock);
-		goto out;
-	}
-
 	spin_lock(&ifp->lock);
 	if (ifp->state == INET6_IFADDR_STATE_DEAD) {
 		spin_unlock(&ifp->lock);
-- 
cgit v1.2.3


From a761129e3625688310aecf26e1be9e98e85f8eb5 Mon Sep 17 00:00:00 2001
From: Dongli Zhang <dongli.zhang@oracle.com>
Date: Tue, 1 Oct 2019 21:56:41 +0800
Subject: xen-netfront: do not use ~0U as error return value for
 xennet_fill_frags()

xennet_fill_frags() uses ~0U as return value when the sk_buff is not able
to cache extra fragments. This is incorrect because the return type of
xennet_fill_frags() is RING_IDX and 0xffffffff is an expected value for
ring buffer index.

In the situation when the rsp_cons is approaching 0xffffffff, the return
value of xennet_fill_frags() may become 0xffffffff which xennet_poll() (the
caller) would regard as error. As a result, queue->rx.rsp_cons is set
incorrectly because it is updated only when there is error. If there is no
error, xennet_poll() would be responsible to update queue->rx.rsp_cons.
Finally, queue->rx.rsp_cons would point to the rx ring buffer entries whose
queue->rx_skbs[i] and queue->grant_rx_ref[i] are already cleared to NULL.
This leads to NULL pointer access in the next iteration to process rx ring
buffer entries.

The symptom is similar to the one fixed in
commit 00b368502d18 ("xen-netfront: do not assume sk_buff_head list is
empty in error handling").

This patch changes the return type of xennet_fill_frags() to indicate
whether it is successful or failed. The queue->rx.rsp_cons will be
always updated inside this function.

Fixes: ad4f15dc2c70 ("xen/netfront: don't bug in case of too many frags")
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index e14ec75b61d6..482c6c8b0fb7 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -887,9 +887,9 @@ static int xennet_set_skb_gso(struct sk_buff *skb,
 	return 0;
 }
 
-static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
-				  struct sk_buff *skb,
-				  struct sk_buff_head *list)
+static int xennet_fill_frags(struct netfront_queue *queue,
+			     struct sk_buff *skb,
+			     struct sk_buff_head *list)
 {
 	RING_IDX cons = queue->rx.rsp_cons;
 	struct sk_buff *nskb;
@@ -908,7 +908,7 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 		if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) {
 			queue->rx.rsp_cons = ++cons + skb_queue_len(list);
 			kfree_skb(nskb);
-			return ~0U;
+			return -ENOENT;
 		}
 
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
@@ -919,7 +919,9 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue,
 		kfree_skb(nskb);
 	}
 
-	return cons;
+	queue->rx.rsp_cons = cons;
+
+	return 0;
 }
 
 static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
@@ -1045,8 +1047,7 @@ err:
 		skb->data_len = rx->status;
 		skb->len += rx->status;
 
-		i = xennet_fill_frags(queue, skb, &tmpq);
-		if (unlikely(i == ~0U))
+		if (unlikely(xennet_fill_frags(queue, skb, &tmpq)))
 			goto err;
 
 		if (rx->flags & XEN_NETRXF_csum_blank)
@@ -1056,7 +1057,7 @@ err:
 
 		__skb_queue_tail(&rxq, skb);
 
-		queue->rx.rsp_cons = ++i;
+		i = ++queue->rx.rsp_cons;
 		work_done++;
 	}
 
-- 
cgit v1.2.3


From ec066de1a567169c4737a5933218c329cedf52bd Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Mon, 16 Sep 2019 09:51:33 +0000
Subject: arm: xen: mm: use __GPF_DMA32 for arm64

arm64 shares some code under arch/arm/xen, including mm.c.
However ZONE_DMA is removed by commit
ad67f5a6545("arm64: replace ZONE_DMA with ZONE_DMA32").

So add a check if CONFIG_ZONE_DMA32 is enabled use __GFP_DMA32.

Signed-off-by: Peng Fan <peng.fan@nxp.com>
Acked-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
---
 arch/arm/xen/mm.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index d33b77e9add3..018093fef80a 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -28,7 +28,10 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order)
 
 	for_each_memblock(memory, reg) {
 		if (reg->base < (phys_addr_t)0xffffffff) {
-			flags |= __GFP_DMA;
+			if (IS_ENABLED(CONFIG_ZONE_DMA32))
+				flags |= __GFP_DMA32;
+			else
+				flags |= __GFP_DMA;
 			break;
 		}
 	}
-- 
cgit v1.2.3


From c91a9cfe9f6d136172a52ff6e01b3f83ba850c19 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Thu, 26 Sep 2019 10:54:33 +0200
Subject: rt2x00: initialize last_reset

Initialize last_reset variable to INITIAL_JIFFIES, otherwise it is not
possible to test H/W reset for first 5 minutes of system run.

Fixes: e403fa31ed71 ("rt2x00: add restart hw")
Reported-and-tested-by: Jonathan Liu <net147@gmail.com>
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ralink/rt2x00/rt2x00debug.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c b/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c
index 4d4e3888ef20..f2395309ec00 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c
@@ -555,7 +555,7 @@ static ssize_t rt2x00debug_write_restart_hw(struct file *file,
 {
 	struct rt2x00debug_intf *intf =	file->private_data;
 	struct rt2x00_dev *rt2x00dev = intf->rt2x00dev;
-	static unsigned long last_reset;
+	static unsigned long last_reset = INITIAL_JIFFIES;
 
 	if (!rt2x00_has_cap_restart_hw(rt2x00dev))
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3


From a4311745bba9763e3c965643d4531bd5765b0513 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 28 Sep 2019 09:25:46 +0100
Subject: drm/i915/userptr: Never allow userptr into the mappable GGTT

Daniel Vetter uncovered a nasty cycle in using the mmu-notifiers to
invalidate userptr objects which also happen to be pulled into GGTT
mmaps. That is when we unbind the userptr object (on mmu invalidation),
we revoke all CPU mmaps, which may then recurse into mmu invalidation.

We looked for ways of breaking the cycle, but the revocation on
invalidation is required and cannot be avoided. The only solution we
could see was to not allow such GGTT bindings of userptr objects in the
first place. In practice, no one really wants to use a GGTT mmapping of
a CPU pointer...

Just before Daniel's explosive lockdep patches land in v5.4-rc1, we got
a genuine blip from CI:

<4>[  246.793958] ======================================================
<4>[  246.793972] WARNING: possible circular locking dependency detected
<4>[  246.793989] 5.3.0-gbd6c56f50d15-drmtip_372+ #1 Tainted: G     U
<4>[  246.794003] ------------------------------------------------------
<4>[  246.794017] kswapd0/145 is trying to acquire lock:
<4>[  246.794030] 000000003f565be6 (&dev->struct_mutex/1){+.+.}, at: userptr_mn_invalidate_range_start+0x18f/0x220 [i915]
<4>[  246.794250]
                  but task is already holding lock:
<4>[  246.794263] 000000001799cef9 (&anon_vma->rwsem){++++}, at: page_lock_anon_vma_read+0xe6/0x2a0
<4>[  246.794291]
                  which lock already depends on the new lock.

<4>[  246.794307]
                  the existing dependency chain (in reverse order) is:
<4>[  246.794322]
                  -> #3 (&anon_vma->rwsem){++++}:
<4>[  246.794344]        down_write+0x33/0x70
<4>[  246.794357]        __vma_adjust+0x3d9/0x7b0
<4>[  246.794370]        __split_vma+0x16a/0x180
<4>[  246.794385]        mprotect_fixup+0x2a5/0x320
<4>[  246.794399]        do_mprotect_pkey+0x208/0x2e0
<4>[  246.794413]        __x64_sys_mprotect+0x16/0x20
<4>[  246.794429]        do_syscall_64+0x55/0x1c0
<4>[  246.794443]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  246.794456]
                  -> #2 (&mapping->i_mmap_rwsem){++++}:
<4>[  246.794478]        down_write+0x33/0x70
<4>[  246.794493]        unmap_mapping_pages+0x48/0x130
<4>[  246.794519]        i915_vma_revoke_mmap+0x81/0x1b0 [i915]
<4>[  246.794519]        i915_vma_unbind+0x11d/0x4a0 [i915]
<4>[  246.794519]        i915_vma_destroy+0x31/0x300 [i915]
<4>[  246.794519]        __i915_gem_free_objects+0xb8/0x4b0 [i915]
<4>[  246.794519]        drm_file_free.part.0+0x1e6/0x290
<4>[  246.794519]        drm_release+0xa6/0xe0
<4>[  246.794519]        __fput+0xc2/0x250
<4>[  246.794519]        task_work_run+0x82/0xb0
<4>[  246.794519]        do_exit+0x35b/0xdb0
<4>[  246.794519]        do_group_exit+0x34/0xb0
<4>[  246.794519]        __x64_sys_exit_group+0xf/0x10
<4>[  246.794519]        do_syscall_64+0x55/0x1c0
<4>[  246.794519]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  246.794519]
                  -> #1 (&vm->mutex){+.+.}:
<4>[  246.794519]        i915_gem_shrinker_taints_mutex+0x6d/0xe0 [i915]
<4>[  246.794519]        i915_address_space_init+0x9f/0x160 [i915]
<4>[  246.794519]        i915_ggtt_init_hw+0x55/0x170 [i915]
<4>[  246.794519]        i915_driver_probe+0xc9f/0x1620 [i915]
<4>[  246.794519]        i915_pci_probe+0x43/0x1b0 [i915]
<4>[  246.794519]        pci_device_probe+0x9e/0x120
<4>[  246.794519]        really_probe+0xea/0x3d0
<4>[  246.794519]        driver_probe_device+0x10b/0x120
<4>[  246.794519]        device_driver_attach+0x4a/0x50
<4>[  246.794519]        __driver_attach+0x97/0x130
<4>[  246.794519]        bus_for_each_dev+0x74/0xc0
<4>[  246.794519]        bus_add_driver+0x13f/0x210
<4>[  246.794519]        driver_register+0x56/0xe0
<4>[  246.794519]        do_one_initcall+0x58/0x300
<4>[  246.794519]        do_init_module+0x56/0x1f6
<4>[  246.794519]        load_module+0x25bd/0x2a40
<4>[  246.794519]        __se_sys_finit_module+0xd3/0xf0
<4>[  246.794519]        do_syscall_64+0x55/0x1c0
<4>[  246.794519]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  246.794519]
                  -> #0 (&dev->struct_mutex/1){+.+.}:
<4>[  246.794519]        __lock_acquire+0x15d8/0x1e90
<4>[  246.794519]        lock_acquire+0xa6/0x1c0
<4>[  246.794519]        __mutex_lock+0x9d/0x9b0
<4>[  246.794519]        userptr_mn_invalidate_range_start+0x18f/0x220 [i915]
<4>[  246.794519]        __mmu_notifier_invalidate_range_start+0x85/0x110
<4>[  246.794519]        try_to_unmap_one+0x76b/0x860
<4>[  246.794519]        rmap_walk_anon+0x104/0x280
<4>[  246.794519]        try_to_unmap+0xc0/0xf0
<4>[  246.794519]        shrink_page_list+0x561/0xc10
<4>[  246.794519]        shrink_inactive_list+0x220/0x440
<4>[  246.794519]        shrink_node_memcg+0x36e/0x740
<4>[  246.794519]        shrink_node+0xcb/0x490
<4>[  246.794519]        balance_pgdat+0x241/0x580
<4>[  246.794519]        kswapd+0x16c/0x530
<4>[  246.794519]        kthread+0x119/0x130
<4>[  246.794519]        ret_from_fork+0x24/0x50
<4>[  246.794519]
                  other info that might help us debug this:

<4>[  246.794519] Chain exists of:
                    &dev->struct_mutex/1 --> &mapping->i_mmap_rwsem --> &anon_vma->rwsem

<4>[  246.794519]  Possible unsafe locking scenario:

<4>[  246.794519]        CPU0                    CPU1
<4>[  246.794519]        ----                    ----
<4>[  246.794519]   lock(&anon_vma->rwsem);
<4>[  246.794519]                                lock(&mapping->i_mmap_rwsem);
<4>[  246.794519]                                lock(&anon_vma->rwsem);
<4>[  246.794519]   lock(&dev->struct_mutex/1);
<4>[  246.794519]
                   *** DEADLOCK ***

v2: Say no to mmap_ioctl

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111744
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111870
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: stable@vger.kernel.org
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190928082546.3473-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_mman.c         | 7 +++++++
 drivers/gpu/drm/i915/gem/i915_gem_object.h       | 6 ++++++
 drivers/gpu/drm/i915/gem/i915_gem_object_types.h | 3 ++-
 drivers/gpu/drm/i915/gem/i915_gem_userptr.c      | 1 +
 drivers/gpu/drm/i915/i915_gem.c                  | 3 +++
 5 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 860b751c51f1..dd0c2840ba4d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -343,6 +343,7 @@ err:
 		/* fallthrough */
 	case -EIO: /* shmemfs failure from swap device */
 	case -EFAULT: /* purged object */
+	case -ENODEV: /* bad object, how did you get here! */
 		return VM_FAULT_SIGBUS;
 
 	case -ENOSPC: /* shmemfs allocation failure */
@@ -466,10 +467,16 @@ i915_gem_mmap_gtt(struct drm_file *file,
 	if (!obj)
 		return -ENOENT;
 
+	if (i915_gem_object_never_bind_ggtt(obj)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	ret = create_mmap_offset(obj);
 	if (ret == 0)
 		*offset = drm_vma_node_offset_addr(&obj->base.vma_node);
 
+out:
 	i915_gem_object_put(obj);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 29b9eddc4c7f..aec05f967d9d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -152,6 +152,12 @@ i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj)
 	return obj->ops->flags & I915_GEM_OBJECT_IS_PROXY;
 }
 
+static inline bool
+i915_gem_object_never_bind_ggtt(const struct drm_i915_gem_object *obj)
+{
+	return obj->ops->flags & I915_GEM_OBJECT_NO_GGTT;
+}
+
 static inline bool
 i915_gem_object_needs_async_cancel(const struct drm_i915_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index d695f187b790..e1aab2fd1cd9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -32,7 +32,8 @@ struct drm_i915_gem_object_ops {
 #define I915_GEM_OBJECT_HAS_STRUCT_PAGE	BIT(0)
 #define I915_GEM_OBJECT_IS_SHRINKABLE	BIT(1)
 #define I915_GEM_OBJECT_IS_PROXY	BIT(2)
-#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(3)
+#define I915_GEM_OBJECT_NO_GGTT		BIT(3)
+#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(4)
 
 	/* Interface between the GEM object and its backing storage.
 	 * get_pages() is called once prior to the use of the associated set
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 74da35611d7c..a0d974ac78a7 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -710,6 +710,7 @@ i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj)
 static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
 	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
 		 I915_GEM_OBJECT_IS_SHRINKABLE |
+		 I915_GEM_OBJECT_NO_GGTT |
 		 I915_GEM_OBJECT_ASYNC_CANCEL,
 	.get_pages = i915_gem_userptr_get_pages,
 	.put_pages = i915_gem_userptr_put_pages,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 3d3fda4cae99..1426e506700d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -970,6 +970,9 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 
 	lockdep_assert_held(&obj->base.dev->struct_mutex);
 
+	if (i915_gem_object_never_bind_ggtt(obj))
+		return ERR_PTR(-ENODEV);
+
 	if (flags & PIN_MAPPABLE &&
 	    (!view || view->type == I915_GGTT_VIEW_NORMAL)) {
 		/* If the required space is larger than the available
-- 
cgit v1.2.3


From 357f16d9e0194cdbc36531ff88b453481560b76a Mon Sep 17 00:00:00 2001
From: Beni Mahler <beni.mahler@gmx.net>
Date: Thu, 5 Sep 2019 00:26:20 +0200
Subject: USB: serial: ftdi_sio: add device IDs for Sienna and Echelon PL-20

Both devices added here have a FTDI chip inside. The device from Echelon
is called 'Network Interface' it is actually a LON network gateway.

 ID 0403:8348 Future Technology Devices International, Ltd
 https://www.eltako.com/fileadmin/downloads/de/datenblatt/Datenblatt_PL-SW-PROF.pdf

 ID 0920:7500 Network Interface
 https://www.echelon.com/products/u20-usb-network-interface

Signed-off-by: Beni Mahler <beni.mahler@gmx.net>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/ftdi_sio.c     | 3 +++
 drivers/usb/serial/ftdi_sio_ids.h | 9 +++++++++
 2 files changed, 12 insertions(+)

diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index f0688c44b04c..25e81faf4c24 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1030,6 +1030,9 @@ static const struct usb_device_id id_table_combined[] = {
 	/* EZPrototypes devices */
 	{ USB_DEVICE(EZPROTOTYPES_VID, HJELMSLUND_USB485_ISO_PID) },
 	{ USB_DEVICE_INTERFACE_NUMBER(UNJO_VID, UNJO_ISODEBUG_V1_PID, 1) },
+	/* Sienna devices */
+	{ USB_DEVICE(FTDI_VID, FTDI_SIENNA_PID) },
+	{ USB_DEVICE(ECHELON_VID, ECHELON_U20_PID) },
 	{ }					/* Terminating entry */
 };
 
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index f12d806220b4..22d66217cb41 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -39,6 +39,9 @@
 
 #define FTDI_LUMEL_PD12_PID	0x6002
 
+/* Sienna Serial Interface by Secyourit GmbH */
+#define FTDI_SIENNA_PID		0x8348
+
 /* Cyber Cortex AV by Fabulous Silicon (http://fabuloussilicon.com) */
 #define CYBER_CORTEX_AV_PID	0x8698
 
@@ -688,6 +691,12 @@
 #define BANDB_TTL3USB9M_PID	0xAC50
 #define BANDB_ZZ_PROG1_USB_PID	0xBA02
 
+/*
+ * Echelon USB Serial Interface
+ */
+#define ECHELON_VID		0x0920
+#define ECHELON_U20_PID		0x7500
+
 /*
  * Intrepid Control Systems (http://www.intrepidcs.com/) ValueCAN and NeoVI
  */
-- 
cgit v1.2.3


From 5eb3f4b87a0e7e949c976f32f296176a06d1a93b Mon Sep 17 00:00:00 2001
From: Daniele Palmas <dnlplm@gmail.com>
Date: Mon, 23 Sep 2019 12:23:28 +0200
Subject: USB: serial: option: add Telit FN980 compositions

This patch adds the following Telit FN980 compositions:

0x1050: tty, adb, rmnet, tty, tty, tty, tty
0x1051: tty, adb, mbim, tty, tty, tty, tty
0x1052: rndis, tty, adb, tty, tty, tty, tty
0x1053: tty, adb, ecm, tty, tty, tty, tty

Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/option.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 38e920ac7f82..10ac3610d922 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1154,6 +1154,14 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) | RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG5, 0xff),
 	  .driver_info = RSVD(0) | RSVD(1) | NCTRL(2) | RSVD(3) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1050, 0xff),	/* Telit FN980 (rmnet) */
+	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1051, 0xff),	/* Telit FN980 (MBIM) */
+	  .driver_info = NCTRL(0) | RSVD(1) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1052, 0xff),	/* Telit FN980 (RNDIS) */
+	  .driver_info = NCTRL(2) | RSVD(3) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1053, 0xff),	/* Telit FN980 (ECM) */
+	  .driver_info = NCTRL(0) | RSVD(1) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
-- 
cgit v1.2.3


From 4fb8783165b7c6fb4b52428dbb80da8554e5fd1e Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 1 Oct 2019 18:25:06 +0300
Subject: drm/i915/display: abstract all vgaarb access to intel_vga.[ch]
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Split out the code related to vga client and vgaarb all over the place
into new intel_vga.[ch]. No functional changes.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191001152506.7854-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/Makefile                      |   3 +-
 drivers/gpu/drm/i915/display/intel_display.c       |  97 +------------
 drivers/gpu/drm/i915/display/intel_display.h       |   3 -
 drivers/gpu/drm/i915/display/intel_display_power.c |  24 +---
 drivers/gpu/drm/i915/display/intel_vga.c           | 160 +++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_vga.h           |  18 +++
 drivers/gpu/drm/i915/i915_drv.c                    |  30 +---
 drivers/gpu/drm/i915/i915_pci.c                    |   1 -
 drivers/gpu/drm/i915/i915_suspend.c                |   3 +-
 drivers/gpu/drm/i915/intel_runtime_pm.c            |   1 -
 10 files changed, 194 insertions(+), 146 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/display/intel_vga.c
 create mode 100644 drivers/gpu/drm/i915/display/intel_vga.h

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 8d407ff7d59d..b020b024286d 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -184,7 +184,8 @@ i915-y += \
 	display/intel_psr.o \
 	display/intel_quirks.o \
 	display/intel_sprite.o \
-	display/intel_tc.o
+	display/intel_tc.o \
+	display/intel_vga.o
 i915-$(CONFIG_ACPI) += \
 	display/intel_acpi.o \
 	display/intel_opregion.o
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index f1328c08f4ad..d99c59e97568 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -31,7 +31,6 @@
 #include <linux/module.h>
 #include <linux/dma-resv.h>
 #include <linux/slab.h>
-#include <linux/vgaarb.h>
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
@@ -79,6 +78,7 @@
 #include "intel_sideband.h"
 #include "intel_sprite.h"
 #include "intel_tc.h"
+#include "intel_vga.h"
 
 /* Primary plane formats for gen <= 3 */
 static const u32 i8xx_primary_formats[] = {
@@ -4241,7 +4241,7 @@ __intel_display_resume(struct drm_device *dev,
 	int i, ret;
 
 	intel_modeset_setup_hw_state(dev, ctx);
-	i915_redisable_vga(to_i915(dev));
+	intel_vga_redisable(to_i915(dev));
 
 	if (!state)
 		return 0;
@@ -15994,35 +15994,6 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv)
 
 }
 
-static i915_reg_t i915_vgacntrl_reg(struct drm_i915_private *dev_priv)
-{
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		return VLV_VGACNTRL;
-	else if (INTEL_GEN(dev_priv) >= 5)
-		return CPU_VGACNTRL;
-	else
-		return VGACNTRL;
-}
-
-/* Disable the VGA plane that we never use */
-static void i915_disable_vga(struct drm_i915_private *dev_priv)
-{
-	struct pci_dev *pdev = dev_priv->drm.pdev;
-	u8 sr1;
-	i915_reg_t vga_reg = i915_vgacntrl_reg(dev_priv);
-
-	/* WaEnableVGAAccessThroughIOPort:ctg,elk,ilk,snb,ivb,vlv,hsw */
-	vga_get_uninterruptible(pdev, VGA_RSRC_LEGACY_IO);
-	outb(SR01, VGA_SR_INDEX);
-	sr1 = inb(VGA_SR_DATA);
-	outb(sr1 | 1<<5, VGA_SR_DATA);
-	vga_put(pdev, VGA_RSRC_LEGACY_IO);
-	udelay(300);
-
-	I915_WRITE(vga_reg, VGA_DISP_DISABLE);
-	POSTING_READ(vga_reg);
-}
-
 void intel_modeset_init_hw(struct drm_i915_private *i915)
 {
 	intel_update_cdclk(i915);
@@ -16288,7 +16259,7 @@ int intel_modeset_init(struct drm_i915_private *i915)
 		intel_update_max_cdclk(i915);
 
 	/* Just disable it once at startup */
-	i915_disable_vga(i915);
+	intel_vga_disable(i915);
 	intel_setup_outputs(i915);
 
 	drm_modeset_lock_all(dev);
@@ -16647,39 +16618,6 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 		icl_sanitize_encoder_pll_mapping(encoder);
 }
 
-void i915_redisable_vga_power_on(struct drm_i915_private *dev_priv)
-{
-	i915_reg_t vga_reg = i915_vgacntrl_reg(dev_priv);
-
-	if (!(I915_READ(vga_reg) & VGA_DISP_DISABLE)) {
-		DRM_DEBUG_KMS("Something enabled VGA plane, disabling it\n");
-		i915_disable_vga(dev_priv);
-	}
-}
-
-void i915_redisable_vga(struct drm_i915_private *dev_priv)
-{
-	intel_wakeref_t wakeref;
-
-	/*
-	 * This function can be called both from intel_modeset_setup_hw_state or
-	 * at a very early point in our resume sequence, where the power well
-	 * structures are not yet restored. Since this function is at a very
-	 * paranoid "someone might have enabled VGA while we were not looking"
-	 * level, just check if the power well is enabled instead of trying to
-	 * follow the "don't touch the power well if we don't need it" policy
-	 * the rest of the driver uses.
-	 */
-	wakeref = intel_display_power_get_if_enabled(dev_priv,
-						     POWER_DOMAIN_VGA);
-	if (!wakeref)
-		return;
-
-	i915_redisable_vga_power_on(dev_priv);
-
-	intel_display_power_put(dev_priv, POWER_DOMAIN_VGA, wakeref);
-}
-
 /* FIXME read out full plane state for all planes */
 static void readout_plane_state(struct drm_i915_private *dev_priv)
 {
@@ -17188,35 +17126,6 @@ void intel_modeset_driver_remove(struct drm_i915_private *i915)
 	intel_fbc_cleanup_cfb(i915);
 }
 
-/*
- * set vga decode state - true == enable VGA decode
- */
-int intel_modeset_vga_set_state(struct drm_i915_private *dev_priv, bool state)
-{
-	unsigned reg = INTEL_GEN(dev_priv) >= 6 ? SNB_GMCH_CTRL : INTEL_GMCH_CTRL;
-	u16 gmch_ctrl;
-
-	if (pci_read_config_word(dev_priv->bridge_dev, reg, &gmch_ctrl)) {
-		DRM_ERROR("failed to read control word\n");
-		return -EIO;
-	}
-
-	if (!!(gmch_ctrl & INTEL_GMCH_VGA_DISABLE) == !state)
-		return 0;
-
-	if (state)
-		gmch_ctrl &= ~INTEL_GMCH_VGA_DISABLE;
-	else
-		gmch_ctrl |= INTEL_GMCH_VGA_DISABLE;
-
-	if (pci_write_config_word(dev_priv->bridge_dev, reg, gmch_ctrl)) {
-		DRM_ERROR("failed to write control word\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
 #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR)
 
 struct intel_display_error_state {
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 4b9e18e5a263..2782f23ee887 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -579,10 +579,7 @@ void intel_display_print_error_state(struct drm_i915_error_state_buf *e,
 void intel_modeset_init_hw(struct drm_i915_private *i915);
 int intel_modeset_init(struct drm_i915_private *i915);
 void intel_modeset_driver_remove(struct drm_i915_private *i915);
-int intel_modeset_vga_set_state(struct drm_i915_private *dev_priv, bool state);
 void intel_display_resume(struct drm_device *dev);
-void i915_redisable_vga(struct drm_i915_private *dev_priv);
-void i915_redisable_vga_power_on(struct drm_i915_private *dev_priv);
 void intel_init_pch_refclk(struct drm_i915_private *dev_priv);
 
 /* modesetting asserts */
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index f1186bc23542..bb642a1a0dd4 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -3,8 +3,6 @@
  * Copyright © 2019 Intel Corporation
  */
 
-#include <linux/vgaarb.h>
-
 #include "display/intel_crt.h"
 #include "display/intel_dp.h"
 
@@ -19,6 +17,7 @@
 #include "intel_hotplug.h"
 #include "intel_sideband.h"
 #include "intel_tc.h"
+#include "intel_vga.h"
 
 bool intel_display_power_well_is_enabled(struct drm_i915_private *dev_priv,
 					 enum i915_power_well_id power_well_id);
@@ -267,23 +266,8 @@ bool intel_display_power_is_enabled(struct drm_i915_private *dev_priv,
 static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv,
 				       u8 irq_pipe_mask, bool has_vga)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
-
-	/*
-	 * After we re-enable the power well, if we touch VGA register 0x3d5
-	 * we'll get unclaimed register interrupts. This stops after we write
-	 * anything to the VGA MSR register. The vgacon module uses this
-	 * register all the time, so if we unbind our driver and, as a
-	 * consequence, bind vgacon, we'll get stuck in an infinite loop at
-	 * console_unlock(). So make here we touch the VGA MSR register, making
-	 * sure vgacon can keep working normally without triggering interrupts
-	 * and error messages.
-	 */
-	if (has_vga) {
-		vga_get_uninterruptible(pdev, VGA_RSRC_LEGACY_IO);
-		outb(inb(VGA_MSR_READ), VGA_MSR_WRITE);
-		vga_put(pdev, VGA_RSRC_LEGACY_IO);
-	}
+	if (has_vga)
+		intel_vga_msr_write(dev_priv);
 
 	if (irq_pipe_mask)
 		gen8_irq_power_well_post_enable(dev_priv, irq_pipe_mask);
@@ -1205,7 +1189,7 @@ static void vlv_display_power_well_init(struct drm_i915_private *dev_priv)
 			intel_crt_reset(&encoder->base);
 	}
 
-	i915_redisable_vga_power_on(dev_priv);
+	intel_vga_redisable_power_on(dev_priv);
 
 	intel_pps_unlock_regs_wa(dev_priv);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_vga.c b/drivers/gpu/drm/i915/display/intel_vga.c
new file mode 100644
index 000000000000..732568eaa988
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_vga.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/pci.h>
+#include <linux/vgaarb.h>
+
+#include <drm/i915_drm.h>
+
+#include "i915_drv.h"
+#include "intel_vga.h"
+
+static i915_reg_t intel_vga_cntrl_reg(struct drm_i915_private *i915)
+{
+	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
+		return VLV_VGACNTRL;
+	else if (INTEL_GEN(i915) >= 5)
+		return CPU_VGACNTRL;
+	else
+		return VGACNTRL;
+}
+
+/* Disable the VGA plane that we never use */
+void intel_vga_disable(struct drm_i915_private *dev_priv)
+{
+	struct pci_dev *pdev = dev_priv->drm.pdev;
+	i915_reg_t vga_reg = intel_vga_cntrl_reg(dev_priv);
+	u8 sr1;
+
+	/* WaEnableVGAAccessThroughIOPort:ctg,elk,ilk,snb,ivb,vlv,hsw */
+	vga_get_uninterruptible(pdev, VGA_RSRC_LEGACY_IO);
+	outb(SR01, VGA_SR_INDEX);
+	sr1 = inb(VGA_SR_DATA);
+	outb(sr1 | 1 << 5, VGA_SR_DATA);
+	vga_put(pdev, VGA_RSRC_LEGACY_IO);
+	udelay(300);
+
+	I915_WRITE(vga_reg, VGA_DISP_DISABLE);
+	POSTING_READ(vga_reg);
+}
+
+void intel_vga_redisable_power_on(struct drm_i915_private *dev_priv)
+{
+	i915_reg_t vga_reg = intel_vga_cntrl_reg(dev_priv);
+
+	if (!(I915_READ(vga_reg) & VGA_DISP_DISABLE)) {
+		DRM_DEBUG_KMS("Something enabled VGA plane, disabling it\n");
+		intel_vga_disable(dev_priv);
+	}
+}
+
+void intel_vga_redisable(struct drm_i915_private *i915)
+{
+	intel_wakeref_t wakeref;
+
+	/*
+	 * This function can be called both from intel_modeset_setup_hw_state or
+	 * at a very early point in our resume sequence, where the power well
+	 * structures are not yet restored. Since this function is at a very
+	 * paranoid "someone might have enabled VGA while we were not looking"
+	 * level, just check if the power well is enabled instead of trying to
+	 * follow the "don't touch the power well if we don't need it" policy
+	 * the rest of the driver uses.
+	 */
+	wakeref = intel_display_power_get_if_enabled(i915, POWER_DOMAIN_VGA);
+	if (!wakeref)
+		return;
+
+	intel_vga_redisable_power_on(i915);
+
+	intel_display_power_put(i915, POWER_DOMAIN_VGA, wakeref);
+}
+
+void intel_vga_msr_write(struct drm_i915_private *i915)
+{
+	struct pci_dev *pdev = i915->drm.pdev;
+
+	/*
+	 * After we re-enable the power well, if we touch VGA register 0x3d5
+	 * we'll get unclaimed register interrupts. This stops after we write
+	 * anything to the VGA MSR register. The vgacon module uses this
+	 * register all the time, so if we unbind our driver and, as a
+	 * consequence, bind vgacon, we'll get stuck in an infinite loop at
+	 * console_unlock(). So make here we touch the VGA MSR register, making
+	 * sure vgacon can keep working normally without triggering interrupts
+	 * and error messages.
+	 */
+	vga_get_uninterruptible(pdev, VGA_RSRC_LEGACY_IO);
+	outb(inb(VGA_MSR_READ), VGA_MSR_WRITE);
+	vga_put(pdev, VGA_RSRC_LEGACY_IO);
+}
+
+static int
+intel_vga_set_state(struct drm_i915_private *i915, bool enable_decode)
+{
+	unsigned int reg = INTEL_GEN(i915) >= 6 ? SNB_GMCH_CTRL : INTEL_GMCH_CTRL;
+	u16 gmch_ctrl;
+
+	if (pci_read_config_word(i915->bridge_dev, reg, &gmch_ctrl)) {
+		DRM_ERROR("failed to read control word\n");
+		return -EIO;
+	}
+
+	if (!!(gmch_ctrl & INTEL_GMCH_VGA_DISABLE) == !enable_decode)
+		return 0;
+
+	if (enable_decode)
+		gmch_ctrl &= ~INTEL_GMCH_VGA_DISABLE;
+	else
+		gmch_ctrl |= INTEL_GMCH_VGA_DISABLE;
+
+	if (pci_write_config_word(i915->bridge_dev, reg, gmch_ctrl)) {
+		DRM_ERROR("failed to write control word\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static unsigned int
+intel_vga_set_decode(void *cookie, bool enable_decode)
+{
+	struct drm_i915_private *i915 = cookie;
+
+	intel_vga_set_state(i915, enable_decode);
+
+	if (enable_decode)
+		return VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM |
+		       VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;
+	else
+		return VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;
+}
+
+int intel_vga_register(struct drm_i915_private *i915)
+{
+	struct pci_dev *pdev = i915->drm.pdev;
+	int ret;
+
+	/*
+	 * If we have > 1 VGA cards, then we need to arbitrate access to the
+	 * common VGA resources.
+	 *
+	 * If we are a secondary display controller (!PCI_DISPLAY_CLASS_VGA),
+	 * then we do not take part in VGA arbitration and the
+	 * vga_client_register() fails with -ENODEV.
+	 */
+	ret = vga_client_register(pdev, i915, NULL, intel_vga_set_decode);
+	if (ret && ret != -ENODEV)
+		return ret;
+
+	return 0;
+}
+
+void intel_vga_unregister(struct drm_i915_private *i915)
+{
+	struct pci_dev *pdev = i915->drm.pdev;
+
+	vga_client_register(pdev, NULL, NULL, NULL);
+}
diff --git a/drivers/gpu/drm/i915/display/intel_vga.h b/drivers/gpu/drm/i915/display/intel_vga.h
new file mode 100644
index 000000000000..3517872e62ac
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_vga.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __INTEL_VGA_H__
+#define __INTEL_VGA_H__
+
+struct drm_i915_private;
+
+void intel_vga_msr_write(struct drm_i915_private *i915);
+void intel_vga_disable(struct drm_i915_private *i915);
+void intel_vga_redisable(struct drm_i915_private *i915);
+void intel_vga_redisable_power_on(struct drm_i915_private *i915);
+int intel_vga_register(struct drm_i915_private *i915);
+void intel_vga_unregister(struct drm_i915_private *i915);
+
+#endif /* __INTEL_VGA_H__ */
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 364f7d0b7e31..1d2246c59cde 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -36,7 +36,6 @@
 #include <linux/pm_runtime.h>
 #include <linux/pnp.h>
 #include <linux/slab.h>
-#include <linux/vgaarb.h>
 #include <linux/vga_switcheroo.h>
 #include <linux/vt.h>
 #include <acpi/video.h>
@@ -59,6 +58,7 @@
 #include "display/intel_overlay.h"
 #include "display/intel_pipe_crc.h"
 #include "display/intel_sprite.h"
+#include "display/intel_vga.h"
 
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_ioctls.h"
@@ -269,19 +269,6 @@ intel_teardown_mchbar(struct drm_i915_private *dev_priv)
 		release_resource(&dev_priv->mch_res);
 }
 
-/* true = enable decode, false = disable decoder */
-static unsigned int i915_vga_set_decode(void *cookie, bool state)
-{
-	struct drm_i915_private *dev_priv = cookie;
-
-	intel_modeset_vga_set_state(dev_priv, state);
-	if (state)
-		return VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM |
-		       VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;
-	else
-		return VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;
-}
-
 static int i915_resume_switcheroo(struct drm_i915_private *i915);
 static int i915_suspend_switcheroo(struct drm_i915_private *i915,
 				   pm_message_t state);
@@ -346,15 +333,8 @@ static int i915_driver_modeset_probe(struct drm_i915_private *i915)
 
 	intel_bios_init(i915);
 
-	/* If we have > 1 VGA cards, then we need to arbitrate access
-	 * to the common VGA resources.
-	 *
-	 * If we are a secondary display controller (!PCI_DISPLAY_CLASS_VGA),
-	 * then we do not take part in VGA arbitration and the
-	 * vga_client_register() fails with -ENODEV.
-	 */
-	ret = vga_client_register(pdev, i915, NULL, i915_vga_set_decode);
-	if (ret && ret != -ENODEV)
+	ret = intel_vga_register(i915);
+	if (ret)
 		goto out;
 
 	intel_register_dsm_handler();
@@ -416,7 +396,7 @@ cleanup_csr:
 	intel_power_domains_driver_remove(i915);
 	vga_switcheroo_unregister_client(pdev);
 cleanup_vga_client:
-	vga_client_register(pdev, NULL, NULL, NULL);
+	intel_vga_unregister(i915);
 out:
 	return ret;
 }
@@ -455,7 +435,7 @@ static void i915_driver_modeset_remove(struct drm_i915_private *i915)
 	intel_bios_driver_remove(i915);
 
 	vga_switcheroo_unregister_client(pdev);
-	vga_client_register(pdev, NULL, NULL, NULL);
+	intel_vga_unregister(i915);
 
 	intel_csr_ucode_fini(i915);
 }
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index ea53dfe2fba0..1cbf3998b361 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -23,7 +23,6 @@
  */
 
 #include <linux/console.h>
-#include <linux/vgaarb.h>
 #include <linux/vga_switcheroo.h>
 
 #include <drm/drm_drv.h>
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index 8508a01ad8b9..2b2086def0f1 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -28,6 +28,7 @@
 
 #include "display/intel_fbc.h"
 #include "display/intel_gmbus.h"
+#include "display/intel_vga.h"
 
 #include "i915_drv.h"
 #include "i915_reg.h"
@@ -57,7 +58,7 @@ static void i915_restore_display(struct drm_i915_private *dev_priv)
 	if (HAS_FBC(dev_priv) && INTEL_GEN(dev_priv) <= 4 && !IS_G4X(dev_priv))
 		I915_WRITE(FBC_CONTROL, dev_priv->regfile.saveFBC_CONTROL);
 
-	i915_redisable_vga(dev_priv);
+	intel_vga_redisable(dev_priv);
 }
 
 int i915_save_state(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 2fd3c097e1f5..ad719c9602af 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -27,7 +27,6 @@
  */
 
 #include <linux/pm_runtime.h>
-#include <linux/vgaarb.h>
 
 #include <drm/drm_print.h>
 
-- 
cgit v1.2.3


From 33ea5aaa87cdae0f9af4d6b7ee4f650a1a36fd1d Mon Sep 17 00:00:00 2001
From: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
Date: Thu, 26 Sep 2019 14:29:38 +0800
Subject: nfs: Fix nfsi->nrequests count error on nfs_inode_remove_request

When xfstests testing, there are some WARNING as below:

WARNING: CPU: 0 PID: 6235 at fs/nfs/inode.c:122 nfs_clear_inode+0x9c/0xd8
Modules linked in:
CPU: 0 PID: 6235 Comm: umount.nfs
Hardware name: linux,dummy-virt (DT)
pstate: 60000005 (nZCv daif -PAN -UAO)
pc : nfs_clear_inode+0x9c/0xd8
lr : nfs_evict_inode+0x60/0x78
sp : fffffc000f68fc00
x29: fffffc000f68fc00 x28: fffffe00c53155c0
x27: fffffe00c5315000 x26: fffffc0009a63748
x25: fffffc000f68fd18 x24: fffffc000bfaaf40
x23: fffffc000936d3c0 x22: fffffe00c4ff5e20
x21: fffffc000bfaaf40 x20: fffffe00c4ff5d10
x19: fffffc000c056000 x18: 000000000000003c
x17: 0000000000000000 x16: 0000000000000000
x15: 0000000000000040 x14: 0000000000000228
x13: fffffc000c3a2000 x12: 0000000000000045
x11: 0000000000000000 x10: 0000000000000000
x9 : 0000000000000000 x8 : 0000000000000000
x7 : 0000000000000000 x6 : fffffc00084b027c
x5 : fffffc0009a64000 x4 : fffffe00c0e77400
x3 : fffffc000c0563a8 x2 : fffffffffffffffb
x1 : 000000000000764e x0 : 0000000000000001
Call trace:
 nfs_clear_inode+0x9c/0xd8
 nfs_evict_inode+0x60/0x78
 evict+0x108/0x380
 dispose_list+0x70/0xa0
 evict_inodes+0x194/0x210
 generic_shutdown_super+0xb0/0x220
 nfs_kill_super+0x40/0x88
 deactivate_locked_super+0xb4/0x120
 deactivate_super+0x144/0x160
 cleanup_mnt+0x98/0x148
 __cleanup_mnt+0x38/0x50
 task_work_run+0x114/0x160
 do_notify_resume+0x2f8/0x308
 work_pending+0x8/0x14

The nrequest should be increased/decreased only if PG_INODE_REF flag
was setted.

But in the nfs_inode_remove_request function, it maybe decrease when
no PG_INODE_REF flag, this maybe lead nrequests count error.

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/write.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 85ca49549b39..52cab65f91cf 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -786,7 +786,6 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_page *head;
 
-	atomic_long_dec(&nfsi->nrequests);
 	if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) {
 		head = req->wb_head;
 
@@ -799,8 +798,10 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 		spin_unlock(&mapping->private_lock);
 	}
 
-	if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags))
+	if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) {
 		nfs_release_request(req);
+		atomic_long_dec(&nfsi->nrequests);
+	}
 }
 
 static void
-- 
cgit v1.2.3


From 539ad001d1557731cb38d4a9d0e8e16244b2d913 Mon Sep 17 00:00:00 2001
From: "amy.shih" <amy.shih@advantech.com.tw>
Date: Wed, 18 Sep 2019 16:48:00 +0800
Subject: hwmon: (nct7904) Fix the incorrect value of vsen_mask in nct7904_data
 struct

Voltage sensors overlap with external temperature sensors. Detect
the multi-function of voltage, thermal diode and thermistor from
register VT_ADC_MD_REG to set value of vsen_mask in nct7904_data
struct.

Signed-off-by: amy.shih <amy.shih@advantech.com.tw>
Link: https://lore.kernel.org/r/20190918084801.9859-1-Amy.Shih@advantech.com.tw
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/nct7904.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index 95b447cfa24c..f62dd1882451 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -915,12 +915,15 @@ static int nct7904_probe(struct i2c_client *client,
 
 	data->temp_mode = 0;
 	for (i = 0; i < 4; i++) {
-		val = (ret & (0x03 << i)) >> (i * 2);
+		val = (ret >> (i * 2)) & 0x03;
 		bit = (1 << i);
-		if (val == 0)
+		if (val == 0) {
 			data->tcpu_mask &= ~bit;
-		else if (val == 0x1 || val == 0x2)
-			data->temp_mode |= bit;
+		} else {
+			if (val == 0x1 || val == 0x2)
+				data->temp_mode |= bit;
+			data->vsen_mask &= ~(0x06 << (i * 2));
+		}
 	}
 
 	/* PECI */
-- 
cgit v1.2.3


From 43fd0cf4c6dcd5a0e383e60168428bda0bc56374 Mon Sep 17 00:00:00 2001
From: Lukas Zapletal <lzap+git@redhat.com>
Date: Mon, 23 Sep 2019 12:59:31 +0200
Subject: hwmon: (k10temp) Update documentation and add temp2_input info

It's been a while since the k10temp documentation has been updated.
There are new CPU families supported as well as Tdie temp was added.
This patch adds all missing families which I was able to find from git
history and provides more info about Tctl vs Tdie exported temps.

Signed-off-by: Lukas Zapletal <lzap+git@redhat.com>
Link: https://lore.kernel.org/r/20190923105931.27881-1-lzap+git@redhat.com
[groeck: Formatting]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/k10temp.rst | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/Documentation/hwmon/k10temp.rst b/Documentation/hwmon/k10temp.rst
index 12a86ba17de9..4451d59b9425 100644
--- a/Documentation/hwmon/k10temp.rst
+++ b/Documentation/hwmon/k10temp.rst
@@ -21,10 +21,17 @@ Supported chips:
 
 * AMD Family 14h processors: "Brazos" (C/E/G/Z-Series)
 
-* AMD Family 15h processors: "Bulldozer" (FX-Series), "Trinity", "Kaveri", "Carrizo"
+* AMD Family 15h processors: "Bulldozer" (FX-Series), "Trinity", "Kaveri",
+  "Carrizo", "Stoney Ridge", "Bristol Ridge"
 
 * AMD Family 16h processors: "Kabini", "Mullins"
 
+* AMD Family 17h processors: "Zen", "Zen 2"
+
+* AMD Family 18h processors: "Hygon Dhyana"
+
+* AMD Family 19h processors: "Zen 3"
+
   Prefix: 'k10temp'
 
   Addresses scanned: PCI space
@@ -110,3 +117,12 @@ The maximum value for Tctl is available in the file temp1_max.
 If the BIOS has enabled hardware temperature control, the threshold at
 which the processor will throttle itself to avoid damage is available in
 temp1_crit and temp1_crit_hyst.
+
+On some AMD CPUs, there is a difference between the die temperature (Tdie) and
+the reported temperature (Tctl). Tdie is the real measured temperature, and
+Tctl is used for fan control. While Tctl is always available as temp1_input,
+the driver exports Tdie temperature as temp2_input for those CPUs which support
+it.
+
+Models from 17h family report relative temperature, the driver aims to
+compensate and report the real temperature.
-- 
cgit v1.2.3


From 30945d31e5761436d9eba6b8cff468a5f7c9c266 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Tue, 24 Sep 2019 14:49:43 +0200
Subject: hwmon: Fix HWMON_P_MIN_ALARM mask
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Both HWMON_P_MIN_ALARM and HWMON_P_MAX_ALARM were using
BIT(hwmon_power_max_alarm).

Fixes: aa7f29b07c870 ("hwmon: Add support for power min, lcrit, min_alarm and lcrit_alarm")
CC: <stable@vger.kernel.org>
Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20190924124945.491326-2-nuno.sa@analog.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 include/linux/hwmon.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index 04c36b7a61dd..72579168189d 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -235,7 +235,7 @@ enum hwmon_power_attributes {
 #define HWMON_P_LABEL			BIT(hwmon_power_label)
 #define HWMON_P_ALARM			BIT(hwmon_power_alarm)
 #define HWMON_P_CAP_ALARM		BIT(hwmon_power_cap_alarm)
-#define HWMON_P_MIN_ALARM		BIT(hwmon_power_max_alarm)
+#define HWMON_P_MIN_ALARM		BIT(hwmon_power_min_alarm)
 #define HWMON_P_MAX_ALARM		BIT(hwmon_power_max_alarm)
 #define HWMON_P_LCRIT_ALARM		BIT(hwmon_power_lcrit_alarm)
 #define HWMON_P_CRIT_ALARM		BIT(hwmon_power_crit_alarm)
-- 
cgit v1.2.3


From b428db1e880d5f0f1cc22009974bee38a095284e Mon Sep 17 00:00:00 2001
From: Adam Zerella <adam.zerella@gmail.com>
Date: Wed, 25 Sep 2019 23:17:15 +1000
Subject: docs: hwmon: Include 'inspur-ipsps1.rst' into docs

When generating documentation output Sphinx
outputs a warning for not including
the page 'inspur-ipsps1.rst' in 'index.rst'.

Assuming this documentation is useful it
should be included in the index.

Signed-off-by: Adam Zerella <adam.zerella@gmail.com>
Link: https://lore.kernel.org/r/20190925131715.GB19073@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/index.rst | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst
index 8147c3f218bf..230ad59b462b 100644
--- a/Documentation/hwmon/index.rst
+++ b/Documentation/hwmon/index.rst
@@ -7,6 +7,7 @@ Linux Hardware Monitoring
 
    hwmon-kernel-api
    pmbus-core
+   inspur-ipsps1
    submitting-patches
    sysfs-interface
    userspace-tools
-- 
cgit v1.2.3


From 6bbfdcbc8e459acda67e32f520f7ecddc391afe9 Mon Sep 17 00:00:00 2001
From: "amy.shih" <amy.shih@advantech.com.tw>
Date: Thu, 19 Sep 2019 11:02:05 +0800
Subject: hwmon: (nct7904) Add array fan_alarm and vsen_alarm to store the
 alarms in nct7904_data struct.

SMI# interrupt for fan and voltage is Two-Times Interrupt Mode.
Fan or voltage exceeds high limit or going below low limit,
it will causes an interrupt if the previous interrupt has been
reset by reading all the interrupt Status Register. Thus, add the
array fan_alarm and vsen_alarm to store the alarms for all of the
fan and voltage sensors.

Signed-off-by: amy.shih <amy.shih@advantech.com.tw>
Link: https://lore.kernel.org/r/20190919030205.11440-1-Amy.Shih@advantech.com.tw
Fixes: 486842db3b79 ("hwmon: (nct7904) Add extra sysfs support for fan, voltage and temperature.")
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/nct7904.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index f62dd1882451..b26419dbe840 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -99,6 +99,8 @@ struct nct7904_data {
 	u8 enable_dts;
 	u8 has_dts;
 	u8 temp_mode; /* 0: TR mode, 1: TD mode */
+	u8 fan_alarm[2];
+	u8 vsen_alarm[3];
 };
 
 /* Access functions */
@@ -214,7 +216,15 @@ static int nct7904_read_fan(struct device *dev, u32 attr, int channel,
 				       SMI_STS5_REG + (channel >> 3));
 		if (ret < 0)
 			return ret;
-		*val = (ret >> (channel & 0x07)) & 1;
+		if (!data->fan_alarm[channel >> 3])
+			data->fan_alarm[channel >> 3] = ret & 0xff;
+		else
+			/* If there is new alarm showing up */
+			data->fan_alarm[channel >> 3] |= (ret & 0xff);
+		*val = (data->fan_alarm[channel >> 3] >> (channel & 0x07)) & 1;
+		/* Needs to clean the alarm if alarm existing */
+		if (*val)
+			data->fan_alarm[channel >> 3] ^= 1 << (channel & 0x07);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
@@ -298,7 +308,15 @@ static int nct7904_read_in(struct device *dev, u32 attr, int channel,
 				       SMI_STS1_REG + (index >> 3));
 		if (ret < 0)
 			return ret;
-		*val = (ret >> (index & 0x07)) & 1;
+		if (!data->vsen_alarm[index >> 3])
+			data->vsen_alarm[index >> 3] = ret & 0xff;
+		else
+			/* If there is new alarm showing up */
+			data->vsen_alarm[index >> 3] |= (ret & 0xff);
+		*val = (data->vsen_alarm[index >> 3] >> (index & 0x07)) & 1;
+		/* Needs to clean the alarm if alarm existing */
+		if (*val)
+			data->vsen_alarm[index >> 3] ^= 1 << (index & 0x07);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 74f1d78965ee16a2617d245fd1f7e40964c0d562 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 1 Oct 2019 18:46:28 +0300
Subject: drm/i915: Limit MST modes based on plane size too
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When adding the max plane size checks to the .mode_valid() hooks
I naturally forgot about MST. Take care of that one as well.

Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Sean Paul <sean@poorly.run>
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Fixes: 2d20411e25a3 ("drm/i915: Don't advertise modes that exceed the max plane size")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191001154629.11063-1-ville.syrjala@linux.intel.com
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp_mst.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index df4f35c10a69..2203be28ea01 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -424,6 +424,7 @@ static enum drm_mode_status
 intel_dp_mst_mode_valid(struct drm_connector *connector,
 			struct drm_display_mode *mode)
 {
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_connector *intel_connector = to_intel_connector(connector);
 	struct intel_dp *intel_dp = intel_connector->mst_port;
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
@@ -451,7 +452,7 @@ intel_dp_mst_mode_valid(struct drm_connector *connector,
 	if (mode_rate > max_rate || mode->clock > max_dotclk)
 		return MODE_CLOCK_HIGH;
 
-	return MODE_OK;
+	return intel_mode_valid_max_plane_size(dev_priv, mode);
 }
 
 static struct drm_encoder *intel_mst_atomic_best_encoder(struct drm_connector *connector,
-- 
cgit v1.2.3


From 15de0889b0c905a64d6f0fbc765a25d7899a560b Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 1 Oct 2019 18:46:29 +0300
Subject: drm/i915: Polish intel_tv_mode_valid()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drop the tv_mode NULL check since intel_tv_mode_find() never
actually returns NULL, and flip the condition around so that
the MODE_OK case is at the end, which is customary to all
the other .mode_valid() implementations.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191001154629.11063-2-ville.syrjala@linux.intel.com
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
---
 drivers/gpu/drm/i915/display/intel_tv.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index b70221f5112a..71c3f7e5df7d 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -961,11 +961,10 @@ intel_tv_mode_valid(struct drm_connector *connector,
 		return MODE_CLOCK_HIGH;
 
 	/* Ensure TV refresh is close to desired refresh */
-	if (tv_mode && abs(tv_mode->refresh - drm_mode_vrefresh(mode) * 1000)
-				< 1000)
-		return MODE_OK;
+	if (abs(tv_mode->refresh - drm_mode_vrefresh(mode) * 1000) >= 1000)
+		return MODE_CLOCK_RANGE;
 
-	return MODE_CLOCK_RANGE;
+	return MODE_OK;
 }
 
 static int
-- 
cgit v1.2.3


From 006e570128f413759b9df64b51bae79903679c9b Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 30 Sep 2019 21:30:45 +0300
Subject: drm/i915: Fix g4x sprite scaling stride check with GTT remapping
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I forgot to update the g4x sprite scaling stride check when GTT
remapping was introduced. The stride of the original framebuffer
is irrelevant when remapping is used and instead we want to check
the stride of the remapped view.

Also drop the duplicate width_bytes check. We already check that
a few lines earlier.

Fixes: df79cf441910 ("drm/i915: Store the final plane stride in plane_state")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190930183045.662-1-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/display/intel_sprite.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index 3d56db32291b..633fa8069348 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -1516,6 +1516,7 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state,
 	int src_x, src_w, src_h, crtc_w, crtc_h;
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->base.adjusted_mode;
+	unsigned int stride = plane_state->color_plane[0].stride;
 	unsigned int cpp = fb->format->cpp[0];
 	unsigned int width_bytes;
 	int min_width, min_height;
@@ -1557,9 +1558,9 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state,
 		return -EINVAL;
 	}
 
-	if (width_bytes > 4096 || fb->pitches[0] > 4096) {
+	if (stride > 4096) {
 		DRM_DEBUG_KMS("Stride (%u) exceeds hardware max with scaling (%u)\n",
-			      fb->pitches[0], 4096);
+			      stride, 4096);
 		return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From dfe324f34c53af095bfe54b322e1a338421a6b0e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 2 Oct 2019 13:24:30 +0100
Subject: drm/i915/selftests: Extract random_offset() for use with a prng

For selftests, we desire repeatability and so prefer using a prng with
known seed over true randomness. Extract random_offset() as a selftest
utility that can take the prng state.

Suggested-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191002122430.23205-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 14 +++++++++-----
 drivers/gpu/drm/i915/selftests/i915_random.c  | 20 ++++++++++++++++++++
 drivers/gpu/drm/i915/selftests/i915_random.h  |  4 ++++
 3 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 0d40e0b42923..f901bbb9586e 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1299,6 +1299,7 @@ static int igt_gtt_reserve(void *arg)
 {
 	struct i915_ggtt *ggtt = arg;
 	struct drm_i915_gem_object *obj, *on;
+	I915_RND_STATE(prng);
 	LIST_HEAD(objects);
 	u64 total;
 	int err = -ENODEV;
@@ -1425,9 +1426,10 @@ static int igt_gtt_reserve(void *arg)
 			goto out;
 		}
 
-		offset = random_offset(0, ggtt->vm.total,
-				       2*I915_GTT_PAGE_SIZE,
-				       I915_GTT_MIN_ALIGNMENT);
+		offset = igt_random_offset(&prng,
+					   0, ggtt->vm.total,
+					   2 * I915_GTT_PAGE_SIZE,
+					   I915_GTT_MIN_ALIGNMENT);
 
 		err = i915_gem_gtt_reserve(&ggtt->vm, &vma->node,
 					   obj->base.size,
@@ -1772,6 +1774,7 @@ static int igt_cs_tlb(void *arg)
 	struct intel_context *ce;
 	struct drm_file *file;
 	struct i915_vma *vma;
+	I915_RND_STATE(prng);
 	unsigned int i;
 	u32 *result;
 	u32 *batch;
@@ -1885,8 +1888,9 @@ static int igt_cs_tlb(void *arg)
 			struct i915_request *rq;
 			u64 offset;
 
-			offset = random_offset(0, vm->total - PAGE_SIZE,
-					       chunk_size, PAGE_SIZE);
+			offset = igt_random_offset(&prng,
+						   0, vm->total - PAGE_SIZE,
+						   chunk_size, PAGE_SIZE);
 
 			err = vm->allocate_va_range(vm, offset, chunk_size);
 			if (err)
diff --git a/drivers/gpu/drm/i915/selftests/i915_random.c b/drivers/gpu/drm/i915/selftests/i915_random.c
index 716a3f19f030..abdfadcf626b 100644
--- a/drivers/gpu/drm/i915/selftests/i915_random.c
+++ b/drivers/gpu/drm/i915/selftests/i915_random.c
@@ -29,6 +29,7 @@
 #include <linux/types.h>
 
 #include "i915_random.h"
+#include "i915_utils.h"
 
 u64 i915_prandom_u64_state(struct rnd_state *rnd)
 {
@@ -87,3 +88,22 @@ unsigned int *i915_random_order(unsigned int count, struct rnd_state *state)
 	i915_random_reorder(order, count, state);
 	return order;
 }
+
+u64 igt_random_offset(struct rnd_state *state,
+		      u64 start, u64 end,
+		      u64 len, u64 align)
+{
+	u64 range, addr;
+
+	BUG_ON(range_overflows(start, len, end));
+	BUG_ON(round_up(start, align) > round_down(end - len, align));
+
+	range = round_down(end - len, align) - round_up(start, align);
+	if (range) {
+		addr = i915_prandom_u64_state(state);
+		div64_u64_rem(addr, range, &addr);
+		start += addr;
+	}
+
+	return round_up(start, align);
+}
diff --git a/drivers/gpu/drm/i915/selftests/i915_random.h b/drivers/gpu/drm/i915/selftests/i915_random.h
index 8e1ff9c105b6..35cc69a3a1b9 100644
--- a/drivers/gpu/drm/i915/selftests/i915_random.h
+++ b/drivers/gpu/drm/i915/selftests/i915_random.h
@@ -57,4 +57,8 @@ void i915_random_reorder(unsigned int *order,
 void i915_prandom_shuffle(void *arr, size_t elsz, size_t count,
 			  struct rnd_state *state);
 
+u64 igt_random_offset(struct rnd_state *state,
+		      u64 start, u64 end,
+		      u64 len, u64 align);
+
 #endif /* !__I915_SELFTESTS_RANDOM_H__ */
-- 
cgit v1.2.3


From 3cbad5d7774953d36c09cca295e6b84e61b03ae7 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 2 Oct 2019 13:30:14 +0100
Subject: drm/i915/gem: Refactor tests on obj->ops->flags

We repeat obj->ops->flags in our object checks, so pull that into its
own little helper for clarity.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191002123014.1545-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_object.h | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index aec05f967d9d..53c7069ba3e8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -134,34 +134,41 @@ i915_gem_object_is_readonly(const struct drm_i915_gem_object *obj)
 	return obj->base.vma_node.readonly;
 }
 
+static inline bool
+i915_gem_object_type_has(const struct drm_i915_gem_object *obj,
+			 unsigned long flags)
+{
+	return obj->ops->flags & flags;
+}
+
 static inline bool
 i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj)
 {
-	return obj->ops->flags & I915_GEM_OBJECT_HAS_STRUCT_PAGE;
+	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_HAS_STRUCT_PAGE);
 }
 
 static inline bool
 i915_gem_object_is_shrinkable(const struct drm_i915_gem_object *obj)
 {
-	return obj->ops->flags & I915_GEM_OBJECT_IS_SHRINKABLE;
+	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_SHRINKABLE);
 }
 
 static inline bool
 i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj)
 {
-	return obj->ops->flags & I915_GEM_OBJECT_IS_PROXY;
+	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_IS_PROXY);
 }
 
 static inline bool
 i915_gem_object_never_bind_ggtt(const struct drm_i915_gem_object *obj)
 {
-	return obj->ops->flags & I915_GEM_OBJECT_NO_GGTT;
+	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_NO_GGTT);
 }
 
 static inline bool
 i915_gem_object_needs_async_cancel(const struct drm_i915_gem_object *obj)
 {
-	return obj->ops->flags & I915_GEM_OBJECT_ASYNC_CANCEL;
+	return i915_gem_object_type_has(obj, I915_GEM_OBJECT_ASYNC_CANCEL);
 }
 
 static inline bool
-- 
cgit v1.2.3


From 09515706857a7d5a2ffb5ce6a44c0bc7859a745b Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Tue, 1 Oct 2019 10:25:34 +0200
Subject: xen/efi: have a common runtime setup function

Today the EFI runtime functions are setup in architecture specific
code (x86 and arm), with the functions themselves living in drivers/xen
as they are not architecture dependent.

As the setup is exactly the same for arm and x86 move the setup to
drivers/xen, too. This at once removes the need to make the single
functions global visible.

Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
[boris: "Dropped EXPORT_SYMBOL_GPL(xen_efi_runtime_setup)"]
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/arm/include/asm/xen/xen-ops.h   |  6 ---
 arch/arm/xen/Makefile                |  1 -
 arch/arm/xen/efi.c                   | 30 -------------
 arch/arm/xen/enlighten.c             |  1 -
 arch/arm64/include/asm/xen/xen-ops.h |  7 ---
 arch/arm64/xen/Makefile              |  1 -
 arch/x86/xen/efi.c                   | 16 +------
 drivers/xen/efi.c                    | 84 ++++++++++++++++++++----------------
 include/xen/xen-ops.h                | 25 +----------
 9 files changed, 49 insertions(+), 122 deletions(-)
 delete mode 100644 arch/arm/include/asm/xen/xen-ops.h
 delete mode 100644 arch/arm/xen/efi.c
 delete mode 100644 arch/arm64/include/asm/xen/xen-ops.h

diff --git a/arch/arm/include/asm/xen/xen-ops.h b/arch/arm/include/asm/xen/xen-ops.h
deleted file mode 100644
index ec154e719b11..000000000000
--- a/arch/arm/include/asm/xen/xen-ops.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_XEN_OPS_H
-#define _ASM_XEN_OPS_H
-
-void xen_efi_runtime_setup(void);
-
-#endif /* _ASM_XEN_OPS_H */
diff --git a/arch/arm/xen/Makefile b/arch/arm/xen/Makefile
index 7ed28982c4c3..c32d04713ba0 100644
--- a/arch/arm/xen/Makefile
+++ b/arch/arm/xen/Makefile
@@ -1,3 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y		:= enlighten.o hypercall.o grant-table.o p2m.o mm.o
-obj-$(CONFIG_XEN_EFI) += efi.o
diff --git a/arch/arm/xen/efi.c b/arch/arm/xen/efi.c
deleted file mode 100644
index cb2aaf98e243..000000000000
--- a/arch/arm/xen/efi.c
+++ /dev/null
@@ -1,30 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (c) 2015, Linaro Limited, Shannon Zhao
- */
-
-#include <linux/efi.h>
-#include <xen/xen-ops.h>
-#include <asm/xen/xen-ops.h>
-
-/* Set XEN EFI runtime services function pointers. Other fields of struct efi,
- * e.g. efi.systab, will be set like normal EFI.
- */
-void __init xen_efi_runtime_setup(void)
-{
-	efi.get_time                 = xen_efi_get_time;
-	efi.set_time                 = xen_efi_set_time;
-	efi.get_wakeup_time          = xen_efi_get_wakeup_time;
-	efi.set_wakeup_time          = xen_efi_set_wakeup_time;
-	efi.get_variable             = xen_efi_get_variable;
-	efi.get_next_variable        = xen_efi_get_next_variable;
-	efi.set_variable             = xen_efi_set_variable;
-	efi.set_variable_nonblocking = xen_efi_set_variable;
-	efi.query_variable_info      = xen_efi_query_variable_info;
-	efi.query_variable_info_nonblocking = xen_efi_query_variable_info;
-	efi.update_capsule           = xen_efi_update_capsule;
-	efi.query_capsule_caps       = xen_efi_query_capsule_caps;
-	efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
-	efi.reset_system             = xen_efi_reset_system;
-}
-EXPORT_SYMBOL_GPL(xen_efi_runtime_setup);
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 522c97d43ef8..dd6804a64f1a 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -15,7 +15,6 @@
 #include <xen/xen-ops.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
-#include <asm/xen/xen-ops.h>
 #include <asm/system_misc.h>
 #include <asm/efi.h>
 #include <linux/interrupt.h>
diff --git a/arch/arm64/include/asm/xen/xen-ops.h b/arch/arm64/include/asm/xen/xen-ops.h
deleted file mode 100644
index e6e784051932..000000000000
--- a/arch/arm64/include/asm/xen/xen-ops.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_XEN_OPS_H
-#define _ASM_XEN_OPS_H
-
-void xen_efi_runtime_setup(void);
-
-#endif /* _ASM_XEN_OPS_H */
diff --git a/arch/arm64/xen/Makefile b/arch/arm64/xen/Makefile
index a4fc65f3928d..b66215e8658e 100644
--- a/arch/arm64/xen/Makefile
+++ b/arch/arm64/xen/Makefile
@@ -1,4 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 xen-arm-y	+= $(addprefix ../../arm/xen/, enlighten.o grant-table.o p2m.o mm.o)
 obj-y		:= xen-arm.o hypercall.o
-obj-$(CONFIG_XEN_EFI) += $(addprefix ../../arm/xen/, efi.o)
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index 7e3eb70f411a..a04551ee5568 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -57,21 +57,7 @@ static efi_system_table_t __init *xen_efi_probe(void)
 		return NULL;
 
 	/* Here we know that Xen runs on EFI platform. */
-
-	efi.get_time                 = xen_efi_get_time;
-	efi.set_time                 = xen_efi_set_time;
-	efi.get_wakeup_time          = xen_efi_get_wakeup_time;
-	efi.set_wakeup_time          = xen_efi_set_wakeup_time;
-	efi.get_variable             = xen_efi_get_variable;
-	efi.get_next_variable        = xen_efi_get_next_variable;
-	efi.set_variable             = xen_efi_set_variable;
-	efi.set_variable_nonblocking = xen_efi_set_variable;
-	efi.query_variable_info      = xen_efi_query_variable_info;
-	efi.query_variable_info_nonblocking = xen_efi_query_variable_info;
-	efi.update_capsule           = xen_efi_update_capsule;
-	efi.query_capsule_caps       = xen_efi_query_capsule_caps;
-	efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
-	efi.reset_system             = xen_efi_reset_system;
+	xen_efi_runtime_setup();
 
 	efi_systab_xen.tables = info->cfg.addr;
 	efi_systab_xen.nr_tables = info->cfg.nent;
diff --git a/drivers/xen/efi.c b/drivers/xen/efi.c
index 89d60f8e3c18..d1ff2186ebb4 100644
--- a/drivers/xen/efi.c
+++ b/drivers/xen/efi.c
@@ -40,7 +40,7 @@
 
 #define efi_data(op)	(op.u.efi_runtime_call)
 
-efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
+static efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	struct xen_platform_op op = INIT_EFI_OP(get_time);
 
@@ -61,9 +61,8 @@ efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 
 	return efi_data(op).status;
 }
-EXPORT_SYMBOL_GPL(xen_efi_get_time);
 
-efi_status_t xen_efi_set_time(efi_time_t *tm)
+static efi_status_t xen_efi_set_time(efi_time_t *tm)
 {
 	struct xen_platform_op op = INIT_EFI_OP(set_time);
 
@@ -75,10 +74,10 @@ efi_status_t xen_efi_set_time(efi_time_t *tm)
 
 	return efi_data(op).status;
 }
-EXPORT_SYMBOL_GPL(xen_efi_set_time);
 
-efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
-				     efi_time_t *tm)
+static efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled,
+					    efi_bool_t *pending,
+					    efi_time_t *tm)
 {
 	struct xen_platform_op op = INIT_EFI_OP(get_wakeup_time);
 
@@ -98,9 +97,8 @@ efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
 
 	return efi_data(op).status;
 }
-EXPORT_SYMBOL_GPL(xen_efi_get_wakeup_time);
 
-efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
+static efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 {
 	struct xen_platform_op op = INIT_EFI_OP(set_wakeup_time);
 
@@ -117,11 +115,10 @@ efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 
 	return efi_data(op).status;
 }
-EXPORT_SYMBOL_GPL(xen_efi_set_wakeup_time);
 
-efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor,
-				  u32 *attr, unsigned long *data_size,
-				  void *data)
+static efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor,
+					 u32 *attr, unsigned long *data_size,
+					 void *data)
 {
 	struct xen_platform_op op = INIT_EFI_OP(get_variable);
 
@@ -141,11 +138,10 @@ efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor,
 
 	return efi_data(op).status;
 }
-EXPORT_SYMBOL_GPL(xen_efi_get_variable);
 
-efi_status_t xen_efi_get_next_variable(unsigned long *name_size,
-				       efi_char16_t *name,
-				       efi_guid_t *vendor)
+static efi_status_t xen_efi_get_next_variable(unsigned long *name_size,
+					      efi_char16_t *name,
+					      efi_guid_t *vendor)
 {
 	struct xen_platform_op op = INIT_EFI_OP(get_next_variable_name);
 
@@ -165,11 +161,10 @@ efi_status_t xen_efi_get_next_variable(unsigned long *name_size,
 
 	return efi_data(op).status;
 }
-EXPORT_SYMBOL_GPL(xen_efi_get_next_variable);
 
-efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor,
-				 u32 attr, unsigned long data_size,
-				 void *data)
+static efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor,
+					 u32 attr, unsigned long data_size,
+					 void *data)
 {
 	struct xen_platform_op op = INIT_EFI_OP(set_variable);
 
@@ -186,11 +181,10 @@ efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 
 	return efi_data(op).status;
 }
-EXPORT_SYMBOL_GPL(xen_efi_set_variable);
 
-efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space,
-					 u64 *remaining_space,
-					 u64 *max_variable_size)
+static efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space,
+						u64 *remaining_space,
+						u64 *max_variable_size)
 {
 	struct xen_platform_op op = INIT_EFI_OP(query_variable_info);
 
@@ -208,9 +202,8 @@ efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space,
 
 	return efi_data(op).status;
 }
-EXPORT_SYMBOL_GPL(xen_efi_query_variable_info);
 
-efi_status_t xen_efi_get_next_high_mono_count(u32 *count)
+static efi_status_t xen_efi_get_next_high_mono_count(u32 *count)
 {
 	struct xen_platform_op op = INIT_EFI_OP(get_next_high_monotonic_count);
 
@@ -221,10 +214,9 @@ efi_status_t xen_efi_get_next_high_mono_count(u32 *count)
 
 	return efi_data(op).status;
 }
-EXPORT_SYMBOL_GPL(xen_efi_get_next_high_mono_count);
 
-efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules,
-				    unsigned long count, unsigned long sg_list)
+static efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules,
+				unsigned long count, unsigned long sg_list)
 {
 	struct xen_platform_op op = INIT_EFI_OP(update_capsule);
 
@@ -241,11 +233,9 @@ efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules,
 
 	return efi_data(op).status;
 }
-EXPORT_SYMBOL_GPL(xen_efi_update_capsule);
 
-efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
-					unsigned long count, u64 *max_size,
-					int *reset_type)
+static efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
+			unsigned long count, u64 *max_size, int *reset_type)
 {
 	struct xen_platform_op op = INIT_EFI_OP(query_capsule_capabilities);
 
@@ -264,10 +254,9 @@ efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
 
 	return efi_data(op).status;
 }
-EXPORT_SYMBOL_GPL(xen_efi_query_capsule_caps);
 
-void xen_efi_reset_system(int reset_type, efi_status_t status,
-			  unsigned long data_size, efi_char16_t *data)
+static void xen_efi_reset_system(int reset_type, efi_status_t status,
+				 unsigned long data_size, efi_char16_t *data)
 {
 	switch (reset_type) {
 	case EFI_RESET_COLD:
@@ -281,4 +270,25 @@ void xen_efi_reset_system(int reset_type, efi_status_t status,
 		BUG();
 	}
 }
-EXPORT_SYMBOL_GPL(xen_efi_reset_system);
+
+/*
+ * Set XEN EFI runtime services function pointers. Other fields of struct efi,
+ * e.g. efi.systab, will be set like normal EFI.
+ */
+void __init xen_efi_runtime_setup(void)
+{
+	efi.get_time			= xen_efi_get_time;
+	efi.set_time			= xen_efi_set_time;
+	efi.get_wakeup_time		= xen_efi_get_wakeup_time;
+	efi.set_wakeup_time		= xen_efi_set_wakeup_time;
+	efi.get_variable		= xen_efi_get_variable;
+	efi.get_next_variable		= xen_efi_get_next_variable;
+	efi.set_variable		= xen_efi_set_variable;
+	efi.set_variable_nonblocking	= xen_efi_set_variable;
+	efi.query_variable_info		= xen_efi_query_variable_info;
+	efi.query_variable_info_nonblocking = xen_efi_query_variable_info;
+	efi.update_capsule		= xen_efi_update_capsule;
+	efi.query_capsule_caps		= xen_efi_query_capsule_caps;
+	efi.get_next_high_mono_count	= xen_efi_get_next_high_mono_count;
+	efi.reset_system		= xen_efi_reset_system;
+}
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 98b30c1613b2..d89969aa9942 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -212,30 +212,7 @@ int xen_xlate_map_ballooned_pages(xen_pfn_t **pfns, void **vaddr,
 
 bool xen_running_on_version_or_later(unsigned int major, unsigned int minor);
 
-efi_status_t xen_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc);
-efi_status_t xen_efi_set_time(efi_time_t *tm);
-efi_status_t xen_efi_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
-				     efi_time_t *tm);
-efi_status_t xen_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm);
-efi_status_t xen_efi_get_variable(efi_char16_t *name, efi_guid_t *vendor,
-				  u32 *attr, unsigned long *data_size,
-				  void *data);
-efi_status_t xen_efi_get_next_variable(unsigned long *name_size,
-				       efi_char16_t *name, efi_guid_t *vendor);
-efi_status_t xen_efi_set_variable(efi_char16_t *name, efi_guid_t *vendor,
-				  u32 attr, unsigned long data_size,
-				  void *data);
-efi_status_t xen_efi_query_variable_info(u32 attr, u64 *storage_space,
-					 u64 *remaining_space,
-					 u64 *max_variable_size);
-efi_status_t xen_efi_get_next_high_mono_count(u32 *count);
-efi_status_t xen_efi_update_capsule(efi_capsule_header_t **capsules,
-				    unsigned long count, unsigned long sg_list);
-efi_status_t xen_efi_query_capsule_caps(efi_capsule_header_t **capsules,
-					unsigned long count, u64 *max_size,
-					int *reset_type);
-void xen_efi_reset_system(int reset_type, efi_status_t status,
-			  unsigned long data_size, efi_char16_t *data);
+void xen_efi_runtime_setup(void);
 
 
 #ifdef CONFIG_PREEMPT
-- 
cgit v1.2.3


From e95584a889e1902fdf1ded9712e2c3c3083baf96 Mon Sep 17 00:00:00 2001
From: Tuong Lien <tuong.t.lien@dektech.com.au>
Date: Wed, 2 Oct 2019 18:49:43 +0700
Subject: tipc: fix unlimited bundling of small messages

We have identified a problem with the "oversubscription" policy in the
link transmission code.

When small messages are transmitted, and the sending link has reached
the transmit window limit, those messages will be bundled and put into
the link backlog queue. However, bundles of data messages are counted
at the 'CRITICAL' level, so that the counter for that level, instead of
the counter for the real, bundled message's level is the one being
increased.
Subsequent, to-be-bundled data messages at non-CRITICAL levels continue
to be tested against the unchanged counter for their own level, while
contributing to an unrestrained increase at the CRITICAL backlog level.

This leaves a gap in congestion control algorithm for small messages
that can result in starvation for other users or a "real" CRITICAL
user. Even that eventually can lead to buffer exhaustion & link reset.

We fix this by keeping a 'target_bskb' buffer pointer at each levels,
then when bundling, we only bundle messages at the same importance
level only. This way, we know exactly how many slots a certain level
have occupied in the queue, so can manage level congestion accurately.

By bundling messages at the same level, we even have more benefits. Let
consider this:
- One socket sends 64-byte messages at the 'CRITICAL' level;
- Another sends 4096-byte messages at the 'LOW' level;

When a 64-byte message comes and is bundled the first time, we put the
overhead of message bundle to it (+ 40-byte header, data copy, etc.)
for later use, but the next message can be a 4096-byte one that cannot
be bundled to the previous one. This means the last bundle carries only
one payload message which is totally inefficient, as for the receiver
also! Later on, another 64-byte message comes, now we make a new bundle
and the same story repeats...

With the new bundling algorithm, this will not happen, the 64-byte
messages will be bundled together even when the 4096-byte message(s)
comes in between. However, if the 4096-byte messages are sent at the
same level i.e. 'CRITICAL', the bundling algorithm will again cause the
same overhead.

Also, the same will happen even with only one socket sending small
messages at a rate close to the link transmit's one, so that, when one
message is bundled, it's transmitted shortly. Then, another message
comes, a new bundle is created and so on...

We will solve this issue radically by another patch.

Fixes: 365ad353c256 ("tipc: reduce risk of user starvation during link congestion")
Reported-by: Hoang Le <hoang.h.le@dektech.com.au>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: Tuong Lien <tuong.t.lien@dektech.com.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/link.c | 29 ++++++++++++++++++-----------
 net/tipc/msg.c  |  5 +----
 2 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 6cc75ffd9e2c..999eab592de8 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -160,6 +160,7 @@ struct tipc_link {
 	struct {
 		u16 len;
 		u16 limit;
+		struct sk_buff *target_bskb;
 	} backlog[5];
 	u16 snd_nxt;
 	u16 window;
@@ -880,6 +881,7 @@ static void link_prepare_wakeup(struct tipc_link *l)
 void tipc_link_reset(struct tipc_link *l)
 {
 	struct sk_buff_head list;
+	u32 imp;
 
 	__skb_queue_head_init(&list);
 
@@ -901,11 +903,10 @@ void tipc_link_reset(struct tipc_link *l)
 	__skb_queue_purge(&l->deferdq);
 	__skb_queue_purge(&l->backlogq);
 	__skb_queue_purge(&l->failover_deferdq);
-	l->backlog[TIPC_LOW_IMPORTANCE].len = 0;
-	l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0;
-	l->backlog[TIPC_HIGH_IMPORTANCE].len = 0;
-	l->backlog[TIPC_CRITICAL_IMPORTANCE].len = 0;
-	l->backlog[TIPC_SYSTEM_IMPORTANCE].len = 0;
+	for (imp = 0; imp <= TIPC_SYSTEM_IMPORTANCE; imp++) {
+		l->backlog[imp].len = 0;
+		l->backlog[imp].target_bskb = NULL;
+	}
 	kfree_skb(l->reasm_buf);
 	kfree_skb(l->reasm_tnlmsg);
 	kfree_skb(l->failover_reasm_skb);
@@ -947,7 +948,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
 	struct sk_buff_head *transmq = &l->transmq;
 	struct sk_buff_head *backlogq = &l->backlogq;
-	struct sk_buff *skb, *_skb, *bskb;
+	struct sk_buff *skb, *_skb, **tskb;
 	int pkt_cnt = skb_queue_len(list);
 	int rc = 0;
 
@@ -999,19 +1000,21 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 			seqno++;
 			continue;
 		}
-		if (tipc_msg_bundle(skb_peek_tail(backlogq), hdr, mtu)) {
+		tskb = &l->backlog[imp].target_bskb;
+		if (tipc_msg_bundle(*tskb, hdr, mtu)) {
 			kfree_skb(__skb_dequeue(list));
 			l->stats.sent_bundled++;
 			continue;
 		}
-		if (tipc_msg_make_bundle(&bskb, hdr, mtu, l->addr)) {
+		if (tipc_msg_make_bundle(tskb, hdr, mtu, l->addr)) {
 			kfree_skb(__skb_dequeue(list));
-			__skb_queue_tail(backlogq, bskb);
-			l->backlog[msg_importance(buf_msg(bskb))].len++;
+			__skb_queue_tail(backlogq, *tskb);
+			l->backlog[imp].len++;
 			l->stats.sent_bundled++;
 			l->stats.sent_bundles++;
 			continue;
 		}
+		l->backlog[imp].target_bskb = NULL;
 		l->backlog[imp].len += skb_queue_len(list);
 		skb_queue_splice_tail_init(list, backlogq);
 	}
@@ -1027,6 +1030,7 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
 	u16 seqno = l->snd_nxt;
 	u16 ack = l->rcv_nxt - 1;
 	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
+	u32 imp;
 
 	while (skb_queue_len(&l->transmq) < l->window) {
 		skb = skb_peek(&l->backlogq);
@@ -1037,7 +1041,10 @@ static void tipc_link_advance_backlog(struct tipc_link *l,
 			break;
 		__skb_dequeue(&l->backlogq);
 		hdr = buf_msg(skb);
-		l->backlog[msg_importance(hdr)].len--;
+		imp = msg_importance(hdr);
+		l->backlog[imp].len--;
+		if (unlikely(skb == l->backlog[imp].target_bskb))
+			l->backlog[imp].target_bskb = NULL;
 		__skb_queue_tail(&l->transmq, skb);
 		/* next retransmit attempt */
 		if (link_is_bc_sndlink(l))
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index e6d49cdc61b4..922d262e153f 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -543,10 +543,7 @@ bool tipc_msg_make_bundle(struct sk_buff **skb,  struct tipc_msg *msg,
 	bmsg = buf_msg(_skb);
 	tipc_msg_init(msg_prevnode(msg), bmsg, MSG_BUNDLER, 0,
 		      INT_H_SIZE, dnode);
-	if (msg_isdata(msg))
-		msg_set_importance(bmsg, TIPC_CRITICAL_IMPORTANCE);
-	else
-		msg_set_importance(bmsg, TIPC_SYSTEM_IMPORTANCE);
+	msg_set_importance(bmsg, msg_importance(msg));
 	msg_set_seqno(bmsg, msg_seqno(msg));
 	msg_set_ack(bmsg, msg_ack(msg));
 	msg_set_bcast_ack(bmsg, msg_bcast_ack(msg));
-- 
cgit v1.2.3


From 8b6b82ad163b54a23f0e89710fb25461d45109c4 Mon Sep 17 00:00:00 2001
From: Michal Kubecek <mkubecek@suse.cz>
Date: Wed, 2 Oct 2019 14:12:41 +0200
Subject: mlx5: avoid 64-bit division in dr_icm_pool_mr_create()

Recently added code introduces 64-bit division in dr_icm_pool_mr_create()
so that build on 32-bit architectures fails with

  ERROR: "__umoddi3" [drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.ko] undefined!

As the divisor is always a power of 2, we can use bitwise operation
instead.

Fixes: 29cf8febd185 ("net/mlx5: DR, ICM pool memory allocator")
Reported-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
index 913f1e5aaaf2..d7c7467e2d53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c
@@ -137,7 +137,8 @@ dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool,
 
 	icm_mr->icm_start_addr = icm_mr->dm.addr;
 
-	align_diff = icm_mr->icm_start_addr % align_base;
+	/* align_base is always a power of 2 */
+	align_diff = icm_mr->icm_start_addr & (align_base - 1);
 	if (align_diff)
 		icm_mr->used_length = align_base - align_diff;
 
-- 
cgit v1.2.3


From ed500bf61279c26bcaa5a9979543bc45883efddf Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 8 Jul 2019 19:20:42 +0300
Subject: drm/i915: Populate possible_crtcs correctly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Don't advertize non-exisiting crtcs in the encoder possible_crtcs
bitmask.

Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190708162048.4286-9-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index d99c59e97568..20ec8a1dc5e1 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -15257,6 +15257,20 @@ static int intel_encoder_clones(struct intel_encoder *encoder)
 	return index_mask;
 }
 
+static u32 intel_encoder_possible_crtcs(struct intel_encoder *encoder)
+{
+	struct drm_device *dev = encoder->base.dev;
+	struct intel_crtc *crtc;
+	u32 possible_crtcs = 0;
+
+	for_each_intel_crtc(dev, crtc) {
+		if (encoder->crtc_mask & BIT(crtc->pipe))
+			possible_crtcs |= drm_crtc_mask(&crtc->base);
+	}
+
+	return possible_crtcs;
+}
+
 static bool ilk_has_edp_a(struct drm_i915_private *dev_priv)
 {
 	if (!IS_MOBILE(dev_priv))
@@ -15557,7 +15571,8 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 	intel_psr_init(dev_priv);
 
 	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		encoder->base.possible_crtcs = encoder->crtc_mask;
+		encoder->base.possible_crtcs =
+			intel_encoder_possible_crtcs(encoder);
 		encoder->base.possible_clones =
 			intel_encoder_clones(encoder);
 	}
-- 
cgit v1.2.3


From 0fbae9d2db851e18ec413da2eba9d875269660e0 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 8 Jul 2019 19:20:44 +0300
Subject: drm/i915: Clean up encoder->crtc_mask setup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use BIT(pipe) for better legibility when populating the crtc_mask
for encoders.

Also remove the redundant possible_crtcs setup for the TV encoder.

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190708162048.4286-11-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_crt.c  | 4 ++--
 drivers/gpu/drm/i915/display/intel_dp.c   | 6 +++---
 drivers/gpu/drm/i915/display/intel_dvo.c  | 2 +-
 drivers/gpu/drm/i915/display/intel_hdmi.c | 6 +++---
 drivers/gpu/drm/i915/display/intel_lvds.c | 6 +++---
 drivers/gpu/drm/i915/display/intel_sdvo.c | 2 +-
 drivers/gpu/drm/i915/display/intel_tv.c   | 3 +--
 7 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c
index e6e8d4a82044..ff6126ea793c 100644
--- a/drivers/gpu/drm/i915/display/intel_crt.c
+++ b/drivers/gpu/drm/i915/display/intel_crt.c
@@ -994,9 +994,9 @@ void intel_crt_init(struct drm_i915_private *dev_priv)
 	crt->base.type = INTEL_OUTPUT_ANALOG;
 	crt->base.cloneable = (1 << INTEL_OUTPUT_DVO) | (1 << INTEL_OUTPUT_HDMI);
 	if (IS_I830(dev_priv))
-		crt->base.crtc_mask = (1 << 0);
+		crt->base.crtc_mask = BIT(PIPE_A);
 	else
-		crt->base.crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
+		crt->base.crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
 
 	if (IS_GEN(dev_priv, 2))
 		connector->interlace_allowed = 0;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 14a5c661f710..b788e332e76a 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -7366,11 +7366,11 @@ bool intel_dp_init(struct drm_i915_private *dev_priv,
 	intel_encoder->power_domain = intel_port_to_power_domain(port);
 	if (IS_CHERRYVIEW(dev_priv)) {
 		if (port == PORT_D)
-			intel_encoder->crtc_mask = 1 << 2;
+			intel_encoder->crtc_mask = BIT(PIPE_C);
 		else
-			intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
+			intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B);
 	} else {
-		intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
+		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
 	}
 	intel_encoder->cloneable = 0;
 	intel_encoder->port = port;
diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c
index 34193d04597a..9827f99491d1 100644
--- a/drivers/gpu/drm/i915/display/intel_dvo.c
+++ b/drivers/gpu/drm/i915/display/intel_dvo.c
@@ -505,7 +505,7 @@ void intel_dvo_init(struct drm_i915_private *dev_priv)
 		intel_encoder->type = INTEL_OUTPUT_DVO;
 		intel_encoder->power_domain = POWER_DOMAIN_PORT_OTHER;
 		intel_encoder->port = port;
-		intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
+		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B);
 
 		switch (dvo->type) {
 		case INTEL_DVO_CHIP_TMDS:
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 5ab73331d35d..03b140980fc4 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -3269,11 +3269,11 @@ void intel_hdmi_init(struct drm_i915_private *dev_priv,
 	intel_encoder->port = port;
 	if (IS_CHERRYVIEW(dev_priv)) {
 		if (port == PORT_D)
-			intel_encoder->crtc_mask = 1 << 2;
+			intel_encoder->crtc_mask = BIT(PIPE_C);
 		else
-			intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
+			intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B);
 	} else {
-		intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
+		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
 	}
 	intel_encoder->cloneable = 1 << INTEL_OUTPUT_ANALOG;
 	/*
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index c786abdc3336..13841d7c455b 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -900,11 +900,11 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 	intel_encoder->port = PORT_NONE;
 	intel_encoder->cloneable = 0;
 	if (HAS_PCH_SPLIT(dev_priv))
-		intel_encoder->crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
+		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
 	else if (IS_GEN(dev_priv, 4))
-		intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
+		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B);
 	else
-		intel_encoder->crtc_mask = (1 << 1);
+		intel_encoder->crtc_mask = BIT(PIPE_B);
 
 	drm_connector_helper_add(connector, &intel_lvds_connector_helper_funcs);
 	connector->display_info.subpixel_order = SubPixelHorizontalRGB;
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index adeb1c840976..47f5d87a938a 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -2921,7 +2921,7 @@ intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags)
 			      bytes[0], bytes[1]);
 		return false;
 	}
-	intel_sdvo->base.crtc_mask = (1 << 0) | (1 << 1) | (1 << 2);
+	intel_sdvo->base.crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
 
 	return true;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index 71c3f7e5df7d..70726b481244 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -1947,9 +1947,8 @@ intel_tv_init(struct drm_i915_private *dev_priv)
 	intel_encoder->type = INTEL_OUTPUT_TVOUT;
 	intel_encoder->power_domain = POWER_DOMAIN_PORT_OTHER;
 	intel_encoder->port = PORT_NONE;
-	intel_encoder->crtc_mask = (1 << 0) | (1 << 1);
+	intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B);
 	intel_encoder->cloneable = 0;
-	intel_encoder->base.possible_crtcs = ((1 << 0) | (1 << 1));
 	intel_tv->type = DRM_MODE_CONNECTOR_Unknown;
 
 	/* BIOS margin values */
-- 
cgit v1.2.3


From e8521e53cca584ddf8ec4584d3c550a6c65f88c4 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 1 Oct 2019 16:28:43 +0200
Subject: net: dsa: rtl8366: Check VLAN ID and not ports

There has been some confusion between the port number and
the VLAN ID in this driver. What we need to check for
validity is the VLAN ID, nothing else.

The current confusion came from assigning a few default
VLANs for default routing and we need to rewrite that
properly.

Instead of checking if the port number is a valid VLAN
ID, check the actual VLAN IDs passed in to the callback
one by one as expected.

Fixes: d8652956cf37 ("net: dsa: realtek-smi: Add Realtek SMI driver")
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rtl8366.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
index ca3d17e43ed8..ac88caca5ad4 100644
--- a/drivers/net/dsa/rtl8366.c
+++ b/drivers/net/dsa/rtl8366.c
@@ -339,10 +339,12 @@ int rtl8366_vlan_prepare(struct dsa_switch *ds, int port,
 			 const struct switchdev_obj_port_vlan *vlan)
 {
 	struct realtek_smi *smi = ds->priv;
+	u16 vid;
 	int ret;
 
-	if (!smi->ops->is_vlan_valid(smi, port))
-		return -EINVAL;
+	for (vid = vlan->vid_begin; vid < vlan->vid_end; vid++)
+		if (!smi->ops->is_vlan_valid(smi, vid))
+			return -EINVAL;
 
 	dev_info(smi->dev, "prepare VLANs %04x..%04x\n",
 		 vlan->vid_begin, vlan->vid_end);
@@ -370,8 +372,9 @@ void rtl8366_vlan_add(struct dsa_switch *ds, int port,
 	u16 vid;
 	int ret;
 
-	if (!smi->ops->is_vlan_valid(smi, port))
-		return;
+	for (vid = vlan->vid_begin; vid < vlan->vid_end; vid++)
+		if (!smi->ops->is_vlan_valid(smi, vid))
+			return;
 
 	dev_info(smi->dev, "add VLAN on port %d, %s, %s\n",
 		 port,
-- 
cgit v1.2.3


From d64bf89a75b65f83f06be9fb8f978e60d53752db Mon Sep 17 00:00:00 2001
From: Dotan Barak <dotanb@dev.mellanox.co.il>
Date: Tue, 1 Oct 2019 10:21:02 -0700
Subject: net/rds: Fix error handling in rds_ib_add_one()

rds_ibdev:ipaddr_list and rds_ibdev:conn_list are initialized
after allocation some resources such as protection domain.
If allocation of such resources fail, then these uninitialized
variables are accessed in rds_ib_dev_free() in failure path. This
can potentially crash the system. The code has been updated to
initialize these variables very early in the function.

Signed-off-by: Dotan Barak <dotanb@dev.mellanox.co.il>
Signed-off-by: Sudhakar Dindukurti <sudhakar.dindukurti@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/rds/ib.c b/net/rds/ib.c
index 45acab2de0cf..9de2ae22d583 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -143,6 +143,9 @@ static void rds_ib_add_one(struct ib_device *device)
 	refcount_set(&rds_ibdev->refcount, 1);
 	INIT_WORK(&rds_ibdev->free_work, rds_ib_dev_free);
 
+	INIT_LIST_HEAD(&rds_ibdev->ipaddr_list);
+	INIT_LIST_HEAD(&rds_ibdev->conn_list);
+
 	rds_ibdev->max_wrs = device->attrs.max_qp_wr;
 	rds_ibdev->max_sge = min(device->attrs.max_send_sge, RDS_IB_MAX_SGE);
 
@@ -203,9 +206,6 @@ static void rds_ib_add_one(struct ib_device *device)
 		device->name,
 		rds_ibdev->use_fastreg ? "FRMR" : "FMR");
 
-	INIT_LIST_HEAD(&rds_ibdev->ipaddr_list);
-	INIT_LIST_HEAD(&rds_ibdev->conn_list);
-
 	down_write(&rds_ib_devices_lock);
 	list_add_tail_rcu(&rds_ibdev->list, &rds_ib_devices);
 	up_write(&rds_ib_devices_lock);
-- 
cgit v1.2.3


From d6530e5ad45089c018c3cc5b5957a34721249f6f Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Tue, 1 Oct 2019 21:58:18 +0300
Subject: net: dsa: sja1105: Initialize the meta_lock

Otherwise, with CONFIG_DEBUG_SPINLOCK=y, this stack trace gets printed
when enabling RX timestamping and receiving a PTP frame:

[  318.537078] INFO: trying to register non-static key.
[  318.542040] the code is fine but needs lockdep annotation.
[  318.547500] turning off the locking correctness validator.
[  318.552972] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.3.0-13257-g0825b0669811-dirty #1962
[  318.561283] Hardware name: Freescale LS1021A
[  318.565566] [<c03144bc>] (unwind_backtrace) from [<c030e164>] (show_stack+0x10/0x14)
[  318.573289] [<c030e164>] (show_stack) from [<c11b9f50>] (dump_stack+0xd4/0x100)
[  318.580579] [<c11b9f50>] (dump_stack) from [<c03b9b40>] (register_lock_class+0x728/0x734)
[  318.588731] [<c03b9b40>] (register_lock_class) from [<c03b60c4>] (__lock_acquire+0x78/0x25cc)
[  318.597227] [<c03b60c4>] (__lock_acquire) from [<c03b8ef8>] (lock_acquire+0xd8/0x234)
[  318.605033] [<c03b8ef8>] (lock_acquire) from [<c11db934>] (_raw_spin_lock+0x44/0x54)
[  318.612755] [<c11db934>] (_raw_spin_lock) from [<c1164370>] (sja1105_rcv+0x1f8/0x4e8)
[  318.620561] [<c1164370>] (sja1105_rcv) from [<c115d7cc>] (dsa_switch_rcv+0x80/0x204)
[  318.628283] [<c115d7cc>] (dsa_switch_rcv) from [<c0f58c80>] (__netif_receive_skb_one_core+0x50/0x6c)
[  318.637386] [<c0f58c80>] (__netif_receive_skb_one_core) from [<c0f58f04>] (netif_receive_skb_internal+0xac/0x264)
[  318.647611] [<c0f58f04>] (netif_receive_skb_internal) from [<c0f59e98>] (napi_gro_receive+0x1d8/0x338)
[  318.656887] [<c0f59e98>] (napi_gro_receive) from [<c0c298a4>] (gfar_clean_rx_ring+0x328/0x724)
[  318.665472] [<c0c298a4>] (gfar_clean_rx_ring) from [<c0c29e60>] (gfar_poll_rx_sq+0x34/0x94)
[  318.673795] [<c0c29e60>] (gfar_poll_rx_sq) from [<c0f5b40c>] (net_rx_action+0x128/0x4f8)
[  318.681860] [<c0f5b40c>] (net_rx_action) from [<c03022f0>] (__do_softirq+0x148/0x5ac)
[  318.689666] [<c03022f0>] (__do_softirq) from [<c0355af4>] (irq_exit+0x160/0x170)
[  318.697040] [<c0355af4>] (irq_exit) from [<c03c6818>] (__handle_domain_irq+0x60/0xb4)
[  318.704847] [<c03c6818>] (__handle_domain_irq) from [<c07e9440>] (gic_handle_irq+0x58/0x9c)
[  318.713172] [<c07e9440>] (gic_handle_irq) from [<c0301a70>] (__irq_svc+0x70/0x98)
[  318.720622] Exception stack(0xc2001f18 to 0xc2001f60)
[  318.725656] 1f00:                                                       00000001 00000006
[  318.733805] 1f20: 00000000 c20165c0 ffffe000 c2010cac c2010cf4 00000001 00000000 c2010c88
[  318.741955] 1f40: c1f7a5a8 00000000 00000000 c2001f68 c03ba140 c030a288 200e0013 ffffffff
[  318.750110] [<c0301a70>] (__irq_svc) from [<c030a288>] (arch_cpu_idle+0x24/0x3c)
[  318.757486] [<c030a288>] (arch_cpu_idle) from [<c038a480>] (do_idle+0x1b8/0x2a4)
[  318.764859] [<c038a480>] (do_idle) from [<c038a94c>] (cpu_startup_entry+0x18/0x1c)
[  318.772407] [<c038a94c>] (cpu_startup_entry) from [<c1e00f10>] (start_kernel+0x4cc/0x4fc)

Fixes: 844d7edc6a34 ("net: dsa: sja1105: Add a global sja1105_tagger_data structure")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index f3d38ff144c4..ea2e7f4f96d0 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -2201,6 +2201,7 @@ static int sja1105_probe(struct spi_device *spi)
 	tagger_data = &priv->tagger_data;
 	skb_queue_head_init(&tagger_data->skb_rxtstamp_queue);
 	INIT_WORK(&tagger_data->rxtstamp_work, sja1105_rxtstamp_work);
+	spin_lock_init(&tagger_data->meta_lock);
 
 	/* Connections between dsa_port and sja1105_port */
 	for (i = 0; i < SJA1105_NUM_PORTS; i++) {
-- 
cgit v1.2.3


From 3e8db7e56082156a37b71d7334860c10fcea8025 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Tue, 1 Oct 2019 21:58:19 +0300
Subject: net: dsa: sja1105: Fix sleeping while atomic in .port_hwtstamp_set

Currently this stack trace can be seen with CONFIG_DEBUG_ATOMIC_SLEEP=y:

[   41.568348] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:909
[   41.576757] in_atomic(): 1, irqs_disabled(): 0, pid: 208, name: ptp4l
[   41.583212] INFO: lockdep is turned off.
[   41.587123] CPU: 1 PID: 208 Comm: ptp4l Not tainted 5.3.0-rc6-01445-ge950f2d4bc7f-dirty #1827
[   41.599873] [<c0313d7c>] (unwind_backtrace) from [<c030e13c>] (show_stack+0x10/0x14)
[   41.607584] [<c030e13c>] (show_stack) from [<c1212d50>] (dump_stack+0xd4/0x100)
[   41.614863] [<c1212d50>] (dump_stack) from [<c037dfc8>] (___might_sleep+0x1c8/0x2b4)
[   41.622574] [<c037dfc8>] (___might_sleep) from [<c122ea90>] (__mutex_lock+0x48/0xab8)
[   41.630368] [<c122ea90>] (__mutex_lock) from [<c122f51c>] (mutex_lock_nested+0x1c/0x24)
[   41.638340] [<c122f51c>] (mutex_lock_nested) from [<c0c6fe08>] (sja1105_static_config_reload+0x30/0x27c)
[   41.647779] [<c0c6fe08>] (sja1105_static_config_reload) from [<c0c7015c>] (sja1105_hwtstamp_set+0x108/0x1cc)
[   41.657562] [<c0c7015c>] (sja1105_hwtstamp_set) from [<c0feb650>] (dev_ifsioc+0x18c/0x330)
[   41.665788] [<c0feb650>] (dev_ifsioc) from [<c0febbd8>] (dev_ioctl+0x320/0x6e8)
[   41.673064] [<c0febbd8>] (dev_ioctl) from [<c0f8b1f4>] (sock_ioctl+0x334/0x5e8)
[   41.680340] [<c0f8b1f4>] (sock_ioctl) from [<c05404a8>] (do_vfs_ioctl+0xb0/0xa10)
[   41.687789] [<c05404a8>] (do_vfs_ioctl) from [<c0540e3c>] (ksys_ioctl+0x34/0x58)
[   41.695151] [<c0540e3c>] (ksys_ioctl) from [<c0301000>] (ret_fast_syscall+0x0/0x28)
[   41.702768] Exception stack(0xe8495fa8 to 0xe8495ff0)
[   41.707796] 5fa0:                   beff4a8c 00000001 00000011 000089b0 beff4a8c beff4a80
[   41.715933] 5fc0: beff4a8c 00000001 0000000c 00000036 b6fa98c8 004e19c1 00000001 00000000
[   41.724069] 5fe0: 004dcedc beff4a6c 004c0738 b6e7af4c
[   41.729860] BUG: scheduling while atomic: ptp4l/208/0x00000002
[   41.735682] INFO: lockdep is turned off.

Enabling RX timestamping will logically disturb the fastpath (processing
of meta frames). Replace bool hwts_rx_en with a bit that is checked
atomically from the fastpath and temporarily unset from the sleepable
context during a change of the RX timestamping process (a destructive
operation anyways, requires switch reset).
If found unset, the fastpath (net/dsa/tag_sja1105.c) will just drop any
received meta frame and not take the meta_lock at all.

Fixes: a602afd200f5 ("net: dsa: sja1105: Expose PTP timestamping ioctls to userspace")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_main.c | 19 +++++++++++--------
 include/linux/dsa/sja1105.h            |  4 +++-
 net/dsa/tag_sja1105.c                  | 12 +++++++++++-
 3 files changed, 25 insertions(+), 10 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index ea2e7f4f96d0..7687ddcae159 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1897,7 +1897,9 @@ static int sja1105_set_ageing_time(struct dsa_switch *ds,
 	return sja1105_static_config_reload(priv);
 }
 
-/* Caller must hold priv->tagger_data.meta_lock */
+/* Must be called only with priv->tagger_data.state bit
+ * SJA1105_HWTS_RX_EN cleared
+ */
 static int sja1105_change_rxtstamping(struct sja1105_private *priv,
 				      bool on)
 {
@@ -1954,16 +1956,17 @@ static int sja1105_hwtstamp_set(struct dsa_switch *ds, int port,
 		break;
 	}
 
-	if (rx_on != priv->tagger_data.hwts_rx_en) {
-		spin_lock(&priv->tagger_data.meta_lock);
+	if (rx_on != test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state)) {
+		clear_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state);
+
 		rc = sja1105_change_rxtstamping(priv, rx_on);
-		spin_unlock(&priv->tagger_data.meta_lock);
 		if (rc < 0) {
 			dev_err(ds->dev,
 				"Failed to change RX timestamping: %d\n", rc);
-			return -EFAULT;
+			return rc;
 		}
-		priv->tagger_data.hwts_rx_en = rx_on;
+		if (rx_on)
+			set_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state);
 	}
 
 	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
@@ -1982,7 +1985,7 @@ static int sja1105_hwtstamp_get(struct dsa_switch *ds, int port,
 		config.tx_type = HWTSTAMP_TX_ON;
 	else
 		config.tx_type = HWTSTAMP_TX_OFF;
-	if (priv->tagger_data.hwts_rx_en)
+	if (test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state))
 		config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
 	else
 		config.rx_filter = HWTSTAMP_FILTER_NONE;
@@ -2031,7 +2034,7 @@ static bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port,
 	struct sja1105_private *priv = ds->priv;
 	struct sja1105_tagger_data *data = &priv->tagger_data;
 
-	if (!data->hwts_rx_en)
+	if (!test_bit(SJA1105_HWTS_RX_EN, &data->state))
 		return false;
 
 	/* We need to read the full PTP clock to reconstruct the Rx
diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h
index 79435cfc20eb..897e799dbcb9 100644
--- a/include/linux/dsa/sja1105.h
+++ b/include/linux/dsa/sja1105.h
@@ -31,6 +31,8 @@
 #define SJA1105_META_SMAC			0x222222222222ull
 #define SJA1105_META_DMAC			0x0180C200000Eull
 
+#define SJA1105_HWTS_RX_EN			0
+
 /* Global tagger data: each struct sja1105_port has a reference to
  * the structure defined in struct sja1105_private.
  */
@@ -42,7 +44,7 @@ struct sja1105_tagger_data {
 	 * from taggers running on multiple ports on SMP systems
 	 */
 	spinlock_t meta_lock;
-	bool hwts_rx_en;
+	unsigned long state;
 };
 
 struct sja1105_skb_cb {
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index 9c9aff3e52cf..63ef2a14c934 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -156,7 +156,11 @@ static struct sk_buff
 	/* Step 1: A timestampable frame was received.
 	 * Buffer it until we get its meta frame.
 	 */
-	if (is_link_local && sp->data->hwts_rx_en) {
+	if (is_link_local) {
+		if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state))
+			/* Do normal processing. */
+			return skb;
+
 		spin_lock(&sp->data->meta_lock);
 		/* Was this a link-local frame instead of the meta
 		 * that we were expecting?
@@ -187,6 +191,12 @@ static struct sk_buff
 	} else if (is_meta) {
 		struct sk_buff *stampable_skb;
 
+		/* Drop the meta frame if we're not in the right state
+		 * to process it.
+		 */
+		if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state))
+			return NULL;
+
 		spin_lock(&sp->data->meta_lock);
 
 		stampable_skb = sp->data->stampable_skb;
-- 
cgit v1.2.3


From db34a4714c013b644eec2de0ec81b1f0373b8b93 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <olteanv@gmail.com>
Date: Tue, 1 Oct 2019 22:07:01 +0300
Subject: ptp_qoriq: Initialize the registers' spinlock before calling
 ptp_qoriq_settime

Because ptp_qoriq_settime is being called prior to spin_lock_init, the
following stack trace can be seen at driver probe time:

[    2.269117] the code is fine but needs lockdep annotation.
[    2.274569] turning off the locking correctness validator.
[    2.280027] CPU: 1 PID: 1 Comm: swapper/0 Not tainted 5.3.0-rc7-01478-g01eaa67a4797 #263
[    2.288073] Hardware name: Freescale LS1021A
[    2.292337] [<c0313cb4>] (unwind_backtrace) from [<c030e11c>] (show_stack+0x10/0x14)
[    2.300045] [<c030e11c>] (show_stack) from [<c1219440>] (dump_stack+0xcc/0xf8)
[    2.307235] [<c1219440>] (dump_stack) from [<c03b9b44>] (register_lock_class+0x730/0x73c)
[    2.315372] [<c03b9b44>] (register_lock_class) from [<c03b6190>] (__lock_acquire+0x78/0x270c)
[    2.323856] [<c03b6190>] (__lock_acquire) from [<c03b90cc>] (lock_acquire+0xe0/0x22c)
[    2.331649] [<c03b90cc>] (lock_acquire) from [<c123c310>] (_raw_spin_lock_irqsave+0x54/0x68)
[    2.340048] [<c123c310>] (_raw_spin_lock_irqsave) from [<c0e73fe4>] (ptp_qoriq_settime+0x38/0x80)
[    2.348878] [<c0e73fe4>] (ptp_qoriq_settime) from [<c0e746d4>] (ptp_qoriq_init+0x1f8/0x484)
[    2.357189] [<c0e746d4>] (ptp_qoriq_init) from [<c0e74aac>] (ptp_qoriq_probe+0xd0/0x184)
[    2.365243] [<c0e74aac>] (ptp_qoriq_probe) from [<c0b0a07c>] (platform_drv_probe+0x48/0x9c)
[    2.373555] [<c0b0a07c>] (platform_drv_probe) from [<c0b07a14>] (really_probe+0x1c4/0x400)
[    2.381779] [<c0b07a14>] (really_probe) from [<c0b07e28>] (driver_probe_device+0x78/0x1b8)
[    2.390003] [<c0b07e28>] (driver_probe_device) from [<c0b081d0>] (device_driver_attach+0x58/0x60)
[    2.398832] [<c0b081d0>] (device_driver_attach) from [<c0b082d4>] (__driver_attach+0xfc/0x160)
[    2.407402] [<c0b082d4>] (__driver_attach) from [<c0b05a84>] (bus_for_each_dev+0x68/0xb4)
[    2.415539] [<c0b05a84>] (bus_for_each_dev) from [<c0b06b68>] (bus_add_driver+0x104/0x20c)
[    2.423763] [<c0b06b68>] (bus_add_driver) from [<c0b0909c>] (driver_register+0x78/0x10c)
[    2.431815] [<c0b0909c>] (driver_register) from [<c030313c>] (do_one_initcall+0x8c/0x3ac)
[    2.439954] [<c030313c>] (do_one_initcall) from [<c1f013f4>] (kernel_init_freeable+0x468/0x548)
[    2.448610] [<c1f013f4>] (kernel_init_freeable) from [<c12344d8>] (kernel_init+0x8/0x10c)
[    2.456745] [<c12344d8>] (kernel_init) from [<c03010b4>] (ret_from_fork+0x14/0x20)
[    2.464273] Exception stack(0xea89ffb0 to 0xea89fff8)
[    2.469297] ffa0:                                     00000000 00000000 00000000 00000000
[    2.477432] ffc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
[    2.485566] ffe0: 00000000 00000000 00000000 00000000 00000013 00000000

Fixes: ff54571a747b ("ptp_qoriq: convert to use ptp_qoriq_init/free")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_qoriq.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c
index c61f00b72e15..a577218d1ab7 100644
--- a/drivers/ptp/ptp_qoriq.c
+++ b/drivers/ptp/ptp_qoriq.c
@@ -507,6 +507,8 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base,
 		ptp_qoriq->regs.etts_regs = base + ETTS_REGS_OFFSET;
 	}
 
+	spin_lock_init(&ptp_qoriq->lock);
+
 	ktime_get_real_ts64(&now);
 	ptp_qoriq_settime(&ptp_qoriq->caps, &now);
 
@@ -514,7 +516,6 @@ int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base,
 	  (ptp_qoriq->tclk_period & TCLK_PERIOD_MASK) << TCLK_PERIOD_SHIFT |
 	  (ptp_qoriq->cksel & CKSEL_MASK) << CKSEL_SHIFT;
 
-	spin_lock_init(&ptp_qoriq->lock);
 	spin_lock_irqsave(&ptp_qoriq->lock, flags);
 
 	regs = &ptp_qoriq->regs;
-- 
cgit v1.2.3


From 0228ecf6128c92b47eadd2ac270c5574d9150c09 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Tue, 1 Oct 2019 21:56:37 +0000
Subject: MIPS: octeon: Include required header; fix octeon ethernet build

Commit 171a9bae68c7 ("staging/octeon: Allow test build on !MIPS") moved
the inclusion of a bunch of headers by various files in the Octeon
ethernet driver into a common header, but in doing so it changed the
order in which those headers are included.

Prior to the referenced commit drivers/staging/octeon/ethernet.c
included asm/octeon/cvmx-pip.h before asm/octeon/cvmx-ipd.h, which makes
use of the CVMX_PIP_SFT_RST definition pulled in by the former. After
commit 171a9bae68c7 ("staging/octeon: Allow test build on !MIPS") we
pull in asm/octeon/cvmx-ipd.h first & builds fail with:

  In file included from drivers/staging/octeon/octeon-ethernet.h:27,
                   from drivers/staging/octeon/ethernet.c:22:
  arch/mips/include/asm/octeon/cvmx-ipd.h: In function 'cvmx_ipd_free_ptr':
  arch/mips/include/asm/octeon/cvmx-ipd.h:330:27: error: storage size of
    'pip_sft_rst' isn't known
      union cvmx_pip_sft_rst pip_sft_rst;
                             ^~~~~~~~~~~
  arch/mips/include/asm/octeon/cvmx-ipd.h:331:36: error: 'CVMX_PIP_SFT_RST'
    undeclared (first use in this function); did you mean 'CVMX_CIU_SOFT_RST'?
      pip_sft_rst.u64 = cvmx_read_csr(CVMX_PIP_SFT_RST);
                                      ^~~~~~~~~~~~~~~~
                                      CVMX_CIU_SOFT_RST
  arch/mips/include/asm/octeon/cvmx-ipd.h:331:36: note: each undeclared
    identifier is reported only once for each function it appears in
  arch/mips/include/asm/octeon/cvmx-ipd.h:330:27: warning: unused variable
    'pip_sft_rst' [-Wunused-variable]
      union cvmx_pip_sft_rst pip_sft_rst;
                             ^~~~~~~~~~~
  make[4]: *** [scripts/Makefile.build:266: drivers/staging/octeon/ethernet.o]
    Error 1
  make[3]: *** [scripts/Makefile.build:509: drivers/staging/octeon] Error 2

Fix this by having asm/octeon/cvmx-ipd.h include the
asm/octeon/cvmx-pip-defs.h header that it is reliant upon, rather than
requiring its users to pull in that header before it.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Fixes: 171a9bae68c7 ("staging/octeon: Allow test build on !MIPS")
Cc: David S. Miller <davem@davemloft.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: linux-mips@vger.kernel.org
Cc: David S . Miller <davem@davemloft.net>
Cc: Matthew Wilcox <willy@infradead.org>
---
 arch/mips/include/asm/octeon/cvmx-ipd.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/mips/include/asm/octeon/cvmx-ipd.h b/arch/mips/include/asm/octeon/cvmx-ipd.h
index cbdc14b77435..adab7b54c3b4 100644
--- a/arch/mips/include/asm/octeon/cvmx-ipd.h
+++ b/arch/mips/include/asm/octeon/cvmx-ipd.h
@@ -36,6 +36,7 @@
 #include <asm/octeon/octeon-feature.h>
 
 #include <asm/octeon/cvmx-ipd-defs.h>
+#include <asm/octeon/cvmx-pip-defs.h>
 
 enum cvmx_ipd_mode {
    CVMX_IPD_OPC_MODE_STT = 0LL,	  /* All blocks DRAM, not cached in L2 */
-- 
cgit v1.2.3


From 69f08e68af25071483b91769957743de3b9deaef Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 12 Sep 2019 12:13:50 +0200
Subject: drm/amdgpu: revert "disable bulk moves for now"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit a213c2c7e235cfc0e0a161a558f7fdf2fb3a624a.

The changes to fix this should have landed in 5.1.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Zhou, David(ChunMing) <David1.Zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index e2fb141ff2e5..5251352f5922 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -603,14 +603,12 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
 	struct ttm_bo_global *glob = adev->mman.bdev.glob;
 	struct amdgpu_vm_bo_base *bo_base;
 
-#if 0
 	if (vm->bulk_moveable) {
 		spin_lock(&glob->lru_lock);
 		ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move);
 		spin_unlock(&glob->lru_lock);
 		return;
 	}
-#endif
 
 	memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move));
 
-- 
cgit v1.2.3


From e0e4a2ce7a059d051c66cd7c94314fef3cd91aea Mon Sep 17 00:00:00 2001
From: Kevin Wang <kevin1.wang@amd.com>
Date: Thu, 26 Sep 2019 16:16:41 +0800
Subject: drm/amd/powerplay: change metrics update period from 1ms to 100ms

v2:
change period from 10ms to 100ms (typo error)

too high frequence to update mertrics table will cause smu firmware
error,so change mertrics table update period from 1ms to 100ms
(navi10, 12, 14)

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 5.3.x
---
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 12c0e469bf35..2574f7186e16 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -547,7 +547,7 @@ static int navi10_get_metrics_table(struct smu_context *smu,
 	struct smu_table_context *smu_table= &smu->smu_table;
 	int ret = 0;
 
-	if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) {
+	if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + msecs_to_jiffies(100))) {
 		ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
 				(void *)smu_table->metrics_table, false);
 		if (ret) {
-- 
cgit v1.2.3


From 00921306751001b539ebee34171485cd9c749024 Mon Sep 17 00:00:00 2001
From: Kevin Wang <kevin1.wang@amd.com>
Date: Thu, 26 Sep 2019 16:22:13 +0800
Subject: drm/amd/powerplay: add sensor lock support for smu

when multithreading access sysfs of amdgpu_pm_info at the sametime.
the swsmu driver cause smu firmware hang.

eg:
single thread access:
Message A + Param A ==> right
Message B + Param B ==> right
Message C + Param C ==> right
multithreading access:
Message A + Param B ==> error
Message B + Param A ==> error
Message C + Param C ==> right

the patch will add sensor lock(mutex) to avoid this error.

Signed-off-by: Kevin Wang <kevin1.wang@amd.com>
Reviewed-by: Kenneth Feng <kenneth.feng@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org # 5.3.x
---
 drivers/gpu/drm/amd/powerplay/amdgpu_smu.c     | 2 ++
 drivers/gpu/drm/amd/powerplay/arcturus_ppt.c   | 2 ++
 drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h | 1 +
 drivers/gpu/drm/amd/powerplay/navi10_ppt.c     | 2 ++
 drivers/gpu/drm/amd/powerplay/vega20_ppt.c     | 2 ++
 5 files changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 33960fb38a5d..4acf139ea014 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -843,6 +843,8 @@ static int smu_sw_init(void *handle)
 	smu->smu_baco.state = SMU_BACO_STATE_EXIT;
 	smu->smu_baco.platform_support = false;
 
+	mutex_init(&smu->sensor_lock);
+
 	smu->watermarks_bitmap = 0;
 	smu->power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
 	smu->default_power_profile_mode = PP_SMC_POWER_PROFILE_BOOTUP_DEFAULT;
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index f1f072012fac..d493a3f8c07a 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -1018,6 +1018,7 @@ static int arcturus_read_sensor(struct smu_context *smu,
 	if (!data || !size)
 		return -EINVAL;
 
+	mutex_lock(&smu->sensor_lock);
 	switch (sensor) {
 	case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
 		*(uint32_t *)data = pptable->FanMaximumRpm;
@@ -1044,6 +1045,7 @@ static int arcturus_read_sensor(struct smu_context *smu,
 	default:
 		ret = smu_smc_read_sensor(smu, sensor, data, size);
 	}
+	mutex_unlock(&smu->sensor_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index 6109815a0401..23171a4d9a31 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -344,6 +344,7 @@ struct smu_context
 	const struct smu_funcs		*funcs;
 	const struct pptable_funcs	*ppt_funcs;
 	struct mutex			mutex;
+	struct mutex			sensor_lock;
 	uint64_t pool_size;
 
 	struct smu_table_context	smu_table;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 2574f7186e16..0b461404af6b 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -1386,6 +1386,7 @@ static int navi10_read_sensor(struct smu_context *smu,
 	if(!data || !size)
 		return -EINVAL;
 
+	mutex_lock(&smu->sensor_lock);
 	switch (sensor) {
 	case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
 		*(uint32_t *)data = pptable->FanMaximumRpm;
@@ -1409,6 +1410,7 @@ static int navi10_read_sensor(struct smu_context *smu,
 	default:
 		ret = smu_smc_read_sensor(smu, sensor, data, size);
 	}
+	mutex_unlock(&smu->sensor_lock);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index 64386ee3f878..bbd8ebd58434 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -3023,6 +3023,7 @@ static int vega20_read_sensor(struct smu_context *smu,
 	if(!data || !size)
 		return -EINVAL;
 
+	mutex_lock(&smu->sensor_lock);
 	switch (sensor) {
 	case AMDGPU_PP_SENSOR_MAX_FAN_RPM:
 		*(uint32_t *)data = pptable->FanMaximumRpm;
@@ -3048,6 +3049,7 @@ static int vega20_read_sensor(struct smu_context *smu,
 	default:
 		ret = smu_smc_read_sensor(smu, sensor, data, size);
 	}
+	mutex_unlock(&smu->sensor_lock);
 
 	return ret;
 }
-- 
cgit v1.2.3


From 8225630ea61da1c96af84849a055d5b20b404438 Mon Sep 17 00:00:00 2001
From: Aaron Liu <aaron.liu@amd.com>
Date: Mon, 16 Sep 2019 10:05:09 +0800
Subject: Revert "drm/amdgpu: disable stutter mode for renoir"

This reverts commit 5813f97a5969bf1e7e723397a74e00b5de7278d6.

Since SBIOS WCD9925N, NMI printing disappeared. Hence enable stutter
mode.

Signed-off-by: Aaron Liu <aaron.liu@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 8cab6da512a0..a97eea304cc0 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2385,8 +2385,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 
 	if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY)
 		dm->dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true;
-	if (adev->asic_type == CHIP_RENOIR)
-		dm->dc->debug.disable_stutter = true;
 
 	return 0;
 fail:
-- 
cgit v1.2.3


From 49379032aa22a040fdd7708fcb6300d1d98a0f57 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 1 Oct 2019 16:45:27 -0500
Subject: drm/amdgpu: don't increment vram lost if we are in hibernation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We reset the GPU as part of our hibernation sequence so we need
to make sure we don't mark vram as lost in that case.

Bug: https://bugs.freedesktop.org/show_bug.cgi?id=111879
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/nv.c    | 6 ++++--
 drivers/gpu/drm/amd/amdgpu/soc15.c | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 85393a99a848..de9b995b65b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -317,10 +317,12 @@ static int nv_asic_reset(struct amdgpu_device *adev)
 	struct smu_context *smu = &adev->smu;
 
 	if (nv_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
-		amdgpu_inc_vram_lost(adev);
+		if (!adev->in_suspend)
+			amdgpu_inc_vram_lost(adev);
 		ret = smu_baco_reset(smu);
 	} else {
-		amdgpu_inc_vram_lost(adev);
+		if (!adev->in_suspend)
+			amdgpu_inc_vram_lost(adev);
 		ret = nv_asic_mode1_reset(adev);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index f70658a536a9..61df616b5d45 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -558,12 +558,14 @@ static int soc15_asic_reset(struct amdgpu_device *adev)
 {
 	switch (soc15_asic_reset_method(adev)) {
 		case AMD_RESET_METHOD_BACO:
-			amdgpu_inc_vram_lost(adev);
+			if (!adev->in_suspend)
+				amdgpu_inc_vram_lost(adev);
 			return soc15_asic_baco_reset(adev);
 		case AMD_RESET_METHOD_MODE2:
 			return soc15_mode2_reset(adev);
 		default:
-			amdgpu_inc_vram_lost(adev);
+			if (!adev->in_suspend)
+				amdgpu_inc_vram_lost(adev);
 			return soc15_asic_mode1_reset(adev);
 	}
 }
-- 
cgit v1.2.3


From 815fb4c9d7da862a47c9d2a9765a4759826c5783 Mon Sep 17 00:00:00 2001
From: Marek Olšák <marek.olsak@amd.com>
Date: Tue, 24 Sep 2019 17:53:25 -0400
Subject: drm/amdgpu: return tcc_disabled_mask to userspace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

UMDs need this for correct programming of harvested chips.

Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c |  3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c |  2 ++
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c  | 12 ++++++++++++
 include/uapi/drm/amdgpu_drm.h           |  2 ++
 5 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 264677ab248a..6f8aaf655a9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -81,9 +81,10 @@
  * - 3.32.0 - Add syncobj timeline support to AMDGPU_CS.
  * - 3.33.0 - Fixes for GDS ENOMEM failures in AMDGPU_CS.
  * - 3.34.0 - Non-DC can flip correctly between buffers with different pitches
+ * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	34
+#define KMS_DRIVER_MINOR	35
 #define KMS_DRIVER_PATCHLEVEL	0
 
 #define AMDGPU_MAX_TIMEOUT_PARAM_LENTH	256
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 554a59b3c4a6..6ee4021910e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -165,6 +165,7 @@ struct amdgpu_gfx_config {
 	uint32_t num_sc_per_sh;
 	uint32_t num_packer_per_sc;
 	uint32_t pa_sc_tile_steering_override;
+	uint64_t tcc_disabled_mask;
 };
 
 struct amdgpu_cu_info {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index f6147528be64..f2c097983f48 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -787,6 +787,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			dev_info.pa_sc_tile_steering_override =
 				adev->gfx.config.pa_sc_tile_steering_override;
 
+		dev_info.tcc_disabled_mask = adev->gfx.config.tcc_disabled_mask;
+
 		return copy_to_user(out, &dev_info,
 				    min((size_t)size, sizeof(dev_info))) ? -EFAULT : 0;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 638c821611ab..957811b73672 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -1691,6 +1691,17 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
 	}
 }
 
+static void gfx_v10_0_get_tcc_info(struct amdgpu_device *adev)
+{
+	/* TCCs are global (not instanced). */
+	uint32_t tcc_disable = RREG32_SOC15(GC, 0, mmCGTS_TCC_DISABLE) |
+			       RREG32_SOC15(GC, 0, mmCGTS_USER_TCC_DISABLE);
+
+	adev->gfx.config.tcc_disabled_mask =
+		REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, TCC_DISABLE) |
+		(REG_GET_FIELD(tcc_disable, CGTS_TCC_DISABLE, HI_TCC_DISABLE) << 16);
+}
+
 static void gfx_v10_0_constants_init(struct amdgpu_device *adev)
 {
 	u32 tmp;
@@ -1702,6 +1713,7 @@ static void gfx_v10_0_constants_init(struct amdgpu_device *adev)
 
 	gfx_v10_0_setup_rb(adev);
 	gfx_v10_0_get_cu_info(adev, &adev->gfx.cu_info);
+	gfx_v10_0_get_tcc_info(adev);
 	adev->gfx.config.pa_sc_tile_steering_override =
 		gfx_v10_0_init_pa_sc_tile_steering_override(adev);
 
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index c99b4f2482c6..4fe35d600ab8 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -1003,6 +1003,8 @@ struct drm_amdgpu_info_device {
 	__u64 high_va_max;
 	/* gfx10 pa_sc_tile_steering_override */
 	__u32 pa_sc_tile_steering_override;
+	/* disabled TCCs */
+	__u64 tcc_disabled_mask;
 };
 
 struct drm_amdgpu_info_hw_ip {
-- 
cgit v1.2.3


From 57be09c6e8747bf48704136d9e3f92bfb93f5725 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Tue, 1 Oct 2019 22:46:07 -0500
Subject: drm/amdgpu: fix multiple memory leaks in acp_hw_init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In acp_hw_init there are some allocations that needs to be released in
case of failure:

1- adev->acp.acp_genpd should be released if any allocation attemp for
adev->acp.acp_cell, adev->acp.acp_res or i2s_pdata fails.
2- all of those allocations should be released if
mfd_add_hotplug_devices or pm_genpd_add_device fail.
3- Release is needed in case of time out values expire.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c | 34 +++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index eba42c752bca..82155ac3288a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -189,7 +189,7 @@ static int acp_hw_init(void *handle)
 	u32 val = 0;
 	u32 count = 0;
 	struct device *dev;
-	struct i2s_platform_data *i2s_pdata;
+	struct i2s_platform_data *i2s_pdata = NULL;
 
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
@@ -231,20 +231,21 @@ static int acp_hw_init(void *handle)
 	adev->acp.acp_cell = kcalloc(ACP_DEVS, sizeof(struct mfd_cell),
 							GFP_KERNEL);
 
-	if (adev->acp.acp_cell == NULL)
-		return -ENOMEM;
+	if (adev->acp.acp_cell == NULL) {
+		r = -ENOMEM;
+		goto failure;
+	}
 
 	adev->acp.acp_res = kcalloc(5, sizeof(struct resource), GFP_KERNEL);
 	if (adev->acp.acp_res == NULL) {
-		kfree(adev->acp.acp_cell);
-		return -ENOMEM;
+		r = -ENOMEM;
+		goto failure;
 	}
 
 	i2s_pdata = kcalloc(3, sizeof(struct i2s_platform_data), GFP_KERNEL);
 	if (i2s_pdata == NULL) {
-		kfree(adev->acp.acp_res);
-		kfree(adev->acp.acp_cell);
-		return -ENOMEM;
+		r = -ENOMEM;
+		goto failure;
 	}
 
 	switch (adev->asic_type) {
@@ -341,14 +342,14 @@ static int acp_hw_init(void *handle)
 	r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell,
 								ACP_DEVS);
 	if (r)
-		return r;
+		goto failure;
 
 	for (i = 0; i < ACP_DEVS ; i++) {
 		dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
 		r = pm_genpd_add_device(&adev->acp.acp_genpd->gpd, dev);
 		if (r) {
 			dev_err(dev, "Failed to add dev to genpd\n");
-			return r;
+			goto failure;
 		}
 	}
 
@@ -367,7 +368,8 @@ static int acp_hw_init(void *handle)
 			break;
 		if (--count == 0) {
 			dev_err(&adev->pdev->dev, "Failed to reset ACP\n");
-			return -ETIMEDOUT;
+			r = -ETIMEDOUT;
+			goto failure;
 		}
 		udelay(100);
 	}
@@ -384,7 +386,8 @@ static int acp_hw_init(void *handle)
 			break;
 		if (--count == 0) {
 			dev_err(&adev->pdev->dev, "Failed to reset ACP\n");
-			return -ETIMEDOUT;
+			r = -ETIMEDOUT;
+			goto failure;
 		}
 		udelay(100);
 	}
@@ -393,6 +396,13 @@ static int acp_hw_init(void *handle)
 	val &= ~ACP_SOFT_RESET__SoftResetAud_MASK;
 	cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val);
 	return 0;
+
+failure:
+	kfree(i2s_pdata);
+	kfree(adev->acp.acp_res);
+	kfree(adev->acp.acp_cell);
+	kfree(adev->acp.acp_genpd);
+	return r;
 }
 
 /**
-- 
cgit v1.2.3


From 055e547478a11a6360c7ce05e2afc3e366968a12 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Mon, 16 Sep 2019 22:20:44 -0500
Subject: drm/amd/display: memory leak

In dcn*_clock_source_create when dcn20_clk_src_construct fails allocated
clk_src needs release.

Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c | 1 +
 drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c | 1 +
 drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c | 1 +
 drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c | 1 +
 drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c   | 1 +
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c   | 1 +
 drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c   | 1 +
 7 files changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index 1787b9bf800a..76d54885374a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -668,6 +668,7 @@ struct clock_source *dce100_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index 318e9c2e2ca8..89620adc81d8 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -714,6 +714,7 @@ struct clock_source *dce110_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 83e1878161c9..21a657e79306 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -687,6 +687,7 @@ struct clock_source *dce112_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 8b85e5274bba..7c52f7f9196c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -500,6 +500,7 @@ static struct clock_source *dce120_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 4625df9f9fd2..643ccb0ade00 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -701,6 +701,7 @@ struct clock_source *dce80_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 59305e411a66..1599bb971111 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -786,6 +786,7 @@ struct clock_source *dcn10_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index b4e3ce22ed52..5a2763daff4d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -1077,6 +1077,7 @@ struct clock_source *dcn20_clock_source_create(
 		return &clk_src->base;
 	}
 
+	kfree(clk_src);
 	BREAK_TO_DEBUGGER();
 	return NULL;
 }
-- 
cgit v1.2.3


From ec3e5c0f0c2b716e768c0eee0fec30d572939ef5 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 2 Oct 2019 14:01:22 +0200
Subject: drm/amdgpu: make pmu support optional, again

When CONFIG_PERF_EVENTS is disabled, we cannot compile the pmu
portion of the amdgpu driver:

drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c:48:38: error: no member named 'hw' in 'struct perf_event'
        struct hw_perf_event *hwc = &event->hw;
                                     ~~~~~  ^
drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c:51:13: error: no member named 'attr' in 'struct perf_event'
        if (event->attr.type != event->pmu->type)
            ~~~~~  ^
...

The same bug was already fixed by commit d155bef0636e ("amdgpu: make pmu
support optional") but broken again by what looks like an incorrectly
rebased patch.

Fixes: 64f55e629237 ("drm/amdgpu: Add RAS EEPROM table.")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 42e2c1f57152..00962a659009 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -54,7 +54,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o \
 	amdgpu_vf_error.o amdgpu_sched.o amdgpu_debugfs.o amdgpu_ids.o \
 	amdgpu_gmc.o amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \
-	amdgpu_vm_sdma.o amdgpu_pmu.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o
+	amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o
 
 amdgpu-$(CONFIG_PERF_EVENTS) += amdgpu_pmu.o
 
-- 
cgit v1.2.3


From 29174a4310bf9b25b4961c30b38be4151732d1c7 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 2 Oct 2019 14:01:23 +0200
Subject: drm/amdgpu: hide another #warning

An earlier patch of mine disabled some #warning statements
that get in the way of build testing, but then another
instance was added around the same time.

Remove that as well.

Fixes: b5203d16aef4 ("drm/amd/amdgpu: hide #warning for missing DC config")
Fixes: e1c14c43395c ("drm/amdgpu: Enable DC on Renoir")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/soc15.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 61df616b5d45..f8ab80c8801b 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -773,8 +773,6 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 #if defined(CONFIG_DRM_AMD_DC)
                 else if (amdgpu_device_has_dc_support(adev))
                         amdgpu_device_ip_block_add(adev, &dm_ip_block);
-#else
-#       warning "Enable CONFIG_DRM_AMD_DC for display support on SOC15."
 #endif
 		amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
 		break;
-- 
cgit v1.2.3


From beda921dbc99ce240ae88e2c9740c99c354c7ca2 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 2 Oct 2019 14:01:24 +0200
Subject: drm/amdgpu: display_mode_vba_21: remove uint typedef

The type definition for 'uint' clashes with the generic kernel
headers:

drivers/gpu/drm/amd/amdgpu/../display/dc/dml/dcn21/display_mode_vba_21.c:43:22: error: redefinition of typedef 'uint' is a C11 feature [-Werror,-Wtypedef-redefinition]
include/linux/types.h:92:23: note: previous definition is here

Just remove this type and use plain 'unsigned int' consistently,
as it is already use almost everywhere in this file.

Fixes: b04641a3f4c5 ("drm/amd/display: Add Renoir DML")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c  | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
index 456cd0e3289c..3b6ed60dcd35 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
@@ -39,9 +39,6 @@
  * ways. Unless there is something clearly wrong with it the code should
  * remain as-is as it provides us with a guarantee from HW that it is correct.
  */
-
-typedef unsigned int uint;
-
 typedef struct {
 	double DPPCLK;
 	double DISPCLK;
@@ -4774,7 +4771,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				mode_lib->vba.MaximumReadBandwidthWithoutPrefetch = 0.0;
 				mode_lib->vba.MaximumReadBandwidthWithPrefetch = 0.0;
 				for (k = 0; k <= mode_lib->vba.NumberOfActivePlanes - 1; k++) {
-					uint m;
+					unsigned int m;
 
 					locals->cursor_bw[k] = 0;
 					locals->cursor_bw_pre[k] = 0;
@@ -5285,7 +5282,7 @@ static void CalculateWatermarksAndDRAMSpeedChangeSupport(
 	double SecondMinActiveDRAMClockChangeMarginOneDisplayInVBLank;
 	double FullDETBufferingTimeYStutterCriticalPlane = 0;
 	double TimeToFinishSwathTransferStutterCriticalPlane = 0;
-	uint k, j;
+	unsigned int k, j;
 
 	mode_lib->vba.TotalActiveDPP = 0;
 	mode_lib->vba.TotalDCCActiveDPP = 0;
@@ -5507,7 +5504,7 @@ static void CalculateDCFCLKDeepSleep(
 		double DPPCLK[],
 		double *DCFCLKDeepSleep)
 {
-	uint k;
+	unsigned int k;
 	double DisplayPipeLineDeliveryTimeLuma;
 	double DisplayPipeLineDeliveryTimeChroma;
 	//double   DCFCLKDeepSleepPerPlane[DC__NUM_DPP__MAX];
@@ -5727,7 +5724,7 @@ static void CalculatePixelDeliveryTimes(
 		double DisplayPipeRequestDeliveryTimeChromaPrefetch[])
 {
 	double req_per_swath_ub;
-	uint k;
+	unsigned int k;
 
 	for (k = 0; k < NumberOfActivePlanes; ++k) {
 		if (VRatio[k] <= 1) {
@@ -5869,7 +5866,7 @@ static void CalculateMetaAndPTETimes(
 	unsigned int dpte_groups_per_row_chroma_ub;
 	unsigned int num_group_per_lower_vm_stage;
 	unsigned int num_req_per_lower_vm_stage;
-	uint k;
+	unsigned int k;
 
 	for (k = 0; k < NumberOfActivePlanes; ++k) {
 		if (GPUVMEnable == true) {
-- 
cgit v1.2.3


From 148d31e38fb37ba442f9b554325114b9e80cf336 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 18 Sep 2019 21:53:58 +0200
Subject: drm/amd/display: hide an unused variable

Without CONFIG_DEBUG_FS, we get a warning for an unused
variable:

drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm.c:6020:33: error: unused variable 'source' [-Werror,-Wunused-variable]

Hide the variable in an #ifdef like its only users.

Fixes: 14b2584636c6 ("drm/amd/display: add functionality to grab DPRX CRC entries.")
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index a97eea304cc0..a52f0b13a2c8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -6017,7 +6017,9 @@ static void amdgpu_dm_enable_crtc_interrupts(struct drm_device *dev,
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	int i;
+#ifdef CONFIG_DEBUG_FS
 	enum amdgpu_dm_pipe_crc_source source;
+#endif
 
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
 				      new_crtc_state, i) {
-- 
cgit v1.2.3


From c0e70e10b11b1b7ca0f537e7ce4404a0459cdc7c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 2 Oct 2019 14:01:25 +0200
Subject: drm/amd/display: fix dcn21 Makefile for clang

Just like all the other variants, this one passes invalid
compile-time options with clang after the new code got
merged:

clang: error: unknown argument: '-mpreferred-stack-boundary=4'
scripts/Makefile.build:265: recipe for target 'drivers/gpu/drm/amd/amdgpu/../display/dc/dcn21/dcn21_resource.o' failed

Use the same variant that we have for dcn20 to fix compilation.

Fixes: eced51f9babb ("drm/amd/display: Add hubp block for Renoir (v2)")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn21/Makefile | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
index 8cd9de8b1a7a..ef673bffc241 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -3,7 +3,17 @@
 
 DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o
 
-CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse -mpreferred-stack-boundary=4
+ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
+	cc_stack_align := -mpreferred-stack-boundary=4
+else ifneq ($(call cc-option, -mstack-alignment=16),)
+	cc_stack_align := -mstack-alignment=16
+endif
+
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse $(cc_stack_align)
+
+ifdef CONFIG_CC_IS_CLANG
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2
+endif
 
 AMD_DAL_DCN21 = $(addprefix $(AMDDALPATH)/dc/dcn21/,$(DCN21))
 
-- 
cgit v1.2.3


From f21e8b80b79d77872e88d853032294ba5bde0bc4 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Tue, 1 Oct 2019 12:37:29 -0700
Subject: drm/i915/mg: Use tc_port instead of port parameter to MG registers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All the MG registers is based on the tc_port not port, so
MG_PHY_PORT_LN() was subtracting port and PORT_C what is very
fragile.
So replacing port to tc_port in all MG register macros and users
like we have for DKL.

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191001193729.123736-1-jose.souza@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c |  64 ++++++++++----------
 drivers/gpu/drm/i915/i915_reg.h          | 100 +++++++++++++++----------------
 2 files changed, 81 insertions(+), 83 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index b463e51f8b45..3c1e885e0187 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -2681,7 +2681,7 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 					   u32 level)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	enum port port = encoder->port;
+	enum tc_port tc_port = intel_port_to_tc(dev_priv, encoder->port);
 	const struct icl_mg_phy_ddi_buf_trans *ddi_translations;
 	u32 n_entries, val;
 	int ln;
@@ -2697,33 +2697,33 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 
 	/* Set MG_TX_LINK_PARAMS cri_use_fs32 to 0. */
 	for (ln = 0; ln < 2; ln++) {
-		val = I915_READ(MG_TX1_LINK_PARAMS(ln, port));
+		val = I915_READ(MG_TX1_LINK_PARAMS(ln, tc_port));
 		val &= ~CRI_USE_FS32;
-		I915_WRITE(MG_TX1_LINK_PARAMS(ln, port), val);
+		I915_WRITE(MG_TX1_LINK_PARAMS(ln, tc_port), val);
 
-		val = I915_READ(MG_TX2_LINK_PARAMS(ln, port));
+		val = I915_READ(MG_TX2_LINK_PARAMS(ln, tc_port));
 		val &= ~CRI_USE_FS32;
-		I915_WRITE(MG_TX2_LINK_PARAMS(ln, port), val);
+		I915_WRITE(MG_TX2_LINK_PARAMS(ln, tc_port), val);
 	}
 
 	/* Program MG_TX_SWINGCTRL with values from vswing table */
 	for (ln = 0; ln < 2; ln++) {
-		val = I915_READ(MG_TX1_SWINGCTRL(ln, port));
+		val = I915_READ(MG_TX1_SWINGCTRL(ln, tc_port));
 		val &= ~CRI_TXDEEMPH_OVERRIDE_17_12_MASK;
 		val |= CRI_TXDEEMPH_OVERRIDE_17_12(
 			ddi_translations[level].cri_txdeemph_override_17_12);
-		I915_WRITE(MG_TX1_SWINGCTRL(ln, port), val);
+		I915_WRITE(MG_TX1_SWINGCTRL(ln, tc_port), val);
 
-		val = I915_READ(MG_TX2_SWINGCTRL(ln, port));
+		val = I915_READ(MG_TX2_SWINGCTRL(ln, tc_port));
 		val &= ~CRI_TXDEEMPH_OVERRIDE_17_12_MASK;
 		val |= CRI_TXDEEMPH_OVERRIDE_17_12(
 			ddi_translations[level].cri_txdeemph_override_17_12);
-		I915_WRITE(MG_TX2_SWINGCTRL(ln, port), val);
+		I915_WRITE(MG_TX2_SWINGCTRL(ln, tc_port), val);
 	}
 
 	/* Program MG_TX_DRVCTRL with values from vswing table */
 	for (ln = 0; ln < 2; ln++) {
-		val = I915_READ(MG_TX1_DRVCTRL(ln, port));
+		val = I915_READ(MG_TX1_DRVCTRL(ln, tc_port));
 		val &= ~(CRI_TXDEEMPH_OVERRIDE_11_6_MASK |
 			 CRI_TXDEEMPH_OVERRIDE_5_0_MASK);
 		val |= CRI_TXDEEMPH_OVERRIDE_5_0(
@@ -2731,9 +2731,9 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 			CRI_TXDEEMPH_OVERRIDE_11_6(
 				ddi_translations[level].cri_txdeemph_override_11_6) |
 			CRI_TXDEEMPH_OVERRIDE_EN;
-		I915_WRITE(MG_TX1_DRVCTRL(ln, port), val);
+		I915_WRITE(MG_TX1_DRVCTRL(ln, tc_port), val);
 
-		val = I915_READ(MG_TX2_DRVCTRL(ln, port));
+		val = I915_READ(MG_TX2_DRVCTRL(ln, tc_port));
 		val &= ~(CRI_TXDEEMPH_OVERRIDE_11_6_MASK |
 			 CRI_TXDEEMPH_OVERRIDE_5_0_MASK);
 		val |= CRI_TXDEEMPH_OVERRIDE_5_0(
@@ -2741,7 +2741,7 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 			CRI_TXDEEMPH_OVERRIDE_11_6(
 				ddi_translations[level].cri_txdeemph_override_11_6) |
 			CRI_TXDEEMPH_OVERRIDE_EN;
-		I915_WRITE(MG_TX2_DRVCTRL(ln, port), val);
+		I915_WRITE(MG_TX2_DRVCTRL(ln, tc_port), val);
 
 		/* FIXME: Program CRI_LOADGEN_SEL after the spec is updated */
 	}
@@ -2752,17 +2752,17 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 	 * values from table for which TX1 and TX2 enabled.
 	 */
 	for (ln = 0; ln < 2; ln++) {
-		val = I915_READ(MG_CLKHUB(ln, port));
+		val = I915_READ(MG_CLKHUB(ln, tc_port));
 		if (link_clock < 300000)
 			val |= CFG_LOW_RATE_LKREN_EN;
 		else
 			val &= ~CFG_LOW_RATE_LKREN_EN;
-		I915_WRITE(MG_CLKHUB(ln, port), val);
+		I915_WRITE(MG_CLKHUB(ln, tc_port), val);
 	}
 
 	/* Program the MG_TX_DCC<LN, port being used> based on the link frequency */
 	for (ln = 0; ln < 2; ln++) {
-		val = I915_READ(MG_TX1_DCC(ln, port));
+		val = I915_READ(MG_TX1_DCC(ln, tc_port));
 		val &= ~CFG_AMI_CK_DIV_OVERRIDE_VAL_MASK;
 		if (link_clock <= 500000) {
 			val &= ~CFG_AMI_CK_DIV_OVERRIDE_EN;
@@ -2770,9 +2770,9 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 			val |= CFG_AMI_CK_DIV_OVERRIDE_EN |
 				CFG_AMI_CK_DIV_OVERRIDE_VAL(1);
 		}
-		I915_WRITE(MG_TX1_DCC(ln, port), val);
+		I915_WRITE(MG_TX1_DCC(ln, tc_port), val);
 
-		val = I915_READ(MG_TX2_DCC(ln, port));
+		val = I915_READ(MG_TX2_DCC(ln, tc_port));
 		val &= ~CFG_AMI_CK_DIV_OVERRIDE_VAL_MASK;
 		if (link_clock <= 500000) {
 			val &= ~CFG_AMI_CK_DIV_OVERRIDE_EN;
@@ -2780,18 +2780,18 @@ static void icl_mg_phy_ddi_vswing_sequence(struct intel_encoder *encoder,
 			val |= CFG_AMI_CK_DIV_OVERRIDE_EN |
 				CFG_AMI_CK_DIV_OVERRIDE_VAL(1);
 		}
-		I915_WRITE(MG_TX2_DCC(ln, port), val);
+		I915_WRITE(MG_TX2_DCC(ln, tc_port), val);
 	}
 
 	/* Program MG_TX_PISO_READLOAD with values from vswing table */
 	for (ln = 0; ln < 2; ln++) {
-		val = I915_READ(MG_TX1_PISO_READLOAD(ln, port));
+		val = I915_READ(MG_TX1_PISO_READLOAD(ln, tc_port));
 		val |= CRI_CALCINIT;
-		I915_WRITE(MG_TX1_PISO_READLOAD(ln, port), val);
+		I915_WRITE(MG_TX1_PISO_READLOAD(ln, tc_port), val);
 
-		val = I915_READ(MG_TX2_PISO_READLOAD(ln, port));
+		val = I915_READ(MG_TX2_PISO_READLOAD(ln, tc_port));
 		val |= CRI_CALCINIT;
-		I915_WRITE(MG_TX2_PISO_READLOAD(ln, port), val);
+		I915_WRITE(MG_TX2_PISO_READLOAD(ln, tc_port), val);
 	}
 }
 
@@ -3150,8 +3150,7 @@ static void
 icl_phy_set_clock_gating(struct intel_digital_port *dig_port, bool enable)
 {
 	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	enum port port = dig_port->base.port;
-	enum tc_port tc_port = intel_port_to_tc(dev_priv, port);
+	enum tc_port tc_port = intel_port_to_tc(dev_priv, dig_port->base.port);
 	u32 val, bits;
 	int ln;
 
@@ -3167,7 +3166,7 @@ icl_phy_set_clock_gating(struct intel_digital_port *dig_port, bool enable)
 			I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, ln));
 			val = I915_READ(DKL_DP_MODE(tc_port));
 		} else {
-			val = I915_READ(MG_DP_MODE(ln, port));
+			val = I915_READ(MG_DP_MODE(ln, tc_port));
 		}
 
 		if (enable)
@@ -3178,7 +3177,7 @@ icl_phy_set_clock_gating(struct intel_digital_port *dig_port, bool enable)
 		if (INTEL_GEN(dev_priv) >= 12)
 			I915_WRITE(DKL_DP_MODE(tc_port), val);
 		else
-			I915_WRITE(MG_DP_MODE(ln, port), val);
+			I915_WRITE(MG_DP_MODE(ln, tc_port), val);
 	}
 
 	if (INTEL_GEN(dev_priv) == 11) {
@@ -3203,8 +3202,7 @@ icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port,
 		       const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
-	enum port port = intel_dig_port->base.port;
-	enum tc_port tc_port = intel_port_to_tc(dev_priv, port);
+	enum tc_port tc_port = intel_port_to_tc(dev_priv, intel_dig_port->base.port);
 	u32 ln0, ln1, pin_assignment;
 	u8 width;
 
@@ -3217,8 +3215,8 @@ icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port,
 		I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, 0x1));
 		ln1 = I915_READ(DKL_DP_MODE(tc_port));
 	} else {
-		ln0 = I915_READ(MG_DP_MODE(0, port));
-		ln1 = I915_READ(MG_DP_MODE(1, port));
+		ln0 = I915_READ(MG_DP_MODE(0, tc_port));
+		ln1 = I915_READ(MG_DP_MODE(1, tc_port));
 	}
 
 	ln0 &= ~(MG_DP_MODE_CFG_DP_X1_MODE | MG_DP_MODE_CFG_DP_X1_MODE);
@@ -3280,8 +3278,8 @@ icl_program_mg_dp_mode(struct intel_digital_port *intel_dig_port,
 		I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, 0x1));
 		I915_WRITE(DKL_DP_MODE(tc_port), ln1);
 	} else {
-		I915_WRITE(MG_DP_MODE(0, port), ln0);
-		I915_WRITE(MG_DP_MODE(1, port), ln1);
+		I915_WRITE(MG_DP_MODE(0, tc_port), ln0);
+		I915_WRITE(MG_DP_MODE(1, tc_port), ln1);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 058aa5ca8b73..eefd789b9a28 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1956,8 +1956,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define ICL_DPHY_CHKN(port)			_MMIO(_ICL_COMBOPHY(port) + _ICL_DPHY_CHKN_REG)
 #define   ICL_DPHY_CHKN_AFE_OVER_PPI_STRAP	REG_BIT(7)
 
-#define MG_PHY_PORT_LN(ln, port, ln0p1, ln0p2, ln1p1) \
-	_MMIO(_PORT((port) - PORT_C, ln0p1, ln0p2) + (ln) * ((ln1p1) - (ln0p1)))
+#define MG_PHY_PORT_LN(ln, tc_port, ln0p1, ln0p2, ln1p1) \
+	_MMIO(_PORT(tc_port, ln0p1, ln0p2) + (ln) * ((ln1p1) - (ln0p1)))
 
 #define MG_TX_LINK_PARAMS_TX1LN0_PORT1		0x16812C
 #define MG_TX_LINK_PARAMS_TX1LN1_PORT1		0x16852C
@@ -1967,10 +1967,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MG_TX_LINK_PARAMS_TX1LN1_PORT3		0x16A52C
 #define MG_TX_LINK_PARAMS_TX1LN0_PORT4		0x16B12C
 #define MG_TX_LINK_PARAMS_TX1LN1_PORT4		0x16B52C
-#define MG_TX1_LINK_PARAMS(ln, port) \
-	MG_PHY_PORT_LN(ln, port, MG_TX_LINK_PARAMS_TX1LN0_PORT1, \
-				 MG_TX_LINK_PARAMS_TX1LN0_PORT2, \
-				 MG_TX_LINK_PARAMS_TX1LN1_PORT1)
+#define MG_TX1_LINK_PARAMS(ln, tc_port) \
+	MG_PHY_PORT_LN(ln, tc_port, MG_TX_LINK_PARAMS_TX1LN0_PORT1, \
+				    MG_TX_LINK_PARAMS_TX1LN0_PORT2, \
+				    MG_TX_LINK_PARAMS_TX1LN1_PORT1)
 
 #define MG_TX_LINK_PARAMS_TX2LN0_PORT1		0x1680AC
 #define MG_TX_LINK_PARAMS_TX2LN1_PORT1		0x1684AC
@@ -1980,10 +1980,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MG_TX_LINK_PARAMS_TX2LN1_PORT3		0x16A4AC
 #define MG_TX_LINK_PARAMS_TX2LN0_PORT4		0x16B0AC
 #define MG_TX_LINK_PARAMS_TX2LN1_PORT4		0x16B4AC
-#define MG_TX2_LINK_PARAMS(ln, port) \
-	MG_PHY_PORT_LN(ln, port, MG_TX_LINK_PARAMS_TX2LN0_PORT1, \
-				 MG_TX_LINK_PARAMS_TX2LN0_PORT2, \
-				 MG_TX_LINK_PARAMS_TX2LN1_PORT1)
+#define MG_TX2_LINK_PARAMS(ln, tc_port) \
+	MG_PHY_PORT_LN(ln, tc_port, MG_TX_LINK_PARAMS_TX2LN0_PORT1, \
+				    MG_TX_LINK_PARAMS_TX2LN0_PORT2, \
+				    MG_TX_LINK_PARAMS_TX2LN1_PORT1)
 #define   CRI_USE_FS32			(1 << 5)
 
 #define MG_TX_PISO_READLOAD_TX1LN0_PORT1		0x16814C
@@ -1994,10 +1994,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MG_TX_PISO_READLOAD_TX1LN1_PORT3		0x16A54C
 #define MG_TX_PISO_READLOAD_TX1LN0_PORT4		0x16B14C
 #define MG_TX_PISO_READLOAD_TX1LN1_PORT4		0x16B54C
-#define MG_TX1_PISO_READLOAD(ln, port) \
-	MG_PHY_PORT_LN(ln, port, MG_TX_PISO_READLOAD_TX1LN0_PORT1, \
-				 MG_TX_PISO_READLOAD_TX1LN0_PORT2, \
-				 MG_TX_PISO_READLOAD_TX1LN1_PORT1)
+#define MG_TX1_PISO_READLOAD(ln, tc_port) \
+	MG_PHY_PORT_LN(ln, tc_port, MG_TX_PISO_READLOAD_TX1LN0_PORT1, \
+				    MG_TX_PISO_READLOAD_TX1LN0_PORT2, \
+				    MG_TX_PISO_READLOAD_TX1LN1_PORT1)
 
 #define MG_TX_PISO_READLOAD_TX2LN0_PORT1		0x1680CC
 #define MG_TX_PISO_READLOAD_TX2LN1_PORT1		0x1684CC
@@ -2007,10 +2007,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MG_TX_PISO_READLOAD_TX2LN1_PORT3		0x16A4CC
 #define MG_TX_PISO_READLOAD_TX2LN0_PORT4		0x16B0CC
 #define MG_TX_PISO_READLOAD_TX2LN1_PORT4		0x16B4CC
-#define MG_TX2_PISO_READLOAD(ln, port) \
-	MG_PHY_PORT_LN(ln, port, MG_TX_PISO_READLOAD_TX2LN0_PORT1, \
-				 MG_TX_PISO_READLOAD_TX2LN0_PORT2, \
-				 MG_TX_PISO_READLOAD_TX2LN1_PORT1)
+#define MG_TX2_PISO_READLOAD(ln, tc_port) \
+	MG_PHY_PORT_LN(ln, tc_port, MG_TX_PISO_READLOAD_TX2LN0_PORT1, \
+				    MG_TX_PISO_READLOAD_TX2LN0_PORT2, \
+				    MG_TX_PISO_READLOAD_TX2LN1_PORT1)
 #define   CRI_CALCINIT					(1 << 1)
 
 #define MG_TX_SWINGCTRL_TX1LN0_PORT1		0x168148
@@ -2021,10 +2021,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MG_TX_SWINGCTRL_TX1LN1_PORT3		0x16A548
 #define MG_TX_SWINGCTRL_TX1LN0_PORT4		0x16B148
 #define MG_TX_SWINGCTRL_TX1LN1_PORT4		0x16B548
-#define MG_TX1_SWINGCTRL(ln, port) \
-	MG_PHY_PORT_LN(ln, port, MG_TX_SWINGCTRL_TX1LN0_PORT1, \
-				 MG_TX_SWINGCTRL_TX1LN0_PORT2, \
-				 MG_TX_SWINGCTRL_TX1LN1_PORT1)
+#define MG_TX1_SWINGCTRL(ln, tc_port) \
+	MG_PHY_PORT_LN(ln, tc_port, MG_TX_SWINGCTRL_TX1LN0_PORT1, \
+				    MG_TX_SWINGCTRL_TX1LN0_PORT2, \
+				    MG_TX_SWINGCTRL_TX1LN1_PORT1)
 
 #define MG_TX_SWINGCTRL_TX2LN0_PORT1		0x1680C8
 #define MG_TX_SWINGCTRL_TX2LN1_PORT1		0x1684C8
@@ -2034,10 +2034,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MG_TX_SWINGCTRL_TX2LN1_PORT3		0x16A4C8
 #define MG_TX_SWINGCTRL_TX2LN0_PORT4		0x16B0C8
 #define MG_TX_SWINGCTRL_TX2LN1_PORT4		0x16B4C8
-#define MG_TX2_SWINGCTRL(ln, port) \
-	MG_PHY_PORT_LN(ln, port, MG_TX_SWINGCTRL_TX2LN0_PORT1, \
-				 MG_TX_SWINGCTRL_TX2LN0_PORT2, \
-				 MG_TX_SWINGCTRL_TX2LN1_PORT1)
+#define MG_TX2_SWINGCTRL(ln, tc_port) \
+	MG_PHY_PORT_LN(ln, tc_port, MG_TX_SWINGCTRL_TX2LN0_PORT1, \
+				    MG_TX_SWINGCTRL_TX2LN0_PORT2, \
+				    MG_TX_SWINGCTRL_TX2LN1_PORT1)
 #define   CRI_TXDEEMPH_OVERRIDE_17_12(x)		((x) << 0)
 #define   CRI_TXDEEMPH_OVERRIDE_17_12_MASK		(0x3F << 0)
 
@@ -2049,10 +2049,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MG_TX_DRVCTRL_TX1LN1_TXPORT3			0x16A544
 #define MG_TX_DRVCTRL_TX1LN0_TXPORT4			0x16B144
 #define MG_TX_DRVCTRL_TX1LN1_TXPORT4			0x16B544
-#define MG_TX1_DRVCTRL(ln, port) \
-	MG_PHY_PORT_LN(ln, port, MG_TX_DRVCTRL_TX1LN0_TXPORT1, \
-				 MG_TX_DRVCTRL_TX1LN0_TXPORT2, \
-				 MG_TX_DRVCTRL_TX1LN1_TXPORT1)
+#define MG_TX1_DRVCTRL(ln, tc_port) \
+	MG_PHY_PORT_LN(ln, tc_port, MG_TX_DRVCTRL_TX1LN0_TXPORT1, \
+				    MG_TX_DRVCTRL_TX1LN0_TXPORT2, \
+				    MG_TX_DRVCTRL_TX1LN1_TXPORT1)
 
 #define MG_TX_DRVCTRL_TX2LN0_PORT1			0x1680C4
 #define MG_TX_DRVCTRL_TX2LN1_PORT1			0x1684C4
@@ -2062,10 +2062,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MG_TX_DRVCTRL_TX2LN1_PORT3			0x16A4C4
 #define MG_TX_DRVCTRL_TX2LN0_PORT4			0x16B0C4
 #define MG_TX_DRVCTRL_TX2LN1_PORT4			0x16B4C4
-#define MG_TX2_DRVCTRL(ln, port) \
-	MG_PHY_PORT_LN(ln, port, MG_TX_DRVCTRL_TX2LN0_PORT1, \
-				 MG_TX_DRVCTRL_TX2LN0_PORT2, \
-				 MG_TX_DRVCTRL_TX2LN1_PORT1)
+#define MG_TX2_DRVCTRL(ln, tc_port) \
+	MG_PHY_PORT_LN(ln, tc_port, MG_TX_DRVCTRL_TX2LN0_PORT1, \
+				    MG_TX_DRVCTRL_TX2LN0_PORT2, \
+				    MG_TX_DRVCTRL_TX2LN1_PORT1)
 #define   CRI_TXDEEMPH_OVERRIDE_11_6(x)			((x) << 24)
 #define   CRI_TXDEEMPH_OVERRIDE_11_6_MASK		(0x3F << 24)
 #define   CRI_TXDEEMPH_OVERRIDE_EN			(1 << 22)
@@ -2082,10 +2082,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MG_CLKHUB_LN1_PORT3			0x16A79C
 #define MG_CLKHUB_LN0_PORT4			0x16B39C
 #define MG_CLKHUB_LN1_PORT4			0x16B79C
-#define MG_CLKHUB(ln, port) \
-	MG_PHY_PORT_LN(ln, port, MG_CLKHUB_LN0_PORT1, \
-				 MG_CLKHUB_LN0_PORT2, \
-				 MG_CLKHUB_LN1_PORT1)
+#define MG_CLKHUB(ln, tc_port) \
+	MG_PHY_PORT_LN(ln, tc_port, MG_CLKHUB_LN0_PORT1, \
+				    MG_CLKHUB_LN0_PORT2, \
+				    MG_CLKHUB_LN1_PORT1)
 #define   CFG_LOW_RATE_LKREN_EN				(1 << 11)
 
 #define MG_TX_DCC_TX1LN0_PORT1			0x168110
@@ -2096,10 +2096,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MG_TX_DCC_TX1LN1_PORT3			0x16A510
 #define MG_TX_DCC_TX1LN0_PORT4			0x16B110
 #define MG_TX_DCC_TX1LN1_PORT4			0x16B510
-#define MG_TX1_DCC(ln, port) \
-	MG_PHY_PORT_LN(ln, port, MG_TX_DCC_TX1LN0_PORT1, \
-				 MG_TX_DCC_TX1LN0_PORT2, \
-				 MG_TX_DCC_TX1LN1_PORT1)
+#define MG_TX1_DCC(ln, tc_port) \
+	MG_PHY_PORT_LN(ln, tc_port, MG_TX_DCC_TX1LN0_PORT1, \
+				    MG_TX_DCC_TX1LN0_PORT2, \
+				    MG_TX_DCC_TX1LN1_PORT1)
 #define MG_TX_DCC_TX2LN0_PORT1			0x168090
 #define MG_TX_DCC_TX2LN1_PORT1			0x168490
 #define MG_TX_DCC_TX2LN0_PORT2			0x169090
@@ -2108,10 +2108,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MG_TX_DCC_TX2LN1_PORT3			0x16A490
 #define MG_TX_DCC_TX2LN0_PORT4			0x16B090
 #define MG_TX_DCC_TX2LN1_PORT4			0x16B490
-#define MG_TX2_DCC(ln, port) \
-	MG_PHY_PORT_LN(ln, port, MG_TX_DCC_TX2LN0_PORT1, \
-				 MG_TX_DCC_TX2LN0_PORT2, \
-				 MG_TX_DCC_TX2LN1_PORT1)
+#define MG_TX2_DCC(ln, tc_port) \
+	MG_PHY_PORT_LN(ln, tc_port, MG_TX_DCC_TX2LN0_PORT1, \
+				    MG_TX_DCC_TX2LN0_PORT2, \
+				    MG_TX_DCC_TX2LN1_PORT1)
 #define   CFG_AMI_CK_DIV_OVERRIDE_VAL(x)	((x) << 25)
 #define   CFG_AMI_CK_DIV_OVERRIDE_VAL_MASK	(0x3 << 25)
 #define   CFG_AMI_CK_DIV_OVERRIDE_EN		(1 << 24)
@@ -2124,10 +2124,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MG_DP_MODE_LN1_ACU_PORT3			0x16A7A0
 #define MG_DP_MODE_LN0_ACU_PORT4			0x16B3A0
 #define MG_DP_MODE_LN1_ACU_PORT4			0x16B7A0
-#define MG_DP_MODE(ln, port)	\
-	MG_PHY_PORT_LN(ln, port, MG_DP_MODE_LN0_ACU_PORT1, \
-				 MG_DP_MODE_LN0_ACU_PORT2, \
-				 MG_DP_MODE_LN1_ACU_PORT1)
+#define MG_DP_MODE(ln, tc_port)	\
+	MG_PHY_PORT_LN(ln, tc_port, MG_DP_MODE_LN0_ACU_PORT1, \
+				    MG_DP_MODE_LN0_ACU_PORT2, \
+				    MG_DP_MODE_LN1_ACU_PORT1)
 #define   MG_DP_MODE_CFG_DP_X2_MODE			(1 << 7)
 #define   MG_DP_MODE_CFG_DP_X1_MODE			(1 << 6)
 #define   MG_DP_MODE_CFG_TR2PWR_GATING			(1 << 5)
-- 
cgit v1.2.3


From e2973352fa1390c9a40d8a23c8c143dadd0c028c Mon Sep 17 00:00:00 2001
From: Maxime Ripard <mripard@kernel.org>
Date: Wed, 2 Oct 2019 16:42:04 +0200
Subject: dt-bindings: dsp: Fix fsl,dsp example

The fsl,dsp binding requires a memory-region, yet its example doesn't have
one which results in a warning. Let's add a memory-region phandle to the
example.

Fixes: 7db2f2dfc701 ("dt-bindings: dsp: fsl: Add DSP core binding support")
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/dsp/fsl,dsp.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml b/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml
index 3248595dc93c..f04870d84542 100644
--- a/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml
+++ b/Documentation/devicetree/bindings/dsp/fsl,dsp.yaml
@@ -85,4 +85,5 @@ examples:
                         <&pd IMX_SC_R_DSP_RAM>;
         mbox-names = "txdb0", "txdb1", "rxdb0", "rxdb1";
         mboxes = <&lsio_mu13 2 0>, <&lsio_mu13 2 1>, <&lsio_mu13 3 0>, <&lsio_mu13 3 1>;
+        memory-region = <&dsp_reserved>;
     };
-- 
cgit v1.2.3


From 58c50fe0c9f02f4065349b7ddefbb9899c589396 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <mripard@kernel.org>
Date: Wed, 2 Oct 2019 16:44:00 +0200
Subject: dt-bindings: media: rc: Fix redundant string

The linux,rc-map-name property is described using an enum, yet a value has
been put in that enum twice, resulting in a warning. Let's fix that.

Fixes: 7c31b9d67342 ("media: dt-bindings: media: Add YAML schemas for the generic RC bindings")
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/media/rc.yaml | 1 -
 1 file changed, 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/media/rc.yaml b/Documentation/devicetree/bindings/media/rc.yaml
index 3d5c154fd230..9054555e6608 100644
--- a/Documentation/devicetree/bindings/media/rc.yaml
+++ b/Documentation/devicetree/bindings/media/rc.yaml
@@ -73,7 +73,6 @@ properties:
           - rc-genius-tvgo-a11mce
           - rc-gotview7135
           - rc-hauppauge
-          - rc-hauppauge
           - rc-hisi-poplar
           - rc-hisi-tv-demo
           - rc-imon-mce
-- 
cgit v1.2.3


From 932bae3a5b4e9b9a40133e4dc989c2099f3d1823 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <mripard@kernel.org>
Date: Wed, 2 Oct 2019 16:45:41 +0200
Subject: dt-bindings: iio: ad7192: Fix Regulator Properties

The AD7192 binding describes two regulator properties, avdd-supply and
dvdd-supply, but describes it as a constant string that must be avdd and
dvdd. This is wrong since a *-supply property is actually a phandle, and
results in warnings when the example is validated (or any device tree using
that device, for that matter).

Let's remove that requirement.

Fixes: f7356e47032c ("dt-bindings: iio: adc: ad7192: Add binding documentation for AD7192")
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
index 676ec42e1438..9e62f54c891a 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
@@ -43,13 +43,9 @@ properties:
 
   dvdd-supply:
     description: DVdd voltage supply
-    items:
-      - const: dvdd
 
   avdd-supply:
     description: AVdd voltage supply
-    items:
-      - const: avdd
 
   adi,rejection-60-Hz-enable:
     description: |
-- 
cgit v1.2.3


From 4d32db74a3cafa9c96608265db6c40317040df41 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <mripard@kernel.org>
Date: Wed, 2 Oct 2019 16:45:42 +0200
Subject: dt-bindings: iio: ad7192: Fix DTC warning in the example

The example contains an SPI bus and device, but doesn't have the
appropriate size and address cells size.

This creates a DTC warning when the example is compiled since the default
ones will not match what the device uses. Let's add them to remove that
warning.

Fixes: f7356e47032c ("dt-bindings: iio: adc: ad7192: Add binding documentation for AD7192")
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
index 9e62f54c891a..567a33a83dce 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7192.yaml
@@ -95,6 +95,9 @@ required:
 examples:
   - |
     spi0 {
+      #address-cells = <1>;
+      #size-cells = <0>;
+
       adc@0 {
         compatible = "adi,ad7192";
         reg = <0>;
-- 
cgit v1.2.3


From f437ade3296bacaddb6d7882ba0515940f01daf4 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <mripard@kernel.org>
Date: Wed, 2 Oct 2019 16:46:40 +0200
Subject: dt-bindings: phy: lantiq: Fix Property Name

The binding has a typo where resets-names should read reset-names, which in
turn leads to a warning when the example is validated, since reset-names is
being used, and the binding prevent the usage of any property that isn't
described.

Fixes: 088e88be5a38 ("dt-bindings: phy: add binding for the Lantiq VRX200 and ARX300 PCIe PHYs")
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml
index 8a56a8526cef..a97482179cf5 100644
--- a/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/lantiq,vrx200-pcie-phy.yaml
@@ -37,7 +37,7 @@ properties:
       - description: exclusive PHY reset line
       - description: shared reset line between the PCIe PHY and PCIe controller
 
-  resets-names:
+  reset-names:
     items:
       - const: phy
       - const: pcie
-- 
cgit v1.2.3


From 8f9577eda5b74de4bd8b186c67f20736bdea6e07 Mon Sep 17 00:00:00 2001
From: "George G. Davis" <george_davis@mentor.com>
Date: Tue, 17 Sep 2019 20:40:22 +0200
Subject: selftests: watchdog: Validate optional file argument

The newly added optional file argument does not validate if the
file is indeed a watchdog, e.g.:

./watchdog-test  -f /dev/zero
Watchdog Ticking Away!

Fix it by confirming that the WDIOC_GETSUPPORT ioctl succeeds.

Fixes: a4864a33f56caa ("selftests: watchdog: Add optional file argument")
Reported-by: Eugeniu Rosca <erosca@de.adit-jv.com>
Signed-off-by: George G. Davis <george_davis@mentor.com>
Signed-off-by: Eugeniu Rosca <erosca@de.adit-jv.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/selftests/watchdog/watchdog-test.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index afff120c7be6..6ed822dc2222 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -97,6 +97,7 @@ int main(int argc, char *argv[])
 	int c;
 	int oneshot = 0;
 	char *file = "/dev/watchdog";
+	struct watchdog_info info;
 
 	setbuf(stdout, NULL);
 
@@ -118,6 +119,16 @@ int main(int argc, char *argv[])
 		exit(-1);
 	}
 
+	/*
+	 * Validate that `file` is a watchdog device
+	 */
+	ret = ioctl(fd, WDIOC_GETSUPPORT, &info);
+	if (ret) {
+		printf("WDIOC_GETSUPPORT error '%s'\n", strerror(errno));
+		close(fd);
+		exit(ret);
+	}
+
 	optind = 0;
 
 	while ((c = getopt_long(argc, argv, sopts, lopts, NULL)) != -1) {
-- 
cgit v1.2.3


From ce3a677802121e038d2f062e90f96f84e7351da0 Mon Sep 17 00:00:00 2001
From: "George G. Davis" <george_davis@mentor.com>
Date: Tue, 17 Sep 2019 20:40:23 +0200
Subject: selftests: watchdog: Add command line option to show watchdog_info

With the new ioctl(WDIOC_GETSUPPORT) call in place, add a command
line option to show the watchdog_info.

Suggested-by: Eugeniu Rosca <erosca@de.adit-jv.com>
Signed-off-by: George G. Davis <george_davis@mentor.com>
Signed-off-by: Eugeniu Rosca <erosca@de.adit-jv.com>
Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
---
 tools/testing/selftests/watchdog/watchdog-test.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/watchdog/watchdog-test.c b/tools/testing/selftests/watchdog/watchdog-test.c
index 6ed822dc2222..f45e510500c0 100644
--- a/tools/testing/selftests/watchdog/watchdog-test.c
+++ b/tools/testing/selftests/watchdog/watchdog-test.c
@@ -19,7 +19,7 @@
 
 int fd;
 const char v = 'V';
-static const char sopts[] = "bdehp:t:Tn:NLf:";
+static const char sopts[] = "bdehp:t:Tn:NLf:i";
 static const struct option lopts[] = {
 	{"bootstatus",          no_argument, NULL, 'b'},
 	{"disable",             no_argument, NULL, 'd'},
@@ -32,6 +32,7 @@ static const struct option lopts[] = {
 	{"getpretimeout",       no_argument, NULL, 'N'},
 	{"gettimeleft",		no_argument, NULL, 'L'},
 	{"file",          required_argument, NULL, 'f'},
+	{"info",		no_argument, NULL, 'i'},
 	{NULL,                  no_argument, NULL, 0x0}
 };
 
@@ -72,6 +73,7 @@ static void usage(char *progname)
 	printf("Usage: %s [options]\n", progname);
 	printf(" -f, --file\t\tOpen watchdog device file\n");
 	printf("\t\t\tDefault is /dev/watchdog\n");
+	printf(" -i, --info\t\tShow watchdog_info\n");
 	printf(" -b, --bootstatus\tGet last boot status (Watchdog/POR)\n");
 	printf(" -d, --disable\t\tTurn off the watchdog timer\n");
 	printf(" -e, --enable\t\tTurn on the watchdog timer\n");
@@ -216,6 +218,18 @@ int main(int argc, char *argv[])
 		case 'f':
 			/* Handled above */
 			break;
+		case 'i':
+			/*
+			 * watchdog_info was obtained as part of file open
+			 * validation. So we just show it here.
+			 */
+			oneshot = 1;
+			printf("watchdog_info:\n");
+			printf(" identity:\t\t%s\n", info.identity);
+			printf(" firmware_version:\t%u\n",
+			       info.firmware_version);
+			printf(" options:\t\t%08x\n", info.options);
+			break;
 
 		default:
 			usage(argv[0]);
-- 
cgit v1.2.3


From a8fabb38525c51a094607768bac3ba46b3f4a9d5 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Tue, 1 Oct 2019 17:03:55 +0200
Subject: xen/xenbus: fix self-deadlock after killing user process

In case a user process using xenbus has open transactions and is killed
e.g. via ctrl-C the following cleanup of the allocated resources might
result in a deadlock due to trying to end a transaction in the xenbus
worker thread:

[ 2551.474706] INFO: task xenbus:37 blocked for more than 120 seconds.
[ 2551.492215]       Tainted: P           OE     5.0.0-29-generic #5
[ 2551.510263] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 2551.528585] xenbus          D    0    37      2 0x80000080
[ 2551.528590] Call Trace:
[ 2551.528603]  __schedule+0x2c0/0x870
[ 2551.528606]  ? _cond_resched+0x19/0x40
[ 2551.528632]  schedule+0x2c/0x70
[ 2551.528637]  xs_talkv+0x1ec/0x2b0
[ 2551.528642]  ? wait_woken+0x80/0x80
[ 2551.528645]  xs_single+0x53/0x80
[ 2551.528648]  xenbus_transaction_end+0x3b/0x70
[ 2551.528651]  xenbus_file_free+0x5a/0x160
[ 2551.528654]  xenbus_dev_queue_reply+0xc4/0x220
[ 2551.528657]  xenbus_thread+0x7de/0x880
[ 2551.528660]  ? wait_woken+0x80/0x80
[ 2551.528665]  kthread+0x121/0x140
[ 2551.528667]  ? xb_read+0x1d0/0x1d0
[ 2551.528670]  ? kthread_park+0x90/0x90
[ 2551.528673]  ret_from_fork+0x35/0x40

Fix this by doing the cleanup via a workqueue instead.

Reported-by: James Dingwall <james@dingwall.me.uk>
Fixes: fd8aa9095a95c ("xen: optimize xenbus driver for multiple concurrent xenstore accesses")
Cc: <stable@vger.kernel.org> # 4.11
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/xenbus/xenbus_dev_frontend.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 08adc590f631..597af455a522 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -55,6 +55,7 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/miscdevice.h>
+#include <linux/workqueue.h>
 
 #include <xen/xenbus.h>
 #include <xen/xen.h>
@@ -116,6 +117,8 @@ struct xenbus_file_priv {
 	wait_queue_head_t read_waitq;
 
 	struct kref kref;
+
+	struct work_struct wq;
 };
 
 /* Read out any raw xenbus messages queued up. */
@@ -300,14 +303,14 @@ static void watch_fired(struct xenbus_watch *watch,
 	mutex_unlock(&adap->dev_data->reply_mutex);
 }
 
-static void xenbus_file_free(struct kref *kref)
+static void xenbus_worker(struct work_struct *wq)
 {
 	struct xenbus_file_priv *u;
 	struct xenbus_transaction_holder *trans, *tmp;
 	struct watch_adapter *watch, *tmp_watch;
 	struct read_buffer *rb, *tmp_rb;
 
-	u = container_of(kref, struct xenbus_file_priv, kref);
+	u = container_of(wq, struct xenbus_file_priv, wq);
 
 	/*
 	 * No need for locking here because there are no other users,
@@ -333,6 +336,18 @@ static void xenbus_file_free(struct kref *kref)
 	kfree(u);
 }
 
+static void xenbus_file_free(struct kref *kref)
+{
+	struct xenbus_file_priv *u;
+
+	/*
+	 * We might be called in xenbus_thread().
+	 * Use workqueue to avoid deadlock.
+	 */
+	u = container_of(kref, struct xenbus_file_priv, kref);
+	schedule_work(&u->wq);
+}
+
 static struct xenbus_transaction_holder *xenbus_get_transaction(
 	struct xenbus_file_priv *u, uint32_t tx_id)
 {
@@ -650,6 +665,7 @@ static int xenbus_file_open(struct inode *inode, struct file *filp)
 	INIT_LIST_HEAD(&u->watches);
 	INIT_LIST_HEAD(&u->read_buffers);
 	init_waitqueue_head(&u->read_waitq);
+	INIT_WORK(&u->wq, xenbus_worker);
 
 	mutex_init(&u->reply_mutex);
 	mutex_init(&u->msgbuffer_mutex);
-- 
cgit v1.2.3


From 3fd57e7a9e66b9a8bcbf0560ff09e84d0b8de1bd Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@alien8.de>
Date: Tue, 1 Oct 2019 19:50:23 +0200
Subject: char/random: Add a newline at the end of the file

On Tue, Oct 01, 2019 at 10:14:40AM -0700, Linus Torvalds wrote:
> The previous state of the file didn't have that 0xa at the end, so you get that
>
>
>   -EXPORT_SYMBOL_GPL(add_bootloader_randomness);
>   \ No newline at end of file
>   +EXPORT_SYMBOL_GPL(add_bootloader_randomness);
>
> which is "the '-' line doesn't have a newline, the '+' line does" marker.

Aaha, that makes total sense, thanks for explaining. Oh well, let's fix
it then so that people don't scratch heads like me.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/char/random.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index c2f7de9dc543..de434feb873a 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -2520,4 +2520,4 @@ void add_bootloader_randomness(const void *buf, unsigned int size)
 	else
 		add_device_randomness(buf, size);
 }
-EXPORT_SYMBOL_GPL(add_bootloader_randomness);
\ No newline at end of file
+EXPORT_SYMBOL_GPL(add_bootloader_randomness);
-- 
cgit v1.2.3


From afce285b859cea91c182015fc9858ea58c26cd0e Mon Sep 17 00:00:00 2001
From: Marco Felsch <m.felsch@pengutronix.de>
Date: Mon, 16 Sep 2019 12:45:48 -0700
Subject: Input: da9063 - fix capability and drop KEY_SLEEP

Since commit f889beaaab1c ("Input: da9063 - report KEY_POWER instead of
KEY_SLEEP during power key-press") KEY_SLEEP isn't supported anymore. This
caused input device to not generate any events if "dlg,disable-key-power"
is set.

Fix this by unconditionally setting KEY_POWER capability, and not
declaring KEY_SLEEP.

Fixes: f889beaaab1c ("Input: da9063 - report KEY_POWER instead of KEY_SLEEP during power key-press")
Signed-off-by: Marco Felsch <m.felsch@pengutronix.de>
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/da9063_onkey.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/input/misc/da9063_onkey.c b/drivers/input/misc/da9063_onkey.c
index dace8577fa43..79851923ee57 100644
--- a/drivers/input/misc/da9063_onkey.c
+++ b/drivers/input/misc/da9063_onkey.c
@@ -232,10 +232,7 @@ static int da9063_onkey_probe(struct platform_device *pdev)
 	onkey->input->phys = onkey->phys;
 	onkey->input->dev.parent = &pdev->dev;
 
-	if (onkey->key_power)
-		input_set_capability(onkey->input, EV_KEY, KEY_POWER);
-
-	input_set_capability(onkey->input, EV_KEY, KEY_SLEEP);
+	input_set_capability(onkey->input, EV_KEY, KEY_POWER);
 
 	INIT_DELAYED_WORK(&onkey->work, da9063_poll_on);
 
-- 
cgit v1.2.3


From 0671c5b84e9e0a6d42d22da9b5d093787ac1c5f3 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Wed, 2 Oct 2019 18:59:49 +0000
Subject: MIPS: Wire up clone3 syscall

Wire up the new clone3 syscall for MIPS, using save_static_function() to
generate a wrapper that saves registers $s0-$s7 prior to invoking the
generic sys_clone3 function just like we do for plain old clone.

Tested atop 64r6el_defconfig using o32, n32 & n64 builds of the simple
test program from:

  https://lore.kernel.org/lkml/20190716130631.tohj4ub54md25dys@brauner.io/

Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Christian Brauner <christian@brauner.io>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Cc: linux-mips@vger.kernel.org
---
 arch/mips/include/asm/unistd.h            | 1 +
 arch/mips/kernel/syscall.c                | 1 +
 arch/mips/kernel/syscalls/syscall_n32.tbl | 2 +-
 arch/mips/kernel/syscalls/syscall_n64.tbl | 2 +-
 arch/mips/kernel/syscalls/syscall_o32.tbl | 2 +-
 5 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index 071053ece677..5d70babfc9ee 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -52,6 +52,7 @@
 # endif
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
 
 /* whitelists for checksyscalls */
 #define __IGNORE_fadvise64_64
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index b0e25e913bdb..3f16f3823031 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -80,6 +80,7 @@ SYSCALL_DEFINE6(mips_mmap2, unsigned long, addr, unsigned long, len,
 
 save_static_function(sys_fork);
 save_static_function(sys_clone);
+save_static_function(sys_clone3);
 
 SYSCALL_DEFINE1(set_thread_area, unsigned long, addr)
 {
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index c9c879ec9b6d..e7c5ab38e403 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -373,4 +373,4 @@
 432	n32	fsmount				sys_fsmount
 433	n32	fspick				sys_fspick
 434	n32	pidfd_open			sys_pidfd_open
-# 435 reserved for clone3
+435	n32	clone3				__sys_clone3
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index bbce9159caa1..13cd66581f3b 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -349,4 +349,4 @@
 432	n64	fsmount				sys_fsmount
 433	n64	fspick				sys_fspick
 434	n64	pidfd_open			sys_pidfd_open
-# 435 reserved for clone3
+435	n64	clone3				__sys_clone3
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 9653591428ec..353539ea4140 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -422,4 +422,4 @@
 432	o32	fsmount				sys_fsmount
 433	o32	fspick				sys_fspick
 434	o32	pidfd_open			sys_pidfd_open
-# 435 reserved for clone3
+435	o32	clone3				__sys_clone3
-- 
cgit v1.2.3


From 90800281e761247d8096ab213c10d638602655f9 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Wed, 2 Oct 2019 17:46:17 +0000
Subject: MIPS: VDSO: Remove unused gettimeofday.c

arch/mips/vdso/gettimeofday.c has been unused since commit 24640f233b46
("mips: Add support for generic vDSO"). Remove the dead code.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Fixes: 24640f233b46 ("mips: Add support for generic vDSO")
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: linux-mips@vger.kernel.org
---
 arch/mips/vdso/gettimeofday.c | 269 ------------------------------------------
 1 file changed, 269 deletions(-)
 delete mode 100644 arch/mips/vdso/gettimeofday.c

diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c
deleted file mode 100644
index e8243c7fd5b5..000000000000
--- a/arch/mips/vdso/gettimeofday.c
+++ /dev/null
@@ -1,269 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2015 Imagination Technologies
- * Author: Alex Smith <alex.smith@imgtec.com>
- */
-
-#include "vdso.h"
-
-#include <linux/compiler.h>
-#include <linux/time.h>
-
-#include <asm/clocksource.h>
-#include <asm/io.h>
-#include <asm/unistd.h>
-#include <asm/vdso.h>
-
-#ifdef CONFIG_MIPS_CLOCK_VSYSCALL
-
-static __always_inline long gettimeofday_fallback(struct timeval *_tv,
-					  struct timezone *_tz)
-{
-	register struct timezone *tz asm("a1") = _tz;
-	register struct timeval *tv asm("a0") = _tv;
-	register long ret asm("v0");
-	register long nr asm("v0") = __NR_gettimeofday;
-	register long error asm("a3");
-
-	asm volatile(
-	"       syscall\n"
-	: "=r" (ret), "=r" (error)
-	: "r" (tv), "r" (tz), "r" (nr)
-	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
-	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
-
-	return error ? -ret : ret;
-}
-
-#endif
-
-static __always_inline long clock_gettime_fallback(clockid_t _clkid,
-					   struct timespec *_ts)
-{
-	register struct timespec *ts asm("a1") = _ts;
-	register clockid_t clkid asm("a0") = _clkid;
-	register long ret asm("v0");
-	register long nr asm("v0") = __NR_clock_gettime;
-	register long error asm("a3");
-
-	asm volatile(
-	"       syscall\n"
-	: "=r" (ret), "=r" (error)
-	: "r" (clkid), "r" (ts), "r" (nr)
-	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
-	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
-
-	return error ? -ret : ret;
-}
-
-static __always_inline int do_realtime_coarse(struct timespec *ts,
-					      const union mips_vdso_data *data)
-{
-	u32 start_seq;
-
-	do {
-		start_seq = vdso_data_read_begin(data);
-
-		ts->tv_sec = data->xtime_sec;
-		ts->tv_nsec = data->xtime_nsec >> data->cs_shift;
-	} while (vdso_data_read_retry(data, start_seq));
-
-	return 0;
-}
-
-static __always_inline int do_monotonic_coarse(struct timespec *ts,
-					       const union mips_vdso_data *data)
-{
-	u32 start_seq;
-	u64 to_mono_sec;
-	u64 to_mono_nsec;
-
-	do {
-		start_seq = vdso_data_read_begin(data);
-
-		ts->tv_sec = data->xtime_sec;
-		ts->tv_nsec = data->xtime_nsec >> data->cs_shift;
-
-		to_mono_sec = data->wall_to_mono_sec;
-		to_mono_nsec = data->wall_to_mono_nsec;
-	} while (vdso_data_read_retry(data, start_seq));
-
-	ts->tv_sec += to_mono_sec;
-	timespec_add_ns(ts, to_mono_nsec);
-
-	return 0;
-}
-
-#ifdef CONFIG_CSRC_R4K
-
-static __always_inline u64 read_r4k_count(void)
-{
-	unsigned int count;
-
-	__asm__ __volatile__(
-	"	.set push\n"
-	"	.set mips32r2\n"
-	"	rdhwr	%0, $2\n"
-	"	.set pop\n"
-	: "=r" (count));
-
-	return count;
-}
-
-#endif
-
-#ifdef CONFIG_CLKSRC_MIPS_GIC
-
-static __always_inline u64 read_gic_count(const union mips_vdso_data *data)
-{
-	void __iomem *gic = get_gic(data);
-	u32 hi, hi2, lo;
-
-	do {
-		hi = __raw_readl(gic + sizeof(lo));
-		lo = __raw_readl(gic);
-		hi2 = __raw_readl(gic + sizeof(lo));
-	} while (hi2 != hi);
-
-	return (((u64)hi) << 32) + lo;
-}
-
-#endif
-
-static __always_inline u64 get_ns(const union mips_vdso_data *data)
-{
-	u64 cycle_now, delta, nsec;
-
-	switch (data->clock_mode) {
-#ifdef CONFIG_CSRC_R4K
-	case VDSO_CLOCK_R4K:
-		cycle_now = read_r4k_count();
-		break;
-#endif
-#ifdef CONFIG_CLKSRC_MIPS_GIC
-	case VDSO_CLOCK_GIC:
-		cycle_now = read_gic_count(data);
-		break;
-#endif
-	default:
-		return 0;
-	}
-
-	delta = (cycle_now - data->cs_cycle_last) & data->cs_mask;
-
-	nsec = (delta * data->cs_mult) + data->xtime_nsec;
-	nsec >>= data->cs_shift;
-
-	return nsec;
-}
-
-static __always_inline int do_realtime(struct timespec *ts,
-				       const union mips_vdso_data *data)
-{
-	u32 start_seq;
-	u64 ns;
-
-	do {
-		start_seq = vdso_data_read_begin(data);
-
-		if (data->clock_mode == VDSO_CLOCK_NONE)
-			return -ENOSYS;
-
-		ts->tv_sec = data->xtime_sec;
-		ns = get_ns(data);
-	} while (vdso_data_read_retry(data, start_seq));
-
-	ts->tv_nsec = 0;
-	timespec_add_ns(ts, ns);
-
-	return 0;
-}
-
-static __always_inline int do_monotonic(struct timespec *ts,
-					const union mips_vdso_data *data)
-{
-	u32 start_seq;
-	u64 ns;
-	u64 to_mono_sec;
-	u64 to_mono_nsec;
-
-	do {
-		start_seq = vdso_data_read_begin(data);
-
-		if (data->clock_mode == VDSO_CLOCK_NONE)
-			return -ENOSYS;
-
-		ts->tv_sec = data->xtime_sec;
-		ns = get_ns(data);
-
-		to_mono_sec = data->wall_to_mono_sec;
-		to_mono_nsec = data->wall_to_mono_nsec;
-	} while (vdso_data_read_retry(data, start_seq));
-
-	ts->tv_sec += to_mono_sec;
-	ts->tv_nsec = 0;
-	timespec_add_ns(ts, ns + to_mono_nsec);
-
-	return 0;
-}
-
-#ifdef CONFIG_MIPS_CLOCK_VSYSCALL
-
-/*
- * This is behind the ifdef so that we don't provide the symbol when there's no
- * possibility of there being a usable clocksource, because there's nothing we
- * can do without it. When libc fails the symbol lookup it should fall back on
- * the standard syscall path.
- */
-int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
-{
-	const union mips_vdso_data *data = get_vdso_data();
-	struct timespec ts;
-	int ret;
-
-	ret = do_realtime(&ts, data);
-	if (ret)
-		return gettimeofday_fallback(tv, tz);
-
-	if (tv) {
-		tv->tv_sec = ts.tv_sec;
-		tv->tv_usec = ts.tv_nsec / 1000;
-	}
-
-	if (tz) {
-		tz->tz_minuteswest = data->tz_minuteswest;
-		tz->tz_dsttime = data->tz_dsttime;
-	}
-
-	return 0;
-}
-
-#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */
-
-int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts)
-{
-	const union mips_vdso_data *data = get_vdso_data();
-	int ret = -1;
-
-	switch (clkid) {
-	case CLOCK_REALTIME_COARSE:
-		ret = do_realtime_coarse(ts, data);
-		break;
-	case CLOCK_MONOTONIC_COARSE:
-		ret = do_monotonic_coarse(ts, data);
-		break;
-	case CLOCK_REALTIME:
-		ret = do_realtime(ts, data);
-		break;
-	case CLOCK_MONOTONIC:
-		ret = do_monotonic(ts, data);
-		break;
-	default:
-		break;
-	}
-
-	if (ret)
-		ret = clock_gettime_fallback(clkid, ts);
-
-	return ret;
-}
-- 
cgit v1.2.3


From 8919975b617197ebe39290d379caa02caf6bf3e3 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Wed, 2 Oct 2019 17:46:36 +0000
Subject: MIPS: VDSO: Fix build for binutils < 2.25

Versions of binutils prior to 2.25 are unable to link our VDSO due to an
unsupported R_MIPS_PC32 relocation generated by the ".word _start - ."
line of the inline asm in get_vdso_base(). As such, the intent is that
when building with binutils older than 2.25 we don't build code for
gettimeofday() & friends in the VDSO that rely upon get_vdso_base().

Commit 24640f233b46 ("mips: Add support for generic vDSO") converted us
to using generic VDSO infrastructure, and as part of that the
gettimeofday() functionality moved to a new vgettimeofday.c file. The
check for binutils < 2.25 wasn't updated to handle this new filename,
and so it continues trying to remove the old unused filename from the
build. The end result is that we try to include the gettimeofday() code
in builds that will fail to link.

Fix this by updating the binutils < 2.25 case to remove vgettimeofday.c
from obj-vdso-y, rather than gettimeofday.c.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Fixes: 24640f233b46 ("mips: Add support for generic vDSO")
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: linux-mips@vger.kernel.org
---
 arch/mips/vdso/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index 69cfa0a5339e..807f0f782f75 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -59,7 +59,7 @@ CFLAGS_REMOVE_vgettimeofday.o = -pg
 ifndef CONFIG_CPU_MIPSR6
   ifeq ($(call ld-ifversion, -lt, 225000000, y),y)
     $(warning MIPS VDSO requires binutils >= 2.25)
-    obj-vdso-y := $(filter-out gettimeofday.o, $(obj-vdso-y))
+    obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y))
     ccflags-vdso += -DDISABLE_MIPS_VDSO
   endif
 endif
-- 
cgit v1.2.3


From 66b416ee41ed7a8216e5234a96288dbb8124e4b6 Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Tue, 24 Sep 2019 17:19:56 +0200
Subject: MIPS: init: Fix reservation of memory between PHYS_OFFSET and mem
 start

Fix calculation of the size for reserving memory between PHYS_OFFSET
and real memory start.

Fixes: a94e4f24ec83 ("MIPS: init: Drop boot_mem_map")
Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/kernel/setup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index b8249c233754..f5c6b4c6de24 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -321,7 +321,7 @@ static void __init bootmem_init(void)
 	 * Reserve any memory between the start of RAM and PHYS_OFFSET
 	 */
 	if (ramstart > PHYS_OFFSET)
-		memblock_reserve(PHYS_OFFSET, PFN_UP(ramstart) - PHYS_OFFSET);
+		memblock_reserve(PHYS_OFFSET, ramstart - PHYS_OFFSET);
 
 	if (PFN_UP(ramstart) > ARCH_PFN_OFFSET) {
 		pr_info("Wasting %lu bytes for tracking %lu unused pages\n",
-- 
cgit v1.2.3


From bd848d1b9235d027e65fcc87de26cc1b02b41cc8 Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Tue, 24 Sep 2019 17:20:51 +0200
Subject: MIPS: init: Prevent adding memory before PHYS_OFFSET

On some SGI machines (IP28 and IP30) a small region of memory is mirrored
to pyhsical address 0 for exception vectors while rest of the memory
is reachable at a higher physical address. ARC PROM marks this
region as reserved, but with commit a94e4f24ec83 ("MIPS: init: Drop
boot_mem_map") this chunk is used, when searching for start of ram,
which breaks at least IP28 and IP30 machines. To fix this
add_region_memory() checks for start address < PHYS_OFFSET and ignores
these chunks.

Fixes: a94e4f24ec83 ("MIPS: init: Drop boot_mem_map")
Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/kernel/setup.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index f5c6b4c6de24..5eec13b8d222 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -108,6 +108,9 @@ void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type)
 		return;
 	}
 
+	if (start < PHYS_OFFSET)
+		return;
+
 	memblock_add(start, size);
 	/* Reserve any memory except the ordinary RAM ranges. */
 	switch (type) {
-- 
cgit v1.2.3


From bd3b8480237680b5967aee3c814b92b2fd87a582 Mon Sep 17 00:00:00 2001
From: Yauhen Kharuzhy <jekhor@gmail.com>
Date: Mon, 16 Sep 2019 16:32:24 -0700
Subject: Input: goodix - add support for 9-bytes reports

Some variants of Goodix touchscreen firmwares use 9-bytes finger
report format instead of common 8-bytes format.

This report format may be present as:

struct goodix_contact_data {
        uint8_t unknown1;
        uint8_t track_id;
        uint8_t unknown2;
        uint16_t x;
        uint16_t y;
        uint16_t w;
}__attribute__((packed));

Add support for such format and use it for Lenovo Yoga Book notebook
(which uses a Goodix touchpad as a touch keyboard).

Signed-off-by: Yauhen Kharuzhy <jekhor@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/goodix.c | 58 ++++++++++++++++++++++++++++++++------
 1 file changed, 50 insertions(+), 8 deletions(-)

diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index 5178ea8b5f30..fb43aa708660 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -53,6 +53,7 @@ struct goodix_ts_data {
 	const char *cfg_name;
 	struct completion firmware_loading_complete;
 	unsigned long irq_flags;
+	unsigned int contact_size;
 };
 
 #define GOODIX_GPIO_INT_NAME		"irq"
@@ -62,6 +63,7 @@ struct goodix_ts_data {
 #define GOODIX_MAX_WIDTH		4096
 #define GOODIX_INT_TRIGGER		1
 #define GOODIX_CONTACT_SIZE		8
+#define GOODIX_MAX_CONTACT_SIZE		9
 #define GOODIX_MAX_CONTACTS		10
 
 #define GOODIX_CONFIG_MAX_LENGTH	240
@@ -144,6 +146,19 @@ static const struct dmi_system_id rotated_screen[] = {
 	{}
 };
 
+static const struct dmi_system_id nine_bytes_report[] = {
+#if defined(CONFIG_DMI) && defined(CONFIG_X86)
+	{
+		.ident = "Lenovo YogaBook",
+		/* YB1-X91L/F and YB1-X90L/F */
+		.matches = {
+			DMI_MATCH(DMI_PRODUCT_NAME, "Lenovo YB1-X9")
+		}
+	},
+#endif
+	{}
+};
+
 /**
  * goodix_i2c_read - read data from a register of the i2c slave device.
  *
@@ -249,7 +264,7 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data)
 	max_timeout = jiffies + msecs_to_jiffies(GOODIX_BUFFER_STATUS_TIMEOUT);
 	do {
 		error = goodix_i2c_read(ts->client, GOODIX_READ_COOR_ADDR,
-					data, GOODIX_CONTACT_SIZE + 1);
+					data, ts->contact_size + 1);
 		if (error) {
 			dev_err(&ts->client->dev, "I2C transfer error: %d\n",
 					error);
@@ -262,12 +277,12 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data)
 				return -EPROTO;
 
 			if (touch_num > 1) {
-				data += 1 + GOODIX_CONTACT_SIZE;
+				data += 1 + ts->contact_size;
 				error = goodix_i2c_read(ts->client,
 						GOODIX_READ_COOR_ADDR +
-							1 + GOODIX_CONTACT_SIZE,
+							1 + ts->contact_size,
 						data,
-						GOODIX_CONTACT_SIZE *
+						ts->contact_size *
 							(touch_num - 1));
 				if (error)
 					return error;
@@ -286,7 +301,7 @@ static int goodix_ts_read_input_report(struct goodix_ts_data *ts, u8 *data)
 	return 0;
 }
 
-static void goodix_ts_report_touch(struct goodix_ts_data *ts, u8 *coor_data)
+static void goodix_ts_report_touch_8b(struct goodix_ts_data *ts, u8 *coor_data)
 {
 	int id = coor_data[0] & 0x0F;
 	int input_x = get_unaligned_le16(&coor_data[1]);
@@ -301,6 +316,21 @@ static void goodix_ts_report_touch(struct goodix_ts_data *ts, u8 *coor_data)
 	input_report_abs(ts->input_dev, ABS_MT_WIDTH_MAJOR, input_w);
 }
 
+static void goodix_ts_report_touch_9b(struct goodix_ts_data *ts, u8 *coor_data)
+{
+	int id = coor_data[1] & 0x0F;
+	int input_x = get_unaligned_le16(&coor_data[3]);
+	int input_y = get_unaligned_le16(&coor_data[5]);
+	int input_w = get_unaligned_le16(&coor_data[7]);
+
+	input_mt_slot(ts->input_dev, id);
+	input_mt_report_slot_state(ts->input_dev, MT_TOOL_FINGER, true);
+	touchscreen_report_pos(ts->input_dev, &ts->prop,
+			       input_x, input_y, true);
+	input_report_abs(ts->input_dev, ABS_MT_TOUCH_MAJOR, input_w);
+	input_report_abs(ts->input_dev, ABS_MT_WIDTH_MAJOR, input_w);
+}
+
 /**
  * goodix_process_events - Process incoming events
  *
@@ -311,7 +341,7 @@ static void goodix_ts_report_touch(struct goodix_ts_data *ts, u8 *coor_data)
  */
 static void goodix_process_events(struct goodix_ts_data *ts)
 {
-	u8  point_data[1 + GOODIX_CONTACT_SIZE * GOODIX_MAX_CONTACTS];
+	u8  point_data[1 + GOODIX_MAX_CONTACT_SIZE * GOODIX_MAX_CONTACTS];
 	int touch_num;
 	int i;
 
@@ -326,8 +356,12 @@ static void goodix_process_events(struct goodix_ts_data *ts)
 	input_report_key(ts->input_dev, KEY_LEFTMETA, point_data[0] & BIT(4));
 
 	for (i = 0; i < touch_num; i++)
-		goodix_ts_report_touch(ts,
-				&point_data[1 + GOODIX_CONTACT_SIZE * i]);
+		if (ts->contact_size == 9)
+			goodix_ts_report_touch_9b(ts,
+				&point_data[1 + ts->contact_size * i]);
+		else
+			goodix_ts_report_touch_8b(ts,
+				&point_data[1 + ts->contact_size * i]);
 
 	input_mt_sync_frame(ts->input_dev);
 	input_sync(ts->input_dev);
@@ -730,6 +764,13 @@ static int goodix_configure_dev(struct goodix_ts_data *ts)
 			"Applying '180 degrees rotated screen' quirk\n");
 	}
 
+	if (dmi_check_system(nine_bytes_report)) {
+		ts->contact_size = 9;
+
+		dev_dbg(&ts->client->dev,
+			"Non-standard 9-bytes report format quirk\n");
+	}
+
 	error = input_mt_init_slots(ts->input_dev, ts->max_touch_num,
 				    INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED);
 	if (error) {
@@ -810,6 +851,7 @@ static int goodix_ts_probe(struct i2c_client *client,
 	ts->client = client;
 	i2c_set_clientdata(client, ts);
 	init_completion(&ts->firmware_loading_complete);
+	ts->contact_size = GOODIX_CONTACT_SIZE;
 
 	error = goodix_get_gpio_config(ts);
 	if (error)
-- 
cgit v1.2.3


From 25b69a889b638b0b7e51e2c4fe717a66bec0e566 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 10 Sep 2019 05:59:07 +0200
Subject: mips: Loongson: Fix the link time qualifier of 'serial_exit()'

'exit' functions should be marked as __exit, not __init.

Fixes: 85cc028817ef ("mips: make loongsoon serial driver explicitly modular")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: chenhc@lemote.com
Cc: ralf@linux-mips.org
Cc: jhogan@kernel.org
Cc: linux-mips@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: kernel-janitors@vger.kernel.org
---
 arch/mips/loongson64/common/serial.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/loongson64/common/serial.c b/arch/mips/loongson64/common/serial.c
index ffefc1cb2612..98c3a7feb10f 100644
--- a/arch/mips/loongson64/common/serial.c
+++ b/arch/mips/loongson64/common/serial.c
@@ -110,7 +110,7 @@ static int __init serial_init(void)
 }
 module_init(serial_init);
 
-static void __init serial_exit(void)
+static void __exit serial_exit(void)
 {
 	platform_device_unregister(&uart8250_device);
 }
-- 
cgit v1.2.3


From 53de429f4e88f538f7a8ec2b18be8c0cd9b2c8e1 Mon Sep 17 00:00:00 2001
From: Yizhuo <yzhai003@ucr.edu>
Date: Tue, 1 Oct 2019 13:24:39 -0700
Subject: net: hisilicon: Fix usage of uninitialized variable in function
 mdio_sc_cfg_reg_write()

In function mdio_sc_cfg_reg_write(), variable "reg_value" could be
uninitialized if regmap_read() fails. However, "reg_value" is used
to decide the control flow later in the if statement, which is
potentially unsafe.

Signed-off-by: Yizhuo <yzhai003@ucr.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns_mdio.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 3e863a71c513..7df5d7d211d4 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -148,11 +148,15 @@ static int mdio_sc_cfg_reg_write(struct hns_mdio_device *mdio_dev,
 {
 	u32 time_cnt;
 	u32 reg_value;
+	int ret;
 
 	regmap_write(mdio_dev->subctrl_vbase, cfg_reg, set_val);
 
 	for (time_cnt = MDIO_TIMEOUT; time_cnt; time_cnt--) {
-		regmap_read(mdio_dev->subctrl_vbase, st_reg, &reg_value);
+		ret = regmap_read(mdio_dev->subctrl_vbase, st_reg, &reg_value);
+		if (ret)
+			return ret;
+
 		reg_value &= st_msk;
 		if ((!!check_st) == (!!reg_value))
 			break;
-- 
cgit v1.2.3


From 0f1a7b3fac0583083ca19d4de47403511ced3521 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 2 Oct 2019 16:16:07 -0700
Subject: timer-of: don't use conditional expression with mixed 'void' types

Randy Dunlap reports on the sparse list that sparse warns about this
expression:

        of_irq->percpu ? free_percpu_irq(of_irq->irq, clkevt) :
                free_irq(of_irq->irq, clkevt);

and honestly, sparse is correct to warn.  The return type of
free_percpu_irq() is 'void', while free_irq() returns a 'const void *'
that is the devname argument passed in to the request_irq().

You can't mix a void type with a non-void types in a conditional
expression according to the C standard.  It so happens that gcc seems to
accept it - and the resulting type of the expression is void - but
there's really no reason for the kernel to have this kind of
non-standard expression with no real upside.

The natural way to write that expression is with an if-statement:

        if (of_irq->percpu)
                free_percpu_irq(of_irq->irq, clkevt);
        else
                free_irq(of_irq->irq, clkevt);

which is more legible anyway.

I'm not sure why that timer-of code seems to have this odd pattern.  It
does the same at allocation time, but at least there the types match,
and it makes sense as an expression.

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/clocksource/timer-of.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c
index d8c2bd4391d0..11ff701ff4bb 100644
--- a/drivers/clocksource/timer-of.c
+++ b/drivers/clocksource/timer-of.c
@@ -25,7 +25,9 @@ static __init void timer_of_irq_exit(struct of_timer_irq *of_irq)
 
 	struct clock_event_device *clkevt = &to->clkevt;
 
-	of_irq->percpu ? free_percpu_irq(of_irq->irq, clkevt) :
+	if (of_irq->percpu)
+		free_percpu_irq(of_irq->irq, clkevt);
+	else
 		free_irq(of_irq->irq, clkevt);
 }
 
-- 
cgit v1.2.3


From fcde8c7eea6004e92f8b329a84c2a520a1a71bc0 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 2 Oct 2019 19:34:59 +0100
Subject: drm/i915/selftests: Exercise potential false lite-restore

If execlists's lite-restore is based on the common GEM context tag
rather than the per-intel_context LRCA, then a context switch between
two intel_contexts on the same engine derived from the same GEM context
will perform a lite-restore instead of a full context switch. We can
exploit this by poisoning the ringbuffer of the first context and trying
to trick a simple RING_TAIL update (i.e. lite-restore)

v2: Also check what happens if preempt ce[0] with ce[1] (both instances
on the same engine from the same parent context) [Tvrtko]

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191002183459.26614-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c    |  18 +++-
 drivers/gpu/drm/i915/gt/selftest_lrc.c | 180 +++++++++++++++++++++++++++++++++
 2 files changed, 194 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 9877b6ba13df..431d3b8c3371 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -235,6 +235,16 @@ static void execlists_init_reg_state(u32 *reg_state,
 				     const struct intel_ring *ring,
 				     bool close);
 
+static void __context_pin_acquire(struct intel_context *ce)
+{
+	mutex_acquire(&ce->pin_mutex.dep_map, 2, 0, _RET_IP_);
+}
+
+static void __context_pin_release(struct intel_context *ce)
+{
+	mutex_release(&ce->pin_mutex.dep_map, 0, _RET_IP_);
+}
+
 static void mark_eio(struct i915_request *rq)
 {
 	if (!i915_request_signaled(rq))
@@ -2761,7 +2771,7 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
 	/* Proclaim we have exclusive access to the context image! */
-	mutex_acquire(&ce->pin_mutex.dep_map, 2, 0, _THIS_IP_);
+	__context_pin_acquire(ce);
 
 	rq = active_request(rq);
 	if (!rq) {
@@ -2825,7 +2835,7 @@ out_replay:
 	__execlists_reset_reg_state(ce, engine);
 	__execlists_update_reg_state(ce, engine);
 	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */
-	mutex_release(&ce->pin_mutex.dep_map, 0, _THIS_IP_);
+	__context_pin_release(ce);
 
 unwind:
 	/* Push back any incomplete requests for replay after the reset. */
@@ -4439,7 +4449,7 @@ void intel_lr_context_reset(struct intel_engine_cs *engine,
 			    bool scrub)
 {
 	GEM_BUG_ON(!intel_context_is_pinned(ce));
-	mutex_acquire(&ce->pin_mutex.dep_map, 2, 0, _THIS_IP_);
+	__context_pin_acquire(ce);
 
 	/*
 	 * We want a simple context + ring to execute the breadcrumb update.
@@ -4465,7 +4475,7 @@ void intel_lr_context_reset(struct intel_engine_cs *engine,
 	intel_ring_update_space(ce->ring);
 
 	__execlists_update_reg_state(ce, engine);
-	mutex_release(&ce->pin_mutex.dep_map, 0, _THIS_IP_);
+	__context_pin_release(ce);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 93f2fcdc49bf..e7bc2dbbb2a5 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -79,6 +79,184 @@ err_unlock:
 	return err;
 }
 
+static int live_unlite_restore(struct drm_i915_private *i915, int prio)
+{
+	struct intel_engine_cs *engine;
+	struct i915_gem_context *ctx;
+	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
+	struct igt_spinner spin;
+	int err = -ENOMEM;
+
+	/*
+	 * Check that we can correctly context switch between 2 instances
+	 * on the same engine from the same parent context.
+	 */
+
+	mutex_lock(&i915->drm.struct_mutex);
+	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
+
+	if (igt_spinner_init(&spin, &i915->gt))
+		goto err_unlock;
+
+	ctx = kernel_context(i915);
+	if (!ctx)
+		goto err_spin;
+
+	err = 0;
+	for_each_engine(engine, i915, id) {
+		struct intel_context *ce[2] = {};
+		struct i915_request *rq[2];
+		struct igt_live_test t;
+		int n;
+
+		if (prio && !intel_engine_has_preemption(engine))
+			continue;
+
+		if (!intel_engine_can_store_dword(engine))
+			continue;
+
+		if (igt_live_test_begin(&t, i915, __func__, engine->name)) {
+			err = -EIO;
+			break;
+		}
+
+		for (n = 0; n < ARRAY_SIZE(ce); n++) {
+			struct intel_context *tmp;
+
+			tmp = intel_context_create(ctx, engine);
+			if (IS_ERR(tmp)) {
+				err = PTR_ERR(tmp);
+				goto err_ce;
+			}
+
+			err = intel_context_pin(tmp);
+			if (err) {
+				intel_context_put(tmp);
+				goto err_ce;
+			}
+
+			/*
+			 * Setup the pair of contexts such that if we
+			 * lite-restore using the RING_TAIL from ce[1] it
+			 * will execute garbage from ce[0]->ring.
+			 */
+			memset(tmp->ring->vaddr,
+			       POISON_INUSE, /* IPEHR: 0x5a5a5a5a [hung!] */
+			       tmp->ring->vma->size);
+
+			ce[n] = tmp;
+		}
+		GEM_BUG_ON(!ce[1]->ring->size);
+		intel_ring_reset(ce[1]->ring, ce[1]->ring->size / 2);
+
+		local_bh_disable(); /* appease lockdep */
+		__context_pin_acquire(ce[1]);
+		__execlists_update_reg_state(ce[1], engine);
+		__context_pin_release(ce[1]);
+		local_bh_enable();
+
+		rq[0] = igt_spinner_create_request(&spin, ce[0], MI_ARB_CHECK);
+		if (IS_ERR(rq[0])) {
+			err = PTR_ERR(rq[0]);
+			goto err_ce;
+		}
+
+		i915_request_get(rq[0]);
+		i915_request_add(rq[0]);
+		GEM_BUG_ON(rq[0]->postfix > ce[1]->ring->emit);
+
+		if (!igt_wait_for_spinner(&spin, rq[0])) {
+			i915_request_put(rq[0]);
+			goto err_ce;
+		}
+
+		rq[1] = i915_request_create(ce[1]);
+		if (IS_ERR(rq[1])) {
+			err = PTR_ERR(rq[1]);
+			i915_request_put(rq[0]);
+			goto err_ce;
+		}
+
+		if (!prio) {
+			/*
+			 * Ensure we do the switch to ce[1] on completion.
+			 *
+			 * rq[0] is already submitted, so this should reduce
+			 * to a no-op (a wait on a request on the same engine
+			 * uses the submit fence, not the completion fence),
+			 * but it will install a dependency on rq[1] for rq[0]
+			 * that will prevent the pair being reordered by
+			 * timeslicing.
+			 */
+			i915_request_await_dma_fence(rq[1], &rq[0]->fence);
+		}
+
+		i915_request_get(rq[1]);
+		i915_request_add(rq[1]);
+		GEM_BUG_ON(rq[1]->postfix <= rq[0]->postfix);
+		i915_request_put(rq[0]);
+
+		if (prio) {
+			struct i915_sched_attr attr = {
+				.priority = prio,
+			};
+
+			/* Alternatively preempt the spinner with ce[1] */
+			engine->schedule(rq[1], &attr);
+		}
+
+		/* And switch back to ce[0] for good measure */
+		rq[0] = i915_request_create(ce[0]);
+		if (IS_ERR(rq[0])) {
+			err = PTR_ERR(rq[0]);
+			i915_request_put(rq[1]);
+			goto err_ce;
+		}
+
+		i915_request_await_dma_fence(rq[0], &rq[1]->fence);
+		i915_request_get(rq[0]);
+		i915_request_add(rq[0]);
+		GEM_BUG_ON(rq[0]->postfix > rq[1]->postfix);
+		i915_request_put(rq[1]);
+		i915_request_put(rq[0]);
+
+err_ce:
+		tasklet_kill(&engine->execlists.tasklet); /* flush submission */
+		igt_spinner_end(&spin);
+		for (n = 0; n < ARRAY_SIZE(ce); n++) {
+			if (IS_ERR_OR_NULL(ce[n]))
+				break;
+
+			intel_context_unpin(ce[n]);
+			intel_context_put(ce[n]);
+		}
+
+		if (igt_live_test_end(&t))
+			err = -EIO;
+		if (err)
+			break;
+	}
+
+	kernel_context_close(ctx);
+err_spin:
+	igt_spinner_fini(&spin);
+err_unlock:
+	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+	mutex_unlock(&i915->drm.struct_mutex);
+	return err;
+}
+
+static int live_unlite_switch(void *arg)
+{
+	return live_unlite_restore(arg, 0);
+}
+
+static int live_unlite_preempt(void *arg)
+{
+	return live_unlite_restore(arg, I915_USER_PRIORITY(I915_PRIORITY_MAX));
+}
+
 static int
 emit_semaphore_chain(struct i915_request *rq, struct i915_vma *vma, int idx)
 {
@@ -2178,6 +2356,8 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(live_sanitycheck),
+		SUBTEST(live_unlite_switch),
+		SUBTEST(live_unlite_preempt),
 		SUBTEST(live_timeslice_preempt),
 		SUBTEST(live_busywait_preempt),
 		SUBTEST(live_preempt),
-- 
cgit v1.2.3


From 134cc4cefad34d8d24670d8a911b59c3b89c6731 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Wed, 2 Oct 2019 16:49:46 +0200
Subject: net: stmmac: Avoid deadlock on suspend/resume

The stmmac driver will try to acquire its private mutex during suspend
via phylink_resolve() -> stmmac_mac_link_down() -> stmmac_eee_init().
However, the phylink configuration is updated with the private mutex
held already, which causes a deadlock during suspend.

Fix this by moving the phylink configuration updates out of the region
of code protected by the private mutex.

Fixes: 19e13cb27b99 ("net: stmmac: Hold rtnl lock in suspend/resume callbacks")
Suggested-by: Bitan Biswas <bbiswas@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 843d53e084b7..c76a1336a451 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4716,10 +4716,10 @@ int stmmac_suspend(struct device *dev)
 	if (!ndev || !netif_running(ndev))
 		return 0;
 
-	mutex_lock(&priv->lock);
-
 	phylink_mac_change(priv->phylink, false);
 
+	mutex_lock(&priv->lock);
+
 	netif_device_detach(ndev);
 	stmmac_stop_all_queues(priv);
 
@@ -4733,9 +4733,11 @@ int stmmac_suspend(struct device *dev)
 		stmmac_pmt(priv, priv->hw, priv->wolopts);
 		priv->irq_wake = 1;
 	} else {
+		mutex_unlock(&priv->lock);
 		rtnl_lock();
 		phylink_stop(priv->phylink);
 		rtnl_unlock();
+		mutex_lock(&priv->lock);
 
 		stmmac_mac_set(priv, priv->ioaddr, false);
 		pinctrl_pm_select_sleep_state(priv->device);
@@ -4827,6 +4829,8 @@ int stmmac_resume(struct device *dev)
 
 	stmmac_start_all_queues(priv);
 
+	mutex_unlock(&priv->lock);
+
 	if (!device_may_wakeup(priv->device)) {
 		rtnl_lock();
 		phylink_start(priv->phylink);
@@ -4835,8 +4839,6 @@ int stmmac_resume(struct device *dev)
 
 	phylink_mac_change(priv->phylink, true);
 
-	mutex_unlock(&priv->lock);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(stmmac_resume);
-- 
cgit v1.2.3


From 3a4b46c3bc73240b31cd324b3551fc4231d9f1d5 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Sat, 20 Jul 2019 21:05:25 +0900
Subject: block: pg: add header include guard

Add a header include guard just in case.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/pg.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/pg.h b/include/uapi/linux/pg.h
index 364c350e85cd..62b6f69bd9fb 100644
--- a/include/uapi/linux/pg.h
+++ b/include/uapi/linux/pg.h
@@ -35,6 +35,9 @@
 
 */
 
+#ifndef _UAPI_LINUX_PG_H
+#define _UAPI_LINUX_PG_H
+
 #define PG_MAGIC	'P'
 #define PG_RESET	'Z'
 #define PG_COMMAND	'C'
@@ -61,4 +64,4 @@ struct pg_read_hdr {
 
 };
 
-/* end of pg.h */
+#endif /* _UAPI_LINUX_PG_H */
-- 
cgit v1.2.3


From cffb4c3ea37248c4fc2f4ce747e5c24af88aec76 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Wed, 25 Sep 2019 10:21:09 +0200
Subject: drm/i915/dp: Fix dsc bpp calculations, v5.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There was a integer wraparound when mode_clock became too high,
and we didn't correct for the FEC overhead factor when dividing,
with the calculations breaking at HBR3.

As a result our calculated bpp was way too high, and the link width
limitation never came into effect.

Print out the resulting bpp calcululations as a sanity check, just
in case we ever have to debug it later on again.

We also used the wrong factor for FEC. While bspec mentions 2.4%,
all the calculations use 1/0.972261, and the same ratio should be
applied to data M/N as well, so use it there when FEC is enabled.

This fixes the FIFO underrun we are seeing with FEC enabled.

Changes since v2:
- Handle fec_enable in intel_link_compute_m_n, so only data M/N is adjusted. (Ville)
- Fix initial hardware readout for FEC. (Ville)
Changes since v3:
- Remove bogus fec_to_mode_clock. (Ville)
Changes since v4:
- Use the correct register for icl. (Ville)
- Split hw readout to a separate patch.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Fixes: d9218c8f6cf4 ("drm/i915/dp: Add helpers for Compressed BPP and Slice Count for DSC")
Cc: <stable@vger.kernel.org> # v5.0+
Cc: Manasi Navare <manasi.d.navare@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190925082110.17439-1-maarten.lankhorst@linux.intel.com
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
(cherry picked from commit ed06efb801bd291e935238d3fba46fa03d098f0e)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c |  12 +-
 drivers/gpu/drm/i915/display/intel_display.h |   2 +-
 drivers/gpu/drm/i915/display/intel_dp.c      | 184 ++++++++++++++-------------
 drivers/gpu/drm/i915/display/intel_dp.h      |   6 +-
 drivers/gpu/drm/i915/display/intel_dp_mst.c  |   2 +-
 5 files changed, 107 insertions(+), 99 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index b51d1ceb8739..ce05e805b08f 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -7261,7 +7261,7 @@ retry:
 	pipe_config->fdi_lanes = lane;
 
 	intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock,
-			       link_bw, &pipe_config->fdi_m_n, false);
+			       link_bw, &pipe_config->fdi_m_n, false, false);
 
 	ret = ironlake_check_fdi_lanes(dev, intel_crtc->pipe, pipe_config);
 	if (ret == -EDEADLK)
@@ -7508,11 +7508,15 @@ void
 intel_link_compute_m_n(u16 bits_per_pixel, int nlanes,
 		       int pixel_clock, int link_clock,
 		       struct intel_link_m_n *m_n,
-		       bool constant_n)
+		       bool constant_n, bool fec_enable)
 {
-	m_n->tu = 64;
+	u32 data_clock = bits_per_pixel * pixel_clock;
+
+	if (fec_enable)
+		data_clock = intel_dp_mode_to_fec_clock(data_clock);
 
-	compute_m_n(bits_per_pixel * pixel_clock,
+	m_n->tu = 64;
+	compute_m_n(data_clock,
 		    link_clock * nlanes * 8,
 		    &m_n->gmch_m, &m_n->gmch_n,
 		    constant_n);
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index e57e6969051d..01fa87ad3270 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -414,7 +414,7 @@ enum phy_fia {
 void intel_link_compute_m_n(u16 bpp, int nlanes,
 			    int pixel_clock, int link_clock,
 			    struct intel_link_m_n *m_n,
-			    bool constant_n);
+			    bool constant_n, bool fec_enable);
 bool is_ccs_modifier(u64 modifier);
 void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv);
 u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 921ad0a2f7ba..57e9f0ba331b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -78,8 +78,8 @@
 #define DP_DSC_MAX_ENC_THROUGHPUT_0		340000
 #define DP_DSC_MAX_ENC_THROUGHPUT_1		400000
 
-/* DP DSC FEC Overhead factor = (100 - 2.4)/100 */
-#define DP_DSC_FEC_OVERHEAD_FACTOR		976
+/* DP DSC FEC Overhead factor = 1/(0.972261) */
+#define DP_DSC_FEC_OVERHEAD_FACTOR		972261
 
 /* Compliance test status bits  */
 #define INTEL_DP_RESOLUTION_SHIFT_MASK	0
@@ -494,6 +494,97 @@ int intel_dp_get_link_train_fallback_values(struct intel_dp *intel_dp,
 	return 0;
 }
 
+u32 intel_dp_mode_to_fec_clock(u32 mode_clock)
+{
+	return div_u64(mul_u32_u32(mode_clock, 1000000U),
+		       DP_DSC_FEC_OVERHEAD_FACTOR);
+}
+
+static u16 intel_dp_dsc_get_output_bpp(u32 link_clock, u32 lane_count,
+				       u32 mode_clock, u32 mode_hdisplay)
+{
+	u32 bits_per_pixel, max_bpp_small_joiner_ram;
+	int i;
+
+	/*
+	 * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)*
+	 * (LinkSymbolClock)* 8 * (TimeSlotsPerMTP)
+	 * for SST -> TimeSlotsPerMTP is 1,
+	 * for MST -> TimeSlotsPerMTP has to be calculated
+	 */
+	bits_per_pixel = (link_clock * lane_count * 8) /
+			 intel_dp_mode_to_fec_clock(mode_clock);
+	DRM_DEBUG_KMS("Max link bpp: %u\n", bits_per_pixel);
+
+	/* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */
+	max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER / mode_hdisplay;
+	DRM_DEBUG_KMS("Max small joiner bpp: %u\n", max_bpp_small_joiner_ram);
+
+	/*
+	 * Greatest allowed DSC BPP = MIN (output BPP from available Link BW
+	 * check, output bpp from small joiner RAM check)
+	 */
+	bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram);
+
+	/* Error out if the max bpp is less than smallest allowed valid bpp */
+	if (bits_per_pixel < valid_dsc_bpp[0]) {
+		DRM_DEBUG_KMS("Unsupported BPP %u, min %u\n",
+			      bits_per_pixel, valid_dsc_bpp[0]);
+		return 0;
+	}
+
+	/* Find the nearest match in the array of known BPPs from VESA */
+	for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) {
+		if (bits_per_pixel < valid_dsc_bpp[i + 1])
+			break;
+	}
+	bits_per_pixel = valid_dsc_bpp[i];
+
+	/*
+	 * Compressed BPP in U6.4 format so multiply by 16, for Gen 11,
+	 * fractional part is 0
+	 */
+	return bits_per_pixel << 4;
+}
+
+static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
+				       int mode_clock, int mode_hdisplay)
+{
+	u8 min_slice_count, i;
+	int max_slice_width;
+
+	if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE)
+		min_slice_count = DIV_ROUND_UP(mode_clock,
+					       DP_DSC_MAX_ENC_THROUGHPUT_0);
+	else
+		min_slice_count = DIV_ROUND_UP(mode_clock,
+					       DP_DSC_MAX_ENC_THROUGHPUT_1);
+
+	max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd);
+	if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) {
+		DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n",
+			      max_slice_width);
+		return 0;
+	}
+	/* Also take into account max slice width */
+	min_slice_count = min_t(u8, min_slice_count,
+				DIV_ROUND_UP(mode_hdisplay,
+					     max_slice_width));
+
+	/* Find the closest match to the valid slice count values */
+	for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) {
+		if (valid_dsc_slicecount[i] >
+		    drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd,
+						    false))
+			break;
+		if (min_slice_count  <= valid_dsc_slicecount[i])
+			return valid_dsc_slicecount[i];
+	}
+
+	DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count);
+	return 0;
+}
+
 static enum drm_mode_status
 intel_dp_mode_valid(struct drm_connector *connector,
 		    struct drm_display_mode *mode)
@@ -2226,7 +2317,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 			       adjusted_mode->crtc_clock,
 			       pipe_config->port_clock,
 			       &pipe_config->dp_m_n,
-			       constant_n);
+			       constant_n, pipe_config->fec_enable);
 
 	if (intel_connector->panel.downclock_mode != NULL &&
 		dev_priv->drrs.type == SEAMLESS_DRRS_SUPPORT) {
@@ -2236,7 +2327,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 					       intel_connector->panel.downclock_mode->clock,
 					       pipe_config->port_clock,
 					       &pipe_config->dp_m2_n2,
-					       constant_n);
+					       constant_n, pipe_config->fec_enable);
 	}
 
 	if (!HAS_DDI(dev_priv))
@@ -4323,91 +4414,6 @@ intel_dp_get_sink_irq_esi(struct intel_dp *intel_dp, u8 *sink_irq_vector)
 		DP_DPRX_ESI_LEN;
 }
 
-u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count,
-				int mode_clock, int mode_hdisplay)
-{
-	u16 bits_per_pixel, max_bpp_small_joiner_ram;
-	int i;
-
-	/*
-	 * Available Link Bandwidth(Kbits/sec) = (NumberOfLanes)*
-	 * (LinkSymbolClock)* 8 * ((100-FECOverhead)/100)*(TimeSlotsPerMTP)
-	 * FECOverhead = 2.4%, for SST -> TimeSlotsPerMTP is 1,
-	 * for MST -> TimeSlotsPerMTP has to be calculated
-	 */
-	bits_per_pixel = (link_clock * lane_count * 8 *
-			  DP_DSC_FEC_OVERHEAD_FACTOR) /
-		mode_clock;
-
-	/* Small Joiner Check: output bpp <= joiner RAM (bits) / Horiz. width */
-	max_bpp_small_joiner_ram = DP_DSC_MAX_SMALL_JOINER_RAM_BUFFER /
-		mode_hdisplay;
-
-	/*
-	 * Greatest allowed DSC BPP = MIN (output BPP from avaialble Link BW
-	 * check, output bpp from small joiner RAM check)
-	 */
-	bits_per_pixel = min(bits_per_pixel, max_bpp_small_joiner_ram);
-
-	/* Error out if the max bpp is less than smallest allowed valid bpp */
-	if (bits_per_pixel < valid_dsc_bpp[0]) {
-		DRM_DEBUG_KMS("Unsupported BPP %d\n", bits_per_pixel);
-		return 0;
-	}
-
-	/* Find the nearest match in the array of known BPPs from VESA */
-	for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp) - 1; i++) {
-		if (bits_per_pixel < valid_dsc_bpp[i + 1])
-			break;
-	}
-	bits_per_pixel = valid_dsc_bpp[i];
-
-	/*
-	 * Compressed BPP in U6.4 format so multiply by 16, for Gen 11,
-	 * fractional part is 0
-	 */
-	return bits_per_pixel << 4;
-}
-
-u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
-				int mode_clock,
-				int mode_hdisplay)
-{
-	u8 min_slice_count, i;
-	int max_slice_width;
-
-	if (mode_clock <= DP_DSC_PEAK_PIXEL_RATE)
-		min_slice_count = DIV_ROUND_UP(mode_clock,
-					       DP_DSC_MAX_ENC_THROUGHPUT_0);
-	else
-		min_slice_count = DIV_ROUND_UP(mode_clock,
-					       DP_DSC_MAX_ENC_THROUGHPUT_1);
-
-	max_slice_width = drm_dp_dsc_sink_max_slice_width(intel_dp->dsc_dpcd);
-	if (max_slice_width < DP_DSC_MIN_SLICE_WIDTH_VALUE) {
-		DRM_DEBUG_KMS("Unsupported slice width %d by DP DSC Sink device\n",
-			      max_slice_width);
-		return 0;
-	}
-	/* Also take into account max slice width */
-	min_slice_count = min_t(u8, min_slice_count,
-				DIV_ROUND_UP(mode_hdisplay,
-					     max_slice_width));
-
-	/* Find the closest match to the valid slice count values */
-	for (i = 0; i < ARRAY_SIZE(valid_dsc_slicecount); i++) {
-		if (valid_dsc_slicecount[i] >
-		    drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd,
-						    false))
-			break;
-		if (min_slice_count  <= valid_dsc_slicecount[i])
-			return valid_dsc_slicecount[i];
-	}
-
-	DRM_DEBUG_KMS("Unsupported Slice Count %d\n", min_slice_count);
-	return 0;
-}
-
 static void
 intel_pixel_encoding_setup_vsc(struct intel_dp *intel_dp,
 			       const struct intel_crtc_state *crtc_state)
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index 657bbb1f5ed0..00981fb9414b 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -102,10 +102,6 @@ bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp);
 bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp);
 bool
 intel_dp_get_link_status(struct intel_dp *intel_dp, u8 *link_status);
-u16 intel_dp_dsc_get_output_bpp(int link_clock, u8 lane_count,
-				int mode_clock, int mode_hdisplay);
-u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp, int mode_clock,
-				int mode_hdisplay);
 
 bool intel_dp_read_dpcd(struct intel_dp *intel_dp);
 bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp);
@@ -118,4 +114,6 @@ static inline unsigned int intel_dp_unused_lane_mask(int lane_count)
 	return ~((1 << lane_count) - 1) & 0xf;
 }
 
+u32 intel_dp_mode_to_fec_clock(u32 mode_clock);
+
 #endif /* __INTEL_DP_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 6df240a01b8c..b6e3504c80a4 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -81,7 +81,7 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder,
 			       adjusted_mode->crtc_clock,
 			       crtc_state->port_clock,
 			       &crtc_state->dp_m_n,
-			       constant_n);
+			       constant_n, crtc_state->fec_enable);
 	crtc_state->dp_m_n.tu = slots;
 
 	return 0;
-- 
cgit v1.2.3


From eb0192fed016db1c5a9701cd6ca47233ff4a43e5 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 30 Sep 2019 21:30:45 +0300
Subject: drm/i915: Fix g4x sprite scaling stride check with GTT remapping
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I forgot to update the g4x sprite scaling stride check when GTT
remapping was introduced. The stride of the original framebuffer
is irrelevant when remapping is used and instead we want to check
the stride of the remapped view.

Also drop the duplicate width_bytes check. We already check that
a few lines earlier.

Fixes: df79cf441910 ("drm/i915: Store the final plane stride in plane_state")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190930183045.662-1-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
(cherry picked from commit 006e570128f413759b9df64b51bae79903679c9b)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_sprite.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index dea63be1964f..cae25e493128 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -1528,6 +1528,7 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state,
 	int src_x, src_w, src_h, crtc_w, crtc_h;
 	const struct drm_display_mode *adjusted_mode =
 		&crtc_state->base.adjusted_mode;
+	unsigned int stride = plane_state->color_plane[0].stride;
 	unsigned int cpp = fb->format->cpp[0];
 	unsigned int width_bytes;
 	int min_width, min_height;
@@ -1569,9 +1570,9 @@ g4x_sprite_check_scaling(struct intel_crtc_state *crtc_state,
 		return -EINVAL;
 	}
 
-	if (width_bytes > 4096 || fb->pitches[0] > 4096) {
+	if (stride > 4096) {
 		DRM_DEBUG_KMS("Stride (%u) exceeds hardware max with scaling (%u)\n",
-			      fb->pitches[0], 4096);
+			      stride, 4096);
 		return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From e2c4ed148cf3ec8669a1d90dc66966028e5fad70 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ti.com>
Date: Wed, 2 Oct 2019 15:25:42 +0300
Subject: drm/omap: fix max fclk divider for omap36xx

The OMAP36xx and AM/DM37x TRMs say that the maximum divider for DSS fclk
(in CM_CLKSEL_DSS) is 32. Experimentation shows that this is not
correct, and using divider of 32 breaks DSS with a flood or underflows
and sync losts. Dividers up to 31 seem to work fine.

There is another patch to the DT files to limit the divider correctly,
but as the DSS driver also needs to know the maximum divider to be able
to iteratively find good rates, we also need to do the fix in the DSS
driver.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Cc: Adam Ford <aford173@gmail.com>
Cc: stable@vger.kernel.org
Link: https://patchwork.freedesktop.org/patch/msgid/20191002122542.8449-1-tomi.valkeinen@ti.com
Tested-by: Adam Ford <aford173@gmail.com>
Reviewed-by: Jyri Sarha <jsarha@ti.com>
---
 drivers/gpu/drm/omapdrm/dss/dss.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index 5711b7a720e6..25b6a79dc385 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -1090,7 +1090,7 @@ static const struct dss_features omap34xx_dss_feats = {
 
 static const struct dss_features omap3630_dss_feats = {
 	.model			=	DSS_MODEL_OMAP3,
-	.fck_div_max		=	32,
+	.fck_div_max		=	31,
 	.fck_freq_max		=	173000000,
 	.dss_fck_multiplier	=	1,
 	.parent_clk_name	=	"dpll4_ck",
-- 
cgit v1.2.3


From 35b9ad840892d979dbeffe702dae95a3cbefa07b Mon Sep 17 00:00:00 2001
From: Daniel Black <daniel@linux.ibm.com>
Date: Tue, 6 Aug 2019 14:24:39 +1000
Subject: ACPI: HMAT: ACPI_HMAT_MEMORY_PD_VALID is deprecated since ACPI-6.3

ACPI-6.3 corresponds to when HMAT revision was bumped
from 1 to 2. In this version ACPI_HMAT_MEMORY_PD_VALID
was deprecated and made reserved.

As such in revision 2+ we shouldn't be testing this flag.

This is as per ACPI-6.3, 5.2.27.3, Table 5-145
"Memory Proximity Domain Attributes Structure"
for Flags.

Signed-off-by: Daniel Black <daniel@linux.ibm.com>
Reviewed-by: Tao Xu <tao3.xu@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/hmat/hmat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/hmat/hmat.c b/drivers/acpi/hmat/hmat.c
index 8f9a28a870b0..8b0de8a3c647 100644
--- a/drivers/acpi/hmat/hmat.c
+++ b/drivers/acpi/hmat/hmat.c
@@ -403,7 +403,7 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade
 		pr_info("HMAT: Memory Flags:%04x Processor Domain:%d Memory Domain:%d\n",
 			p->flags, p->processor_PD, p->memory_PD);
 
-	if (p->flags & ACPI_HMAT_MEMORY_PD_VALID) {
+	if (p->flags & ACPI_HMAT_MEMORY_PD_VALID && hmat_revision == 1) {
 		target = find_mem_target(p->memory_PD);
 		if (!target) {
 			pr_debug("HMAT: Memory Domain missing from SRAT\n");
-- 
cgit v1.2.3


From 0d52cc7e0311c17dfce2249532b6f7073fcac252 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 2 Oct 2019 17:54:04 +0300
Subject: drm/i915: use DRM_ERROR() instead of drm_err()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unify on current common usage to allow repurposing drm_err() later. Fix
newlines while at it.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191002145405.27848-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 20ec8a1dc5e1..32ca766d9a63 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -12562,10 +12562,10 @@ pipe_config_infoframe_mismatch(struct drm_i915_private *dev_priv,
 		drm_dbg(DRM_UT_KMS, "found");
 		hdmi_infoframe_log(KERN_DEBUG, dev_priv->drm.dev, b);
 	} else {
-		drm_err("mismatch in %s infoframe", name);
-		drm_err("expected:");
+		DRM_ERROR("mismatch in %s infoframe\n", name);
+		DRM_ERROR("expected:\n");
 		hdmi_infoframe_log(KERN_ERR, dev_priv->drm.dev, a);
-		drm_err("found");
+		DRM_ERROR("found:\n");
 		hdmi_infoframe_log(KERN_ERR, dev_priv->drm.dev, b);
 	}
 }
@@ -12583,7 +12583,7 @@ pipe_config_mismatch(bool fastset, const char *name, const char *format, ...)
 	if (fastset)
 		drm_dbg(DRM_UT_KMS, "fastset mismatch in %s %pV", name, &vaf);
 	else
-		drm_err("mismatch in %s %pV", name, &vaf);
+		DRM_ERROR("mismatch in %s %pV\n", name, &vaf);
 
 	va_end(args);
 }
-- 
cgit v1.2.3


From 48c38154d539e3c3fd32b0cdf654b10e5631d18c Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 2 Oct 2019 17:54:05 +0300
Subject: drm/i915: use DRM_DEBUG_KMS() instead of drm_dbg(DRM_UT_KMS, ...)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unify on current common usage to allow repurposing drm_dbg() later. Fix
newlines while at it.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191002145405.27848-2-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 32ca766d9a63..c3ac5a5c5185 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -12556,10 +12556,10 @@ pipe_config_infoframe_mismatch(struct drm_i915_private *dev_priv,
 		if ((drm_debug & DRM_UT_KMS) == 0)
 			return;
 
-		drm_dbg(DRM_UT_KMS, "fastset mismatch in %s infoframe", name);
-		drm_dbg(DRM_UT_KMS, "expected:");
+		DRM_DEBUG_KMS("fastset mismatch in %s infoframe\n", name);
+		DRM_DEBUG_KMS("expected:\n");
 		hdmi_infoframe_log(KERN_DEBUG, dev_priv->drm.dev, a);
-		drm_dbg(DRM_UT_KMS, "found");
+		DRM_DEBUG_KMS("found:\n");
 		hdmi_infoframe_log(KERN_DEBUG, dev_priv->drm.dev, b);
 	} else {
 		DRM_ERROR("mismatch in %s infoframe\n", name);
@@ -12581,7 +12581,7 @@ pipe_config_mismatch(bool fastset, const char *name, const char *format, ...)
 	vaf.va = &args;
 
 	if (fastset)
-		drm_dbg(DRM_UT_KMS, "fastset mismatch in %s %pV", name, &vaf);
+		DRM_DEBUG_KMS("fastset mismatch in %s %pV\n", name, &vaf);
 	else
 		DRM_ERROR("mismatch in %s %pV\n", name, &vaf);
 
-- 
cgit v1.2.3


From e8307ec51efebf579da5966aa5da5ab5353c61c7 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 2 Oct 2019 17:29:46 +0200
Subject: mmc: renesas_sdhi: Do not use platform_get_irq() to count interrupts

As platform_get_irq() now prints an error when the interrupt does not
exist, counting interrupts by looping until failure causes the printing
of scary messages like:

    renesas_sdhi_internal_dmac ee140000.sd: IRQ index 1 not found

Fix this by using the platform_irq_count() helper to avoid touching
non-existent interrupts.

Fixes: 7723f4c5ecdb8d83 ("driver core: platform: Add an error message to platform_get_irq*()")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/renesas_sdhi_core.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c
index d4ada5cca2d1..234551a68739 100644
--- a/drivers/mmc/host/renesas_sdhi_core.c
+++ b/drivers/mmc/host/renesas_sdhi_core.c
@@ -646,8 +646,8 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 	struct tmio_mmc_dma *dma_priv;
 	struct tmio_mmc_host *host;
 	struct renesas_sdhi *priv;
+	int num_irqs, irq, ret, i;
 	struct resource *res;
-	int irq, ret, i;
 	u16 ver;
 
 	of_data = of_device_get_match_data(&pdev->dev);
@@ -825,24 +825,31 @@ int renesas_sdhi_probe(struct platform_device *pdev,
 		host->hs400_complete = renesas_sdhi_hs400_complete;
 	}
 
-	i = 0;
-	while (1) {
+	num_irqs = platform_irq_count(pdev);
+	if (num_irqs < 0) {
+		ret = num_irqs;
+		goto eirq;
+	}
+
+	/* There must be at least one IRQ source */
+	if (!num_irqs) {
+		ret = -ENXIO;
+		goto eirq;
+	}
+
+	for (i = 0; i < num_irqs; i++) {
 		irq = platform_get_irq(pdev, i);
-		if (irq < 0)
-			break;
-		i++;
+		if (irq < 0) {
+			ret = irq;
+			goto eirq;
+		}
+
 		ret = devm_request_irq(&pdev->dev, irq, tmio_mmc_irq, 0,
 				       dev_name(&pdev->dev), host);
 		if (ret)
 			goto eirq;
 	}
 
-	/* There must be at least one IRQ source */
-	if (!i) {
-		ret = irq;
-		goto eirq;
-	}
-
 	dev_info(&pdev->dev, "%s base at 0x%08lx max clock rate %u MHz\n",
 		 mmc_hostname(host->mmc), (unsigned long)
 		 (platform_get_resource(pdev, IORESOURCE_MEM, 0)->start),
-- 
cgit v1.2.3


From faf97b84fa86d40eba5a30e9071dfb55133fb1b7 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 1 Oct 2019 20:08:34 +0200
Subject: mmc: sh_mmcif: Use platform_get_irq_optional() for optional interrupt

As platform_get_irq() now prints an error when the interrupt does not
exist, a scary warning may be printed for an optional interrupt:

    sh_mmcif ee200000.mmc: IRQ index 1 not found

Fix this by calling platform_get_irq_optional() instead for the second
interrupt, which is optional.

Remove the now superfluous error printing for the first interrupt, which
is mandatory.

Fixes: 7723f4c5ecdb8d83 ("driver core: platform: Add an error message to platform_get_irq*()")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Tested-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sh_mmcif.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 81bd9afb0980..98c575de43c7 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -1393,11 +1393,9 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	const char *name;
 
 	irq[0] = platform_get_irq(pdev, 0);
-	irq[1] = platform_get_irq(pdev, 1);
-	if (irq[0] < 0) {
-		dev_err(dev, "Get irq error\n");
+	irq[1] = platform_get_irq_optional(pdev, 1);
+	if (irq[0] < 0)
 		return -ENXIO;
-	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	reg = devm_ioremap_resource(dev, res);
-- 
cgit v1.2.3


From 6e06983dde969c15eb4fdab77f0eda8b18ea28e6 Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Wed, 2 Oct 2019 17:14:30 -0600
Subject: selftests: kvm: Fix libkvm build error

Fix the following build error from "make TARGETS=kvm kselftest":

libkvm.a(assert.o): relocation R_X86_64_32 against `.rodata.str1.1' can not be used when making a PIE object; recompile with -fPIC

This error is seen when build is done from the main Makefile using
kselftest target. In this case KBUILD_CPPFLAGS and CC_OPTION_CFLAGS
are defined.

When build is invoked using:

"make -C tools/testing/selftests/kvm" KBUILD_CPPFLAGS and CC_OPTION_CFLAGS
aren't defined.

There is no need to pass in KBUILD_CPPFLAGS and CC_OPTION_CFLAGS for the
check to determine if --no-pie is necessary, which is the case when these
two aren't defined when "make -C tools/testing/selftests/kvm" runs.

Fix it by simplifying the no-pie-option logic. With this change, both
build variations work.

"make TARGETS=kvm kselftest"
"make -C tools/testing/selftests/kvm"

Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index fd84b7a78dcf..c5ec868fa1e5 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -49,7 +49,7 @@ CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
 	-I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
 
 no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
-        $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
+        $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie)
 
 # On s390, build the testcases KVM-enabled
 pgste-option = $(call try-run, echo 'int main() { return 0; }' | \
-- 
cgit v1.2.3


From 24c29b7ac0da3e2eb589553f7a98bade6d0a0e60 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Tue, 1 Oct 2019 15:18:26 +0200
Subject: KVM: x86: omit absent pmu MSRs from MSR list

INTEL_PMC_MAX_GENERIC is currently 32, which exceeds the 18 contiguous
MSR indices reserved by Intel for event selectors.  Since some machines
actually have MSRs past the reserved range, these may survive the
filtering of msrs_to_save array and would be rejected by KVM_GET/SET_MSR.
To avoid this, cut the list to whatever CPUID reports for the host's
architectural PMU.

Reported-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Suggested-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jim Mattson <jmattson@google.com>
Fixes: e2ada66ec418 ("kvm: x86: Add Intel PMU MSRs to msrs_to_save[]", 2019-08-21)
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8072acaaf028..31607174f442 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5105,13 +5105,14 @@ out:
 
 static void kvm_init_msr_list(void)
 {
+	struct x86_pmu_capability x86_pmu;
 	u32 dummy[2];
 	unsigned i, j;
 
 	BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4,
 			 "Please update the fixed PMCs in msrs_to_save[]");
-	BUILD_BUG_ON_MSG(INTEL_PMC_MAX_GENERIC != 32,
-			 "Please update the generic perfctr/eventsel MSRs in msrs_to_save[]");
+
+	perf_get_x86_pmu_capability(&x86_pmu);
 
 	for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
 		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
@@ -5153,6 +5154,15 @@ static void kvm_init_msr_list(void)
 				intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
 				continue;
 			break;
+		case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 31:
+			if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
+			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
+				continue;
+			break;
+		case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 31:
+			if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
+			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
+				continue;
 		}
 		default:
 			break;
-- 
cgit v1.2.3


From 567926cca99ba1750be8aae9c4178796bf9bb90b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Tue, 1 Oct 2019 09:21:23 -0700
Subject: KVM: nVMX: Fix consistency check on injected exception error code

Current versions of Intel's SDM incorrectly state that "bits 31:15 of
the VM-Entry exception error-code field" must be zero.  In reality, bits
31:16 must be zero, i.e. error codes are 16-bit values.

The bogus error code check manifests as an unexpected VM-Entry failure
due to an invalid code field (error number 7) in L1, e.g. when injecting
a #GP with error_code=0x9f00.

Nadav previously reported the bug[*], both to KVM and Intel, and fixed
the associated kvm-unit-test.

[*] https://patchwork.kernel.org/patch/11124749/

Reported-by: Nadav Amit <namit@vmware.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 41abc62c9a8a..e76eb4f07f6c 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2610,7 +2610,7 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu,
 
 		/* VM-entry exception error code */
 		if (CC(has_error_code &&
-		       vmcs12->vm_entry_exception_error_code & GENMASK(31, 15)))
+		       vmcs12->vm_entry_exception_error_code & GENMASK(31, 16)))
 			return -EINVAL;
 
 		/* VM-entry interruption-info field: reserved bits */
-- 
cgit v1.2.3


From c5f4987e86f6692fdb12533ea1fc7a7bb98e555a Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Wed, 2 Oct 2019 10:03:36 -0400
Subject: btrfs: fix uninitialized ret in ref-verify

Coverity caught a case where we could return with a uninitialized value
in ret in process_leaf.  This is actually pretty likely because we could
very easily run into a block group item key and have a garbage value in
ret and think there was an errror.  Fix this by initializing ret to 0.

Reported-by: Colin Ian King <colin.king@canonical.com>
Fixes: fd708b81d972 ("Btrfs: add a extent ref verify tool")
CC: stable@vger.kernel.org # 4.19+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ref-verify.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index e87cbdad02a3..b57f3618e58e 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -500,7 +500,7 @@ static int process_leaf(struct btrfs_root *root,
 	struct btrfs_extent_data_ref *dref;
 	struct btrfs_shared_data_ref *sref;
 	u32 count;
-	int i = 0, tree_block_level = 0, ret;
+	int i = 0, tree_block_level = 0, ret = 0;
 	struct btrfs_key key;
 	int nritems = btrfs_header_nritems(leaf);
 
-- 
cgit v1.2.3


From e55190f26f92927e95aba22b069679311d5379ea Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Tue, 1 Oct 2019 13:22:49 +0200
Subject: samples/bpf: Fix build for task_fd_query_user.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add missing include for <linux/perf_event.h> which was removed from
perf-sys.h in commit 91854f9a077e ("perf tools: Move everything
related to sys_perf_event_open() to perf-sys.h").

Fixes: 91854f9a077e ("perf tools: Move everything related to sys_perf_event_open() to perf-sys.h")
Reported-by: KP Singh <kpsingh@google.com>
Reported-by: Florent Revest <revest@google.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: KP Singh <kpsingh@google.com>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20191001112249.27341-1-bjorn.topel@gmail.com
---
 samples/bpf/task_fd_query_user.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c
index e39938058223..4c31b305e6ef 100644
--- a/samples/bpf/task_fd_query_user.c
+++ b/samples/bpf/task_fd_query_user.c
@@ -13,6 +13,7 @@
 #include <sys/resource.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <linux/perf_event.h>
 
 #include "libbpf.h"
 #include "bpf_load.h"
-- 
cgit v1.2.3


From df551058f7a303bd3a17a4cef001349974962ce8 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 2 Oct 2019 08:31:59 +0200
Subject: xsk: Fix crash in poll when device does not support ndo_xsk_wakeup

Fixes a crash in poll() when an AF_XDP socket is opened in copy mode
and the bound device does not have ndo_xsk_wakeup defined. Avoid
trying to call the non-existing ndo and instead call the internal xsk
sendmsg function to send packets in the same way (from the
application's point of view) as calling sendmsg() in any mode or
poll() in zero-copy mode would have done. The application should
behave in the same way independent on if zero-copy mode or copy mode
is used.

Fixes: 77cd0d7b3f25 ("xsk: add support for need_wakeup flag in AF_XDP rings")
Reported-by: syzbot+a5765ed8cdb1cca4d249@syzkaller.appspotmail.com
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/1569997919-11541-1-git-send-email-magnus.karlsson@intel.com
---
 net/xdp/xsk.c | 42 +++++++++++++++++++++++++++---------------
 1 file changed, 27 insertions(+), 15 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index fa8fbb8fa3c8..9044073fbf22 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -305,9 +305,8 @@ out:
 }
 EXPORT_SYMBOL(xsk_umem_consume_tx);
 
-static int xsk_zc_xmit(struct sock *sk)
+static int xsk_zc_xmit(struct xdp_sock *xs)
 {
-	struct xdp_sock *xs = xdp_sk(sk);
 	struct net_device *dev = xs->dev;
 
 	return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id,
@@ -327,11 +326,10 @@ static void xsk_destruct_skb(struct sk_buff *skb)
 	sock_wfree(skb);
 }
 
-static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
-			    size_t total_len)
+static int xsk_generic_xmit(struct sock *sk)
 {
-	u32 max_batch = TX_BATCH_SIZE;
 	struct xdp_sock *xs = xdp_sk(sk);
+	u32 max_batch = TX_BATCH_SIZE;
 	bool sent_frame = false;
 	struct xdp_desc desc;
 	struct sk_buff *skb;
@@ -394,6 +392,18 @@ out:
 	return err;
 }
 
+static int __xsk_sendmsg(struct sock *sk)
+{
+	struct xdp_sock *xs = xdp_sk(sk);
+
+	if (unlikely(!(xs->dev->flags & IFF_UP)))
+		return -ENETDOWN;
+	if (unlikely(!xs->tx))
+		return -ENOBUFS;
+
+	return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk);
+}
+
 static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 {
 	bool need_wait = !(m->msg_flags & MSG_DONTWAIT);
@@ -402,21 +412,18 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 
 	if (unlikely(!xsk_is_bound(xs)))
 		return -ENXIO;
-	if (unlikely(!(xs->dev->flags & IFF_UP)))
-		return -ENETDOWN;
-	if (unlikely(!xs->tx))
-		return -ENOBUFS;
-	if (need_wait)
+	if (unlikely(need_wait))
 		return -EOPNOTSUPP;
 
-	return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len);
+	return __xsk_sendmsg(sk);
 }
 
 static unsigned int xsk_poll(struct file *file, struct socket *sock,
 			     struct poll_table_struct *wait)
 {
 	unsigned int mask = datagram_poll(file, sock, wait);
-	struct xdp_sock *xs = xdp_sk(sock->sk);
+	struct sock *sk = sock->sk;
+	struct xdp_sock *xs = xdp_sk(sk);
 	struct net_device *dev;
 	struct xdp_umem *umem;
 
@@ -426,9 +433,14 @@ static unsigned int xsk_poll(struct file *file, struct socket *sock,
 	dev = xs->dev;
 	umem = xs->umem;
 
-	if (umem->need_wakeup)
-		dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id,
-						umem->need_wakeup);
+	if (umem->need_wakeup) {
+		if (dev->netdev_ops->ndo_xsk_wakeup)
+			dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id,
+							umem->need_wakeup);
+		else
+			/* Poll needs to drive Tx also in copy mode */
+			__xsk_sendmsg(sk);
+	}
 
 	if (xs->rx && !xskq_empty_desc(xs->rx))
 		mask |= POLLIN | POLLRDNORM;
-- 
cgit v1.2.3


From 98beb3edeb974e906a81f305d88f7bc96b2ec83e Mon Sep 17 00:00:00 2001
From: KP Singh <kpsingh@google.com>
Date: Wed, 2 Oct 2019 21:16:52 +0200
Subject: samples/bpf: Add a workaround for asm_inline

This was added in commit eb111869301e ("compiler-types.h: add asm_inline
definition") and breaks samples/bpf as clang does not support asm __inline.

Fixes: eb111869301e ("compiler-types.h: add asm_inline definition")
Co-developed-by: Florent Revest <revest@google.com>
Signed-off-by: Florent Revest <revest@google.com>
Signed-off-by: KP Singh <kpsingh@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20191002191652.11432-1-kpsingh@chromium.org
---
 samples/bpf/asm_goto_workaround.h | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h
index 7409722727ca..7048bb3594d6 100644
--- a/samples/bpf/asm_goto_workaround.h
+++ b/samples/bpf/asm_goto_workaround.h
@@ -3,7 +3,8 @@
 #ifndef __ASM_GOTO_WORKAROUND_H
 #define __ASM_GOTO_WORKAROUND_H
 
-/* this will bring in asm_volatile_goto macro definition
+/*
+ * This will bring in asm_volatile_goto and asm_inline macro definitions
  * if enabled by compiler and config options.
  */
 #include <linux/types.h>
@@ -13,5 +14,15 @@
 #define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto")
 #endif
 
+/*
+ * asm_inline is defined as asm __inline in "include/linux/compiler_types.h"
+ * if supported by the kernel's CC (i.e CONFIG_CC_HAS_ASM_INLINE) which is not
+ * supported by CLANG.
+ */
+#ifdef asm_inline
+#undef asm_inline
+#define asm_inline asm
+#endif
+
 #define volatile(x...) volatile("")
 #endif
-- 
cgit v1.2.3


From 6af1799aaf3f1bc8defedddfa00df3192445bbf3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Oct 2019 09:38:55 -0700
Subject: ipv6: drop incoming packets having a v4mapped source address

This began with a syzbot report. syzkaller was injecting
IPv6 TCP SYN packets having a v4mapped source address.

After an unsuccessful 4-tuple lookup, TCP creates a request
socket (SYN_RECV) and calls reqsk_queue_hash_req()

reqsk_queue_hash_req() calls sk_ehashfn(sk)

At this point we have AF_INET6 sockets, and the heuristic
used by sk_ehashfn() to either hash the IPv4 or IPv6 addresses
is to use ipv6_addr_v4mapped(&sk->sk_v6_daddr)

For the particular spoofed packet, we end up hashing V4 addresses
which were not initialized by the TCP IPv6 stack, so KMSAN fired
a warning.

I first fixed sk_ehashfn() to test both source and destination addresses,
but then faced various problems, including user-space programs
like packetdrill that had similar assumptions.

Instead of trying to fix the whole ecosystem, it is better
to admit that we have a dual stack behavior, and that we
can not build linux kernels without V4 stack anyway.

The dual stack API automatically forces the traffic to be IPv4
if v4mapped addresses are used at bind() or connect(), so it makes
no sense to allow IPv6 traffic to use the same v4mapped class.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_input.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 7e5df23cbe7b..3d71c7d6102c 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -223,6 +223,16 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
 	if (ipv6_addr_is_multicast(&hdr->saddr))
 		goto err;
 
+	/* While RFC4291 is not explicit about v4mapped addresses
+	 * in IPv6 headers, it seems clear linux dual-stack
+	 * model can not deal properly with these.
+	 * Security models could be fooled by ::ffff:127.0.0.1 for example.
+	 *
+	 * https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02
+	 */
+	if (ipv6_addr_v4mapped(&hdr->saddr))
+		goto err;
+
 	skb->transport_header = skb->network_header + sizeof(*hdr);
 	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
 
-- 
cgit v1.2.3


From 086bf301f541eb4acfb5dadae7b1b207ad1b95a3 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Fri, 20 Sep 2019 10:44:47 -0700
Subject: MAINTAINERS: kgdb: Add myself as a reviewer for kgdb/kdb

I'm interested in kdb / kgdb and have sent various fixes over the
years.  I'd like to get CCed on patches so I can be aware of them and
also help review.

Signed-off-by: Douglas Anderson <dianders@chromium.org>
Acked-by: Daniel Thompson <daniel.thompson@linaro.org>
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 296de2b51c83..acdd996774d6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9075,6 +9075,7 @@ F:	security/keys/
 KGDB / KDB /debug_core
 M:	Jason Wessel <jason.wessel@windriver.com>
 M:	Daniel Thompson <daniel.thompson@linaro.org>
+R:	Douglas Anderson <dianders@chromium.org>
 W:	http://kgdb.wiki.kernel.org/
 L:	kgdb-bugreport@lists.sourceforge.net
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/kgdb.git
-- 
cgit v1.2.3


From 44b321e5020d782ad6e8ae8183f09b163be6e6e2 Mon Sep 17 00:00:00 2001
From: Josh Hunt <johunt@akamai.com>
Date: Wed, 2 Oct 2019 13:29:22 -0400
Subject: udp: fix gso_segs calculations

Commit dfec0ee22c0a ("udp: Record gso_segs when supporting UDP segmentation offload")
added gso_segs calculation, but incorrectly got sizeof() the pointer and
not the underlying data type. In addition let's fix the v6 case.

Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT")
Fixes: dfec0ee22c0a ("udp: Record gso_segs when supporting UDP segmentation offload")
Signed-off-by: Josh Hunt <johunt@akamai.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 2 +-
 net/ipv6/udp.c | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e8443cc5c1ab..3e2b90181879 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -856,7 +856,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 
 		skb_shinfo(skb)->gso_size = cork->gso_size;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(uh),
+		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
 							 cork->gso_size);
 		goto csum_partial;
 	}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index aae4938f3dea..eb9a9934ac05 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1143,6 +1143,8 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 
 		skb_shinfo(skb)->gso_size = cork->gso_size;
 		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
+							 cork->gso_size);
 		goto csum_partial;
 	}
 
-- 
cgit v1.2.3


From 4094871db1d65810acab3d57f6089aa39ef7f648 Mon Sep 17 00:00:00 2001
From: Josh Hunt <johunt@akamai.com>
Date: Wed, 2 Oct 2019 13:29:23 -0400
Subject: udp: only do GSO if # of segs > 1

Prior to this change an application sending <= 1MSS worth of data and
enabling UDP GSO would fail if the system had SW GSO enabled, but the
same send would succeed if HW GSO offload is enabled. In addition to this
inconsistency the error in the SW GSO case does not get back to the
application if sending out of a real device so the user is unaware of this
failure.

With this change we only perform GSO if the # of segments is > 1 even
if the application has enabled segmentation. I've also updated the
relevant udpgso selftests.

Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT")
Signed-off-by: Josh Hunt <johunt@akamai.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c                       | 11 +++++++----
 net/ipv6/udp.c                       | 11 +++++++----
 tools/testing/selftests/net/udpgso.c | 16 ++++------------
 3 files changed, 18 insertions(+), 20 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3e2b90181879..14bc654b6842 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -821,6 +821,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 	int is_udplite = IS_UDPLITE(sk);
 	int offset = skb_transport_offset(skb);
 	int len = skb->len - offset;
+	int datalen = len - sizeof(*uh);
 	__wsum csum = 0;
 
 	/*
@@ -854,10 +855,12 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 			return -EIO;
 		}
 
-		skb_shinfo(skb)->gso_size = cork->gso_size;
-		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
-							 cork->gso_size);
+		if (datalen > cork->gso_size) {
+			skb_shinfo(skb)->gso_size = cork->gso_size;
+			skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+			skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
+								 cork->gso_size);
+		}
 		goto csum_partial;
 	}
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index eb9a9934ac05..6324d3a8cb53 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1109,6 +1109,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 	__wsum csum = 0;
 	int offset = skb_transport_offset(skb);
 	int len = skb->len - offset;
+	int datalen = len - sizeof(*uh);
 
 	/*
 	 * Create a UDP header
@@ -1141,10 +1142,12 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
 			return -EIO;
 		}
 
-		skb_shinfo(skb)->gso_size = cork->gso_size;
-		skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(*uh),
-							 cork->gso_size);
+		if (datalen > cork->gso_size) {
+			skb_shinfo(skb)->gso_size = cork->gso_size;
+			skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
+			skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
+								 cork->gso_size);
+		}
 		goto csum_partial;
 	}
 
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
index b8265ee9923f..614b31aad168 100644
--- a/tools/testing/selftests/net/udpgso.c
+++ b/tools/testing/selftests/net/udpgso.c
@@ -89,12 +89,9 @@ struct testcase testcases_v4[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single MSS: will fail with GSO, because the segment
-		 * logic in udp4_ufo_fragment demands a gso skb to be > MTU
-		 */
+		/* send a single MSS: will fall back to no GSO */
 		.tlen = CONST_MSS_V4,
 		.gso_len = CONST_MSS_V4,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
@@ -139,10 +136,9 @@ struct testcase testcases_v4[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single 1B MSS: will fail, see single MSS above */
+		/* send a single 1B MSS: will fall back to no GSO */
 		.tlen = 1,
 		.gso_len = 1,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
@@ -196,12 +192,9 @@ struct testcase testcases_v6[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single MSS: will fail with GSO, because the segment
-		 * logic in udp4_ufo_fragment demands a gso skb to be > MTU
-		 */
+		/* send a single MSS: will fall back to no GSO */
 		.tlen = CONST_MSS_V6,
 		.gso_len = CONST_MSS_V6,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
@@ -246,10 +239,9 @@ struct testcase testcases_v6[] = {
 		.tfail = true,
 	},
 	{
-		/* send a single 1B MSS: will fail, see single MSS above */
+		/* send a single 1B MSS: will fall back to no GSO */
 		.tlen = 1,
 		.gso_len = 1,
-		.tfail = true,
 		.r_num_mss = 1,
 	},
 	{
-- 
cgit v1.2.3


From 2105b52e30debe7f19f3218598d8ae777dcc6776 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 2 Oct 2019 17:08:18 -0700
Subject: lib: textsearch: fix escapes in example code

This textsearch code example does not need the '\' escapes and they can
be misleading to someone reading the example. Also, gcc and sparse warn
that the "\%d" is an unknown escape sequence.

Fixes: 5968a70d7af5 ("textsearch: fix kernel-doc warnings and add kernel-api section")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/textsearch.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/textsearch.c b/lib/textsearch.c
index 4f16eec5d554..f68dea8806be 100644
--- a/lib/textsearch.c
+++ b/lib/textsearch.c
@@ -89,9 +89,9 @@
  *       goto errout;
  *   }
  *
- *   pos = textsearch_find_continuous(conf, \&state, example, strlen(example));
+ *   pos = textsearch_find_continuous(conf, &state, example, strlen(example));
  *   if (pos != UINT_MAX)
- *       panic("Oh my god, dancing chickens at \%d\n", pos);
+ *       panic("Oh my god, dancing chickens at %d\n", pos);
  *
  *   textsearch_destroy(conf);
  */
-- 
cgit v1.2.3


From 2a5243937c700ffe6a28e6557a4562a9ab0a17a4 Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Thu, 3 Oct 2019 15:59:22 +0200
Subject: selinux: fix context string corruption in convert_context()

string_to_context_struct() may garble the context string, so we need to
copy back the contents again from the old context struct to avoid
storing the corrupted context.

Since string_to_context_struct() tokenizes (and therefore truncates) the
context string and we are later potentially copying it with kstrdup(),
this may eventually cause pieces of uninitialized kernel memory to be
disclosed to userspace (when copying to userspace based on the stored
length and not the null character).

How to reproduce on Fedora and similar:
    # dnf install -y memcached
    # systemctl start memcached
    # semodule -d memcached
    # load_policy
    # load_policy
    # systemctl stop memcached
    # ausearch -m AVC
    type=AVC msg=audit(1570090572.648:313): avc:  denied  { signal } for  pid=1 comm="systemd" scontext=system_u:system_r:init_t:s0 tcontext=system_u:object_r:unlabeled_t:s0 tclass=process permissive=0 trawcon=73797374656D5F75007400000000000070BE6E847296FFFF726F6D000096FFFF76

Cc: stable@vger.kernel.org
Reported-by: Milos Malik <mmalik@redhat.com>
Fixes: ee1a84fdfeed ("selinux: overhaul sidtab to fix bug and improve performance")
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Acked-by: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/ss/services.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index ca56cd045bf9..39c317099d8d 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1948,7 +1948,14 @@ static int convert_context(struct context *oldc, struct context *newc, void *p)
 		rc = string_to_context_struct(args->newp, NULL, s,
 					      newc, SECSID_NULL);
 		if (rc == -EINVAL) {
-			/* Retain string representation for later mapping. */
+			/*
+			 * Retain string representation for later mapping.
+			 *
+			 * IMPORTANT: We need to copy the contents of oldc->str
+			 * back into s again because string_to_context_struct()
+			 * may have garbled it.
+			 */
+			memcpy(s, oldc->str, oldc->len);
 			context_init(newc);
 			newc->str = s;
 			newc->len = oldc->len;
-- 
cgit v1.2.3


From 3afb0961884046c8fb4acbce65139088959681c8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 2 Oct 2019 20:19:59 -0700
Subject: tcp: fix slab-out-of-bounds in tcp_zerocopy_receive()

Apparently a refactoring patch brought a bug, that was caught
by syzbot [1]

Original code was correct, do not try to be smarter than the
compiler :/

[1]
BUG: KASAN: slab-out-of-bounds in tcp_zerocopy_receive net/ipv4/tcp.c:1807 [inline]
BUG: KASAN: slab-out-of-bounds in do_tcp_getsockopt.isra.0+0x2c6c/0x3120 net/ipv4/tcp.c:3654
Read of size 4 at addr ffff8880943cf188 by task syz-executor.2/17508

CPU: 0 PID: 17508 Comm: syz-executor.2 Not tainted 5.3.0-rc7+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 print_address_description.cold+0xd4/0x306 mm/kasan/report.c:351
 __kasan_report.cold+0x1b/0x36 mm/kasan/report.c:482
 kasan_report+0x12/0x17 mm/kasan/common.c:618
 __asan_report_load4_noabort+0x14/0x20 mm/kasan/generic_report.c:131
 tcp_zerocopy_receive net/ipv4/tcp.c:1807 [inline]
 do_tcp_getsockopt.isra.0+0x2c6c/0x3120 net/ipv4/tcp.c:3654
 tcp_getsockopt+0xbf/0xe0 net/ipv4/tcp.c:3680
 sock_common_getsockopt+0x94/0xd0 net/core/sock.c:3098
 __sys_getsockopt+0x16d/0x310 net/socket.c:2129
 __do_sys_getsockopt net/socket.c:2144 [inline]
 __se_sys_getsockopt net/socket.c:2141 [inline]
 __x64_sys_getsockopt+0xbe/0x150 net/socket.c:2141
 do_syscall_64+0xfd/0x6a0 arch/x86/entry/common.c:296

Fixes: d8e18a516f8f ("net: Use skb accessors in network core")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 79c325a07ba5..f98a1882e537 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1798,13 +1798,11 @@ static int tcp_zerocopy_receive(struct sock *sk,
 		}
 		if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) {
 			int remaining = zc->recv_skip_hint;
-			int size = skb_frag_size(frags);
 
-			while (remaining && (size != PAGE_SIZE ||
+			while (remaining && (skb_frag_size(frags) != PAGE_SIZE ||
 					     skb_frag_off(frags))) {
-				remaining -= size;
+				remaining -= skb_frag_size(frags);
 				frags++;
-				size = skb_frag_size(frags);
 			}
 			zc->recv_skip_hint -= remaining;
 			break;
-- 
cgit v1.2.3


From 341115822f8832f0c2d8af2f7e151c4c9a77bcd1 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <natechancellor@gmail.com>
Date: Thu, 3 Oct 2019 10:11:21 -0700
Subject: usercopy: Add parentheses around assignment in
 test_copy_struct_from_user

Clang warns:

lib/test_user_copy.c:96:10: warning: using the result of an assignment
as a condition without parentheses [-Wparentheses]
        if (ret |= test(umem_src == NULL, "kmalloc failed"))
            ~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
lib/test_user_copy.c:96:10: note: place parentheses around the
assignment to silence this warning
        if (ret |= test(umem_src == NULL, "kmalloc failed"))
                ^
            (                                              )
lib/test_user_copy.c:96:10: note: use '!=' to turn this compound
assignment into an inequality comparison
        if (ret |= test(umem_src == NULL, "kmalloc failed"))
                ^~
                !=

Add the parentheses as it suggests because this is intentional.

Fixes: f5a1a536fa14 ("lib: introduce copy_struct_from_user() helper")
Link: https://github.com/ClangBuiltLinux/linux/issues/731
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Acked-by: Aleksa Sarai <cyphar@cyphar.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20191003171121.2723619-1-natechancellor@gmail.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 lib/test_user_copy.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c
index 950ee88cd6ac..e365ace06538 100644
--- a/lib/test_user_copy.c
+++ b/lib/test_user_copy.c
@@ -93,11 +93,11 @@ static int test_copy_struct_from_user(char *kmem, char __user *umem,
 	size_t ksize, usize;
 
 	umem_src = kmalloc(size, GFP_KERNEL);
-	if (ret |= test(umem_src == NULL, "kmalloc failed"))
+	if ((ret |= test(umem_src == NULL, "kmalloc failed")))
 		goto out_free;
 
 	expected = kmalloc(size, GFP_KERNEL);
-	if (ret |= test(expected == NULL, "kmalloc failed"))
+	if ((ret |= test(expected == NULL, "kmalloc failed")))
 		goto out_free;
 
 	/* Fill umem with a fixed byte pattern. */
-- 
cgit v1.2.3


From 501bd0166eb949820c8e4204e62aaee5c89c84d9 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Fri, 27 Sep 2019 17:28:42 +0200
Subject: fork: add kernel-doc for clone3

Add kernel-doc for the clone3() syscall.

Link: https://lore.kernel.org/r/20191001114701.24661-2-christian.brauner@ubuntu.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 kernel/fork.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/kernel/fork.c b/kernel/fork.c
index f9572f416126..bf11cf39579a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2604,6 +2604,17 @@ static bool clone3_args_valid(const struct kernel_clone_args *kargs)
 	return true;
 }
 
+/**
+ * clone3 - create a new process with specific properties
+ * @uargs: argument structure
+ * @size:  size of @uargs
+ *
+ * clone3() is the extensible successor to clone()/clone2().
+ * It takes a struct as argument that is versioned by its size.
+ *
+ * Return: On success, a positive PID for the child process.
+ *         On error, a negative errno number.
+ */
 SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size)
 {
 	int err;
-- 
cgit v1.2.3


From 78f6face5af344f12f4bd48b32faa6f499a06f36 Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Fri, 27 Sep 2019 17:29:05 +0200
Subject: sched: add kernel-doc for struct clone_args

Add kernel-doc for struct clone_args for the clone3() syscall.

Link: https://lore.kernel.org/r/20191001114701.24661-3-christian.brauner@ubuntu.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 include/uapi/linux/sched.h | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 851ff1feadd5..3d8f03bfd428 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -34,8 +34,30 @@
 #define CLONE_IO		0x80000000	/* Clone io context */
 
 #ifndef __ASSEMBLY__
-/*
- * Arguments for the clone3 syscall
+/**
+ * struct clone_args - arguments for the clone3 syscall
+ * @flags:       Flags for the new process as listed above.
+ *               All flags are valid except for CSIGNAL and
+ *               CLONE_DETACHED.
+ * @pidfd:       If CLONE_PIDFD is set, a pidfd will be
+ *               returned in this argument.
+ * @child_tid:   If CLONE_CHILD_SETTID is set, the TID of the
+ *               child process will be returned in the child's
+ *               memory.
+ * @parent_tid:  If CLONE_PARENT_SETTID is set, the TID of
+ *               the child process will be returned in the
+ *               parent's memory.
+ * @exit_signal: The exit_signal the parent process will be
+ *               sent when the child exits.
+ * @stack:       Specify the location of the stack for the
+ *               child process.
+ * @stack_size:  The size of the stack for the child process.
+ * @tls:         If CLONE_SETTLS is set, the tls descriptor
+ *               is set to tls.
+ *
+ * The structure is versioned by size and thus extensible.
+ * New struct members must go at the end of the struct and
+ * must be properly 64bit aligned.
  */
 struct clone_args {
 	__aligned_u64 flags;
-- 
cgit v1.2.3


From 485f682be9fc8d41376936a3b01423edd07b9a75 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 3 Sep 2019 18:40:18 +0300
Subject: Revert "drm/i915: Fix DP-MST crtc_mask"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 4eaceea3a00f8e936a7f48dcd0c975a57f88930f.

Several userspace clients (modesetting ddx and mutter+wayland at least)
handle encoder.possible_crtcs incorrectly. What they essentially do is
the following:

possible_crtcs = ~0;
for_each_possible_encoder(connector)
	possible_crtcs &= encoder->possible_crtcs;

Ie. they calculate the intersection of the possible_crtcs
for the connector when they really should be calculating the
union instead.

In our case each MST encoder now has just one unique bit set,
and so the intersection is always zero. The end result is that
MST connectors can't be lit up because no crtc can be found to
drive them.

I've submitted a fix for the modesetting ddx [1], and complained
on #wayland about mutter, so hopefully the situation will improve
in the future. In the meantime we have regression, and so must go
back to the old way of misconfiguring possible_crtcs in the kernel.

[1] https://gitlab.freedesktop.org/xorg/xserver/merge_requests/277

Cc: Jonas Ådahl <jadahl@gmail.com>
Cc: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111507
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190903154018.26357-1-ville.syrjala@linux.intel.com
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
(cherry picked from commit e838bfa8e170415fa3cc8e83ecb171e809c0c422)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp_mst.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index b6e3504c80a4..600873c796d0 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -615,7 +615,7 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
 	intel_encoder->type = INTEL_OUTPUT_DP_MST;
 	intel_encoder->power_domain = intel_dig_port->base.power_domain;
 	intel_encoder->port = intel_dig_port->base.port;
-	intel_encoder->crtc_mask = BIT(pipe);
+	intel_encoder->crtc_mask = 0x7;
 	intel_encoder->cloneable = 0;
 
 	intel_encoder->compute_config = intel_dp_mst_compute_config;
-- 
cgit v1.2.3


From dc301025658aef326763765b0bebeaa44569ed20 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 2 Oct 2019 19:23:05 -0700
Subject: block: sed-opal: fix sparse warning: obsolete array init.

Fix sparse warning: (missing '=')
../block/sed-opal.c:133:17: warning: obsolete array initializer, use C99 syntax

Fixes: ff91064ea37c ("block: sed-opal: check size of shadow mbr")
Cc: linux-block@vger.kernel.org
Cc: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Cc: David Kozub <zub@linux.fjfi.cvut.cz>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Reviewed-by:  Revanth Rajashekar <revanth.rajashekar@intel.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/sed-opal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/sed-opal.c b/block/sed-opal.c
index 4e95a9792162..59a6ba2131d5 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -129,7 +129,7 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
 		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x84, 0x01 },
 
 	/* tables */
-	[OPAL_TABLE_TABLE]
+	[OPAL_TABLE_TABLE] =
 		{ 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x01 },
 	[OPAL_LOCKINGRANGE_GLOBAL] =
 		{ 0x00, 0x00, 0x08, 0x02, 0x00, 0x00, 0x00, 0x01 },
-- 
cgit v1.2.3


From a9eb49c964884654dd6394cb6abe7ceb021c9c96 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 2 Oct 2019 19:23:15 -0700
Subject: block: sed-opal: fix sparse warning: convert __be64 data

sparse warns about incorrect type when using __be64 data.
It is not being converted to CPU-endian but it should be.

Fixes these sparse warnings:

../block/sed-opal.c:375:20: warning: incorrect type in assignment (different base types)
../block/sed-opal.c:375:20:    expected unsigned long long [usertype] align
../block/sed-opal.c:375:20:    got restricted __be64 const [usertype] alignment_granularity
../block/sed-opal.c:376:25: warning: incorrect type in assignment (different base types)
../block/sed-opal.c:376:25:    expected unsigned long long [usertype] lowest_lba
../block/sed-opal.c:376:25:    got restricted __be64 const [usertype] lowest_aligned_lba

Fixes: 455a7b238cd6 ("block: Add Sed-opal library")
Cc: Scott Bauer <scott.bauer@intel.com>
Cc: Rafael Antognolli <rafael.antognolli@intel.com>
Cc: linux-block@vger.kernel.org
Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/sed-opal.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/block/sed-opal.c b/block/sed-opal.c
index 59a6ba2131d5..b4c761973ac1 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -372,8 +372,8 @@ static void check_geometry(struct opal_dev *dev, const void *data)
 {
 	const struct d0_geometry_features *geo = data;
 
-	dev->align = geo->alignment_granularity;
-	dev->lowest_lba = geo->lowest_aligned_lba;
+	dev->align = be64_to_cpu(geo->alignment_granularity);
+	dev->lowest_lba = be64_to_cpu(geo->lowest_aligned_lba);
 }
 
 static int execute_step(struct opal_dev *dev,
-- 
cgit v1.2.3


From cc3a7bfe62b947b423fcb2cfe89fcba92bf48fa3 Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@redhat.com>
Date: Wed, 2 Oct 2019 16:17:54 -0500
Subject: vfs: Fix EOVERFLOW testing in put_compat_statfs64

Today, put_compat_statfs64() disallows nearly any field value over
2^32 if f_bsize is only 32 bits, but that makes no sense.
compat_statfs64 is there for the explicit purpose of providing 64-bit
fields for f_files, f_ffree, etc.  And f_bsize is always only 32 bits.

As a result, 32-bit userspace gets -EOVERFLOW for i.e.  large file
counts even with -D_FILE_OFFSET_BITS=64 set.

In reality, only f_bsize and f_frsize can legitimately overflow
(fields like f_type and f_namelen should never be large), so test
only those fields.

This bug was discussed at length some time ago, and this is the proposal
Al suggested at https://lkml.org/lkml/2018/8/6/640.  It seemed to get
dropped amid the discussion of other related changes, but this
part seems obviously correct on its own, so I've picked it up and
sent it, for expediency.

Fixes: 64d2ab32efe3 ("vfs: fix put_compat_statfs64() does not handle errors")
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/statfs.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

diff --git a/fs/statfs.c b/fs/statfs.c
index eea7af6f2f22..2616424012ea 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -318,19 +318,10 @@ COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *,
 static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf)
 {
 	struct compat_statfs64 buf;
-	if (sizeof(ubuf->f_bsize) == 4) {
-		if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen |
-		     kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL)
-			return -EOVERFLOW;
-		/* f_files and f_ffree may be -1; it's okay
-		 * to stuff that into 32 bits */
-		if (kbuf->f_files != 0xffffffffffffffffULL
-		 && (kbuf->f_files & 0xffffffff00000000ULL))
-			return -EOVERFLOW;
-		if (kbuf->f_ffree != 0xffffffffffffffffULL
-		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
-			return -EOVERFLOW;
-	}
+
+	if ((kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
+		return -EOVERFLOW;
+
 	memset(&buf, 0, sizeof(struct compat_statfs64));
 	buf.f_type = kbuf->f_type;
 	buf.f_bsize = kbuf->f_bsize;
-- 
cgit v1.2.3


From 101c40ed269ccf67d3535bf2d131584008edbbd1 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Thu, 3 Oct 2019 22:46:23 +0000
Subject: MIPS: pmcs-msp71xx: Add missing MAX_PROM_MEM definition

Commit b3c948e2c00f ("MIPS: msp: Record prom memory") introduced use of
a MAX_PROM_MEM value but didn't define it. A bounds check in
prom_meminit() suggests its value was supposed to be 5, so define it as
such & adjust the bounds check to use the macro rather than a magic
number.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Fixes: b3c948e2c00f ("MIPS: msp: Record prom memory")
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: linux-mips@vger.kernel.org
---
 arch/mips/pmcs-msp71xx/msp_prom.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/mips/pmcs-msp71xx/msp_prom.c b/arch/mips/pmcs-msp71xx/msp_prom.c
index dfb527961a27..f87c522a63e6 100644
--- a/arch/mips/pmcs-msp71xx/msp_prom.c
+++ b/arch/mips/pmcs-msp71xx/msp_prom.c
@@ -61,6 +61,7 @@ int init_debug = 1;
 /* memory blocks */
 struct prom_pmemblock mdesc[PROM_MAX_PMEMBLOCKS];
 
+#define MAX_PROM_MEM 5
 static phys_addr_t prom_mem_base[MAX_PROM_MEM] __initdata;
 static phys_addr_t prom_mem_size[MAX_PROM_MEM] __initdata;
 static unsigned int nr_prom_mem __initdata;
@@ -358,7 +359,7 @@ void __init prom_meminit(void)
 		p++;
 
 		if (type == BOOT_MEM_ROM_DATA) {
-			if (nr_prom_mem >= 5) {
+			if (nr_prom_mem >= MAX_PROM_MEM) {
 				pr_err("Too many ROM DATA regions");
 				continue;
 			}
-- 
cgit v1.2.3


From 437450cf09c382ff26c14c868d3a1e82c269be12 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Thu, 3 Oct 2019 22:46:36 +0000
Subject: MIPS: pmcs-msp71xx: Remove unused addr variable

The addr variable in prom_free_prom_memory() has been unused since
commit b3c948e2c00f ("MIPS: msp: Record prom memory"), causing a warning
& build failure due to -Werror. Remove the unused variable.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Fixes: b3c948e2c00f ("MIPS: msp: Record prom memory")
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: linux-mips@vger.kernel.org
---
 arch/mips/pmcs-msp71xx/msp_prom.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/mips/pmcs-msp71xx/msp_prom.c b/arch/mips/pmcs-msp71xx/msp_prom.c
index f87c522a63e6..800a21b8b8b0 100644
--- a/arch/mips/pmcs-msp71xx/msp_prom.c
+++ b/arch/mips/pmcs-msp71xx/msp_prom.c
@@ -378,7 +378,6 @@ void __init prom_free_prom_memory(void)
 	char	*ptr;
 	int	len = 0;
 	int	i;
-	unsigned long addr;
 
 	/*
 	 * preserve environment variables and command line from pmon/bbload
-- 
cgit v1.2.3


From 8f8fed0cdbbd6cdbf28d9ebe662f45765d2f7d39 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@wdc.com>
Date: Tue, 1 Oct 2019 16:48:39 +0900
Subject: scsi: core: save/restore command resid for error handling

When a non-passthrough command is terminated with CHECK CONDITION, request
sense is executed by hijacking the command descriptor. Since
scsi_eh_prep_cmnd() and scsi_eh_restore_cmnd() do not save/restore the
original command resid, the value returned on failure of the original
command is lost and replaced with the value set by the execution of the
request sense command. This value may in many instances be unaligned to the
device sector size, causing sd_done() to print a warning message about the
incorrect unaligned resid before the command is retried.

Fix this problem by saving the original command residual in struct
scsi_eh_save using scsi_eh_prep_cmnd() and restoring it in
scsi_eh_restore_cmnd(). In addition, to make sure that the request sense
command is executed with a correctly initialized command structure, also
reset the residual to 0 in scsi_eh_prep_cmnd() after saving the original
command value in struct scsi_eh_save.

Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20191001074839.1994-1-damien.lemoal@wdc.com
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_error.c | 3 +++
 include/scsi/scsi_eh.h    | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 1c470e31ae81..ae2fa170f6ad 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -967,6 +967,7 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses,
 	ses->data_direction = scmd->sc_data_direction;
 	ses->sdb = scmd->sdb;
 	ses->result = scmd->result;
+	ses->resid_len = scmd->req.resid_len;
 	ses->underflow = scmd->underflow;
 	ses->prot_op = scmd->prot_op;
 	ses->eh_eflags = scmd->eh_eflags;
@@ -977,6 +978,7 @@ void scsi_eh_prep_cmnd(struct scsi_cmnd *scmd, struct scsi_eh_save *ses,
 	memset(scmd->cmnd, 0, BLK_MAX_CDB);
 	memset(&scmd->sdb, 0, sizeof(scmd->sdb));
 	scmd->result = 0;
+	scmd->req.resid_len = 0;
 
 	if (sense_bytes) {
 		scmd->sdb.length = min_t(unsigned, SCSI_SENSE_BUFFERSIZE,
@@ -1029,6 +1031,7 @@ void scsi_eh_restore_cmnd(struct scsi_cmnd* scmd, struct scsi_eh_save *ses)
 	scmd->sc_data_direction = ses->data_direction;
 	scmd->sdb = ses->sdb;
 	scmd->result = ses->result;
+	scmd->req.resid_len = ses->resid_len;
 	scmd->underflow = ses->underflow;
 	scmd->prot_op = ses->prot_op;
 	scmd->eh_eflags = ses->eh_eflags;
diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h
index 3810b340551c..6bd5ed695a5e 100644
--- a/include/scsi/scsi_eh.h
+++ b/include/scsi/scsi_eh.h
@@ -32,6 +32,7 @@ extern int scsi_ioctl_reset(struct scsi_device *, int __user *);
 struct scsi_eh_save {
 	/* saved state */
 	int result;
+	unsigned int resid_len;
 	int eh_eflags;
 	enum dma_data_direction data_direction;
 	unsigned underflow;
-- 
cgit v1.2.3


From 2190168aaea42c31bff7b9a967e7b045f07df095 Mon Sep 17 00:00:00 2001
From: Steffen Maier <maier@linux.ibm.com>
Date: Tue, 1 Oct 2019 12:49:49 +0200
Subject: scsi: zfcp: fix reaction on bit error threshold notification

On excessive bit errors for the FCP channel ingress fibre path, the channel
notifies us.  Previously, we only emitted a kernel message and a trace
record.  Since performance can become suboptimal with I/O timeouts due to
bit errors, we now stop using an FCP device by default on channel
notification so multipath on top can timely failover to other paths.  A new
module parameter zfcp.ber_stop can be used to get zfcp old behavior.

User explanation of new kernel message:

 * Description:
 * The FCP channel reported that its bit error threshold has been exceeded.
 * These errors might result from a problem with the physical components
 * of the local fibre link into the FCP channel.
 * The problem might be damage or malfunction of the cable or
 * cable connection between the FCP channel and
 * the adjacent fabric switch port or the point-to-point peer.
 * Find details about the errors in the HBA trace for the FCP device.
 * The zfcp device driver closed down the FCP device
 * to limit the performance impact from possible I/O command timeouts.
 * User action:
 * Check for problems on the local fibre link, ensure that fibre optics are
 * clean and functional, and all cables are properly plugged.
 * After the repair action, you can manually recover the FCP device by
 * writing "0" into its "failed" sysfs attribute.
 * If recovery through sysfs is not possible, set the CHPID of the device
 * offline and back online on the service element.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: <stable@vger.kernel.org> #2.6.30+
Link: https://lore.kernel.org/r/20191001104949.42810-1-maier@linux.ibm.com
Reviewed-by: Jens Remus <jremus@linux.ibm.com>
Reviewed-by: Benjamin Block <bblock@linux.ibm.com>
Signed-off-by: Steffen Maier <maier@linux.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/s390/scsi/zfcp_fsf.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 296bbc3c4606..cf63916814cc 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -27,6 +27,11 @@
 
 struct kmem_cache *zfcp_fsf_qtcb_cache;
 
+static bool ber_stop = true;
+module_param(ber_stop, bool, 0600);
+MODULE_PARM_DESC(ber_stop,
+		 "Shuts down FCP devices for FCP channels that report a bit-error count in excess of its threshold (default on)");
+
 static void zfcp_fsf_request_timeout_handler(struct timer_list *t)
 {
 	struct zfcp_fsf_req *fsf_req = from_timer(fsf_req, t, timer);
@@ -236,10 +241,15 @@ static void zfcp_fsf_status_read_handler(struct zfcp_fsf_req *req)
 	case FSF_STATUS_READ_SENSE_DATA_AVAIL:
 		break;
 	case FSF_STATUS_READ_BIT_ERROR_THRESHOLD:
-		dev_warn(&adapter->ccw_device->dev,
-			 "The error threshold for checksum statistics "
-			 "has been exceeded\n");
 		zfcp_dbf_hba_bit_err("fssrh_3", req);
+		if (ber_stop) {
+			dev_warn(&adapter->ccw_device->dev,
+				 "All paths over this FCP device are disused because of excessive bit errors\n");
+			zfcp_erp_adapter_shutdown(adapter, 0, "fssrh_b");
+		} else {
+			dev_warn(&adapter->ccw_device->dev,
+				 "The error threshold for checksum statistics has been exceeded\n");
+		}
 		break;
 	case FSF_STATUS_READ_LINK_DOWN:
 		zfcp_fsf_status_read_link_down(req);
-- 
cgit v1.2.3


From b23f330d5145b92f90cf16f1adc5444ad06764b4 Mon Sep 17 00:00:00 2001
From: Himanshu Madhani <hmadhani@marvell.com>
Date: Tue, 1 Oct 2019 08:33:38 -0700
Subject: scsi: MAINTAINERS: Update qla2xxx driver

Update maintainer entry for qla2xxx driver now that email addresses have
been changed to Marvell.

Link: https://lore.kernel.org/r/20191001153338.28765-1-hmadhani@marvell.com
Signed-off-by: Himanshu Madhani <hmadhani@marvell.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 783569e3c4b4..91f33522393a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13184,7 +13184,7 @@ S:	Maintained
 F:	drivers/scsi/qla1280.[ch]
 
 QLOGIC QLA2XXX FC-SCSI DRIVER
-M:	qla2xxx-upstream@qlogic.com
+M:	hmadhani@marvell.com
 L:	linux-scsi@vger.kernel.org
 S:	Supported
 F:	Documentation/scsi/LICENSE.qla2xxx
-- 
cgit v1.2.3


From 5dcaa1fcea1bfc15c0a93c9b0c6afe655fa577f0 Mon Sep 17 00:00:00 2001
From: Okash Khawaja <okash.khawaja@gmail.com>
Date: Tue, 1 Oct 2019 22:47:29 +0100
Subject: staging: speakup: document sysfs attributes

Speakup exposes a set of sysfs attributes under
/sys/accessibility/speakup/ for user-space to interact with and
configure speakup's kernel modules. This patch describes those
attributes. Some attributes either lack a description or contain
incomplete description. They are marked wit TODO.

Authored-by: Gregory Nowak <greg@gregn.net>
Submitted-by: Okash Khawaja <okash.khawaja@gmail.com>
Signed-off-by: Okash Khawaja <okash.khawaja@gmail.com>
Link: https://lore.kernel.org/r/20191001214729.1770-1-okash.khawaja@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/speakup/sysfs-driver-speakup | 369 +++++++++++++++++++++++++++
 1 file changed, 369 insertions(+)
 create mode 100644 drivers/staging/speakup/sysfs-driver-speakup

diff --git a/drivers/staging/speakup/sysfs-driver-speakup b/drivers/staging/speakup/sysfs-driver-speakup
new file mode 100644
index 000000000000..be3f5d6962e9
--- /dev/null
+++ b/drivers/staging/speakup/sysfs-driver-speakup
@@ -0,0 +1,369 @@
+What:		/sys/accessibility/speakup/attrib_bleep
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Beeps the PC speaker when there is an attribute change such as
+		foreground or background color when using speakup review
+		commands. One = on, zero = off.
+
+What:		/sys/accessibility/speakup/bell_pos
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This works much like a typewriter bell. If for example 72 is
+		echoed to bell_pos, it will beep the PC speaker when typing on
+		a line past character 72.
+
+What:		/sys/accessibility/speakup/bleeps
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This controls whether one hears beeps through the PC speaker
+		when using speakup's review commands.
+		TODO: what values does it accept?
+
+What:		/sys/accessibility/speakup/bleep_time
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This controls the duration of the PC speaker beeps speakup
+		produces.
+		TODO: What are the units? Jiffies?
+
+What:		/sys/accessibility/speakup/cursor_time
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This controls cursor delay when using arrow keys. When a
+		connection is very slow, with the default setting, when moving
+		with  the arrows, or backspacing etc. speakup says the incorrect
+		characters. Set this to a higher value to adjust for the delay
+		and better synchronisation between cursor position and speech.
+
+What:		/sys/accessibility/speakup/delimiters
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Delimit a word from speakup.
+		TODO: add more info
+
+What:		/sys/accessibility/speakup/ex_num
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	TODO:
+
+What:		/sys/accessibility/speakup/key_echo
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Controls if speakup speaks keys when they are typed. One = on,
+		zero = off or don't echo keys.
+
+What:		/sys/accessibility/speakup/keymap
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Speakup keymap remaps keys to Speakup functions.
+		It uses a binary
+		format. A special program called genmap is needed to compile a
+		textual  keymap into the binary format which is then loaded into
+		/sys/accessibility/speakup/keymap.
+
+What:		/sys/accessibility/speakup/no_interrupt
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Controls if typing interrupts output from speakup. With
+		no_interrupt set to zero, typing on the keyboard will interrupt
+		speakup if for example
+		the say screen command is used before the
+		entire screen  is read.
+		With no_interrupt set to one, if the say
+		screen command is used, and one then types on the keyboard,
+		speakup will continue to say the whole screen regardless until
+		it finishes.
+
+What:		/sys/accessibility/speakup/punc_all
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This is a list of all the punctuation speakup should speak when
+		punc_level is set to four.
+
+What:		/sys/accessibility/speakup/punc_level
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Controls the level of punctuation spoken as the screen is
+		displayed, not reviewed. Levels range from zero no punctuation,
+		to four, all punctuation. One corresponds to punc_some, two
+		corresponds to punc_most, and three as well as four both
+		correspond to punc_all. Some hardware synthesizers may have
+		different levels each corresponding to  three and four for
+		punc_level. Also note that if punc_level is set to zero, and
+		key_echo is set to one, typed punctuation is still spoken as it
+		is typed.
+
+What:		/sys/accessibility/speakup/punc_most
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This is a list of all the punctuation speakup should speak when
+		punc_level is set to two.
+
+What:		/sys/accessibility/speakup/punc_some
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This is a list of all the punctuation speakup should speak when
+		punc_level is set to one.
+
+What:		/sys/accessibility/speakup/reading_punc
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Almost the same as punc_level, the differences being that
+		reading_punc controls the level of punctuation when reviewing
+		the screen with speakup's screen review commands. The other
+		difference is that reading_punc set to three speaks punc_all,
+		and reading_punc set to four speaks all punctuation, including
+		spaces.
+
+What:		/sys/accessibility/speakup/repeats
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	A list of characters speakup repeats. Normally, when there are
+		more than three characters in a row, speakup
+		just reads three of
+		those characters. For example, "......" would be read as dot,
+		dot, dot. If a . is added to the list of characters in repeats,
+		"......" would be read as dot, dot, dot, times six.
+
+What:		/sys/accessibility/speakup/say_control
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	If set to one, speakup speaks shift, alt and control when those
+		keys are pressed. If say_control is set to zero, shift, ctrl,
+		and alt are not spoken when they are pressed.
+
+What:		/sys/accessibility/speakup/say_word_ctl
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	TODO:
+
+What:		/sys/accessibility/speakup/silent
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	TODO:
+
+What:		/sys/accessibility/speakup/spell_delay
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This controls how fast a word is spelled
+		when speakup's say word
+		review command is pressed twice quickly to speak the current
+		word being reviewed. Zero just speaks the letters one after
+		another, while values one through four
+		seem to introduce more of
+		a pause between the spelling of each letter by speakup.
+
+What:		/sys/accessibility/speakup/synth
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Gets or sets the synthesizer driver currently in use. Reading
+		synth returns the synthesizer driver currently in use. Writing
+		synth switches to the given synthesizer driver, provided it is
+		either built into the kernel, or already loaded as a module.
+
+What:		/sys/accessibility/speakup/synth_direct
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Sends whatever is written to synth_direct
+		directly to the speech synthesizer in use, bypassing speakup.
+		This could be used to make the synthesizer speak
+		a string, or to
+		send control sequences to the synthesizer to change how the
+		synthesizer behaves.
+
+What:		/sys/accessibility/speakup/version
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Reading version returns the version of speakup, and the version
+		of the synthesizer driver currently in use.
+
+What:		/sys/accessibility/speakup/i18n/announcements
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This file contains various general announcements, most of which
+		cannot be categorized.  You will find messages such as "You
+		killed Speakup", "I'm alive", "leaving help", "parked",
+		"unparked", and others. You will also find the names of the
+		screen edges and cursor tracking modes here.
+
+What:		/sys/accessibility/speakup/i18n/chartab
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	TODO
+
+What:		/sys/accessibility/speakup/i18n/ctl_keys
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Here, you will find names of control keys.  These are used with
+		Speakup's say_control feature.
+
+What:		/sys/accessibility/speakup/i18n/function_names
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Here, you will find a list of names for Speakup functions.
+		These are used by the help system.  For example, suppose that
+		you have activated help mode, and you pressed
+		keypad 3.  Speakup
+		says: "keypad 3 is character, say next."
+		The message "character, say next" names a Speakup function, and
+		it comes from this function_names file.
+
+What:		/sys/accessibility/speakup/i18n/states
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This file contains names for key states.
+		Again, these are part of the help system.  For instance, if you
+		had pressed speakup + keypad 3, you would hear:
+		"speakup keypad 3 is go to bottom edge."
+		The speakup key is depressed, so the name of the key state is
+		speakup.
+		This part of the message comes from the states collection.
+
+What:		/sys/accessibility/speakup/i18n/characters
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Through this sys entry, Speakup gives you the ability to change
+		how Speakup pronounces a given character. You could, for
+		example, change how some punctuation characters are spoken. You
+		can even change how Speakup will pronounce certain letters. For
+		further details see '12.  Changing the Pronunciation of
+		Characters' in Speakup User's Guide (file spkguide.txt in
+		source).
+
+What:		/sys/accessibility/speakup/i18n/colors
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	When you use the "say attributes" function, Speakup says the
+		name of the foreground and background colors.  These names come
+		from the i18n/colors file.
+
+What:		/sys/accessibility/speakup/i18n/formatted
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This group of messages contains embedded formatting codes, to
+		specify the type and width of displayed data.  If you change
+		these, you must preserve all of the formatting codes, and they
+		must appear in the order used by the default messages.
+
+What:		/sys/accessibility/speakup/i18n/key_names
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Again, key_names is used by Speakup's help system.  In the
+		previous example, Speakup said that you pressed "keypad 3."
+		This name came from the key_names file.
+
+What:		/sys/accessibility/speakup/<synth-name>/
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	In `/sys/accessibility/speakup` is a directory corresponding to
+		the synthesizer driver currently in use (E.G) `soft` for the
+		soft driver. This directory contains files which control the
+		speech synthesizer itself,
+		as opposed to controlling the speakup
+		screen reader. The parameters in this directory have the same
+		names and functions across all
+		supported synthesizers. The range
+		of values for freq, pitch, rate, and vol is the same for all
+		supported synthesizers, with the given range being internally
+		mapped by the driver to  more or less fit the range of values
+		supported for a given parameter by the individual synthesizer.
+		Below is a description of values and  parameters for soft
+		synthesizer, which is currently the most commonly used.
+
+What:		/sys/accessibility/speakup/soft/caps_start
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This is the string that is sent to the synthesizer to cause it
+		to start speaking uppercase letters. For the soft synthesizer
+		and most others, this causes the pitch of the voice to rise
+		above the currently set pitch.
+
+What:		/sys/accessibility/speakup/soft/caps_stop
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This is the string sent to the synthesizer to cause it to stop
+		speaking uppercase letters. In the case of the soft synthesizer
+		and most others, this returns the pitch of the voice
+		down to the
+		currently set pitch.
+
+What:		/sys/accessibility/speakup/soft/delay_time
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	TODO:
+
+What:		/sys/accessibility/speakup/soft/direct
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Controls if punctuation is spoken by speakup, or by the
+		synthesizer.
+		For example, speakup speaks ">" as "greater", while
+		the espeak synthesizer used by the soft driver speaks "greater
+		than". Zero lets speakup speak the punctuation. One lets the
+		synthesizer itself speak punctuation.
+
+What:		/sys/accessibility/speakup/soft/freq
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Gets or sets the frequency of the speech synthesizer. Range is
+		0-9.
+
+What:		/sys/accessibility/speakup/soft/full_time
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	TODO:
+
+What:		/sys/accessibility/speakup/soft/jiffy_delta
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	This controls how many jiffys the kernel gives to the
+		synthesizer. Setting this too high can make a system unstable,
+		or even crash it.
+
+What:		/sys/accessibility/speakup/soft/pitch
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Gets or sets the pitch of the synthesizer. The range is 0-9.
+
+What:		/sys/accessibility/speakup/soft/punct
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Gets or sets the amount of punctuation spoken by the
+		synthesizer. The range for the soft driver seems to be 0-2.
+		TODO: How is this related to speakup's punc_level, or
+		reading_punc.
+
+What:		/sys/accessibility/speakup/soft/rate
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Gets or sets the rate of the synthesizer. Range is from zero
+		slowest, to nine fastest.
+
+What:		/sys/accessibility/speakup/soft/tone
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Gets or sets the tone of the speech synthesizer. The range for
+		the soft driver seems to be 0-2. This seems to make no
+		difference if using espeak and the espeakup connector.
+		TODO: does espeakup support different tonalities?
+
+What:		/sys/accessibility/speakup/soft/trigger_time
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	TODO:
+
+What:		/sys/accessibility/speakup/soft/voice
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Gets or sets the voice used by the synthesizer if the
+		synthesizer can speak in more than one voice. The range for the
+		soft driver is 0-7. Note that while espeak supports multiple
+		voices, this parameter will not set the voice when the espeakup
+		connector is used  between speakup and espeak.
+
+What:		/sys/accessibility/speakup/soft/vol
+KernelVersion:	2.6
+Contact:	speakup@linux-speakup.org
+Description:	Gets or sets the volume of the speech synthesizer. Range is 0-9,
+		with zero being the softest, and nine being the loudest.
+
-- 
cgit v1.2.3


From 5bdea6060618cfcf1459dca137e89aee038ac8b9 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Sun, 29 Sep 2019 22:09:45 -0500
Subject: Staging: fbtft: fix memory leak in fbtft_framebuffer_alloc

In fbtft_framebuffer_alloc the error handling path should take care of
releasing frame buffer after it is allocated via framebuffer_alloc, too.
Therefore, in two failure cases the goto destination is changed to
address this issue.

Fixes: c296d5f9957c ("staging: fbtft: core support")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@gmail.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20190930030949.28615-1-navid.emamdoost@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/fbtft/fbtft-core.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c
index cf5700a2ea66..a0a67aa517f0 100644
--- a/drivers/staging/fbtft/fbtft-core.c
+++ b/drivers/staging/fbtft/fbtft-core.c
@@ -714,7 +714,7 @@ struct fb_info *fbtft_framebuffer_alloc(struct fbtft_display *display,
 	if (par->gamma.curves && gamma) {
 		if (fbtft_gamma_parse_str(par, par->gamma.curves, gamma,
 					  strlen(gamma)))
-			goto alloc_fail;
+			goto release_framebuf;
 	}
 
 	/* Transmit buffer */
@@ -731,7 +731,7 @@ struct fb_info *fbtft_framebuffer_alloc(struct fbtft_display *display,
 	if (txbuflen > 0) {
 		txbuf = devm_kzalloc(par->info->device, txbuflen, GFP_KERNEL);
 		if (!txbuf)
-			goto alloc_fail;
+			goto release_framebuf;
 		par->txbuf.buf = txbuf;
 		par->txbuf.len = txbuflen;
 	}
@@ -753,6 +753,9 @@ struct fb_info *fbtft_framebuffer_alloc(struct fbtft_display *display,
 
 	return info;
 
+release_framebuf:
+	framebuffer_release(info);
+
 alloc_fail:
 	vfree(vmem);
 
-- 
cgit v1.2.3


From 6e58fc14d7ed9160dc6e0e55ac11dfc84ed578e1 Mon Sep 17 00:00:00 2001
From: Jia-Ye Li <jiayeli@synology.com>
Date: Wed, 25 Sep 2019 16:37:29 +0800
Subject: staging: exfat: Use kvzalloc() instead of kzalloc() for exfat_sb_info

Fix mount failed "Cannot allocate memory".

When the memory gets fragmented, kzalloc() might fail to allocate
physically contiguous pages for the struct exfat_sb_info (its size is
about 34KiB) even the total free memory is enough.
Use kvzalloc() to solve this problem.

Reviewed-by: Ethan Wu <ethanwu@synology.com>
Signed-off-by: Jia-Ye Li <jiayeli@synology.com>
Link: https://lore.kernel.org/r/20190925083729.4653-1-jiayeli@synology.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/exfat/exfat_super.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/exfat/exfat_super.c b/drivers/staging/exfat/exfat_super.c
index 229ecabe7a93..3b2b0ceb7297 100644
--- a/drivers/staging/exfat/exfat_super.c
+++ b/drivers/staging/exfat/exfat_super.c
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/time.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
 #include <linux/seq_file.h>
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
@@ -3450,7 +3451,7 @@ static void exfat_free_super(struct exfat_sb_info *sbi)
 		kfree(sbi->options.iocharset);
 	/* mutex_init is in exfat_fill_super function. only for 3.7+ */
 	mutex_destroy(&sbi->s_lock);
-	kfree(sbi);
+	kvfree(sbi);
 }
 
 static void exfat_put_super(struct super_block *sb)
@@ -3845,7 +3846,7 @@ static int exfat_fill_super(struct super_block *sb, void *data, int silent)
 	 * the filesystem, since we're only just about to mount
 	 * it and have no inodes etc active!
 	 */
-	sbi = kzalloc(sizeof(struct exfat_sb_info), GFP_KERNEL);
+	sbi = kvzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
 		return -ENOMEM;
 	mutex_init(&sbi->s_lock);
-- 
cgit v1.2.3


From 015664d15270a112c2371d812f03f7c579b35a73 Mon Sep 17 00:00:00 2001
From: Bastien Nocera <hadess@hadess.net>
Date: Mon, 23 Sep 2019 18:18:43 +0200
Subject: USB: rio500: Remove Rio 500 kernel driver

The Rio500 kernel driver has not been used by Rio500 owners since 2001
not long after the rio500 project added support for a user-space USB stack
through the very first versions of usbdevfs and then libusb.

Support for the kernel driver was removed from the upstream utilities
in 2008:
https://gitlab.freedesktop.org/hadess/rio500/commit/943f624ab721eb8281c287650fcc9e2026f6f5db

Cc: Cesar Miquel <miquel@df.uba.ar>
Signed-off-by: Bastien Nocera <hadess@hadess.net>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/6251c17584d220472ce882a3d9c199c401a51a71.camel@hadess.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/usb/rio.rst          | 109 --------
 MAINTAINERS                        |   7 -
 arch/arm/configs/badge4_defconfig  |   1 -
 arch/arm/configs/corgi_defconfig   |   1 -
 arch/arm/configs/pxa_defconfig     |   1 -
 arch/arm/configs/s3c2410_defconfig |   1 -
 arch/arm/configs/spitz_defconfig   |   1 -
 arch/mips/configs/mtx1_defconfig   |   1 -
 arch/mips/configs/rm200_defconfig  |   1 -
 drivers/usb/misc/Kconfig           |  10 -
 drivers/usb/misc/Makefile          |   1 -
 drivers/usb/misc/rio500.c          | 554 -------------------------------------
 drivers/usb/misc/rio500_usb.h      |  20 --
 13 files changed, 708 deletions(-)
 delete mode 100644 Documentation/usb/rio.rst
 delete mode 100644 drivers/usb/misc/rio500.c
 delete mode 100644 drivers/usb/misc/rio500_usb.h

diff --git a/Documentation/usb/rio.rst b/Documentation/usb/rio.rst
deleted file mode 100644
index ea73475471db..000000000000
--- a/Documentation/usb/rio.rst
+++ /dev/null
@@ -1,109 +0,0 @@
-============
-Diamonds Rio
-============
-
-Copyright (C) 1999, 2000 Bruce Tenison
-
-Portions Copyright (C) 1999, 2000 David Nelson
-
-Thanks to David Nelson for guidance and the usage of the scanner.txt
-and scanner.c files to model our driver and this informative file.
-
-Mar. 2, 2000
-
-Changes
-=======
-
-- Initial Revision
-
-
-Overview
-========
-
-This README will address issues regarding how to configure the kernel
-to access a RIO 500 mp3 player.
-Before I explain how to use this to access the Rio500 please be warned:
-
-.. warning::
-
-   Please note that this software is still under development.  The authors
-   are in no way responsible for any damage that may occur, no matter how
-   inconsequential.
-
-It seems that the Rio has a problem when sending .mp3 with low batteries.
-I suggest when the batteries are low and you want to transfer stuff that you
-replace it with a fresh one. In my case, what happened is I lost two 16kb
-blocks (they are no longer usable to store information to it). But I don't
-know if that's normal or not; it could simply be a problem with the flash
-memory.
-
-In an extreme case, I left my Rio playing overnight and the batteries wore
-down to nothing and appear to have corrupted the flash memory. My RIO
-needed to be replaced as a result.  Diamond tech support is aware of the
-problem.  Do NOT allow your batteries to wear down to nothing before
-changing them.  It appears RIO 500 firmware does not handle low battery
-power well at all.
-
-On systems with OHCI controllers, the kernel OHCI code appears to have
-power on problems with some chipsets.  If you are having problems
-connecting to your RIO 500, try turning it on first and then plugging it
-into the USB cable.
-
-Contact Information
--------------------
-
-   The main page for the project is hosted at sourceforge.net in the following
-   URL: <http://rio500.sourceforge.net>. You can also go to the project's
-   sourceforge home page at: <http://sourceforge.net/projects/rio500/>.
-   There is also a mailing list: rio500-users@lists.sourceforge.net
-
-Authors
--------
-
-Most of the code was written by Cesar Miquel <miquel@df.uba.ar>. Keith
-Clayton <kclayton@jps.net> is incharge of the PPC port and making sure
-things work there. Bruce Tenison <btenison@dibbs.net> is adding support
-for .fon files and also does testing. The program will mostly sure be
-re-written and Pete Ikusz along with the rest will re-design it. I would
-also like to thank Tri Nguyen <tmn_3022000@hotmail.com> who provided use
-with some important information regarding the communication with the Rio.
-
-Additional Information and userspace tools
-
-	http://rio500.sourceforge.net/
-
-
-Requirements
-============
-
-A host with a USB port running a Linux kernel with RIO 500 support enabled.
-
-The driver is a module called rio500, which should be automatically loaded
-as you plug in your device. If that fails you can manually load it with
-
-  modprobe rio500
-
-Udev should automatically create a device node as soon as plug in your device.
-If that fails, you can manually add a device for the USB rio500::
-
-  mknod /dev/usb/rio500 c 180 64
-
-In that case, set appropriate permissions for /dev/usb/rio500 (don't forget
-about group and world permissions).  Both read and write permissions are
-required for proper operation.
-
-That's it.  The Rio500 Utils at: http://rio500.sourceforge.net should
-be able to access the rio500.
-
-Limits
-======
-
-You can use only a single rio500 device at a time with your computer.
-
-Bugs
-====
-
-If you encounter any problems feel free to drop me an email.
-
-Bruce Tenison
-btenison@dibbs.net
diff --git a/MAINTAINERS b/MAINTAINERS
index 296de2b51c83..3bcf493f3f8c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16762,13 +16762,6 @@ W:	http://www.linux-usb.org/usbnet
 S:	Maintained
 F:	drivers/net/usb/dm9601.c
 
-USB DIAMOND RIO500 DRIVER
-M:	Cesar Miquel <miquel@df.uba.ar>
-L:	rio500-users@lists.sourceforge.net
-W:	http://rio500.sourceforge.net
-S:	Maintained
-F:	drivers/usb/misc/rio500*
-
 USB EHCI DRIVER
 M:	Alan Stern <stern@rowland.harvard.edu>
 L:	linux-usb@vger.kernel.org
diff --git a/arch/arm/configs/badge4_defconfig b/arch/arm/configs/badge4_defconfig
index 5ae5b5228467..ef484c4cfd1a 100644
--- a/arch/arm/configs/badge4_defconfig
+++ b/arch/arm/configs/badge4_defconfig
@@ -91,7 +91,6 @@ CONFIG_USB_SERIAL_PL2303=m
 CONFIG_USB_SERIAL_CYBERJACK=m
 CONFIG_USB_SERIAL_XIRCOM=m
 CONFIG_USB_SERIAL_OMNINET=m
-CONFIG_USB_RIO500=m
 CONFIG_EXT2_FS=m
 CONFIG_EXT3_FS=m
 CONFIG_MSDOS_FS=y
diff --git a/arch/arm/configs/corgi_defconfig b/arch/arm/configs/corgi_defconfig
index e4f6442588e7..4fec2ec379ad 100644
--- a/arch/arm/configs/corgi_defconfig
+++ b/arch/arm/configs/corgi_defconfig
@@ -195,7 +195,6 @@ CONFIG_USB_SERIAL_XIRCOM=m
 CONFIG_USB_SERIAL_OMNINET=m
 CONFIG_USB_EMI62=m
 CONFIG_USB_EMI26=m
-CONFIG_USB_RIO500=m
 CONFIG_USB_LEGOTOWER=m
 CONFIG_USB_LCD=m
 CONFIG_USB_CYTHERM=m
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index 787c3f9be414..b817c57f05f1 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -581,7 +581,6 @@ CONFIG_USB_SERIAL_XIRCOM=m
 CONFIG_USB_SERIAL_OMNINET=m
 CONFIG_USB_EMI62=m
 CONFIG_USB_EMI26=m
-CONFIG_USB_RIO500=m
 CONFIG_USB_LEGOTOWER=m
 CONFIG_USB_LCD=m
 CONFIG_USB_CYTHERM=m
diff --git a/arch/arm/configs/s3c2410_defconfig b/arch/arm/configs/s3c2410_defconfig
index 95b5a4ffddea..73ed73a8785a 100644
--- a/arch/arm/configs/s3c2410_defconfig
+++ b/arch/arm/configs/s3c2410_defconfig
@@ -327,7 +327,6 @@ CONFIG_USB_EMI62=m
 CONFIG_USB_EMI26=m
 CONFIG_USB_ADUTUX=m
 CONFIG_USB_SEVSEG=m
-CONFIG_USB_RIO500=m
 CONFIG_USB_LEGOTOWER=m
 CONFIG_USB_LCD=m
 CONFIG_USB_CYPRESS_CY7C63=m
diff --git a/arch/arm/configs/spitz_defconfig b/arch/arm/configs/spitz_defconfig
index 4fb51d665abb..a1cdbfa064c5 100644
--- a/arch/arm/configs/spitz_defconfig
+++ b/arch/arm/configs/spitz_defconfig
@@ -189,7 +189,6 @@ CONFIG_USB_SERIAL_XIRCOM=m
 CONFIG_USB_SERIAL_OMNINET=m
 CONFIG_USB_EMI62=m
 CONFIG_USB_EMI26=m
-CONFIG_USB_RIO500=m
 CONFIG_USB_LEGOTOWER=m
 CONFIG_USB_LCD=m
 CONFIG_USB_CYTHERM=m
diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig
index 16bef819fe98..914af125a7fa 100644
--- a/arch/mips/configs/mtx1_defconfig
+++ b/arch/mips/configs/mtx1_defconfig
@@ -571,7 +571,6 @@ CONFIG_USB_SERIAL_OMNINET=m
 CONFIG_USB_EMI62=m
 CONFIG_USB_EMI26=m
 CONFIG_USB_ADUTUX=m
-CONFIG_USB_RIO500=m
 CONFIG_USB_LEGOTOWER=m
 CONFIG_USB_LCD=m
 CONFIG_USB_CYPRESS_CY7C63=m
diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig
index 8762e75f5d5f..2c7adea7638f 100644
--- a/arch/mips/configs/rm200_defconfig
+++ b/arch/mips/configs/rm200_defconfig
@@ -314,7 +314,6 @@ CONFIG_USB_SERIAL_SAFE_PADDED=y
 CONFIG_USB_SERIAL_CYBERJACK=m
 CONFIG_USB_SERIAL_XIRCOM=m
 CONFIG_USB_SERIAL_OMNINET=m
-CONFIG_USB_RIO500=m
 CONFIG_USB_LEGOTOWER=m
 CONFIG_USB_LCD=m
 CONFIG_USB_CYTHERM=m
diff --git a/drivers/usb/misc/Kconfig b/drivers/usb/misc/Kconfig
index bdae62b2ffe0..9bce583aada3 100644
--- a/drivers/usb/misc/Kconfig
+++ b/drivers/usb/misc/Kconfig
@@ -47,16 +47,6 @@ config USB_SEVSEG
 	  To compile this driver as a module, choose M here: the
 	  module will be called usbsevseg.
 
-config USB_RIO500
-	tristate "USB Diamond Rio500 support"
-	help
-	  Say Y here if you want to connect a USB Rio500 mp3 player to your
-	  computer's USB port. Please read <file:Documentation/usb/rio.rst>
-	  for more information.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called rio500.
-
 config USB_LEGOTOWER
 	tristate "USB Lego Infrared Tower support"
 	help
diff --git a/drivers/usb/misc/Makefile b/drivers/usb/misc/Makefile
index 109f54f5b9aa..0d416eb624bb 100644
--- a/drivers/usb/misc/Makefile
+++ b/drivers/usb/misc/Makefile
@@ -17,7 +17,6 @@ obj-$(CONFIG_USB_ISIGHTFW)		+= isight_firmware.o
 obj-$(CONFIG_USB_LCD)			+= usblcd.o
 obj-$(CONFIG_USB_LD)			+= ldusb.o
 obj-$(CONFIG_USB_LEGOTOWER)		+= legousbtower.o
-obj-$(CONFIG_USB_RIO500)		+= rio500.o
 obj-$(CONFIG_USB_TEST)			+= usbtest.o
 obj-$(CONFIG_USB_EHSET_TEST_FIXTURE)    += ehset.o
 obj-$(CONFIG_USB_TRANCEVIBRATOR)	+= trancevibrator.o
diff --git a/drivers/usb/misc/rio500.c b/drivers/usb/misc/rio500.c
deleted file mode 100644
index 30cae5e1954d..000000000000
--- a/drivers/usb/misc/rio500.c
+++ /dev/null
@@ -1,554 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/* -*- linux-c -*- */
-
-/* 
- * Driver for USB Rio 500
- *
- * Cesar Miquel (miquel@df.uba.ar)
- * 
- * based on hp_scanner.c by David E. Nelson (dnelson@jump.net)
- *
- * Based upon mouse.c (Brad Keryan) and printer.c (Michael Gee).
- *
- * Changelog:
- * 30/05/2003  replaced lock/unlock kernel with up/down
- *             Daniele Bellucci  bellucda@tiscali.it
- * */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/signal.h>
-#include <linux/sched/signal.h>
-#include <linux/mutex.h>
-#include <linux/errno.h>
-#include <linux/random.h>
-#include <linux/poll.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/usb.h>
-#include <linux/wait.h>
-
-#include "rio500_usb.h"
-
-#define DRIVER_AUTHOR "Cesar Miquel <miquel@df.uba.ar>"
-#define DRIVER_DESC "USB Rio 500 driver"
-
-#define RIO_MINOR	64
-
-/* stall/wait timeout for rio */
-#define NAK_TIMEOUT (HZ)
-
-#define IBUF_SIZE 0x1000
-
-/* Size of the rio buffer */
-#define OBUF_SIZE 0x10000
-
-struct rio_usb_data {
-        struct usb_device *rio_dev;     /* init: probe_rio */
-        unsigned int ifnum;             /* Interface number of the USB device */
-        int isopen;                     /* nz if open */
-        int present;                    /* Device is present on the bus */
-        char *obuf, *ibuf;              /* transfer buffers */
-        char bulk_in_ep, bulk_out_ep;   /* Endpoint assignments */
-        wait_queue_head_t wait_q;       /* for timeouts */
-};
-
-static DEFINE_MUTEX(rio500_mutex);
-static struct rio_usb_data rio_instance;
-
-static int open_rio(struct inode *inode, struct file *file)
-{
-	struct rio_usb_data *rio = &rio_instance;
-
-	/* against disconnect() */
-	mutex_lock(&rio500_mutex);
-
-	if (rio->isopen || !rio->present) {
-		mutex_unlock(&rio500_mutex);
-		return -EBUSY;
-	}
-	rio->isopen = 1;
-
-	init_waitqueue_head(&rio->wait_q);
-
-
-	dev_info(&rio->rio_dev->dev, "Rio opened.\n");
-	mutex_unlock(&rio500_mutex);
-
-	return 0;
-}
-
-static int close_rio(struct inode *inode, struct file *file)
-{
-	struct rio_usb_data *rio = &rio_instance;
-
-	/* against disconnect() */
-	mutex_lock(&rio500_mutex);
-
-	rio->isopen = 0;
-	if (!rio->present) {
-		/* cleanup has been delayed */
-		kfree(rio->ibuf);
-		kfree(rio->obuf);
-		rio->ibuf = NULL;
-		rio->obuf = NULL;
-	} else {
-		dev_info(&rio->rio_dev->dev, "Rio closed.\n");
-	}
-	mutex_unlock(&rio500_mutex);
-	return 0;
-}
-
-static long ioctl_rio(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	struct RioCommand rio_cmd;
-	struct rio_usb_data *rio = &rio_instance;
-	void __user *data;
-	unsigned char *buffer;
-	int result, requesttype;
-	int retries;
-	int retval=0;
-
-	mutex_lock(&rio500_mutex);
-        /* Sanity check to make sure rio is connected, powered, etc */
-        if (rio->present == 0 || rio->rio_dev == NULL) {
-		retval = -ENODEV;
-		goto err_out;
-	}
-
-	switch (cmd) {
-	case RIO_RECV_COMMAND:
-		data = (void __user *) arg;
-		if (data == NULL)
-			break;
-		if (copy_from_user(&rio_cmd, data, sizeof(struct RioCommand))) {
-			retval = -EFAULT;
-			goto err_out;
-		}
-		if (rio_cmd.length < 0 || rio_cmd.length > PAGE_SIZE) {
-			retval = -EINVAL;
-			goto err_out;
-		}
-		buffer = (unsigned char *) __get_free_page(GFP_KERNEL);
-		if (buffer == NULL) {
-			retval = -ENOMEM;
-			goto err_out;
-		}
-		if (copy_from_user(buffer, rio_cmd.buffer, rio_cmd.length)) {
-			retval = -EFAULT;
-			free_page((unsigned long) buffer);
-			goto err_out;
-		}
-
-		requesttype = rio_cmd.requesttype | USB_DIR_IN |
-		    USB_TYPE_VENDOR | USB_RECIP_DEVICE;
-		dev_dbg(&rio->rio_dev->dev,
-			"sending command:reqtype=%0x req=%0x value=%0x index=%0x len=%0x\n",
-			requesttype, rio_cmd.request, rio_cmd.value,
-			rio_cmd.index, rio_cmd.length);
-		/* Send rio control message */
-		retries = 3;
-		while (retries) {
-			result = usb_control_msg(rio->rio_dev,
-						 usb_rcvctrlpipe(rio-> rio_dev, 0),
-						 rio_cmd.request,
-						 requesttype,
-						 rio_cmd.value,
-						 rio_cmd.index, buffer,
-						 rio_cmd.length,
-						 jiffies_to_msecs(rio_cmd.timeout));
-			if (result == -ETIMEDOUT)
-				retries--;
-			else if (result < 0) {
-				dev_err(&rio->rio_dev->dev,
-					"Error executing ioctrl. code = %d\n",
-					result);
-				retries = 0;
-			} else {
-				dev_dbg(&rio->rio_dev->dev,
-					"Executed ioctl. Result = %d (data=%02x)\n",
-					result, buffer[0]);
-				if (copy_to_user(rio_cmd.buffer, buffer,
-						 rio_cmd.length)) {
-					free_page((unsigned long) buffer);
-					retval = -EFAULT;
-					goto err_out;
-				}
-				retries = 0;
-			}
-
-			/* rio_cmd.buffer contains a raw stream of single byte
-			   data which has been returned from rio.  Data is
-			   interpreted at application level.  For data that
-			   will be cast to data types longer than 1 byte, data
-			   will be little_endian and will potentially need to
-			   be swapped at the app level */
-
-		}
-		free_page((unsigned long) buffer);
-		break;
-
-	case RIO_SEND_COMMAND:
-		data = (void __user *) arg;
-		if (data == NULL)
-			break;
-		if (copy_from_user(&rio_cmd, data, sizeof(struct RioCommand))) {
-			retval = -EFAULT;
-			goto err_out;
-		}
-		if (rio_cmd.length < 0 || rio_cmd.length > PAGE_SIZE) {
-			retval = -EINVAL;
-			goto err_out;
-		}
-		buffer = (unsigned char *) __get_free_page(GFP_KERNEL);
-		if (buffer == NULL) {
-			retval = -ENOMEM;
-			goto err_out;
-		}
-		if (copy_from_user(buffer, rio_cmd.buffer, rio_cmd.length)) {
-			free_page((unsigned long)buffer);
-			retval = -EFAULT;
-			goto err_out;
-		}
-
-		requesttype = rio_cmd.requesttype | USB_DIR_OUT |
-		    USB_TYPE_VENDOR | USB_RECIP_DEVICE;
-		dev_dbg(&rio->rio_dev->dev,
-			"sending command: reqtype=%0x req=%0x value=%0x index=%0x len=%0x\n",
-			requesttype, rio_cmd.request, rio_cmd.value,
-			rio_cmd.index, rio_cmd.length);
-		/* Send rio control message */
-		retries = 3;
-		while (retries) {
-			result = usb_control_msg(rio->rio_dev,
-						 usb_sndctrlpipe(rio-> rio_dev, 0),
-						 rio_cmd.request,
-						 requesttype,
-						 rio_cmd.value,
-						 rio_cmd.index, buffer,
-						 rio_cmd.length,
-						 jiffies_to_msecs(rio_cmd.timeout));
-			if (result == -ETIMEDOUT)
-				retries--;
-			else if (result < 0) {
-				dev_err(&rio->rio_dev->dev,
-					"Error executing ioctrl. code = %d\n",
-					result);
-				retries = 0;
-			} else {
-				dev_dbg(&rio->rio_dev->dev,
-					"Executed ioctl. Result = %d\n", result);
-				retries = 0;
-
-			}
-
-		}
-		free_page((unsigned long) buffer);
-		break;
-
-	default:
-		retval = -ENOTTY;
-		break;
-	}
-
-
-err_out:
-	mutex_unlock(&rio500_mutex);
-	return retval;
-}
-
-static ssize_t
-write_rio(struct file *file, const char __user *buffer,
-	  size_t count, loff_t * ppos)
-{
-	DEFINE_WAIT(wait);
-	struct rio_usb_data *rio = &rio_instance;
-
-	unsigned long copy_size;
-	unsigned long bytes_written = 0;
-	unsigned int partial;
-
-	int result = 0;
-	int maxretry;
-	int errn = 0;
-	int intr;
-
-	intr = mutex_lock_interruptible(&rio500_mutex);
-	if (intr)
-		return -EINTR;
-        /* Sanity check to make sure rio is connected, powered, etc */
-        if (rio->present == 0 || rio->rio_dev == NULL) {
-		mutex_unlock(&rio500_mutex);
-		return -ENODEV;
-	}
-
-
-
-	do {
-		unsigned long thistime;
-		char *obuf = rio->obuf;
-
-		thistime = copy_size =
-		    (count >= OBUF_SIZE) ? OBUF_SIZE : count;
-		if (copy_from_user(rio->obuf, buffer, copy_size)) {
-			errn = -EFAULT;
-			goto error;
-		}
-		maxretry = 5;
-		while (thistime) {
-			if (!rio->rio_dev) {
-				errn = -ENODEV;
-				goto error;
-			}
-			if (signal_pending(current)) {
-				mutex_unlock(&rio500_mutex);
-				return bytes_written ? bytes_written : -EINTR;
-			}
-
-			result = usb_bulk_msg(rio->rio_dev,
-					 usb_sndbulkpipe(rio->rio_dev, 2),
-					 obuf, thistime, &partial, 5000);
-
-			dev_dbg(&rio->rio_dev->dev,
-				"write stats: result:%d thistime:%lu partial:%u\n",
-				result, thistime, partial);
-
-			if (result == -ETIMEDOUT) {	/* NAK - so hold for a while */
-				if (!maxretry--) {
-					errn = -ETIME;
-					goto error;
-				}
-				prepare_to_wait(&rio->wait_q, &wait, TASK_INTERRUPTIBLE);
-				schedule_timeout(NAK_TIMEOUT);
-				finish_wait(&rio->wait_q, &wait);
-				continue;
-			} else if (!result && partial) {
-				obuf += partial;
-				thistime -= partial;
-			} else
-				break;
-		}
-		if (result) {
-			dev_err(&rio->rio_dev->dev, "Write Whoops - %x\n",
-				result);
-			errn = -EIO;
-			goto error;
-		}
-		bytes_written += copy_size;
-		count -= copy_size;
-		buffer += copy_size;
-	} while (count > 0);
-
-	mutex_unlock(&rio500_mutex);
-
-	return bytes_written ? bytes_written : -EIO;
-
-error:
-	mutex_unlock(&rio500_mutex);
-	return errn;
-}
-
-static ssize_t
-read_rio(struct file *file, char __user *buffer, size_t count, loff_t * ppos)
-{
-	DEFINE_WAIT(wait);
-	struct rio_usb_data *rio = &rio_instance;
-	ssize_t read_count;
-	unsigned int partial;
-	int this_read;
-	int result;
-	int maxretry = 10;
-	char *ibuf;
-	int intr;
-
-	intr = mutex_lock_interruptible(&rio500_mutex);
-	if (intr)
-		return -EINTR;
-	/* Sanity check to make sure rio is connected, powered, etc */
-        if (rio->present == 0 || rio->rio_dev == NULL) {
-		mutex_unlock(&rio500_mutex);
-		return -ENODEV;
-	}
-
-	ibuf = rio->ibuf;
-
-	read_count = 0;
-
-
-	while (count > 0) {
-		if (signal_pending(current)) {
-			mutex_unlock(&rio500_mutex);
-			return read_count ? read_count : -EINTR;
-		}
-		if (!rio->rio_dev) {
-			mutex_unlock(&rio500_mutex);
-			return -ENODEV;
-		}
-		this_read = (count >= IBUF_SIZE) ? IBUF_SIZE : count;
-
-		result = usb_bulk_msg(rio->rio_dev,
-				      usb_rcvbulkpipe(rio->rio_dev, 1),
-				      ibuf, this_read, &partial,
-				      8000);
-
-		dev_dbg(&rio->rio_dev->dev,
-			"read stats: result:%d this_read:%u partial:%u\n",
-			result, this_read, partial);
-
-		if (partial) {
-			count = this_read = partial;
-		} else if (result == -ETIMEDOUT || result == 15) {	/* FIXME: 15 ??? */
-			if (!maxretry--) {
-				mutex_unlock(&rio500_mutex);
-				dev_err(&rio->rio_dev->dev,
-					"read_rio: maxretry timeout\n");
-				return -ETIME;
-			}
-			prepare_to_wait(&rio->wait_q, &wait, TASK_INTERRUPTIBLE);
-			schedule_timeout(NAK_TIMEOUT);
-			finish_wait(&rio->wait_q, &wait);
-			continue;
-		} else if (result != -EREMOTEIO) {
-			mutex_unlock(&rio500_mutex);
-			dev_err(&rio->rio_dev->dev,
-				"Read Whoops - result:%d partial:%u this_read:%u\n",
-				result, partial, this_read);
-			return -EIO;
-		} else {
-			mutex_unlock(&rio500_mutex);
-			return (0);
-		}
-
-		if (this_read) {
-			if (copy_to_user(buffer, ibuf, this_read)) {
-				mutex_unlock(&rio500_mutex);
-				return -EFAULT;
-			}
-			count -= this_read;
-			read_count += this_read;
-			buffer += this_read;
-		}
-	}
-	mutex_unlock(&rio500_mutex);
-	return read_count;
-}
-
-static const struct file_operations usb_rio_fops = {
-	.owner =	THIS_MODULE,
-	.read =		read_rio,
-	.write =	write_rio,
-	.unlocked_ioctl = ioctl_rio,
-	.open =		open_rio,
-	.release =	close_rio,
-	.llseek =	noop_llseek,
-};
-
-static struct usb_class_driver usb_rio_class = {
-	.name =		"rio500%d",
-	.fops =		&usb_rio_fops,
-	.minor_base =	RIO_MINOR,
-};
-
-static int probe_rio(struct usb_interface *intf,
-		     const struct usb_device_id *id)
-{
-	struct usb_device *dev = interface_to_usbdev(intf);
-	struct rio_usb_data *rio = &rio_instance;
-	int retval = -ENOMEM;
-	char *ibuf, *obuf;
-
-	if (rio->present) {
-		dev_info(&intf->dev, "Second USB Rio at address %d refused\n", dev->devnum);
-		return -EBUSY;
-	}
-	dev_info(&intf->dev, "USB Rio found at address %d\n", dev->devnum);
-
-	obuf = kmalloc(OBUF_SIZE, GFP_KERNEL);
-	if (!obuf) {
-		dev_err(&dev->dev,
-			"probe_rio: Not enough memory for the output buffer\n");
-		goto err_obuf;
-	}
-	dev_dbg(&intf->dev, "obuf address: %p\n", obuf);
-
-	ibuf = kmalloc(IBUF_SIZE, GFP_KERNEL);
-	if (!ibuf) {
-		dev_err(&dev->dev,
-			"probe_rio: Not enough memory for the input buffer\n");
-		goto err_ibuf;
-	}
-	dev_dbg(&intf->dev, "ibuf address: %p\n", ibuf);
-
-	mutex_lock(&rio500_mutex);
-	rio->rio_dev = dev;
-	rio->ibuf = ibuf;
-	rio->obuf = obuf;
-	rio->present = 1;
-	mutex_unlock(&rio500_mutex);
-
-	retval = usb_register_dev(intf, &usb_rio_class);
-	if (retval) {
-		dev_err(&dev->dev,
-			"Not able to get a minor for this device.\n");
-		goto err_register;
-	}
-
-	usb_set_intfdata(intf, rio);
-	return retval;
-
- err_register:
-	mutex_lock(&rio500_mutex);
-	rio->present = 0;
-	mutex_unlock(&rio500_mutex);
- err_ibuf:
-	kfree(obuf);
- err_obuf:
-	return retval;
-}
-
-static void disconnect_rio(struct usb_interface *intf)
-{
-	struct rio_usb_data *rio = usb_get_intfdata (intf);
-
-	usb_set_intfdata (intf, NULL);
-	if (rio) {
-		usb_deregister_dev(intf, &usb_rio_class);
-
-		mutex_lock(&rio500_mutex);
-		if (rio->isopen) {
-			rio->isopen = 0;
-			/* better let it finish - the release will do whats needed */
-			rio->rio_dev = NULL;
-			mutex_unlock(&rio500_mutex);
-			return;
-		}
-		kfree(rio->ibuf);
-		kfree(rio->obuf);
-
-		dev_info(&intf->dev, "USB Rio disconnected.\n");
-
-		rio->present = 0;
-		mutex_unlock(&rio500_mutex);
-	}
-}
-
-static const struct usb_device_id rio_table[] = {
-	{ USB_DEVICE(0x0841, 1) }, 		/* Rio 500 */
-	{ }					/* Terminating entry */
-};
-
-MODULE_DEVICE_TABLE (usb, rio_table);
-
-static struct usb_driver rio_driver = {
-	.name =		"rio500",
-	.probe =	probe_rio,
-	.disconnect =	disconnect_rio,
-	.id_table =	rio_table,
-};
-
-module_usb_driver(rio_driver);
-
-MODULE_AUTHOR( DRIVER_AUTHOR );
-MODULE_DESCRIPTION( DRIVER_DESC );
-MODULE_LICENSE("GPL");
-
diff --git a/drivers/usb/misc/rio500_usb.h b/drivers/usb/misc/rio500_usb.h
deleted file mode 100644
index 6db7a5863496..000000000000
--- a/drivers/usb/misc/rio500_usb.h
+++ /dev/null
@@ -1,20 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*  ----------------------------------------------------------------------
-    Copyright (C) 2000  Cesar Miquel  (miquel@df.uba.ar)
-    ---------------------------------------------------------------------- */
-
-#define RIO_SEND_COMMAND			0x1
-#define RIO_RECV_COMMAND			0x2
-
-#define RIO_DIR_OUT               	        0x0
-#define RIO_DIR_IN				0x1
-
-struct RioCommand {
-	short length;
-	int request;
-	int requesttype;
-	int value;
-	int index;
-	void __user *buffer;
-	int timeout;
-};
-- 
cgit v1.2.3


From dfbac2f4da6a0c4a8f6b4d715a4077a7b8df53ad Mon Sep 17 00:00:00 2001
From: Reinhard Speyerer <rspmn@arcor.de>
Date: Thu, 3 Oct 2019 18:53:21 +0200
Subject: USB: serial: option: add support for Cinterion CLS8 devices

Add support for the serial ports of Cinterion CLS8 devices.

T:  Bus=01 Lev=03 Prnt=05 Port=01 Cnt=02 Dev#= 25 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1e2d ProdID=00b0 Rev= 3.18
S:  Manufacturer=GEMALTO
S:  Product=USB Modem
C:* #Ifs= 5 Cfg#= 1 Atr=80 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=83(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=85(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=87(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=89(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Signed-off-by: Reinhard Speyerer <rspmn@arcor.de>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/option.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 10ac3610d922..06ab016be0b6 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -419,6 +419,7 @@ static void option_instat_callback(struct urb *urb);
 #define CINTERION_PRODUCT_PH8_AUDIO		0x0083
 #define CINTERION_PRODUCT_AHXX_2RMNET		0x0084
 #define CINTERION_PRODUCT_AHXX_AUDIO		0x0085
+#define CINTERION_PRODUCT_CLS8			0x00b0
 
 /* Olivetti products */
 #define OLIVETTI_VENDOR_ID			0x0b3c
@@ -1855,6 +1856,8 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX_2RMNET, 0xff) },
 	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_AHXX_AUDIO, 0xff) },
+	{ USB_DEVICE_INTERFACE_CLASS(CINTERION_VENDOR_ID, CINTERION_PRODUCT_CLS8, 0xff),
+	  .driver_info = RSVD(0) | RSVD(4) },
 	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDM) },
 	{ USB_DEVICE(CINTERION_VENDOR_ID, CINTERION_PRODUCT_HC28_MDMNET) },
 	{ USB_DEVICE(SIEMENS_VENDOR_ID, CINTERION_PRODUCT_HC25_MDM) },
-- 
cgit v1.2.3


From 7d7e21fafdbc7fcf0854b877bd0975b487ed2717 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 3 Oct 2019 15:49:58 +0200
Subject: USB: serial: keyspan: fix NULL-derefs on open() and write()

Fix NULL-pointer dereferences on open() and write() which can be
triggered by a malicious USB device.

The current URB allocation helper would fail to initialise the newly
allocated URB if the device has unexpected endpoint descriptors,
something which could lead NULL-pointer dereferences in a number of
open() and write() paths when accessing the URB. For example:

	BUG: kernel NULL pointer dereference, address: 0000000000000000
	...
	RIP: 0010:usb_clear_halt+0x11/0xc0
	...
	Call Trace:
	 ? tty_port_open+0x4d/0xd0
	 keyspan_open+0x70/0x160 [keyspan]
	 serial_port_activate+0x5b/0x80 [usbserial]
	 tty_port_open+0x7b/0xd0
	 ? check_tty_count+0x43/0xa0
	 tty_open+0xf1/0x490

	BUG: kernel NULL pointer dereference, address: 0000000000000000
	...
	RIP: 0010:keyspan_write+0x14e/0x1f3 [keyspan]
	...
	Call Trace:
	 serial_write+0x43/0xa0 [usbserial]
	 n_tty_write+0x1af/0x4f0
	 ? do_wait_intr_irq+0x80/0x80
	 ? process_echoes+0x60/0x60
	 tty_write+0x13f/0x2f0

	BUG: kernel NULL pointer dereference, address: 0000000000000000
	...
	RIP: 0010:keyspan_usa26_send_setup+0x298/0x305 [keyspan]
	...
	Call Trace:
	 keyspan_open+0x10f/0x160 [keyspan]
	 serial_port_activate+0x5b/0x80 [usbserial]
	 tty_port_open+0x7b/0xd0
	 ? check_tty_count+0x43/0xa0
	 tty_open+0xf1/0x490

Fixes: fdcba53e2d58 ("fix for bugzilla #7544 (keyspan USB-to-serial converter)")
Cc: stable <stable@vger.kernel.org>	# 2.6.21
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/keyspan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/serial/keyspan.c b/drivers/usb/serial/keyspan.c
index d34779fe4a8d..e66a59ef43a1 100644
--- a/drivers/usb/serial/keyspan.c
+++ b/drivers/usb/serial/keyspan.c
@@ -1741,8 +1741,8 @@ static struct urb *keyspan_setup_urb(struct usb_serial *serial, int endpoint,
 
 	ep_desc = find_ep(serial, endpoint);
 	if (!ep_desc) {
-		/* leak the urb, something's wrong and the callers don't care */
-		return urb;
+		usb_free_urb(urb);
+		return NULL;
 	}
 	if (usb_endpoint_xfer_int(ep_desc)) {
 		ep_type_name = "INT";
-- 
cgit v1.2.3


From 0aa760382040cc3d70b538ade56ba9c37ed8b702 Mon Sep 17 00:00:00 2001
From: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Date: Thu, 3 Oct 2019 21:31:32 +0200
Subject: dt-bindings: usb: Fix references to usb-hcd.yaml
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

usb-hcd.txt has been converted to YAML. Update references accordingly.

Fixes: 14ec072a19ad ("dt-bindings: usb: Convert USB HCD generic binding to YAML")
Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Link: https://lore.kernel.org/r/20191003193132.17758-1-j.neuschaefer@gmx.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt | 4 ++--
 Documentation/devicetree/bindings/usb/mediatek,mtu3.txt     | 4 ++--
 Documentation/devicetree/bindings/usb/usb-uhci.txt          | 2 +-
 Documentation/devicetree/bindings/usb/usb-xhci.txt          | 4 ++--
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt
index f3e4acecabe8..42d8814f903a 100644
--- a/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt
+++ b/Documentation/devicetree/bindings/usb/mediatek,mtk-xhci.txt
@@ -33,7 +33,7 @@ Required properties:
 	"dma_ck": dma_bus clock for data transfer by DMA,
 	"xhci_ck": controller clock
 
- - phys : see usb-hcd.txt in the current directory
+ - phys : see usb-hcd.yaml in the current directory
 
 Optional properties:
  - wakeup-source : enable USB remote wakeup;
@@ -53,7 +53,7 @@ Optional properties:
 	See: Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
  - imod-interval-ns: default interrupt moderation interval is 5000ns
 
-additionally the properties from usb-hcd.txt (in the current directory) are
+additionally the properties from usb-hcd.yaml (in the current directory) are
 supported.
 
 Example:
diff --git a/Documentation/devicetree/bindings/usb/mediatek,mtu3.txt b/Documentation/devicetree/bindings/usb/mediatek,mtu3.txt
index b9af7f5ee91d..e0ae6096f7ac 100644
--- a/Documentation/devicetree/bindings/usb/mediatek,mtu3.txt
+++ b/Documentation/devicetree/bindings/usb/mediatek,mtu3.txt
@@ -17,7 +17,7 @@ Required properties:
  - clock-names : must contain "sys_ck" for clock of controller,
 	the following clocks are optional:
 	"ref_ck", "mcu_ck" and "dma_ck";
- - phys : see usb-hcd.txt in the current directory
+ - phys : see usb-hcd.yaml in the current directory
  - dr_mode : should be one of "host", "peripheral" or "otg",
 	refer to usb/generic.txt
 
@@ -60,7 +60,7 @@ Optional properties:
  - mediatek,u3p-dis-msk : mask to disable u3ports, bit0 for u3port0,
 	bit1 for u3port1, ... etc;
 
-additionally the properties from usb-hcd.txt (in the current directory) are
+additionally the properties from usb-hcd.yaml (in the current directory) are
 supported.
 
 Sub-nodes:
diff --git a/Documentation/devicetree/bindings/usb/usb-uhci.txt b/Documentation/devicetree/bindings/usb/usb-uhci.txt
index cc2e6f7d602e..d1702eb2c8bd 100644
--- a/Documentation/devicetree/bindings/usb/usb-uhci.txt
+++ b/Documentation/devicetree/bindings/usb/usb-uhci.txt
@@ -6,7 +6,7 @@ Required properties:
 - reg : Should contain 1 register ranges(address and length)
 - interrupts : UHCI controller interrupt
 
-additionally the properties from usb-hcd.txt (in the current directory) are
+additionally the properties from usb-hcd.yaml (in the current directory) are
 supported.
 
 Example:
diff --git a/Documentation/devicetree/bindings/usb/usb-xhci.txt b/Documentation/devicetree/bindings/usb/usb-xhci.txt
index 97400e8f8605..b49b819571f9 100644
--- a/Documentation/devicetree/bindings/usb/usb-xhci.txt
+++ b/Documentation/devicetree/bindings/usb/usb-xhci.txt
@@ -41,9 +41,9 @@ Optional properties:
   - usb3-lpm-capable: determines if platform is USB3 LPM capable
   - quirk-broken-port-ped: set if the controller has broken port disable mechanism
   - imod-interval-ns: default interrupt moderation interval is 5000ns
-  - phys : see usb-hcd.txt in the current directory
+  - phys : see usb-hcd.yaml in the current directory
 
-additionally the properties from usb-hcd.txt (in the current directory) are
+additionally the properties from usb-hcd.yaml (in the current directory) are
 supported.
 
 
-- 
cgit v1.2.3


From 177238c3d47d54b2ed8f0da7a4290db492f4a057 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 3 Oct 2019 09:09:31 +0200
Subject: USB: microtek: fix info-leak at probe

Add missing bulk-in endpoint sanity check to prevent uninitialised stack
data from being reported to the system log and used as endpoint
addresses.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable <stable@vger.kernel.org>
Reported-by: syzbot+5630ca7c3b2be5c9da5e@syzkaller.appspotmail.com
Signed-off-by: Johan Hovold <johan@kernel.org>
Acked-by: Oliver Neukum <oneukum@suse.com>
Link: https://lore.kernel.org/r/20191003070931.17009-1-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/image/microtek.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/usb/image/microtek.c b/drivers/usb/image/microtek.c
index 0a57c2cc8e5a..7a6b122c833f 100644
--- a/drivers/usb/image/microtek.c
+++ b/drivers/usb/image/microtek.c
@@ -716,6 +716,10 @@ static int mts_usb_probe(struct usb_interface *intf,
 
 	}
 
+	if (ep_in_current != &ep_in_set[2]) {
+		MTS_WARNING("couldn't find two input bulk endpoints. Bailing out.\n");
+		return -ENODEV;
+	}
 
 	if ( ep_out == -1 ) {
 		MTS_WARNING( "couldn't find an output bulk endpoint. Bailing out.\n" );
-- 
cgit v1.2.3


From 5f318dad72d227438f4da4c57afb2dfbd9dacddb Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 4 Sep 2019 13:01:02 +0300
Subject: usb: cdns3: Fix use after free in probe error handling

We can't use "wrap" after it has been freed.

Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Link: https://lore.kernel.org/r/20190904100102.GB7007@mwanda
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/cdns3-pci-wrap.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/cdns3/cdns3-pci-wrap.c b/drivers/usb/cdns3/cdns3-pci-wrap.c
index c41ddb61b857..b0a29efe7d31 100644
--- a/drivers/usb/cdns3/cdns3-pci-wrap.c
+++ b/drivers/usb/cdns3/cdns3-pci-wrap.c
@@ -159,8 +159,9 @@ static int cdns3_pci_probe(struct pci_dev *pdev,
 		wrap->plat_dev = platform_device_register_full(&plat_info);
 		if (IS_ERR(wrap->plat_dev)) {
 			pci_disable_device(pdev);
+			err = PTR_ERR(wrap->plat_dev);
 			kfree(wrap);
-			return PTR_ERR(wrap->plat_dev);
+			return err;
 		}
 	}
 
-- 
cgit v1.2.3


From 9816144313d33974bbd4599d4e8e554c11cae27e Mon Sep 17 00:00:00 2001
From: Pawel Laszczak <pawell@cadence.com>
Date: Thu, 26 Sep 2019 08:58:41 +0100
Subject: usb: cdns3: Fix sheduling with locks held.

Patch fix issue in cdns3_ep0_feature_handle_device function.

The function usleep_range can't be used there because this function is
called with locks held and IRQs disabled in
cdns3_device_thread_irq_handler().

To resolve this issue patch replaces usleep_range with mdelay.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Pawel Laszczak <pawell@cadence.com>
Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver")
Reviewed-by: Peter Chen <peter.chen@nxp.com>
Link: https://lore.kernel.org/r/1569484721-4424-1-git-send-email-pawell@cadence.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/ep0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/cdns3/ep0.c b/drivers/usb/cdns3/ep0.c
index 44f652e8b5a2..0445da0a5a0c 100644
--- a/drivers/usb/cdns3/ep0.c
+++ b/drivers/usb/cdns3/ep0.c
@@ -332,7 +332,7 @@ static int cdns3_ep0_feature_handle_device(struct cdns3_device *priv_dev,
 			 * for sending status stage.
 			 * This time should be less then 3ms.
 			 */
-			usleep_range(1000, 2000);
+			mdelay(1);
 			cdns3_set_register_bit(&priv_dev->regs->usb_cmd,
 					       USB_CMD_STMODE |
 					       USB_STS_TMODE_SEL(tmode - 1));
-- 
cgit v1.2.3


From 44efc269db7929f6275a1fa927ef082e533ecde0 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 25 Sep 2019 11:29:12 +0200
Subject: USB: adutux: fix use-after-free on disconnect

The driver was clearing its struct usb_device pointer, which it used as
an inverted disconnected flag, before deregistering the character device
and without serialising against racing release().

This could lead to a use-after-free if a racing release() callback
observes the cleared pointer and frees the driver data before
disconnect() is finished with it.

This could also lead to NULL-pointer dereferences in a racing open().

Fixes: f08812d5eb8f ("USB: FIx locks and urb->status in adutux (updated)")
Cc: stable <stable@vger.kernel.org>     # 2.6.24
Reported-by: syzbot+0243cb250a51eeefb8cc@syzkaller.appspotmail.com
Tested-by: syzbot+0243cb250a51eeefb8cc@syzkaller.appspotmail.com
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20190925092913.8608-1-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/adutux.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/misc/adutux.c b/drivers/usb/misc/adutux.c
index 344d523b0502..bcc138990e2f 100644
--- a/drivers/usb/misc/adutux.c
+++ b/drivers/usb/misc/adutux.c
@@ -762,14 +762,15 @@ static void adu_disconnect(struct usb_interface *interface)
 
 	dev = usb_get_intfdata(interface);
 
-	mutex_lock(&dev->mtx);	/* not interruptible */
-	dev->udev = NULL;	/* poison */
 	usb_deregister_dev(interface, &adu_class);
-	mutex_unlock(&dev->mtx);
 
 	mutex_lock(&adutux_mutex);
 	usb_set_intfdata(interface, NULL);
 
+	mutex_lock(&dev->mtx);	/* not interruptible */
+	dev->udev = NULL;	/* poison */
+	mutex_unlock(&dev->mtx);
+
 	/* if the device is not opened, then we clean up right now */
 	if (!dev->open_count)
 		adu_delete(dev);
-- 
cgit v1.2.3


From b2fa7baee744fde746c17bc1860b9c6f5c2eebb7 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 25 Sep 2019 11:29:13 +0200
Subject: USB: adutux: fix NULL-derefs on disconnect

The driver was using its struct usb_device pointer as an inverted
disconnected flag, but was setting it to NULL before making sure all
completion handlers had run. This could lead to a NULL-pointer
dereference in a number of dev_dbg statements in the completion handlers
which relies on said pointer.

The pointer was also dereferenced unconditionally in a dev_dbg statement
release() something which would lead to a NULL-deref whenever a device
was disconnected before the final character-device close if debugging
was enabled.

Fix this by unconditionally stopping all I/O and preventing
resubmissions by poisoning the interrupt URBs at disconnect and using a
dedicated disconnected flag.

This also makes sure that all I/O has completed by the time the
disconnect callback returns.

Fixes: 1ef37c6047fe ("USB: adutux: remove custom debug macro and module parameter")
Fixes: 66d4bc30d128 ("USB: adutux: remove custom debug macro")
Cc: stable <stable@vger.kernel.org>     # 3.12
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20190925092913.8608-2-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/adutux.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/misc/adutux.c b/drivers/usb/misc/adutux.c
index bcc138990e2f..f9efec719359 100644
--- a/drivers/usb/misc/adutux.c
+++ b/drivers/usb/misc/adutux.c
@@ -75,6 +75,7 @@ struct adu_device {
 	char			serial_number[8];
 
 	int			open_count; /* number of times this port has been opened */
+	unsigned long		disconnected:1;
 
 	char		*read_buffer_primary;
 	int			read_buffer_length;
@@ -116,7 +117,7 @@ static void adu_abort_transfers(struct adu_device *dev)
 {
 	unsigned long flags;
 
-	if (dev->udev == NULL)
+	if (dev->disconnected)
 		return;
 
 	/* shutdown transfer */
@@ -243,7 +244,7 @@ static int adu_open(struct inode *inode, struct file *file)
 	}
 
 	dev = usb_get_intfdata(interface);
-	if (!dev || !dev->udev) {
+	if (!dev) {
 		retval = -ENODEV;
 		goto exit_no_device;
 	}
@@ -326,7 +327,7 @@ static int adu_release(struct inode *inode, struct file *file)
 	}
 
 	adu_release_internal(dev);
-	if (dev->udev == NULL) {
+	if (dev->disconnected) {
 		/* the device was unplugged before the file was released */
 		if (!dev->open_count)	/* ... and we're the last user */
 			adu_delete(dev);
@@ -354,7 +355,7 @@ static ssize_t adu_read(struct file *file, __user char *buffer, size_t count,
 		return -ERESTARTSYS;
 
 	/* verify that the device wasn't unplugged */
-	if (dev->udev == NULL) {
+	if (dev->disconnected) {
 		retval = -ENODEV;
 		pr_err("No device or device unplugged %d\n", retval);
 		goto exit;
@@ -518,7 +519,7 @@ static ssize_t adu_write(struct file *file, const __user char *buffer,
 		goto exit_nolock;
 
 	/* verify that the device wasn't unplugged */
-	if (dev->udev == NULL) {
+	if (dev->disconnected) {
 		retval = -ENODEV;
 		pr_err("No device or device unplugged %d\n", retval);
 		goto exit;
@@ -764,11 +765,14 @@ static void adu_disconnect(struct usb_interface *interface)
 
 	usb_deregister_dev(interface, &adu_class);
 
+	usb_poison_urb(dev->interrupt_in_urb);
+	usb_poison_urb(dev->interrupt_out_urb);
+
 	mutex_lock(&adutux_mutex);
 	usb_set_intfdata(interface, NULL);
 
 	mutex_lock(&dev->mtx);	/* not interruptible */
-	dev->udev = NULL;	/* poison */
+	dev->disconnected = 1;
 	mutex_unlock(&dev->mtx);
 
 	/* if the device is not opened, then we clean up right now */
-- 
cgit v1.2.3


From 32a0721c6620b77504916dac0cea8ad497c4878a Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Tue, 17 Sep 2019 12:47:23 -0400
Subject: USB: yurex: Don't retry on unexpected errors

According to Greg KH, it has been generally agreed that when a USB
driver encounters an unknown error (or one it can't handle directly),
it should just give up instead of going into a potentially infinite
retry loop.

The three codes -EPROTO, -EILSEQ, and -ETIME fall into this category.
They can be caused by bus errors such as packet loss or corruption,
attempting to communicate with a disconnected device, or by malicious
firmware.  Nowadays the extent of packet loss or corruption is
negligible, so it should be safe for a driver to give up whenever one
of these errors occurs.

Although the yurex driver handles -EILSEQ errors in this way, it
doesn't do the same for -EPROTO (as discovered by the syzbot fuzzer)
or other unrecognized errors.  This patch adjusts the driver so that
it doesn't log an error message for -EPROTO or -ETIME, and it doesn't
retry after any errors.

Reported-and-tested-by: syzbot+b24d736f18a1541ad550@syzkaller.appspotmail.com
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
CC: Tomoki Sekiyama <tomoki.sekiyama@gmail.com>
CC: <stable@vger.kernel.org>

Link: https://lore.kernel.org/r/Pine.LNX.4.44L0.1909171245410.1590-100000@iolanthe.rowland.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/yurex.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 6715a128e6c8..8d52d4336c29 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -132,6 +132,7 @@ static void yurex_interrupt(struct urb *urb)
 	switch (status) {
 	case 0: /*success*/
 		break;
+	/* The device is terminated or messed up, give up */
 	case -EOVERFLOW:
 		dev_err(&dev->interface->dev,
 			"%s - overflow with length %d, actual length is %d\n",
@@ -140,12 +141,13 @@ static void yurex_interrupt(struct urb *urb)
 	case -ENOENT:
 	case -ESHUTDOWN:
 	case -EILSEQ:
-		/* The device is terminated, clean up */
+	case -EPROTO:
+	case -ETIME:
 		return;
 	default:
 		dev_err(&dev->interface->dev,
 			"%s - unknown status received: %d\n", __func__, status);
-		goto exit;
+		return;
 	}
 
 	/* handle received message */
@@ -177,7 +179,6 @@ static void yurex_interrupt(struct urb *urb)
 		break;
 	}
 
-exit:
 	retval = usb_submit_urb(dev->urb, GFP_ATOMIC);
 	if (retval) {
 		dev_err(&dev->interface->dev, "%s - usb_submit_urb failed: %d\n",
-- 
cgit v1.2.3


From 3f384d7c490374b2ae8f61a6c67f14deab77bab2 Mon Sep 17 00:00:00 2001
From: Mao Wenan <maowenan@huawei.com>
Date: Mon, 16 Sep 2019 23:09:21 +0800
Subject: usbip: vhci_hcd indicate failed message

If the return value of vhci_init_attr_group and
sysfs_create_group is non-zero, which mean they failed
to init attr_group and create sysfs group, so it would
better add 'failed' message to indicate that.
This patch also change pr_err to dev_err to trace which
device is failed.

Fixes: 0775a9cbc694 ("usbip: vhci extension: modifications to vhci driver")
Signed-off-by: Mao Wenan <maowenan@huawei.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/20190916150921.152977-1-maowenan@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usbip/vhci_hcd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index 585a84d319bd..65850e9c7190 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -1195,12 +1195,12 @@ static int vhci_start(struct usb_hcd *hcd)
 	if (id == 0 && usb_hcd_is_primary_hcd(hcd)) {
 		err = vhci_init_attr_group();
 		if (err) {
-			pr_err("init attr group\n");
+			dev_err(hcd_dev(hcd), "init attr group failed, err = %d\n", err);
 			return err;
 		}
 		err = sysfs_create_group(&hcd_dev(hcd)->kobj, &vhci_attr_group);
 		if (err) {
-			pr_err("create sysfs files\n");
+			dev_err(hcd_dev(hcd), "create sysfs files failed, err = %d\n", err);
 			vhci_finish_attr_group();
 			return err;
 		}
-- 
cgit v1.2.3


From 2636d49b64671d3d90ecc4daf971b58df3956519 Mon Sep 17 00:00:00 2001
From: "Jacky.Cao@sony.com" <Jacky.Cao@sony.com>
Date: Thu, 5 Sep 2019 04:11:57 +0000
Subject: USB: dummy-hcd: fix power budget for SuperSpeed mode

The power budget for SuperSpeed mode should be 900 mA
according to USB specification, so set the power budget
to 900mA for dummy_start_ss which is only used for
SuperSpeed mode.

If the max power consumption of SuperSpeed device is
larger than 500 mA, insufficient available bus power
error happens in usb_choose_configuration function
when the device connects to dummy hcd.

Signed-off-by: Jacky Cao <Jacky.Cao@sony.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/16EA1F625E922C43B00B9D82250220500871CDE5@APYOKXMS108.ap.sony.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/dummy_hcd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index 8414fac74493..3d499d93c083 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -48,6 +48,7 @@
 #define DRIVER_VERSION	"02 May 2005"
 
 #define POWER_BUDGET	500	/* in mA; use 8 for low-power port testing */
+#define POWER_BUDGET_3	900	/* in mA */
 
 static const char	driver_name[] = "dummy_hcd";
 static const char	driver_desc[] = "USB Host+Gadget Emulator";
@@ -2432,7 +2433,7 @@ static int dummy_start_ss(struct dummy_hcd *dum_hcd)
 	dum_hcd->rh_state = DUMMY_RH_RUNNING;
 	dum_hcd->stream_en_ep = 0;
 	INIT_LIST_HEAD(&dum_hcd->urbp_list);
-	dummy_hcd_to_hcd(dum_hcd)->power_budget = POWER_BUDGET;
+	dummy_hcd_to_hcd(dum_hcd)->power_budget = POWER_BUDGET_3;
 	dummy_hcd_to_hcd(dum_hcd)->state = HC_STATE_RUNNING;
 	dummy_hcd_to_hcd(dum_hcd)->uses_new_polling = 1;
 #ifdef CONFIG_USB_OTG
-- 
cgit v1.2.3


From 7101949f36fc77b530b73e4c6bd0066a2740d75b Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 1 Oct 2019 15:01:17 +0300
Subject: usb: typec: tcpm: usb: typec: tcpm: Fix a signedness bug in
 tcpm_fw_get_caps()

The "port->typec_caps.data" and "port->typec_caps.type" variables are
enums and in this context GCC will treat them as an unsigned int so they
can never be less than zero.

Fixes: ae8a2ca8a221 ("usb: typec: Group all TCPCI/TCPM code together")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: stable <stable@vger.kernel.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20191001120117.GA23528@mwanda
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 96562744101c..5f61d9977a15 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -4409,18 +4409,20 @@ static int tcpm_fw_get_caps(struct tcpm_port *port,
 	/* USB data support is optional */
 	ret = fwnode_property_read_string(fwnode, "data-role", &cap_str);
 	if (ret == 0) {
-		port->typec_caps.data = typec_find_port_data_role(cap_str);
-		if (port->typec_caps.data < 0)
-			return -EINVAL;
+		ret = typec_find_port_data_role(cap_str);
+		if (ret < 0)
+			return ret;
+		port->typec_caps.data = ret;
 	}
 
 	ret = fwnode_property_read_string(fwnode, "power-role", &cap_str);
 	if (ret < 0)
 		return ret;
 
-	port->typec_caps.type = typec_find_port_power_role(cap_str);
-	if (port->typec_caps.type < 0)
-		return -EINVAL;
+	ret = typec_find_port_power_role(cap_str);
+	if (ret < 0)
+		return ret;
+	port->typec_caps.type = ret;
 	port->port_type = port->typec_caps.type;
 
 	if (port->port_type == TYPEC_PORT_SNK)
-- 
cgit v1.2.3


From 976392650a00651ea29f64c5dc54f059aa54e0d1 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 24 Sep 2019 10:01:29 -0300
Subject: bindings: rename links to mason USB2/USB3 DT files

Those files got renamed, but another DT file still points to the older
places.

Fixes: 87a55485f2fc ("dt-bindings: phy: meson-g12a-usb3-pcie-phy: convert to yaml")
Fixes: da86d286cce8 ("dt-bindings: phy: meson-g12a-usb2-phy: convert to yaml")
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/9ca2d136a1f79c878fff1208f9b536b0b613c0d5.1569330078.git.mchehab+samsung@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/amlogic,dwc3.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/usb/amlogic,dwc3.txt b/Documentation/devicetree/bindings/usb/amlogic,dwc3.txt
index b9f04e617eb7..6ffb09be7a76 100644
--- a/Documentation/devicetree/bindings/usb/amlogic,dwc3.txt
+++ b/Documentation/devicetree/bindings/usb/amlogic,dwc3.txt
@@ -85,8 +85,8 @@ A child node must exist to represent the core DWC2 IP block. The name of
 the node is not important. The content of the node is defined in dwc2.txt.
 
 PHY documentation is provided in the following places:
-- Documentation/devicetree/bindings/phy/meson-g12a-usb2-phy.txt
-- Documentation/devicetree/bindings/phy/meson-g12a-usb3-pcie-phy.txt
+- Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml
+- Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml
 
 Example device nodes:
 	usb: usb@ffe09000 {
-- 
cgit v1.2.3


From eb7f5a490c5edfe8126f64bc58b9ba2edef0a425 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 26 Sep 2019 11:12:25 +0200
Subject: USB: usblcd: fix I/O after disconnect

Make sure to stop all I/O on disconnect by adding a disconnected flag
which is used to prevent new I/O from being started and by stopping all
ongoing I/O before returning.

This also fixes a potential use-after-free on driver unbind in case the
driver data is freed before the completion handler has run.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable <stable@vger.kernel.org>	# 7bbe990c989e
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20190926091228.24634-7-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/usblcd.c | 33 +++++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/misc/usblcd.c b/drivers/usb/misc/usblcd.c
index 9ba4a4e68d91..aa982d3ca36b 100644
--- a/drivers/usb/misc/usblcd.c
+++ b/drivers/usb/misc/usblcd.c
@@ -18,6 +18,7 @@
 #include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/uaccess.h>
 #include <linux/usb.h>
 
@@ -57,6 +58,8 @@ struct usb_lcd {
 							   using up all RAM */
 	struct usb_anchor	submitted;		/* URBs to wait for
 							   before suspend */
+	struct rw_semaphore	io_rwsem;
+	unsigned long		disconnected:1;
 };
 #define to_lcd_dev(d) container_of(d, struct usb_lcd, kref)
 
@@ -142,6 +145,13 @@ static ssize_t lcd_read(struct file *file, char __user * buffer,
 
 	dev = file->private_data;
 
+	down_read(&dev->io_rwsem);
+
+	if (dev->disconnected) {
+		retval = -ENODEV;
+		goto out_up_io;
+	}
+
 	/* do a blocking bulk read to get data from the device */
 	retval = usb_bulk_msg(dev->udev,
 			      usb_rcvbulkpipe(dev->udev,
@@ -158,6 +168,9 @@ static ssize_t lcd_read(struct file *file, char __user * buffer,
 			retval = bytes_read;
 	}
 
+out_up_io:
+	up_read(&dev->io_rwsem);
+
 	return retval;
 }
 
@@ -237,11 +250,18 @@ static ssize_t lcd_write(struct file *file, const char __user * user_buffer,
 	if (r < 0)
 		return -EINTR;
 
+	down_read(&dev->io_rwsem);
+
+	if (dev->disconnected) {
+		retval = -ENODEV;
+		goto err_up_io;
+	}
+
 	/* create a urb, and a buffer for it, and copy the data to the urb */
 	urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!urb) {
 		retval = -ENOMEM;
-		goto err_no_buf;
+		goto err_up_io;
 	}
 
 	buf = usb_alloc_coherent(dev->udev, count, GFP_KERNEL,
@@ -278,6 +298,7 @@ static ssize_t lcd_write(struct file *file, const char __user * user_buffer,
 	   the USB core will eventually free it entirely */
 	usb_free_urb(urb);
 
+	up_read(&dev->io_rwsem);
 exit:
 	return count;
 error_unanchor:
@@ -285,7 +306,8 @@ error_unanchor:
 error:
 	usb_free_coherent(dev->udev, count, buf, urb->transfer_dma);
 	usb_free_urb(urb);
-err_no_buf:
+err_up_io:
+	up_read(&dev->io_rwsem);
 	up(&dev->limit_sem);
 	return retval;
 }
@@ -325,6 +347,7 @@ static int lcd_probe(struct usb_interface *interface,
 
 	kref_init(&dev->kref);
 	sema_init(&dev->limit_sem, USB_LCD_CONCURRENT_WRITES);
+	init_rwsem(&dev->io_rwsem);
 	init_usb_anchor(&dev->submitted);
 
 	dev->udev = usb_get_dev(interface_to_usbdev(interface));
@@ -422,6 +445,12 @@ static void lcd_disconnect(struct usb_interface *interface)
 	/* give back our minor */
 	usb_deregister_dev(interface, &lcd_class);
 
+	down_write(&dev->io_rwsem);
+	dev->disconnected = 1;
+	up_write(&dev->io_rwsem);
+
+	usb_kill_anchored_urbs(&dev->submitted);
+
 	/* decrement our usage count */
 	kref_put(&dev->kref, lcd_delete);
 
-- 
cgit v1.2.3


From 61991d02fd33698182460bf62dca1b8162e3472b Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 26 Sep 2019 11:12:26 +0200
Subject: USB: usblcd: drop redundant disconnect mutex

Drop the redundant disconnect mutex which was introduced after the
open-disconnect race had been addressed generally in USB core by commit
d4ead16f50f9 ("USB: prevent char device open/deregister race").

Specifically, the rw-semaphore in core guarantees that all calls to
open() will have completed and that no new calls to open() will occur
after usb_deregister_dev() returns. Hence there is no need use the
driver data as an inverted disconnected flag.

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20190926091228.24634-8-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/usblcd.c | 18 +-----------------
 1 file changed, 1 insertion(+), 17 deletions(-)

diff --git a/drivers/usb/misc/usblcd.c b/drivers/usb/misc/usblcd.c
index aa982d3ca36b..b898650a5570 100644
--- a/drivers/usb/misc/usblcd.c
+++ b/drivers/usb/misc/usblcd.c
@@ -37,9 +37,6 @@ static const struct usb_device_id id_table[] = {
 };
 MODULE_DEVICE_TABLE(usb, id_table);
 
-static DEFINE_MUTEX(open_disc_mutex);
-
-
 struct usb_lcd {
 	struct usb_device	*udev;			/* init: probe_lcd */
 	struct usb_interface	*interface;		/* the interface for
@@ -95,17 +92,10 @@ static int lcd_open(struct inode *inode, struct file *file)
 		return -ENODEV;
 	}
 
-	mutex_lock(&open_disc_mutex);
 	dev = usb_get_intfdata(interface);
-	if (!dev) {
-		mutex_unlock(&open_disc_mutex);
-		mutex_unlock(&lcd_mutex);
-		return -ENODEV;
-	}
 
 	/* increment our usage count for the device */
 	kref_get(&dev->kref);
-	mutex_unlock(&open_disc_mutex);
 
 	/* grab a power reference */
 	r = usb_autopm_get_interface(interface);
@@ -388,7 +378,6 @@ static int lcd_probe(struct usb_interface *interface,
 		/* something prevented us from registering this driver */
 		dev_err(&interface->dev,
 			"Not able to get a minor for this device.\n");
-		usb_set_intfdata(interface, NULL);
 		goto error;
 	}
 
@@ -434,14 +423,9 @@ static int lcd_resume(struct usb_interface *intf)
 
 static void lcd_disconnect(struct usb_interface *interface)
 {
-	struct usb_lcd *dev;
+	struct usb_lcd *dev = usb_get_intfdata(interface);
 	int minor = interface->minor;
 
-	mutex_lock(&open_disc_mutex);
-	dev = usb_get_intfdata(interface);
-	usb_set_intfdata(interface, NULL);
-	mutex_unlock(&open_disc_mutex);
-
 	/* give back our minor */
 	usb_deregister_dev(interface, &lcd_class);
 
-- 
cgit v1.2.3


From d046fd5e058535dbb98812f414aeb061724dc3b0 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 26 Sep 2019 11:12:27 +0200
Subject: USB: usblcd: drop redundant lcd mutex

Drop the redundant lcd mutex introduced by commit 925ce689bb31 ("USB:
autoconvert trivial BKL users to private mutex") which replaced an
earlier BKL use.

The lock serialised calls to open() against other open() and a custom
ioctl() returning the bcdDevice (sic!), but neither is needed.

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20190926091228.24634-9-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/usblcd.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/usb/misc/usblcd.c b/drivers/usb/misc/usblcd.c
index b898650a5570..732eb1f81368 100644
--- a/drivers/usb/misc/usblcd.c
+++ b/drivers/usb/misc/usblcd.c
@@ -30,7 +30,6 @@
 #define IOCTL_GET_DRV_VERSION	2
 
 
-static DEFINE_MUTEX(lcd_mutex);
 static const struct usb_device_id id_table[] = {
 	{ .idVendor = 0x10D2, .match_flags = USB_DEVICE_ID_MATCH_VENDOR, },
 	{ },
@@ -81,12 +80,10 @@ static int lcd_open(struct inode *inode, struct file *file)
 	struct usb_interface *interface;
 	int subminor, r;
 
-	mutex_lock(&lcd_mutex);
 	subminor = iminor(inode);
 
 	interface = usb_find_interface(&lcd_driver, subminor);
 	if (!interface) {
-		mutex_unlock(&lcd_mutex);
 		printk(KERN_ERR "USBLCD: %s - error, can't find device for minor %d\n",
 		       __func__, subminor);
 		return -ENODEV;
@@ -101,13 +98,11 @@ static int lcd_open(struct inode *inode, struct file *file)
 	r = usb_autopm_get_interface(interface);
 	if (r < 0) {
 		kref_put(&dev->kref, lcd_delete);
-		mutex_unlock(&lcd_mutex);
 		return r;
 	}
 
 	/* save our object in the file's private structure */
 	file->private_data = dev;
-	mutex_unlock(&lcd_mutex);
 
 	return 0;
 }
@@ -176,14 +171,12 @@ static long lcd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	switch (cmd) {
 	case IOCTL_GET_HARD_VERSION:
-		mutex_lock(&lcd_mutex);
 		bcdDevice = le16_to_cpu((dev->udev)->descriptor.bcdDevice);
 		sprintf(buf, "%1d%1d.%1d%1d",
 			(bcdDevice & 0xF000)>>12,
 			(bcdDevice & 0xF00)>>8,
 			(bcdDevice & 0xF0)>>4,
 			(bcdDevice & 0xF));
-		mutex_unlock(&lcd_mutex);
 		if (copy_to_user((void __user *)arg, buf, strlen(buf)) != 0)
 			return -EFAULT;
 		break;
-- 
cgit v1.2.3


From c9a2baa79698295565cadcced86df63c2257933a Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 26 Sep 2019 11:12:28 +0200
Subject: USB: usblcd: use pr_err()

Replace the one remaining printk with pr_err().

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20190926091228.24634-10-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/usblcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/misc/usblcd.c b/drivers/usb/misc/usblcd.c
index 732eb1f81368..61e9e987fe4a 100644
--- a/drivers/usb/misc/usblcd.c
+++ b/drivers/usb/misc/usblcd.c
@@ -84,7 +84,7 @@ static int lcd_open(struct inode *inode, struct file *file)
 
 	interface = usb_find_interface(&lcd_driver, subminor);
 	if (!interface) {
-		printk(KERN_ERR "USBLCD: %s - error, can't find device for minor %d\n",
+		pr_err("USBLCD: %s - error, can't find device for minor %d\n",
 		       __func__, subminor);
 		return -ENODEV;
 	}
-- 
cgit v1.2.3


From a48e61de758c6b45f080fabc6fed3f4ed42598dc Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 1 Oct 2019 11:43:13 +0100
Subject: arm64: Mark functions using explicit register variables as
 '__always_inline'

As of ac7c3e4ff401 ("compiler: enable CONFIG_OPTIMIZE_INLINING forcibly"),
inline functions are no longer annotated with '__always_inline', which
allows the compiler to decide whether inlining is really a good idea or
not. Although this is a great idea on paper, the reality is that AArch64
GCC prior to 9.1 has been shown to get confused when creating an
out-of-line copy of a function passing explicit 'register' variables
into an inline assembly block:

  https://gcc.gnu.org/bugzilla/show_bug.cgi?id=91111

It's not clear whether this is specific to arm64 or not but, for now,
ensure that all of our functions using 'register' variables are marked
as '__always_inline' so that the old behaviour is effectively preserved.

Hopefully other architectures are luckier with their compilers.

Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/atomic_lse.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index c6bd87d2915b..574808b9df4c 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -321,7 +321,8 @@ static inline s64 __lse_atomic64_dec_if_positive(atomic64_t *v)
 }
 
 #define __CMPXCHG_CASE(w, sfx, name, sz, mb, cl...)			\
-static inline u##sz __lse__cmpxchg_case_##name##sz(volatile void *ptr,	\
+static __always_inline u##sz						\
+__lse__cmpxchg_case_##name##sz(volatile void *ptr,			\
 					      u##sz old,		\
 					      u##sz new)		\
 {									\
@@ -362,7 +363,8 @@ __CMPXCHG_CASE(x,  ,  mb_, 64, al, "memory")
 #undef __CMPXCHG_CASE
 
 #define __CMPXCHG_DBL(name, mb, cl...)					\
-static inline long __lse__cmpxchg_double##name(unsigned long old1,	\
+static __always_inline long						\
+__lse__cmpxchg_double##name(unsigned long old1,				\
 					 unsigned long old2,		\
 					 unsigned long new1,		\
 					 unsigned long new2,		\
-- 
cgit v1.2.3


From 3032c0b47e5f71a9a3c4c8e7bfa83d9005814510 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 2 Oct 2019 23:41:08 +0300
Subject: drm/i915/tgl: Add the Thunderbolt PLL divider values
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Thunderbolt PLL divider values on TGL differ from the ICL ones,
update the PLL parameter calculation function accordingly.

Bspec: 49204

v2:
- Remove unused refclk config. (José)

Cc: Jose Souza <jose.souza@intel.com>
Cc: Clinton A Taylor <clinton.a.taylor@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Mika Westerberg <mika.westerberg@intel.com>
Tested-by: Mika Westerberg <mika.westerberg@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jose Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191002204108.32242-1-imre.deak@intel.com
---
 drivers/gpu/drm/i915/display/intel_dpll_mgr.c | 42 +++++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index be69a2344294..5e9e84c94a15 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -2520,6 +2520,18 @@ static const struct skl_wrpll_params icl_tbt_pll_19_2MHz_values = {
 	.pdiv = 0x4 /* 5 */, .kdiv = 1, .qdiv_mode = 0, .qdiv_ratio = 0,
 };
 
+static const struct skl_wrpll_params tgl_tbt_pll_19_2MHz_values = {
+	.dco_integer = 0x54, .dco_fraction = 0x3000,
+	/* the following params are unused */
+	.pdiv = 0, .kdiv = 0, .qdiv_mode = 0, .qdiv_ratio = 0,
+};
+
+static const struct skl_wrpll_params tgl_tbt_pll_24MHz_values = {
+	.dco_integer = 0x43, .dco_fraction = 0x4000,
+	/* the following params are unused */
+	.pdiv = 0, .kdiv = 0, .qdiv_mode = 0, .qdiv_ratio = 0,
+};
+
 static bool icl_calc_dp_combo_pll(struct intel_crtc_state *crtc_state,
 				  struct skl_wrpll_params *pll_params)
 {
@@ -2547,8 +2559,34 @@ static bool icl_calc_tbt_pll(struct intel_crtc_state *crtc_state,
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
 
-	*pll_params = dev_priv->cdclk.hw.ref == 24000 ?
-			icl_tbt_pll_24MHz_values : icl_tbt_pll_19_2MHz_values;
+	if (INTEL_GEN(dev_priv) >= 12) {
+		switch (dev_priv->cdclk.hw.ref) {
+		default:
+			MISSING_CASE(dev_priv->cdclk.hw.ref);
+			/* fall-through */
+		case 19200:
+		case 38400:
+			*pll_params = tgl_tbt_pll_19_2MHz_values;
+			break;
+		case 24000:
+			*pll_params = tgl_tbt_pll_24MHz_values;
+			break;
+		}
+	} else {
+		switch (dev_priv->cdclk.hw.ref) {
+		default:
+			MISSING_CASE(dev_priv->cdclk.hw.ref);
+			/* fall-through */
+		case 19200:
+		case 38400:
+			*pll_params = icl_tbt_pll_19_2MHz_values;
+			break;
+		case 24000:
+			*pll_params = icl_tbt_pll_24MHz_values;
+			break;
+		}
+	}
+
 	return true;
 }
 
-- 
cgit v1.2.3


From 7230f7e99fecc684180322b056fad3853d1029d3 Mon Sep 17 00:00:00 2001
From: Julien Grall <julien.grall@arm.com>
Date: Thu, 3 Oct 2019 12:12:08 +0100
Subject: arm64: cpufeature: Effectively expose FRINT capability to userspace

The HWCAP framework will detect a new capability based on the sanitized
version of the ID registers.

Sanitization is based on a whitelist, so any field not described will end
up to be zeroed.

At the moment, ID_AA64ISAR1_EL1.FRINTTS is not described in
ftr_id_aa64isar1. This means the field will be zeroed and therefore the
userspace will not be able to see the HWCAP even if the hardware
supports the feature.

This can be fixed by describing the field in ftr_id_aa64isar1.

Fixes: ca9503fc9e98 ("arm64: Expose FRINT capabilities to userspace")
Signed-off-by: Julien Grall <julien.grall@arm.com>
Cc: mark.brown@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/cpufeature.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 9323bcc40a58..cabebf1a7976 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -136,6 +136,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
 
 static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_SB_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FRINTTS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
 		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_GPI_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
-- 
cgit v1.2.3


From e4365f968fcd5ef4a2f69f11ebc9ee66f47fc879 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 3 Oct 2019 10:49:32 +0100
Subject: arm64: mm: avoid virt_to_phys(init_mm.pgd)

If we take an unhandled fault in the kernel, we call show_pte() to dump
the {PGDP,PGD,PUD,PMD,PTE} values for the corresponding page table walk,
where the PGDP value is virt_to_phys(mm->pgd).

The boot-time and runtime kernel page tables, init_pg_dir and
swapper_pg_dir respectively, are kernel symbols. Thus, it is not valid
to call virt_to_phys() on either of these, though we'll do so if we take
a fault on a TTBR1 address.

When CONFIG_DEBUG_VIRTUAL is not selected, virt_to_phys() will silently
fix this up. However, when CONFIG_DEBUG_VIRTUAL is selected, this
results in splats as below. Depending on when these occur, they can
happen to suppress information needed to debug the original unhandled
fault, such as the backtrace:

| Unable to handle kernel paging request at virtual address ffff7fffec73cf0f
| Mem abort info:
|   ESR = 0x96000004
|   EC = 0x25: DABT (current EL), IL = 32 bits
|   SET = 0, FnV = 0
|   EA = 0, S1PTW = 0
| Data abort info:
|   ISV = 0, ISS = 0x00000004
|   CM = 0, WnR = 0
| ------------[ cut here ]------------
| virt_to_phys used for non-linear address: 00000000102c9dbe (swapper_pg_dir+0x0/0x1000)
| WARNING: CPU: 1 PID: 7558 at arch/arm64/mm/physaddr.c:15 __virt_to_phys+0xe0/0x170 arch/arm64/mm/physaddr.c:12
| Kernel panic - not syncing: panic_on_warn set ...
| SMP: stopping secondary CPUs
| Dumping ftrace buffer:
|    (ftrace buffer empty)
| Kernel Offset: disabled
| CPU features: 0x0002,23000438
| Memory Limit: none
| Rebooting in 1 seconds..

We can avoid this by ensuring that we call __pa_symbol() for
init_mm.pgd, as this will always be a kernel symbol. As the dumped
{PGD,PUD,PMD,PTE} values are the raw values from the relevant entries we
don't need to handle these specially.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/fault.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 115d7a0e4b08..6acd866f31fd 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -113,6 +113,15 @@ static inline bool is_ttbr1_addr(unsigned long addr)
 	return arch_kasan_reset_tag(addr) >= PAGE_OFFSET;
 }
 
+static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm)
+{
+	/* Either init_pg_dir or swapper_pg_dir */
+	if (mm == &init_mm)
+		return __pa_symbol(mm->pgd);
+
+	return (unsigned long)virt_to_phys(mm->pgd);
+}
+
 /*
  * Dump out the page tables associated with 'addr' in the currently active mm.
  */
@@ -141,7 +150,7 @@ static void show_pte(unsigned long addr)
 
 	pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n",
 		 mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K,
-		 vabits_actual, (unsigned long)virt_to_phys(mm->pgd));
+		 vabits_actual, mm_to_pgd_phys(mm));
 	pgdp = pgd_offset(mm, addr);
 	pgd = READ_ONCE(*pgdp);
 	pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd));
-- 
cgit v1.2.3


From f46f27a576cc3b1e3d45ea50bc06287aa46b04b2 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Thu, 3 Oct 2019 18:01:27 +0100
Subject: arm64: Fix incorrect irqflag restore for priority masking for compat

Commit bd82d4bd2188 ("arm64: Fix incorrect irqflag restore for priority
masking") added a macro to the entry.S call paths that leave the
PSTATE.I bit set. This tells the pPNMI masking logic that interrupts
are masked by the CPU, not by the PMR. This value is read back by
local_daif_save().

Commit bd82d4bd2188 added this call to el0_svc, as el0_svc_handler
is called with interrupts masked. el0_svc_compat was missed, but should
be covered in the same way as both of these paths end up in
el0_svc_common(), which expects to unmask interrupts.

Fixes: bd82d4bd2188 ("arm64: Fix incorrect irqflag restore for priority masking")
Signed-off-by: James Morse <james.morse@arm.com>
Cc: Julien Thierry <julien.thierry.kdev@gmail.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/entry.S | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 84a822748c84..e304fe04b098 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -775,6 +775,7 @@ el0_sync_compat:
 	b.ge	el0_dbg
 	b	el0_inv
 el0_svc_compat:
+	gic_prio_kentry_setup tmp=x1
 	mov	x0, sp
 	bl	el0_svc_compat_handler
 	b	ret_to_user
-- 
cgit v1.2.3


From dd8a1f13488438c6c220b7cafa500baaf21a6e53 Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Wed, 2 Oct 2019 10:49:35 +0100
Subject: arm64: ftrace: Ensure synchronisation in PLT setup for Neoverse-N1
 #1542419

CPUs affected by Neoverse-N1 #1542419 may execute a stale instruction if
it was recently modified. The affected sequence requires freshly written
instructions to be executable before a branch to them is updated.

There are very few places in the kernel that modify executable text,
all but one come with sufficient synchronisation:
 * The module loader's flush_module_icache() calls flush_icache_range(),
   which does a kick_all_cpus_sync()
 * bpf_int_jit_compile() calls flush_icache_range().
 * Kprobes calls aarch64_insn_patch_text(), which does its work in
   stop_machine().
 * static keys and ftrace both patch between nops and branches to
   existing kernel code (not generated code).

The affected sequence is the interaction between ftrace and modules.
The module PLT is cleaned using __flush_icache_range() as the trampoline
shouldn't be executable until we update the branch to it.

Drop the double-underscore so that this path runs kick_all_cpus_sync()
too.

Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/ftrace.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 171773257974..06e56b470315 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -121,10 +121,16 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
 			/*
 			 * Ensure updated trampoline is visible to instruction
-			 * fetch before we patch in the branch.
+			 * fetch before we patch in the branch. Although the
+			 * architecture doesn't require an IPI in this case,
+			 * Neoverse-N1 erratum #1542419 does require one
+			 * if the TLB maintenance in module_enable_ro() is
+			 * skipped due to rodata_enabled. It doesn't seem worth
+			 * it to make it conditional given that this is
+			 * certainly not a fast-path.
 			 */
-			__flush_icache_range((unsigned long)&dst[0],
-					     (unsigned long)&dst[1]);
+			flush_icache_range((unsigned long)&dst[0],
+					   (unsigned long)&dst[1]);
 		}
 		addr = (unsigned long)dst;
 #else /* CONFIG_ARM64_MODULE_PLTS */
-- 
cgit v1.2.3


From cd24ee2a9a091432deb8da461b9b1055107460d4 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Tue, 27 Nov 2018 21:50:56 +0100
Subject: MAINTAINERS: Add hp_sdc drivers to parisc arch

Signed-off-by: Helge Deller <deller@gmx.de>
---
 MAINTAINERS | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 296de2b51c83..59dd4c8f070d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12310,12 +12310,15 @@ F:	arch/parisc/
 F:	Documentation/parisc/
 F:	drivers/parisc/
 F:	drivers/char/agp/parisc-agp.c
+F:	drivers/input/misc/hp_sdc_rtc.c
 F:	drivers/input/serio/gscps2.c
+F:	drivers/input/serio/hp_sdc*
 F:	drivers/parport/parport_gsc.*
 F:	drivers/tty/serial/8250/8250_gsc.c
 F:	drivers/video/fbdev/sti*
 F:	drivers/video/console/sti*
 F:	drivers/video/logo/logo_parisc*
+F:	include/linux/hp_sdc.h
 
 PARMAN
 M:	Jiri Pirko <jiri@mellanox.com>
-- 
cgit v1.2.3


From 8530e4e20ec2355c273f4dba9002969e68275e5f Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Fri, 4 Oct 2019 13:02:18 +0300
Subject: usb: typec: ucsi: ccg: Remove run_isr flag

The "run_isr" flag is used for preventing the driver from
calling the interrupt service routine in its runtime resume
callback when the driver is expecting completion to a
command, but what that basically does is that it hides the
real problem. The real problem is that the controller is
allowed to suspend in the middle of command execution.

As a more appropriate fix for the problem, using autosuspend
delay time that matches UCSI_TIMEOUT_MS (5s). That prevents
the controller from suspending while still in the middle of
executing a command.

This fixes a potential deadlock. Both ccg_read() and
ccg_write() are called with the mutex already taken at least
from ccg_send_command(). In ccg_read() and ccg_write, the
mutex is only acquired so that run_isr flag can be set.

Fixes: f0e4cd948b91 ("usb: typec: ucsi: ccg: add runtime pm workaround")
Cc: stable@vger.kernel.org
Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20191004100219.71152-2-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/ucsi_ccg.c | 42 ++++-----------------------------------
 1 file changed, 4 insertions(+), 38 deletions(-)

diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c
index 907e20e1a71e..d772fce51905 100644
--- a/drivers/usb/typec/ucsi/ucsi_ccg.c
+++ b/drivers/usb/typec/ucsi/ucsi_ccg.c
@@ -195,7 +195,6 @@ struct ucsi_ccg {
 
 	/* fw build with vendor information */
 	u16 fw_build;
-	bool run_isr; /* flag to call ISR routine during resume */
 	struct work_struct pm_work;
 };
 
@@ -224,18 +223,6 @@ static int ccg_read(struct ucsi_ccg *uc, u16 rab, u8 *data, u32 len)
 	if (quirks && quirks->max_read_len)
 		max_read_len = quirks->max_read_len;
 
-	if (uc->fw_build == CCG_FW_BUILD_NVIDIA &&
-	    uc->fw_version <= CCG_OLD_FW_VERSION) {
-		mutex_lock(&uc->lock);
-		/*
-		 * Do not schedule pm_work to run ISR in
-		 * ucsi_ccg_runtime_resume() after pm_runtime_get_sync()
-		 * since we are already in ISR path.
-		 */
-		uc->run_isr = false;
-		mutex_unlock(&uc->lock);
-	}
-
 	pm_runtime_get_sync(uc->dev);
 	while (rem_len > 0) {
 		msgs[1].buf = &data[len - rem_len];
@@ -278,18 +265,6 @@ static int ccg_write(struct ucsi_ccg *uc, u16 rab, u8 *data, u32 len)
 	msgs[0].len = len + sizeof(rab);
 	msgs[0].buf = buf;
 
-	if (uc->fw_build == CCG_FW_BUILD_NVIDIA &&
-	    uc->fw_version <= CCG_OLD_FW_VERSION) {
-		mutex_lock(&uc->lock);
-		/*
-		 * Do not schedule pm_work to run ISR in
-		 * ucsi_ccg_runtime_resume() after pm_runtime_get_sync()
-		 * since we are already in ISR path.
-		 */
-		uc->run_isr = false;
-		mutex_unlock(&uc->lock);
-	}
-
 	pm_runtime_get_sync(uc->dev);
 	status = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
 	if (status < 0) {
@@ -1130,7 +1105,6 @@ static int ucsi_ccg_probe(struct i2c_client *client,
 	uc->ppm.sync = ucsi_ccg_sync;
 	uc->dev = dev;
 	uc->client = client;
-	uc->run_isr = true;
 	mutex_init(&uc->lock);
 	INIT_WORK(&uc->work, ccg_update_firmware);
 	INIT_WORK(&uc->pm_work, ccg_pm_workaround_work);
@@ -1188,6 +1162,8 @@ static int ucsi_ccg_probe(struct i2c_client *client,
 
 	pm_runtime_set_active(uc->dev);
 	pm_runtime_enable(uc->dev);
+	pm_runtime_use_autosuspend(uc->dev);
+	pm_runtime_set_autosuspend_delay(uc->dev, 5000);
 	pm_runtime_idle(uc->dev);
 
 	return 0;
@@ -1229,7 +1205,6 @@ static int ucsi_ccg_runtime_resume(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct ucsi_ccg *uc = i2c_get_clientdata(client);
-	bool schedule = true;
 
 	/*
 	 * Firmware version 3.1.10 or earlier, built for NVIDIA has known issue
@@ -1237,17 +1212,8 @@ static int ucsi_ccg_runtime_resume(struct device *dev)
 	 * Schedule a work to call ISR as a workaround.
 	 */
 	if (uc->fw_build == CCG_FW_BUILD_NVIDIA &&
-	    uc->fw_version <= CCG_OLD_FW_VERSION) {
-		mutex_lock(&uc->lock);
-		if (!uc->run_isr) {
-			uc->run_isr = true;
-			schedule = false;
-		}
-		mutex_unlock(&uc->lock);
-
-		if (schedule)
-			schedule_work(&uc->pm_work);
-	}
+	    uc->fw_version <= CCG_OLD_FW_VERSION)
+		schedule_work(&uc->pm_work);
 
 	return 0;
 }
-- 
cgit v1.2.3


From f2372b87c386871b16d7dbda680d98d4092ab708 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Fri, 4 Oct 2019 13:02:19 +0300
Subject: usb: typec: ucsi: displayport: Fix for the mode entering routine

Making sure that ucsi_displayport_enter() function does not
return an error if the displayport alternate mode has
already been entered. It's normal that the firmware (or
controller) has already entered the alternate mode by the
time the operating system is notified about the device.

Fixes: af8622f6a585 ("usb: typec: ucsi: Support for DisplayPort alt mode")
Cc: stable@vger.kernel.org
Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20191004100219.71152-3-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/displayport.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c
index 6c103697c582..d99700cb4dca 100644
--- a/drivers/usb/typec/ucsi/displayport.c
+++ b/drivers/usb/typec/ucsi/displayport.c
@@ -75,6 +75,8 @@ static int ucsi_displayport_enter(struct typec_altmode *alt)
 
 	if (cur != 0xff) {
 		mutex_unlock(&dp->con->lock);
+		if (dp->con->port_altmode[cur] == alt)
+			return 0;
 		return -EBUSY;
 	}
 
-- 
cgit v1.2.3


From 44d0a9c05bc078aef75229d0750e9c55959caae4 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 3 Oct 2019 22:00:56 +0100
Subject: drm/i915/execlists: Skip redundant resubmission

If we unwind the active requests, and on resubmission discover that we
intend to preempt the active contexts with themselves, simply skip the
ELSP submission.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191003210100.22250-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 431d3b8c3371..3cfea1758fd2 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1739,11 +1739,26 @@ done:
 
 	if (submit) {
 		*port = execlists_schedule_in(last, port - execlists->pending);
-		memset(port + 1, 0, (last_port - port) * sizeof(*port));
 		execlists->switch_priority_hint =
 			switch_prio(engine, *execlists->pending);
+
+		/*
+		 * Skip if we ended up with exactly the same set of requests,
+		 * e.g. trying to timeslice a pair of ordered contexts
+		 */
+		if (!memcmp(execlists->active, execlists->pending,
+			    (port - execlists->pending + 1) * sizeof(*port))) {
+			do
+				execlists_schedule_out(fetch_and_zero(port));
+			while (port-- != execlists->pending);
+
+			goto skip_submit;
+		}
+
+		memset(port + 1, 0, (last_port - port) * sizeof(*port));
 		execlists_submit_ports(engine);
 	} else {
+skip_submit:
 		ring_set_paused(engine, 0);
 	}
 }
-- 
cgit v1.2.3


From 313c3fe9c2348e7147eca38bb446f295b45403a0 Mon Sep 17 00:00:00 2001
From: Michael Vassernis <michael.vassernis@tandemg.com>
Date: Thu, 3 Oct 2019 07:31:38 +0000
Subject: mac80211_hwsim: fix incorrect dev_alloc_name failure goto

If dev_alloc_name fails, hwsim_mon's memory allocated in alloc_netdev
needs to be freed.
Change goto command in dev_alloc_name failure to out_free_mon in
order to perform free_netdev.

Signed-off-by: Michael Vassernis <michael.vassernis@tandemg.com>
Link: https://lore.kernel.org/r/20191003073049.3760-1-michael.vassernis@tandemg.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 45c73a6f09a1..14f562cd715c 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -4026,7 +4026,7 @@ static int __init init_mac80211_hwsim(void)
 	err = dev_alloc_name(hwsim_mon, hwsim_mon->name);
 	if (err < 0) {
 		rtnl_unlock();
-		goto out_free_radios;
+		goto out_free_mon;
 	}
 
 	err = register_netdevice(hwsim_mon);
-- 
cgit v1.2.3


From 4152561f5da3fca92af7179dd538ea89e248f9d0 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 4 Oct 2019 10:51:31 +0100
Subject: mac80211: Reject malformed SSID elements

Although this shouldn't occur in practice, it's a good idea to bounds
check the length field of the SSID element prior to using it for things
like allocations or memcpy operations.

Cc: <stable@vger.kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Reported-by: Nicolas Waisman <nico@semmle.com>
Signed-off-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20191004095132.15777-1-will@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 26a2f49208b6..54dd8849d1cc 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2633,7 +2633,8 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw,
 
 	rcu_read_lock();
 	ssid = ieee80211_bss_get_ie(cbss, WLAN_EID_SSID);
-	if (WARN_ON_ONCE(ssid == NULL))
+	if (WARN_ONCE(!ssid || ssid[1] > IEEE80211_MAX_SSID_LEN,
+		      "invalid SSID element (len=%d)", ssid ? ssid[1] : -1))
 		ssid_len = 0;
 	else
 		ssid_len = ssid[1];
@@ -5233,7 +5234,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 
 	rcu_read_lock();
 	ssidie = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID);
-	if (!ssidie) {
+	if (!ssidie || ssidie[1] > sizeof(assoc_data->ssid)) {
 		rcu_read_unlock();
 		kfree(assoc_data);
 		return -EINVAL;
-- 
cgit v1.2.3


From cf05a67b68b8d9d6469bedb63ee461f8c7de62e6 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Tue, 1 Oct 2019 15:33:07 +0200
Subject: KVM: x86: omit "impossible" pmu MSRs from MSR list

INTEL_PMC_MAX_GENERIC is currently 32, which exceeds the 18
contiguous MSR indices reserved by Intel for event selectors.
Since some machines actually have MSRs past the reserved range,
filtering them against x86_pmu.num_counters_gp may have false
positives.  Cut the list to 18 entries to avoid this.

Reported-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Suggested-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jim Mattson <jamttson@google.com>
Fixes: e2ada66ec418 ("kvm: x86: Add Intel PMU MSRs to msrs_to_save[]", 2019-08-21)
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 31607174f442..661e2bf38526 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1169,13 +1169,6 @@ static u32 msrs_to_save[] = {
 	MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13,
 	MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15,
 	MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17,
-	MSR_ARCH_PERFMON_PERFCTR0 + 18, MSR_ARCH_PERFMON_PERFCTR0 + 19,
-	MSR_ARCH_PERFMON_PERFCTR0 + 20, MSR_ARCH_PERFMON_PERFCTR0 + 21,
-	MSR_ARCH_PERFMON_PERFCTR0 + 22, MSR_ARCH_PERFMON_PERFCTR0 + 23,
-	MSR_ARCH_PERFMON_PERFCTR0 + 24, MSR_ARCH_PERFMON_PERFCTR0 + 25,
-	MSR_ARCH_PERFMON_PERFCTR0 + 26, MSR_ARCH_PERFMON_PERFCTR0 + 27,
-	MSR_ARCH_PERFMON_PERFCTR0 + 28, MSR_ARCH_PERFMON_PERFCTR0 + 29,
-	MSR_ARCH_PERFMON_PERFCTR0 + 30, MSR_ARCH_PERFMON_PERFCTR0 + 31,
 	MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5,
@@ -1185,13 +1178,6 @@ static u32 msrs_to_save[] = {
 	MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 18, MSR_ARCH_PERFMON_EVENTSEL0 + 19,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 20, MSR_ARCH_PERFMON_EVENTSEL0 + 21,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 22, MSR_ARCH_PERFMON_EVENTSEL0 + 23,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 24, MSR_ARCH_PERFMON_EVENTSEL0 + 25,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 26, MSR_ARCH_PERFMON_EVENTSEL0 + 27,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 28, MSR_ARCH_PERFMON_EVENTSEL0 + 29,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 30, MSR_ARCH_PERFMON_EVENTSEL0 + 31,
 };
 
 static unsigned num_msrs_to_save;
@@ -5154,12 +5140,12 @@ static void kvm_init_msr_list(void)
 				intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
 				continue;
 			break;
-		case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 31:
+		case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
 			if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
 			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
 				continue;
 			break;
-		case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 31:
+		case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17:
 			if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
 			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
 				continue;
-- 
cgit v1.2.3


From 1d427be4a39defadda6dd8f4659bc17f7591740f Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 19 Sep 2019 10:30:36 +0200
Subject: USB: legousbtower: fix slab info leak at probe

Make sure to check for short transfers when retrieving the version
information at probe to avoid leaking uninitialised slab data when
logging it.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20190919083039.30898-2-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/legousbtower.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c
index 006cf13b2199..1db07d4dc738 100644
--- a/drivers/usb/misc/legousbtower.c
+++ b/drivers/usb/misc/legousbtower.c
@@ -891,8 +891,10 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device
 				  get_version_reply,
 				  sizeof(*get_version_reply),
 				  1000);
-	if (result < 0) {
-		dev_err(idev, "LEGO USB Tower get version control request failed\n");
+	if (result < sizeof(*get_version_reply)) {
+		if (result >= 0)
+			result = -EIO;
+		dev_err(idev, "get version request failed: %d\n", result);
 		retval = result;
 		goto error;
 	}
-- 
cgit v1.2.3


From 33a7813219f208f4952ece60ee255fd983272dec Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 19 Sep 2019 10:30:37 +0200
Subject: USB: legousbtower: fix deadlock on disconnect

Fix a potential deadlock if disconnect races with open.

Since commit d4ead16f50f9 ("USB: prevent char device open/deregister
race") core holds an rw-semaphore while open is called and when
releasing the minor number during deregistration. This can lead to an
ABBA deadlock if a driver takes a lock in open which it also holds
during deregistration.

This effectively reverts commit 78663ecc344b ("USB: disconnect open race
in legousbtower") which needlessly introduced this issue after a generic
fix for this race had been added to core by commit d4ead16f50f9 ("USB:
prevent char device open/deregister race").

Fixes: 78663ecc344b ("USB: disconnect open race in legousbtower")
Cc: stable <stable@vger.kernel.org>	# 2.6.24
Reported-by: syzbot+f9549f5ee8a5416f0b95@syzkaller.appspotmail.com
Tested-by: syzbot+f9549f5ee8a5416f0b95@syzkaller.appspotmail.com
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20190919083039.30898-3-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/legousbtower.c | 19 ++-----------------
 1 file changed, 2 insertions(+), 17 deletions(-)

diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c
index 1db07d4dc738..773e4188f336 100644
--- a/drivers/usb/misc/legousbtower.c
+++ b/drivers/usb/misc/legousbtower.c
@@ -179,7 +179,6 @@ static const struct usb_device_id tower_table[] = {
 };
 
 MODULE_DEVICE_TABLE (usb, tower_table);
-static DEFINE_MUTEX(open_disc_mutex);
 
 #define LEGO_USB_TOWER_MINOR_BASE	160
 
@@ -332,18 +331,14 @@ static int tower_open (struct inode *inode, struct file *file)
 		goto exit;
 	}
 
-	mutex_lock(&open_disc_mutex);
 	dev = usb_get_intfdata(interface);
-
 	if (!dev) {
-		mutex_unlock(&open_disc_mutex);
 		retval = -ENODEV;
 		goto exit;
 	}
 
 	/* lock this device */
 	if (mutex_lock_interruptible(&dev->lock)) {
-		mutex_unlock(&open_disc_mutex);
 	        retval = -ERESTARTSYS;
 		goto exit;
 	}
@@ -351,12 +346,10 @@ static int tower_open (struct inode *inode, struct file *file)
 
 	/* allow opening only once */
 	if (dev->open_count) {
-		mutex_unlock(&open_disc_mutex);
 		retval = -EBUSY;
 		goto unlock_exit;
 	}
 	dev->open_count = 1;
-	mutex_unlock(&open_disc_mutex);
 
 	/* reset the tower */
 	result = usb_control_msg (dev->udev,
@@ -423,10 +416,9 @@ static int tower_release (struct inode *inode, struct file *file)
 
 	if (dev == NULL) {
 		retval = -ENODEV;
-		goto exit_nolock;
+		goto exit;
 	}
 
-	mutex_lock(&open_disc_mutex);
 	if (mutex_lock_interruptible(&dev->lock)) {
 	        retval = -ERESTARTSYS;
 		goto exit;
@@ -456,10 +448,7 @@ static int tower_release (struct inode *inode, struct file *file)
 
 unlock_exit:
 	mutex_unlock(&dev->lock);
-
 exit:
-	mutex_unlock(&open_disc_mutex);
-exit_nolock:
 	return retval;
 }
 
@@ -912,7 +901,6 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device
 	if (retval) {
 		/* something prevented us from registering this driver */
 		dev_err(idev, "Not able to get a minor for this device.\n");
-		usb_set_intfdata (interface, NULL);
 		goto error;
 	}
 	dev->minor = interface->minor;
@@ -944,16 +932,13 @@ static void tower_disconnect (struct usb_interface *interface)
 	int minor;
 
 	dev = usb_get_intfdata (interface);
-	mutex_lock(&open_disc_mutex);
-	usb_set_intfdata (interface, NULL);
 
 	minor = dev->minor;
 
-	/* give back our minor */
+	/* give back our minor and prevent further open() */
 	usb_deregister_dev (interface, &tower_class);
 
 	mutex_lock(&dev->lock);
-	mutex_unlock(&open_disc_mutex);
 
 	/* if the device is not opened, then we clean up right now */
 	if (!dev->open_count) {
-- 
cgit v1.2.3


From cd81e6fa8e033e7bcd59415b4a65672b4780030b Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 19 Sep 2019 10:30:38 +0200
Subject: USB: legousbtower: fix potential NULL-deref on disconnect

The driver is using its struct usb_device pointer as an inverted
disconnected flag, but was setting it to NULL before making sure all
completion handlers had run. This could lead to a NULL-pointer
dereference in a number of dev_dbg and dev_err statements in the
completion handlers which relies on said pointer.

Fix this by unconditionally stopping all I/O and preventing
resubmissions by poisoning the interrupt URBs at disconnect and using a
dedicated disconnected flag.

This also makes sure that all I/O has completed by the time the
disconnect callback returns.

Fixes: 9d974b2a06e3 ("USB: legousbtower.c: remove err() usage")
Fixes: fef526cae700 ("USB: legousbtower: remove custom debug macro")
Fixes: 4dae99638097 ("USB: legotower: remove custom debug macro and module parameter")
Cc: stable <stable@vger.kernel.org>     # 3.5
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20190919083039.30898-4-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/legousbtower.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c
index 773e4188f336..4fa999882635 100644
--- a/drivers/usb/misc/legousbtower.c
+++ b/drivers/usb/misc/legousbtower.c
@@ -190,6 +190,7 @@ struct lego_usb_tower {
 	unsigned char		minor;		/* the starting minor number for this device */
 
 	int			open_count;	/* number of times this port has been opened */
+	unsigned long		disconnected:1;
 
 	char*			read_buffer;
 	size_t			read_buffer_length; /* this much came in */
@@ -289,8 +290,6 @@ static inline void lego_usb_tower_debug_data(struct device *dev,
  */
 static inline void tower_delete (struct lego_usb_tower *dev)
 {
-	tower_abort_transfers (dev);
-
 	/* free data structures */
 	usb_free_urb(dev->interrupt_in_urb);
 	usb_free_urb(dev->interrupt_out_urb);
@@ -430,7 +429,8 @@ static int tower_release (struct inode *inode, struct file *file)
 		retval = -ENODEV;
 		goto unlock_exit;
 	}
-	if (dev->udev == NULL) {
+
+	if (dev->disconnected) {
 		/* the device was unplugged before the file was released */
 
 		/* unlock here as tower_delete frees dev */
@@ -466,10 +466,9 @@ static void tower_abort_transfers (struct lego_usb_tower *dev)
 	if (dev->interrupt_in_running) {
 		dev->interrupt_in_running = 0;
 		mb();
-		if (dev->udev)
-			usb_kill_urb (dev->interrupt_in_urb);
+		usb_kill_urb(dev->interrupt_in_urb);
 	}
-	if (dev->interrupt_out_busy && dev->udev)
+	if (dev->interrupt_out_busy)
 		usb_kill_urb(dev->interrupt_out_urb);
 }
 
@@ -505,7 +504,7 @@ static __poll_t tower_poll (struct file *file, poll_table *wait)
 
 	dev = file->private_data;
 
-	if (!dev->udev)
+	if (dev->disconnected)
 		return EPOLLERR | EPOLLHUP;
 
 	poll_wait(file, &dev->read_wait, wait);
@@ -552,7 +551,7 @@ static ssize_t tower_read (struct file *file, char __user *buffer, size_t count,
 	}
 
 	/* verify that the device wasn't unplugged */
-	if (dev->udev == NULL) {
+	if (dev->disconnected) {
 		retval = -ENODEV;
 		pr_err("No device or device unplugged %d\n", retval);
 		goto unlock_exit;
@@ -638,7 +637,7 @@ static ssize_t tower_write (struct file *file, const char __user *buffer, size_t
 	}
 
 	/* verify that the device wasn't unplugged */
-	if (dev->udev == NULL) {
+	if (dev->disconnected) {
 		retval = -ENODEV;
 		pr_err("No device or device unplugged %d\n", retval);
 		goto unlock_exit;
@@ -748,7 +747,7 @@ static void tower_interrupt_in_callback (struct urb *urb)
 
 resubmit:
 	/* resubmit if we're still running */
-	if (dev->interrupt_in_running && dev->udev) {
+	if (dev->interrupt_in_running) {
 		retval = usb_submit_urb (dev->interrupt_in_urb, GFP_ATOMIC);
 		if (retval)
 			dev_err(&dev->udev->dev,
@@ -813,6 +812,7 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device
 
 	dev->udev = udev;
 	dev->open_count = 0;
+	dev->disconnected = 0;
 
 	dev->read_buffer = NULL;
 	dev->read_buffer_length = 0;
@@ -938,6 +938,10 @@ static void tower_disconnect (struct usb_interface *interface)
 	/* give back our minor and prevent further open() */
 	usb_deregister_dev (interface, &tower_class);
 
+	/* stop I/O */
+	usb_poison_urb(dev->interrupt_in_urb);
+	usb_poison_urb(dev->interrupt_out_urb);
+
 	mutex_lock(&dev->lock);
 
 	/* if the device is not opened, then we clean up right now */
@@ -945,7 +949,7 @@ static void tower_disconnect (struct usb_interface *interface)
 		mutex_unlock(&dev->lock);
 		tower_delete (dev);
 	} else {
-		dev->udev = NULL;
+		dev->disconnected = 1;
 		/* wake up pollers */
 		wake_up_interruptible_all(&dev->read_wait);
 		wake_up_interruptible_all(&dev->write_wait);
-- 
cgit v1.2.3


From 0b074f6986751361ff442bc1127c1648567aa8d6 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 19 Sep 2019 10:30:39 +0200
Subject: USB: legousbtower: fix open after failed reset request

The driver would return with a nonzero open count in case the reset
control request failed. This would prevent any further attempts to open
the char dev until the device was disconnected.

Fix this by incrementing the open count only on successful open.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Johan Hovold <johan@kernel.org>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20190919083039.30898-5-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/legousbtower.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c
index 4fa999882635..44d6a3381804 100644
--- a/drivers/usb/misc/legousbtower.c
+++ b/drivers/usb/misc/legousbtower.c
@@ -348,7 +348,6 @@ static int tower_open (struct inode *inode, struct file *file)
 		retval = -EBUSY;
 		goto unlock_exit;
 	}
-	dev->open_count = 1;
 
 	/* reset the tower */
 	result = usb_control_msg (dev->udev,
@@ -388,13 +387,14 @@ static int tower_open (struct inode *inode, struct file *file)
 		dev_err(&dev->udev->dev,
 			"Couldn't submit interrupt_in_urb %d\n", retval);
 		dev->interrupt_in_running = 0;
-		dev->open_count = 0;
 		goto unlock_exit;
 	}
 
 	/* save device in the file's private structure */
 	file->private_data = dev;
 
+	dev->open_count = 1;
+
 unlock_exit:
 	mutex_unlock(&dev->lock);
 
-- 
cgit v1.2.3


From 4ac2813cc867ae563a1ba5a9414bfb554e5796fa Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 4 Oct 2019 10:51:32 +0100
Subject: cfg80211: wext: avoid copying malformed SSIDs

Ensure the SSID element is bounds-checked prior to invoking memcpy()
with its length field, when copying to userspace.

Cc: <stable@vger.kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Reported-by: Nicolas Waisman <nico@semmle.com>
Signed-off-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20191004095132.15777-2-will@kernel.org
[adjust commit log a bit]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/wext-sme.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c
index c67d7a82ab13..73fd0eae08ca 100644
--- a/net/wireless/wext-sme.c
+++ b/net/wireless/wext-sme.c
@@ -202,6 +202,7 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev,
 			       struct iw_point *data, char *ssid)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	int ret = 0;
 
 	/* call only for station! */
 	if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION))
@@ -219,7 +220,10 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev,
 		if (ie) {
 			data->flags = 1;
 			data->length = ie[1];
-			memcpy(ssid, ie + 2, data->length);
+			if (data->length > IW_ESSID_MAX_SIZE)
+				ret = -EINVAL;
+			else
+				memcpy(ssid, ie + 2, data->length);
 		}
 		rcu_read_unlock();
 	} else if (wdev->wext.connect.ssid && wdev->wext.connect.ssid_len) {
@@ -229,7 +233,7 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev,
 	}
 	wdev_unlock(wdev);
 
-	return 0;
+	return ret;
 }
 
 int cfg80211_mgd_wext_siwap(struct net_device *dev,
-- 
cgit v1.2.3


From 81cdeca45a061f0ec9ecbbf7de864e2a57df5ee4 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 2 Oct 2019 17:41:38 +0300
Subject: drm/i915/dp: remove static variable for aux last status
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add aux_busy_last_status to intel_dp. Don't bother with initializing to
all ones; the only difference is potentially missing logging for one
error case if the readout is all zeros.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191002144138.7917-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/display/intel_display_types.h | 1 +
 drivers/gpu/drm/i915/display/intel_dp.c            | 5 ++---
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 976669f01a8c..1602aac7ca0f 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1185,6 +1185,7 @@ struct intel_dp {
 	/* sink or branch descriptor */
 	struct drm_dp_desc desc;
 	struct drm_dp_aux aux;
+	u32 aux_busy_last_status;
 	u8 train_set[4];
 	int panel_power_up_delay;
 	int panel_power_down_delay;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index b788e332e76a..38aa09cfbed3 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1347,13 +1347,12 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 	trace_i915_reg_rw(false, ch_ctl, status, sizeof(status), true);
 
 	if (try == 3) {
-		static u32 last_status = -1;
 		const u32 status = intel_uncore_read(uncore, ch_ctl);
 
-		if (status != last_status) {
+		if (status != intel_dp->aux_busy_last_status) {
 			WARN(1, "dp_aux_ch not started status 0x%08x\n",
 			     status);
-			last_status = status;
+			intel_dp->aux_busy_last_status = status;
 		}
 
 		ret = -EBUSY;
-- 
cgit v1.2.3


From c03101ff4f74bb30679c1a03d551ecbef1024bf6 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Fri, 4 Oct 2019 14:59:26 +0300
Subject: xhci: Fix false warning message about wrong bounce buffer write
 length

The check printing out the "WARN Wrong bounce buffer write length:"
uses incorrect values when comparing bytes written from scatterlist
to bounce buffer. Actual copied lengths are fine.

The used seg->bounce_len will be set to equal new_buf_len a few lines later
in the code, but is incorrect when doing the comparison.

The patch which added this false warning was backported to 4.8+ kernels
so this should be backported as far as well.

Cc: <stable@vger.kernel.org> # v4.8+
Fixes: 597c56e372da ("xhci: update bounce buffer with correct sg num")
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/1570190373-30684-2-git-send-email-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-ring.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 9741cdeea9d7..85ceb43e3405 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -3202,10 +3202,10 @@ static int xhci_align_td(struct xhci_hcd *xhci, struct urb *urb, u32 enqd_len,
 	if (usb_urb_dir_out(urb)) {
 		len = sg_pcopy_to_buffer(urb->sg, urb->num_sgs,
 				   seg->bounce_buf, new_buff_len, enqd_len);
-		if (len != seg->bounce_len)
+		if (len != new_buff_len)
 			xhci_warn(xhci,
 				"WARN Wrong bounce buffer write length: %zu != %d\n",
-				len, seg->bounce_len);
+				len, new_buff_len);
 		seg->bounce_dma = dma_map_single(dev, seg->bounce_buf,
 						 max_pkt, DMA_TO_DEVICE);
 	} else {
-- 
cgit v1.2.3


From cd9d9491e835a845c1a98b8471f88d26285e0bb9 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Fri, 4 Oct 2019 14:59:27 +0300
Subject: xhci: Prevent device initiated U1/U2 link pm if exit latency is too
 long

If host/hub initiated link pm is prevented by a driver flag we still must
ensure that periodic endpoints have longer service intervals than link pm
exit latency before allowing device initiated link pm.

Fix this by continue walking and checking endpoint service interval if
xhci_get_timeout_no_hub_lpm() returns anything else than USB3_LPM_DISABLED

While at it fix the split line error message

Tested-by: Jan Schmidt <jan@centricular.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/1570190373-30684-3-git-send-email-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 500865975687..aed5a65f25bd 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -4790,10 +4790,12 @@ static u16 xhci_calculate_lpm_timeout(struct usb_hcd *hcd,
 		if (intf->dev.driver) {
 			driver = to_usb_driver(intf->dev.driver);
 			if (driver && driver->disable_hub_initiated_lpm) {
-				dev_dbg(&udev->dev, "Hub-initiated %s disabled "
-						"at request of driver %s\n",
-						state_name, driver->name);
-				return xhci_get_timeout_no_hub_lpm(udev, state);
+				dev_dbg(&udev->dev, "Hub-initiated %s disabled at request of driver %s\n",
+					state_name, driver->name);
+				timeout = xhci_get_timeout_no_hub_lpm(udev,
+								      state);
+				if (timeout == USB3_LPM_DISABLED)
+					return timeout;
 			}
 		}
 
-- 
cgit v1.2.3


From d500c63f80f2ea08ee300e57da5f2af1c13875f5 Mon Sep 17 00:00:00 2001
From: Jan Schmidt <jan@centricular.com>
Date: Fri, 4 Oct 2019 14:59:28 +0300
Subject: xhci: Check all endpoints for LPM timeout

If an endpoint is encountered that returns USB3_LPM_DEVICE_INITIATED, keep
checking further endpoints, as there might be periodic endpoints later
that return USB3_LPM_DISABLED due to shorter service intervals.

Without this, the code can set too high a maximum-exit-latency and
prevent the use of multiple USB3 cameras that should be able to work.

Cc: <stable@vger.kernel.org>
Signed-off-by: Jan Schmidt <jan@centricular.com>
Tested-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/1570190373-30684-4-git-send-email-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index aed5a65f25bd..a5ba5ace3d00 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -4674,12 +4674,12 @@ static int xhci_update_timeout_for_endpoint(struct xhci_hcd *xhci,
 	alt_timeout = xhci_call_host_update_timeout_for_endpoint(xhci, udev,
 		desc, state, timeout);
 
-	/* If we found we can't enable hub-initiated LPM, or
+	/* If we found we can't enable hub-initiated LPM, and
 	 * the U1 or U2 exit latency was too high to allow
-	 * device-initiated LPM as well, just stop searching.
+	 * device-initiated LPM as well, then we will disable LPM
+	 * for this device, so stop searching any further.
 	 */
-	if (alt_timeout == USB3_LPM_DISABLED ||
-			alt_timeout == USB3_LPM_DEVICE_INITIATED) {
+	if (alt_timeout == USB3_LPM_DISABLED) {
 		*timeout = alt_timeout;
 		return -E2BIG;
 	}
-- 
cgit v1.2.3


From 47f50d61076523e1a0d5a070062c2311320eeca8 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Fri, 4 Oct 2019 14:59:29 +0300
Subject: xhci: Fix USB 3.1 capability detection on early xHCI 1.1 spec based
 hosts
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Early xHCI 1.1 spec did not mention USB 3.1 capable hosts should set
sbrn to 0x31, or that the minor revision is a two digit BCD
containing minor and sub-minor numbers.
This was later clarified in xHCI 1.2.

Some USB 3.1 capable hosts therefore have sbrn set to 0x30, or minor
revision set to 0x1 instead of 0x10.

Detect the USB 3.1 capability correctly for these hosts as well

Fixes: ddd57980a0fd ("xhci: detect USB 3.2 capable host controllers correctly")
Cc: <stable@vger.kernel.org> # v4.18+
Cc: Loïc Yhuel <loic.yhuel@gmail.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/1570190373-30684-5-git-send-email-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index a5ba5ace3d00..aec69d294973 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -5079,11 +5079,18 @@ int xhci_gen_setup(struct usb_hcd *hcd, xhci_get_quirks_t get_quirks)
 		hcd->has_tt = 1;
 	} else {
 		/*
-		 * Some 3.1 hosts return sbrn 0x30, use xhci supported protocol
-		 * minor revision instead of sbrn. Minor revision is a two digit
-		 * BCD containing minor and sub-minor numbers, only show minor.
+		 * Early xHCI 1.1 spec did not mention USB 3.1 capable hosts
+		 * should return 0x31 for sbrn, or that the minor revision
+		 * is a two digit BCD containig minor and sub-minor numbers.
+		 * This was later clarified in xHCI 1.2.
+		 *
+		 * Some USB 3.1 capable hosts therefore have sbrn 0x30, and
+		 * minor revision set to 0x1 instead of 0x10.
 		 */
-		minor_rev = xhci->usb3_rhub.min_rev / 0x10;
+		if (xhci->usb3_rhub.min_rev == 0x1)
+			minor_rev = 1;
+		else
+			minor_rev = xhci->usb3_rhub.min_rev / 0x10;
 
 		switch (minor_rev) {
 		case 2:
-- 
cgit v1.2.3


From a70bcbc322837eda1ab5994d12db941dc9733a7d Mon Sep 17 00:00:00 2001
From: Rick Tseng <rtseng@nvidia.com>
Date: Fri, 4 Oct 2019 14:59:30 +0300
Subject: usb: xhci: wait for CNR controller not ready bit in xhci resume

NVIDIA 3.1 xHCI card would lose power when moving power state into D3Cold.
Thus we need to wait for CNR bit to clear in xhci resume, just as in
xhci init.

[Minor changes to comment and commit message -Mathias]
Cc: <stable@vger.kernel.org>
Signed-off-by: Rick Tseng <rtseng@nvidia.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/1570190373-30684-6-git-send-email-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index aec69d294973..fe8f9ff58015 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1108,6 +1108,18 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 		hibernated = true;
 
 	if (!hibernated) {
+		/*
+		 * Some controllers might lose power during suspend, so wait
+		 * for controller not ready bit to clear, just as in xHC init.
+		 */
+		retval = xhci_handshake(&xhci->op_regs->status,
+					STS_CNR, 0, 10 * 1000 * 1000);
+		if (retval) {
+			xhci_warn(xhci, "Controller not ready at resume %d\n",
+				  retval);
+			spin_unlock_irq(&xhci->lock);
+			return retval;
+		}
 		/* step 1: restore register */
 		xhci_restore_registers(xhci);
 		/* step 2: initialize command ring buffer */
-- 
cgit v1.2.3


From 8de66b0e6a56ff10dd00d2b0f2ae52e300178587 Mon Sep 17 00:00:00 2001
From: Bill Kuzeja <William.Kuzeja@stratus.com>
Date: Fri, 4 Oct 2019 14:59:31 +0300
Subject: xhci: Prevent deadlock when xhci adapter breaks during init

The system can hit a deadlock if an xhci adapter breaks while initializing.
The deadlock is between two threads: thread 1 is tearing down the
adapter and is stuck in usb_unlocked_disable_lpm waiting to lock the
hcd->handwidth_mutex. Thread 2 is holding this mutex (while still trying
to add a usb device), but is stuck in xhci_endpoint_reset waiting for a
stop or config command to complete. A reboot is required to resolve.

It turns out when calling xhci_queue_stop_endpoint and
xhci_queue_configure_endpoint in xhci_endpoint_reset, the return code is
not checked for errors. If the timing is right and the adapter dies just
before either of these commands get issued, we hang indefinitely waiting
for a completion on a command that didn't get issued.

This wasn't a problem before the following fix because we didn't send
commands in xhci_endpoint_reset:

commit f5249461b504 ("xhci: Clear the host side toggle manually when
    endpoint is soft reset")

With the patch I am submitting, a duration test which breaks adapters
during initialization (and which deadlocks with the standard kernel) runs
without issue.

Fixes: f5249461b504 ("xhci: Clear the host side toggle manually when endpoint is soft reset")
Cc: <stable@vger.kernel.org> # v4.17+
Cc: Torez Smith <torez@redhat.com>
Signed-off-by: Bill Kuzeja <william.kuzeja@stratus.com>
Signed-off-by: Torez Smith <torez@redhat.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/1570190373-30684-7-git-send-email-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index fe8f9ff58015..8c068d0cc7c1 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3095,6 +3095,7 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
 	unsigned int ep_index;
 	unsigned long flags;
 	u32 ep_flag;
+	int err;
 
 	xhci = hcd_to_xhci(hcd);
 	if (!host_ep->hcpriv)
@@ -3154,7 +3155,17 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
 		xhci_free_command(xhci, cfg_cmd);
 		goto cleanup;
 	}
-	xhci_queue_stop_endpoint(xhci, stop_cmd, udev->slot_id, ep_index, 0);
+
+	err = xhci_queue_stop_endpoint(xhci, stop_cmd, udev->slot_id,
+					ep_index, 0);
+	if (err < 0) {
+		spin_unlock_irqrestore(&xhci->lock, flags);
+		xhci_free_command(xhci, cfg_cmd);
+		xhci_dbg(xhci, "%s: Failed to queue stop ep command, %d ",
+				__func__, err);
+		goto cleanup;
+	}
+
 	xhci_ring_cmd_db(xhci);
 	spin_unlock_irqrestore(&xhci->lock, flags);
 
@@ -3168,8 +3179,16 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
 					   ctrl_ctx, ep_flag, ep_flag);
 	xhci_endpoint_copy(xhci, cfg_cmd->in_ctx, vdev->out_ctx, ep_index);
 
-	xhci_queue_configure_endpoint(xhci, cfg_cmd, cfg_cmd->in_ctx->dma,
+	err = xhci_queue_configure_endpoint(xhci, cfg_cmd, cfg_cmd->in_ctx->dma,
 				      udev->slot_id, false);
+	if (err < 0) {
+		spin_unlock_irqrestore(&xhci->lock, flags);
+		xhci_free_command(xhci, cfg_cmd);
+		xhci_dbg(xhci, "%s: Failed to queue config ep command, %d ",
+				__func__, err);
+		goto cleanup;
+	}
+
 	xhci_ring_cmd_db(xhci);
 	spin_unlock_irqrestore(&xhci->lock, flags);
 
-- 
cgit v1.2.3


From ac343366846a445bb81f0a0e8f16abb8bd5d5d88 Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Fri, 4 Oct 2019 14:59:32 +0300
Subject: xhci: Increase STS_SAVE timeout in xhci_suspend()

After commit f7fac17ca925 ("xhci: Convert xhci_handshake() to use
readl_poll_timeout_atomic()"), ASMedia xHCI may fail to suspend.

Although the algorithms are essentially the same, the old max timeout is
(usec + usec * time of doing readl()), and the new max timeout is just
usec, which is much less than the old one.

Increase the timeout to make ASMedia xHCI able to suspend again.

BugLink: https://bugs.launchpad.net/bugs/1844021
Fixes: f7fac17ca925 ("xhci: Convert xhci_handshake() to use readl_poll_timeout_atomic()")
Cc: <stable@vger.kernel.org> # v5.2+
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/1570190373-30684-8-git-send-email-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 8c068d0cc7c1..00f3804f7aa7 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1032,7 +1032,7 @@ int xhci_suspend(struct xhci_hcd *xhci, bool do_wakeup)
 	writel(command, &xhci->op_regs->command);
 	xhci->broken_suspend = 0;
 	if (xhci_handshake(&xhci->op_regs->status,
-				STS_SAVE, 0, 10 * 1000)) {
+				STS_SAVE, 0, 20 * 1000)) {
 	/*
 	 * AMD SNPS xHC 3.0 occasionally does not clear the
 	 * SSS bit of USBSTS and when driver tries to poll
-- 
cgit v1.2.3


From cfbb8a84c2d2ef49bccacb511002bca4f6053555 Mon Sep 17 00:00:00 2001
From: Mathias Nyman <mathias.nyman@linux.intel.com>
Date: Fri, 4 Oct 2019 14:59:33 +0300
Subject: xhci: Fix NULL pointer dereference in xhci_clear_tt_buffer_complete()

udev stored in ep->hcpriv might be NULL if tt buffer is cleared
due to a halted control endpoint during device enumeration

xhci_clear_tt_buffer_complete is called by hub_tt_work() once it's
scheduled,  and by then usb core might have freed and allocated a
new udev for the next enumeration attempt.

Fixes: ef513be0a905 ("usb: xhci: Add Clear_TT_Buffer")
Cc: <stable@vger.kernel.org> # v5.3
Reported-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/1570190373-30684-9-git-send-email-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 00f3804f7aa7..517ec3206f6e 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -5238,8 +5238,16 @@ static void xhci_clear_tt_buffer_complete(struct usb_hcd *hcd,
 	unsigned int ep_index;
 	unsigned long flags;
 
+	/*
+	 * udev might be NULL if tt buffer is cleared during a failed device
+	 * enumeration due to a halted control endpoint. Usb core might
+	 * have allocated a new udev for the next enumeration attempt.
+	 */
+
 	xhci = hcd_to_xhci(hcd);
 	udev = (struct usb_device *)ep->hcpriv;
+	if (!udev)
+		return;
 	slot_id = udev->slot_id;
 	ep_index = xhci_get_endpoint_index(&ep->desc);
 
-- 
cgit v1.2.3


From 792e559e94bc88a281b10568e99fc469fc28a34d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 18 Sep 2019 22:01:41 +0200
Subject: udc: lpc32xx: fix 64-bit compiler warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

gcc points out a suspicious cast from a pointer to an 'int' when
compile-testing on 64-bit architectures.

drivers/usb/gadget/udc/lpc32xx_udc.c: In function ‘udc_pop_fifo’:
drivers/usb/gadget/udc/lpc32xx_udc.c:1156:11: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
drivers/usb/gadget/udc/lpc32xx_udc.c: In function ‘udc_stuff_fifo’:
drivers/usb/gadget/udc/lpc32xx_udc.c:1257:11: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]

The code works find, but it's easy enough to change the cast to
a uintptr_t to shut up that warning.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20190918200201.2292008-1-arnd@arndb.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/udc/Kconfig       | 2 +-
 drivers/usb/gadget/udc/lpc32xx_udc.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/gadget/udc/Kconfig b/drivers/usb/gadget/udc/Kconfig
index d7e611645533..d354036ff6c8 100644
--- a/drivers/usb/gadget/udc/Kconfig
+++ b/drivers/usb/gadget/udc/Kconfig
@@ -45,7 +45,7 @@ config USB_AT91
 
 config USB_LPC32XX
 	tristate "LPC32XX USB Peripheral Controller"
-	depends on ARCH_LPC32XX
+	depends on ARCH_LPC32XX || COMPILE_TEST
 	depends on I2C
 	select USB_ISP1301
 	help
diff --git a/drivers/usb/gadget/udc/lpc32xx_udc.c b/drivers/usb/gadget/udc/lpc32xx_udc.c
index b3e073fb88c6..2b1f3cc7819b 100644
--- a/drivers/usb/gadget/udc/lpc32xx_udc.c
+++ b/drivers/usb/gadget/udc/lpc32xx_udc.c
@@ -1151,7 +1151,7 @@ static void udc_pop_fifo(struct lpc32xx_udc *udc, u8 *data, u32 bytes)
 	u32 *p32, tmp, cbytes;
 
 	/* Use optimal data transfer method based on source address and size */
-	switch (((u32) data) & 0x3) {
+	switch (((uintptr_t) data) & 0x3) {
 	case 0: /* 32-bit aligned */
 		p32 = (u32 *) data;
 		cbytes = (bytes & ~0x3);
@@ -1252,7 +1252,7 @@ static void udc_stuff_fifo(struct lpc32xx_udc *udc, u8 *data, u32 bytes)
 	u32 *p32, tmp, cbytes;
 
 	/* Use optimal data transfer method based on source address and size */
-	switch (((u32) data) & 0x3) {
+	switch (((uintptr_t) data) & 0x3) {
 	case 0: /* 32-bit aligned */
 		p32 = (u32 *) data;
 		cbytes = (bytes & ~0x3);
-- 
cgit v1.2.3


From 1aae1394294cb71c6aa0bc904a94a7f2f1e75936 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Tue, 1 Oct 2019 19:10:32 +0900
Subject: usb: renesas_usbhs: gadget: Do not discard queues in
 usb_ep_set_{halt,wedge}()

The commit 97664a207bc2 ("usb: renesas_usbhs: shrink spin lock area")
had added a usbhsg_pipe_disable() calling into
__usbhsg_ep_set_halt_wedge() accidentally. But, this driver should
not call the usbhsg_pipe_disable() because the function discards
all queues. So, this patch removes it.

Fixes: 97664a207bc2 ("usb: renesas_usbhs: shrink spin lock area")
Cc: <stable@vger.kernel.org> # v3.1+
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/1569924633-322-2-git-send-email-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/renesas_usbhs/mod_gadget.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c
index 4d571a5205e2..2c7523a211c0 100644
--- a/drivers/usb/renesas_usbhs/mod_gadget.c
+++ b/drivers/usb/renesas_usbhs/mod_gadget.c
@@ -723,8 +723,6 @@ static int __usbhsg_ep_set_halt_wedge(struct usb_ep *ep, int halt, int wedge)
 	struct device *dev = usbhsg_gpriv_to_dev(gpriv);
 	unsigned long flags;
 
-	usbhsg_pipe_disable(uep);
-
 	dev_dbg(dev, "set halt %d (pipe %d)\n",
 		halt, usbhs_pipe_number(pipe));
 
-- 
cgit v1.2.3


From 4d599cd3a097a85a5c68a2c82b9a48cddf9953ec Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Tue, 1 Oct 2019 19:10:33 +0900
Subject: usb: renesas_usbhs: gadget: Fix usb_ep_set_{halt,wedge}() behavior

According to usb_ep_set_halt()'s description,
__usbhsg_ep_set_halt_wedge() should return -EAGAIN if the IN endpoint
has any queue or data. Otherwise, this driver is possible to cause
just STALL without sending a short packet data on g_mass_storage driver,
and then a few resetting a device happens on a host side during
a usb enumaration.

Fixes: 2f98382dcdfe ("usb: renesas_usbhs: Add Renesas USBHS Gadget")
Cc: <stable@vger.kernel.org> # v3.0+
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/1569924633-322-3-git-send-email-yoshihiro.shimoda.uh@renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/renesas_usbhs/common.h     |  1 +
 drivers/usb/renesas_usbhs/fifo.c       |  2 +-
 drivers/usb/renesas_usbhs/fifo.h       |  1 +
 drivers/usb/renesas_usbhs/mod_gadget.c | 16 +++++++++++++++-
 drivers/usb/renesas_usbhs/pipe.c       | 15 +++++++++++++++
 drivers/usb/renesas_usbhs/pipe.h       |  1 +
 6 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/renesas_usbhs/common.h b/drivers/usb/renesas_usbhs/common.h
index d1a0a35ecfff..0824099b905e 100644
--- a/drivers/usb/renesas_usbhs/common.h
+++ b/drivers/usb/renesas_usbhs/common.h
@@ -211,6 +211,7 @@ struct usbhs_priv;
 /* DCPCTR */
 #define BSTS		(1 << 15)	/* Buffer Status */
 #define SUREQ		(1 << 14)	/* Sending SETUP Token */
+#define INBUFM		(1 << 14)	/* (PIPEnCTR) Transfer Buffer Monitor */
 #define CSSTS		(1 << 12)	/* CSSTS Status */
 #define	ACLRM		(1 << 9)	/* Buffer Auto-Clear Mode */
 #define SQCLR		(1 << 8)	/* Toggle Bit Clear */
diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c
index 2a01ceb71641..86637cd066cf 100644
--- a/drivers/usb/renesas_usbhs/fifo.c
+++ b/drivers/usb/renesas_usbhs/fifo.c
@@ -89,7 +89,7 @@ static void __usbhsf_pkt_del(struct usbhs_pkt *pkt)
 	list_del_init(&pkt->node);
 }
 
-static struct usbhs_pkt *__usbhsf_pkt_get(struct usbhs_pipe *pipe)
+struct usbhs_pkt *__usbhsf_pkt_get(struct usbhs_pipe *pipe)
 {
 	return list_first_entry_or_null(&pipe->list, struct usbhs_pkt, node);
 }
diff --git a/drivers/usb/renesas_usbhs/fifo.h b/drivers/usb/renesas_usbhs/fifo.h
index 88d1816bcda2..c3d3cc35cee0 100644
--- a/drivers/usb/renesas_usbhs/fifo.h
+++ b/drivers/usb/renesas_usbhs/fifo.h
@@ -97,5 +97,6 @@ void usbhs_pkt_push(struct usbhs_pipe *pipe, struct usbhs_pkt *pkt,
 		    void *buf, int len, int zero, int sequence);
 struct usbhs_pkt *usbhs_pkt_pop(struct usbhs_pipe *pipe, struct usbhs_pkt *pkt);
 void usbhs_pkt_start(struct usbhs_pipe *pipe);
+struct usbhs_pkt *__usbhsf_pkt_get(struct usbhs_pipe *pipe);
 
 #endif /* RENESAS_USB_FIFO_H */
diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c
index 2c7523a211c0..e5ef56991dba 100644
--- a/drivers/usb/renesas_usbhs/mod_gadget.c
+++ b/drivers/usb/renesas_usbhs/mod_gadget.c
@@ -722,6 +722,7 @@ static int __usbhsg_ep_set_halt_wedge(struct usb_ep *ep, int halt, int wedge)
 	struct usbhs_priv *priv = usbhsg_gpriv_to_priv(gpriv);
 	struct device *dev = usbhsg_gpriv_to_dev(gpriv);
 	unsigned long flags;
+	int ret = 0;
 
 	dev_dbg(dev, "set halt %d (pipe %d)\n",
 		halt, usbhs_pipe_number(pipe));
@@ -729,6 +730,18 @@ static int __usbhsg_ep_set_halt_wedge(struct usb_ep *ep, int halt, int wedge)
 	/********************  spin lock ********************/
 	usbhs_lock(priv, flags);
 
+	/*
+	 * According to usb_ep_set_halt()'s description, this function should
+	 * return -EAGAIN if the IN endpoint has any queue or data. Note
+	 * that the usbhs_pipe_is_dir_in() returns false if the pipe is an
+	 * IN endpoint in the gadget mode.
+	 */
+	if (!usbhs_pipe_is_dir_in(pipe) && (__usbhsf_pkt_get(pipe) ||
+	    usbhs_pipe_contains_transmittable_data(pipe))) {
+		ret = -EAGAIN;
+		goto out;
+	}
+
 	if (halt)
 		usbhs_pipe_stall(pipe);
 	else
@@ -739,10 +752,11 @@ static int __usbhsg_ep_set_halt_wedge(struct usb_ep *ep, int halt, int wedge)
 	else
 		usbhsg_status_clr(gpriv, USBHSG_STATUS_WEDGE);
 
+out:
 	usbhs_unlock(priv, flags);
 	/********************  spin unlock ******************/
 
-	return 0;
+	return ret;
 }
 
 static int usbhsg_ep_set_halt(struct usb_ep *ep, int value)
diff --git a/drivers/usb/renesas_usbhs/pipe.c b/drivers/usb/renesas_usbhs/pipe.c
index c4922b96c93b..9e5afdde1adb 100644
--- a/drivers/usb/renesas_usbhs/pipe.c
+++ b/drivers/usb/renesas_usbhs/pipe.c
@@ -277,6 +277,21 @@ int usbhs_pipe_is_accessible(struct usbhs_pipe *pipe)
 	return -EBUSY;
 }
 
+bool usbhs_pipe_contains_transmittable_data(struct usbhs_pipe *pipe)
+{
+	u16 val;
+
+	/* Do not support for DCP pipe */
+	if (usbhs_pipe_is_dcp(pipe))
+		return false;
+
+	val = usbhsp_pipectrl_get(pipe);
+	if (val & INBUFM)
+		return true;
+
+	return false;
+}
+
 /*
  *		PID ctrl
  */
diff --git a/drivers/usb/renesas_usbhs/pipe.h b/drivers/usb/renesas_usbhs/pipe.h
index 3080423e600c..3b130529408b 100644
--- a/drivers/usb/renesas_usbhs/pipe.h
+++ b/drivers/usb/renesas_usbhs/pipe.h
@@ -83,6 +83,7 @@ void usbhs_pipe_clear(struct usbhs_pipe *pipe);
 void usbhs_pipe_clear_without_sequence(struct usbhs_pipe *pipe,
 				       int needs_bfre, int bfre_enable);
 int usbhs_pipe_is_accessible(struct usbhs_pipe *pipe);
+bool usbhs_pipe_contains_transmittable_data(struct usbhs_pipe *pipe);
 void usbhs_pipe_enable(struct usbhs_pipe *pipe);
 void usbhs_pipe_disable(struct usbhs_pipe *pipe);
 void usbhs_pipe_stall(struct usbhs_pipe *pipe);
-- 
cgit v1.2.3


From e6064cf4dafd75240ec7f512abfd5a63da9fce24 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <mripard@kernel.org>
Date: Wed, 2 Oct 2019 13:26:50 +0200
Subject: ARM: dts: sunxi: Revert phy-names removal for ECHI and OHCI

This reverts commits 3d109bdca981 ("ARM: dts: sunxi: Remove useless
phy-names from EHCI and OHCI"), 0a3df8bb6dad ("ARM: dts: sunxi: h3/h5:
Remove useless phy-names from EHCI and OHCI") and 3c7ab90aaa28 ("arm64:
dts: allwinner: Remove useless phy-names from EHCI and OHCI").

It turns out that while the USB bindings were not mentionning it, the PHY
client bindings were mandating that phy-names is set when phys is. Let's
add it back.

Fixes: 3d109bdca981 ("ARM: dts: sunxi: Remove useless phy-names from EHCI and OHCI")
Fixes: 0a3df8bb6dad ("ARM: dts: sunxi: h3/h5: Remove useless phy-names from EHCI and OHCI")
Fixes: 3c7ab90aaa28 ("arm64: dts: allwinner: Remove useless phy-names from EHCI and OHCI")
Reported-by: Emmanuel Vadot <manu@bidouilliste.com>
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Link: https://lore.kernel.org/r/20191002112651.100504-1-mripard@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm/boot/dts/sun4i-a10.dtsi                      | 4 ++++
 arch/arm/boot/dts/sun5i.dtsi                          | 2 ++
 arch/arm/boot/dts/sun6i-a31.dtsi                      | 4 ++++
 arch/arm/boot/dts/sun7i-a20.dtsi                      | 4 ++++
 arch/arm/boot/dts/sun8i-a23-a33.dtsi                  | 2 ++
 arch/arm/boot/dts/sun8i-a83t.dtsi                     | 3 +++
 arch/arm/boot/dts/sun8i-r40.dtsi                      | 4 ++++
 arch/arm/boot/dts/sun9i-a80.dtsi                      | 5 +++++
 arch/arm/boot/dts/sunxi-h3-h5.dtsi                    | 6 ++++++
 arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts | 2 ++
 arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi         | 2 ++
 arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi          | 2 ++
 12 files changed, 40 insertions(+)

diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index ce823c44e98a..4c268b70b735 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -520,6 +520,7 @@
 			interrupts = <39>;
 			clocks = <&ccu CLK_AHB_EHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -529,6 +530,7 @@
 			interrupts = <64>;
 			clocks = <&ccu CLK_USB_OHCI0>, <&ccu CLK_AHB_OHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -608,6 +610,7 @@
 			interrupts = <40>;
 			clocks = <&ccu CLK_AHB_EHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -617,6 +620,7 @@
 			interrupts = <65>;
 			clocks = <&ccu CLK_USB_OHCI1>, <&ccu CLK_AHB_OHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi
index cfb1efc8828c..6befa236ba99 100644
--- a/arch/arm/boot/dts/sun5i.dtsi
+++ b/arch/arm/boot/dts/sun5i.dtsi
@@ -391,6 +391,7 @@
 			interrupts = <39>;
 			clocks = <&ccu CLK_AHB_EHCI>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -400,6 +401,7 @@
 			interrupts = <40>;
 			clocks = <&ccu CLK_USB_OHCI>, <&ccu CLK_AHB_OHCI>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi
index bbeb743633c6..ac7638078420 100644
--- a/arch/arm/boot/dts/sun6i-a31.dtsi
+++ b/arch/arm/boot/dts/sun6i-a31.dtsi
@@ -545,6 +545,7 @@
 			clocks = <&ccu CLK_AHB1_EHCI0>;
 			resets = <&ccu RST_AHB1_EHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -555,6 +556,7 @@
 			clocks = <&ccu CLK_AHB1_OHCI0>, <&ccu CLK_USB_OHCI0>;
 			resets = <&ccu RST_AHB1_OHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -565,6 +567,7 @@
 			clocks = <&ccu CLK_AHB1_EHCI1>;
 			resets = <&ccu RST_AHB1_EHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -575,6 +578,7 @@
 			clocks = <&ccu CLK_AHB1_OHCI1>, <&ccu CLK_USB_OHCI1>;
 			resets = <&ccu RST_AHB1_OHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 49380de754a9..874231be04e4 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -623,6 +623,7 @@
 			interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_AHB_EHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -632,6 +633,7 @@
 			interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_USB_OHCI0>, <&ccu CLK_AHB_OHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -714,6 +716,7 @@
 			interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_AHB_EHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -723,6 +726,7 @@
 			interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&ccu CLK_USB_OHCI1>, <&ccu CLK_AHB_OHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun8i-a23-a33.dtsi b/arch/arm/boot/dts/sun8i-a23-a33.dtsi
index 52eed0ae3607..f292f96ab39b 100644
--- a/arch/arm/boot/dts/sun8i-a23-a33.dtsi
+++ b/arch/arm/boot/dts/sun8i-a23-a33.dtsi
@@ -307,6 +307,7 @@
 			clocks = <&ccu CLK_BUS_EHCI>;
 			resets = <&ccu RST_BUS_EHCI>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -317,6 +318,7 @@
 			clocks = <&ccu CLK_BUS_OHCI>, <&ccu CLK_USB_OHCI>;
 			resets = <&ccu RST_BUS_OHCI>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun8i-a83t.dtsi b/arch/arm/boot/dts/sun8i-a83t.dtsi
index 523be6611c50..74bb053cf23c 100644
--- a/arch/arm/boot/dts/sun8i-a83t.dtsi
+++ b/arch/arm/boot/dts/sun8i-a83t.dtsi
@@ -632,6 +632,7 @@
 			clocks = <&ccu CLK_BUS_EHCI0>;
 			resets = <&ccu RST_BUS_EHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -643,6 +644,7 @@
 			clocks = <&ccu CLK_BUS_OHCI0>, <&ccu CLK_USB_OHCI0>;
 			resets = <&ccu RST_BUS_OHCI0>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -654,6 +656,7 @@
 			clocks = <&ccu CLK_BUS_EHCI1>;
 			resets = <&ccu RST_BUS_EHCI1>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun8i-r40.dtsi b/arch/arm/boot/dts/sun8i-r40.dtsi
index bde068111b85..c9c2688db66d 100644
--- a/arch/arm/boot/dts/sun8i-r40.dtsi
+++ b/arch/arm/boot/dts/sun8i-r40.dtsi
@@ -273,6 +273,7 @@
 			clocks = <&ccu CLK_BUS_EHCI1>;
 			resets = <&ccu RST_BUS_EHCI1>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -284,6 +285,7 @@
 				 <&ccu CLK_USB_OHCI1>;
 			resets = <&ccu RST_BUS_OHCI1>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -294,6 +296,7 @@
 			clocks = <&ccu CLK_BUS_EHCI2>;
 			resets = <&ccu RST_BUS_EHCI2>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -305,6 +308,7 @@
 				 <&ccu CLK_USB_OHCI2>;
 			resets = <&ccu RST_BUS_OHCI2>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun9i-a80.dtsi b/arch/arm/boot/dts/sun9i-a80.dtsi
index c34d505c7efe..b9b6fb00be28 100644
--- a/arch/arm/boot/dts/sun9i-a80.dtsi
+++ b/arch/arm/boot/dts/sun9i-a80.dtsi
@@ -346,6 +346,7 @@
 			clocks = <&usb_clocks CLK_BUS_HCI0>;
 			resets = <&usb_clocks RST_USB0_HCI>;
 			phys = <&usbphy1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -357,6 +358,7 @@
 				 <&usb_clocks CLK_USB_OHCI0>;
 			resets = <&usb_clocks RST_USB0_HCI>;
 			phys = <&usbphy1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -378,6 +380,7 @@
 			clocks = <&usb_clocks CLK_BUS_HCI1>;
 			resets = <&usb_clocks RST_USB1_HCI>;
 			phys = <&usbphy2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -407,6 +410,7 @@
 			clocks = <&usb_clocks CLK_BUS_HCI2>;
 			resets = <&usb_clocks RST_USB2_HCI>;
 			phys = <&usbphy3>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -418,6 +422,7 @@
 				 <&usb_clocks CLK_USB_OHCI2>;
 			resets = <&usb_clocks RST_USB2_HCI>;
 			phys = <&usbphy3>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sunxi-h3-h5.dtsi b/arch/arm/boot/dts/sunxi-h3-h5.dtsi
index eba190b3f9de..107eeafad20a 100644
--- a/arch/arm/boot/dts/sunxi-h3-h5.dtsi
+++ b/arch/arm/boot/dts/sunxi-h3-h5.dtsi
@@ -304,6 +304,7 @@
 			clocks = <&ccu CLK_BUS_EHCI1>, <&ccu CLK_BUS_OHCI1>;
 			resets = <&ccu RST_BUS_EHCI1>, <&ccu RST_BUS_OHCI1>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -315,6 +316,7 @@
 				 <&ccu CLK_USB_OHCI1>;
 			resets = <&ccu RST_BUS_EHCI1>, <&ccu RST_BUS_OHCI1>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -325,6 +327,7 @@
 			clocks = <&ccu CLK_BUS_EHCI2>, <&ccu CLK_BUS_OHCI2>;
 			resets = <&ccu RST_BUS_EHCI2>, <&ccu RST_BUS_OHCI2>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -336,6 +339,7 @@
 				 <&ccu CLK_USB_OHCI2>;
 			resets = <&ccu RST_BUS_EHCI2>, <&ccu RST_BUS_OHCI2>;
 			phys = <&usbphy 2>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -346,6 +350,7 @@
 			clocks = <&ccu CLK_BUS_EHCI3>, <&ccu CLK_BUS_OHCI3>;
 			resets = <&ccu RST_BUS_EHCI3>, <&ccu RST_BUS_OHCI3>;
 			phys = <&usbphy 3>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -357,6 +362,7 @@
 				 <&ccu CLK_USB_OHCI3>;
 			resets = <&ccu RST_BUS_EHCI3>, <&ccu RST_BUS_OHCI3>;
 			phys = <&usbphy 3>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts
index 2b6345db7dc0..78c82a665c84 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinebook.dts
@@ -104,6 +104,7 @@
 
 &ehci0 {
 	phys = <&usbphy 0>;
+	phy-names = "usb";
 	status = "okay";
 };
 
@@ -150,6 +151,7 @@
 
 &ohci0 {
 	phys = <&usbphy 0>;
+	phy-names = "usb";
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
index 69128a6dfc46..3eccbdba7154 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
@@ -553,6 +553,7 @@
 			resets = <&ccu RST_BUS_OHCI1>,
 				 <&ccu RST_BUS_EHCI1>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -564,6 +565,7 @@
 				 <&ccu CLK_USB_OHCI1>;
 			resets = <&ccu RST_BUS_OHCI1>;
 			phys = <&usbphy 1>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
index 4020a1aafa3e..0d5ea19336a1 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
@@ -547,6 +547,7 @@
 			resets = <&ccu RST_BUS_OHCI3>,
 				 <&ccu RST_BUS_EHCI3>;
 			phys = <&usb2phy 3>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
@@ -558,6 +559,7 @@
 				 <&ccu CLK_USB_OHCI3>;
 			resets = <&ccu RST_BUS_OHCI3>;
 			phys = <&usb2phy 3>;
+			phy-names = "usb";
 			status = "disabled";
 		};
 
-- 
cgit v1.2.3


From 3aa3c66aedef6a21ea1ad53f5b4491430ef0c84e Mon Sep 17 00:00:00 2001
From: Maxime Ripard <mripard@kernel.org>
Date: Wed, 2 Oct 2019 13:26:51 +0200
Subject: dt-bindings: usb: Bring back phy-names

While the original bindings that were superseeded by the YAML schemas
didn't mention that phy-names was needed, it turns out that phy-names is
required if phys is set according to phy/phy-bindings.txt.

Let's add back those properties.

Fixes: 14ec072a19ad ("dt-bindings: usb: Convert USB HCD generic binding to YAML")
Fixes: c93bcace1098 ("dt-bindings: usb: Convert the generic OHCI binding to YAML")
Fixes: c3e2485d5f4f ("dt-bindings: usb: Convert the generic EHCI binding to YAML")
Reported-by: Emmanuel Vadot <manu@bidouilliste.com>
Signed-off-by: Maxime Ripard <mripard@kernel.org>
Link: https://lore.kernel.org/r/20191002112651.100504-2-mripard@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/generic-ehci.yaml | 7 ++++++-
 Documentation/devicetree/bindings/usb/generic-ohci.yaml | 7 ++++++-
 Documentation/devicetree/bindings/usb/usb-hcd.yaml      | 5 +++++
 3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/usb/generic-ehci.yaml b/Documentation/devicetree/bindings/usb/generic-ehci.yaml
index 059f6ef1ad4a..1ca64c85191a 100644
--- a/Documentation/devicetree/bindings/usb/generic-ehci.yaml
+++ b/Documentation/devicetree/bindings/usb/generic-ehci.yaml
@@ -63,7 +63,11 @@ properties:
     description:
       Set this flag to force EHCI reset after resume.
 
-  phys: true
+  phys:
+    description: PHY specifier for the USB PHY
+
+  phy-names:
+    const: usb
 
 required:
   - compatible
@@ -89,6 +93,7 @@ examples:
         interrupts = <39>;
         clocks = <&ahb_gates 1>;
         phys = <&usbphy 1>;
+        phy-names = "usb";
     };
 
 ...
diff --git a/Documentation/devicetree/bindings/usb/generic-ohci.yaml b/Documentation/devicetree/bindings/usb/generic-ohci.yaml
index da5a14becbe5..bcffec1f1341 100644
--- a/Documentation/devicetree/bindings/usb/generic-ohci.yaml
+++ b/Documentation/devicetree/bindings/usb/generic-ohci.yaml
@@ -67,7 +67,11 @@ properties:
     description:
       Overrides the detected port count
 
-  phys: true
+  phys:
+    description: PHY specifier for the USB PHY
+
+  phy-names:
+    const: usb
 
 required:
   - compatible
@@ -84,6 +88,7 @@ examples:
           interrupts = <64>;
           clocks = <&usb_clk 6>, <&ahb_gates 2>;
           phys = <&usbphy 1>;
+          phy-names = "usb";
       };
 
 ...
diff --git a/Documentation/devicetree/bindings/usb/usb-hcd.yaml b/Documentation/devicetree/bindings/usb/usb-hcd.yaml
index 9c8c56d3a792..7263b7f2b510 100644
--- a/Documentation/devicetree/bindings/usb/usb-hcd.yaml
+++ b/Documentation/devicetree/bindings/usb/usb-hcd.yaml
@@ -18,8 +18,13 @@ properties:
     description:
       List of all the USB PHYs on this HCD
 
+  phy-names:
+    description:
+      Name specifier for the USB PHY
+
 examples:
   - |
     usb {
         phys = <&usb2_phy1>, <&usb3_phy1>;
+        phy-names = "usb";
     };
-- 
cgit v1.2.3


From ee4155f40cefea8af78b0bd20897ca97e2a8e72e Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Thu, 5 Sep 2019 10:00:01 +0000
Subject: xhci-ext-caps.c: Add missing platform_device_put() on error in
 xhci_create_intel_xhci_sw_pdev()

Add the missing platform_device_put() before return from
xhci_create_intel_xhci_sw_pdev() in the error handling case.

Fixes: 6ed151f26484 ("xhci-ext-caps.c: Add property to disable Intel SW switch")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Link: https://lore.kernel.org/r/20190905100001.128349-1-weiyongjun1@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-ext-caps.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/host/xhci-ext-caps.c b/drivers/usb/host/xhci-ext-caps.c
index f498160df969..3351d07c431f 100644
--- a/drivers/usb/host/xhci-ext-caps.c
+++ b/drivers/usb/host/xhci-ext-caps.c
@@ -57,6 +57,7 @@ static int xhci_create_intel_xhci_sw_pdev(struct xhci_hcd *xhci, u32 cap_offset)
 		ret = platform_device_add_properties(pdev, role_switch_props);
 		if (ret) {
 			dev_err(dev, "failed to register device properties\n");
+			platform_device_put(pdev);
 			return ret;
 		}
 	}
-- 
cgit v1.2.3


From 5c290a5e42c3387e82de86965784d30e6c5270fd Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 1 Oct 2019 10:49:05 +0200
Subject: USB: usb-skeleton: fix runtime PM after driver unbind

Since commit c2b71462d294 ("USB: core: Fix bug caused by duplicate
interface PM usage counter") USB drivers must always balance their
runtime PM gets and puts, including when the driver has already been
unbound from the interface.

Leaving the interface with a positive PM usage counter would prevent a
later bound driver from suspending the device.

Fixes: c2b71462d294 ("USB: core: Fix bug caused by duplicate interface PM usage counter")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191001084908.2003-2-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usb-skeleton.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/usb-skeleton.c b/drivers/usb/usb-skeleton.c
index c31d17d05810..8001d6384c73 100644
--- a/drivers/usb/usb-skeleton.c
+++ b/drivers/usb/usb-skeleton.c
@@ -73,6 +73,7 @@ static void skel_delete(struct kref *kref)
 	struct usb_skel *dev = to_skel_dev(kref);
 
 	usb_free_urb(dev->bulk_in_urb);
+	usb_put_intf(dev->interface);
 	usb_put_dev(dev->udev);
 	kfree(dev->bulk_in_buffer);
 	kfree(dev);
@@ -124,10 +125,7 @@ static int skel_release(struct inode *inode, struct file *file)
 		return -ENODEV;
 
 	/* allow the device to be autosuspended */
-	mutex_lock(&dev->io_mutex);
-	if (dev->interface)
-		usb_autopm_put_interface(dev->interface);
-	mutex_unlock(&dev->io_mutex);
+	usb_autopm_put_interface(dev->interface);
 
 	/* decrement the count on our device */
 	kref_put(&dev->kref, skel_delete);
@@ -507,7 +505,7 @@ static int skel_probe(struct usb_interface *interface,
 	init_waitqueue_head(&dev->bulk_in_wait);
 
 	dev->udev = usb_get_dev(interface_to_usbdev(interface));
-	dev->interface = interface;
+	dev->interface = usb_get_intf(interface);
 
 	/* set up the endpoint information */
 	/* use only the first bulk-in and bulk-out endpoints */
-- 
cgit v1.2.3


From 9a31535859bfd8d1c3ed391f5e9247cd87bb7909 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 1 Oct 2019 10:49:06 +0200
Subject: USB: usblp: fix runtime PM after driver unbind

Since commit c2b71462d294 ("USB: core: Fix bug caused by duplicate
interface PM usage counter") USB drivers must always balance their
runtime PM gets and puts, including when the driver has already been
unbound from the interface.

Leaving the interface with a positive PM usage counter would prevent a
later bound driver from suspending the device.

Fixes: c2b71462d294 ("USB: core: Fix bug caused by duplicate interface PM usage counter")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191001084908.2003-3-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/class/usblp.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c
index 7fea4999d352..fb8bd60c83f4 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -461,10 +461,12 @@ static int usblp_release(struct inode *inode, struct file *file)
 
 	mutex_lock(&usblp_mutex);
 	usblp->used = 0;
-	if (usblp->present) {
+	if (usblp->present)
 		usblp_unlink_urbs(usblp);
-		usb_autopm_put_interface(usblp->intf);
-	} else		/* finish cleanup from disconnect */
+
+	usb_autopm_put_interface(usblp->intf);
+
+	if (!usblp->present)		/* finish cleanup from disconnect */
 		usblp_cleanup(usblp);
 	mutex_unlock(&usblp_mutex);
 	return 0;
-- 
cgit v1.2.3


From d51bdb93ca7e71d7fb30a572c7b47ed0194bf3fe Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 1 Oct 2019 10:49:07 +0200
Subject: USB: serial: fix runtime PM after driver unbind

Since commit c2b71462d294 ("USB: core: Fix bug caused by duplicate
interface PM usage counter") USB drivers must always balance their
runtime PM gets and puts, including when the driver has already been
unbound from the interface.

Leaving the interface with a positive PM usage counter would prevent a
later bound driver from suspending the device.

Fixes: c2b71462d294 ("USB: core: Fix bug caused by duplicate interface PM usage counter")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191001084908.2003-4-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/serial/usb-serial.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index a3179fea38c8..8f066bb55d7d 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -314,10 +314,7 @@ static void serial_cleanup(struct tty_struct *tty)
 	serial = port->serial;
 	owner = serial->type->driver.owner;
 
-	mutex_lock(&serial->disc_mutex);
-	if (!serial->disconnected)
-		usb_autopm_put_interface(serial->interface);
-	mutex_unlock(&serial->disc_mutex);
+	usb_autopm_put_interface(serial->interface);
 
 	usb_serial_put(serial);
 	module_put(owner);
-- 
cgit v1.2.3


From 30045f2174aab7fb4db7a9cf902d0aa6c75856a7 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 1 Oct 2019 10:49:08 +0200
Subject: media: stkwebcam: fix runtime PM after driver unbind

Since commit c2b71462d294 ("USB: core: Fix bug caused by duplicate
interface PM usage counter") USB drivers must always balance their
runtime PM gets and puts, including when the driver has already been
unbound from the interface.

Leaving the interface with a positive PM usage counter would prevent a
later bound driver from suspending the device.

Note that runtime PM has never actually been enabled for this driver
since the support_autosuspend flag in its usb_driver struct is not set.

Fixes: c2b71462d294 ("USB: core: Fix bug caused by duplicate interface PM usage counter")
Cc: stable <stable@vger.kernel.org>
Acked-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191001084908.2003-5-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/media/usb/stkwebcam/stk-webcam.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/media/usb/stkwebcam/stk-webcam.c b/drivers/media/usb/stkwebcam/stk-webcam.c
index cfca3c70599b..21f90a887485 100644
--- a/drivers/media/usb/stkwebcam/stk-webcam.c
+++ b/drivers/media/usb/stkwebcam/stk-webcam.c
@@ -643,8 +643,7 @@ static int v4l_stk_release(struct file *fp)
 		dev->owner = NULL;
 	}
 
-	if (is_present(dev))
-		usb_autopm_put_interface(dev->interface);
+	usb_autopm_put_interface(dev->interface);
 	mutex_unlock(&dev->lock);
 	return v4l2_fh_release(fp);
 }
-- 
cgit v1.2.3


From 1580d3cdddbba4a5ef78a04a5289e32844e6af24 Mon Sep 17 00:00:00 2001
From: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Date: Thu, 3 Oct 2019 11:55:30 +0300
Subject: drm/i915: Fix audio power up sequence for gen10+ display

On platfroms with gen10+ display, driver must set the enable bit of
AUDIO_PIN_BUF_CTL register before transactions with the HDA controller
can proceed. Add setting this bit to the audio power up sequence.

Failing to do this resulted in errors during display audio codec probe,
and failures during resume from suspend.

Note: We may also need to disable the bit afterwards, but there are
still unresolved issues with that.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111214
Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191003085531.30990-1-kai.vehmanen@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_audio.c | 5 +++++
 drivers/gpu/drm/i915/i915_reg.h            | 2 ++
 2 files changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index 54638d99e021..e93776710abc 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -862,6 +862,11 @@ static unsigned long i915_audio_component_get_power(struct device *kdev)
 		/* Force CDCLK to 2*BCLK as long as we need audio powered. */
 		if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
 			glk_force_audio_cdclk(dev_priv, true);
+
+		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+			I915_WRITE(AUD_PIN_BUF_CTL,
+				   (I915_READ(AUD_PIN_BUF_CTL) |
+				    AUD_PIN_BUF_ENABLE));
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index eefd789b9a28..813ddea3f9f1 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -9133,6 +9133,8 @@ enum {
 #define   SKL_AUD_CODEC_WAKE_SIGNAL		(1 << 15)
 
 #define AUD_FREQ_CNTRL			_MMIO(0x65900)
+#define AUD_PIN_BUF_CTL		_MMIO(0x48414)
+#define   AUD_PIN_BUF_ENABLE		REG_BIT(31)
 
 /*
  * HSW - ICL power wells
-- 
cgit v1.2.3


From f6ec9483091f8e67adab0311a4e2f90aab523310 Mon Sep 17 00:00:00 2001
From: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Date: Thu, 3 Oct 2019 11:55:31 +0300
Subject: drm/i915: extend audio CDCLK>=2*BCLK constraint to more platforms

The CDCLK>=2*BCLK constraint applies to all generations since gen10.
Extend the constraint logic in audio get/put_power().

Signed-off-by: Kai Vehmanen <kai.vehmanen@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191003085531.30990-2-kai.vehmanen@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_audio.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index e93776710abc..ed18511befa3 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -860,7 +860,7 @@ static unsigned long i915_audio_component_get_power(struct device *kdev)
 		}
 
 		/* Force CDCLK to 2*BCLK as long as we need audio powered. */
-		if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 			glk_force_audio_cdclk(dev_priv, true);
 
 		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
@@ -879,7 +879,7 @@ static void i915_audio_component_put_power(struct device *kdev,
 
 	/* Stop forcing CDCLK to 2*BCLK if no need for audio to be powered. */
 	if (--dev_priv->audio_power_refcount == 0)
-		if (IS_CANNONLAKE(dev_priv) || IS_GEMINILAKE(dev_priv))
+		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 			glk_force_audio_cdclk(dev_priv, false);
 
 	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO, cookie);
-- 
cgit v1.2.3


From 6264dab6efd6069f0387efb078a9960b5642377b Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 10 Sep 2019 06:11:29 +0200
Subject: tty: serial: owl: Fix the link time qualifier of 'owl_uart_exit()'

'exit' functions should be marked as __exit, not __init.

Fixes: fc60a8b675bd ("tty: serial: owl: Implement console driver")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/20190910041129.6978-1-christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/owl-uart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/owl-uart.c b/drivers/tty/serial/owl-uart.c
index 03963af77b15..d2d8b3494685 100644
--- a/drivers/tty/serial/owl-uart.c
+++ b/drivers/tty/serial/owl-uart.c
@@ -740,7 +740,7 @@ static int __init owl_uart_init(void)
 	return ret;
 }
 
-static void __init owl_uart_exit(void)
+static void __exit owl_uart_exit(void)
 {
 	platform_driver_unregister(&owl_uart_platform_driver);
 	uart_unregister_driver(&owl_uart_driver);
-- 
cgit v1.2.3


From 5080d127127ac5b610b57900774d9559ae55e817 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Tue, 10 Sep 2019 06:17:02 +0200
Subject: tty: serial: rda: Fix the link time qualifier of 'rda_uart_exit()'

'exit' functions should be marked as __exit, not __init.

Fixes: c10b13325ced ("tty: serial: Add RDA8810PL UART driver")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/20190910041702.7357-1-christophe.jaillet@wanadoo.fr
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/rda-uart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/rda-uart.c b/drivers/tty/serial/rda-uart.c
index c1b0d7662ef9..ff9a27d48bca 100644
--- a/drivers/tty/serial/rda-uart.c
+++ b/drivers/tty/serial/rda-uart.c
@@ -815,7 +815,7 @@ static int __init rda_uart_init(void)
 	return ret;
 }
 
-static void __init rda_uart_exit(void)
+static void __exit rda_uart_exit(void)
 {
 	platform_driver_unregister(&rda_uart_platform_driver);
 	uart_unregister_driver(&rda_uart_driver);
-- 
cgit v1.2.3


From 7e2a165de5a52003d10a611ee3884cdb5c44e8cd Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 10 Sep 2019 07:59:23 +0200
Subject: serial/sifive: select SERIAL_EARLYCON

The sifive serial driver implements earlycon support, but unless
another driver is built in that supports earlycon support it won't
be usable.  Explicitly select SERIAL_EARLYCON instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Paul Walmsley <paul.walmsley@sifive.com>
Link: https://lore.kernel.org/r/20190910055923.28384-1-hch@lst.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 4789b5d62f63..67a9eb3f94ce 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1032,6 +1032,7 @@ config SERIAL_SIFIVE_CONSOLE
 	bool "Console on SiFive UART"
 	depends on SERIAL_SIFIVE=y
 	select SERIAL_CORE_CONSOLE
+	select SERIAL_EARLYCON
 	help
 	  Select this option if you would like to use a SiFive UART as the
 	  system console.
-- 
cgit v1.2.3


From fc5f3782da3c73bbbe2293551219b2ded0660357 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das@bp.renesas.com>
Date: Tue, 17 Sep 2019 13:45:24 +0100
Subject: dt-bindings: serial: sh-sci: Document r8a774b1 bindings

RZ/G2N (R8A774B1) SoC also has the R-Car Gen3 compatible SCIF and
HSCIF ports, so document the SoC specific bindings.

Signed-off-by: Biju Das <biju.das@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://lore.kernel.org/r/1568724324-26995-1-git-send-email-biju.das@bp.renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/serial/renesas,sci-serial.txt | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
index dd63151dc8b6..b143d9a21b2d 100644
--- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
+++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt
@@ -26,6 +26,8 @@ Required properties:
     - "renesas,hscif-r8a77470" for R8A77470 (RZ/G1C) HSCIF compatible UART.
     - "renesas,scif-r8a774a1" for R8A774A1 (RZ/G2M) SCIF compatible UART.
     - "renesas,hscif-r8a774a1" for R8A774A1 (RZ/G2M) HSCIF compatible UART.
+    - "renesas,scif-r8a774b1" for R8A774B1 (RZ/G2N) SCIF compatible UART.
+    - "renesas,hscif-r8a774b1" for R8A774B1 (RZ/G2N) HSCIF compatible UART.
     - "renesas,scif-r8a774c0" for R8A774C0 (RZ/G2E) SCIF compatible UART.
     - "renesas,hscif-r8a774c0" for R8A774C0 (RZ/G2E) HSCIF compatible UART.
     - "renesas,scif-r8a7778" for R8A7778 (R-Car M1) SCIF compatible UART.
-- 
cgit v1.2.3


From 392fb8df528b97a06e19312772afd38aec542b96 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 1 Oct 2019 20:07:43 +0200
Subject: serial: sh-sci: Use platform_get_irq_optional() for optional
 interrupts

As platform_get_irq() now prints an error when the interrupt does not
exist, scary warnings may be printed for optional interrupts:

    sh-sci e6550000.serial: IRQ index 1 not found
    sh-sci e6550000.serial: IRQ index 2 not found
    sh-sci e6550000.serial: IRQ index 3 not found
    sh-sci e6550000.serial: IRQ index 4 not found
    sh-sci e6550000.serial: IRQ index 5 not found

Fix this by calling platform_get_irq_optional() instead for all but the
first interrupts, which are optional.

Fixes: 7723f4c5ecdb8d83 ("driver core: platform: Add an error message to platform_get_irq*()")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/20191001180743.1041-1-geert+renesas@glider.be
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sh-sci.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 4e754a4850e6..22e5d4e13714 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -2894,8 +2894,12 @@ static int sci_init_single(struct platform_device *dev,
 	port->mapbase = res->start;
 	sci_port->reg_size = resource_size(res);
 
-	for (i = 0; i < ARRAY_SIZE(sci_port->irqs); ++i)
-		sci_port->irqs[i] = platform_get_irq(dev, i);
+	for (i = 0; i < ARRAY_SIZE(sci_port->irqs); ++i) {
+		if (i)
+			sci_port->irqs[i] = platform_get_irq_optional(dev, i);
+		else
+			sci_port->irqs[i] = platform_get_irq(dev, i);
+	}
 
 	/* The SCI generates several interrupts. They can be muxed together or
 	 * connected to different interrupt lines. In the muxed case only one
-- 
cgit v1.2.3


From 9050079719021776e48437827eb9d5986b6e45d4 Mon Sep 17 00:00:00 2001
From: Stefan-gabriel Mirea <stefan-gabriel.mirea@nxp.com>
Date: Wed, 18 Sep 2019 18:45:49 +0000
Subject: tty: serial: linflexuart: Fix magic SysRq handling

Following an incorrect indentation reported to me by Dan Carpenter, I
noticed that the SysRq lines were inherited from the lpuart driver[1] (note
how the 'continue' is aligned to 'sport->port.sysrq = 0') and we have never
actually tested the SysRq support.

'sport->sysrq = 0' is not necessary neither before nor after 'continue',
because sysrq will already be 0 after uart_handle_sysrq_char() will finish.
Also, since the LINFlexD driver never called uart_handle_break(), sysrq
would have never been set to a nonzero value, so uart_handle_sysrq_char()
was not going to do anything.

Break conditions are detected based on a null data byte along with a
framing error (stop bit sampled to 0).

[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/tty/serial/fsl_lpuart.c?h=b3e3bf2ef2c74f5ce5c19510edbbb9bfc1d249c2#n659

Fixes: 09864c1cdf5c ("tty: serial: Add linflexuart driver for S32V234")
Signed-off-by: Stefan-Gabriel Mirea <stefan-gabriel.mirea@nxp.com>
Reported-by: kbuild test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Link: https://lore.kernel.org/r/20190918184439.7465-1-stefan-gabriel.mirea@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/fsl_linflexuart.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/tty/serial/fsl_linflexuart.c b/drivers/tty/serial/fsl_linflexuart.c
index 68d74f2b5106..a32f0d2afd59 100644
--- a/drivers/tty/serial/fsl_linflexuart.c
+++ b/drivers/tty/serial/fsl_linflexuart.c
@@ -3,7 +3,7 @@
  * Freescale linflexuart serial port driver
  *
  * Copyright 2012-2016 Freescale Semiconductor, Inc.
- * Copyright 2017-2018 NXP
+ * Copyright 2017-2019 NXP
  */
 
 #if defined(CONFIG_SERIAL_FSL_LINFLEXUART_CONSOLE) && \
@@ -246,12 +246,14 @@ static irqreturn_t linflex_rxint(int irq, void *dev_id)
 	struct tty_port *port = &sport->state->port;
 	unsigned long flags, status;
 	unsigned char rx;
+	bool brk;
 
 	spin_lock_irqsave(&sport->lock, flags);
 
 	status = readl(sport->membase + UARTSR);
 	while (status & LINFLEXD_UARTSR_RMB) {
 		rx = readb(sport->membase + BDRM);
+		brk = false;
 		flg = TTY_NORMAL;
 		sport->icount.rx++;
 
@@ -261,8 +263,11 @@ static irqreturn_t linflex_rxint(int irq, void *dev_id)
 				status |= LINFLEXD_UARTSR_SZF;
 			if (status & LINFLEXD_UARTSR_BOF)
 				status |= LINFLEXD_UARTSR_BOF;
-			if (status & LINFLEXD_UARTSR_FEF)
+			if (status & LINFLEXD_UARTSR_FEF) {
+				if (!rx)
+					brk = true;
 				status |= LINFLEXD_UARTSR_FEF;
+			}
 			if (status & LINFLEXD_UARTSR_PE)
 				status |=  LINFLEXD_UARTSR_PE;
 		}
@@ -271,13 +276,15 @@ static irqreturn_t linflex_rxint(int irq, void *dev_id)
 		       sport->membase + UARTSR);
 		status = readl(sport->membase + UARTSR);
 
-		if (uart_handle_sysrq_char(sport, (unsigned char)rx))
-			continue;
-
+		if (brk) {
+			uart_handle_break(sport);
+		} else {
 #ifdef SUPPORT_SYSRQ
-			sport->sysrq = 0;
+			if (uart_handle_sysrq_char(sport, (unsigned char)rx))
+				continue;
 #endif
-		tty_insert_flip_char(port, rx, flg);
+			tty_insert_flip_char(port, rx, flg);
+		}
 	}
 
 	spin_unlock_irqrestore(&sport->lock, flags);
-- 
cgit v1.2.3


From a553add0846f355a28ed4e81134012e4a1e280c2 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 16 Sep 2019 16:12:23 -0700
Subject: serial: uartlite: fix exit path null pointer

Call uart_unregister_driver() conditionally instead of
unconditionally, only if it has been previously registered.

This uses driver.state, just as the sh-sci.c driver does.

Fixes this null pointer dereference in tty_unregister_driver(),
since the 'driver' argument is null:

  general protection fault: 0000 [#1] PREEMPT SMP KASAN PTI
  RIP: 0010:tty_unregister_driver+0x25/0x1d0

Fixes: 238b8721a554 ("[PATCH] serial uartlite driver")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: stable <stable@vger.kernel.org>
Cc: Peter Korsgaard <jacmet@sunsite.dk>
Link: https://lore.kernel.org/r/9c8e6581-6fcc-a595-0897-4d90f5d710df@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/uartlite.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/tty/serial/uartlite.c b/drivers/tty/serial/uartlite.c
index b8b912b5a8b9..06e79c11141d 100644
--- a/drivers/tty/serial/uartlite.c
+++ b/drivers/tty/serial/uartlite.c
@@ -897,7 +897,8 @@ static int __init ulite_init(void)
 static void __exit ulite_exit(void)
 {
 	platform_driver_unregister(&ulite_platform_driver);
-	uart_unregister_driver(&ulite_uart_driver);
+	if (ulite_uart_driver.state)
+		uart_unregister_driver(&ulite_uart_driver);
 }
 
 module_init(ulite_init);
-- 
cgit v1.2.3


From 5e9bd2d70ae7c00a95a22994abf1eef728649e64 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@xilinx.com>
Date: Fri, 4 Oct 2019 15:04:11 +0200
Subject: serial: uartps: Fix uartps_major handling

There are two parts which should be fixed. The first one is to assigned
uartps_major at the end of probe() to avoid complicated logic when
something fails.
The second part is initialized uartps_major number to 0 when last device is
removed. This will ensure that on next probe driver will ask for new
dynamic major number.

Fixes: ab262666018d ("serial: uartps: Use the same dynamic major number for all ports")
Reported-by: Paul Thomas <pthomas8589@gmail.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Link: https://lore.kernel.org/r/d2652cda992833315c4f96f06953eb547f928918.1570194248.git.michal.simek@xilinx.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/xilinx_uartps.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c
index da4563aaaf5c..4e55bc327a54 100644
--- a/drivers/tty/serial/xilinx_uartps.c
+++ b/drivers/tty/serial/xilinx_uartps.c
@@ -1550,7 +1550,6 @@ static int cdns_uart_probe(struct platform_device *pdev)
 		goto err_out_id;
 	}
 
-	uartps_major = cdns_uart_uart_driver->tty_driver->major;
 	cdns_uart_data->cdns_uart_driver = cdns_uart_uart_driver;
 
 	/*
@@ -1680,6 +1679,7 @@ static int cdns_uart_probe(struct platform_device *pdev)
 		console_port = NULL;
 #endif
 
+	uartps_major = cdns_uart_uart_driver->tty_driver->major;
 	cdns_uart_data->cts_override = of_property_read_bool(pdev->dev.of_node,
 							     "cts-override");
 	return 0;
@@ -1741,6 +1741,12 @@ static int cdns_uart_remove(struct platform_device *pdev)
 		console_port = NULL;
 #endif
 
+	/* If this is last instance major number should be initialized */
+	mutex_lock(&bitmap_lock);
+	if (bitmap_empty(bitmap, MAX_UART_INSTANCES))
+		uartps_major = 0;
+	mutex_unlock(&bitmap_lock);
+
 	uart_unregister_driver(cdns_uart_data->cdns_uart_driver);
 	return rc;
 }
-- 
cgit v1.2.3


From 47a7e5e97d4edd7b14974d34f0e5a5560fad2915 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 30 Sep 2019 19:15:12 -0700
Subject: tty: n_hdlc: fix build on SPARC

Fix tty driver build on SPARC by not using __exitdata.
It appears that SPARC does not support section .exit.data.

Fixes these build errors:

`.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
`.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
`.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o
`.exit.data' referenced in section `.exit.text' of drivers/tty/n_hdlc.o: defined in discarded section `.exit.data' of drivers/tty/n_hdlc.o

Reported-by: kbuild test robot <lkp@intel.com>
Fixes: 063246641d4a ("format-security: move static strings to const")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: https://lore.kernel.org/r/675e7bd9-955b-3ff3-1101-a973b58b5b75@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/n_hdlc.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index e55c79eb6430..98361acd3053 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -968,6 +968,11 @@ static int __init n_hdlc_init(void)
 	
 }	/* end of init_module() */
 
+#ifdef CONFIG_SPARC
+#undef __exitdata
+#define __exitdata
+#endif
+
 static const char hdlc_unregister_ok[] __exitdata =
 	KERN_INFO "N_HDLC: line discipline unregistered\n";
 static const char hdlc_unregister_fail[] __exitdata =
-- 
cgit v1.2.3


From 4d86dfd38285c83a6df01093b8547f742e3b2470 Mon Sep 17 00:00:00 2001
From: Tomas Winkler <tomas.winkler@intel.com>
Date: Wed, 2 Oct 2019 02:59:57 +0300
Subject: mei: me: add comet point (lake) LP device ids

Add Comet Point devices IDs for Comet Lake U platforms.

Cc: <stable@vger.kernel.org>
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Link: https://lore.kernel.org/r/20191001235958.19979-1-tomas.winkler@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/hw-me-regs.h | 3 +++
 drivers/misc/mei/pci-me.c     | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index 77f7dff7098d..c09f8bb49495 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -79,6 +79,9 @@
 #define MEI_DEV_ID_CNP_H      0xA360  /* Cannon Point H */
 #define MEI_DEV_ID_CNP_H_4    0xA364  /* Cannon Point H 4 (iTouch) */
 
+#define MEI_DEV_ID_CMP_LP     0x02e0  /* Comet Point LP */
+#define MEI_DEV_ID_CMP_LP_3   0x02e4  /* Comet Point LP 3 (iTouch) */
+
 #define MEI_DEV_ID_ICP_LP     0x34E0  /* Ice Lake Point LP */
 
 #define MEI_DEV_ID_TGP_LP     0xA0E0  /* Tiger Lake Point LP */
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index d5a92c6eadb3..775a2090c2ac 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -96,6 +96,9 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 	{MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H, MEI_ME_PCH12_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H_4, MEI_ME_PCH8_CFG)},
 
+	{MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP, MEI_ME_PCH12_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_CMP_LP_3, MEI_ME_PCH8_CFG)},
+
 	{MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)},
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_TGP_LP, MEI_ME_PCH12_CFG)},
-- 
cgit v1.2.3


From 261ea7e29ed1e6a172d4ba829f4d5e3706ab29e4 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 11:59:58 +0100
Subject: drm/i915: Restrict L3 remapping sysfs interface to dwords

The L3 cache remapping is stored as u32 elements, and we should ensure
that the user only supplies complete slice information(u32).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004105958.1741-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_sysfs.c | 57 ++++++++++++++++++++-------------------
 1 file changed, 29 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 034b8abc5062..1e08c5961535 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -144,12 +144,12 @@ static const struct attribute_group media_rc6_attr_group = {
 };
 #endif
 
-static int l3_access_valid(struct drm_i915_private *dev_priv, loff_t offset)
+static int l3_access_valid(struct drm_i915_private *i915, loff_t offset)
 {
-	if (!HAS_L3_DPF(dev_priv))
+	if (!HAS_L3_DPF(i915))
 		return -EPERM;
 
-	if (offset % 4 != 0)
+	if (!IS_ALIGNED(offset, sizeof(u32)))
 		return -EINVAL;
 
 	if (offset >= GEN7_L3LOG_SIZE)
@@ -164,31 +164,28 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	     loff_t offset, size_t count)
 {
 	struct device *kdev = kobj_to_dev(kobj);
-	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct drm_device *dev = &dev_priv->drm;
+	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
 	int slice = (int)(uintptr_t)attr->private;
 	int ret;
 
-	count = round_down(count, 4);
-
-	ret = l3_access_valid(dev_priv, offset);
+	ret = l3_access_valid(i915, offset);
 	if (ret)
 		return ret;
 
+	count = round_down(count, sizeof(u32));
 	count = min_t(size_t, GEN7_L3LOG_SIZE - offset, count);
+	memset(buf, 0, count);
 
-	ret = i915_mutex_lock_interruptible(dev);
+	ret = i915_mutex_lock_interruptible(&i915->drm);
 	if (ret)
 		return ret;
 
-	if (dev_priv->l3_parity.remap_info[slice])
+	if (i915->l3_parity.remap_info[slice])
 		memcpy(buf,
-		       dev_priv->l3_parity.remap_info[slice] + (offset/4),
+		       i915->l3_parity.remap_info[slice] + offset / sizeof(u32),
 		       count);
-	else
-		memset(buf, 0, count);
 
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&i915->drm.struct_mutex);
 
 	return count;
 }
@@ -199,22 +196,24 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	      loff_t offset, size_t count)
 {
 	struct device *kdev = kobj_to_dev(kobj);
-	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct drm_device *dev = &dev_priv->drm;
-	struct i915_gem_context *ctx;
+	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
 	int slice = (int)(uintptr_t)attr->private;
+	struct i915_gem_context *ctx;
 	u32 **remap_info;
 	int ret;
 
-	ret = l3_access_valid(dev_priv, offset);
+	ret = l3_access_valid(i915, offset);
 	if (ret)
 		return ret;
 
-	ret = i915_mutex_lock_interruptible(dev);
+	if (count < sizeof(u32))
+		return -EINVAL;
+
+	ret = i915_mutex_lock_interruptible(&i915->drm);
 	if (ret)
 		return ret;
 
-	remap_info = &dev_priv->l3_parity.remap_info[slice];
+	remap_info = &i915->l3_parity.remap_info[slice];
 	if (!*remap_info) {
 		*remap_info = kzalloc(GEN7_L3LOG_SIZE, GFP_KERNEL);
 		if (!*remap_info) {
@@ -223,20 +222,22 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 		}
 	}
 
-	/* TODO: Ideally we really want a GPU reset here to make sure errors
+	count = round_down(count, sizeof(u32));
+	memcpy(*remap_info + offset / sizeof(u32), buf, count);
+
+	/* NB: We defer the remapping until we switch to the context */
+	list_for_each_entry(ctx, &i915->contexts.list, link)
+		ctx->remap_slice |= BIT(slice);
+
+	/*
+	 * TODO: Ideally we really want a GPU reset here to make sure errors
 	 * aren't propagated. Since I cannot find a stable way to reset the GPU
 	 * at this point it is left as a TODO.
 	*/
-	memcpy(*remap_info + (offset/4), buf, count);
-
-	/* NB: We defer the remapping until we switch to the context */
-	list_for_each_entry(ctx, &dev_priv->contexts.list, link)
-		ctx->remap_slice |= (1<<slice);
 
 	ret = count;
-
 out:
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&i915->drm.struct_mutex);
 
 	return ret;
 }
-- 
cgit v1.2.3


From 47934ef7f1883209120781b59d78eaf8b83e2fb7 Mon Sep 17 00:00:00 2001
From: Stefan-gabriel Mirea <stefan-gabriel.mirea@nxp.com>
Date: Fri, 4 Oct 2019 13:51:13 +0000
Subject: tty: serial: Fix PORT_LINFLEXUART definition

The port type macros should have different values for different devices.
Currently, PORT_LINFLEXUART conflicts with PORT_SUNIX.

Fixes: 09864c1cdf5c ("tty: serial: Add linflexuart driver for S32V234")
Signed-off-by: Stefan-Gabriel Mirea <stefan-gabriel.mirea@nxp.com>
Link: https://lore.kernel.org/r/20191004135058.18007-1-stefan-gabriel.mirea@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/uapi/linux/serial_core.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h
index 0f4f87a6fd54..e7fe550b6038 100644
--- a/include/uapi/linux/serial_core.h
+++ b/include/uapi/linux/serial_core.h
@@ -291,6 +291,6 @@
 #define PORT_SUNIX	121
 
 /* Freescale Linflex UART */
-#define PORT_LINFLEXUART	121
+#define PORT_LINFLEXUART	122
 
 #endif /* _UAPILINUX_SERIAL_CORE_H */
-- 
cgit v1.2.3


From bf7ec93c644cb0064ba7d2fc40d4841c5ba382ab Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Fri, 4 Oct 2019 17:01:08 +0300
Subject: io_uring: fix reversed nonblock flag for link submission

io_queue_link_head() accepts @force_nonblock flag, but io_ring_submit()
passes something opposite.

Fixes: c576666863b78 ("io_uring: optimize submit_and_wait API")
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 0bc167aca46d..ab8c4e5e442c 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2761,7 +2761,7 @@ out:
 
 	if (link)
 		io_queue_link_head(ctx, link, &link->submit, shadow_req,
-					block_for_last);
+					!block_for_last);
 	if (statep)
 		io_submit_state_end(statep);
 
-- 
cgit v1.2.3


From b290a78b5c3d78c337b8d9856cc0671aea0c2ef3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 3 Oct 2019 22:00:58 +0100
Subject: drm/i915: Use helpers for drm_mm_node booleans

A subset of 71724f708997 ("drm/mm: Use helpers for drm_mm_node booleans")
in order to prepare drm-intel-next-queued for subsequent patches before
we can backmerge 71724f708997 itself.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004142226.13711-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c |  4 ++--
 drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c       |  2 +-
 drivers/gpu/drm/i915/i915_gem.c                | 12 ++++++------
 drivers/gpu/drm/i915/i915_gem_evict.c          |  2 +-
 drivers/gpu/drm/i915/i915_vma.c                |  2 +-
 drivers/gpu/drm/i915/i915_vma.h                |  4 ++--
 6 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 8fbb454cfd6b..228ce24ea280 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -968,7 +968,7 @@ static void reloc_cache_reset(struct reloc_cache *cache)
 		intel_gt_flush_ggtt_writes(ggtt->vm.gt);
 		io_mapping_unmap_atomic((void __iomem *)vaddr);
 
-		if (cache->node.allocated) {
+		if (drm_mm_node_allocated(&cache->node)) {
 			ggtt->vm.clear_range(&ggtt->vm,
 					     cache->node.start,
 					     cache->node.size);
@@ -1061,7 +1061,7 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj,
 	}
 
 	offset = cache->node.start;
-	if (cache->node.allocated) {
+	if (drm_mm_node_allocated(&cache->node)) {
 		ggtt->vm.insert_page(&ggtt->vm,
 				     i915_gem_object_get_dma_address(obj, page),
 				     offset, I915_CACHE_NONE, 0);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index bb878119f06c..bb4889d2346d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -387,7 +387,7 @@ static u32 uc_fw_ggtt_offset(struct intel_uc_fw *uc_fw, struct i915_ggtt *ggtt)
 {
 	struct drm_mm_node *node = &ggtt->uc_fw;
 
-	GEM_BUG_ON(!node->allocated);
+	GEM_BUG_ON(!drm_mm_node_allocated(node));
 	GEM_BUG_ON(upper_32_bits(node->start));
 	GEM_BUG_ON(upper_32_bits(node->start + node->size - 1));
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1426e506700d..fa8e028ac0b5 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -356,7 +356,7 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 		ret = insert_mappable_node(ggtt, &node, PAGE_SIZE);
 		if (ret)
 			goto out_unlock;
-		GEM_BUG_ON(!node.allocated);
+		GEM_BUG_ON(!drm_mm_node_allocated(&node));
 	}
 
 	mutex_unlock(&i915->drm.struct_mutex);
@@ -393,7 +393,7 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 		unsigned page_offset = offset_in_page(offset);
 		unsigned page_length = PAGE_SIZE - page_offset;
 		page_length = remain < page_length ? remain : page_length;
-		if (node.allocated) {
+		if (drm_mm_node_allocated(&node)) {
 			ggtt->vm.insert_page(&ggtt->vm,
 					     i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
 					     node.start, I915_CACHE_NONE, 0);
@@ -415,7 +415,7 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 	i915_gem_object_unlock_fence(obj, fence);
 out_unpin:
 	mutex_lock(&i915->drm.struct_mutex);
-	if (node.allocated) {
+	if (drm_mm_node_allocated(&node)) {
 		ggtt->vm.clear_range(&ggtt->vm, node.start, node.size);
 		remove_mappable_node(&node);
 	} else {
@@ -566,7 +566,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		ret = insert_mappable_node(ggtt, &node, PAGE_SIZE);
 		if (ret)
 			goto out_rpm;
-		GEM_BUG_ON(!node.allocated);
+		GEM_BUG_ON(!drm_mm_node_allocated(&node));
 	}
 
 	mutex_unlock(&i915->drm.struct_mutex);
@@ -604,7 +604,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		unsigned int page_offset = offset_in_page(offset);
 		unsigned int page_length = PAGE_SIZE - page_offset;
 		page_length = remain < page_length ? remain : page_length;
-		if (node.allocated) {
+		if (drm_mm_node_allocated(&node)) {
 			/* flush the write before we modify the GGTT */
 			intel_gt_flush_ggtt_writes(ggtt->vm.gt);
 			ggtt->vm.insert_page(&ggtt->vm,
@@ -636,7 +636,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 out_unpin:
 	mutex_lock(&i915->drm.struct_mutex);
 	intel_gt_flush_ggtt_writes(ggtt->vm.gt);
-	if (node.allocated) {
+	if (drm_mm_node_allocated(&node)) {
 		ggtt->vm.clear_range(&ggtt->vm, node.start, node.size);
 		remove_mappable_node(&node);
 	} else {
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index e76c9da9992d..8c1e04f402bc 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -299,7 +299,7 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 			break;
 		}
 
-		GEM_BUG_ON(!node->allocated);
+		GEM_BUG_ON(!drm_mm_node_allocated(node));
 		vma = container_of(node, typeof(*vma), node);
 
 		/* If we are using coloring to insert guard pages between
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 9d5b0f87c210..68c34b1a20e4 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -795,7 +795,7 @@ void i915_vma_reopen(struct i915_vma *vma)
 
 static void __i915_vma_destroy(struct i915_vma *vma)
 {
-	GEM_BUG_ON(vma->node.allocated);
+	GEM_BUG_ON(drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(vma->fence);
 
 	mutex_lock(&vma->vm->mutex);
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 8bcb5812c446..e49b199f7de7 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -228,7 +228,7 @@ static inline bool i915_vma_is_closed(const struct i915_vma *vma)
 static inline u32 i915_ggtt_offset(const struct i915_vma *vma)
 {
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
-	GEM_BUG_ON(!vma->node.allocated);
+	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(upper_32_bits(vma->node.start));
 	GEM_BUG_ON(upper_32_bits(vma->node.start + vma->node.size - 1));
 	return lower_32_bits(vma->node.start);
@@ -390,7 +390,7 @@ static inline bool i915_vma_is_bound(const struct i915_vma *vma,
 static inline bool i915_node_color_differs(const struct drm_mm_node *node,
 					   unsigned long color)
 {
-	return node->allocated && node->color != color;
+	return drm_mm_node_allocated(node) && node->color != color;
 }
 
 /**
-- 
cgit v1.2.3


From 5c8e10f8326294b0f860da6e7266174f28fc1341 Mon Sep 17 00:00:00 2001
From: Jiri Kosina <jkosina@suse.cz>
Date: Tue, 1 Oct 2019 22:08:01 +0200
Subject: s390: mark __cpacf_query() as __always_inline

arch/s390/kvm/kvm-s390.c calls on several places __cpacf_query() directly,
which makes it impossible to meet the "i" constraint for the asm operands
(opcode in this case).

As we are now force-enabling CONFIG_OPTIMIZE_INLINING on all
architectures, this causes a build failure on s390:

   In file included from arch/s390/kvm/kvm-s390.c:44:
   ./arch/s390/include/asm/cpacf.h: In function '__cpacf_query':
   ./arch/s390/include/asm/cpacf.h:179:2: warning: asm operand 3 probably doesn't match constraints
     179 |  asm volatile(
         |  ^~~
   ./arch/s390/include/asm/cpacf.h:179:2: error: impossible constraint in 'asm'

Mark __cpacf_query() as __always_inline in order to fix that, analogically
how we fixes __cpacf_check_opcode(), cpacf_query_func() and scpacf_query()
already.

Reported-and-tested-by: Michal Kubecek <mkubecek@suse.cz>
Fixes: d83623c5eab2 ("s390: mark __cpacf_check_opcode() and cpacf_query_func() as __always_inline")
Fixes: e60fb8bf68d4 ("s390/cpacf: mark scpacf_query() as __always_inline")
Fixes: ac7c3e4ff401 ("compiler: enable CONFIG_OPTIMIZE_INLINING forcibly")
Fixes: 9012d011660e ("compiler: allow all arches to enable CONFIG_OPTIMIZE_INLINING")
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Link: https://lore.kernel.org/lkml/nycvar.YFH.7.76.1910012203010.13160@cbobk.fhfr.pm
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/cpacf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h
index a092f63aac6a..c0f3bfeddcbe 100644
--- a/arch/s390/include/asm/cpacf.h
+++ b/arch/s390/include/asm/cpacf.h
@@ -171,7 +171,7 @@ typedef struct { unsigned char bytes[16]; } cpacf_mask_t;
  *
  * Returns 1 if @func is available for @opcode, 0 otherwise
  */
-static inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
+static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
 {
 	register unsigned long r0 asm("0") = 0;	/* query function */
 	register unsigned long r1 asm("1") = (unsigned long) mask;
-- 
cgit v1.2.3


From 51ce02216d4ad4e8f6a58de81d6e803cf04c418e Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Thu, 3 Oct 2019 17:36:36 -0400
Subject: s390/mm: fix -Wunused-but-set-variable warnings

Convert two functions to static inline to get ride of W=1 GCC warnings
like,

mm/gup.c: In function 'gup_pte_range':
mm/gup.c:1816:16: warning: variable 'ptem' set but not used
[-Wunused-but-set-variable]
  pte_t *ptep, *ptem;
                ^~~~

mm/mmap.c: In function 'acct_stack_growth':
mm/mmap.c:2322:16: warning: variable 'new_start' set but not used
[-Wunused-but-set-variable]
  unsigned long new_start;
                ^~~~~~~~~

Signed-off-by: Qian Cai <cai@lca.pw>
Link: https://lore.kernel.org/lkml/1570138596-11913-1-git-send-email-cai@lca.pw/
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/hugetlb.h | 9 +++++++--
 arch/s390/include/asm/pgtable.h | 3 ++-
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index bb59dd964590..de8f0bf5f238 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -12,8 +12,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
-
-#define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range			free_pgd_range
 #define hugepages_supported()			(MACHINE_HAS_EDAT1)
 
@@ -23,6 +21,13 @@ pte_t huge_ptep_get(pte_t *ptep);
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep);
 
+static inline bool is_hugepage_only_range(struct mm_struct *mm,
+					  unsigned long addr,
+					  unsigned long len)
+{
+	return false;
+}
+
 /*
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 36c578c0ff96..19c2cf001df3 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1269,7 +1269,8 @@ static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address)
 
 #define pte_offset_kernel(pmd, address) pte_offset(pmd, address)
 #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
-#define pte_unmap(pte) do { } while (0)
+
+static inline void pte_unmap(pte_t *pte) { }
 
 static inline bool gup_fast_permitted(unsigned long start, unsigned long end)
 {
-- 
cgit v1.2.3


From b4fd5a0a9295d87da629c72378a7f4967a277030 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Fri, 4 Oct 2019 12:28:43 +0200
Subject: s390/atomic,bitops: mark function(s) __always_inline

Always inline asm inlines with variable operands for "i" constraints,
since they won't compile if the compiler would decide to not inline
them.

Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/atomic_ops.h | 2 +-
 arch/s390/include/asm/bitops.h     | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
index d3f09526ee19..61467b9eecc7 100644
--- a/arch/s390/include/asm/atomic_ops.h
+++ b/arch/s390/include/asm/atomic_ops.h
@@ -41,7 +41,7 @@ __ATOMIC_OPS(__atomic64_xor, long, "laxg")
 #undef __ATOMIC_OP
 
 #define __ATOMIC_CONST_OP(op_name, op_type, op_string, op_barrier)	\
-static inline void op_name(op_type val, op_type *ptr)			\
+static __always_inline void op_name(op_type val, op_type *ptr)		\
 {									\
 	asm volatile(							\
 		op_string "	%[ptr],%[val]\n"			\
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index b8833ac983fa..eb7eed43e780 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -56,7 +56,7 @@ __bitops_byte(unsigned long nr, volatile unsigned long *ptr)
 	return ((unsigned char *)ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
 }
 
-static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr)
+static __always_inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr)
 {
 	unsigned long *addr = __bitops_word(nr, ptr);
 	unsigned long mask;
@@ -77,7 +77,7 @@ static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr)
 	__atomic64_or(mask, (long *)addr);
 }
 
-static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr)
+static __always_inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr)
 {
 	unsigned long *addr = __bitops_word(nr, ptr);
 	unsigned long mask;
@@ -98,8 +98,8 @@ static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr)
 	__atomic64_and(mask, (long *)addr);
 }
 
-static inline void arch_change_bit(unsigned long nr,
-				   volatile unsigned long *ptr)
+static __always_inline void arch_change_bit(unsigned long nr,
+					    volatile unsigned long *ptr)
 {
 	unsigned long *addr = __bitops_word(nr, ptr);
 	unsigned long mask;
-- 
cgit v1.2.3


From 44967bfb552090981751074aeb4ad372f5979902 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Fri, 4 Oct 2019 12:29:00 +0200
Subject: s390/cpu_mf: mark function(s) __always_inline

Always inline asm inlines with variable operands for "i" constraints,
since they won't compile if the compiler would decide to not inline
them.

Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/cpu_mf.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index 753669bfbe99..819803a97c2b 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -223,7 +223,8 @@ enum stcctm_ctr_set {
 	MT_DIAG = 5,
 	MT_DIAG_CLEARING = 9,	/* clears loss-of-MT-ctr-data alert */
 };
-static inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest)
+
+static __always_inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest)
 {
 	int cc;
 
-- 
cgit v1.2.3


From 7f032febb665f6c1fe95068be14aa891a4dfb8fc Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Fri, 4 Oct 2019 12:29:18 +0200
Subject: s390/jump_label: mark function(s) __always_inline

Always inline asm inlines with variable operands for "i" constraints,
since they won't compile if the compiler would decide to not inline
them.

Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/jump_label.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index e548ec1ec12c..39f747d63758 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -20,7 +20,7 @@
  * We use a brcl 0,2 instruction for jump labels at compile time so it
  * can be easily distinguished from a hotpatch generated instruction.
  */
-static inline bool arch_static_branch(struct static_key *key, bool branch)
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("0:	brcl	0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n"
 			  ".pushsection __jump_table,\"aw\"\n"
@@ -34,7 +34,7 @@ label:
 	return true;
 }
 
-static inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("0:	brcl 15,%l[label]\n"
 			  ".pushsection __jump_table,\"aw\"\n"
-- 
cgit v1.2.3


From 6818b542a084689366a2b6211f79d9122aea4ac6 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Fri, 4 Oct 2019 12:29:37 +0200
Subject: s390/mm: mark function(s) __always_inline

Always inline asm inlines with variable operands for "i" constraints,
since they won't compile if the compiler would decide to not inline
them.

Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/pgtable.h | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 19c2cf001df3..5ff98d76a66c 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -997,9 +997,9 @@ static inline pte_t pte_mkhuge(pte_t pte)
 #define IPTE_NODAT	0x400
 #define IPTE_GUEST_ASCE	0x800
 
-static inline void __ptep_ipte(unsigned long address, pte_t *ptep,
-			       unsigned long opt, unsigned long asce,
-			       int local)
+static __always_inline void __ptep_ipte(unsigned long address, pte_t *ptep,
+					unsigned long opt, unsigned long asce,
+					int local)
 {
 	unsigned long pto = (unsigned long) ptep;
 
@@ -1020,8 +1020,8 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep,
 		: [r1] "a" (pto), [m4] "i" (local) : "memory");
 }
 
-static inline void __ptep_ipte_range(unsigned long address, int nr,
-				     pte_t *ptep, int local)
+static __always_inline void __ptep_ipte_range(unsigned long address, int nr,
+					      pte_t *ptep, int local)
 {
 	unsigned long pto = (unsigned long) ptep;
 
@@ -1436,9 +1436,9 @@ static inline void __pmdp_csp(pmd_t *pmdp)
 #define IDTE_NODAT	0x1000
 #define IDTE_GUEST_ASCE	0x2000
 
-static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp,
-			       unsigned long opt, unsigned long asce,
-			       int local)
+static __always_inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp,
+					unsigned long opt, unsigned long asce,
+					int local)
 {
 	unsigned long sto;
 
@@ -1462,9 +1462,9 @@ static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp,
 	}
 }
 
-static inline void __pudp_idte(unsigned long addr, pud_t *pudp,
-			       unsigned long opt, unsigned long asce,
-			       int local)
+static __always_inline void __pudp_idte(unsigned long addr, pud_t *pudp,
+					unsigned long opt, unsigned long asce,
+					int local)
 {
 	unsigned long r3o;
 
-- 
cgit v1.2.3


From 771c24f6da06042e8aa8303e37c069fa01f96a09 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Fri, 4 Oct 2019 12:29:43 +0200
Subject: s390/pci: mark function(s) __always_inline

Always inline asm inlines with variable operands for "i" constraints,
since they won't compile if the compiler would decide to not inline
them.

Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/pci/pci_clp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 9bdff4defef1..e585a62d6530 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -66,7 +66,7 @@ static inline int clp_get_ilp(unsigned long *ilp)
 /*
  * Call Logical Processor with c=0, the give constant lps and an lpcb request.
  */
-static inline int clp_req(void *data, unsigned int lps)
+static __always_inline int clp_req(void *data, unsigned int lps)
 {
 	struct { u8 _[CLP_BLK_SIZE]; } *req = data;
 	u64 ignored;
-- 
cgit v1.2.3


From 61c313471574de93c63868689d42cd9fff297a1a Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Fri, 4 Oct 2019 15:05:03 +0200
Subject: s390: update defconfigs

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/configs/debug_defconfig    | 24 ++++++++++++++++--------
 arch/s390/configs/defconfig          | 25 ++++++++++++++++---------
 arch/s390/configs/zfcpdump_defconfig |  2 +-
 3 files changed, 33 insertions(+), 18 deletions(-)

diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 347f48702edb..38d64030aacf 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -44,6 +44,7 @@ CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_SIG=y
 CONFIG_EXPOLINE=y
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_CHSC_SCH=y
@@ -69,12 +70,13 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_MODULE_SIG=y
 CONFIG_MODULE_SIG_SHA256=y
+CONFIG_UNUSED_SYMBOLS=y
 CONFIG_BLK_DEV_INTEGRITY=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
+CONFIG_BLK_CGROUP_IOCOST=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_BSD_DISKLABEL=y
@@ -370,6 +372,7 @@ CONFIG_NETLINK_DIAG=m
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
+# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_PCI=y
 CONFIG_PCI_DEBUG=y
 CONFIG_HOTPLUG_PCI=y
@@ -424,6 +427,7 @@ CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_LOG_USERSPACE=m
 CONFIG_DM_RAID=m
@@ -435,6 +439,7 @@ CONFIG_DM_DELAY=m
 CONFIG_DM_UEVENT=y
 CONFIG_DM_FLAKEY=m
 CONFIG_DM_VERITY=m
+CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
 CONFIG_DM_SWITCH=m
 CONFIG_NETDEVICES=y
 CONFIG_BONDING=m
@@ -489,6 +494,7 @@ CONFIG_MLX5_CORE_EN=y
 # CONFIG_NET_VENDOR_NVIDIA is not set
 # CONFIG_NET_VENDOR_OKI is not set
 # CONFIG_NET_VENDOR_PACKET_ENGINES is not set
+# CONFIG_NET_VENDOR_PENSANDO is not set
 # CONFIG_NET_VENDOR_QLOGIC is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RDC is not set
@@ -538,15 +544,16 @@ CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
 CONFIG_DIAG288_WATCHDOG=m
-CONFIG_DRM=y
-CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_MLX4_INFINIBAND=m
 CONFIG_MLX5_INFINIBAND=m
+CONFIG_SYNC_FILE=y
 CONFIG_VFIO=m
 CONFIG_VFIO_PCI=m
 CONFIG_VFIO_MDEV=m
@@ -580,6 +587,8 @@ CONFIG_NILFS2_FS=m
 CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
+CONFIG_FS_VERITY=y
+CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
@@ -589,6 +598,7 @@ CONFIG_QFMT_V2=m
 CONFIG_AUTOFS4_FS=m
 CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
+CONFIG_VIRTIO_FS=m
 CONFIG_OVERLAY_FS=m
 CONFIG_FSCACHE=m
 CONFIG_CACHEFILES=m
@@ -648,12 +658,15 @@ CONFIG_FORTIFY_SOURCE=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_LOCKDOWN_LSM=y
+CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
 CONFIG_INTEGRITY_SIGNATURE=y
 CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
 CONFIG_IMA=y
 CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
+CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
 CONFIG_CRYPTO_USER=m
 # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
 CONFIG_CRYPTO_PCRYPT=m
@@ -664,10 +677,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -739,7 +748,6 @@ CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_INFO_DWARF4=y
 CONFIG_GDB_SCRIPTS=y
 CONFIG_FRAME_WARN=1024
-CONFIG_UNUSED_SYMBOLS=y
 CONFIG_HEADERS_INSTALL=y
 CONFIG_HEADERS_CHECK=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 8514b8b9500f..25f799849582 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -44,6 +44,7 @@ CONFIG_NUMA=y
 # CONFIG_NUMA_EMU is not set
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_SIG=y
 CONFIG_EXPOLINE=y
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_CHSC_SCH=y
@@ -66,11 +67,12 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_MODULE_SIG=y
 CONFIG_MODULE_SIG_SHA256=y
+CONFIG_UNUSED_SYMBOLS=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
+CONFIG_BLK_CGROUP_IOCOST=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_BSD_DISKLABEL=y
@@ -363,6 +365,7 @@ CONFIG_NETLINK_DIAG=m
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
+# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_PCI=y
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
@@ -418,6 +421,7 @@ CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_LOG_USERSPACE=m
 CONFIG_DM_RAID=m
@@ -429,6 +433,7 @@ CONFIG_DM_DELAY=m
 CONFIG_DM_UEVENT=y
 CONFIG_DM_FLAKEY=m
 CONFIG_DM_VERITY=m
+CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
 CONFIG_DM_SWITCH=m
 CONFIG_DM_INTEGRITY=m
 CONFIG_NETDEVICES=y
@@ -484,6 +489,7 @@ CONFIG_MLX5_CORE_EN=y
 # CONFIG_NET_VENDOR_NVIDIA is not set
 # CONFIG_NET_VENDOR_OKI is not set
 # CONFIG_NET_VENDOR_PACKET_ENGINES is not set
+# CONFIG_NET_VENDOR_PENSANDO is not set
 # CONFIG_NET_VENDOR_QLOGIC is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RDC is not set
@@ -533,16 +539,16 @@ CONFIG_WATCHDOG_CORE=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
 CONFIG_DIAG288_WATCHDOG=m
-CONFIG_DRM=y
-CONFIG_DRM_VIRTIO_GPU=y
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
+CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_MLX4_INFINIBAND=m
 CONFIG_MLX5_INFINIBAND=m
+CONFIG_SYNC_FILE=y
 CONFIG_VFIO=m
 CONFIG_VFIO_PCI=m
 CONFIG_VFIO_MDEV=m
@@ -573,6 +579,8 @@ CONFIG_NILFS2_FS=m
 CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
+CONFIG_FS_VERITY=y
+CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
@@ -581,6 +589,7 @@ CONFIG_QFMT_V2=m
 CONFIG_AUTOFS4_FS=m
 CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
+CONFIG_VIRTIO_FS=m
 CONFIG_OVERLAY_FS=m
 CONFIG_FSCACHE=m
 CONFIG_CACHEFILES=m
@@ -639,12 +648,15 @@ CONFIG_SECURITY_NETWORK=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_LOCKDOWN_LSM=y
+CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
 CONFIG_INTEGRITY_SIGNATURE=y
 CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
 CONFIG_IMA=y
 CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
+CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
 CONFIG_CRYPTO_FIPS=y
 CONFIG_CRYPTO_USER=m
 # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
@@ -656,10 +668,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
@@ -727,7 +735,6 @@ CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_INFO_DWARF4=y
 CONFIG_GDB_SCRIPTS=y
 CONFIG_FRAME_WARN=1024
-CONFIG_UNUSED_SYMBOLS=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_MEMORY_INIT=y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index be09a208b608..20c51e5d9353 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -61,7 +61,7 @@ CONFIG_RAW_DRIVER=y
 CONFIG_CONFIGFS_FS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_DIMLIB is not set
+CONFIG_LSM="yama,loadpin,safesetid,integrity"
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_FS=y
-- 
cgit v1.2.3


From 5e053450c1c3af316aef9a96dc88f52cd803d1ee Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:39:56 +0100
Subject: drm/i915: Only track bound elements of the GTT

The premise here is to simply avoiding having to acquire the vm->mutex
inside vma create/destroy to update the vm->unbound_lists, to avoid some
nasty lock recursions later.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_stolen.c    |  2 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c           | 23 ++++-------------------
 drivers/gpu/drm/i915/i915_gem_gtt.h           |  5 -----
 drivers/gpu/drm/i915/i915_vma.c               | 12 ++----------
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c |  2 +-
 5 files changed, 8 insertions(+), 36 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index bfbc3e3daf92..e45eb8721850 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -692,7 +692,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	__i915_vma_set_map_and_fenceable(vma);
 
 	mutex_lock(&ggtt->vm.mutex);
-	list_move_tail(&vma->vm_link, &ggtt->vm.bound_list);
+	list_add_tail(&vma->vm_link, &ggtt->vm.bound_list);
 	mutex_unlock(&ggtt->vm.mutex);
 
 	GEM_BUG_ON(i915_gem_object_is_shrinkable(obj));
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index e62e9d1a1307..ad9eb2d68f3f 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -505,19 +505,12 @@ static void i915_address_space_fini(struct i915_address_space *vm)
 
 static void ppgtt_destroy_vma(struct i915_address_space *vm)
 {
-	struct list_head *phases[] = {
-		&vm->bound_list,
-		&vm->unbound_list,
-		NULL,
-	}, **phase;
+	struct i915_vma *vma, *vn;
 
 	mutex_lock(&vm->i915->drm.struct_mutex);
-	for (phase = phases; *phase; phase++) {
-		struct i915_vma *vma, *vn;
-
-		list_for_each_entry_safe(vma, vn, *phase, vm_link)
-			i915_vma_destroy(vma);
-	}
+	list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link)
+		i915_vma_destroy(vma);
+	GEM_BUG_ON(!list_empty(&vm->bound_list));
 	mutex_unlock(&vm->i915->drm.struct_mutex);
 }
 
@@ -528,9 +521,6 @@ static void __i915_vm_release(struct work_struct *work)
 
 	ppgtt_destroy_vma(vm);
 
-	GEM_BUG_ON(!list_empty(&vm->bound_list));
-	GEM_BUG_ON(!list_empty(&vm->unbound_list));
-
 	vm->cleanup(vm);
 	i915_address_space_fini(vm);
 
@@ -569,7 +559,6 @@ static void i915_address_space_init(struct i915_address_space *vm, int subclass)
 
 	stash_init(&vm->free_pages);
 
-	INIT_LIST_HEAD(&vm->unbound_list);
 	INIT_LIST_HEAD(&vm->bound_list);
 }
 
@@ -1887,10 +1876,6 @@ static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
 	INIT_LIST_HEAD(&vma->obj_link);
 	INIT_LIST_HEAD(&vma->closed_link);
 
-	mutex_lock(&vma->vm->mutex);
-	list_add(&vma->vm_link, &vma->vm->unbound_list);
-	mutex_unlock(&vma->vm->mutex);
-
 	return vma;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 8fd2234ba0bf..bbdc735466c1 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -320,11 +320,6 @@ struct i915_address_space {
 	 */
 	struct list_head bound_list;
 
-	/**
-	 * List of vma that are not unbound.
-	 */
-	struct list_head unbound_list;
-
 	struct pagestash free_pages;
 
 	/* Global GTT */
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 68c34b1a20e4..d097f77890ba 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -218,10 +218,6 @@ vma_create(struct drm_i915_gem_object *obj,
 
 	spin_unlock(&obj->vma.lock);
 
-	mutex_lock(&vm->mutex);
-	list_add(&vma->vm_link, &vm->unbound_list);
-	mutex_unlock(&vm->mutex);
-
 	return vma;
 
 err_vma:
@@ -657,7 +653,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	GEM_BUG_ON(!i915_gem_valid_gtt_space(vma, color));
 
 	mutex_lock(&vma->vm->mutex);
-	list_move_tail(&vma->vm_link, &vma->vm->bound_list);
+	list_add_tail(&vma->vm_link, &vma->vm->bound_list);
 	mutex_unlock(&vma->vm->mutex);
 
 	if (vma->obj) {
@@ -685,7 +681,7 @@ i915_vma_remove(struct i915_vma *vma)
 
 	mutex_lock(&vma->vm->mutex);
 	drm_mm_remove_node(&vma->node);
-	list_move_tail(&vma->vm_link, &vma->vm->unbound_list);
+	list_del(&vma->vm_link);
 	mutex_unlock(&vma->vm->mutex);
 
 	/*
@@ -798,10 +794,6 @@ static void __i915_vma_destroy(struct i915_vma *vma)
 	GEM_BUG_ON(drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(vma->fence);
 
-	mutex_lock(&vma->vm->mutex);
-	list_del(&vma->vm_link);
-	mutex_unlock(&vma->vm->mutex);
-
 	if (vma->obj) {
 		struct drm_i915_gem_object *obj = vma->obj;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index f901bbb9586e..0945d6e978a2 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1242,7 +1242,7 @@ static void track_vma_bind(struct i915_vma *vma)
 	vma->pages = obj->mm.pages;
 
 	mutex_lock(&vma->vm->mutex);
-	list_move_tail(&vma->vm_link, &vma->vm->bound_list);
+	list_add_tail(&vma->vm_link, &vma->vm->bound_list);
 	mutex_unlock(&vma->vm->mutex);
 }
 
-- 
cgit v1.2.3


From 11331125e1480ff786be9d2051301401b652bbe1 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:39:57 +0100
Subject: drm/i915: Mark up address spaces that may need to allocate

Since we cannot allocate underneath the vm->mutex (it is used in the
direct-reclaim paths), we need to shift the allocations off into a
mutexless worker with fence recursion prevention. To know when we need
this protection, we mark up the address spaces that do allocate before
insertion. In the future, we may wish to extend the async bind scheme to
more than just allocations.

v2: s/vm->bind_alloc/vm->bind_async_flags/

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 3 +++
 drivers/gpu/drm/i915/i915_gem_gtt.h | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index ad9eb2d68f3f..8eba63ecdb03 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1502,6 +1502,7 @@ static struct i915_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 			goto err_free_pd;
 	}
 
+	ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND;
 	ppgtt->vm.insert_entries = gen8_ppgtt_insert;
 	ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc;
 	ppgtt->vm.clear_range = gen8_ppgtt_clear;
@@ -1950,6 +1951,7 @@ static struct i915_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 	ppgtt_init(&ppgtt->base, &i915->gt);
 	ppgtt->base.vm.top = 1;
 
+	ppgtt->base.vm.bind_async_flags = I915_VMA_LOCAL_BIND;
 	ppgtt->base.vm.allocate_va_range = gen6_alloc_va_range;
 	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
 	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
@@ -2581,6 +2583,7 @@ static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
 		goto err_ppgtt;
 
 	ggtt->alias = ppgtt;
+	ggtt->vm.bind_async_flags |= ppgtt->vm.bind_async_flags;
 
 	GEM_BUG_ON(ggtt->vm.vma_ops.bind_vma != ggtt_bind_vma);
 	ggtt->vm.vma_ops.bind_vma = aliasing_gtt_bind_vma;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index bbdc735466c1..3502b9c85a8e 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -305,6 +305,8 @@ struct i915_address_space {
 	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
 	u64 reserved;		/* size addr space reserved */
 
+	unsigned int bind_async_flags;
+
 	bool closed;
 
 	struct mutex mutex; /* protects vma and our lists */
-- 
cgit v1.2.3


From 2850748ef8763ab46958e43a4d1c445f29eeb37d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:39:58 +0100
Subject: drm/i915: Pull i915_vma_pin under the vm->mutex

Replace the struct_mutex requirement for pinning the i915_vma with the
local vm->mutex instead. Note that the vm->mutex is tainted by the
shrinker (we require unbinding from inside fs-reclaim) and so we cannot
allocate while holding that mutex. Instead we have to preallocate
workers to do allocate and apply the PTE updates after we have we
reserved their slot in the drm_mm (using fences to order the PTE writes
with the GPU work and with later unbind).

In adding the asynchronous vma binding, one subtle requirement is to
avoid coupling the binding fence into the backing object->resv. That is
the asynchronous binding only applies to the vma timeline itself and not
to the pages as that is a more global timeline (the binding of one vma
does not need to be ordered with another vma, nor does the implicit GEM
fencing depend on a vma, only on writes to the backing store). Keeping
the vma binding distinct from the backing store timelines is verified by
a number of async gem_exec_fence and gem_exec_schedule tests. The way we
do this is quite simple, we keep the fence for the vma binding separate
and only wait on it as required, and never add it to the obj->resv
itself.

Another consequence in reducing the locking around the vma is the
destruction of the vma is no longer globally serialised by struct_mutex.
A natural solution would be to add a kref to i915_vma, but that requires
decoupling the reference cycles, possibly by introducing a new
i915_mm_pages object that is own by both obj->mm and vma->pages.
However, we have not taken that route due to the overshadowing lmem/ttm
discussions, and instead play a series of complicated games with
trylocks to (hopefully) ensure that only one destruction path is called!

v2: Add some commentary, and some helpers to reduce patch churn.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/display/intel_display.c       |  29 +-
 drivers/gpu/drm/i915/display/intel_dsb.c           |   7 +-
 drivers/gpu/drm/i915/display/intel_fbdev.c         |   8 +-
 drivers/gpu/drm/i915/display/intel_overlay.c       |  11 +-
 drivers/gpu/drm/i915/gem/i915_gem_client_blt.c     |   2 +-
 drivers/gpu/drm/i915/gem/i915_gem_context.c        |  20 +-
 drivers/gpu/drm/i915/gem/i915_gem_domain.c         |  13 +-
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c     |  43 +-
 drivers/gpu/drm/i915/gem/i915_gem_mman.c           |  20 +-
 drivers/gpu/drm/i915/gem/i915_gem_object.c         |  33 +-
 drivers/gpu/drm/i915/gem/i915_gem_object.h         |   5 +
 drivers/gpu/drm/i915/gem/i915_gem_shrinker.c       |  73 +--
 drivers/gpu/drm/i915/gem/i915_gem_stolen.c         |   8 +-
 drivers/gpu/drm/i915/gem/i915_gem_tiling.c         |  27 +-
 drivers/gpu/drm/i915/gem/i915_gem_userptr.c        |  27 +-
 drivers/gpu/drm/i915/gem/selftests/huge_pages.c    |   9 +-
 .../gpu/drm/i915/gem/selftests/i915_gem_context.c  |  12 +-
 drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c |   4 -
 drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c |   7 +-
 drivers/gpu/drm/i915/gt/intel_gt.c                 |   5 +-
 drivers/gpu/drm/i915/gt/intel_ringbuffer.c         |   4 +-
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c       |  19 +-
 drivers/gpu/drm/i915/gvt/aperture_gm.c             |  12 +-
 drivers/gpu/drm/i915/i915_active.c                 |  95 +++-
 drivers/gpu/drm/i915/i915_active.h                 |   7 +
 drivers/gpu/drm/i915/i915_active_types.h           |   5 +
 drivers/gpu/drm/i915/i915_drv.c                    |   2 -
 drivers/gpu/drm/i915/i915_gem.c                    |  83 ++--
 drivers/gpu/drm/i915/i915_gem_evict.c              |  28 +-
 drivers/gpu/drm/i915/i915_gem_fence_reg.c          |   9 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c                | 109 +++--
 drivers/gpu/drm/i915/i915_gem_gtt.h                |  45 +-
 drivers/gpu/drm/i915/i915_perf.c                   |  32 +-
 drivers/gpu/drm/i915/i915_vma.c                    | 524 ++++++++++++++-------
 drivers/gpu/drm/i915/i915_vma.h                    |  84 ++--
 drivers/gpu/drm/i915/selftests/i915_gem.c          |   2 -
 drivers/gpu/drm/i915/selftests/i915_gem_evict.c    |  36 +-
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c      |  58 ++-
 drivers/gpu/drm/i915/selftests/i915_request.c      |   7 +
 drivers/gpu/drm/i915/selftests/i915_vma.c          |   6 +-
 40 files changed, 824 insertions(+), 706 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index c3ac5a5c5185..8f7365b8dffb 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -2079,7 +2079,6 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	unsigned int pinctl;
 	u32 alignment;
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 	if (WARN_ON(!i915_gem_object_is_framebuffer(obj)))
 		return ERR_PTR(-EINVAL);
 
@@ -2163,8 +2162,6 @@ err:
 
 void intel_unpin_fb_vma(struct i915_vma *vma, unsigned long flags)
 {
-	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
-
 	i915_gem_object_lock(vma->obj);
 	if (flags & PLANE_HAS_FENCE)
 		i915_vma_unpin_fence(vma);
@@ -3065,12 +3062,10 @@ intel_alloc_initial_plane_obj(struct intel_crtc *crtc,
 		return false;
 	}
 
-	mutex_lock(&dev->struct_mutex);
 	obj = i915_gem_object_create_stolen_for_preallocated(dev_priv,
 							     base_aligned,
 							     base_aligned,
 							     size_aligned);
-	mutex_unlock(&dev->struct_mutex);
 	if (!obj)
 		return false;
 
@@ -3232,13 +3227,11 @@ valid_fb:
 	intel_state->color_plane[0].stride =
 		intel_fb_pitch(fb, 0, intel_state->base.rotation);
 
-	mutex_lock(&dev->struct_mutex);
 	intel_state->vma =
 		intel_pin_and_fence_fb_obj(fb,
 					   &intel_state->view,
 					   intel_plane_uses_fence(intel_state),
 					   &intel_state->flags);
-	mutex_unlock(&dev->struct_mutex);
 	if (IS_ERR(intel_state->vma)) {
 		DRM_ERROR("failed to pin boot fb on pipe %d: %li\n",
 			  intel_crtc->pipe, PTR_ERR(intel_state->vma));
@@ -14365,8 +14358,6 @@ static void fb_obj_bump_render_priority(struct drm_i915_gem_object *obj)
  * bits.  Some older platforms need special physical address handling for
  * cursor planes.
  *
- * Must be called with struct_mutex held.
- *
  * Returns 0 on success, negative error code on failure.
  */
 int
@@ -14423,15 +14414,8 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 	if (ret)
 		return ret;
 
-	ret = mutex_lock_interruptible(&dev_priv->drm.struct_mutex);
-	if (ret) {
-		i915_gem_object_unpin_pages(obj);
-		return ret;
-	}
-
 	ret = intel_plane_pin_fb(to_intel_plane_state(new_state));
 
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 	i915_gem_object_unpin_pages(obj);
 	if (ret)
 		return ret;
@@ -14480,8 +14464,6 @@ intel_prepare_plane_fb(struct drm_plane *plane,
  * @old_state: the state from the previous modeset
  *
  * Cleans up a framebuffer that has just been removed from a plane.
- *
- * Must be called with struct_mutex held.
  */
 void
 intel_cleanup_plane_fb(struct drm_plane *plane,
@@ -14497,9 +14479,7 @@ intel_cleanup_plane_fb(struct drm_plane *plane,
 	}
 
 	/* Should only be called after a successful intel_prepare_plane_fb()! */
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_plane_unpin_fb(to_intel_plane_state(old_state));
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 }
 
 int
@@ -14702,7 +14682,6 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 			   u32 src_w, u32 src_h,
 			   struct drm_modeset_acquire_ctx *ctx)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct drm_plane_state *old_plane_state, *new_plane_state;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct intel_crtc_state *crtc_state =
@@ -14768,13 +14747,9 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 	if (ret)
 		goto out_free;
 
-	ret = mutex_lock_interruptible(&dev_priv->drm.struct_mutex);
-	if (ret)
-		goto out_free;
-
 	ret = intel_plane_pin_fb(to_intel_plane_state(new_plane_state));
 	if (ret)
-		goto out_unlock;
+		goto out_free;
 
 	intel_frontbuffer_flush(to_intel_frontbuffer(fb), ORIGIN_FLIP);
 	intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->fb),
@@ -14804,8 +14779,6 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 
 	intel_plane_unpin_fb(to_intel_plane_state(old_plane_state));
 
-out_unlock:
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 out_free:
 	if (new_crtc_state)
 		intel_crtc_destroy_state(crtc, &new_crtc_state->base);
diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c
index 0a0a1536ac96..bb5a0e91b370 100644
--- a/drivers/gpu/drm/i915/display/intel_dsb.c
+++ b/drivers/gpu/drm/i915/display/intel_dsb.c
@@ -119,9 +119,7 @@ intel_dsb_get(struct intel_crtc *crtc)
 		goto err;
 	}
 
-	mutex_lock(&i915->drm.struct_mutex);
 	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
-	mutex_unlock(&i915->drm.struct_mutex);
 	if (IS_ERR(vma)) {
 		DRM_ERROR("Vma creation failed\n");
 		i915_gem_object_put(obj);
@@ -164,10 +162,7 @@ void intel_dsb_put(struct intel_dsb *dsb)
 		return;
 
 	if (atomic_dec_and_test(&dsb->refcount)) {
-		mutex_lock(&i915->drm.struct_mutex);
-		i915_gem_object_unpin_map(dsb->vma->obj);
-		i915_vma_unpin_and_release(&dsb->vma, 0);
-		mutex_unlock(&i915->drm.struct_mutex);
+		i915_vma_unpin_and_release(&dsb->vma, I915_VMA_RELEASE_MAP);
 		dsb->cmd_buf = NULL;
 		dsb->free_pos = 0;
 		dsb->ins_start_offset = 0;
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index 68338669f054..97cde017670a 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -204,7 +204,6 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		sizes->fb_height = intel_fb->base.height;
 	}
 
-	mutex_lock(&dev->struct_mutex);
 	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
 
 	/* Pin the GGTT vma for our access via info->screen_base.
@@ -266,7 +265,6 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	ifbdev->vma_flags = flags;
 
 	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
-	mutex_unlock(&dev->struct_mutex);
 	vga_switcheroo_client_fb_set(pdev, info);
 	return 0;
 
@@ -274,7 +272,6 @@ out_unpin:
 	intel_unpin_fb_vma(vma, flags);
 out_unlock:
 	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
-	mutex_unlock(&dev->struct_mutex);
 	return ret;
 }
 
@@ -291,11 +288,8 @@ static void intel_fbdev_destroy(struct intel_fbdev *ifbdev)
 
 	drm_fb_helper_fini(&ifbdev->helper);
 
-	if (ifbdev->vma) {
-		mutex_lock(&ifbdev->helper.dev->struct_mutex);
+	if (ifbdev->vma)
 		intel_unpin_fb_vma(ifbdev->vma, ifbdev->vma_flags);
-		mutex_unlock(&ifbdev->helper.dev->struct_mutex);
-	}
 
 	if (ifbdev->fb)
 		drm_framebuffer_remove(&ifbdev->fb->base);
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 5efef9babadb..3f4ac1ee7668 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -1303,15 +1303,11 @@ static int get_registers(struct intel_overlay *overlay, bool use_phys)
 	struct i915_vma *vma;
 	int err;
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	obj = i915_gem_object_create_stolen(i915, PAGE_SIZE);
 	if (obj == NULL)
 		obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
-	if (IS_ERR(obj)) {
-		err = PTR_ERR(obj);
-		goto err_unlock;
-	}
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
 	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
 	if (IS_ERR(vma)) {
@@ -1332,13 +1328,10 @@ static int get_registers(struct intel_overlay *overlay, bool use_phys)
 	}
 
 	overlay->reg_bo = obj;
-	mutex_unlock(&i915->drm.struct_mutex);
 	return 0;
 
 err_put_bo:
 	i915_gem_object_put(obj);
-err_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
index 7f61a8024133..c1fca5728e6e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
@@ -211,7 +211,7 @@ static void clear_pages_worker(struct work_struct *work)
 	 * keep track of the GPU activity within this vma/request, and
 	 * propagate the signal from the request to w->dma.
 	 */
-	err = i915_active_add_request(&vma->active, rq);
+	err = __i915_vma_move_to_active(vma, rq);
 	if (err)
 		goto out_request;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index f7ba0935ed67..95f8e66e45db 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -313,8 +313,6 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
 	GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
 
 	release_hw_id(ctx);
-	if (ctx->vm)
-		i915_vm_put(ctx->vm);
 
 	free_engines(rcu_access_pointer(ctx->engines));
 	mutex_destroy(&ctx->engines_mutex);
@@ -379,9 +377,13 @@ void i915_gem_context_release(struct kref *ref)
 
 static void context_close(struct i915_gem_context *ctx)
 {
+	i915_gem_context_set_closed(ctx);
+
+	if (ctx->vm)
+		i915_vm_close(ctx->vm);
+
 	mutex_lock(&ctx->mutex);
 
-	i915_gem_context_set_closed(ctx);
 	ctx->file_priv = ERR_PTR(-EBADF);
 
 	/*
@@ -474,7 +476,7 @@ __set_ppgtt(struct i915_gem_context *ctx, struct i915_address_space *vm)
 
 	GEM_BUG_ON(old && i915_vm_is_4lvl(vm) != i915_vm_is_4lvl(old));
 
-	ctx->vm = i915_vm_get(vm);
+	ctx->vm = i915_vm_open(vm);
 	context_apply_all(ctx, __apply_ppgtt, vm);
 
 	return old;
@@ -488,7 +490,7 @@ static void __assign_ppgtt(struct i915_gem_context *ctx,
 
 	vm = __set_ppgtt(ctx, vm);
 	if (vm)
-		i915_vm_put(vm);
+		i915_vm_close(vm);
 }
 
 static void __set_timeline(struct intel_timeline **dst,
@@ -953,7 +955,7 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv,
 	if (ret < 0)
 		goto err_unlock;
 
-	i915_vm_get(vm);
+	i915_vm_open(vm);
 
 	args->size = 0;
 	args->value = ret;
@@ -973,7 +975,7 @@ static void set_ppgtt_barrier(void *data)
 	if (INTEL_GEN(old->i915) < 8)
 		gen6_ppgtt_unpin_all(i915_vm_to_ppgtt(old));
 
-	i915_vm_put(old);
+	i915_vm_close(old);
 }
 
 static int emit_ppgtt_update(struct i915_request *rq, void *data)
@@ -1090,8 +1092,8 @@ static int set_ppgtt(struct drm_i915_file_private *file_priv,
 				   set_ppgtt_barrier,
 				   old);
 	if (err) {
-		i915_vm_put(__set_ppgtt(ctx, old));
-		i915_vm_put(old);
+		i915_vm_close(__set_ppgtt(ctx, old));
+		i915_vm_close(old);
 	}
 
 unlock:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 55c3ab59e3aa..9937b4c341f1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -288,7 +288,12 @@ restart:
 			if (!drm_mm_node_allocated(&vma->node))
 				continue;
 
-			ret = i915_vma_bind(vma, cache_level, PIN_UPDATE);
+			/* Wait for an earlier async bind, need to rewrite it */
+			ret = i915_vma_sync(vma);
+			if (ret)
+				return ret;
+
+			ret = i915_vma_bind(vma, cache_level, PIN_UPDATE, NULL);
 			if (ret)
 				return ret;
 		}
@@ -391,16 +396,11 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto out;
 
-	ret = mutex_lock_interruptible(&i915->drm.struct_mutex);
-	if (ret)
-		goto out;
-
 	ret = i915_gem_object_lock_interruptible(obj);
 	if (ret == 0) {
 		ret = i915_gem_object_set_cache_level(obj, level);
 		i915_gem_object_unlock(obj);
 	}
-	mutex_unlock(&i915->drm.struct_mutex);
 
 out:
 	i915_gem_object_put(obj);
@@ -485,6 +485,7 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj)
 		if (!drm_mm_node_allocated(&vma->node))
 			continue;
 
+		GEM_BUG_ON(vma->vm != &i915->ggtt.vm);
 		list_move_tail(&vma->vm_link, &vma->vm->bound_list);
 	}
 	mutex_unlock(&i915->ggtt.vm.mutex);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 228ce24ea280..42c15e8bf166 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -698,7 +698,9 @@ static int eb_reserve(struct i915_execbuffer *eb)
 
 		case 1:
 			/* Too fragmented, unbind everything and retry */
+			mutex_lock(&eb->context->vm->mutex);
 			err = i915_gem_evict_vm(eb->context->vm);
+			mutex_unlock(&eb->context->vm->mutex);
 			if (err)
 				return err;
 			break;
@@ -972,7 +974,9 @@ static void reloc_cache_reset(struct reloc_cache *cache)
 			ggtt->vm.clear_range(&ggtt->vm,
 					     cache->node.start,
 					     cache->node.size);
+			mutex_lock(&ggtt->vm.mutex);
 			drm_mm_remove_node(&cache->node);
+			mutex_unlock(&ggtt->vm.mutex);
 		} else {
 			i915_vma_unpin((struct i915_vma *)cache->node.mm);
 		}
@@ -1047,11 +1051,13 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj,
 					       PIN_NOEVICT);
 		if (IS_ERR(vma)) {
 			memset(&cache->node, 0, sizeof(cache->node));
+			mutex_lock(&ggtt->vm.mutex);
 			err = drm_mm_insert_node_in_range
 				(&ggtt->vm.mm, &cache->node,
 				 PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
 				 0, ggtt->mappable_end,
 				 DRM_MM_INSERT_LOW);
+			mutex_unlock(&ggtt->vm.mutex);
 			if (err) /* no inactive aperture space, use cpu reloc */
 				return NULL;
 		} else {
@@ -1416,7 +1422,7 @@ eb_relocate_entry(struct i915_execbuffer *eb,
 		if (reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
 		    IS_GEN(eb->i915, 6)) {
 			err = i915_vma_bind(target, target->obj->cache_level,
-					    PIN_GLOBAL);
+					    PIN_GLOBAL, NULL);
 			if (WARN_ONCE(err,
 				      "Unexpected failure to bind target VMA!"))
 				return err;
@@ -2142,35 +2148,6 @@ static struct i915_request *eb_throttle(struct intel_context *ce)
 	return i915_request_get(rq);
 }
 
-static int
-__eb_pin_context(struct i915_execbuffer *eb, struct intel_context *ce)
-{
-	int err;
-
-	if (likely(atomic_inc_not_zero(&ce->pin_count)))
-		return 0;
-
-	err = mutex_lock_interruptible(&eb->i915->drm.struct_mutex);
-	if (err)
-		return err;
-
-	err = __intel_context_do_pin(ce);
-	mutex_unlock(&eb->i915->drm.struct_mutex);
-
-	return err;
-}
-
-static void
-__eb_unpin_context(struct i915_execbuffer *eb, struct intel_context *ce)
-{
-	if (likely(atomic_add_unless(&ce->pin_count, -1, 1)))
-		return;
-
-	mutex_lock(&eb->i915->drm.struct_mutex);
-	intel_context_unpin(ce);
-	mutex_unlock(&eb->i915->drm.struct_mutex);
-}
-
 static int __eb_pin_engine(struct i915_execbuffer *eb, struct intel_context *ce)
 {
 	struct intel_timeline *tl;
@@ -2190,7 +2167,7 @@ static int __eb_pin_engine(struct i915_execbuffer *eb, struct intel_context *ce)
 	 * GGTT space, so do this first before we reserve a seqno for
 	 * ourselves.
 	 */
-	err = __eb_pin_context(eb, ce);
+	err = intel_context_pin(ce);
 	if (err)
 		return err;
 
@@ -2234,7 +2211,7 @@ err_exit:
 	intel_context_exit(ce);
 	intel_context_timeline_unlock(tl);
 err_unpin:
-	__eb_unpin_context(eb, ce);
+	intel_context_unpin(ce);
 	return err;
 }
 
@@ -2247,7 +2224,7 @@ static void eb_unpin_engine(struct i915_execbuffer *eb)
 	intel_context_exit(ce);
 	mutex_unlock(&tl->mutex);
 
-	__eb_unpin_context(eb, ce);
+	intel_context_unpin(ce);
 }
 
 static unsigned int
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index dd0c2840ba4d..c19431d609fc 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -249,16 +249,6 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 	if (ret)
 		goto err_rpm;
 
-	ret = i915_mutex_lock_interruptible(dev);
-	if (ret)
-		goto err_reset;
-
-	/* Access to snoopable pages through the GTT is incoherent. */
-	if (obj->cache_level != I915_CACHE_NONE && !HAS_LLC(i915)) {
-		ret = -EFAULT;
-		goto err_unlock;
-	}
-
 	/* Now pin it into the GTT as needed */
 	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
 				       PIN_MAPPABLE |
@@ -291,7 +281,13 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 	}
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
-		goto err_unlock;
+		goto err_reset;
+	}
+
+	/* Access to snoopable pages through the GTT is incoherent. */
+	if (obj->cache_level != I915_CACHE_NONE && !HAS_LLC(i915)) {
+		ret = -EFAULT;
+		goto err_unpin;
 	}
 
 	ret = i915_vma_pin_fence(vma);
@@ -329,8 +325,6 @@ err_fence:
 	i915_vma_unpin_fence(vma);
 err_unpin:
 	__i915_vma_unpin(vma);
-err_unlock:
-	mutex_unlock(&dev->struct_mutex);
 err_reset:
 	intel_gt_reset_unlock(ggtt->vm.gt, srcu);
 err_rpm:
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 0ef60dae23a7..dbf9be9a79f4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -155,21 +155,30 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 	llist_for_each_entry_safe(obj, on, freed, freed) {
-		struct i915_vma *vma, *vn;
-
 		trace_i915_gem_object_destroy(obj);
 
-		mutex_lock(&i915->drm.struct_mutex);
-
-		list_for_each_entry_safe(vma, vn, &obj->vma.list, obj_link) {
-			GEM_BUG_ON(i915_vma_is_active(vma));
-			atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
-			i915_vma_destroy(vma);
+		if (!list_empty(&obj->vma.list)) {
+			struct i915_vma *vma;
+
+			/*
+			 * Note that the vma keeps an object reference while
+			 * it is active, so it *should* not sleep while we
+			 * destroy it. Our debug code errs insits it *might*.
+			 * For the moment, play along.
+			 */
+			spin_lock(&obj->vma.lock);
+			while ((vma = list_first_entry_or_null(&obj->vma.list,
+							       struct i915_vma,
+							       obj_link))) {
+				GEM_BUG_ON(vma->obj != obj);
+				spin_unlock(&obj->vma.lock);
+
+				i915_vma_destroy(vma);
+
+				spin_lock(&obj->vma.lock);
+			}
+			spin_unlock(&obj->vma.lock);
 		}
-		GEM_BUG_ON(!list_empty(&obj->vma.list));
-		GEM_BUG_ON(!RB_EMPTY_ROOT(&obj->vma.tree));
-
-		mutex_unlock(&i915->drm.struct_mutex);
 
 		GEM_BUG_ON(atomic_read(&obj->bind_count));
 		GEM_BUG_ON(obj->userfault_count);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 53c7069ba3e8..086a9bf5adcc 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -106,6 +106,11 @@ static inline void i915_gem_object_lock(struct drm_i915_gem_object *obj)
 	dma_resv_lock(obj->base.resv, NULL);
 }
 
+static inline bool i915_gem_object_trylock(struct drm_i915_gem_object *obj)
+{
+	return dma_resv_trylock(obj->base.resv);
+}
+
 static inline int
 i915_gem_object_lock_interruptible(struct drm_i915_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index d2c05d752909..fd3ce6da8497 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -16,40 +16,6 @@
 
 #include "i915_trace.h"
 
-static bool shrinker_lock(struct drm_i915_private *i915,
-			  unsigned int flags,
-			  bool *unlock)
-{
-	struct mutex *m = &i915->drm.struct_mutex;
-
-	switch (mutex_trylock_recursive(m)) {
-	case MUTEX_TRYLOCK_RECURSIVE:
-		*unlock = false;
-		return true;
-
-	case MUTEX_TRYLOCK_FAILED:
-		*unlock = false;
-		if (flags & I915_SHRINK_ACTIVE &&
-		    mutex_lock_killable_nested(m, I915_MM_SHRINKER) == 0)
-			*unlock = true;
-		return *unlock;
-
-	case MUTEX_TRYLOCK_SUCCESS:
-		*unlock = true;
-		return true;
-	}
-
-	BUG();
-}
-
-static void shrinker_unlock(struct drm_i915_private *i915, bool unlock)
-{
-	if (!unlock)
-		return;
-
-	mutex_unlock(&i915->drm.struct_mutex);
-}
-
 static bool swap_available(void)
 {
 	return get_nr_swap_pages() > 0;
@@ -155,10 +121,6 @@ i915_gem_shrink(struct drm_i915_private *i915,
 	intel_wakeref_t wakeref = 0;
 	unsigned long count = 0;
 	unsigned long scanned = 0;
-	bool unlock;
-
-	if (!shrinker_lock(i915, shrink, &unlock))
-		return 0;
 
 	/*
 	 * When shrinking the active list, we should also consider active
@@ -268,8 +230,6 @@ i915_gem_shrink(struct drm_i915_private *i915,
 	if (shrink & I915_SHRINK_BOUND)
 		intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 
-	shrinker_unlock(i915, unlock);
-
 	if (nr_scanned)
 		*nr_scanned += scanned;
 	return count;
@@ -339,19 +299,14 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 	struct drm_i915_private *i915 =
 		container_of(shrinker, struct drm_i915_private, mm.shrinker);
 	unsigned long freed;
-	bool unlock;
 
 	sc->nr_scanned = 0;
 
-	if (!shrinker_lock(i915, 0, &unlock))
-		return SHRINK_STOP;
-
 	freed = i915_gem_shrink(i915,
 				sc->nr_to_scan,
 				&sc->nr_scanned,
 				I915_SHRINK_BOUND |
-				I915_SHRINK_UNBOUND |
-				I915_SHRINK_WRITEBACK);
+				I915_SHRINK_UNBOUND);
 	if (sc->nr_scanned < sc->nr_to_scan && current_is_kswapd()) {
 		intel_wakeref_t wakeref;
 
@@ -366,8 +321,6 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 		}
 	}
 
-	shrinker_unlock(i915, unlock);
-
 	return sc->nr_scanned ? freed : SHRINK_STOP;
 }
 
@@ -384,6 +337,7 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
 	freed_pages = 0;
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
 		freed_pages += i915_gem_shrink(i915, -1UL, NULL,
+					       I915_SHRINK_ACTIVE |
 					       I915_SHRINK_BOUND |
 					       I915_SHRINK_UNBOUND |
 					       I915_SHRINK_WRITEBACK);
@@ -419,10 +373,6 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 	struct i915_vma *vma, *next;
 	unsigned long freed_pages = 0;
 	intel_wakeref_t wakeref;
-	bool unlock;
-
-	if (!shrinker_lock(i915, 0, &unlock))
-		return NOTIFY_DONE;
 
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
 		freed_pages += i915_gem_shrink(i915, -1UL, NULL,
@@ -439,15 +389,11 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 		if (!vma->iomap || i915_vma_is_active(vma))
 			continue;
 
-		mutex_unlock(&i915->ggtt.vm.mutex);
-		if (i915_vma_unbind(vma) == 0)
+		if (__i915_vma_unbind(vma) == 0)
 			freed_pages += count;
-		mutex_lock(&i915->ggtt.vm.mutex);
 	}
 	mutex_unlock(&i915->ggtt.vm.mutex);
 
-	shrinker_unlock(i915, unlock);
-
 	*(unsigned long *)ptr += freed_pages;
 	return NOTIFY_DONE;
 }
@@ -490,22 +436,9 @@ void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915,
 
 	fs_reclaim_acquire(GFP_KERNEL);
 
-	/*
-	 * As we invariably rely on the struct_mutex within the shrinker,
-	 * but have a complicated recursion dance, taint all the mutexes used
-	 * within the shrinker with the struct_mutex. For completeness, we
-	 * taint with all subclass of struct_mutex, even though we should
-	 * only need tainting by I915_MM_NORMAL to catch possible ABBA
-	 * deadlocks from using struct_mutex inside @mutex.
-	 */
-	mutex_acquire(&i915->drm.struct_mutex.dep_map,
-		      I915_MM_SHRINKER, 0, _RET_IP_);
-
 	mutex_acquire(&mutex->dep_map, 0, 0, _RET_IP_);
 	mutex_release(&mutex->dep_map, 0, _RET_IP_);
 
-	mutex_release(&i915->drm.struct_mutex.dep_map, 0, _RET_IP_);
-
 	fs_reclaim_release(GFP_KERNEL);
 
 	if (unlock)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index e45eb8721850..fad98a921cde 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -624,8 +624,6 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return NULL;
 
-	lockdep_assert_held(&dev_priv->drm.struct_mutex);
-
 	DRM_DEBUG_DRIVER("creating preallocated stolen object: stolen_offset=%pa, gtt_offset=%pa, size=%pa\n",
 			 &stolen_offset, &gtt_offset, &size);
 
@@ -677,21 +675,25 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	 * setting up the GTT space. The actual reservation will occur
 	 * later.
 	 */
+	mutex_lock(&ggtt->vm.mutex);
 	ret = i915_gem_gtt_reserve(&ggtt->vm, &vma->node,
 				   size, gtt_offset, obj->cache_level,
 				   0);
 	if (ret) {
 		DRM_DEBUG_DRIVER("failed to allocate stolen GTT space\n");
+		mutex_unlock(&ggtt->vm.mutex);
 		goto err_pages;
 	}
 
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 
+	GEM_BUG_ON(vma->pages);
 	vma->pages = obj->mm.pages;
+	atomic_set(&vma->pages_count, I915_VMA_PAGES_ACTIVE);
+
 	set_bit(I915_VMA_GLOBAL_BIND_BIT, __i915_vma_flags(vma));
 	__i915_vma_set_map_and_fenceable(vma);
 
-	mutex_lock(&ggtt->vm.mutex);
 	list_add_tail(&vma->vm_link, &ggtt->vm.bound_list);
 	mutex_unlock(&ggtt->vm.mutex);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
index e5d1ae8d4dba..dc2a83ce44d5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
@@ -181,22 +181,25 @@ static int
 i915_gem_object_fence_prepare(struct drm_i915_gem_object *obj,
 			      int tiling_mode, unsigned int stride)
 {
+	struct i915_ggtt *ggtt = &to_i915(obj->base.dev)->ggtt;
 	struct i915_vma *vma;
-	int ret;
+	int ret = 0;
 
 	if (tiling_mode == I915_TILING_NONE)
 		return 0;
 
+	mutex_lock(&ggtt->vm.mutex);
 	for_each_ggtt_vma(vma, obj) {
 		if (i915_vma_fence_prepare(vma, tiling_mode, stride))
 			continue;
 
-		ret = i915_vma_unbind(vma);
+		ret = __i915_vma_unbind(vma);
 		if (ret)
-			return ret;
+			break;
 	}
+	mutex_unlock(&ggtt->vm.mutex);
 
-	return 0;
+	return ret;
 }
 
 int
@@ -212,7 +215,6 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
 
 	GEM_BUG_ON(!i915_tiling_ok(obj, tiling, stride));
 	GEM_BUG_ON(!stride ^ (tiling == I915_TILING_NONE));
-	lockdep_assert_held(&i915->drm.struct_mutex);
 
 	if ((tiling | stride) == obj->tiling_and_stride)
 		return 0;
@@ -233,16 +235,18 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
 	 * whilst executing a fenced command for an untiled object.
 	 */
 
-	err = i915_gem_object_fence_prepare(obj, tiling, stride);
-	if (err)
-		return err;
-
 	i915_gem_object_lock(obj);
 	if (i915_gem_object_is_framebuffer(obj)) {
 		i915_gem_object_unlock(obj);
 		return -EBUSY;
 	}
 
+	err = i915_gem_object_fence_prepare(obj, tiling, stride);
+	if (err) {
+		i915_gem_object_unlock(obj);
+		return err;
+	}
+
 	/* If the memory has unknown (i.e. varying) swizzling, we pin the
 	 * pages to prevent them being swapped out and causing corruption
 	 * due to the change in swizzling.
@@ -368,12 +372,7 @@ i915_gem_set_tiling_ioctl(struct drm_device *dev, void *data,
 		}
 	}
 
-	err = mutex_lock_interruptible(&dev->struct_mutex);
-	if (err)
-		goto err;
-
 	err = i915_gem_object_set_tiling(obj, args->tiling_mode, args->stride);
-	mutex_unlock(&dev->struct_mutex);
 
 	/* We have to maintain this existing ABI... */
 	args->stride = i915_gem_object_get_stride(obj);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index a0d974ac78a7..3798502097b4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -92,7 +92,6 @@ userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 	struct i915_mmu_notifier *mn =
 		container_of(_mn, struct i915_mmu_notifier, mn);
 	struct interval_tree_node *it;
-	struct mutex *unlock = NULL;
 	unsigned long end;
 	int ret = 0;
 
@@ -129,33 +128,13 @@ userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 		}
 		spin_unlock(&mn->lock);
 
-		if (!unlock) {
-			unlock = &mn->mm->i915->drm.struct_mutex;
-
-			switch (mutex_trylock_recursive(unlock)) {
-			default:
-			case MUTEX_TRYLOCK_FAILED:
-				if (mutex_lock_killable_nested(unlock, I915_MM_SHRINKER)) {
-					i915_gem_object_put(obj);
-					return -EINTR;
-				}
-				/* fall through */
-			case MUTEX_TRYLOCK_SUCCESS:
-				break;
-
-			case MUTEX_TRYLOCK_RECURSIVE:
-				unlock = ERR_PTR(-EEXIST);
-				break;
-			}
-		}
-
 		ret = i915_gem_object_unbind(obj,
 					     I915_GEM_OBJECT_UNBIND_ACTIVE);
 		if (ret == 0)
 			ret = __i915_gem_object_put_pages(obj, I915_MM_SHRINKER);
 		i915_gem_object_put(obj);
 		if (ret)
-			goto unlock;
+			return ret;
 
 		spin_lock(&mn->lock);
 
@@ -168,10 +147,6 @@ userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 	}
 	spin_unlock(&mn->lock);
 
-unlock:
-	if (!IS_ERR_OR_NULL(unlock))
-		mutex_unlock(unlock);
-
 	return ret;
 
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index c5cea4379216..98b2a6ccfcc1 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -333,7 +333,12 @@ static int igt_check_page_sizes(struct i915_vma *vma)
 	struct drm_i915_private *i915 = vma->vm->i915;
 	unsigned int supported = INTEL_INFO(i915)->page_sizes;
 	struct drm_i915_gem_object *obj = vma->obj;
-	int err = 0;
+	int err;
+
+	/* We have to wait for the async bind to complete before our asserts */
+	err = i915_vma_sync(vma);
+	if (err)
+		return err;
 
 	if (!HAS_PAGE_SIZES(i915, vma->page_sizes.sg)) {
 		pr_err("unsupported page_sizes.sg=%u, supported=%u\n",
@@ -1390,7 +1395,7 @@ static int igt_ppgtt_pin_update(void *arg)
 			goto out_unpin;
 		}
 
-		err = i915_vma_bind(vma, I915_CACHE_NONE, PIN_UPDATE);
+		err = i915_vma_bind(vma, I915_CACHE_NONE, PIN_UPDATE, NULL);
 		if (err)
 			goto out_unpin;
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 0f4d0644a480..8eba0d3a31de 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -971,10 +971,7 @@ emit_rpcs_query(struct drm_i915_gem_object *obj,
 	if (err)
 		goto skip_request;
 
-	i915_vma_unpin(batch);
-	i915_vma_close(batch);
-	i915_vma_put(batch);
-
+	i915_vma_unpin_and_release(&batch, 0);
 	i915_vma_unpin(vma);
 
 	*rq_out = i915_request_get(rq);
@@ -988,8 +985,7 @@ skip_request:
 err_request:
 	i915_request_add(rq);
 err_batch:
-	i915_vma_unpin(batch);
-	i915_vma_put(batch);
+	i915_vma_unpin_and_release(&batch, 0);
 err_vma:
 	i915_vma_unpin(vma);
 
@@ -1533,9 +1529,7 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 	if (err)
 		goto skip_request;
 
-	i915_vma_unpin(vma);
-	i915_vma_close(vma);
-	i915_vma_put(vma);
+	i915_vma_unpin_and_release(&vma, 0);
 
 	i915_request_add(rq);
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index aefe557527f8..36aca1c172e7 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -322,7 +322,6 @@ static int igt_partial_tiling(void *arg)
 		goto out;
 	}
 
-	mutex_lock(&i915->drm.struct_mutex);
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 
 	if (1) {
@@ -415,7 +414,6 @@ next_tiling: ;
 
 out_unlock:
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	i915_gem_object_unpin_pages(obj);
 out:
 	i915_gem_object_put(obj);
@@ -458,7 +456,6 @@ static int igt_smoke_tiling(void *arg)
 		goto out;
 	}
 
-	mutex_lock(&i915->drm.struct_mutex);
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 
 	count = 0;
@@ -508,7 +505,6 @@ static int igt_smoke_tiling(void *arg)
 	pr_info("%s: Completed %lu trials\n", __func__, count);
 
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	i915_gem_object_unpin_pages(obj);
 out:
 	i915_gem_object_put(obj);
diff --git a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
index ee5dc13a30b3..6718da20f35d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
+++ b/drivers/gpu/drm/i915/gem/selftests/igt_gem_utils.c
@@ -154,9 +154,7 @@ int igt_gpu_fill_dw(struct intel_context *ce,
 
 	i915_request_add(rq);
 
-	i915_vma_unpin(batch);
-	i915_vma_close(batch);
-	i915_vma_put(batch);
+	i915_vma_unpin_and_release(&batch, 0);
 
 	return 0;
 
@@ -165,7 +163,6 @@ skip_request:
 err_request:
 	i915_request_add(rq);
 err_batch:
-	i915_vma_unpin(batch);
-	i915_vma_put(batch);
+	i915_vma_unpin_and_release(&batch, 0);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 0e5909ee0657..7205595369be 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -302,11 +302,12 @@ void intel_gt_flush_ggtt_writes(struct intel_gt *gt)
 
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
 		struct intel_uncore *uncore = gt->uncore;
+		unsigned long flags;
 
-		spin_lock_irq(&uncore->lock);
+		spin_lock_irqsave(&uncore->lock, flags);
 		intel_uncore_posting_read_fw(uncore,
 					     RING_HEAD(RENDER_RING_BASE));
-		spin_unlock_irq(&uncore->lock);
+		spin_unlock_irqrestore(&uncore->lock, flags);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index 0747b8c9f768..ec32996254c0 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -1338,15 +1338,13 @@ void intel_ring_free(struct kref *ref)
 {
 	struct intel_ring *ring = container_of(ref, typeof(*ring), ref);
 
-	i915_vma_close(ring->vma);
 	i915_vma_put(ring->vma);
-
 	kfree(ring);
 }
 
 static void __ring_context_fini(struct intel_context *ce)
 {
-	i915_gem_object_put(ce->state->obj);
+	i915_vma_put(ce->state);
 }
 
 static void ring_context_destroy(struct kref *ref)
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 9c0c8441c22a..d3bee9f88008 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -1127,15 +1127,14 @@ static int evict_vma(void *data)
 {
 	struct evict_vma *arg = data;
 	struct i915_address_space *vm = arg->vma->vm;
-	struct drm_i915_private *i915 = vm->i915;
 	struct drm_mm_node evict = arg->vma->node;
 	int err;
 
 	complete(&arg->completion);
 
-	mutex_lock(&i915->drm.struct_mutex);
+	mutex_lock(&vm->mutex);
 	err = i915_gem_evict_for_node(vm, &evict, 0);
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_unlock(&vm->mutex);
 
 	return err;
 }
@@ -1143,39 +1142,33 @@ static int evict_vma(void *data)
 static int evict_fence(void *data)
 {
 	struct evict_vma *arg = data;
-	struct drm_i915_private *i915 = arg->vma->vm->i915;
 	int err;
 
 	complete(&arg->completion);
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	/* Mark the fence register as dirty to force the mmio update. */
 	err = i915_gem_object_set_tiling(arg->vma->obj, I915_TILING_Y, 512);
 	if (err) {
 		pr_err("Invalid Y-tiling settings; err:%d\n", err);
-		goto out_unlock;
+		return err;
 	}
 
 	err = i915_vma_pin(arg->vma, 0, 0, PIN_GLOBAL | PIN_MAPPABLE);
 	if (err) {
 		pr_err("Unable to pin vma for Y-tiled fence; err:%d\n", err);
-		goto out_unlock;
+		return err;
 	}
 
 	err = i915_vma_pin_fence(arg->vma);
 	i915_vma_unpin(arg->vma);
 	if (err) {
 		pr_err("Unable to pin Y-tiled fence; err:%d\n", err);
-		goto out_unlock;
+		return err;
 	}
 
 	i915_vma_unpin_fence(arg->vma);
 
-out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
-
-	return err;
+	return 0;
 }
 
 static int __igt_reset_evict_vma(struct intel_gt *gt,
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c
index 5ff2437b2998..d996bbc7ea59 100644
--- a/drivers/gpu/drm/i915/gvt/aperture_gm.c
+++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c
@@ -61,14 +61,14 @@ static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm)
 		flags = PIN_MAPPABLE;
 	}
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
+	mutex_lock(&dev_priv->ggtt.vm.mutex);
 	mmio_hw_access_pre(dev_priv);
 	ret = i915_gem_gtt_insert(&dev_priv->ggtt.vm, node,
 				  size, I915_GTT_PAGE_SIZE,
 				  I915_COLOR_UNEVICTABLE,
 				  start, end, flags);
 	mmio_hw_access_post(dev_priv);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
+	mutex_unlock(&dev_priv->ggtt.vm.mutex);
 	if (ret)
 		gvt_err("fail to alloc %s gm space from host\n",
 			high_gm ? "high" : "low");
@@ -98,9 +98,9 @@ static int alloc_vgpu_gm(struct intel_vgpu *vgpu)
 
 	return 0;
 out_free_aperture:
-	mutex_lock(&dev_priv->drm.struct_mutex);
+	mutex_lock(&dev_priv->ggtt.vm.mutex);
 	drm_mm_remove_node(&vgpu->gm.low_gm_node);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
+	mutex_unlock(&dev_priv->ggtt.vm.mutex);
 	return ret;
 }
 
@@ -108,10 +108,10 @@ static void free_vgpu_gm(struct intel_vgpu *vgpu)
 {
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
+	mutex_lock(&dev_priv->ggtt.vm.mutex);
 	drm_mm_remove_node(&vgpu->gm.low_gm_node);
 	drm_mm_remove_node(&vgpu->gm.high_gm_node);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
+	mutex_unlock(&dev_priv->ggtt.vm.mutex);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index d5aac6ff803a..0791736a08fd 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -146,6 +146,7 @@ __active_retire(struct i915_active *ref)
 	if (!retire)
 		return;
 
+	GEM_BUG_ON(rcu_access_pointer(ref->excl));
 	rbtree_postorder_for_each_entry_safe(it, n, &root, node) {
 		GEM_BUG_ON(i915_active_request_isset(&it->base));
 		kmem_cache_free(global.slab_cache, it);
@@ -245,6 +246,8 @@ void __i915_active_init(struct drm_i915_private *i915,
 	ref->flags = 0;
 	ref->active = active;
 	ref->retire = retire;
+
+	ref->excl = NULL;
 	ref->tree = RB_ROOT;
 	ref->cache = NULL;
 	init_llist_head(&ref->preallocated_barriers);
@@ -341,6 +344,46 @@ out:
 	return err;
 }
 
+static void excl_cb(struct dma_fence *f, struct dma_fence_cb *cb)
+{
+	struct i915_active *ref = container_of(cb, typeof(*ref), excl_cb);
+
+	RCU_INIT_POINTER(ref->excl, NULL);
+	dma_fence_put(f);
+
+	active_retire(ref);
+}
+
+void i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f)
+{
+	/* We expect the caller to manage the exclusive timeline ordering */
+	GEM_BUG_ON(i915_active_is_idle(ref));
+
+	dma_fence_get(f);
+
+	rcu_read_lock();
+	if (rcu_access_pointer(ref->excl)) {
+		struct dma_fence *old;
+
+		old = dma_fence_get_rcu_safe(&ref->excl);
+		if (old) {
+			if (dma_fence_remove_callback(old, &ref->excl_cb))
+				atomic_dec(&ref->count);
+			dma_fence_put(old);
+		}
+	}
+	rcu_read_unlock();
+
+	atomic_inc(&ref->count);
+	rcu_assign_pointer(ref->excl, f);
+
+	if (dma_fence_add_callback(f, &ref->excl_cb, excl_cb)) {
+		RCU_INIT_POINTER(ref->excl, NULL);
+		atomic_dec(&ref->count);
+		dma_fence_put(f);
+	}
+}
+
 int i915_active_acquire(struct i915_active *ref)
 {
 	int err;
@@ -399,6 +442,25 @@ void i915_active_ungrab(struct i915_active *ref)
 	__active_ungrab(ref);
 }
 
+static int excl_wait(struct i915_active *ref)
+{
+	struct dma_fence *old;
+	int err = 0;
+
+	if (!rcu_access_pointer(ref->excl))
+		return 0;
+
+	rcu_read_lock();
+	old = dma_fence_get_rcu_safe(&ref->excl);
+	rcu_read_unlock();
+	if (old) {
+		err = dma_fence_wait(old, true);
+		dma_fence_put(old);
+	}
+
+	return err;
+}
+
 int i915_active_wait(struct i915_active *ref)
 {
 	struct active_node *it, *n;
@@ -419,6 +481,10 @@ int i915_active_wait(struct i915_active *ref)
 		return 0;
 	}
 
+	err = excl_wait(ref);
+	if (err)
+		goto out;
+
 	rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
 		if (is_barrier(&it->base)) { /* unconnected idle-barrier */
 			err = -EBUSY;
@@ -430,6 +496,7 @@ int i915_active_wait(struct i915_active *ref)
 			break;
 	}
 
+out:
 	__active_retire(ref);
 	if (err)
 		return err;
@@ -454,26 +521,22 @@ int i915_request_await_active_request(struct i915_request *rq,
 
 int i915_request_await_active(struct i915_request *rq, struct i915_active *ref)
 {
-	struct active_node *it, *n;
-	int err;
-
-	if (RB_EMPTY_ROOT(&ref->tree))
-		return 0;
+	int err = 0;
 
-	/* await allocates and so we need to avoid hitting the shrinker */
-	err = i915_active_acquire(ref);
-	if (err)
-		return err;
+	if (rcu_access_pointer(ref->excl)) {
+		struct dma_fence *fence;
 
-	mutex_lock(&ref->mutex);
-	rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
-		err = i915_request_await_active_request(rq, &it->base);
-		if (err)
-			break;
+		rcu_read_lock();
+		fence = dma_fence_get_rcu_safe(&ref->excl);
+		rcu_read_unlock();
+		if (fence) {
+			err = i915_request_await_dma_fence(rq, fence);
+			dma_fence_put(fence);
+		}
 	}
-	mutex_unlock(&ref->mutex);
 
-	i915_active_release(ref);
+	/* In the future we may choose to await on all fences */
+
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index 949c6835335b..90034f61b7c2 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -379,6 +379,13 @@ i915_active_add_request(struct i915_active *ref, struct i915_request *rq)
 	return i915_active_ref(ref, i915_request_timeline(rq), rq);
 }
 
+void i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f);
+
+static inline bool i915_active_has_exclusive(struct i915_active *ref)
+{
+	return rcu_access_pointer(ref->excl);
+}
+
 int i915_active_wait(struct i915_active *ref);
 
 int i915_request_await_active(struct i915_request *rq,
diff --git a/drivers/gpu/drm/i915/i915_active_types.h b/drivers/gpu/drm/i915/i915_active_types.h
index 1854e7d168c1..86e7a232ea3c 100644
--- a/drivers/gpu/drm/i915/i915_active_types.h
+++ b/drivers/gpu/drm/i915/i915_active_types.h
@@ -8,6 +8,7 @@
 #define _I915_ACTIVE_TYPES_H_
 
 #include <linux/atomic.h>
+#include <linux/dma-fence.h>
 #include <linux/llist.h>
 #include <linux/mutex.h>
 #include <linux/rbtree.h>
@@ -51,6 +52,10 @@ struct i915_active {
 	struct mutex mutex;
 	atomic_t count;
 
+	/* Preallocated "exclusive" node */
+	struct dma_fence __rcu *excl;
+	struct dma_fence_cb excl_cb;
+
 	unsigned long flags;
 #define I915_ACTIVE_GRAB_BIT 0
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 1d2246c59cde..b711324ca294 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1895,10 +1895,8 @@ static int i915_drm_resume(struct drm_device *dev)
 	if (ret)
 		DRM_ERROR("failed to re-enable GGTT\n");
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	i915_gem_restore_gtt_mappings(dev_priv);
 	i915_gem_restore_fences(dev_priv);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	intel_csr_ucode_resume(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index fa8e028ac0b5..fc5c618f6c19 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -62,20 +62,31 @@
 #include "intel_pm.h"
 
 static int
-insert_mappable_node(struct i915_ggtt *ggtt,
-                     struct drm_mm_node *node, u32 size)
+insert_mappable_node(struct i915_ggtt *ggtt, struct drm_mm_node *node, u32 size)
 {
+	int err;
+
+	err = mutex_lock_interruptible(&ggtt->vm.mutex);
+	if (err)
+		return err;
+
 	memset(node, 0, sizeof(*node));
-	return drm_mm_insert_node_in_range(&ggtt->vm.mm, node,
-					   size, 0, I915_COLOR_UNEVICTABLE,
-					   0, ggtt->mappable_end,
-					   DRM_MM_INSERT_LOW);
+	err = drm_mm_insert_node_in_range(&ggtt->vm.mm, node,
+					  size, 0, I915_COLOR_UNEVICTABLE,
+					  0, ggtt->mappable_end,
+					  DRM_MM_INSERT_LOW);
+
+	mutex_unlock(&ggtt->vm.mutex);
+
+	return err;
 }
 
 static void
-remove_mappable_node(struct drm_mm_node *node)
+remove_mappable_node(struct i915_ggtt *ggtt, struct drm_mm_node *node)
 {
+	mutex_lock(&ggtt->vm.mutex);
 	drm_mm_remove_node(node);
+	mutex_unlock(&ggtt->vm.mutex);
 }
 
 int
@@ -87,7 +98,8 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 	struct i915_vma *vma;
 	u64 pinned;
 
-	mutex_lock(&ggtt->vm.mutex);
+	if (mutex_lock_interruptible(&ggtt->vm.mutex))
+		return -EINTR;
 
 	pinned = ggtt->vm.reserved;
 	list_for_each_entry(vma, &ggtt->vm.bound_list, vm_link)
@@ -109,20 +121,24 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 	LIST_HEAD(still_in_list);
 	int ret = 0;
 
-	lockdep_assert_held(&obj->base.dev->struct_mutex);
-
 	spin_lock(&obj->vma.lock);
 	while (!ret && (vma = list_first_entry_or_null(&obj->vma.list,
 						       struct i915_vma,
 						       obj_link))) {
+		struct i915_address_space *vm = vma->vm;
+
+		ret = -EBUSY;
+		if (!i915_vm_tryopen(vm))
+			break;
+
 		list_move_tail(&vma->obj_link, &still_in_list);
 		spin_unlock(&obj->vma.lock);
 
-		ret = -EBUSY;
 		if (flags & I915_GEM_OBJECT_UNBIND_ACTIVE ||
 		    !i915_vma_is_active(vma))
 			ret = i915_vma_unbind(vma);
 
+		i915_vm_close(vm);
 		spin_lock(&obj->vma.lock);
 	}
 	list_splice(&still_in_list, &obj->vma.list);
@@ -338,10 +354,6 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 	u64 remain, offset;
 	int ret;
 
-	ret = mutex_lock_interruptible(&i915->drm.struct_mutex);
-	if (ret)
-		return ret;
-
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 	vma = ERR_PTR(-ENODEV);
 	if (!i915_gem_object_is_tiled(obj))
@@ -355,12 +367,10 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 	} else {
 		ret = insert_mappable_node(ggtt, &node, PAGE_SIZE);
 		if (ret)
-			goto out_unlock;
+			goto out_rpm;
 		GEM_BUG_ON(!drm_mm_node_allocated(&node));
 	}
 
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	ret = i915_gem_object_lock_interruptible(obj);
 	if (ret)
 		goto out_unpin;
@@ -414,17 +424,14 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 
 	i915_gem_object_unlock_fence(obj, fence);
 out_unpin:
-	mutex_lock(&i915->drm.struct_mutex);
 	if (drm_mm_node_allocated(&node)) {
 		ggtt->vm.clear_range(&ggtt->vm, node.start, node.size);
-		remove_mappable_node(&node);
+		remove_mappable_node(ggtt, &node);
 	} else {
 		i915_vma_unpin(vma);
 	}
-out_unlock:
+out_rpm:
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	return ret;
 }
 
@@ -531,10 +538,6 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 	void __user *user_data;
 	int ret;
 
-	ret = mutex_lock_interruptible(&i915->drm.struct_mutex);
-	if (ret)
-		return ret;
-
 	if (i915_gem_object_has_struct_page(obj)) {
 		/*
 		 * Avoid waking the device up if we can fallback, as
@@ -544,10 +547,8 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		 * using the cache bypass of indirect GGTT access.
 		 */
 		wakeref = intel_runtime_pm_get_if_in_use(rpm);
-		if (!wakeref) {
-			ret = -EFAULT;
-			goto out_unlock;
-		}
+		if (!wakeref)
+			return -EFAULT;
 	} else {
 		/* No backing pages, no fallback, we must force GGTT access */
 		wakeref = intel_runtime_pm_get(rpm);
@@ -569,8 +570,6 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		GEM_BUG_ON(!drm_mm_node_allocated(&node));
 	}
 
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	ret = i915_gem_object_lock_interruptible(obj);
 	if (ret)
 		goto out_unpin;
@@ -634,18 +633,15 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 
 	i915_gem_object_unlock_fence(obj, fence);
 out_unpin:
-	mutex_lock(&i915->drm.struct_mutex);
 	intel_gt_flush_ggtt_writes(ggtt->vm.gt);
 	if (drm_mm_node_allocated(&node)) {
 		ggtt->vm.clear_range(&ggtt->vm, node.start, node.size);
-		remove_mappable_node(&node);
+		remove_mappable_node(ggtt, &node);
 	} else {
 		i915_vma_unpin(vma);
 	}
 out_rpm:
 	intel_runtime_pm_put(rpm, wakeref);
-out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
 	return ret;
 }
 
@@ -968,8 +964,6 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 	struct i915_vma *vma;
 	int ret;
 
-	lockdep_assert_held(&obj->base.dev->struct_mutex);
-
 	if (i915_gem_object_never_bind_ggtt(obj))
 		return ERR_PTR(-ENODEV);
 
@@ -1019,13 +1013,6 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 				return ERR_PTR(-ENOSPC);
 		}
 
-		WARN(i915_vma_is_pinned(vma),
-		     "bo is already pinned in ggtt with incorrect alignment:"
-		     " offset=%08x, req.alignment=%llx,"
-		     " req.map_and_fenceable=%d, vma->map_and_fenceable=%d\n",
-		     i915_ggtt_offset(vma), alignment,
-		     !!(flags & PIN_MAPPABLE),
-		     i915_vma_is_map_and_fenceable(vma));
 		ret = i915_vma_unbind(vma);
 		if (ret)
 			return ERR_PTR(ret);
@@ -1444,8 +1431,6 @@ err_unlock:
 	}
 
 	if (ret == -EIO) {
-		mutex_lock(&dev_priv->drm.struct_mutex);
-
 		/*
 		 * Allow engines or uC initialisation to fail by marking the GPU
 		 * as wedged. But we only want to do this when the GPU is angry,
@@ -1462,8 +1447,6 @@ err_unlock:
 		i915_gem_restore_gtt_mappings(dev_priv);
 		i915_gem_restore_fences(dev_priv);
 		intel_init_clock_gating(dev_priv);
-
-		mutex_unlock(&dev_priv->drm.struct_mutex);
 	}
 
 	i915_gem_drain_freed_objects(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 8c1e04f402bc..0552bf93eea3 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -47,8 +47,7 @@ static int ggtt_flush(struct drm_i915_private *i915)
 	 * bound by their active reference.
 	 */
 	return i915_gem_wait_for_idle(i915,
-				      I915_WAIT_INTERRUPTIBLE |
-				      I915_WAIT_LOCKED,
+				      I915_WAIT_INTERRUPTIBLE,
 				      MAX_SCHEDULE_TIMEOUT);
 }
 
@@ -104,7 +103,7 @@ i915_gem_evict_something(struct i915_address_space *vm,
 	struct i915_vma *active;
 	int ret;
 
-	lockdep_assert_held(&vm->i915->drm.struct_mutex);
+	lockdep_assert_held(&vm->mutex);
 	trace_i915_gem_evict(vm, min_size, alignment, flags);
 
 	/*
@@ -127,15 +126,6 @@ i915_gem_evict_something(struct i915_address_space *vm,
 				    min_size, alignment, color,
 				    start, end, mode);
 
-	/*
-	 * Retire before we search the active list. Although we have
-	 * reasonable accuracy in our retirement lists, we may have
-	 * a stray pin (preventing eviction) that can only be resolved by
-	 * retiring.
-	 */
-	if (!(flags & PIN_NONBLOCK))
-		i915_retire_requests(dev_priv);
-
 search_again:
 	active = NULL;
 	INIT_LIST_HEAD(&eviction_list);
@@ -235,12 +225,12 @@ found:
 	list_for_each_entry_safe(vma, next, &eviction_list, evict_link) {
 		__i915_vma_unpin(vma);
 		if (ret == 0)
-			ret = i915_vma_unbind(vma);
+			ret = __i915_vma_unbind(vma);
 	}
 
 	while (ret == 0 && (node = drm_mm_scan_color_evict(&scan))) {
 		vma = container_of(node, struct i915_vma, node);
-		ret = i915_vma_unbind(vma);
+		ret = __i915_vma_unbind(vma);
 	}
 
 	return ret;
@@ -268,7 +258,7 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 	struct i915_vma *vma, *next;
 	int ret = 0;
 
-	lockdep_assert_held(&vm->i915->drm.struct_mutex);
+	lockdep_assert_held(&vm->mutex);
 	GEM_BUG_ON(!IS_ALIGNED(start, I915_GTT_PAGE_SIZE));
 	GEM_BUG_ON(!IS_ALIGNED(end, I915_GTT_PAGE_SIZE));
 
@@ -349,7 +339,7 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 	list_for_each_entry_safe(vma, next, &eviction_list, evict_link) {
 		__i915_vma_unpin(vma);
 		if (ret == 0)
-			ret = i915_vma_unbind(vma);
+			ret = __i915_vma_unbind(vma);
 	}
 
 	return ret;
@@ -373,7 +363,7 @@ int i915_gem_evict_vm(struct i915_address_space *vm)
 	struct i915_vma *vma, *next;
 	int ret;
 
-	lockdep_assert_held(&vm->i915->drm.struct_mutex);
+	lockdep_assert_held(&vm->mutex);
 	trace_i915_gem_evict_vm(vm);
 
 	/* Switch back to the default context in order to unpin
@@ -388,7 +378,6 @@ int i915_gem_evict_vm(struct i915_address_space *vm)
 	}
 
 	INIT_LIST_HEAD(&eviction_list);
-	mutex_lock(&vm->mutex);
 	list_for_each_entry(vma, &vm->bound_list, vm_link) {
 		if (i915_vma_is_pinned(vma))
 			continue;
@@ -396,13 +385,12 @@ int i915_gem_evict_vm(struct i915_address_space *vm)
 		__i915_vma_pin(vma);
 		list_add(&vma->evict_link, &eviction_list);
 	}
-	mutex_unlock(&vm->mutex);
 
 	ret = 0;
 	list_for_each_entry_safe(vma, next, &eviction_list, evict_link) {
 		__i915_vma_unpin(vma);
 		if (ret == 0)
-			ret = i915_vma_unbind(vma);
+			ret = __i915_vma_unbind(vma);
 	}
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
index 615a9f4ef30c..487b7261f7ed 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
@@ -230,14 +230,15 @@ static int fence_update(struct i915_fence_reg *fence,
 			 i915_gem_object_get_tiling(vma->obj)))
 			return -EINVAL;
 
-		ret = i915_active_wait(&vma->active);
+		ret = i915_vma_sync(vma);
 		if (ret)
 			return ret;
 	}
 
 	old = xchg(&fence->vma, NULL);
 	if (old) {
-		ret = i915_active_wait(&old->active);
+		/* XXX Ideally we would move the waiting to outside the mutex */
+		ret = i915_vma_sync(old);
 		if (ret) {
 			fence->vma = old;
 			return ret;
@@ -331,13 +332,15 @@ static struct i915_fence_reg *fence_find(struct drm_i915_private *i915)
 	return ERR_PTR(-EDEADLK);
 }
 
-static int __i915_vma_pin_fence(struct i915_vma *vma)
+int __i915_vma_pin_fence(struct i915_vma *vma)
 {
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vma->vm);
 	struct i915_fence_reg *fence;
 	struct i915_vma *set = i915_gem_object_is_tiled(vma->obj) ? vma : NULL;
 	int err;
 
+	lockdep_assert_held(&vma->vm->mutex);
+
 	/* Just update our place in the LRU if our fence is getting reused. */
 	if (vma->fence) {
 		fence = vma->fence;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 8eba63ecdb03..55cebf256d03 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -150,16 +150,18 @@ static void gmch_ggtt_invalidate(struct i915_ggtt *ggtt)
 
 static int ppgtt_bind_vma(struct i915_vma *vma,
 			  enum i915_cache_level cache_level,
-			  u32 unused)
+			  u32 flags)
 {
 	u32 pte_flags;
 	int err;
 
-	if (!i915_vma_is_bound(vma, I915_VMA_LOCAL_BIND)) {
+	if (flags & I915_VMA_ALLOC) {
 		err = vma->vm->allocate_va_range(vma->vm,
 						 vma->node.start, vma->size);
 		if (err)
 			return err;
+
+		set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
 	}
 
 	/* Applicable to VLV, and gen8+ */
@@ -167,6 +169,7 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
 	if (i915_gem_object_is_readonly(vma->obj))
 		pte_flags |= PTE_READ_ONLY;
 
+	GEM_BUG_ON(!test_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma)));
 	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
 	wmb();
 
@@ -175,7 +178,8 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
 
 static void ppgtt_unbind_vma(struct i915_vma *vma)
 {
-	vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
+	if (test_and_clear_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma)))
+		vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
 }
 
 static int ppgtt_set_pages(struct i915_vma *vma)
@@ -503,15 +507,26 @@ static void i915_address_space_fini(struct i915_address_space *vm)
 	mutex_destroy(&vm->mutex);
 }
 
-static void ppgtt_destroy_vma(struct i915_address_space *vm)
+void __i915_vm_close(struct i915_address_space *vm)
 {
 	struct i915_vma *vma, *vn;
 
-	mutex_lock(&vm->i915->drm.struct_mutex);
-	list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link)
+	mutex_lock(&vm->mutex);
+	list_for_each_entry_safe(vma, vn, &vm->bound_list, vm_link) {
+		struct drm_i915_gem_object *obj = vma->obj;
+
+		/* Keep the obj (and hence the vma) alive as _we_ destroy it */
+		if (!kref_get_unless_zero(&obj->base.refcount))
+			continue;
+
+		atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
+		WARN_ON(__i915_vma_unbind(vma));
 		i915_vma_destroy(vma);
+
+		i915_gem_object_put(obj);
+	}
 	GEM_BUG_ON(!list_empty(&vm->bound_list));
-	mutex_unlock(&vm->i915->drm.struct_mutex);
+	mutex_unlock(&vm->mutex);
 }
 
 static void __i915_vm_release(struct work_struct *work)
@@ -519,8 +534,6 @@ static void __i915_vm_release(struct work_struct *work)
 	struct i915_address_space *vm =
 		container_of(work, struct i915_address_space, rcu.work);
 
-	ppgtt_destroy_vma(vm);
-
 	vm->cleanup(vm);
 	i915_address_space_fini(vm);
 
@@ -535,7 +548,6 @@ void i915_vm_release(struct kref *kref)
 	GEM_BUG_ON(i915_is_ggtt(vm));
 	trace_i915_ppgtt_release(vm);
 
-	vm->closed = true;
 	queue_rcu_work(vm->i915->wq, &vm->rcu);
 }
 
@@ -543,6 +555,7 @@ static void i915_address_space_init(struct i915_address_space *vm, int subclass)
 {
 	kref_init(&vm->ref);
 	INIT_RCU_WORK(&vm->rcu, __i915_vm_release);
+	atomic_set(&vm->open, 1);
 
 	/*
 	 * The vm->mutex must be reclaim safe (for use in the shrinker).
@@ -1771,12 +1784,8 @@ static void gen6_ppgtt_free_pd(struct gen6_ppgtt *ppgtt)
 static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 {
 	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
-	struct drm_i915_private *i915 = vm->i915;
 
-	/* FIXME remove the struct_mutex to bring the locking under control */
-	mutex_lock(&i915->drm.struct_mutex);
 	i915_vma_destroy(ppgtt->vma);
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	gen6_ppgtt_free_pd(ppgtt);
 	free_scratch(vm);
@@ -1865,7 +1874,8 @@ static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
 
 	i915_active_init(i915, &vma->active, NULL, NULL);
 
-	vma->vm = &ggtt->vm;
+	mutex_init(&vma->pages_mutex);
+	vma->vm = i915_vm_get(&ggtt->vm);
 	vma->ops = &pd_vma_ops;
 	vma->private = ppgtt;
 
@@ -1885,7 +1895,7 @@ int gen6_ppgtt_pin(struct i915_ppgtt *base)
 	struct gen6_ppgtt *ppgtt = to_gen6_ppgtt(base);
 	int err = 0;
 
-	GEM_BUG_ON(ppgtt->base.vm.closed);
+	GEM_BUG_ON(!atomic_read(&ppgtt->base.vm.open));
 
 	/*
 	 * Workaround the limited maximum vma->pin_count and the aliasing_ppgtt
@@ -2463,14 +2473,18 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 	if (flags & I915_VMA_LOCAL_BIND) {
 		struct i915_ppgtt *alias = i915_vm_to_ggtt(vma->vm)->alias;
 
-		if (!i915_vma_is_bound(vma, I915_VMA_LOCAL_BIND)) {
+		if (flags & I915_VMA_ALLOC) {
 			ret = alias->vm.allocate_va_range(&alias->vm,
 							  vma->node.start,
 							  vma->size);
 			if (ret)
 				return ret;
+
+			set_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma));
 		}
 
+		GEM_BUG_ON(!test_bit(I915_VMA_ALLOC_BIT,
+				     __i915_vma_flags(vma)));
 		alias->vm.insert_entries(&alias->vm, vma,
 					 cache_level, pte_flags);
 	}
@@ -2499,7 +2513,7 @@ static void aliasing_gtt_unbind_vma(struct i915_vma *vma)
 			vm->clear_range(vm, vma->node.start, vma->size);
 	}
 
-	if (i915_vma_is_bound(vma, I915_VMA_LOCAL_BIND)) {
+	if (test_and_clear_bit(I915_VMA_ALLOC_BIT, __i915_vma_flags(vma))) {
 		struct i915_address_space *vm =
 			&i915_vm_to_ggtt(vma->vm)->alias->vm;
 
@@ -2602,22 +2616,16 @@ err_ppgtt:
 
 static void fini_aliasing_ppgtt(struct i915_ggtt *ggtt)
 {
-	struct drm_i915_private *i915 = ggtt->vm.i915;
 	struct i915_ppgtt *ppgtt;
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	ppgtt = fetch_and_zero(&ggtt->alias);
 	if (!ppgtt)
-		goto out;
+		return;
 
 	i915_vm_put(&ppgtt->vm);
 
 	ggtt->vm.vma_ops.bind_vma   = ggtt_bind_vma;
 	ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma;
-
-out:
-	mutex_unlock(&i915->drm.struct_mutex);
 }
 
 static int ggtt_reserve_guc_top(struct i915_ggtt *ggtt)
@@ -2734,32 +2742,28 @@ int i915_init_ggtt(struct drm_i915_private *i915)
 
 static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
 {
-	struct drm_i915_private *i915 = ggtt->vm.i915;
 	struct i915_vma *vma, *vn;
 
-	ggtt->vm.closed = true;
+	atomic_set(&ggtt->vm.open, 0);
 
 	rcu_barrier(); /* flush the RCU'ed__i915_vm_release */
-	flush_workqueue(i915->wq);
+	flush_workqueue(ggtt->vm.i915->wq);
 
-	mutex_lock(&i915->drm.struct_mutex);
+	mutex_lock(&ggtt->vm.mutex);
 
 	list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link)
-		WARN_ON(i915_vma_unbind(vma));
+		WARN_ON(__i915_vma_unbind(vma));
 
 	if (drm_mm_node_allocated(&ggtt->error_capture))
 		drm_mm_remove_node(&ggtt->error_capture);
 
 	ggtt_release_guc_top(ggtt);
-
-	if (drm_mm_initialized(&ggtt->vm.mm)) {
-		intel_vgt_deballoon(ggtt);
-		i915_address_space_fini(&ggtt->vm);
-	}
+	intel_vgt_deballoon(ggtt);
 
 	ggtt->vm.cleanup(&ggtt->vm);
 
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_unlock(&ggtt->vm.mutex);
+	i915_address_space_fini(&ggtt->vm);
 
 	arch_phys_wc_del(ggtt->mtrr);
 	io_mapping_fini(&ggtt->iomap);
@@ -3188,9 +3192,6 @@ int i915_ggtt_probe_hw(struct drm_i915_private *i915)
 static int ggtt_init_hw(struct i915_ggtt *ggtt)
 {
 	struct drm_i915_private *i915 = ggtt->vm.i915;
-	int ret = 0;
-
-	mutex_lock(&i915->drm.struct_mutex);
 
 	i915_address_space_init(&ggtt->vm, VM_CLASS_GGTT);
 
@@ -3206,18 +3207,14 @@ static int ggtt_init_hw(struct i915_ggtt *ggtt)
 				ggtt->gmadr.start,
 				ggtt->mappable_end)) {
 		ggtt->vm.cleanup(&ggtt->vm);
-		ret = -EIO;
-		goto out;
+		return -EIO;
 	}
 
 	ggtt->mtrr = arch_phys_wc_add(ggtt->gmadr.start, ggtt->mappable_end);
 
 	i915_ggtt_init_fences(ggtt);
 
-out:
-	mutex_unlock(&i915->drm.struct_mutex);
-
-	return ret;
+	return 0;
 }
 
 /**
@@ -3289,6 +3286,7 @@ static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
 {
 	struct i915_vma *vma, *vn;
 	bool flush = false;
+	int open;
 
 	intel_gt_check_and_clear_faults(ggtt->vm.gt);
 
@@ -3296,7 +3294,9 @@ static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
 
 	/* First fill our portion of the GTT with scratch pages */
 	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
-	ggtt->vm.closed = true; /* skip rewriting PTE on VMA unbind */
+
+	/* Skip rewriting PTE on VMA unbind. */
+	open = atomic_xchg(&ggtt->vm.open, 0);
 
 	/* clflush objects bound into the GGTT and rebind them. */
 	list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link) {
@@ -3305,24 +3305,20 @@ static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
 		if (!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
 			continue;
 
-		mutex_unlock(&ggtt->vm.mutex);
-
-		if (!i915_vma_unbind(vma))
-			goto lock;
+		if (!__i915_vma_unbind(vma))
+			continue;
 
+		clear_bit(I915_VMA_GLOBAL_BIND_BIT, __i915_vma_flags(vma));
 		WARN_ON(i915_vma_bind(vma,
 				      obj ? obj->cache_level : 0,
-				      PIN_UPDATE));
+				      PIN_GLOBAL, NULL));
 		if (obj) { /* only used during resume => exclusive access */
 			flush |= fetch_and_zero(&obj->write_domain);
 			obj->read_domains |= I915_GEM_DOMAIN_GTT;
 		}
-
-lock:
-		mutex_lock(&ggtt->vm.mutex);
 	}
 
-	ggtt->vm.closed = false;
+	atomic_set(&ggtt->vm.open, open);
 	ggtt->invalidate(ggtt);
 
 	mutex_unlock(&ggtt->vm.mutex);
@@ -3714,7 +3710,8 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 	u64 offset;
 	int err;
 
-	lockdep_assert_held(&vm->i915->drm.struct_mutex);
+	lockdep_assert_held(&vm->mutex);
+
 	GEM_BUG_ON(!size);
 	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE));
 	GEM_BUG_ON(alignment && !is_power_of_2(alignment));
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 3502b9c85a8e..0a18fdfe63ff 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -307,7 +307,14 @@ struct i915_address_space {
 
 	unsigned int bind_async_flags;
 
-	bool closed;
+	/*
+	 * Each active user context has its own address space (in full-ppgtt).
+	 * Since the vm may be shared between multiple contexts, we count how
+	 * many contexts keep us "open". Once open hits zero, we are closed
+	 * and do not allow any new attachments, and proceed to shutdown our
+	 * vma and page directories.
+	 */
+	atomic_t open;
 
 	struct mutex mutex; /* protects vma and our lists */
 #define VM_CLASS_GGTT 0
@@ -581,6 +588,35 @@ static inline void i915_vm_put(struct i915_address_space *vm)
 	kref_put(&vm->ref, i915_vm_release);
 }
 
+static inline struct i915_address_space *
+i915_vm_open(struct i915_address_space *vm)
+{
+	GEM_BUG_ON(!atomic_read(&vm->open));
+	atomic_inc(&vm->open);
+	return i915_vm_get(vm);
+}
+
+static inline bool
+i915_vm_tryopen(struct i915_address_space *vm)
+{
+	if (atomic_add_unless(&vm->open, 1, 0))
+		return i915_vm_get(vm);
+
+	return false;
+}
+
+void __i915_vm_close(struct i915_address_space *vm);
+
+static inline void
+i915_vm_close(struct i915_address_space *vm)
+{
+	GEM_BUG_ON(!atomic_read(&vm->open));
+	if (atomic_dec_and_test(&vm->open))
+		__i915_vm_close(vm);
+
+	i915_vm_put(vm);
+}
+
 int gen6_ppgtt_pin(struct i915_ppgtt *base);
 void gen6_ppgtt_unpin(struct i915_ppgtt *base);
 void gen6_ppgtt_unpin_all(struct i915_ppgtt *base);
@@ -613,10 +649,9 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 #define PIN_OFFSET_BIAS		BIT_ULL(6)
 #define PIN_OFFSET_FIXED	BIT_ULL(7)
 
-#define PIN_MBZ			BIT_ULL(8) /* I915_VMA_PIN_OVERFLOW */
-#define PIN_GLOBAL		BIT_ULL(9) /* I915_VMA_GLOBAL_BIND */
-#define PIN_USER		BIT_ULL(10) /* I915_VMA_LOCAL_BIND */
-#define PIN_UPDATE		BIT_ULL(11)
+#define PIN_UPDATE		BIT_ULL(9)
+#define PIN_GLOBAL		BIT_ULL(10) /* I915_VMA_GLOBAL_BIND */
+#define PIN_USER		BIT_ULL(11) /* I915_VMA_LOCAL_BIND */
 
 #define PIN_OFFSET_MASK		(-I915_GTT_PAGE_SIZE)
 
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 524f6710b7aa..80055501eccb 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1204,15 +1204,10 @@ static int i915_oa_read(struct i915_perf_stream *stream,
 static struct intel_context *oa_pin_context(struct i915_perf_stream *stream)
 {
 	struct i915_gem_engines_iter it;
-	struct drm_i915_private *i915 = stream->dev_priv;
 	struct i915_gem_context *ctx = stream->ctx;
 	struct intel_context *ce;
 	int err;
 
-	err = i915_mutex_lock_interruptible(&i915->drm);
-	if (err)
-		return ERR_PTR(err);
-
 	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
 		if (ce->engine->class != RENDER_CLASS)
 			continue;
@@ -1229,10 +1224,6 @@ static struct intel_context *oa_pin_context(struct i915_perf_stream *stream)
 	}
 	i915_gem_context_unlock_engines(ctx);
 
-	mutex_unlock(&i915->drm.struct_mutex);
-	if (err)
-		return ERR_PTR(err);
-
 	return stream->pinned_ctx;
 }
 
@@ -1331,32 +1322,22 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
  */
 static void oa_put_render_ctx_id(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
 	struct intel_context *ce;
 
 	stream->specific_ctx_id = INVALID_CTX_ID;
 	stream->specific_ctx_id_mask = 0;
 
 	ce = fetch_and_zero(&stream->pinned_ctx);
-	if (ce) {
-		mutex_lock(&dev_priv->drm.struct_mutex);
+	if (ce)
 		intel_context_unpin(ce);
-		mutex_unlock(&dev_priv->drm.struct_mutex);
-	}
 }
 
 static void
 free_oa_buffer(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *i915 = stream->dev_priv;
-
-	mutex_lock(&i915->drm.struct_mutex);
-
 	i915_vma_unpin_and_release(&stream->oa_buffer.vma,
 				   I915_VMA_RELEASE_MAP);
 
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	stream->oa_buffer.vaddr = NULL;
 }
 
@@ -1511,18 +1492,13 @@ static int alloc_oa_buffer(struct i915_perf_stream *stream)
 	if (WARN_ON(stream->oa_buffer.vma))
 		return -ENODEV;
 
-	ret = i915_mutex_lock_interruptible(&dev_priv->drm);
-	if (ret)
-		return ret;
-
 	BUILD_BUG_ON_NOT_POWER_OF_2(OA_BUFFER_SIZE);
 	BUILD_BUG_ON(OA_BUFFER_SIZE < SZ_128K || OA_BUFFER_SIZE > SZ_16M);
 
 	bo = i915_gem_object_create_shmem(dev_priv, OA_BUFFER_SIZE);
 	if (IS_ERR(bo)) {
 		DRM_ERROR("Failed to allocate OA buffer\n");
-		ret = PTR_ERR(bo);
-		goto unlock;
+		return PTR_ERR(bo);
 	}
 
 	i915_gem_object_set_cache_coherency(bo, I915_CACHE_LLC);
@@ -1546,7 +1522,7 @@ static int alloc_oa_buffer(struct i915_perf_stream *stream)
 			 i915_ggtt_offset(stream->oa_buffer.vma),
 			 stream->oa_buffer.vaddr);
 
-	goto unlock;
+	return 0;
 
 err_unpin:
 	__i915_vma_unpin(vma);
@@ -1557,8 +1533,6 @@ err_unref:
 	stream->oa_buffer.vaddr = NULL;
 	stream->oa_buffer.vma = NULL;
 
-unlock:
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index d097f77890ba..fe91a0e47b88 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -32,6 +32,7 @@
 
 #include "i915_drv.h"
 #include "i915_globals.h"
+#include "i915_sw_fence_work.h"
 #include "i915_trace.h"
 #include "i915_vma.h"
 
@@ -110,7 +111,8 @@ vma_create(struct drm_i915_gem_object *obj,
 	if (vma == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	vma->vm = vm;
+	mutex_init(&vma->pages_mutex);
+	vma->vm = i915_vm_get(vm);
 	vma->ops = &vm->vma_ops;
 	vma->obj = obj;
 	vma->resv = obj->base.resv;
@@ -261,8 +263,6 @@ vma_lookup(struct drm_i915_gem_object *obj,
  * Once created, the VMA is kept until either the object is freed, or the
  * address space is closed.
  *
- * Must be called with struct_mutex held.
- *
  * Returns the vma, or an error pointer.
  */
 struct i915_vma *
@@ -273,7 +273,7 @@ i915_vma_instance(struct drm_i915_gem_object *obj,
 	struct i915_vma *vma;
 
 	GEM_BUG_ON(view && !i915_is_ggtt(vm));
-	GEM_BUG_ON(vm->closed);
+	GEM_BUG_ON(!atomic_read(&vm->open));
 
 	spin_lock(&obj->vma.lock);
 	vma = vma_lookup(obj, vm, view);
@@ -287,18 +287,63 @@ i915_vma_instance(struct drm_i915_gem_object *obj,
 	return vma;
 }
 
+struct i915_vma_work {
+	struct dma_fence_work base;
+	struct i915_vma *vma;
+	enum i915_cache_level cache_level;
+	unsigned int flags;
+};
+
+static int __vma_bind(struct dma_fence_work *work)
+{
+	struct i915_vma_work *vw = container_of(work, typeof(*vw), base);
+	struct i915_vma *vma = vw->vma;
+	int err;
+
+	err = vma->ops->bind_vma(vma, vw->cache_level, vw->flags);
+	if (err)
+		atomic_or(I915_VMA_ERROR, &vma->flags);
+
+	if (vma->obj)
+		__i915_gem_object_unpin_pages(vma->obj);
+
+	return err;
+}
+
+static const struct dma_fence_work_ops bind_ops = {
+	.name = "bind",
+	.work = __vma_bind,
+};
+
+struct i915_vma_work *i915_vma_work(void)
+{
+	struct i915_vma_work *vw;
+
+	vw = kzalloc(sizeof(*vw), GFP_KERNEL);
+	if (!vw)
+		return NULL;
+
+	dma_fence_work_init(&vw->base, &bind_ops);
+	vw->base.dma.error = -EAGAIN; /* disable the worker by default */
+
+	return vw;
+}
+
 /**
  * i915_vma_bind - Sets up PTEs for an VMA in it's corresponding address space.
  * @vma: VMA to map
  * @cache_level: mapping cache level
  * @flags: flags like global or local mapping
+ * @work: preallocated worker for allocating and binding the PTE
  *
  * DMA addresses are taken from the scatter-gather table of this object (or of
  * this VMA in case of non-default GGTT views) and PTE entries set up.
  * Note that DMA addresses are also the only part of the SG table we care about.
  */
-int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
-		  u32 flags)
+int i915_vma_bind(struct i915_vma *vma,
+		  enum i915_cache_level cache_level,
+		  u32 flags,
+		  struct i915_vma_work *work)
 {
 	u32 bind_flags;
 	u32 vma_flags;
@@ -315,11 +360,8 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 	if (GEM_DEBUG_WARN_ON(!flags))
 		return -EINVAL;
 
-	bind_flags = 0;
-	if (flags & PIN_GLOBAL)
-		bind_flags |= I915_VMA_GLOBAL_BIND;
-	if (flags & PIN_USER)
-		bind_flags |= I915_VMA_LOCAL_BIND;
+	bind_flags = flags;
+	bind_flags &= I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
 
 	vma_flags = atomic_read(&vma->flags);
 	vma_flags &= I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
@@ -333,9 +375,32 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 	GEM_BUG_ON(!vma->pages);
 
 	trace_i915_vma_bind(vma, bind_flags);
-	ret = vma->ops->bind_vma(vma, cache_level, bind_flags);
-	if (ret)
-		return ret;
+	if (work && (bind_flags & ~vma_flags) & vma->vm->bind_async_flags) {
+		work->vma = vma;
+		work->cache_level = cache_level;
+		work->flags = bind_flags | I915_VMA_ALLOC;
+
+		/*
+		 * Note we only want to chain up to the migration fence on
+		 * the pages (not the object itself). As we don't track that,
+		 * yet, we have to use the exclusive fence instead.
+		 *
+		 * Also note that we do not want to track the async vma as
+		 * part of the obj->resv->excl_fence as it only affects
+		 * execution and not content or object's backing store lifetime.
+		 */
+		GEM_BUG_ON(i915_active_has_exclusive(&vma->active));
+		i915_active_set_exclusive(&vma->active, &work->base.dma);
+		work->base.dma.error = 0; /* enable the queue_work() */
+
+		if (vma->obj)
+			__i915_gem_object_pin_pages(vma->obj);
+	} else {
+		GEM_BUG_ON((bind_flags & ~vma_flags) & vma->vm->bind_async_flags);
+		ret = vma->ops->bind_vma(vma, cache_level, bind_flags);
+		if (ret)
+			return ret;
+	}
 
 	atomic_or(bind_flags, &vma->flags);
 	return 0;
@@ -348,9 +413,7 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 
 	/* Access through the GTT requires the device to be awake. */
 	assert_rpm_wakelock_held(&vma->vm->i915->runtime_pm);
-
-	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
-	if (WARN_ON(!i915_vma_is_map_and_fenceable(vma))) {
+	if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) {
 		err = -ENODEV;
 		goto err;
 	}
@@ -358,7 +421,7 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
 	GEM_BUG_ON(!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND));
 
-	ptr = vma->iomap;
+	ptr = READ_ONCE(vma->iomap);
 	if (ptr == NULL) {
 		ptr = io_mapping_map_wc(&i915_vm_to_ggtt(vma->vm)->iomap,
 					vma->node.start,
@@ -368,7 +431,10 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 			goto err;
 		}
 
-		vma->iomap = ptr;
+		if (unlikely(cmpxchg(&vma->iomap, NULL, ptr))) {
+			io_mapping_unmap(ptr);
+			ptr = vma->iomap;
+		}
 	}
 
 	__i915_vma_pin(vma);
@@ -388,18 +454,12 @@ err:
 
 void i915_vma_flush_writes(struct i915_vma *vma)
 {
-	if (!i915_vma_has_ggtt_write(vma))
-		return;
-
-	intel_gt_flush_ggtt_writes(vma->vm->gt);
-
-	i915_vma_unset_ggtt_write(vma);
+	if (i915_vma_unset_ggtt_write(vma))
+		intel_gt_flush_ggtt_writes(vma->vm->gt);
 }
 
 void i915_vma_unpin_iomap(struct i915_vma *vma)
 {
-	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
-
 	GEM_BUG_ON(vma->iomap == NULL);
 
 	i915_vma_flush_writes(vma);
@@ -435,6 +495,9 @@ bool i915_vma_misplaced(const struct i915_vma *vma,
 	if (!drm_mm_node_allocated(&vma->node))
 		return false;
 
+	if (test_bit(I915_VMA_ERROR_BIT, __i915_vma_flags(vma)))
+		return true;
+
 	if (vma->node.size < size)
 		return true;
 
@@ -535,7 +598,6 @@ static void assert_bind_count(const struct drm_i915_gem_object *obj)
 static int
 i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 {
-	struct drm_i915_private *dev_priv = vma->vm->i915;
 	unsigned long color;
 	u64 start, end;
 	int ret;
@@ -561,7 +623,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 
 	end = vma->vm->total;
 	if (flags & PIN_MAPPABLE)
-		end = min_t(u64, end, dev_priv->ggtt.mappable_end);
+		end = min_t(u64, end, i915_vm_to_ggtt(vma->vm)->mappable_end);
 	if (flags & PIN_ZONE_4G)
 		end = min_t(u64, end, (1ULL << 32) - I915_GTT_PAGE_SIZE);
 	GEM_BUG_ON(!IS_ALIGNED(end, I915_GTT_PAGE_SIZE));
@@ -578,34 +640,20 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	}
 
 	color = 0;
-	if (vma->obj) {
-		ret = i915_gem_object_pin_pages(vma->obj);
-		if (ret)
-			return ret;
-
-		if (i915_vm_has_cache_coloring(vma->vm))
-			color = vma->obj->cache_level;
-	}
-
-	GEM_BUG_ON(vma->pages);
-
-	ret = vma->ops->set_pages(vma);
-	if (ret)
-		goto err_unpin;
+	if (vma->obj && i915_vm_has_cache_coloring(vma->vm))
+		color = vma->obj->cache_level;
 
 	if (flags & PIN_OFFSET_FIXED) {
 		u64 offset = flags & PIN_OFFSET_MASK;
 		if (!IS_ALIGNED(offset, alignment) ||
-		    range_overflows(offset, size, end)) {
-			ret = -EINVAL;
-			goto err_clear;
-		}
+		    range_overflows(offset, size, end))
+			return -EINVAL;
 
 		ret = i915_gem_gtt_reserve(vma->vm, &vma->node,
 					   size, offset, color,
 					   flags);
 		if (ret)
-			goto err_clear;
+			return ret;
 	} else {
 		/*
 		 * We only support huge gtt pages through the 48b PPGTT,
@@ -644,7 +692,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 					  size, alignment, color,
 					  start, end, flags);
 		if (ret)
-			goto err_clear;
+			return ret;
 
 		GEM_BUG_ON(vma->node.start < start);
 		GEM_BUG_ON(vma->node.start + vma->node.size > end);
@@ -652,23 +700,15 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(!i915_gem_valid_gtt_space(vma, color));
 
-	mutex_lock(&vma->vm->mutex);
 	list_add_tail(&vma->vm_link, &vma->vm->bound_list);
-	mutex_unlock(&vma->vm->mutex);
 
 	if (vma->obj) {
+		atomic_inc(&vma->obj->mm.pages_pin_count);
 		atomic_inc(&vma->obj->bind_count);
 		assert_bind_count(vma->obj);
 	}
 
 	return 0;
-
-err_clear:
-	vma->ops->clear_pages(vma);
-err_unpin:
-	if (vma->obj)
-		i915_gem_object_unpin_pages(vma->obj);
-	return ret;
 }
 
 static void
@@ -677,12 +717,7 @@ i915_vma_remove(struct i915_vma *vma)
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
 
-	vma->ops->clear_pages(vma);
-
-	mutex_lock(&vma->vm->mutex);
-	drm_mm_remove_node(&vma->node);
 	list_del(&vma->vm_link);
-	mutex_unlock(&vma->vm->mutex);
 
 	/*
 	 * Since the unbound list is global, only move to that list if
@@ -701,51 +736,211 @@ i915_vma_remove(struct i915_vma *vma)
 		i915_gem_object_unpin_pages(obj);
 		assert_bind_count(obj);
 	}
+
+	drm_mm_remove_node(&vma->node);
 }
 
-int __i915_vma_do_pin(struct i915_vma *vma,
-		      u64 size, u64 alignment, u64 flags)
+static bool try_qad_pin(struct i915_vma *vma, unsigned int flags)
 {
-	const unsigned int bound = atomic_read(&vma->flags);
-	int ret;
+	unsigned int bound;
+	bool pinned = true;
 
-	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
-	GEM_BUG_ON((flags & (PIN_GLOBAL | PIN_USER)) == 0);
-	GEM_BUG_ON((flags & PIN_GLOBAL) && !i915_vma_is_ggtt(vma));
+	bound = atomic_read(&vma->flags);
+	do {
+		if (unlikely(flags & ~bound))
+			return false;
 
-	if (WARN_ON(bound & I915_VMA_PIN_OVERFLOW)) {
-		ret = -EBUSY;
-		goto err_unpin;
+		if (unlikely(bound & (I915_VMA_OVERFLOW | I915_VMA_ERROR)))
+			return false;
+
+		if (!(bound & I915_VMA_PIN_MASK))
+			goto unpinned;
+
+		GEM_BUG_ON(((bound + 1) & I915_VMA_PIN_MASK) == 0);
+	} while (!atomic_try_cmpxchg(&vma->flags, &bound, bound + 1));
+
+	return true;
+
+unpinned:
+	/*
+	 * If pin_count==0, but we are bound, check under the lock to avoid
+	 * racing with a concurrent i915_vma_unbind().
+	 */
+	mutex_lock(&vma->vm->mutex);
+	do {
+		if (unlikely(bound & (I915_VMA_OVERFLOW | I915_VMA_ERROR))) {
+			pinned = false;
+			break;
+		}
+
+		if (unlikely(flags & ~bound)) {
+			pinned = false;
+			break;
+		}
+	} while (!atomic_try_cmpxchg(&vma->flags, &bound, bound + 1));
+	mutex_unlock(&vma->vm->mutex);
+
+	return pinned;
+}
+
+static int vma_get_pages(struct i915_vma *vma)
+{
+	int err = 0;
+
+	if (atomic_add_unless(&vma->pages_count, 1, 0))
+		return 0;
+
+	/* Allocations ahoy! */
+	if (mutex_lock_interruptible(&vma->pages_mutex))
+		return -EINTR;
+
+	if (!atomic_read(&vma->pages_count)) {
+		if (vma->obj) {
+			err = i915_gem_object_pin_pages(vma->obj);
+			if (err)
+				goto unlock;
+		}
+
+		err = vma->ops->set_pages(vma);
+		if (err)
+			goto unlock;
 	}
+	atomic_inc(&vma->pages_count);
 
-	if ((bound & I915_VMA_BIND_MASK) == 0) {
-		ret = i915_vma_insert(vma, size, alignment, flags);
-		if (ret)
-			goto err_unpin;
+unlock:
+	mutex_unlock(&vma->pages_mutex);
+
+	return err;
+}
+
+static void __vma_put_pages(struct i915_vma *vma, unsigned int count)
+{
+	/* We allocate under vma_get_pages, so beware the shrinker */
+	mutex_lock_nested(&vma->pages_mutex, SINGLE_DEPTH_NESTING);
+	GEM_BUG_ON(atomic_read(&vma->pages_count) < count);
+	if (atomic_sub_return(count, &vma->pages_count) == 0) {
+		vma->ops->clear_pages(vma);
+		GEM_BUG_ON(vma->pages);
+		if (vma->obj)
+			i915_gem_object_unpin_pages(vma->obj);
 	}
-	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
+	mutex_unlock(&vma->pages_mutex);
+}
 
-	ret = i915_vma_bind(vma, vma->obj ? vma->obj->cache_level : 0, flags);
-	if (ret)
-		goto err_remove;
+static void vma_put_pages(struct i915_vma *vma)
+{
+	if (atomic_add_unless(&vma->pages_count, -1, 1))
+		return;
+
+	__vma_put_pages(vma, 1);
+}
+
+static void vma_unbind_pages(struct i915_vma *vma)
+{
+	unsigned int count;
+
+	lockdep_assert_held(&vma->vm->mutex);
+
+	/* The upper portion of pages_count is the number of bindings */
+	count = atomic_read(&vma->pages_count);
+	count >>= I915_VMA_PAGES_BIAS;
+	GEM_BUG_ON(!count);
+
+	__vma_put_pages(vma, count | count << I915_VMA_PAGES_BIAS);
+}
+
+int i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
+{
+	struct i915_vma_work *work = NULL;
+	unsigned int bound;
+	int err;
+
+	BUILD_BUG_ON(PIN_GLOBAL != I915_VMA_GLOBAL_BIND);
+	BUILD_BUG_ON(PIN_USER != I915_VMA_LOCAL_BIND);
+
+	GEM_BUG_ON(flags & PIN_UPDATE);
+	GEM_BUG_ON(!(flags & (PIN_USER | PIN_GLOBAL)));
+
+	/* First try and grab the pin without rebinding the vma */
+	if (try_qad_pin(vma, flags & I915_VMA_BIND_MASK))
+		return 0;
+
+	err = vma_get_pages(vma);
+	if (err)
+		return err;
+
+	if (flags & vma->vm->bind_async_flags) {
+		work = i915_vma_work();
+		if (!work) {
+			err = -ENOMEM;
+			goto err_pages;
+		}
+	}
+
+	/* No more allocations allowed once we hold vm->mutex */
+	err = mutex_lock_interruptible(&vma->vm->mutex);
+	if (err)
+		goto err_fence;
+
+	bound = atomic_read(&vma->flags);
+	if (unlikely(bound & I915_VMA_ERROR)) {
+		err = -ENOMEM;
+		goto err_unlock;
+	}
+
+	if (unlikely(!((bound + 1) & I915_VMA_PIN_MASK))) {
+		err = -EAGAIN; /* pins are meant to be fairly temporary */
+		goto err_unlock;
+	}
+
+	if (unlikely(!(flags & ~bound & I915_VMA_BIND_MASK))) {
+		__i915_vma_pin(vma);
+		goto err_unlock;
+	}
+
+	err = i915_active_acquire(&vma->active);
+	if (err)
+		goto err_unlock;
+
+	if (!(bound & I915_VMA_BIND_MASK)) {
+		err = i915_vma_insert(vma, size, alignment, flags);
+		if (err)
+			goto err_active;
+
+		if (i915_is_ggtt(vma->vm))
+			__i915_vma_set_map_and_fenceable(vma);
+	}
 
-	GEM_BUG_ON(!i915_vma_is_bound(vma, I915_VMA_BIND_MASK));
+	GEM_BUG_ON(!vma->pages);
+	err = i915_vma_bind(vma,
+			    vma->obj ? vma->obj->cache_level : 0,
+			    flags, work);
+	if (err)
+		goto err_remove;
 
-	if ((bound ^ atomic_read(&vma->flags)) & I915_VMA_GLOBAL_BIND)
-		__i915_vma_set_map_and_fenceable(vma);
+	/* There should only be at most 2 active bindings (user, global) */
+	GEM_BUG_ON(bound + I915_VMA_PAGES_ACTIVE < bound);
+	atomic_add(I915_VMA_PAGES_ACTIVE, &vma->pages_count);
+	list_move_tail(&vma->vm_link, &vma->vm->bound_list);
 
+	__i915_vma_pin(vma);
+	GEM_BUG_ON(!i915_vma_is_pinned(vma));
+	GEM_BUG_ON(!i915_vma_is_bound(vma, flags));
 	GEM_BUG_ON(i915_vma_misplaced(vma, size, alignment, flags));
-	return 0;
 
 err_remove:
-	if ((bound & I915_VMA_BIND_MASK) == 0) {
+	if (!i915_vma_is_bound(vma, I915_VMA_BIND_MASK))
 		i915_vma_remove(vma);
-		GEM_BUG_ON(vma->pages);
-		GEM_BUG_ON(atomic_read(&vma->flags) & I915_VMA_BIND_MASK);
-	}
-err_unpin:
-	__i915_vma_unpin(vma);
-	return ret;
+err_active:
+	i915_active_release(&vma->active);
+err_unlock:
+	mutex_unlock(&vma->vm->mutex);
+err_fence:
+	if (work)
+		dma_fence_work_commit(&work->base);
+err_pages:
+	vma_put_pages(vma);
+	return err;
 }
 
 void i915_vma_close(struct i915_vma *vma)
@@ -776,9 +971,6 @@ static void __i915_vma_remove_closed(struct i915_vma *vma)
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
 
-	if (!i915_vma_is_closed(vma))
-		return;
-
 	spin_lock_irq(&i915->gt.closed_lock);
 	list_del_init(&vma->closed_link);
 	spin_unlock_irq(&i915->gt.closed_lock);
@@ -786,40 +978,35 @@ static void __i915_vma_remove_closed(struct i915_vma *vma)
 
 void i915_vma_reopen(struct i915_vma *vma)
 {
-	__i915_vma_remove_closed(vma);
+	if (i915_vma_is_closed(vma))
+		__i915_vma_remove_closed(vma);
 }
 
-static void __i915_vma_destroy(struct i915_vma *vma)
+void i915_vma_destroy(struct i915_vma *vma)
 {
-	GEM_BUG_ON(drm_mm_node_allocated(&vma->node));
-	GEM_BUG_ON(vma->fence);
+	if (drm_mm_node_allocated(&vma->node)) {
+		mutex_lock(&vma->vm->mutex);
+		atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
+		WARN_ON(__i915_vma_unbind(vma));
+		mutex_unlock(&vma->vm->mutex);
+		GEM_BUG_ON(drm_mm_node_allocated(&vma->node));
+	}
+	GEM_BUG_ON(i915_vma_is_active(vma));
 
 	if (vma->obj) {
 		struct drm_i915_gem_object *obj = vma->obj;
 
 		spin_lock(&obj->vma.lock);
 		list_del(&vma->obj_link);
-		rb_erase(&vma->obj_node, &vma->obj->vma.tree);
+		rb_erase(&vma->obj_node, &obj->vma.tree);
 		spin_unlock(&obj->vma.lock);
 	}
 
-	i915_active_fini(&vma->active);
-
-	i915_vma_free(vma);
-}
-
-void i915_vma_destroy(struct i915_vma *vma)
-{
-	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
-
-	GEM_BUG_ON(i915_vma_is_pinned(vma));
-
 	__i915_vma_remove_closed(vma);
+	i915_vm_put(vma->vm);
 
-	WARN_ON(i915_vma_unbind(vma));
-	GEM_BUG_ON(i915_vma_is_active(vma));
-
-	__i915_vma_destroy(vma);
+	i915_active_fini(&vma->active);
+	i915_vma_free(vma);
 }
 
 void i915_vma_parked(struct drm_i915_private *i915)
@@ -828,12 +1015,32 @@ void i915_vma_parked(struct drm_i915_private *i915)
 
 	spin_lock_irq(&i915->gt.closed_lock);
 	list_for_each_entry_safe(vma, next, &i915->gt.closed_vma, closed_link) {
-		list_del_init(&vma->closed_link);
+		struct drm_i915_gem_object *obj = vma->obj;
+		struct i915_address_space *vm = vma->vm;
+
+		/* XXX All to avoid keeping a reference on i915_vma itself */
+
+		if (!kref_get_unless_zero(&obj->base.refcount))
+			continue;
+
+		if (!i915_vm_tryopen(vm)) {
+			i915_gem_object_put(obj);
+			obj = NULL;
+		}
+
 		spin_unlock_irq(&i915->gt.closed_lock);
 
-		i915_vma_destroy(vma);
+		if (obj) {
+			i915_vma_destroy(vma);
+			i915_gem_object_put(obj);
+		}
 
+		i915_vm_close(vm);
+
+		/* Restart after dropping lock */
 		spin_lock_irq(&i915->gt.closed_lock);
+		next = list_first_entry(&i915->gt.closed_vma,
+					typeof(*next), closed_link);
 	}
 	spin_unlock_irq(&i915->gt.closed_lock);
 }
@@ -873,6 +1080,20 @@ void i915_vma_revoke_mmap(struct i915_vma *vma)
 		list_del(&vma->obj->userfault_link);
 }
 
+int __i915_vma_move_to_active(struct i915_vma *vma, struct i915_request *rq)
+{
+	int err;
+
+	GEM_BUG_ON(!i915_vma_is_pinned(vma));
+
+	/* Wait for the vma to be bound before we start! */
+	err = i915_request_await_active(rq, &vma->active);
+	if (err)
+		return err;
+
+	return i915_active_add_request(&vma->active, rq);
+}
+
 int i915_vma_move_to_active(struct i915_vma *vma,
 			    struct i915_request *rq,
 			    unsigned int flags)
@@ -880,19 +1101,9 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 	struct drm_i915_gem_object *obj = vma->obj;
 	int err;
 
-	assert_vma_held(vma);
 	assert_object_held(obj);
-	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 
-	/*
-	 * Add a reference if we're newly entering the active list.
-	 * The order in which we add operations to the retirement queue is
-	 * vital here: mark_active adds to the start of the callback list,
-	 * such that subsequent callbacks are called first. Therefore we
-	 * add the active reference first and queue for it to be dropped
-	 * *last*.
-	 */
-	err = i915_active_add_request(&vma->active, rq);
+	err = __i915_vma_move_to_active(vma, rq);
 	if (unlikely(err))
 		return err;
 
@@ -918,38 +1129,23 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 	return 0;
 }
 
-int i915_vma_unbind(struct i915_vma *vma)
+int __i915_vma_unbind(struct i915_vma *vma)
 {
 	int ret;
 
-	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
+	lockdep_assert_held(&vma->vm->mutex);
 
 	/*
 	 * First wait upon any activity as retiring the request may
 	 * have side-effects such as unpinning or even unbinding this vma.
+	 *
+	 * XXX Actually waiting under the vm->mutex is a hinderance and
+	 * should be pipelined wherever possible. In cases where that is
+	 * unavoidable, we should lift the wait to before the mutex.
 	 */
-	might_sleep();
-	if (i915_vma_is_active(vma)) {
-		/*
-		 * When a closed VMA is retired, it is unbound - eek.
-		 * In order to prevent it from being recursively closed,
-		 * take a pin on the vma so that the second unbind is
-		 * aborted.
-		 *
-		 * Even more scary is that the retire callback may free
-		 * the object (last active vma). To prevent the explosion
-		 * we defer the actual object free to a worker that can
-		 * only proceed once it acquires the struct_mutex (which
-		 * we currently hold, therefore it cannot free this object
-		 * before we are finished).
-		 */
-		__i915_vma_pin(vma);
-		ret = i915_active_wait(&vma->active);
-		__i915_vma_unpin(vma);
-		if (ret)
-			return ret;
-	}
-	GEM_BUG_ON(i915_vma_is_active(vma));
+	ret = i915_vma_sync(vma);
+	if (ret)
+		return ret;
 
 	if (i915_vma_is_pinned(vma)) {
 		vma_print_allocator(vma, "is pinned");
@@ -970,16 +1166,12 @@ int i915_vma_unbind(struct i915_vma *vma)
 		GEM_BUG_ON(i915_vma_has_ggtt_write(vma));
 
 		/* release the fence reg _after_ flushing */
-		mutex_lock(&vma->vm->mutex);
 		ret = i915_vma_revoke_fence(vma);
-		mutex_unlock(&vma->vm->mutex);
 		if (ret)
 			return ret;
 
 		/* Force a pagefault for domain tracking on next user access */
-		mutex_lock(&vma->vm->mutex);
 		i915_vma_revoke_mmap(vma);
-		mutex_unlock(&vma->vm->mutex);
 
 		__i915_vma_iounmap(vma);
 		clear_bit(I915_VMA_CAN_FENCE_BIT, __i915_vma_flags(vma));
@@ -987,17 +1179,33 @@ int i915_vma_unbind(struct i915_vma *vma)
 	GEM_BUG_ON(vma->fence);
 	GEM_BUG_ON(i915_vma_has_userfault(vma));
 
-	if (likely(!vma->vm->closed)) {
+	if (likely(atomic_read(&vma->vm->open))) {
 		trace_i915_vma_unbind(vma);
 		vma->ops->unbind_vma(vma);
 	}
-	atomic_and(~I915_VMA_BIND_MASK, &vma->flags);
+	atomic_and(~(I915_VMA_BIND_MASK | I915_VMA_ERROR), &vma->flags);
 
+	vma_unbind_pages(vma);
 	i915_vma_remove(vma);
 
 	return 0;
 }
 
+int i915_vma_unbind(struct i915_vma *vma)
+{
+	struct i915_address_space *vm = vma->vm;
+	int err;
+
+	err = mutex_lock_interruptible(&vm->mutex);
+	if (err)
+		return err;
+
+	err = __i915_vma_unbind(vma);
+	mutex_unlock(&vm->mutex);
+
+	return err;
+}
+
 struct i915_vma *i915_vma_make_unshrinkable(struct i915_vma *vma)
 {
 	i915_gem_object_make_unshrinkable(vma->obj);
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index e49b199f7de7..858908e3d1cc 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -96,25 +96,28 @@ struct i915_vma {
 	 * exclusive cachelines of a single page, so a maximum of 64 possible
 	 * users.
 	 */
-#define I915_VMA_PIN_MASK 0xff
-#define I915_VMA_PIN_OVERFLOW_BIT 8
-#define I915_VMA_PIN_OVERFLOW	((int)BIT(I915_VMA_PIN_OVERFLOW_BIT))
+#define I915_VMA_PIN_MASK 0x3ff
+#define I915_VMA_OVERFLOW 0x200
 
 	/** Flags and address space this VMA is bound to */
-#define I915_VMA_GLOBAL_BIND_BIT 9
-#define I915_VMA_LOCAL_BIND_BIT 10
+#define I915_VMA_GLOBAL_BIND_BIT 10
+#define I915_VMA_LOCAL_BIND_BIT  11
 
 #define I915_VMA_GLOBAL_BIND	((int)BIT(I915_VMA_GLOBAL_BIND_BIT))
 #define I915_VMA_LOCAL_BIND	((int)BIT(I915_VMA_LOCAL_BIND_BIT))
 
-#define I915_VMA_BIND_MASK (I915_VMA_GLOBAL_BIND | \
-			    I915_VMA_LOCAL_BIND | \
-			    I915_VMA_PIN_OVERFLOW)
+#define I915_VMA_BIND_MASK (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND)
 
-#define I915_VMA_GGTT_BIT	11
-#define I915_VMA_CAN_FENCE_BIT	12
-#define I915_VMA_USERFAULT_BIT	13
-#define I915_VMA_GGTT_WRITE_BIT	14
+#define I915_VMA_ALLOC_BIT	12
+#define I915_VMA_ALLOC		((int)BIT(I915_VMA_ALLOC_BIT))
+
+#define I915_VMA_ERROR_BIT	13
+#define I915_VMA_ERROR		((int)BIT(I915_VMA_ERROR_BIT))
+
+#define I915_VMA_GGTT_BIT	14
+#define I915_VMA_CAN_FENCE_BIT	15
+#define I915_VMA_USERFAULT_BIT	16
+#define I915_VMA_GGTT_WRITE_BIT	17
 
 #define I915_VMA_GGTT		((int)BIT(I915_VMA_GGTT_BIT))
 #define I915_VMA_CAN_FENCE	((int)BIT(I915_VMA_CAN_FENCE_BIT))
@@ -123,6 +126,11 @@ struct i915_vma {
 
 	struct i915_active active;
 
+#define I915_VMA_PAGES_BIAS 24
+#define I915_VMA_PAGES_ACTIVE (BIT(24) | 1)
+	atomic_t pages_count; /* number of active binds to the pages */
+	struct mutex pages_mutex; /* protect acquire/release of backing pages */
+
 	/**
 	 * Support different GGTT views into the same object.
 	 * This means there can be multiple VMA mappings per object and per VM.
@@ -169,6 +177,8 @@ static inline bool i915_vma_is_active(const struct i915_vma *vma)
 	return !i915_active_is_idle(&vma->active);
 }
 
+int __must_check __i915_vma_move_to_active(struct i915_vma *vma,
+					   struct i915_request *rq);
 int __must_check i915_vma_move_to_active(struct i915_vma *vma,
 					 struct i915_request *rq,
 					 unsigned int flags);
@@ -307,13 +317,18 @@ i915_vma_compare(struct i915_vma *vma,
 	return memcmp(&vma->ggtt_view.partial, &view->partial, view->type);
 }
 
-int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
-		  u32 flags);
+struct i915_vma_work *i915_vma_work(void);
+int i915_vma_bind(struct i915_vma *vma,
+		  enum i915_cache_level cache_level,
+		  u32 flags,
+		  struct i915_vma_work *work);
+
 bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long color);
 bool i915_vma_misplaced(const struct i915_vma *vma,
 			u64 size, u64 alignment, u64 flags);
 void __i915_vma_set_map_and_fenceable(struct i915_vma *vma);
 void i915_vma_revoke_mmap(struct i915_vma *vma);
+int __i915_vma_unbind(struct i915_vma *vma);
 int __must_check i915_vma_unbind(struct i915_vma *vma);
 void i915_vma_unlink_ctx(struct i915_vma *vma);
 void i915_vma_close(struct i915_vma *vma);
@@ -332,26 +347,8 @@ static inline void i915_vma_unlock(struct i915_vma *vma)
 	dma_resv_unlock(vma->resv);
 }
 
-int __i915_vma_do_pin(struct i915_vma *vma,
-		      u64 size, u64 alignment, u64 flags);
-static inline int __must_check
-i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
-{
-	BUILD_BUG_ON(PIN_MBZ != I915_VMA_PIN_OVERFLOW);
-	BUILD_BUG_ON(PIN_GLOBAL != I915_VMA_GLOBAL_BIND);
-	BUILD_BUG_ON(PIN_USER != I915_VMA_LOCAL_BIND);
-
-	/* Pin early to prevent the shrinker/eviction logic from destroying
-	 * our vma as we insert and bind.
-	 */
-	if (likely(((atomic_inc_return(&vma->flags) ^ flags) & I915_VMA_BIND_MASK) == 0)) {
-		GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
-		GEM_BUG_ON(i915_vma_misplaced(vma, size, alignment, flags));
-		return 0;
-	}
-
-	return __i915_vma_do_pin(vma, size, alignment, flags);
-}
+int __must_check
+i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags);
 
 static inline int i915_vma_pin_count(const struct i915_vma *vma)
 {
@@ -366,17 +363,17 @@ static inline bool i915_vma_is_pinned(const struct i915_vma *vma)
 static inline void __i915_vma_pin(struct i915_vma *vma)
 {
 	atomic_inc(&vma->flags);
-	GEM_BUG_ON(atomic_read(&vma->flags) & I915_VMA_PIN_OVERFLOW);
+	GEM_BUG_ON(!i915_vma_is_pinned(vma));
 }
 
 static inline void __i915_vma_unpin(struct i915_vma *vma)
 {
+	GEM_BUG_ON(!i915_vma_is_pinned(vma));
 	atomic_dec(&vma->flags);
 }
 
 static inline void i915_vma_unpin(struct i915_vma *vma)
 {
-	GEM_BUG_ON(!i915_vma_is_pinned(vma));
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	__i915_vma_unpin(vma);
 }
@@ -402,8 +399,6 @@ static inline bool i915_node_color_differs(const struct drm_mm_node *node,
  * the caller must call i915_vma_unpin_iomap to relinquish the pinning
  * after the iomapping is no longer required.
  *
- * Callers must hold the struct_mutex.
- *
  * Returns a valid iomapped pointer or ERR_PTR.
  */
 void __iomem *i915_vma_pin_iomap(struct i915_vma *vma);
@@ -415,8 +410,8 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma);
  *
  * Unpins the previously iomapped VMA from i915_vma_pin_iomap().
  *
- * Callers must hold the struct_mutex. This function is only valid to be
- * called on a VMA previously iomapped by the caller with i915_vma_pin_iomap().
+ * This function is only valid to be called on a VMA previously
+ * iomapped by the caller with i915_vma_pin_iomap().
  */
 void i915_vma_unpin_iomap(struct i915_vma *vma);
 
@@ -444,6 +439,8 @@ static inline struct page *i915_vma_first_page(struct i915_vma *vma)
 int __must_check i915_vma_pin_fence(struct i915_vma *vma);
 int __must_check i915_vma_revoke_fence(struct i915_vma *vma);
 
+int __i915_vma_pin_fence(struct i915_vma *vma);
+
 static inline void __i915_vma_unpin_fence(struct i915_vma *vma)
 {
 	GEM_BUG_ON(atomic_read(&vma->fence->pin_count) <= 0);
@@ -461,7 +458,6 @@ static inline void __i915_vma_unpin_fence(struct i915_vma *vma)
 static inline void
 i915_vma_unpin_fence(struct i915_vma *vma)
 {
-	/* lockdep_assert_held(&vma->vm->i915->drm.struct_mutex); */
 	if (vma->fence)
 		__i915_vma_unpin_fence(vma);
 }
@@ -490,4 +486,10 @@ struct i915_vma *i915_vma_make_unshrinkable(struct i915_vma *vma);
 void i915_vma_make_shrinkable(struct i915_vma *vma);
 void i915_vma_make_purgeable(struct i915_vma *vma);
 
+static inline int i915_vma_sync(struct i915_vma *vma)
+{
+	/* Wait for the asynchronous bindings and pending GPU reads */
+	return i915_active_wait(&vma->active);
+}
+
 #endif
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index 37593831b539..0346c3e5b6b6 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -119,10 +119,8 @@ static void pm_resume(struct drm_i915_private *i915)
 		intel_gt_sanitize(&i915->gt, false);
 		i915_gem_sanitize(i915);
 
-		mutex_lock(&i915->drm.struct_mutex);
 		i915_gem_restore_gtt_mappings(i915);
 		i915_gem_restore_fences(i915);
-		mutex_unlock(&i915->drm.struct_mutex);
 
 		i915_gem_resume(i915);
 	}
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index 2905fb21d866..75a4695b82bb 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -106,14 +106,11 @@ static int populate_ggtt(struct drm_i915_private *i915,
 
 static void unpin_ggtt(struct drm_i915_private *i915)
 {
-	struct i915_ggtt *ggtt = &i915->ggtt;
 	struct i915_vma *vma;
 
-	mutex_lock(&ggtt->vm.mutex);
 	list_for_each_entry(vma, &i915->ggtt.vm.bound_list, vm_link)
 		if (vma->obj->mm.quirked)
 			i915_vma_unpin(vma);
-	mutex_unlock(&ggtt->vm.mutex);
 }
 
 static void cleanup_objects(struct drm_i915_private *i915,
@@ -127,11 +124,7 @@ static void cleanup_objects(struct drm_i915_private *i915,
 		i915_gem_object_put(obj);
 	}
 
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	i915_gem_drain_freed_objects(i915);
-
-	mutex_lock(&i915->drm.struct_mutex);
 }
 
 static int igt_evict_something(void *arg)
@@ -148,10 +141,12 @@ static int igt_evict_something(void *arg)
 		goto cleanup;
 
 	/* Everything is pinned, nothing should happen */
+	mutex_lock(&ggtt->vm.mutex);
 	err = i915_gem_evict_something(&ggtt->vm,
 				       I915_GTT_PAGE_SIZE, 0, 0,
 				       0, U64_MAX,
 				       0);
+	mutex_unlock(&ggtt->vm.mutex);
 	if (err != -ENOSPC) {
 		pr_err("i915_gem_evict_something failed on a full GGTT with err=%d\n",
 		       err);
@@ -161,10 +156,12 @@ static int igt_evict_something(void *arg)
 	unpin_ggtt(i915);
 
 	/* Everything is unpinned, we should be able to evict something */
+	mutex_lock(&ggtt->vm.mutex);
 	err = i915_gem_evict_something(&ggtt->vm,
 				       I915_GTT_PAGE_SIZE, 0, 0,
 				       0, U64_MAX,
 				       0);
+	mutex_unlock(&ggtt->vm.mutex);
 	if (err) {
 		pr_err("i915_gem_evict_something failed on a full GGTT with err=%d\n",
 		       err);
@@ -230,7 +227,9 @@ static int igt_evict_for_vma(void *arg)
 		goto cleanup;
 
 	/* Everything is pinned, nothing should happen */
+	mutex_lock(&ggtt->vm.mutex);
 	err = i915_gem_evict_for_node(&ggtt->vm, &target, 0);
+	mutex_unlock(&ggtt->vm.mutex);
 	if (err != -ENOSPC) {
 		pr_err("i915_gem_evict_for_node on a full GGTT returned err=%d\n",
 		       err);
@@ -240,7 +239,9 @@ static int igt_evict_for_vma(void *arg)
 	unpin_ggtt(i915);
 
 	/* Everything is unpinned, we should be able to evict the node */
+	mutex_lock(&ggtt->vm.mutex);
 	err = i915_gem_evict_for_node(&ggtt->vm, &target, 0);
+	mutex_unlock(&ggtt->vm.mutex);
 	if (err) {
 		pr_err("i915_gem_evict_for_node returned err=%d\n",
 		       err);
@@ -319,7 +320,9 @@ static int igt_evict_for_cache_color(void *arg)
 	i915_vma_unpin(vma);
 
 	/* Remove just the second vma */
+	mutex_lock(&ggtt->vm.mutex);
 	err = i915_gem_evict_for_node(&ggtt->vm, &target, 0);
+	mutex_unlock(&ggtt->vm.mutex);
 	if (err) {
 		pr_err("[0]i915_gem_evict_for_node returned err=%d\n", err);
 		goto cleanup;
@@ -330,7 +333,9 @@ static int igt_evict_for_cache_color(void *arg)
 	 */
 	target.color = I915_CACHE_L3_LLC;
 
+	mutex_lock(&ggtt->vm.mutex);
 	err = i915_gem_evict_for_node(&ggtt->vm, &target, 0);
+	mutex_unlock(&ggtt->vm.mutex);
 	if (!err) {
 		pr_err("[1]i915_gem_evict_for_node returned err=%d\n", err);
 		err = -EINVAL;
@@ -360,7 +365,9 @@ static int igt_evict_vm(void *arg)
 		goto cleanup;
 
 	/* Everything is pinned, nothing should happen */
+	mutex_lock(&ggtt->vm.mutex);
 	err = i915_gem_evict_vm(&ggtt->vm);
+	mutex_unlock(&ggtt->vm.mutex);
 	if (err) {
 		pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n",
 		       err);
@@ -369,7 +376,9 @@ static int igt_evict_vm(void *arg)
 
 	unpin_ggtt(i915);
 
+	mutex_lock(&ggtt->vm.mutex);
 	err = i915_gem_evict_vm(&ggtt->vm);
+	mutex_unlock(&ggtt->vm.mutex);
 	if (err) {
 		pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n",
 		       err);
@@ -410,11 +419,11 @@ static int igt_evict_contexts(void *arg)
 	if (!HAS_FULL_PPGTT(i915))
 		return 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 
 	/* Reserve a block so that we know we have enough to fit a few rq */
 	memset(&hole, 0, sizeof(hole));
+	mutex_lock(&i915->ggtt.vm.mutex);
 	err = i915_gem_gtt_insert(&i915->ggtt.vm, &hole,
 				  PRETEND_GGTT_SIZE, 0, I915_COLOR_UNEVICTABLE,
 				  0, i915->ggtt.vm.total,
@@ -427,7 +436,9 @@ static int igt_evict_contexts(void *arg)
 	do {
 		struct reserved *r;
 
+		mutex_unlock(&i915->ggtt.vm.mutex);
 		r = kcalloc(1, sizeof(*r), GFP_KERNEL);
+		mutex_lock(&i915->ggtt.vm.mutex);
 		if (!r) {
 			err = -ENOMEM;
 			goto out_locked;
@@ -447,7 +458,7 @@ static int igt_evict_contexts(void *arg)
 		count++;
 	} while (1);
 	drm_mm_remove_node(&hole);
-	mutex_unlock(&i915->drm.struct_mutex);
+	mutex_unlock(&i915->ggtt.vm.mutex);
 	pr_info("Filled GGTT with %lu 1MiB nodes\n", count);
 
 	/* Overfill the GGTT with context objects and so try to evict one. */
@@ -510,7 +521,7 @@ static int igt_evict_contexts(void *arg)
 			break;
 	}
 
-	mutex_lock(&i915->drm.struct_mutex);
+	mutex_lock(&i915->ggtt.vm.mutex);
 out_locked:
 	if (igt_flush_test(i915, I915_WAIT_LOCKED))
 		err = -EIO;
@@ -524,8 +535,8 @@ out_locked:
 	}
 	if (drm_mm_node_allocated(&hole))
 		drm_mm_remove_node(&hole);
+	mutex_unlock(&i915->ggtt.vm.mutex);
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	return err;
 }
@@ -547,12 +558,9 @@ int i915_gem_evict_mock_selftests(void)
 	if (!i915)
 		return -ENOMEM;
 
-	mutex_lock(&i915->drm.struct_mutex);
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
 		err = i915_subtests(tests, i915);
 
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	drm_dev_put(&i915->drm);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 0945d6e978a2..02749bbfd0cf 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -38,16 +38,7 @@
 
 static void cleanup_freed_objects(struct drm_i915_private *i915)
 {
-	/*
-	 * As we may hold onto the struct_mutex for inordinate lengths of
-	 * time, the NMI khungtaskd detector may fire for the free objects
-	 * worker.
-	 */
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	i915_gem_drain_freed_objects(i915);
-
-	mutex_lock(&i915->drm.struct_mutex);
 }
 
 static void fake_free_pages(struct drm_i915_gem_object *obj,
@@ -880,6 +871,15 @@ static int __shrink_hole(struct drm_i915_private *i915,
 		i915_vma_unpin(vma);
 		addr += size;
 
+		/*
+		 * Since we are injecting allocation faults at random intervals,
+		 * wait for this allocation to complete before we change the
+		 * faultinjection.
+		 */
+		err = i915_vma_sync(vma);
+		if (err)
+			break;
+
 		if (igt_timeout(end_time,
 				"%s timed out at ofset %llx [%llx - %llx]\n",
 				__func__, addr, hole_start, hole_end)) {
@@ -1013,21 +1013,19 @@ static int exercise_ppgtt(struct drm_i915_private *dev_priv,
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	ppgtt = i915_ppgtt_create(dev_priv);
 	if (IS_ERR(ppgtt)) {
 		err = PTR_ERR(ppgtt);
-		goto out_unlock;
+		goto out_free;
 	}
 	GEM_BUG_ON(offset_in_page(ppgtt->vm.total));
-	GEM_BUG_ON(ppgtt->vm.closed);
+	GEM_BUG_ON(!atomic_read(&ppgtt->vm.open));
 
 	err = func(dev_priv, &ppgtt->vm, 0, ppgtt->vm.total, end_time);
 
 	i915_vm_put(&ppgtt->vm);
-out_unlock:
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 
+out_free:
 	mock_file_free(dev_priv, file);
 	return err;
 }
@@ -1090,7 +1088,6 @@ static int exercise_ggtt(struct drm_i915_private *i915,
 	IGT_TIMEOUT(end_time);
 	int err = 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
 restart:
 	list_sort(NULL, &ggtt->vm.mm.hole_stack, sort_holes);
 	drm_mm_for_each_hole(node, &ggtt->vm.mm, hole_start, hole_end) {
@@ -1111,7 +1108,6 @@ restart:
 		last = hole_end;
 		goto restart;
 	}
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	return err;
 }
@@ -1153,13 +1149,9 @@ static int igt_ggtt_page(void *arg)
 	unsigned int *order, n;
 	int err;
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
-	if (IS_ERR(obj)) {
-		err = PTR_ERR(obj);
-		goto out_unlock;
-	}
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
 	err = i915_gem_object_pin_pages(obj);
 	if (err)
@@ -1227,8 +1219,6 @@ out_unpin:
 	i915_gem_object_unpin_pages(obj);
 out_free:
 	i915_gem_object_put(obj);
-out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
@@ -1239,6 +1229,9 @@ static void track_vma_bind(struct i915_vma *vma)
 	atomic_inc(&obj->bind_count); /* track for eviction later */
 	__i915_gem_object_pin_pages(obj);
 
+	GEM_BUG_ON(vma->pages);
+	atomic_set(&vma->pages_count, I915_VMA_PAGES_ACTIVE);
+	__i915_gem_object_pin_pages(obj);
 	vma->pages = obj->mm.pages;
 
 	mutex_lock(&vma->vm->mutex);
@@ -1336,11 +1329,13 @@ static int igt_gtt_reserve(void *arg)
 			goto out;
 		}
 
+		mutex_lock(&ggtt->vm.mutex);
 		err = i915_gem_gtt_reserve(&ggtt->vm, &vma->node,
 					   obj->base.size,
 					   total,
 					   obj->cache_level,
 					   0);
+		mutex_unlock(&ggtt->vm.mutex);
 		if (err) {
 			pr_err("i915_gem_gtt_reserve (pass 1) failed at %llu/%llu with err=%d\n",
 			       total, ggtt->vm.total, err);
@@ -1386,11 +1381,13 @@ static int igt_gtt_reserve(void *arg)
 			goto out;
 		}
 
+		mutex_lock(&ggtt->vm.mutex);
 		err = i915_gem_gtt_reserve(&ggtt->vm, &vma->node,
 					   obj->base.size,
 					   total,
 					   obj->cache_level,
 					   0);
+		mutex_unlock(&ggtt->vm.mutex);
 		if (err) {
 			pr_err("i915_gem_gtt_reserve (pass 2) failed at %llu/%llu with err=%d\n",
 			       total, ggtt->vm.total, err);
@@ -1431,11 +1428,13 @@ static int igt_gtt_reserve(void *arg)
 					   2 * I915_GTT_PAGE_SIZE,
 					   I915_GTT_MIN_ALIGNMENT);
 
+		mutex_lock(&ggtt->vm.mutex);
 		err = i915_gem_gtt_reserve(&ggtt->vm, &vma->node,
 					   obj->base.size,
 					   offset,
 					   obj->cache_level,
 					   0);
+		mutex_unlock(&ggtt->vm.mutex);
 		if (err) {
 			pr_err("i915_gem_gtt_reserve (pass 3) failed at %llu/%llu with err=%d\n",
 			       total, ggtt->vm.total, err);
@@ -1504,11 +1503,13 @@ static int igt_gtt_insert(void *arg)
 
 	/* Check a couple of obviously invalid requests */
 	for (ii = invalid_insert; ii->size; ii++) {
+		mutex_lock(&ggtt->vm.mutex);
 		err = i915_gem_gtt_insert(&ggtt->vm, &tmp,
 					  ii->size, ii->alignment,
 					  I915_COLOR_UNEVICTABLE,
 					  ii->start, ii->end,
 					  0);
+		mutex_unlock(&ggtt->vm.mutex);
 		if (err != -ENOSPC) {
 			pr_err("Invalid i915_gem_gtt_insert(.size=%llx, .alignment=%llx, .start=%llx, .end=%llx) succeeded (err=%d)\n",
 			       ii->size, ii->alignment, ii->start, ii->end,
@@ -1544,10 +1545,12 @@ static int igt_gtt_insert(void *arg)
 			goto out;
 		}
 
+		mutex_lock(&ggtt->vm.mutex);
 		err = i915_gem_gtt_insert(&ggtt->vm, &vma->node,
 					  obj->base.size, 0, obj->cache_level,
 					  0, ggtt->vm.total,
 					  0);
+		mutex_unlock(&ggtt->vm.mutex);
 		if (err == -ENOSPC) {
 			/* maxed out the GGTT space */
 			i915_gem_object_put(obj);
@@ -1602,10 +1605,12 @@ static int igt_gtt_insert(void *arg)
 			goto out;
 		}
 
+		mutex_lock(&ggtt->vm.mutex);
 		err = i915_gem_gtt_insert(&ggtt->vm, &vma->node,
 					  obj->base.size, 0, obj->cache_level,
 					  0, ggtt->vm.total,
 					  0);
+		mutex_unlock(&ggtt->vm.mutex);
 		if (err) {
 			pr_err("i915_gem_gtt_insert (pass 2) failed at %llu/%llu with err=%d\n",
 			       total, ggtt->vm.total, err);
@@ -1649,10 +1654,12 @@ static int igt_gtt_insert(void *arg)
 			goto out;
 		}
 
+		mutex_lock(&ggtt->vm.mutex);
 		err = i915_gem_gtt_insert(&ggtt->vm, &vma->node,
 					  obj->base.size, 0, obj->cache_level,
 					  0, ggtt->vm.total,
 					  0);
+		mutex_unlock(&ggtt->vm.mutex);
 		if (err) {
 			pr_err("i915_gem_gtt_insert (pass 3) failed at %llu/%llu with err=%d\n",
 			       total, ggtt->vm.total, err);
@@ -1696,8 +1703,9 @@ int i915_gem_gtt_mock_selftests(void)
 	}
 	mock_init_ggtt(i915, ggtt);
 
-	mutex_lock(&i915->drm.struct_mutex);
 	err = i915_subtests(tests, ggtt);
+
+	mutex_lock(&i915->drm.struct_mutex);
 	mock_device_flush(i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 57cd4180d06c..eb175da48547 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -647,8 +647,15 @@ static struct i915_vma *empty_batch(struct drm_i915_private *i915)
 	if (err)
 		goto err;
 
+	/* Force the wait wait now to avoid including it in the benchmark */
+	err = i915_vma_sync(vma);
+	if (err)
+		goto err_pin;
+
 	return vma;
 
+err_pin:
+	i915_vma_unpin(vma);
 err:
 	i915_gem_object_put(obj);
 	return ERR_PTR(err);
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index 97752deecccb..0e4f66312b39 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -831,8 +831,9 @@ int i915_vma_mock_selftests(void)
 	}
 	mock_init_ggtt(i915, ggtt);
 
-	mutex_lock(&i915->drm.struct_mutex);
 	err = i915_subtests(tests, ggtt);
+
+	mutex_lock(&i915->drm.struct_mutex);
 	mock_device_flush(i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
@@ -879,8 +880,6 @@ static int igt_vma_remapped_gtt(void *arg)
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 
 	for (t = types; *t; t++) {
@@ -976,7 +975,6 @@ static int igt_vma_remapped_gtt(void *arg)
 
 out:
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	i915_gem_object_put(obj);
 
 	return err;
-- 
cgit v1.2.3


From 274cbf20fd108fa26d0497282b102e00371210fd Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:39:59 +0100
Subject: drm/i915: Push the i915_active.retire into a worker

As we need to use a mutex to serialise i915_active activation
(because we want to allow the callback to sleep), we need to push the
i915_active.retire into a worker callback in case we get need to retire
from an atomic context.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-5-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/display/intel_frontbuffer.c |  4 ++-
 drivers/gpu/drm/i915/gem/i915_gem_context.c      |  1 +
 drivers/gpu/drm/i915/gt/intel_context.c          |  2 ++
 drivers/gpu/drm/i915/gt/intel_engine_pool.c      |  1 +
 drivers/gpu/drm/i915/gt/intel_timeline.c         |  1 +
 drivers/gpu/drm/i915/i915_active.c               | 34 +++++++++++++++++++++---
 drivers/gpu/drm/i915/i915_active_types.h         | 13 ++++++++-
 drivers/gpu/drm/i915/i915_vma.c                  |  2 ++
 drivers/gpu/drm/i915/selftests/i915_active.c     |  6 ++---
 9 files changed, 55 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
index fc40dc1fdbcc..6428b8dd70d3 100644
--- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
@@ -206,6 +206,7 @@ static int frontbuffer_active(struct i915_active *ref)
 	return 0;
 }
 
+__i915_active_call
 static void frontbuffer_retire(struct i915_active *ref)
 {
 	struct intel_frontbuffer *front =
@@ -257,7 +258,8 @@ intel_frontbuffer_get(struct drm_i915_gem_object *obj)
 	kref_init(&front->ref);
 	atomic_set(&front->bits, 0);
 	i915_active_init(i915, &front->write,
-			 frontbuffer_active, frontbuffer_retire);
+			 frontbuffer_active,
+			 i915_active_may_sleep(frontbuffer_retire));
 
 	spin_lock(&i915->fb_tracking.lock);
 	if (obj->frontbuffer) {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 95f8e66e45db..4cd7d2ecf1d5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -848,6 +848,7 @@ struct context_barrier_task {
 	void *data;
 };
 
+__i915_active_call
 static void cb_retire(struct i915_active *base)
 {
 	struct context_barrier_task *cb = container_of(base, typeof(*cb), base);
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 26cb838c272c..06fabdf205cf 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -138,6 +138,7 @@ static void __context_unpin_state(struct i915_vma *vma)
 	__i915_vma_unpin(vma);
 }
 
+__i915_active_call
 static void __intel_context_retire(struct i915_active *active)
 {
 	struct intel_context *ce = container_of(active, typeof(*ce), active);
@@ -150,6 +151,7 @@ static void __intel_context_retire(struct i915_active *active)
 
 	intel_timeline_unpin(ce->timeline);
 	intel_ring_unpin(ce->ring);
+
 	intel_context_put(ce);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pool.c b/drivers/gpu/drm/i915/gt/intel_engine_pool.c
index 97d36cca8ded..81fab101fdb4 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pool.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pool.c
@@ -61,6 +61,7 @@ static int pool_active(struct i915_active *ref)
 	return 0;
 }
 
+__i915_active_call
 static void pool_retire(struct i915_active *ref)
 {
 	struct intel_engine_pool_node *node =
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 9d436e14ea8d..653f60e78392 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -136,6 +136,7 @@ static void __idle_cacheline_free(struct intel_timeline_cacheline *cl)
 	kfree(cl);
 }
 
+__i915_active_call
 static void __cacheline_retire(struct i915_active *active)
 {
 	struct intel_timeline_cacheline *cl =
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 0791736a08fd..7ca066688b98 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -132,6 +132,7 @@ __active_retire(struct i915_active *ref)
 	bool retire = false;
 
 	lockdep_assert_held(&ref->mutex);
+	GEM_BUG_ON(i915_active_is_idle(ref));
 
 	/* return the unused nodes to our slabcache -- flushing the allocator */
 	if (atomic_dec_and_test(&ref->count)) {
@@ -157,6 +158,19 @@ __active_retire(struct i915_active *ref)
 		ref->retire(ref);
 }
 
+static void
+active_work(struct work_struct *wrk)
+{
+	struct i915_active *ref = container_of(wrk, typeof(*ref), work);
+
+	GEM_BUG_ON(!atomic_read(&ref->count));
+	if (atomic_add_unless(&ref->count, -1, 1))
+		return;
+
+	mutex_lock(&ref->mutex);
+	__active_retire(ref);
+}
+
 static void
 active_retire(struct i915_active *ref)
 {
@@ -164,8 +178,13 @@ active_retire(struct i915_active *ref)
 	if (atomic_add_unless(&ref->count, -1, 1))
 		return;
 
-	/* One active may be flushed from inside the acquire of another */
-	mutex_lock_nested(&ref->mutex, SINGLE_DEPTH_NESTING);
+	/* If we are inside interrupt context (fence signaling), defer */
+	if (ref->flags & I915_ACTIVE_RETIRE_SLEEPS ||
+	    !mutex_trylock(&ref->mutex)) {
+		queue_work(system_unbound_wq, &ref->work);
+		return;
+	}
+
 	__active_retire(ref);
 }
 
@@ -240,12 +259,16 @@ void __i915_active_init(struct drm_i915_private *i915,
 			void (*retire)(struct i915_active *ref),
 			struct lock_class_key *key)
 {
+	unsigned long bits;
+
 	debug_active_init(ref);
 
 	ref->i915 = i915;
 	ref->flags = 0;
 	ref->active = active;
-	ref->retire = retire;
+	ref->retire = ptr_unpack_bits(retire, &bits, 2);
+	if (bits & I915_ACTIVE_MAY_SLEEP)
+		ref->flags |= I915_ACTIVE_RETIRE_SLEEPS;
 
 	ref->excl = NULL;
 	ref->tree = RB_ROOT;
@@ -253,6 +276,7 @@ void __i915_active_init(struct drm_i915_private *i915,
 	init_llist_head(&ref->preallocated_barriers);
 	atomic_set(&ref->count, 0);
 	__mutex_init(&ref->mutex, "i915_active", key);
+	INIT_WORK(&ref->work, active_work);
 }
 
 static bool ____active_del_barrier(struct i915_active *ref,
@@ -504,6 +528,7 @@ out:
 	if (wait_on_bit(&ref->flags, I915_ACTIVE_GRAB_BIT, TASK_KILLABLE))
 		return -EINTR;
 
+	flush_work(&ref->work);
 	if (!i915_active_is_idle(ref))
 		return -EBUSY;
 
@@ -544,8 +569,9 @@ int i915_request_await_active(struct i915_request *rq, struct i915_active *ref)
 void i915_active_fini(struct i915_active *ref)
 {
 	debug_active_fini(ref);
-	GEM_BUG_ON(!RB_EMPTY_ROOT(&ref->tree));
 	GEM_BUG_ON(atomic_read(&ref->count));
+	GEM_BUG_ON(work_pending(&ref->work));
+	GEM_BUG_ON(!RB_EMPTY_ROOT(&ref->tree));
 	mutex_destroy(&ref->mutex);
 }
 #endif
diff --git a/drivers/gpu/drm/i915/i915_active_types.h b/drivers/gpu/drm/i915/i915_active_types.h
index 86e7a232ea3c..021167f0004d 100644
--- a/drivers/gpu/drm/i915/i915_active_types.h
+++ b/drivers/gpu/drm/i915/i915_active_types.h
@@ -13,6 +13,9 @@
 #include <linux/mutex.h>
 #include <linux/rbtree.h>
 #include <linux/rcupdate.h>
+#include <linux/workqueue.h>
+
+#include "i915_utils.h"
 
 struct drm_i915_private;
 struct i915_active_request;
@@ -44,6 +47,11 @@ struct i915_active_request {
 
 struct active_node;
 
+#define I915_ACTIVE_MAY_SLEEP BIT(0)
+
+#define __i915_active_call __aligned(4)
+#define i915_active_may_sleep(fn) ptr_pack_bits(&(fn), I915_ACTIVE_MAY_SLEEP, 2)
+
 struct i915_active {
 	struct drm_i915_private *i915;
 
@@ -57,11 +65,14 @@ struct i915_active {
 	struct dma_fence_cb excl_cb;
 
 	unsigned long flags;
-#define I915_ACTIVE_GRAB_BIT 0
+#define I915_ACTIVE_RETIRE_SLEEPS BIT(0)
+#define I915_ACTIVE_GRAB_BIT 1
 
 	int (*active)(struct i915_active *ref);
 	void (*retire)(struct i915_active *ref);
 
+	struct work_struct work;
+
 	struct llist_head preallocated_barriers;
 };
 
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index fe91a0e47b88..e191247c7c5f 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -91,6 +91,7 @@ static int __i915_vma_active(struct i915_active *ref)
 	return i915_vma_tryget(active_to_vma(ref)) ? 0 : -ENOENT;
 }
 
+__i915_active_call
 static void __i915_vma_retire(struct i915_active *ref)
 {
 	i915_vma_put(active_to_vma(ref));
@@ -1152,6 +1153,7 @@ int __i915_vma_unbind(struct i915_vma *vma)
 		return -EBUSY;
 	}
 
+	GEM_BUG_ON(i915_vma_is_active(vma));
 	if (!drm_mm_node_allocated(&vma->node))
 		return 0;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
index afecfa081ff4..a41785822ed9 100644
--- a/drivers/gpu/drm/i915/selftests/i915_active.c
+++ b/drivers/gpu/drm/i915/selftests/i915_active.c
@@ -121,7 +121,7 @@ __live_active_setup(struct drm_i915_private *i915)
 	}
 
 	i915_active_release(&active->base);
-	if (active->retired && count) {
+	if (READ_ONCE(active->retired) && count) {
 		pr_err("i915_active retired before submission!\n");
 		err = -EINVAL;
 	}
@@ -161,7 +161,7 @@ static int live_active_wait(void *arg)
 	}
 
 	i915_active_wait(&active->base);
-	if (!active->retired) {
+	if (!READ_ONCE(active->retired)) {
 		pr_err("i915_active not retired after waiting!\n");
 		err = -EINVAL;
 	}
@@ -200,7 +200,7 @@ static int live_active_retire(void *arg)
 	if (igt_flush_test(i915, I915_WAIT_LOCKED))
 		err = -EIO;
 
-	if (!active->retired) {
+	if (!READ_ONCE(active->retired)) {
 		pr_err("i915_active not retired after flushing!\n");
 		err = -EINVAL;
 	}
-- 
cgit v1.2.3


From b1e3177bd1d8f41e2a9cc847e56a96cdc0eefe62 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:00 +0100
Subject: drm/i915: Coordinate i915_active with its own mutex

Forgo the struct_mutex serialisation for i915_active, and interpose its
own mutex handling for active/retire.

This is a multi-layered sleight-of-hand. First, we had to ensure that no
active/retire callbacks accidentally inverted the mutex ordering rules,
nor assumed that they were themselves serialised by struct_mutex. More
challenging though, is the rule over updating elements of the active
rbtree. Instead of the whole i915_active now being serialised by
struct_mutex, allocations/rotations of the tree are serialised by the
i915_active.mutex and individual nodes are serialised by the caller
using the i915_timeline.mutex (we need to use nested spinlocks to
interact with the dma_fence callback lists).

The pain point here is that instead of a single mutex around execbuf, we
now have to take a mutex for active tracker (one for each vma, context,
etc) and a couple of spinlocks for each fence update. The improvement in
fine grained locking allowing for multiple concurrent clients
(eventually!) should be worth it in typical loads.

v2: Add some comments that barely elucidate anything :(

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-6-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/display/intel_frontbuffer.c  |   2 +-
 drivers/gpu/drm/i915/display/intel_overlay.c      |   3 +-
 drivers/gpu/drm/i915/gem/i915_gem_context.c       |   4 +-
 drivers/gpu/drm/i915/gem/i915_gem_object_types.h  |   1 +
 drivers/gpu/drm/i915/gem/i915_gem_pm.c            |   9 +-
 drivers/gpu/drm/i915/gt/intel_context.c           |   4 +-
 drivers/gpu/drm/i915/gt/intel_engine_pool.c       |   2 +-
 drivers/gpu/drm/i915/gt/intel_reset.c             |  10 +-
 drivers/gpu/drm/i915/gt/intel_timeline.c          |   7 +-
 drivers/gpu/drm/i915/gt/intel_timeline_types.h    |   9 +-
 drivers/gpu/drm/i915/gt/selftest_context.c        |  16 +-
 drivers/gpu/drm/i915/gt/selftest_lrc.c            |  10 +-
 drivers/gpu/drm/i915/gt/selftests/mock_timeline.c |   2 +-
 drivers/gpu/drm/i915/gvt/scheduler.c              |   3 -
 drivers/gpu/drm/i915/i915_active.c                | 322 +++++++++++-----------
 drivers/gpu/drm/i915/i915_active.h                | 319 ++++-----------------
 drivers/gpu/drm/i915/i915_active_types.h          |  23 +-
 drivers/gpu/drm/i915/i915_gem.c                   |  42 +--
 drivers/gpu/drm/i915/i915_gem_gtt.c               |   3 +-
 drivers/gpu/drm/i915/i915_gpu_error.c             |   4 +-
 drivers/gpu/drm/i915/i915_request.c               |  38 +--
 drivers/gpu/drm/i915/i915_request.h               |   1 -
 drivers/gpu/drm/i915/i915_vma.c                   |   4 +-
 drivers/gpu/drm/i915/selftests/i915_active.c      |  32 +--
 24 files changed, 298 insertions(+), 572 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
index 6428b8dd70d3..84b164f31895 100644
--- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c
@@ -257,7 +257,7 @@ intel_frontbuffer_get(struct drm_i915_gem_object *obj)
 	front->obj = obj;
 	kref_init(&front->ref);
 	atomic_set(&front->bits, 0);
-	i915_active_init(i915, &front->write,
+	i915_active_init(&front->write,
 			 frontbuffer_active,
 			 i915_active_may_sleep(frontbuffer_retire));
 
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 3f4ac1ee7668..e12e1a753af0 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -1360,8 +1360,7 @@ void intel_overlay_setup(struct drm_i915_private *dev_priv)
 	overlay->contrast = 75;
 	overlay->saturation = 146;
 
-	i915_active_init(dev_priv,
-			 &overlay->last_flip,
+	i915_active_init(&overlay->last_flip,
 			 NULL, intel_overlay_last_flip_retire);
 
 	ret = get_registers(overlay, OVERLAY_NEEDS_PHYSICAL(dev_priv));
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 4cd7d2ecf1d5..9d85aab68d34 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -868,20 +868,18 @@ static int context_barrier_task(struct i915_gem_context *ctx,
 				void (*task)(void *data),
 				void *data)
 {
-	struct drm_i915_private *i915 = ctx->i915;
 	struct context_barrier_task *cb;
 	struct i915_gem_engines_iter it;
 	struct intel_context *ce;
 	int err = 0;
 
-	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(!task);
 
 	cb = kmalloc(sizeof(*cb), GFP_KERNEL);
 	if (!cb)
 		return -ENOMEM;
 
-	i915_active_init(i915, &cb->base, NULL, cb_retire);
+	i915_active_init(&cb->base, NULL, cb_retire);
 	err = i915_active_acquire(&cb->base);
 	if (err) {
 		kfree(cb);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index e1aab2fd1cd9..c00b4f077f9e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -8,6 +8,7 @@
 #define __I915_GEM_OBJECT_TYPES_H__
 
 #include <drm/drm_gem.h>
+#include <uapi/drm/i915_drm.h>
 
 #include "i915_active.h"
 #include "i915_selftest.h"
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index cca192ecff8b..0a4115c6c275 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -16,14 +16,11 @@ static void call_idle_barriers(struct intel_engine_cs *engine)
 	struct llist_node *node, *next;
 
 	llist_for_each_safe(node, next, llist_del_all(&engine->barrier_tasks)) {
-		struct i915_active_request *active =
+		struct dma_fence_cb *cb =
 			container_of((struct list_head *)node,
-				     typeof(*active), link);
+				     typeof(*cb), node);
 
-		INIT_LIST_HEAD(&active->link);
-		RCU_INIT_POINTER(active->request, NULL);
-
-		active->retire(active, NULL);
+		cb->func(NULL, cb);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 06fabdf205cf..35a40c2820a2 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -240,7 +240,7 @@ intel_context_init(struct intel_context *ce,
 
 	mutex_init(&ce->pin_mutex);
 
-	i915_active_init(ctx->i915, &ce->active,
+	i915_active_init(&ce->active,
 			 __intel_context_active, __intel_context_retire);
 }
 
@@ -307,7 +307,7 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 			return err;
 
 		/* Queue this switch after current activity by this context. */
-		err = i915_active_request_set(&tl->last_request, rq);
+		err = i915_active_fence_set(&tl->last_request, rq);
 		mutex_unlock(&tl->mutex);
 		if (err)
 			return err;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pool.c b/drivers/gpu/drm/i915/gt/intel_engine_pool.c
index 81fab101fdb4..3cdbd5f8b5be 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pool.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pool.c
@@ -95,7 +95,7 @@ node_create(struct intel_engine_pool *pool, size_t sz)
 		return ERR_PTR(-ENOMEM);
 
 	node->pool = pool;
-	i915_active_init(engine->i915, &node->active, pool_active, pool_retire);
+	i915_active_init(&node->active, pool_active, pool_retire);
 
 	obj = i915_gem_object_create_internal(engine->i915, sz);
 	if (IS_ERR(obj)) {
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index e189897e8797..055496f0825f 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -844,10 +844,10 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	 */
 	spin_lock_irqsave(&timelines->lock, flags);
 	list_for_each_entry(tl, &timelines->active_list, link) {
-		struct i915_request *rq;
+		struct dma_fence *fence;
 
-		rq = i915_active_request_get_unlocked(&tl->last_request);
-		if (!rq)
+		fence = i915_active_fence_get(&tl->last_request);
+		if (!fence)
 			continue;
 
 		spin_unlock_irqrestore(&timelines->lock, flags);
@@ -859,8 +859,8 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 		 * (I915_FENCE_TIMEOUT) so this wait should not be unbounded
 		 * in the worst case.
 		 */
-		dma_fence_default_wait(&rq->fence, false, MAX_SCHEDULE_TIMEOUT);
-		i915_request_put(rq);
+		dma_fence_default_wait(fence, false, MAX_SCHEDULE_TIMEOUT);
+		dma_fence_put(fence);
 
 		/* Restart iteration after droping lock */
 		spin_lock_irqsave(&timelines->lock, flags);
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 653f60e78392..0f959694303c 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -178,8 +178,7 @@ cacheline_alloc(struct intel_timeline_hwsp *hwsp, unsigned int cacheline)
 	cl->hwsp = hwsp;
 	cl->vaddr = page_pack_bits(vaddr, cacheline);
 
-	i915_active_init(hwsp->gt->i915, &cl->active,
-			 __cacheline_active, __cacheline_retire);
+	i915_active_init(&cl->active, __cacheline_active, __cacheline_retire);
 
 	return cl;
 }
@@ -255,7 +254,7 @@ int intel_timeline_init(struct intel_timeline *timeline,
 
 	mutex_init(&timeline->mutex);
 
-	INIT_ACTIVE_REQUEST(&timeline->last_request, &timeline->mutex);
+	INIT_ACTIVE_FENCE(&timeline->last_request, &timeline->mutex);
 	INIT_LIST_HEAD(&timeline->requests);
 
 	i915_syncmap_init(&timeline->sync);
@@ -443,7 +442,7 @@ __intel_timeline_get_seqno(struct intel_timeline *tl,
 	 * free it after the current request is retired, which ensures that
 	 * all writes into the cacheline from previous requests are complete.
 	 */
-	err = i915_active_ref(&tl->hwsp_cacheline->active, tl, rq);
+	err = i915_active_ref(&tl->hwsp_cacheline->active, tl, &rq->fence);
 	if (err)
 		goto err_cacheline;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
index c668c4c50e75..98d9ee166379 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
@@ -58,12 +58,13 @@ struct intel_timeline {
 	 */
 	struct list_head requests;
 
-	/* Contains an RCU guarded pointer to the last request. No reference is
+	/*
+	 * Contains an RCU guarded pointer to the last request. No reference is
 	 * held to the request, users must carefully acquire a reference to
-	 * the request using i915_active_request_get_request_rcu(), or hold the
-	 * struct_mutex.
+	 * the request using i915_active_fence_get(), or manage the RCU
+	 * protection themselves (cf the i915_active_fence API).
 	 */
-	struct i915_active_request last_request;
+	struct i915_active_fence last_request;
 
 	/**
 	 * We track the most recent seqno that we wait on in every context so
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index 4ce1e25433d2..e6bcbe7ab5e1 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -47,24 +47,20 @@ static int context_sync(struct intel_context *ce)
 
 	mutex_lock(&tl->mutex);
 	do {
-		struct i915_request *rq;
+		struct dma_fence *fence;
 		long timeout;
 
-		rcu_read_lock();
-		rq = rcu_dereference(tl->last_request.request);
-		if (rq)
-			rq = i915_request_get_rcu(rq);
-		rcu_read_unlock();
-		if (!rq)
+		fence = i915_active_fence_get(&tl->last_request);
+		if (!fence)
 			break;
 
-		timeout = i915_request_wait(rq, 0, HZ / 10);
+		timeout = dma_fence_wait_timeout(fence, false, HZ / 10);
 		if (timeout < 0)
 			err = timeout;
 		else
-			i915_request_retire_upto(rq);
+			i915_request_retire_upto(to_request(fence));
 
-		i915_request_put(rq);
+		dma_fence_put(fence);
 	} while (!err);
 	mutex_unlock(&tl->mutex);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index e7bc2dbbb2a5..dd25636abc5b 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -1172,9 +1172,13 @@ static struct i915_request *dummy_request(struct intel_engine_cs *engine)
 	if (!rq)
 		return NULL;
 
-	INIT_LIST_HEAD(&rq->active_list);
 	rq->engine = engine;
 
+	spin_lock_init(&rq->lock);
+	INIT_LIST_HEAD(&rq->fence.cb_list);
+	rq->fence.lock = &rq->lock;
+	rq->fence.ops = &i915_fence_ops;
+
 	i915_sched_node_init(&rq->sched);
 
 	/* mark this request as permanently incomplete */
@@ -1267,8 +1271,8 @@ static int live_suppress_wait_preempt(void *arg)
 				}
 
 				/* Disable NEWCLIENT promotion */
-				__i915_active_request_set(&i915_request_timeline(rq[i])->last_request,
-							  dummy);
+				__i915_active_fence_set(&i915_request_timeline(rq[i])->last_request,
+							&dummy->fence);
 				i915_request_add(rq[i]);
 			}
 
diff --git a/drivers/gpu/drm/i915/gt/selftests/mock_timeline.c b/drivers/gpu/drm/i915/gt/selftests/mock_timeline.c
index 598170efcaf6..2a77c051f36a 100644
--- a/drivers/gpu/drm/i915/gt/selftests/mock_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftests/mock_timeline.c
@@ -15,7 +15,7 @@ void mock_timeline_init(struct intel_timeline *timeline, u64 context)
 
 	mutex_init(&timeline->mutex);
 
-	INIT_ACTIVE_REQUEST(&timeline->last_request, &timeline->mutex);
+	INIT_ACTIVE_FENCE(&timeline->last_request, &timeline->mutex);
 	INIT_LIST_HEAD(&timeline->requests);
 
 	i915_syncmap_init(&timeline->sync);
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 1a28e3666951..7052c90d937f 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -385,11 +385,8 @@ intel_gvt_workload_req_alloc(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	struct i915_request *rq;
 
-	lockdep_assert_held(&dev_priv->drm.struct_mutex);
-
 	if (workload->req)
 		return 0;
 
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 7ca066688b98..023652ded4be 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -12,8 +12,6 @@
 #include "i915_active.h"
 #include "i915_globals.h"
 
-#define BKL(ref) (&(ref)->i915->drm.struct_mutex)
-
 /*
  * Active refs memory management
  *
@@ -27,35 +25,35 @@ static struct i915_global_active {
 } global;
 
 struct active_node {
-	struct i915_active_request base;
+	struct i915_active_fence base;
 	struct i915_active *ref;
 	struct rb_node node;
 	u64 timeline;
 };
 
 static inline struct active_node *
-node_from_active(struct i915_active_request *active)
+node_from_active(struct i915_active_fence *active)
 {
 	return container_of(active, struct active_node, base);
 }
 
 #define take_preallocated_barriers(x) llist_del_all(&(x)->preallocated_barriers)
 
-static inline bool is_barrier(const struct i915_active_request *active)
+static inline bool is_barrier(const struct i915_active_fence *active)
 {
-	return IS_ERR(rcu_access_pointer(active->request));
+	return IS_ERR(rcu_access_pointer(active->fence));
 }
 
 static inline struct llist_node *barrier_to_ll(struct active_node *node)
 {
 	GEM_BUG_ON(!is_barrier(&node->base));
-	return (struct llist_node *)&node->base.link;
+	return (struct llist_node *)&node->base.cb.node;
 }
 
 static inline struct intel_engine_cs *
 __barrier_to_engine(struct active_node *node)
 {
-	return (struct intel_engine_cs *)READ_ONCE(node->base.link.prev);
+	return (struct intel_engine_cs *)READ_ONCE(node->base.cb.node.prev);
 }
 
 static inline struct intel_engine_cs *
@@ -68,7 +66,7 @@ barrier_to_engine(struct active_node *node)
 static inline struct active_node *barrier_from_ll(struct llist_node *x)
 {
 	return container_of((struct list_head *)x,
-			    struct active_node, base.link);
+			    struct active_node, base.cb.node);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) && IS_ENABLED(CONFIG_DEBUG_OBJECTS)
@@ -147,15 +145,18 @@ __active_retire(struct i915_active *ref)
 	if (!retire)
 		return;
 
-	GEM_BUG_ON(rcu_access_pointer(ref->excl));
+	GEM_BUG_ON(rcu_access_pointer(ref->excl.fence));
 	rbtree_postorder_for_each_entry_safe(it, n, &root, node) {
-		GEM_BUG_ON(i915_active_request_isset(&it->base));
+		GEM_BUG_ON(i915_active_fence_isset(&it->base));
 		kmem_cache_free(global.slab_cache, it);
 	}
 
 	/* After the final retire, the entire struct may be freed */
 	if (ref->retire)
 		ref->retire(ref);
+
+	/* ... except if you wait on it, you must manage your own references! */
+	wake_up_var(ref);
 }
 
 static void
@@ -189,12 +190,20 @@ active_retire(struct i915_active *ref)
 }
 
 static void
-node_retire(struct i915_active_request *base, struct i915_request *rq)
+node_retire(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	active_retire(node_from_active(base)->ref);
+	i915_active_fence_cb(fence, cb);
+	active_retire(container_of(cb, struct active_node, base.cb)->ref);
 }
 
-static struct i915_active_request *
+static void
+excl_retire(struct dma_fence *fence, struct dma_fence_cb *cb)
+{
+	i915_active_fence_cb(fence, cb);
+	active_retire(container_of(cb, struct i915_active, excl.cb));
+}
+
+static struct i915_active_fence *
 active_instance(struct i915_active *ref, struct intel_timeline *tl)
 {
 	struct active_node *node, *prealloc;
@@ -238,7 +247,7 @@ active_instance(struct i915_active *ref, struct intel_timeline *tl)
 	}
 
 	node = prealloc;
-	i915_active_request_init(&node->base, &tl->mutex, NULL, node_retire);
+	__i915_active_fence_init(&node->base, &tl->mutex, NULL, node_retire);
 	node->ref = ref;
 	node->timeline = idx;
 
@@ -253,8 +262,7 @@ out:
 	return &node->base;
 }
 
-void __i915_active_init(struct drm_i915_private *i915,
-			struct i915_active *ref,
+void __i915_active_init(struct i915_active *ref,
 			int (*active)(struct i915_active *ref),
 			void (*retire)(struct i915_active *ref),
 			struct lock_class_key *key)
@@ -263,19 +271,18 @@ void __i915_active_init(struct drm_i915_private *i915,
 
 	debug_active_init(ref);
 
-	ref->i915 = i915;
 	ref->flags = 0;
 	ref->active = active;
 	ref->retire = ptr_unpack_bits(retire, &bits, 2);
 	if (bits & I915_ACTIVE_MAY_SLEEP)
 		ref->flags |= I915_ACTIVE_RETIRE_SLEEPS;
 
-	ref->excl = NULL;
 	ref->tree = RB_ROOT;
 	ref->cache = NULL;
 	init_llist_head(&ref->preallocated_barriers);
 	atomic_set(&ref->count, 0);
 	__mutex_init(&ref->mutex, "i915_active", key);
+	__i915_active_fence_init(&ref->excl, &ref->mutex, NULL, excl_retire);
 	INIT_WORK(&ref->work, active_work);
 }
 
@@ -329,9 +336,9 @@ __active_del_barrier(struct i915_active *ref, struct active_node *node)
 
 int i915_active_ref(struct i915_active *ref,
 		    struct intel_timeline *tl,
-		    struct i915_request *rq)
+		    struct dma_fence *fence)
 {
-	struct i915_active_request *active;
+	struct i915_active_fence *active;
 	int err;
 
 	lockdep_assert_held(&tl->mutex);
@@ -354,66 +361,44 @@ int i915_active_ref(struct i915_active *ref,
 		 * request that we want to emit on the kernel_context.
 		 */
 		__active_del_barrier(ref, node_from_active(active));
-		RCU_INIT_POINTER(active->request, NULL);
-		INIT_LIST_HEAD(&active->link);
-	} else {
-		if (!i915_active_request_isset(active))
-			atomic_inc(&ref->count);
+		RCU_INIT_POINTER(active->fence, NULL);
+		atomic_dec(&ref->count);
 	}
-	GEM_BUG_ON(!atomic_read(&ref->count));
-	__i915_active_request_set(active, rq);
+	if (!__i915_active_fence_set(active, fence))
+		atomic_inc(&ref->count);
 
 out:
 	i915_active_release(ref);
 	return err;
 }
 
-static void excl_cb(struct dma_fence *f, struct dma_fence_cb *cb)
-{
-	struct i915_active *ref = container_of(cb, typeof(*ref), excl_cb);
-
-	RCU_INIT_POINTER(ref->excl, NULL);
-	dma_fence_put(f);
-
-	active_retire(ref);
-}
-
 void i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f)
 {
 	/* We expect the caller to manage the exclusive timeline ordering */
 	GEM_BUG_ON(i915_active_is_idle(ref));
 
-	dma_fence_get(f);
-
-	rcu_read_lock();
-	if (rcu_access_pointer(ref->excl)) {
-		struct dma_fence *old;
-
-		old = dma_fence_get_rcu_safe(&ref->excl);
-		if (old) {
-			if (dma_fence_remove_callback(old, &ref->excl_cb))
-				atomic_dec(&ref->count);
-			dma_fence_put(old);
-		}
-	}
-	rcu_read_unlock();
-
-	atomic_inc(&ref->count);
-	rcu_assign_pointer(ref->excl, f);
+	/*
+	 * As we don't know which mutex the caller is using, we told a small
+	 * lie to the debug code that it is using the i915_active.mutex;
+	 * and now we must stick to that lie.
+	 */
+	mutex_acquire(&ref->mutex.dep_map, 0, 0, _THIS_IP_);
+	if (!__i915_active_fence_set(&ref->excl, f))
+		atomic_inc(&ref->count);
+	mutex_release(&ref->mutex.dep_map, 0, _THIS_IP_);
+}
 
-	if (dma_fence_add_callback(f, &ref->excl_cb, excl_cb)) {
-		RCU_INIT_POINTER(ref->excl, NULL);
-		atomic_dec(&ref->count);
-		dma_fence_put(f);
-	}
+bool i915_active_acquire_if_busy(struct i915_active *ref)
+{
+	debug_active_assert(ref);
+	return atomic_add_unless(&ref->count, 1, 0);
 }
 
 int i915_active_acquire(struct i915_active *ref)
 {
 	int err;
 
-	debug_active_assert(ref);
-	if (atomic_add_unless(&ref->count, 1, 0))
+	if (i915_active_acquire_if_busy(ref))
 		return 0;
 
 	err = mutex_lock_interruptible(&ref->mutex);
@@ -438,121 +423,57 @@ void i915_active_release(struct i915_active *ref)
 	active_retire(ref);
 }
 
-static void __active_ungrab(struct i915_active *ref)
-{
-	clear_and_wake_up_bit(I915_ACTIVE_GRAB_BIT, &ref->flags);
-}
-
-bool i915_active_trygrab(struct i915_active *ref)
+static void enable_signaling(struct i915_active_fence *active)
 {
-	debug_active_assert(ref);
-
-	if (test_and_set_bit(I915_ACTIVE_GRAB_BIT, &ref->flags))
-		return false;
-
-	if (!atomic_add_unless(&ref->count, 1, 0)) {
-		__active_ungrab(ref);
-		return false;
-	}
+	struct dma_fence *fence;
 
-	return true;
-}
-
-void i915_active_ungrab(struct i915_active *ref)
-{
-	GEM_BUG_ON(!test_bit(I915_ACTIVE_GRAB_BIT, &ref->flags));
-
-	active_retire(ref);
-	__active_ungrab(ref);
-}
-
-static int excl_wait(struct i915_active *ref)
-{
-	struct dma_fence *old;
-	int err = 0;
-
-	if (!rcu_access_pointer(ref->excl))
-		return 0;
-
-	rcu_read_lock();
-	old = dma_fence_get_rcu_safe(&ref->excl);
-	rcu_read_unlock();
-	if (old) {
-		err = dma_fence_wait(old, true);
-		dma_fence_put(old);
-	}
+	fence = i915_active_fence_get(active);
+	if (!fence)
+		return;
 
-	return err;
+	dma_fence_enable_sw_signaling(fence);
+	dma_fence_put(fence);
 }
 
 int i915_active_wait(struct i915_active *ref)
 {
 	struct active_node *it, *n;
-	int err;
+	int err = 0;
 
 	might_sleep();
-	might_lock(&ref->mutex);
-
-	if (i915_active_is_idle(ref))
-		return 0;
-
-	err = mutex_lock_interruptible(&ref->mutex);
-	if (err)
-		return err;
 
-	if (!atomic_add_unless(&ref->count, 1, 0)) {
-		mutex_unlock(&ref->mutex);
+	if (!i915_active_acquire_if_busy(ref))
 		return 0;
-	}
-
-	err = excl_wait(ref);
-	if (err)
-		goto out;
 
+	/* Flush lazy signals */
+	enable_signaling(&ref->excl);
 	rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
-		if (is_barrier(&it->base)) { /* unconnected idle-barrier */
-			err = -EBUSY;
-			break;
-		}
+		if (is_barrier(&it->base)) /* unconnected idle barrier */
+			continue;
 
-		err = i915_active_request_retire(&it->base, BKL(ref));
-		if (err)
-			break;
+		enable_signaling(&it->base);
 	}
+	/* Any fence added after the wait begins will not be auto-signaled */
 
-out:
-	__active_retire(ref);
+	i915_active_release(ref);
 	if (err)
 		return err;
 
-	if (wait_on_bit(&ref->flags, I915_ACTIVE_GRAB_BIT, TASK_KILLABLE))
+	if (wait_var_event_interruptible(ref, i915_active_is_idle(ref)))
 		return -EINTR;
 
-	flush_work(&ref->work);
-	if (!i915_active_is_idle(ref))
-		return -EBUSY;
-
 	return 0;
 }
 
-int i915_request_await_active_request(struct i915_request *rq,
-				      struct i915_active_request *active)
-{
-	struct i915_request *barrier =
-		i915_active_request_raw(active, &rq->i915->drm.struct_mutex);
-
-	return barrier ? i915_request_await_dma_fence(rq, &barrier->fence) : 0;
-}
-
 int i915_request_await_active(struct i915_request *rq, struct i915_active *ref)
 {
 	int err = 0;
 
-	if (rcu_access_pointer(ref->excl)) {
+	if (rcu_access_pointer(ref->excl.fence)) {
 		struct dma_fence *fence;
 
 		rcu_read_lock();
-		fence = dma_fence_get_rcu_safe(&ref->excl);
+		fence = dma_fence_get_rcu_safe(&ref->excl.fence);
 		rcu_read_unlock();
 		if (fence) {
 			err = i915_request_await_dma_fence(rq, fence);
@@ -578,7 +499,7 @@ void i915_active_fini(struct i915_active *ref)
 
 static inline bool is_idle_barrier(struct active_node *node, u64 idx)
 {
-	return node->timeline == idx && !i915_active_request_isset(&node->base);
+	return node->timeline == idx && !i915_active_fence_isset(&node->base);
 }
 
 static struct active_node *reuse_idle_barrier(struct i915_active *ref, u64 idx)
@@ -698,13 +619,13 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 			node->base.lock =
 				&engine->kernel_context->timeline->mutex;
 #endif
-			RCU_INIT_POINTER(node->base.request, NULL);
-			node->base.retire = node_retire;
+			RCU_INIT_POINTER(node->base.fence, NULL);
+			node->base.cb.func = node_retire;
 			node->timeline = idx;
 			node->ref = ref;
 		}
 
-		if (!i915_active_request_isset(&node->base)) {
+		if (!i915_active_fence_isset(&node->base)) {
 			/*
 			 * Mark this as being *our* unconnected proto-node.
 			 *
@@ -714,8 +635,8 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 			 * and then we can use the rb_node and list pointers
 			 * for our tracking of the pending barrier.
 			 */
-			RCU_INIT_POINTER(node->base.request, ERR_PTR(-EAGAIN));
-			node->base.link.prev = (void *)engine;
+			RCU_INIT_POINTER(node->base.fence, ERR_PTR(-EAGAIN));
+			node->base.cb.node.prev = (void *)engine;
 			atomic_inc(&ref->count);
 		}
 
@@ -782,44 +703,113 @@ void i915_request_add_active_barriers(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
 	struct llist_node *node, *next;
+	unsigned long flags;
 
 	GEM_BUG_ON(intel_engine_is_virtual(engine));
 	GEM_BUG_ON(i915_request_timeline(rq) != engine->kernel_context->timeline);
 
+	node = llist_del_all(&engine->barrier_tasks);
+	if (!node)
+		return;
 	/*
 	 * Attach the list of proto-fences to the in-flight request such
 	 * that the parent i915_active will be released when this request
 	 * is retired.
 	 */
-	llist_for_each_safe(node, next, llist_del_all(&engine->barrier_tasks)) {
-		RCU_INIT_POINTER(barrier_from_ll(node)->base.request, rq);
+	spin_lock_irqsave(&rq->lock, flags);
+	llist_for_each_safe(node, next, node) {
+		RCU_INIT_POINTER(barrier_from_ll(node)->base.fence, &rq->fence);
 		smp_wmb(); /* serialise with reuse_idle_barrier */
-		list_add_tail((struct list_head *)node, &rq->active_list);
+		list_add_tail((struct list_head *)node, &rq->fence.cb_list);
+	}
+	spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+#define active_is_held(active) lockdep_is_held((active)->lock)
+#else
+#define active_is_held(active) true
+#endif
+
+/*
+ * __i915_active_fence_set: Update the last active fence along its timeline
+ * @active: the active tracker
+ * @fence: the new fence (under construction)
+ *
+ * Records the new @fence as the last active fence along its timeline in
+ * this active tracker, moving the tracking callbacks from the previous
+ * fence onto this one. Returns the previous fence (if not already completed),
+ * which the caller must ensure is executed before the new fence. To ensure
+ * that the order of fences within the timeline of the i915_active_fence is
+ * maintained, it must be locked by the caller.
+ */
+struct dma_fence *
+__i915_active_fence_set(struct i915_active_fence *active,
+			struct dma_fence *fence)
+{
+	struct dma_fence *prev;
+	unsigned long flags;
+
+	/* NB: must be serialised by an outer timeline mutex (active->lock) */
+	spin_lock_irqsave(fence->lock, flags);
+	GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags));
+
+	prev = rcu_dereference_protected(active->fence, active_is_held(active));
+	if (prev) {
+		GEM_BUG_ON(prev == fence);
+		spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING);
+		__list_del_entry(&active->cb.node);
+		spin_unlock(prev->lock); /* serialise with prev->cb_list */
+
+		/*
+		 * active->fence is reset by the callback from inside
+		 * interrupt context. We need to serialise our list
+		 * manipulation with the fence->lock to prevent the prev
+		 * being lost inside an interrupt (it can't be replaced as
+		 * no other caller is allowed to enter __i915_active_fence_set
+		 * as we hold the timeline lock). After serialising with
+		 * the callback, we need to double check which ran first,
+		 * our list_del() [decoupling prev from the callback] or
+		 * the callback...
+		 */
+		prev = rcu_access_pointer(active->fence);
 	}
+
+	rcu_assign_pointer(active->fence, fence);
+	list_add_tail(&active->cb.node, &fence->cb_list);
+
+	spin_unlock_irqrestore(fence->lock, flags);
+
+	return prev;
 }
 
-int i915_active_request_set(struct i915_active_request *active,
-			    struct i915_request *rq)
+int i915_active_fence_set(struct i915_active_fence *active,
+			  struct i915_request *rq)
 {
-	int err;
+	struct dma_fence *fence;
+	int err = 0;
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
 	lockdep_assert_held(active->lock);
 #endif
 
-	/* Must maintain ordering wrt previous active requests */
-	err = i915_request_await_active_request(rq, active);
-	if (err)
-		return err;
+	/* Must maintain timeline ordering wrt previous active requests */
+	rcu_read_lock();
+	fence = __i915_active_fence_set(active, &rq->fence);
+	if (fence) /* but the previous fence may not belong to that timeline! */
+		fence = dma_fence_get_rcu(fence);
+	rcu_read_unlock();
+	if (fence) {
+		err = i915_request_await_dma_fence(rq, fence);
+		dma_fence_put(fence);
+	}
 
-	__i915_active_request_set(active, rq);
-	return 0;
+	return err;
 }
 
-void i915_active_retire_noop(struct i915_active_request *active,
-			     struct i915_request *request)
+void i915_active_noop(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	/* Space left intentionally blank */
+	i915_active_fence_cb(fence, cb);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index 90034f61b7c2..4f52fe6146d2 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -12,6 +12,10 @@
 #include "i915_active_types.h"
 #include "i915_request.h"
 
+struct i915_request;
+struct intel_engine_cs;
+struct intel_timeline;
+
 /*
  * We treat requests as fences. This is not be to confused with our
  * "fence registers" but pipeline synchronisation objects ala GL_ARB_sync.
@@ -28,308 +32,108 @@
  * write access so that we can perform concurrent read operations between
  * the CPU and GPU engines, as well as waiting for all rendering to
  * complete, or waiting for the last GPU user of a "fence register". The
- * object then embeds a #i915_active_request to track the most recent (in
+ * object then embeds a #i915_active_fence to track the most recent (in
  * retirement order) request relevant for the desired mode of access.
- * The #i915_active_request is updated with i915_active_request_set() to
+ * The #i915_active_fence is updated with i915_active_fence_set() to
  * track the most recent fence request, typically this is done as part of
  * i915_vma_move_to_active().
  *
- * When the #i915_active_request completes (is retired), it will
+ * When the #i915_active_fence completes (is retired), it will
  * signal its completion to the owner through a callback as well as mark
- * itself as idle (i915_active_request.request == NULL). The owner
+ * itself as idle (i915_active_fence.request == NULL). The owner
  * can then perform any action, such as delayed freeing of an active
  * resource including itself.
  */
 
-void i915_active_retire_noop(struct i915_active_request *active,
-			     struct i915_request *request);
+void i915_active_noop(struct dma_fence *fence, struct dma_fence_cb *cb);
 
 /**
- * i915_active_request_init - prepares the activity tracker for use
+ * __i915_active_fence_init - prepares the activity tracker for use
  * @active - the active tracker
- * @rq - initial request to track, can be NULL
+ * @fence - initial fence to track, can be NULL
  * @func - a callback when then the tracker is retired (becomes idle),
  *         can be NULL
  *
- * i915_active_request_init() prepares the embedded @active struct for use as
- * an activity tracker, that is for tracking the last known active request
- * associated with it. When the last request becomes idle, when it is retired
+ * i915_active_fence_init() prepares the embedded @active struct for use as
+ * an activity tracker, that is for tracking the last known active fence
+ * associated with it. When the last fence becomes idle, when it is retired
  * after completion, the optional callback @func is invoked.
  */
 static inline void
-i915_active_request_init(struct i915_active_request *active,
+__i915_active_fence_init(struct i915_active_fence *active,
 			 struct mutex *lock,
-			 struct i915_request *rq,
-			 i915_active_retire_fn retire)
+			 void *fence,
+			 dma_fence_func_t fn)
 {
-	RCU_INIT_POINTER(active->request, rq);
-	INIT_LIST_HEAD(&active->link);
-	active->retire = retire ?: i915_active_retire_noop;
+	RCU_INIT_POINTER(active->fence, fence);
+	active->cb.func = fn ?: i915_active_noop;
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
 	active->lock = lock;
 #endif
 }
 
-#define INIT_ACTIVE_REQUEST(name, lock) \
-	i915_active_request_init((name), (lock), NULL, NULL)
-
-/**
- * i915_active_request_set - updates the tracker to watch the current request
- * @active - the active tracker
- * @request - the request to watch
- *
- * __i915_active_request_set() watches the given @request for completion. Whilst
- * that @request is busy, the @active reports busy. When that @request is
- * retired, the @active tracker is updated to report idle.
- */
-static inline void
-__i915_active_request_set(struct i915_active_request *active,
-			  struct i915_request *request)
-{
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
-	lockdep_assert_held(active->lock);
-#endif
-	list_move(&active->link, &request->active_list);
-	rcu_assign_pointer(active->request, request);
-}
+#define INIT_ACTIVE_FENCE(A, LOCK) \
+	__i915_active_fence_init((A), (LOCK), NULL, NULL)
 
-int __must_check
-i915_active_request_set(struct i915_active_request *active,
-			struct i915_request *rq);
+struct dma_fence *
+__i915_active_fence_set(struct i915_active_fence *active,
+			struct dma_fence *fence);
 
 /**
- * i915_active_request_raw - return the active request
+ * i915_active_fence_set - updates the tracker to watch the current fence
  * @active - the active tracker
+ * @rq - the request to watch
  *
- * i915_active_request_raw() returns the current request being tracked, or NULL.
- * It does not obtain a reference on the request for the caller, so the caller
- * must hold struct_mutex.
+ * i915_active_fence_set() watches the given @rq for completion. While
+ * that @rq is busy, the @active reports busy. When that @rq is signaled
+ * (or else retired) the @active tracker is updated to report idle.
  */
-static inline struct i915_request *
-i915_active_request_raw(const struct i915_active_request *active,
-			struct mutex *mutex)
-{
-	return rcu_dereference_protected(active->request,
-					 lockdep_is_held(mutex));
-}
-
-/**
- * i915_active_request_peek - report the active request being monitored
- * @active - the active tracker
- *
- * i915_active_request_peek() returns the current request being tracked if
- * still active, or NULL. It does not obtain a reference on the request
- * for the caller, so the caller must hold struct_mutex.
- */
-static inline struct i915_request *
-i915_active_request_peek(const struct i915_active_request *active,
-			 struct mutex *mutex)
-{
-	struct i915_request *request;
-
-	request = i915_active_request_raw(active, mutex);
-	if (!request || i915_request_completed(request))
-		return NULL;
-
-	return request;
-}
-
-/**
- * i915_active_request_get - return a reference to the active request
- * @active - the active tracker
- *
- * i915_active_request_get() returns a reference to the active request, or NULL
- * if the active tracker is idle. The caller must hold struct_mutex.
- */
-static inline struct i915_request *
-i915_active_request_get(const struct i915_active_request *active,
-			struct mutex *mutex)
-{
-	return i915_request_get(i915_active_request_peek(active, mutex));
-}
-
-/**
- * __i915_active_request_get_rcu - return a reference to the active request
- * @active - the active tracker
- *
- * __i915_active_request_get() returns a reference to the active request,
- * or NULL if the active tracker is idle. The caller must hold the RCU read
- * lock, but the returned pointer is safe to use outside of RCU.
- */
-static inline struct i915_request *
-__i915_active_request_get_rcu(const struct i915_active_request *active)
-{
-	/*
-	 * Performing a lockless retrieval of the active request is super
-	 * tricky. SLAB_TYPESAFE_BY_RCU merely guarantees that the backing
-	 * slab of request objects will not be freed whilst we hold the
-	 * RCU read lock. It does not guarantee that the request itself
-	 * will not be freed and then *reused*. Viz,
-	 *
-	 * Thread A			Thread B
-	 *
-	 * rq = active.request
-	 *				retire(rq) -> free(rq);
-	 *				(rq is now first on the slab freelist)
-	 *				active.request = NULL
-	 *
-	 *				rq = new submission on a new object
-	 * ref(rq)
-	 *
-	 * To prevent the request from being reused whilst the caller
-	 * uses it, we take a reference like normal. Whilst acquiring
-	 * the reference we check that it is not in a destroyed state
-	 * (refcnt == 0). That prevents the request being reallocated
-	 * whilst the caller holds on to it. To check that the request
-	 * was not reallocated as we acquired the reference we have to
-	 * check that our request remains the active request across
-	 * the lookup, in the same manner as a seqlock. The visibility
-	 * of the pointer versus the reference counting is controlled
-	 * by using RCU barriers (rcu_dereference and rcu_assign_pointer).
-	 *
-	 * In the middle of all that, we inspect whether the request is
-	 * complete. Retiring is lazy so the request may be completed long
-	 * before the active tracker is updated. Querying whether the
-	 * request is complete is far cheaper (as it involves no locked
-	 * instructions setting cachelines to exclusive) than acquiring
-	 * the reference, so we do it first. The RCU read lock ensures the
-	 * pointer dereference is valid, but does not ensure that the
-	 * seqno nor HWS is the right one! However, if the request was
-	 * reallocated, that means the active tracker's request was complete.
-	 * If the new request is also complete, then both are and we can
-	 * just report the active tracker is idle. If the new request is
-	 * incomplete, then we acquire a reference on it and check that
-	 * it remained the active request.
-	 *
-	 * It is then imperative that we do not zero the request on
-	 * reallocation, so that we can chase the dangling pointers!
-	 * See i915_request_alloc().
-	 */
-	do {
-		struct i915_request *request;
-
-		request = rcu_dereference(active->request);
-		if (!request || i915_request_completed(request))
-			return NULL;
-
-		/*
-		 * An especially silly compiler could decide to recompute the
-		 * result of i915_request_completed, more specifically
-		 * re-emit the load for request->fence.seqno. A race would catch
-		 * a later seqno value, which could flip the result from true to
-		 * false. Which means part of the instructions below might not
-		 * be executed, while later on instructions are executed. Due to
-		 * barriers within the refcounting the inconsistency can't reach
-		 * past the call to i915_request_get_rcu, but not executing
-		 * that while still executing i915_request_put() creates
-		 * havoc enough.  Prevent this with a compiler barrier.
-		 */
-		barrier();
-
-		request = i915_request_get_rcu(request);
-
-		/*
-		 * What stops the following rcu_access_pointer() from occurring
-		 * before the above i915_request_get_rcu()? If we were
-		 * to read the value before pausing to get the reference to
-		 * the request, we may not notice a change in the active
-		 * tracker.
-		 *
-		 * The rcu_access_pointer() is a mere compiler barrier, which
-		 * means both the CPU and compiler are free to perform the
-		 * memory read without constraint. The compiler only has to
-		 * ensure that any operations after the rcu_access_pointer()
-		 * occur afterwards in program order. This means the read may
-		 * be performed earlier by an out-of-order CPU, or adventurous
-		 * compiler.
-		 *
-		 * The atomic operation at the heart of
-		 * i915_request_get_rcu(), see dma_fence_get_rcu(), is
-		 * atomic_inc_not_zero() which is only a full memory barrier
-		 * when successful. That is, if i915_request_get_rcu()
-		 * returns the request (and so with the reference counted
-		 * incremented) then the following read for rcu_access_pointer()
-		 * must occur after the atomic operation and so confirm
-		 * that this request is the one currently being tracked.
-		 *
-		 * The corresponding write barrier is part of
-		 * rcu_assign_pointer().
-		 */
-		if (!request || request == rcu_access_pointer(active->request))
-			return rcu_pointer_handoff(request);
-
-		i915_request_put(request);
-	} while (1);
-}
-
+int __must_check
+i915_active_fence_set(struct i915_active_fence *active,
+		      struct i915_request *rq);
 /**
- * i915_active_request_get_unlocked - return a reference to the active request
+ * i915_active_fence_get - return a reference to the active fence
  * @active - the active tracker
  *
- * i915_active_request_get_unlocked() returns a reference to the active request,
+ * i915_active_fence_get() returns a reference to the active fence,
  * or NULL if the active tracker is idle. The reference is obtained under RCU,
  * so no locking is required by the caller.
  *
- * The reference should be freed with i915_request_put().
+ * The reference should be freed with dma_fence_put().
  */
-static inline struct i915_request *
-i915_active_request_get_unlocked(const struct i915_active_request *active)
+static inline struct dma_fence *
+i915_active_fence_get(struct i915_active_fence *active)
 {
-	struct i915_request *request;
+	struct dma_fence *fence;
 
 	rcu_read_lock();
-	request = __i915_active_request_get_rcu(active);
+	fence = dma_fence_get_rcu_safe(&active->fence);
 	rcu_read_unlock();
 
-	return request;
+	return fence;
 }
 
 /**
- * i915_active_request_isset - report whether the active tracker is assigned
+ * i915_active_fence_isset - report whether the active tracker is assigned
  * @active - the active tracker
  *
- * i915_active_request_isset() returns true if the active tracker is currently
- * assigned to a request. Due to the lazy retiring, that request may be idle
+ * i915_active_fence_isset() returns true if the active tracker is currently
+ * assigned to a fence. Due to the lazy retiring, that fence may be idle
  * and this may report stale information.
  */
 static inline bool
-i915_active_request_isset(const struct i915_active_request *active)
+i915_active_fence_isset(const struct i915_active_fence *active)
 {
-	return rcu_access_pointer(active->request);
+	return rcu_access_pointer(active->fence);
 }
 
-/**
- * i915_active_request_retire - waits until the request is retired
- * @active - the active request on which to wait
- *
- * i915_active_request_retire() waits until the request is completed,
- * and then ensures that at least the retirement handler for this
- * @active tracker is called before returning. If the @active
- * tracker is idle, the function returns immediately.
- */
-static inline int __must_check
-i915_active_request_retire(struct i915_active_request *active,
-			   struct mutex *mutex)
+static inline void
+i915_active_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 {
-	struct i915_request *request;
-	long ret;
-
-	request = i915_active_request_raw(active, mutex);
-	if (!request)
-		return 0;
-
-	ret = i915_request_wait(request,
-				I915_WAIT_INTERRUPTIBLE,
-				MAX_SCHEDULE_TIMEOUT);
-	if (ret < 0)
-		return ret;
+	struct i915_active_fence *active =
+		container_of(cb, typeof(*active), cb);
 
-	list_del_init(&active->link);
-	RCU_INIT_POINTER(active->request, NULL);
-
-	active->retire(active, request);
-
-	return 0;
+	RCU_INIT_POINTER(active->fence, NULL);
 }
 
 /*
@@ -358,47 +162,40 @@ i915_active_request_retire(struct i915_active_request *active,
  * synchronisation.
  */
 
-void __i915_active_init(struct drm_i915_private *i915,
-			struct i915_active *ref,
+void __i915_active_init(struct i915_active *ref,
 			int (*active)(struct i915_active *ref),
 			void (*retire)(struct i915_active *ref),
 			struct lock_class_key *key);
-#define i915_active_init(i915, ref, active, retire) do {		\
+#define i915_active_init(ref, active, retire) do {		\
 	static struct lock_class_key __key;				\
 									\
-	__i915_active_init(i915, ref, active, retire, &__key);		\
+	__i915_active_init(ref, active, retire, &__key);		\
 } while (0)
 
 int i915_active_ref(struct i915_active *ref,
 		    struct intel_timeline *tl,
-		    struct i915_request *rq);
+		    struct dma_fence *fence);
 
 static inline int
 i915_active_add_request(struct i915_active *ref, struct i915_request *rq)
 {
-	return i915_active_ref(ref, i915_request_timeline(rq), rq);
+	return i915_active_ref(ref, i915_request_timeline(rq), &rq->fence);
 }
 
 void i915_active_set_exclusive(struct i915_active *ref, struct dma_fence *f);
 
 static inline bool i915_active_has_exclusive(struct i915_active *ref)
 {
-	return rcu_access_pointer(ref->excl);
+	return rcu_access_pointer(ref->excl.fence);
 }
 
 int i915_active_wait(struct i915_active *ref);
 
-int i915_request_await_active(struct i915_request *rq,
-			      struct i915_active *ref);
-int i915_request_await_active_request(struct i915_request *rq,
-				      struct i915_active_request *active);
+int i915_request_await_active(struct i915_request *rq, struct i915_active *ref);
 
 int i915_active_acquire(struct i915_active *ref);
+bool i915_active_acquire_if_busy(struct i915_active *ref);
 void i915_active_release(struct i915_active *ref);
-void __i915_active_release_nested(struct i915_active *ref, int subclass);
-
-bool i915_active_trygrab(struct i915_active *ref);
-void i915_active_ungrab(struct i915_active *ref);
 
 static inline bool
 i915_active_is_idle(const struct i915_active *ref)
diff --git a/drivers/gpu/drm/i915/i915_active_types.h b/drivers/gpu/drm/i915/i915_active_types.h
index 021167f0004d..d89a74c142c6 100644
--- a/drivers/gpu/drm/i915/i915_active_types.h
+++ b/drivers/gpu/drm/i915/i915_active_types.h
@@ -17,17 +17,9 @@
 
 #include "i915_utils.h"
 
-struct drm_i915_private;
-struct i915_active_request;
-struct i915_request;
-
-typedef void (*i915_active_retire_fn)(struct i915_active_request *,
-				      struct i915_request *);
-
-struct i915_active_request {
-	struct i915_request __rcu *request;
-	struct list_head link;
-	i915_active_retire_fn retire;
+struct i915_active_fence {
+	struct dma_fence __rcu *fence;
+	struct dma_fence_cb cb;
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
 	/*
 	 * Incorporeal!
@@ -53,20 +45,17 @@ struct active_node;
 #define i915_active_may_sleep(fn) ptr_pack_bits(&(fn), I915_ACTIVE_MAY_SLEEP, 2)
 
 struct i915_active {
-	struct drm_i915_private *i915;
+	atomic_t count;
+	struct mutex mutex;
 
 	struct active_node *cache;
 	struct rb_root tree;
-	struct mutex mutex;
-	atomic_t count;
 
 	/* Preallocated "exclusive" node */
-	struct dma_fence __rcu *excl;
-	struct dma_fence_cb excl_cb;
+	struct i915_active_fence excl;
 
 	unsigned long flags;
 #define I915_ACTIVE_RETIRE_SLEEPS BIT(0)
-#define I915_ACTIVE_GRAB_BIT 1
 
 	int (*active)(struct i915_active *ref);
 	void (*retire)(struct i915_active *ref);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index fc5c618f6c19..b0aa0a7c680f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -892,28 +892,38 @@ wait_for_timelines(struct intel_gt *gt, unsigned int wait, long timeout)
 
 	spin_lock_irqsave(&timelines->lock, flags);
 	list_for_each_entry(tl, &timelines->active_list, link) {
-		struct i915_request *rq;
+		struct dma_fence *fence;
 
-		rq = i915_active_request_get_unlocked(&tl->last_request);
-		if (!rq)
+		fence = i915_active_fence_get(&tl->last_request);
+		if (!fence)
 			continue;
 
 		spin_unlock_irqrestore(&timelines->lock, flags);
 
-		/*
-		 * "Race-to-idle".
-		 *
-		 * Switching to the kernel context is often used a synchronous
-		 * step prior to idling, e.g. in suspend for flushing all
-		 * current operations to memory before sleeping. These we
-		 * want to complete as quickly as possible to avoid prolonged
-		 * stalls, so allow the gpu to boost to maximum clocks.
-		 */
-		if (wait & I915_WAIT_FOR_IDLE_BOOST)
-			gen6_rps_boost(rq);
+		if (!dma_fence_is_i915(fence)) {
+			timeout = dma_fence_wait_timeout(fence,
+							 flags & I915_WAIT_INTERRUPTIBLE,
+							 timeout);
+		} else {
+			struct i915_request *rq = to_request(fence);
+
+			/*
+			 * "Race-to-idle".
+			 *
+			 * Switching to the kernel context is often used as
+			 * a synchronous step prior to idling, e.g. in suspend
+			 * for flushing all current operations to memory before
+			 * sleeping. These we want to complete as quickly as
+			 * possible to avoid prolonged stalls, so allow the gpu
+			 * to boost to maximum clocks.
+			 */
+			if (flags & I915_WAIT_FOR_IDLE_BOOST)
+				gen6_rps_boost(rq);
+
+			timeout = i915_request_wait(rq, flags, timeout);
+		}
 
-		timeout = i915_request_wait(rq, wait, timeout);
-		i915_request_put(rq);
+		dma_fence_put(fence);
 		if (timeout < 0)
 			return timeout;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 55cebf256d03..7462d87f7a48 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1861,7 +1861,6 @@ static const struct i915_vma_ops pd_vma_ops = {
 
 static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
 {
-	struct drm_i915_private *i915 = ppgtt->base.vm.i915;
 	struct i915_ggtt *ggtt = ppgtt->base.vm.gt->ggtt;
 	struct i915_vma *vma;
 
@@ -1872,7 +1871,7 @@ static struct i915_vma *pd_vma_create(struct gen6_ppgtt *ppgtt, int size)
 	if (!vma)
 		return ERR_PTR(-ENOMEM);
 
-	i915_active_init(i915, &vma->active, NULL, NULL);
+	i915_active_init(&vma->active, NULL, NULL);
 
 	mutex_init(&vma->pages_mutex);
 	vma->vm = i915_vm_get(&ggtt->vm);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 6384a06aa5bf..a28ee754b7b4 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1299,7 +1299,7 @@ capture_vma(struct capture_vma *next,
 	if (!c)
 		return next;
 
-	if (!i915_active_trygrab(&vma->active)) {
+	if (!i915_active_acquire_if_busy(&vma->active)) {
 		kfree(c);
 		return next;
 	}
@@ -1439,7 +1439,7 @@ gem_record_rings(struct i915_gpu_state *error, struct compress *compress)
 			*this->slot =
 				i915_error_object_create(i915, vma, compress);
 
-			i915_active_ungrab(&vma->active);
+			i915_active_release(&vma->active);
 			i915_vma_put(vma);
 
 			capture = this->next;
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index a8916412759b..4ffe62a42186 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -218,8 +218,6 @@ static void remove_from_engine(struct i915_request *rq)
 
 static bool i915_request_retire(struct i915_request *rq)
 {
-	struct i915_active_request *active, *next;
-
 	if (!i915_request_completed(rq))
 		return false;
 
@@ -244,35 +242,6 @@ static bool i915_request_retire(struct i915_request *rq)
 				  &i915_request_timeline(rq)->requests));
 	rq->ring->head = rq->postfix;
 
-	/*
-	 * Walk through the active list, calling retire on each. This allows
-	 * objects to track their GPU activity and mark themselves as idle
-	 * when their *last* active request is completed (updating state
-	 * tracking lists for eviction, active references for GEM, etc).
-	 *
-	 * As the ->retire() may free the node, we decouple it first and
-	 * pass along the auxiliary information (to avoid dereferencing
-	 * the node after the callback).
-	 */
-	list_for_each_entry_safe(active, next, &rq->active_list, link) {
-		/*
-		 * In microbenchmarks or focusing upon time inside the kernel,
-		 * we may spend an inordinate amount of time simply handling
-		 * the retirement of requests and processing their callbacks.
-		 * Of which, this loop itself is particularly hot due to the
-		 * cache misses when jumping around the list of
-		 * i915_active_request.  So we try to keep this loop as
-		 * streamlined as possible and also prefetch the next
-		 * i915_active_request to try and hide the likely cache miss.
-		 */
-		prefetchw(next);
-
-		INIT_LIST_HEAD(&active->link);
-		RCU_INIT_POINTER(active->request, NULL);
-
-		active->retire(active, rq);
-	}
-
 	local_irq_disable();
 
 	/*
@@ -704,7 +673,6 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->flags = 0;
 	rq->execution_mask = ALL_ENGINES;
 
-	INIT_LIST_HEAD(&rq->active_list);
 	INIT_LIST_HEAD(&rq->execute_cb);
 
 	/*
@@ -743,7 +711,6 @@ err_unwind:
 	ce->ring->emit = rq->head;
 
 	/* Make sure we didn't add ourselves to external state before freeing */
-	GEM_BUG_ON(!list_empty(&rq->active_list));
 	GEM_BUG_ON(!list_empty(&rq->sched.signalers_list));
 	GEM_BUG_ON(!list_empty(&rq->sched.waiters_list));
 
@@ -1174,8 +1141,8 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 	 * precludes optimising to use semaphores serialisation of a single
 	 * timeline across engines.
 	 */
-	prev = rcu_dereference_protected(timeline->last_request.request,
-					 lockdep_is_held(&timeline->mutex));
+	prev = to_request(__i915_active_fence_set(&timeline->last_request,
+						  &rq->fence));
 	if (prev && !i915_request_completed(prev)) {
 		if (is_power_of_2(prev->engine->mask | rq->engine->mask))
 			i915_sw_fence_await_sw_fence(&rq->submit,
@@ -1200,7 +1167,6 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 	 * us, the timeline will hold its seqno which is later than ours.
 	 */
 	GEM_BUG_ON(timeline->seqno != rq->fence.seqno);
-	__i915_active_request_set(&timeline->last_request, rq);
 
 	return prev;
 }
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index ec5bb4c2e5ae..91a885c36c6b 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -211,7 +211,6 @@ struct i915_request {
 	 * on the active_list (of their final request).
 	 */
 	struct i915_capture_list *capture_list;
-	struct list_head active_list;
 
 	/** Time at which this request was emitted, in jiffies. */
 	unsigned long emitted_jiffies;
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index e191247c7c5f..9fdcd4e2c799 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -120,8 +120,7 @@ vma_create(struct drm_i915_gem_object *obj,
 	vma->size = obj->base.size;
 	vma->display_alignment = I915_GTT_MIN_ALIGNMENT;
 
-	i915_active_init(vm->i915, &vma->active,
-			 __i915_vma_active, __i915_vma_retire);
+	i915_active_init(&vma->active, __i915_vma_active, __i915_vma_retire);
 
 	/* Declare ourselves safe for use inside shrinkers */
 	if (IS_ENABLED(CONFIG_LOCKDEP)) {
@@ -1148,6 +1147,7 @@ int __i915_vma_unbind(struct i915_vma *vma)
 	if (ret)
 		return ret;
 
+	GEM_BUG_ON(i915_vma_is_active(vma));
 	if (i915_vma_is_pinned(vma)) {
 		vma_print_allocator(vma, "is pinned");
 		return -EBUSY;
diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
index a41785822ed9..2cc71bcf884f 100644
--- a/drivers/gpu/drm/i915/selftests/i915_active.c
+++ b/drivers/gpu/drm/i915/selftests/i915_active.c
@@ -68,7 +68,7 @@ static struct live_active *__live_alloc(struct drm_i915_private *i915)
 		return NULL;
 
 	kref_init(&active->ref);
-	i915_active_init(i915, &active->base, __live_active, __live_retire);
+	i915_active_init(&active->base, __live_active, __live_retire);
 
 	return active;
 }
@@ -146,19 +146,13 @@ static int live_active_wait(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct live_active *active;
-	intel_wakeref_t wakeref;
 	int err = 0;
 
 	/* Check that we get a callback when requests retire upon waiting */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	active = __live_active_setup(i915);
-	if (IS_ERR(active)) {
-		err = PTR_ERR(active);
-		goto err;
-	}
+	if (IS_ERR(active))
+		return PTR_ERR(active);
 
 	i915_active_wait(&active->base);
 	if (!READ_ONCE(active->retired)) {
@@ -168,11 +162,9 @@ static int live_active_wait(void *arg)
 
 	__live_put(active);
 
+	mutex_lock(&i915->drm.struct_mutex);
 	if (igt_flush_test(i915, I915_WAIT_LOCKED))
 		err = -EIO;
-
-err:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 	mutex_unlock(&i915->drm.struct_mutex);
 
 	return err;
@@ -182,23 +174,19 @@ static int live_active_retire(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct live_active *active;
-	intel_wakeref_t wakeref;
 	int err = 0;
 
 	/* Check that we get a callback when requests are indirectly retired */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	active = __live_active_setup(i915);
-	if (IS_ERR(active)) {
-		err = PTR_ERR(active);
-		goto err;
-	}
+	if (IS_ERR(active))
+		return PTR_ERR(active);
 
 	/* waits for & retires all requests */
+	mutex_lock(&i915->drm.struct_mutex);
 	if (igt_flush_test(i915, I915_WAIT_LOCKED))
 		err = -EIO;
+	mutex_unlock(&i915->drm.struct_mutex);
 
 	if (!READ_ONCE(active->retired)) {
 		pr_err("i915_active not retired after flushing!\n");
@@ -207,10 +195,6 @@ static int live_active_retire(void *arg)
 
 	__live_put(active);
 
-err:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	return err;
 }
 
-- 
cgit v1.2.3


From b72348406927740d4cfb55f2c1e19c6769ffc666 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:01 +0100
Subject: drm/i915: Move idle barrier cleanup into engine-pm

Now that we now longer need to guarantee that the active callback is
under the struct_mutex, we can lift it out of the i915_gem_park() and
into the engine parking itself.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-7-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_pm.c    | 19 -------------------
 drivers/gpu/drm/i915/gt/intel_engine_pm.c | 15 +++++++++++++++
 drivers/gpu/drm/i915/i915_active.c        |  1 +
 3 files changed, 16 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 0a4115c6c275..5180b2ee1cb7 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -11,29 +11,10 @@
 #include "i915_drv.h"
 #include "i915_globals.h"
 
-static void call_idle_barriers(struct intel_engine_cs *engine)
-{
-	struct llist_node *node, *next;
-
-	llist_for_each_safe(node, next, llist_del_all(&engine->barrier_tasks)) {
-		struct dma_fence_cb *cb =
-			container_of((struct list_head *)node,
-				     typeof(*cb), node);
-
-		cb->func(NULL, cb);
-	}
-}
-
 static void i915_gem_park(struct drm_i915_private *i915)
 {
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-
 	lockdep_assert_held(&i915->drm.struct_mutex);
 
-	for_each_engine(engine, i915, id)
-		call_idle_barriers(engine); /* cleanup after wedging */
-
 	i915_vma_parked(i915);
 
 	i915_globals_park();
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 66fc49b76ea8..8e5e513eddc9 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -124,6 +124,19 @@ out_unlock:
 	return result;
 }
 
+static void call_idle_barriers(struct intel_engine_cs *engine)
+{
+	struct llist_node *node, *next;
+
+	llist_for_each_safe(node, next, llist_del_all(&engine->barrier_tasks)) {
+		struct dma_fence_cb *cb =
+			container_of((struct list_head *)node,
+				     typeof(*cb), node);
+
+		cb->func(NULL, cb);
+	}
+}
+
 static int __engine_park(struct intel_wakeref *wf)
 {
 	struct intel_engine_cs *engine =
@@ -143,6 +156,8 @@ static int __engine_park(struct intel_wakeref *wf)
 
 	GEM_TRACE("%s\n", engine->name);
 
+	call_idle_barriers(engine); /* cleanup after wedging */
+
 	intel_engine_disarm_breadcrumbs(engine);
 	intel_engine_pool_park(&engine->pool);
 
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 023652ded4be..aa37c07004b9 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -693,6 +693,7 @@ void i915_active_acquire_barrier(struct i915_active *ref)
 		rb_link_node(&node->node, parent, p);
 		rb_insert_color(&node->node, &ref->tree);
 
+		GEM_BUG_ON(!intel_engine_pm_is_awake(engine));
 		llist_add(barrier_to_ll(node), &engine->barrier_tasks);
 		intel_engine_pm_put(engine);
 	}
-- 
cgit v1.2.3


From 7e8057626640cfedbae000c5032be32269713687 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:02 +0100
Subject: drm/i915: Drop struct_mutex from around i915_retire_requests()

We don't need to hold struct_mutex now for retiring requests, so drop it
from i915_retire_requests() and i915_gem_wait_for_idle(), finally
removing I915_WAIT_LOCKED for good.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-8-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_client_blt.c     |   7 +-
 drivers/gpu/drm/i915/gem/i915_gem_context.c        |  20 +--
 drivers/gpu/drm/i915/gem/i915_gem_pm.c             |  45 +++---
 .../drm/i915/gem/selftests/i915_gem_coherency.c    |  40 +++---
 .../gpu/drm/i915/gem/selftests/i915_gem_context.c  |  18 +--
 drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c |   6 +-
 .../drm/i915/gem/selftests/i915_gem_object_blt.c   |   4 -
 drivers/gpu/drm/i915/gt/intel_gt_pm.c              |  28 ++--
 drivers/gpu/drm/i915/gt/selftest_context.c         |   4 +-
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c       |  89 ++----------
 drivers/gpu/drm/i915/gt/selftest_lrc.c             |  23 ++--
 drivers/gpu/drm/i915/gt/selftest_timeline.c        |  91 ++++++-------
 drivers/gpu/drm/i915/gt/selftest_workarounds.c     |   6 +-
 drivers/gpu/drm/i915/i915_debugfs.c                |  42 ++----
 drivers/gpu/drm/i915/i915_gem.c                    |  19 ++-
 drivers/gpu/drm/i915/i915_request.h                |   7 +-
 drivers/gpu/drm/i915/selftests/i915_active.c       |   8 +-
 drivers/gpu/drm/i915/selftests/i915_gem_evict.c    |   2 +-
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c      |   6 +-
 drivers/gpu/drm/i915/selftests/i915_request.c      | 151 ++++++---------------
 drivers/gpu/drm/i915/selftests/i915_selftest.c     |   8 +-
 drivers/gpu/drm/i915/selftests/i915_vma.c          |   4 -
 drivers/gpu/drm/i915/selftests/igt_flush_test.c    |  30 ++--
 drivers/gpu/drm/i915/selftests/igt_flush_test.h    |   2 +-
 drivers/gpu/drm/i915/selftests/igt_live_test.c     |   9 +-
 drivers/gpu/drm/i915/selftests/mock_gem_device.c   |   4 -
 26 files changed, 213 insertions(+), 460 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
index c1fca5728e6e..81366aa4812b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_client_blt.c
@@ -155,7 +155,6 @@ static void clear_pages_dma_fence_cb(struct dma_fence *fence,
 static void clear_pages_worker(struct work_struct *work)
 {
 	struct clear_pages_work *w = container_of(work, typeof(*w), work);
-	struct drm_i915_private *i915 = w->ce->engine->i915;
 	struct drm_i915_gem_object *obj = w->sleeve->vma->obj;
 	struct i915_vma *vma = w->sleeve->vma;
 	struct i915_request *rq;
@@ -173,11 +172,9 @@ static void clear_pages_worker(struct work_struct *work)
 	obj->read_domains = I915_GEM_GPU_DOMAINS;
 	obj->write_domain = 0;
 
-	/* XXX: we need to kill this */
-	mutex_lock(&i915->drm.struct_mutex);
 	err = i915_vma_pin(vma, 0, 0, PIN_USER);
 	if (unlikely(err))
-		goto out_unlock;
+		goto out_signal;
 
 	batch = intel_emit_vma_fill_blt(w->ce, vma, w->value);
 	if (IS_ERR(batch)) {
@@ -229,8 +226,6 @@ out_batch:
 	intel_emit_vma_release(w->ce, batch);
 out_unpin:
 	i915_vma_unpin(vma);
-out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
 out_signal:
 	if (unlikely(err)) {
 		dma_fence_set_error(&w->dma, err);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 9d85aab68d34..0ab416887fc2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1159,8 +1159,7 @@ gen8_modify_rpcs(struct intel_context *ce, struct intel_sseu sseu)
 }
 
 static int
-__intel_context_reconfigure_sseu(struct intel_context *ce,
-				 struct intel_sseu sseu)
+intel_context_reconfigure_sseu(struct intel_context *ce, struct intel_sseu sseu)
 {
 	int ret;
 
@@ -1183,23 +1182,6 @@ unlock:
 	return ret;
 }
 
-static int
-intel_context_reconfigure_sseu(struct intel_context *ce, struct intel_sseu sseu)
-{
-	struct drm_i915_private *i915 = ce->engine->i915;
-	int ret;
-
-	ret = mutex_lock_interruptible(&i915->drm.struct_mutex);
-	if (ret)
-		return ret;
-
-	ret = __intel_context_reconfigure_sseu(ce, sseu);
-
-	mutex_unlock(&i915->drm.struct_mutex);
-
-	return ret;
-}
-
 static int
 user_to_context_sseu(struct drm_i915_private *i915,
 		     const struct drm_i915_gem_context_param_sseu *user,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 5180b2ee1cb7..2ddc3aeaac9d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -48,11 +48,7 @@ static void retire_work_handler(struct work_struct *work)
 	struct drm_i915_private *i915 =
 		container_of(work, typeof(*i915), gem.retire_work.work);
 
-	/* Come back later if the device is busy... */
-	if (mutex_trylock(&i915->drm.struct_mutex)) {
-		i915_retire_requests(i915);
-		mutex_unlock(&i915->drm.struct_mutex);
-	}
+	i915_retire_requests(i915);
 
 	queue_delayed_work(i915->wq,
 			   &i915->gem.retire_work,
@@ -86,26 +82,23 @@ static bool switch_to_kernel_context_sync(struct intel_gt *gt)
 {
 	bool result = !intel_gt_is_wedged(gt);
 
-	do {
-		if (i915_gem_wait_for_idle(gt->i915,
-					   I915_WAIT_LOCKED |
-					   I915_WAIT_FOR_IDLE_BOOST,
-					   I915_GEM_IDLE_TIMEOUT) == -ETIME) {
-			/* XXX hide warning from gem_eio */
-			if (i915_modparams.reset) {
-				dev_err(gt->i915->drm.dev,
-					"Failed to idle engines, declaring wedged!\n");
-				GEM_TRACE_DUMP();
-			}
-
-			/*
-			 * Forcibly cancel outstanding work and leave
-			 * the gpu quiet.
-			 */
-			intel_gt_set_wedged(gt);
-			result = false;
+	if (i915_gem_wait_for_idle(gt->i915,
+				   I915_WAIT_FOR_IDLE_BOOST,
+				   I915_GEM_IDLE_TIMEOUT) == -ETIME) {
+		/* XXX hide warning from gem_eio */
+		if (i915_modparams.reset) {
+			dev_err(gt->i915->drm.dev,
+				"Failed to idle engines, declaring wedged!\n");
+			GEM_TRACE_DUMP();
 		}
-	} while (i915_retire_requests(gt->i915) && result);
+
+		/*
+		 * Forcibly cancel outstanding work and leave
+		 * the gpu quiet.
+		 */
+		intel_gt_set_wedged(gt);
+		result = false;
+	}
 
 	if (intel_gt_pm_wait_for_idle(gt))
 		result = false;
@@ -145,8 +138,6 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 
 	user_forcewake(&i915->gt, true);
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	/*
 	 * We have to flush all the executing contexts to main memory so
 	 * that they can saved in the hibernation image. To ensure the last
@@ -158,8 +149,6 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	 */
 	switch_to_kernel_context_sync(&i915->gt);
 
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	cancel_delayed_work_sync(&i915->gt.hangcheck.work);
 
 	i915_gem_drain_freed_objects(i915);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
index 0ff7a89aadca..549810f70aeb 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
@@ -7,6 +7,7 @@
 #include <linux/prime_numbers.h>
 
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_pm.h"
 
 #include "i915_selftest.h"
 #include "selftests/i915_random.h"
@@ -78,7 +79,7 @@ static int gtt_set(struct drm_i915_gem_object *obj,
 {
 	struct i915_vma *vma;
 	u32 __iomem *map;
-	int err;
+	int err = 0;
 
 	i915_gem_object_lock(obj);
 	err = i915_gem_object_set_to_gtt_domain(obj, true);
@@ -90,15 +91,21 @@ static int gtt_set(struct drm_i915_gem_object *obj,
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
+	intel_gt_pm_get(vma->vm->gt);
+
 	map = i915_vma_pin_iomap(vma);
 	i915_vma_unpin(vma);
-	if (IS_ERR(map))
-		return PTR_ERR(map);
+	if (IS_ERR(map)) {
+		err = PTR_ERR(map);
+		goto out_rpm;
+	}
 
 	iowrite32(v, &map[offset / sizeof(*map)]);
 	i915_vma_unpin_iomap(vma);
 
-	return 0;
+out_rpm:
+	intel_gt_pm_put(vma->vm->gt);
+	return err;
 }
 
 static int gtt_get(struct drm_i915_gem_object *obj,
@@ -107,7 +114,7 @@ static int gtt_get(struct drm_i915_gem_object *obj,
 {
 	struct i915_vma *vma;
 	u32 __iomem *map;
-	int err;
+	int err = 0;
 
 	i915_gem_object_lock(obj);
 	err = i915_gem_object_set_to_gtt_domain(obj, false);
@@ -119,15 +126,21 @@ static int gtt_get(struct drm_i915_gem_object *obj,
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
+	intel_gt_pm_get(vma->vm->gt);
+
 	map = i915_vma_pin_iomap(vma);
 	i915_vma_unpin(vma);
-	if (IS_ERR(map))
-		return PTR_ERR(map);
+	if (IS_ERR(map)) {
+		err = PTR_ERR(map);
+		goto out_rpm;
+	}
 
 	*v = ioread32(&map[offset / sizeof(*map)]);
 	i915_vma_unpin_iomap(vma);
 
-	return 0;
+out_rpm:
+	intel_gt_pm_put(vma->vm->gt);
+	return err;
 }
 
 static int wc_set(struct drm_i915_gem_object *obj,
@@ -280,7 +293,6 @@ static int igt_gem_coherency(void *arg)
 	struct drm_i915_private *i915 = arg;
 	const struct igt_coherency_mode *read, *write, *over;
 	struct drm_i915_gem_object *obj;
-	intel_wakeref_t wakeref;
 	unsigned long count, n;
 	u32 *offsets, *values;
 	int err = 0;
@@ -299,8 +311,6 @@ static int igt_gem_coherency(void *arg)
 
 	values = offsets + ncachelines;
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 	for (over = igt_coherency_mode; over->name; over++) {
 		if (!over->set)
 			continue;
@@ -326,7 +336,7 @@ static int igt_gem_coherency(void *arg)
 					obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 					if (IS_ERR(obj)) {
 						err = PTR_ERR(obj);
-						goto unlock;
+						goto free;
 					}
 
 					i915_random_reorder(offsets, ncachelines, &prng);
@@ -377,15 +387,13 @@ static int igt_gem_coherency(void *arg)
 			}
 		}
 	}
-unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
+free:
 	kfree(offsets);
 	return err;
 
 put_object:
 	i915_gem_object_put(obj);
-	goto unlock;
+	goto free;
 }
 
 int i915_gem_coherency_live_selftests(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 8eba0d3a31de..f5402aad9b5a 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -164,7 +164,6 @@ struct parallel_switch {
 static int __live_parallel_switch1(void *data)
 {
 	struct parallel_switch *arg = data;
-	struct drm_i915_private *i915 = arg->ce[0]->engine->i915;
 	IGT_TIMEOUT(end_time);
 	unsigned long count;
 
@@ -176,16 +175,12 @@ static int __live_parallel_switch1(void *data)
 		for (n = 0; n < ARRAY_SIZE(arg->ce); n++) {
 			i915_request_put(rq);
 
-			mutex_lock(&i915->drm.struct_mutex);
 			rq = i915_request_create(arg->ce[n]);
-			if (IS_ERR(rq)) {
-				mutex_unlock(&i915->drm.struct_mutex);
+			if (IS_ERR(rq))
 				return PTR_ERR(rq);
-			}
 
 			i915_request_get(rq);
 			i915_request_add(rq);
-			mutex_unlock(&i915->drm.struct_mutex);
 		}
 
 		err = 0;
@@ -205,7 +200,6 @@ static int __live_parallel_switch1(void *data)
 static int __live_parallel_switchN(void *data)
 {
 	struct parallel_switch *arg = data;
-	struct drm_i915_private *i915 = arg->ce[0]->engine->i915;
 	IGT_TIMEOUT(end_time);
 	unsigned long count;
 	int n;
@@ -215,15 +209,11 @@ static int __live_parallel_switchN(void *data)
 		for (n = 0; n < ARRAY_SIZE(arg->ce); n++) {
 			struct i915_request *rq;
 
-			mutex_lock(&i915->drm.struct_mutex);
 			rq = i915_request_create(arg->ce[n]);
-			if (IS_ERR(rq)) {
-				mutex_unlock(&i915->drm.struct_mutex);
+			if (IS_ERR(rq))
 				return PTR_ERR(rq);
-			}
 
 			i915_request_add(rq);
-			mutex_unlock(&i915->drm.struct_mutex);
 		}
 
 		count++;
@@ -1173,7 +1163,7 @@ __sseu_test(const char *name,
 	if (ret)
 		return ret;
 
-	ret = __intel_context_reconfigure_sseu(ce, sseu);
+	ret = intel_context_reconfigure_sseu(ce, sseu);
 	if (ret)
 		goto out_spin;
 
@@ -1277,7 +1267,7 @@ __igt_ctx_sseu(struct drm_i915_private *i915,
 		goto out_fail;
 
 out_fail:
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		ret = -EIO;
 
 	intel_context_unpin(ce);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 36aca1c172e7..856b8e467ee8 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -581,12 +581,8 @@ static void disable_retire_worker(struct drm_i915_private *i915)
 
 static void restore_retire_worker(struct drm_i915_private *i915)
 {
+	igt_flush_test(i915);
 	intel_gt_pm_put(&i915->gt);
-
-	mutex_lock(&i915->drm.struct_mutex);
-	igt_flush_test(i915, I915_WAIT_LOCKED);
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	i915_gem_driver_register__shrinker(i915);
 }
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
index c21d747e7d05..9ec55b3a3815 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
@@ -65,9 +65,7 @@ static int igt_fill_blt(void *arg)
 		if (!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE))
 			obj->cache_dirty = true;
 
-		mutex_lock(&i915->drm.struct_mutex);
 		err = i915_gem_object_fill_blt(obj, ce, val);
-		mutex_unlock(&i915->drm.struct_mutex);
 		if (err)
 			goto err_unpin;
 
@@ -166,9 +164,7 @@ static int igt_copy_blt(void *arg)
 		if (!(dst->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE))
 			dst->cache_dirty = true;
 
-		mutex_lock(&i915->drm.struct_mutex);
 		err = i915_gem_object_copy_blt(src, dst, ce);
-		mutex_unlock(&i915->drm.struct_mutex);
 		if (err)
 			goto err_unpin;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 29fa1dabbc2e..d4cefdd38431 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -196,26 +196,14 @@ int intel_gt_resume(struct intel_gt *gt)
 
 static void wait_for_idle(struct intel_gt *gt)
 {
-	mutex_lock(&gt->i915->drm.struct_mutex); /* XXX */
-	do {
-		if (i915_gem_wait_for_idle(gt->i915,
-					   I915_WAIT_LOCKED,
-					   I915_GEM_IDLE_TIMEOUT) == -ETIME) {
-			/* XXX hide warning from gem_eio */
-			if (i915_modparams.reset) {
-				dev_err(gt->i915->drm.dev,
-					"Failed to idle engines, declaring wedged!\n");
-				GEM_TRACE_DUMP();
-			}
-
-			/*
-			 * Forcibly cancel outstanding work and leave
-			 * the gpu quiet.
-			 */
-			intel_gt_set_wedged(gt);
-		}
-	} while (i915_retire_requests(gt->i915));
-	mutex_unlock(&gt->i915->drm.struct_mutex);
+	if (i915_gem_wait_for_idle(gt->i915, 0,
+				   I915_GEM_IDLE_TIMEOUT) == -ETIME) {
+		/*
+		 * Forcibly cancel outstanding work and leave
+		 * the gpu quiet.
+		 */
+		intel_gt_set_wedged(gt);
+	}
 
 	intel_gt_pm_wait_for_idle(gt);
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index e6bcbe7ab5e1..86cffbb0a9cb 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -318,7 +318,7 @@ static int live_active_context(void *arg)
 		if (err)
 			break;
 
-		err = igt_flush_test(gt->i915, I915_WAIT_LOCKED);
+		err = igt_flush_test(gt->i915);
 		if (err)
 			break;
 	}
@@ -431,7 +431,7 @@ static int live_remote_context(void *arg)
 		if (err)
 			break;
 
-		err = igt_flush_test(gt->i915, I915_WAIT_LOCKED);
+		err = igt_flush_test(gt->i915);
 		if (err)
 			break;
 	}
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index d3bee9f88008..ffbb3d23b887 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -58,7 +58,9 @@ static int hang_init(struct hang *h, struct intel_gt *gt)
 	memset(h, 0, sizeof(*h));
 	h->gt = gt;
 
+	mutex_lock(&gt->i915->drm.struct_mutex);
 	h->ctx = kernel_context(gt->i915);
+	mutex_unlock(&gt->i915->drm.struct_mutex);
 	if (IS_ERR(h->ctx))
 		return PTR_ERR(h->ctx);
 
@@ -285,7 +287,7 @@ static void hang_fini(struct hang *h)
 
 	kernel_context_close(h->ctx);
 
-	igt_flush_test(h->gt->i915, I915_WAIT_LOCKED);
+	igt_flush_test(h->gt->i915);
 }
 
 static bool wait_until_running(struct hang *h, struct i915_request *rq)
@@ -309,10 +311,9 @@ static int igt_hang_sanitycheck(void *arg)
 
 	/* Basic check that we can execute our hanging batch */
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
 	err = hang_init(&h, gt);
 	if (err)
-		goto unlock;
+		return err;
 
 	for_each_engine(engine, gt->i915, id) {
 		struct intel_wedge_me w;
@@ -355,8 +356,6 @@ static int igt_hang_sanitycheck(void *arg)
 
 fini:
 	hang_fini(&h);
-unlock:
-	mutex_unlock(&gt->i915->drm.struct_mutex);
 	return err;
 }
 
@@ -395,8 +394,6 @@ static int igt_reset_nop(void *arg)
 	reset_count = i915_reset_count(global);
 	count = 0;
 	do {
-		mutex_lock(&gt->i915->drm.struct_mutex);
-
 		for_each_engine(engine, gt->i915, id) {
 			int i;
 
@@ -417,7 +414,6 @@ static int igt_reset_nop(void *arg)
 		intel_gt_reset(gt, ALL_ENGINES, NULL);
 		igt_global_reset_unlock(gt);
 
-		mutex_unlock(&gt->i915->drm.struct_mutex);
 		if (intel_gt_is_wedged(gt)) {
 			err = -EIO;
 			break;
@@ -429,16 +425,13 @@ static int igt_reset_nop(void *arg)
 			break;
 		}
 
-		err = igt_flush_test(gt->i915, 0);
+		err = igt_flush_test(gt->i915);
 		if (err)
 			break;
 	} while (time_before(jiffies, end_time));
 	pr_info("%s: %d resets\n", __func__, count);
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
-	err = igt_flush_test(gt->i915, I915_WAIT_LOCKED);
-	mutex_unlock(&gt->i915->drm.struct_mutex);
-
+	err = igt_flush_test(gt->i915);
 out:
 	mock_file_free(gt->i915, file);
 	if (intel_gt_is_wedged(gt))
@@ -494,7 +487,6 @@ static int igt_reset_nop_engine(void *arg)
 				break;
 			}
 
-			mutex_lock(&gt->i915->drm.struct_mutex);
 			for (i = 0; i < 16; i++) {
 				struct i915_request *rq;
 
@@ -507,7 +499,6 @@ static int igt_reset_nop_engine(void *arg)
 				i915_request_add(rq);
 			}
 			err = intel_engine_reset(engine, NULL);
-			mutex_unlock(&gt->i915->drm.struct_mutex);
 			if (err) {
 				pr_err("i915_reset_engine failed\n");
 				break;
@@ -533,15 +524,12 @@ static int igt_reset_nop_engine(void *arg)
 		if (err)
 			break;
 
-		err = igt_flush_test(gt->i915, 0);
+		err = igt_flush_test(gt->i915);
 		if (err)
 			break;
 	}
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
-	err = igt_flush_test(gt->i915, I915_WAIT_LOCKED);
-	mutex_unlock(&gt->i915->drm.struct_mutex);
-
+	err = igt_flush_test(gt->i915);
 out:
 	mock_file_free(gt->i915, file);
 	if (intel_gt_is_wedged(gt))
@@ -563,9 +551,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 		return 0;
 
 	if (active) {
-		mutex_lock(&gt->i915->drm.struct_mutex);
 		err = hang_init(&h, gt);
-		mutex_unlock(&gt->i915->drm.struct_mutex);
 		if (err)
 			return err;
 	}
@@ -593,17 +579,14 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 			if (active) {
 				struct i915_request *rq;
 
-				mutex_lock(&gt->i915->drm.struct_mutex);
 				rq = hang_create_request(&h, engine);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
-					mutex_unlock(&gt->i915->drm.struct_mutex);
 					break;
 				}
 
 				i915_request_get(rq);
 				i915_request_add(rq);
-				mutex_unlock(&gt->i915->drm.struct_mutex);
 
 				if (!wait_until_running(&h, rq)) {
 					struct drm_printer p = drm_info_printer(gt->i915->drm.dev);
@@ -647,7 +630,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 		if (err)
 			break;
 
-		err = igt_flush_test(gt->i915, 0);
+		err = igt_flush_test(gt->i915);
 		if (err)
 			break;
 	}
@@ -655,11 +638,8 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 	if (intel_gt_is_wedged(gt))
 		err = -EIO;
 
-	if (active) {
-		mutex_lock(&gt->i915->drm.struct_mutex);
+	if (active)
 		hang_fini(&h);
-		mutex_unlock(&gt->i915->drm.struct_mutex);
-	}
 
 	return err;
 }
@@ -741,10 +721,8 @@ static int active_engine(void *data)
 		struct i915_request *old = rq[idx];
 		struct i915_request *new;
 
-		mutex_lock(&engine->i915->drm.struct_mutex);
 		new = igt_request_alloc(ctx[idx], engine);
 		if (IS_ERR(new)) {
-			mutex_unlock(&engine->i915->drm.struct_mutex);
 			err = PTR_ERR(new);
 			break;
 		}
@@ -755,7 +733,6 @@ static int active_engine(void *data)
 
 		rq[idx] = i915_request_get(new);
 		i915_request_add(new);
-		mutex_unlock(&engine->i915->drm.struct_mutex);
 
 		err = active_request_put(old);
 		if (err)
@@ -795,9 +772,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 		return 0;
 
 	if (flags & TEST_ACTIVE) {
-		mutex_lock(&gt->i915->drm.struct_mutex);
 		err = hang_init(&h, gt);
-		mutex_unlock(&gt->i915->drm.struct_mutex);
 		if (err)
 			return err;
 
@@ -855,17 +830,14 @@ static int __igt_reset_engines(struct intel_gt *gt,
 			struct i915_request *rq = NULL;
 
 			if (flags & TEST_ACTIVE) {
-				mutex_lock(&gt->i915->drm.struct_mutex);
 				rq = hang_create_request(&h, engine);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
-					mutex_unlock(&gt->i915->drm.struct_mutex);
 					break;
 				}
 
 				i915_request_get(rq);
 				i915_request_add(rq);
-				mutex_unlock(&gt->i915->drm.struct_mutex);
 
 				if (!wait_until_running(&h, rq)) {
 					struct drm_printer p = drm_info_printer(gt->i915->drm.dev);
@@ -977,9 +949,7 @@ unwind:
 		if (err)
 			break;
 
-		mutex_lock(&gt->i915->drm.struct_mutex);
-		err = igt_flush_test(gt->i915, I915_WAIT_LOCKED);
-		mutex_unlock(&gt->i915->drm.struct_mutex);
+		err = igt_flush_test(gt->i915);
 		if (err)
 			break;
 	}
@@ -987,11 +957,8 @@ unwind:
 	if (intel_gt_is_wedged(gt))
 		err = -EIO;
 
-	if (flags & TEST_ACTIVE) {
-		mutex_lock(&gt->i915->drm.struct_mutex);
+	if (flags & TEST_ACTIVE)
 		hang_fini(&h);
-		mutex_unlock(&gt->i915->drm.struct_mutex);
-	}
 
 	return err;
 }
@@ -1061,7 +1028,6 @@ static int igt_reset_wait(void *arg)
 
 	igt_global_reset_lock(gt);
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
 	err = hang_init(&h, gt);
 	if (err)
 		goto unlock;
@@ -1109,7 +1075,6 @@ out_rq:
 fini:
 	hang_fini(&h);
 unlock:
-	mutex_unlock(&gt->i915->drm.struct_mutex);
 	igt_global_reset_unlock(gt);
 
 	if (intel_gt_is_wedged(gt))
@@ -1189,10 +1154,9 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 
 	/* Check that we can recover an unbind stuck on a hanging request */
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
 	err = hang_init(&h, gt);
 	if (err)
-		goto unlock;
+		return err;
 
 	obj = i915_gem_object_create_internal(gt->i915, SZ_1M);
 	if (IS_ERR(obj)) {
@@ -1255,8 +1219,6 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 	if (err)
 		goto out_rq;
 
-	mutex_unlock(&gt->i915->drm.struct_mutex);
-
 	if (!wait_until_running(&h, rq)) {
 		struct drm_printer p = drm_info_printer(gt->i915->drm.dev);
 
@@ -1305,16 +1267,12 @@ out_reset:
 		put_task_struct(tsk);
 	}
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
 out_rq:
 	i915_request_put(rq);
 out_obj:
 	i915_gem_object_put(obj);
 fini:
 	hang_fini(&h);
-unlock:
-	mutex_unlock(&gt->i915->drm.struct_mutex);
-
 	if (intel_gt_is_wedged(gt))
 		return -EIO;
 
@@ -1396,7 +1354,6 @@ static int igt_reset_queue(void *arg)
 
 	igt_global_reset_lock(gt);
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
 	err = hang_init(&h, gt);
 	if (err)
 		goto unlock;
@@ -1511,7 +1468,7 @@ static int igt_reset_queue(void *arg)
 
 		i915_request_put(prev);
 
-		err = igt_flush_test(gt->i915, I915_WAIT_LOCKED);
+		err = igt_flush_test(gt->i915);
 		if (err)
 			break;
 	}
@@ -1519,7 +1476,6 @@ static int igt_reset_queue(void *arg)
 fini:
 	hang_fini(&h);
 unlock:
-	mutex_unlock(&gt->i915->drm.struct_mutex);
 	igt_global_reset_unlock(gt);
 
 	if (intel_gt_is_wedged(gt))
@@ -1546,11 +1502,9 @@ static int igt_handle_error(void *arg)
 	if (!engine || !intel_engine_can_store_dword(engine))
 		return 0;
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
-
 	err = hang_init(&h, gt);
 	if (err)
-		goto err_unlock;
+		return err;
 
 	rq = hang_create_request(&h, engine);
 	if (IS_ERR(rq)) {
@@ -1574,8 +1528,6 @@ static int igt_handle_error(void *arg)
 		goto err_request;
 	}
 
-	mutex_unlock(&gt->i915->drm.struct_mutex);
-
 	/* Temporarily disable error capture */
 	error = xchg(&global->first_error, (void *)-1);
 
@@ -1583,8 +1535,6 @@ static int igt_handle_error(void *arg)
 
 	xchg(&global->first_error, error);
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
-
 	if (rq->fence.error != -EIO) {
 		pr_err("Guilty request not identified!\n");
 		err = -EINVAL;
@@ -1595,8 +1545,6 @@ err_request:
 	i915_request_put(rq);
 err_fini:
 	hang_fini(&h);
-err_unlock:
-	mutex_unlock(&gt->i915->drm.struct_mutex);
 	return err;
 }
 
@@ -1689,7 +1637,6 @@ static int igt_reset_engines_atomic(void *arg)
 		return 0;
 
 	igt_global_reset_lock(gt);
-	mutex_lock(&gt->i915->drm.struct_mutex);
 
 	/* Flush any requests before we get started and check basics */
 	if (!igt_force_reset(gt))
@@ -1709,9 +1656,7 @@ static int igt_reset_engines_atomic(void *arg)
 out:
 	/* As we poke around the guts, do a full reset before continuing. */
 	igt_force_reset(gt);
-
 unlock:
-	mutex_unlock(&gt->i915->drm.struct_mutex);
 	igt_global_reset_unlock(gt);
 
 	return err;
@@ -1751,10 +1696,6 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 
 	err = intel_gt_live_subtests(tests, gt);
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
-	igt_flush_test(gt->i915, I915_WAIT_LOCKED);
-	mutex_unlock(&gt->i915->drm.struct_mutex);
-
 	i915_modparams.enable_hangcheck = saved_hangcheck;
 	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index dd25636abc5b..04c1cf573642 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -61,7 +61,7 @@ static int live_sanitycheck(void *arg)
 		}
 
 		igt_spinner_end(&spin);
-		if (igt_flush_test(i915, I915_WAIT_LOCKED)) {
+		if (igt_flush_test(i915)) {
 			err = -EIO;
 			goto err_ctx;
 		}
@@ -384,8 +384,7 @@ slice_semaphore_queue(struct intel_engine_cs *outer,
 	if (err)
 		goto out;
 
-	if (i915_request_wait(head,
-			      I915_WAIT_LOCKED,
+	if (i915_request_wait(head, 0,
 			      2 * RUNTIME_INFO(outer->i915)->num_engines * (count + 2) * (count + 3)) < 0) {
 		pr_err("Failed to slice along semaphore chain of length (%d, %d)!\n",
 		       count, n);
@@ -457,7 +456,7 @@ static int live_timeslice_preempt(void *arg)
 			if (err)
 				goto err_pin;
 
-			if (igt_flush_test(i915, I915_WAIT_LOCKED)) {
+			if (igt_flush_test(i915)) {
 				err = -EIO;
 				goto err_pin;
 			}
@@ -1010,7 +1009,7 @@ static int live_nopreempt(void *arg)
 			goto err_wedged;
 		}
 
-		if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		if (igt_flush_test(i915))
 			goto err_wedged;
 	}
 
@@ -1075,7 +1074,7 @@ static int live_suppress_self_preempt(void *arg)
 		if (!intel_engine_has_preemption(engine))
 			continue;
 
-		if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		if (igt_flush_test(i915))
 			goto err_wedged;
 
 		intel_engine_pm_get(engine);
@@ -1136,7 +1135,7 @@ static int live_suppress_self_preempt(void *arg)
 		}
 
 		intel_engine_pm_put(engine);
-		if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		if (igt_flush_test(i915))
 			goto err_wedged;
 	}
 
@@ -1297,7 +1296,7 @@ static int live_suppress_wait_preempt(void *arg)
 			for (i = 0; i < ARRAY_SIZE(client); i++)
 				igt_spinner_end(&client[i].spin);
 
-			if (igt_flush_test(i915, I915_WAIT_LOCKED))
+			if (igt_flush_test(i915))
 				goto err_wedged;
 
 			if (engine->execlists.preempt_hang.count) {
@@ -1576,7 +1575,7 @@ static int live_preempt_hang(void *arg)
 
 		igt_spinner_end(&spin_hi);
 		igt_spinner_end(&spin_lo);
-		if (igt_flush_test(i915, I915_WAIT_LOCKED)) {
+		if (igt_flush_test(i915)) {
 			err = -EIO;
 			goto err_ctx_lo;
 		}
@@ -1973,7 +1972,7 @@ static int nop_virtual_engine(struct drm_i915_private *i915,
 		prime, div64_u64(ktime_to_ns(times[1]), prime));
 
 out:
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		err = -EIO;
 
 	for (nc = 0; nc < nctx; nc++) {
@@ -2118,7 +2117,7 @@ static int mask_virtual_engine(struct drm_i915_private *i915,
 		goto out;
 
 out:
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		err = -EIO;
 
 	for (n = 0; n < nsibling; n++)
@@ -2296,7 +2295,7 @@ static int bond_virtual_engine(struct drm_i915_private *i915,
 out:
 	for (n = 0; !IS_ERR(rq[n]); n++)
 		i915_request_put(rq[n]);
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		err = -EIO;
 
 	kernel_context_close(ctx);
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index 321481403165..16abfabf08c7 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -6,7 +6,7 @@
 
 #include <linux/prime_numbers.h>
 
-#include "gem/i915_gem_pm.h"
+#include "intel_engine_pm.h"
 #include "intel_gt.h"
 
 #include "../selftests/i915_random.h"
@@ -136,7 +136,6 @@ static int mock_hwsp_freelist(void *arg)
 		goto err_put;
 	}
 
-	mutex_lock(&state.i915->drm.struct_mutex);
 	for (p = phases; p->name; p++) {
 		pr_debug("%s(%s)\n", __func__, p->name);
 		for_each_prime_number_from(na, 1, 2 * CACHELINES_PER_PAGE) {
@@ -149,7 +148,6 @@ static int mock_hwsp_freelist(void *arg)
 out:
 	for (na = 0; na < state.max; na++)
 		__mock_hwsp_record(&state, na, NULL);
-	mutex_unlock(&state.i915->drm.struct_mutex);
 	kfree(state.history);
 err_put:
 	drm_dev_put(&state.i915->drm);
@@ -449,8 +447,6 @@ tl_write(struct intel_timeline *tl, struct intel_engine_cs *engine, u32 value)
 	struct i915_request *rq;
 	int err;
 
-	lockdep_assert_held(&tl->gt->i915->drm.struct_mutex); /* lazy rq refs */
-
 	err = intel_timeline_pin(tl);
 	if (err) {
 		rq = ERR_PTR(err);
@@ -461,10 +457,14 @@ tl_write(struct intel_timeline *tl, struct intel_engine_cs *engine, u32 value)
 	if (IS_ERR(rq))
 		goto out_unpin;
 
+	i915_request_get(rq);
+
 	err = emit_ggtt_store_dw(rq, tl->hwsp_offset, value);
 	i915_request_add(rq);
-	if (err)
+	if (err) {
+		i915_request_put(rq);
 		rq = ERR_PTR(err);
+	}
 
 out_unpin:
 	intel_timeline_unpin(tl);
@@ -500,7 +500,6 @@ static int live_hwsp_engine(void *arg)
 	struct intel_timeline **timelines;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	unsigned long count, n;
 	int err = 0;
 
@@ -515,14 +514,13 @@ static int live_hwsp_engine(void *arg)
 	if (!timelines)
 		return -ENOMEM;
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	count = 0;
 	for_each_engine(engine, i915, id) {
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
+		intel_engine_pm_get(engine);
+
 		for (n = 0; n < NUM_TIMELINES; n++) {
 			struct intel_timeline *tl;
 			struct i915_request *rq;
@@ -530,22 +528,26 @@ static int live_hwsp_engine(void *arg)
 			tl = checked_intel_timeline_create(i915);
 			if (IS_ERR(tl)) {
 				err = PTR_ERR(tl);
-				goto out;
+				break;
 			}
 
 			rq = tl_write(tl, engine, count);
 			if (IS_ERR(rq)) {
 				intel_timeline_put(tl);
 				err = PTR_ERR(rq);
-				goto out;
+				break;
 			}
 
 			timelines[count++] = tl;
+			i915_request_put(rq);
 		}
+
+		intel_engine_pm_put(engine);
+		if (err)
+			break;
 	}
 
-out:
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		err = -EIO;
 
 	for (n = 0; n < count; n++) {
@@ -559,11 +561,7 @@ out:
 		intel_timeline_put(tl);
 	}
 
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	kvfree(timelines);
-
 	return err;
 #undef NUM_TIMELINES
 }
@@ -575,7 +573,6 @@ static int live_hwsp_alternate(void *arg)
 	struct intel_timeline **timelines;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	unsigned long count, n;
 	int err = 0;
 
@@ -591,9 +588,6 @@ static int live_hwsp_alternate(void *arg)
 	if (!timelines)
 		return -ENOMEM;
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	count = 0;
 	for (n = 0; n < NUM_TIMELINES; n++) {
 		for_each_engine(engine, i915, id) {
@@ -605,11 +599,14 @@ static int live_hwsp_alternate(void *arg)
 
 			tl = checked_intel_timeline_create(i915);
 			if (IS_ERR(tl)) {
+				intel_engine_pm_put(engine);
 				err = PTR_ERR(tl);
 				goto out;
 			}
 
+			intel_engine_pm_get(engine);
 			rq = tl_write(tl, engine, count);
+			intel_engine_pm_put(engine);
 			if (IS_ERR(rq)) {
 				intel_timeline_put(tl);
 				err = PTR_ERR(rq);
@@ -617,11 +614,12 @@ static int live_hwsp_alternate(void *arg)
 			}
 
 			timelines[count++] = tl;
+			i915_request_put(rq);
 		}
 	}
 
 out:
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		err = -EIO;
 
 	for (n = 0; n < count; n++) {
@@ -635,11 +633,7 @@ out:
 		intel_timeline_put(tl);
 	}
 
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	kvfree(timelines);
-
 	return err;
 #undef NUM_TIMELINES
 }
@@ -650,7 +644,6 @@ static int live_hwsp_wrap(void *arg)
 	struct intel_engine_cs *engine;
 	struct intel_timeline *tl;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	int err = 0;
 
 	/*
@@ -658,14 +651,10 @@ static int live_hwsp_wrap(void *arg)
 	 * foreign GPU references.
 	 */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	tl = intel_timeline_create(&i915->gt, NULL);
-	if (IS_ERR(tl)) {
-		err = PTR_ERR(tl);
-		goto out_rpm;
-	}
+	if (IS_ERR(tl))
+		return PTR_ERR(tl);
+
 	if (!tl->has_initial_breadcrumb || !tl->hwsp_cacheline)
 		goto out_free;
 
@@ -681,7 +670,9 @@ static int live_hwsp_wrap(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
+		intel_engine_pm_get(engine);
 		rq = i915_request_create(engine->kernel_context);
+		intel_engine_pm_put(engine);
 		if (IS_ERR(rq)) {
 			err = PTR_ERR(rq);
 			goto out;
@@ -747,16 +738,12 @@ static int live_hwsp_wrap(void *arg)
 	}
 
 out:
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		err = -EIO;
 
 	intel_timeline_unpin(tl);
 out_free:
 	intel_timeline_put(tl);
-out_rpm:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	return err;
 }
 
@@ -765,7 +752,6 @@ static int live_hwsp_recycle(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	unsigned long count;
 	int err = 0;
 
@@ -775,9 +761,6 @@ static int live_hwsp_recycle(void *arg)
 	 * want to confuse ourselves or the GPU.
 	 */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	count = 0;
 	for_each_engine(engine, i915, id) {
 		IGT_TIMEOUT(end_time);
@@ -785,6 +768,8 @@ static int live_hwsp_recycle(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
+		intel_engine_pm_get(engine);
+
 		do {
 			struct intel_timeline *tl;
 			struct i915_request *rq;
@@ -792,21 +777,22 @@ static int live_hwsp_recycle(void *arg)
 			tl = checked_intel_timeline_create(i915);
 			if (IS_ERR(tl)) {
 				err = PTR_ERR(tl);
-				goto out;
+				break;
 			}
 
 			rq = tl_write(tl, engine, count);
 			if (IS_ERR(rq)) {
 				intel_timeline_put(tl);
 				err = PTR_ERR(rq);
-				goto out;
+				break;
 			}
 
 			if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 				pr_err("Wait for timeline writes timed out!\n");
+				i915_request_put(rq);
 				intel_timeline_put(tl);
 				err = -EIO;
-				goto out;
+				break;
 			}
 
 			if (*tl->hwsp_seqno != count) {
@@ -815,17 +801,18 @@ static int live_hwsp_recycle(void *arg)
 				err = -EINVAL;
 			}
 
+			i915_request_put(rq);
 			intel_timeline_put(tl);
 			count++;
 
 			if (err)
-				goto out;
+				break;
 		} while (!__igt_timeout(end_time, NULL));
-	}
 
-out:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
+		intel_engine_pm_put(engine);
+		if (err)
+			break;
+	}
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index d40ce0709bff..4ee2e2babd0d 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -676,7 +676,7 @@ out_unpin:
 			break;
 	}
 
-	if (igt_flush_test(ctx->i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(ctx->i915))
 		err = -EIO;
 out_batch:
 	i915_vma_unpin_and_release(&batch, 0);
@@ -1090,7 +1090,7 @@ err:
 		kernel_context_close(client[i].ctx);
 	}
 
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		err = -EIO;
 
 	return err;
@@ -1248,7 +1248,7 @@ err:
 	igt_global_reset_unlock(&i915->gt);
 	kernel_context_close(ctx);
 
-	igt_flush_test(i915, I915_WAIT_LOCKED);
+	igt_flush_test(i915);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index fec9fb7cc384..385289895107 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3621,6 +3621,7 @@ static int
 i915_drop_caches_set(void *data, u64 val)
 {
 	struct drm_i915_private *i915 = data;
+	int ret;
 
 	DRM_DEBUG("Dropping caches: 0x%08llx [0x%08llx]\n",
 		  val, val & DROP_ALL);
@@ -3630,40 +3631,21 @@ i915_drop_caches_set(void *data, u64 val)
 		     I915_IDLE_ENGINES_TIMEOUT))
 		intel_gt_set_wedged(&i915->gt);
 
-	/* No need to check and wait for gpu resets, only libdrm auto-restarts
-	 * on ioctls on -EAGAIN. */
-	if (val & (DROP_ACTIVE | DROP_IDLE | DROP_RETIRE | DROP_RESET_SEQNO)) {
-		int ret;
+	if (val & DROP_RETIRE)
+		i915_retire_requests(i915);
 
-		ret = mutex_lock_interruptible(&i915->drm.struct_mutex);
+	if (val & (DROP_IDLE | DROP_ACTIVE)) {
+		ret = i915_gem_wait_for_idle(i915,
+					     I915_WAIT_INTERRUPTIBLE,
+					     MAX_SCHEDULE_TIMEOUT);
 		if (ret)
 			return ret;
+	}
 
-		/*
-		 * To finish the flush of the idle_worker, we must complete
-		 * the switch-to-kernel-context, which requires a double
-		 * pass through wait_for_idle: first queues the switch,
-		 * second waits for the switch.
-		 */
-		if (ret == 0 && val & (DROP_IDLE | DROP_ACTIVE))
-			ret = i915_gem_wait_for_idle(i915,
-						     I915_WAIT_INTERRUPTIBLE |
-						     I915_WAIT_LOCKED,
-						     MAX_SCHEDULE_TIMEOUT);
-
-		if (ret == 0 && val & DROP_IDLE)
-			ret = i915_gem_wait_for_idle(i915,
-						     I915_WAIT_INTERRUPTIBLE |
-						     I915_WAIT_LOCKED,
-						     MAX_SCHEDULE_TIMEOUT);
-
-		if (val & DROP_RETIRE)
-			i915_retire_requests(i915);
-
-		mutex_unlock(&i915->drm.struct_mutex);
-
-		if (ret == 0 && val & DROP_IDLE)
-			ret = intel_gt_pm_wait_for_idle(&i915->gt);
+	if (val & DROP_IDLE) {
+		ret = intel_gt_pm_wait_for_idle(&i915->gt);
+		if (ret)
+			return ret;
 	}
 
 	if (val & DROP_RESET_ACTIVE && intel_gt_terminally_wedged(&i915->gt))
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b0aa0a7c680f..83c2c7bf1e34 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -945,19 +945,16 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915,
 	if (!intel_gt_pm_is_awake(gt))
 		return 0;
 
-	GEM_TRACE("flags=%x (%s), timeout=%ld%s\n",
-		  flags, flags & I915_WAIT_LOCKED ? "locked" : "unlocked",
-		  timeout, timeout == MAX_SCHEDULE_TIMEOUT ? " (forever)" : "");
-
-	timeout = wait_for_timelines(gt, flags, timeout);
-	if (timeout < 0)
-		return timeout;
+	do {
+		timeout = wait_for_timelines(gt, flags, timeout);
+		if (timeout < 0)
+			return timeout;
 
-	if (flags & I915_WAIT_LOCKED) {
-		lockdep_assert_held(&i915->drm.struct_mutex);
+		cond_resched();
+		if (signal_pending(current))
+			return -EINTR;
 
-		i915_retire_requests(i915);
-	}
+	} while (i915_retire_requests(i915));
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 91a885c36c6b..621fb33cda30 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -308,10 +308,9 @@ long i915_request_wait(struct i915_request *rq,
 		       long timeout)
 	__attribute__((nonnull(1)));
 #define I915_WAIT_INTERRUPTIBLE	BIT(0)
-#define I915_WAIT_LOCKED	BIT(1) /* struct_mutex held, handle GPU reset */
-#define I915_WAIT_PRIORITY	BIT(2) /* small priority bump for the request */
-#define I915_WAIT_ALL		BIT(3) /* used by i915_gem_object_wait() */
-#define I915_WAIT_FOR_IDLE_BOOST BIT(4)
+#define I915_WAIT_PRIORITY	BIT(1) /* small priority bump for the request */
+#define I915_WAIT_ALL		BIT(2) /* used by i915_gem_object_wait() */
+#define I915_WAIT_FOR_IDLE_BOOST BIT(3)
 
 static inline bool i915_request_signaled(const struct i915_request *rq)
 {
diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
index 2cc71bcf884f..268192b5613b 100644
--- a/drivers/gpu/drm/i915/selftests/i915_active.c
+++ b/drivers/gpu/drm/i915/selftests/i915_active.c
@@ -162,10 +162,8 @@ static int live_active_wait(void *arg)
 
 	__live_put(active);
 
-	mutex_lock(&i915->drm.struct_mutex);
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		err = -EIO;
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	return err;
 }
@@ -183,10 +181,8 @@ static int live_active_retire(void *arg)
 		return PTR_ERR(active);
 
 	/* waits for & retires all requests */
-	mutex_lock(&i915->drm.struct_mutex);
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		err = -EIO;
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	if (!READ_ONCE(active->retired)) {
 		pr_err("i915_active not retired after flushing!\n");
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index 75a4695b82bb..52d2df843148 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -523,7 +523,7 @@ static int igt_evict_contexts(void *arg)
 
 	mutex_lock(&i915->ggtt.vm.mutex);
 out_locked:
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		err = -EIO;
 	while (reserved) {
 		struct reserved *next = reserved->next;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 02749bbfd0cf..e40e6cfa51f1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1705,12 +1705,8 @@ int i915_gem_gtt_mock_selftests(void)
 
 	err = i915_subtests(tests, ggtt);
 
-	mutex_lock(&i915->drm.struct_mutex);
 	mock_device_flush(i915);
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	i915_gem_drain_freed_objects(i915);
-
 	mock_fini_ggtt(ggtt);
 	kfree(ggtt);
 out_put:
@@ -2006,7 +2002,7 @@ static int igt_cs_tlb(void *arg)
 		}
 	}
 end:
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		err = -EIO;
 	i915_gem_context_unlock_engines(ctx);
 	i915_gem_object_unpin_map(out);
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index eb175da48547..d7d68c6a6bd5 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -41,21 +41,16 @@ static int igt_add_request(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct i915_request *request;
-	int err = -ENOMEM;
 
 	/* Basic preliminary test to create a request and let it loose! */
 
-	mutex_lock(&i915->drm.struct_mutex);
 	request = mock_request(i915->engine[RCS0]->kernel_context, HZ / 10);
 	if (!request)
-		goto out_unlock;
+		return -ENOMEM;
 
 	i915_request_add(request);
 
-	err = 0;
-out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
-	return err;
+	return 0;
 }
 
 static int igt_wait_request(void *arg)
@@ -67,12 +62,10 @@ static int igt_wait_request(void *arg)
 
 	/* Submit a request, then wait upon it */
 
-	mutex_lock(&i915->drm.struct_mutex);
 	request = mock_request(i915->engine[RCS0]->kernel_context, T);
-	if (!request) {
-		err = -ENOMEM;
-		goto out_unlock;
-	}
+	if (!request)
+		return -ENOMEM;
+
 	i915_request_get(request);
 
 	if (i915_request_wait(request, 0, 0) != -ETIME) {
@@ -125,9 +118,7 @@ static int igt_wait_request(void *arg)
 	err = 0;
 out_request:
 	i915_request_put(request);
-out_unlock:
 	mock_device_flush(i915);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
@@ -140,52 +131,45 @@ static int igt_fence_wait(void *arg)
 
 	/* Submit a request, treat it as a fence and wait upon it */
 
-	mutex_lock(&i915->drm.struct_mutex);
 	request = mock_request(i915->engine[RCS0]->kernel_context, T);
-	if (!request) {
-		err = -ENOMEM;
-		goto out_locked;
-	}
+	if (!request)
+		return -ENOMEM;
 
 	if (dma_fence_wait_timeout(&request->fence, false, T) != -ETIME) {
 		pr_err("fence wait success before submit (expected timeout)!\n");
-		goto out_locked;
+		goto out;
 	}
 
 	i915_request_add(request);
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	if (dma_fence_is_signaled(&request->fence)) {
 		pr_err("fence signaled immediately!\n");
-		goto out_device;
+		goto out;
 	}
 
 	if (dma_fence_wait_timeout(&request->fence, false, T / 2) != -ETIME) {
 		pr_err("fence wait success after submit (expected timeout)!\n");
-		goto out_device;
+		goto out;
 	}
 
 	if (dma_fence_wait_timeout(&request->fence, false, T) <= 0) {
 		pr_err("fence wait timed out (expected success)!\n");
-		goto out_device;
+		goto out;
 	}
 
 	if (!dma_fence_is_signaled(&request->fence)) {
 		pr_err("fence unsignaled after waiting!\n");
-		goto out_device;
+		goto out;
 	}
 
 	if (dma_fence_wait_timeout(&request->fence, false, T) <= 0) {
 		pr_err("fence wait timed out when complete (expected success)!\n");
-		goto out_device;
+		goto out;
 	}
 
 	err = 0;
-out_device:
-	mutex_lock(&i915->drm.struct_mutex);
-out_locked:
+out:
 	mock_device_flush(i915);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
@@ -199,6 +183,8 @@ static int igt_request_rewind(void *arg)
 
 	mutex_lock(&i915->drm.struct_mutex);
 	ctx[0] = mock_context(i915, "A");
+	mutex_unlock(&i915->drm.struct_mutex);
+
 	ce = i915_gem_context_get_engine(ctx[0], RCS0);
 	GEM_BUG_ON(IS_ERR(ce));
 	request = mock_request(ce, 2 * HZ);
@@ -211,7 +197,10 @@ static int igt_request_rewind(void *arg)
 	i915_request_get(request);
 	i915_request_add(request);
 
+	mutex_lock(&i915->drm.struct_mutex);
 	ctx[1] = mock_context(i915, "B");
+	mutex_unlock(&i915->drm.struct_mutex);
+
 	ce = i915_gem_context_get_engine(ctx[1], RCS0);
 	GEM_BUG_ON(IS_ERR(ce));
 	vip = mock_request(ce, 0);
@@ -233,7 +222,6 @@ static int igt_request_rewind(void *arg)
 	request->engine->submit_request(request);
 	rcu_read_unlock();
 
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	if (i915_request_wait(vip, 0, HZ) == -ETIME) {
 		pr_err("timed out waiting for high priority request\n");
@@ -248,14 +236,12 @@ static int igt_request_rewind(void *arg)
 	err = 0;
 err:
 	i915_request_put(vip);
-	mutex_lock(&i915->drm.struct_mutex);
 err_context_1:
 	mock_context_close(ctx[1]);
 	i915_request_put(request);
 err_context_0:
 	mock_context_close(ctx[0]);
 	mock_device_flush(i915);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
@@ -282,7 +268,6 @@ __live_request_alloc(struct intel_context *ce)
 static int __igt_breadcrumbs_smoketest(void *arg)
 {
 	struct smoketest *t = arg;
-	struct mutex * const BKL = &t->engine->i915->drm.struct_mutex;
 	const unsigned int max_batch = min(t->ncontexts, t->max_batch) - 1;
 	const unsigned int total = 4 * t->ncontexts + 1;
 	unsigned int num_waits = 0, num_fences = 0;
@@ -337,14 +322,11 @@ static int __igt_breadcrumbs_smoketest(void *arg)
 			struct i915_request *rq;
 			struct intel_context *ce;
 
-			mutex_lock(BKL);
-
 			ce = i915_gem_context_get_engine(ctx, t->engine->legacy_idx);
 			GEM_BUG_ON(IS_ERR(ce));
 			rq = t->request_alloc(ce);
 			intel_context_put(ce);
 			if (IS_ERR(rq)) {
-				mutex_unlock(BKL);
 				err = PTR_ERR(rq);
 				count = n;
 				break;
@@ -357,8 +339,6 @@ static int __igt_breadcrumbs_smoketest(void *arg)
 			requests[n] = i915_request_get(rq);
 			i915_request_add(rq);
 
-			mutex_unlock(BKL);
-
 			if (err >= 0)
 				err = i915_sw_fence_await_dma_fence(wait,
 								    &rq->fence,
@@ -457,15 +437,15 @@ static int mock_breadcrumbs_smoketest(void *arg)
 		goto out_threads;
 	}
 
-	mutex_lock(&t.engine->i915->drm.struct_mutex);
 	for (n = 0; n < t.ncontexts; n++) {
+		mutex_lock(&t.engine->i915->drm.struct_mutex);
 		t.contexts[n] = mock_context(t.engine->i915, "mock");
+		mutex_unlock(&t.engine->i915->drm.struct_mutex);
 		if (!t.contexts[n]) {
 			ret = -ENOMEM;
 			goto out_contexts;
 		}
 	}
-	mutex_unlock(&t.engine->i915->drm.struct_mutex);
 
 	for (n = 0; n < ncpus; n++) {
 		threads[n] = kthread_run(__igt_breadcrumbs_smoketest,
@@ -495,18 +475,15 @@ static int mock_breadcrumbs_smoketest(void *arg)
 		atomic_long_read(&t.num_fences),
 		ncpus);
 
-	mutex_lock(&t.engine->i915->drm.struct_mutex);
 out_contexts:
 	for (n = 0; n < t.ncontexts; n++) {
 		if (!t.contexts[n])
 			break;
 		mock_context_close(t.contexts[n]);
 	}
-	mutex_unlock(&t.engine->i915->drm.struct_mutex);
 	kfree(t.contexts);
 out_threads:
 	kfree(threads);
-
 	return ret;
 }
 
@@ -539,7 +516,6 @@ static int live_nop_request(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct intel_engine_cs *engine;
-	intel_wakeref_t wakeref;
 	struct igt_live_test t;
 	unsigned int id;
 	int err = -ENODEV;
@@ -549,28 +525,25 @@ static int live_nop_request(void *arg)
 	 * the overhead of submitting requests to the hardware.
 	 */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	for_each_engine(engine, i915, id) {
-		struct i915_request *request = NULL;
 		unsigned long n, prime;
 		IGT_TIMEOUT(end_time);
 		ktime_t times[2] = {};
 
 		err = igt_live_test_begin(&t, i915, __func__, engine->name);
 		if (err)
-			goto out_unlock;
+			return err;
 
 		for_each_prime_number_from(prime, 1, 8192) {
+			struct i915_request *request = NULL;
+
 			times[1] = ktime_get_raw();
 
 			for (n = 0; n < prime; n++) {
+				i915_request_put(request);
 				request = i915_request_create(engine->kernel_context);
-				if (IS_ERR(request)) {
-					err = PTR_ERR(request);
-					goto out_unlock;
-				}
+				if (IS_ERR(request))
+					return PTR_ERR(request);
 
 				/* This space is left intentionally blank.
 				 *
@@ -585,9 +558,11 @@ static int live_nop_request(void *arg)
 				 * for latency.
 				 */
 
+				i915_request_get(request);
 				i915_request_add(request);
 			}
 			i915_request_wait(request, 0, MAX_SCHEDULE_TIMEOUT);
+			i915_request_put(request);
 
 			times[1] = ktime_sub(ktime_get_raw(), times[1]);
 			if (prime == 1)
@@ -599,7 +574,7 @@ static int live_nop_request(void *arg)
 
 		err = igt_live_test_end(&t);
 		if (err)
-			goto out_unlock;
+			return err;
 
 		pr_info("Request latencies on %s: 1 = %lluns, %lu = %lluns\n",
 			engine->name,
@@ -607,9 +582,6 @@ static int live_nop_request(void *arg)
 			prime, div64_u64(ktime_to_ns(times[1]), prime));
 	}
 
-out_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
@@ -679,6 +651,7 @@ empty_request(struct intel_engine_cs *engine,
 	if (err)
 		goto out_request;
 
+	i915_request_get(request);
 out_request:
 	i915_request_add(request);
 	return err ? ERR_PTR(err) : request;
@@ -688,7 +661,6 @@ static int live_empty_request(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct intel_engine_cs *engine;
-	intel_wakeref_t wakeref;
 	struct igt_live_test t;
 	struct i915_vma *batch;
 	unsigned int id;
@@ -699,14 +671,9 @@ static int live_empty_request(void *arg)
 	 * the overhead of submitting requests to the hardware.
 	 */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	batch = empty_batch(i915);
-	if (IS_ERR(batch)) {
-		err = PTR_ERR(batch);
-		goto out_unlock;
-	}
+	if (IS_ERR(batch))
+		return PTR_ERR(batch);
 
 	for_each_engine(engine, i915, id) {
 		IGT_TIMEOUT(end_time);
@@ -730,6 +697,7 @@ static int live_empty_request(void *arg)
 			times[1] = ktime_get_raw();
 
 			for (n = 0; n < prime; n++) {
+				i915_request_put(request);
 				request = empty_request(engine, batch);
 				if (IS_ERR(request)) {
 					err = PTR_ERR(request);
@@ -745,6 +713,7 @@ static int live_empty_request(void *arg)
 			if (__igt_timeout(end_time, NULL))
 				break;
 		}
+		i915_request_put(request);
 
 		err = igt_live_test_end(&t);
 		if (err)
@@ -759,9 +728,6 @@ static int live_empty_request(void *arg)
 out_batch:
 	i915_vma_unpin(batch);
 	i915_vma_put(batch);
-out_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
@@ -841,7 +807,6 @@ static int live_all_engines(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct intel_engine_cs *engine;
 	struct i915_request *request[I915_NUM_ENGINES];
-	intel_wakeref_t wakeref;
 	struct igt_live_test t;
 	struct i915_vma *batch;
 	unsigned int id;
@@ -852,18 +817,15 @@ static int live_all_engines(void *arg)
 	 * block doing so, and that they don't complete too soon.
 	 */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	err = igt_live_test_begin(&t, i915, __func__, "");
 	if (err)
-		goto out_unlock;
+		return err;
 
 	batch = recursive_batch(i915);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
 		pr_err("%s: Unable to create batch, err=%d\n", __func__, err);
-		goto out_unlock;
+		return err;
 	}
 
 	for_each_engine(engine, i915, id) {
@@ -933,9 +895,6 @@ out_request:
 			i915_request_put(request[id]);
 	i915_vma_unpin(batch);
 	i915_vma_put(batch);
-out_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
@@ -945,7 +904,6 @@ static int live_sequential_engines(void *arg)
 	struct i915_request *request[I915_NUM_ENGINES] = {};
 	struct i915_request *prev = NULL;
 	struct intel_engine_cs *engine;
-	intel_wakeref_t wakeref;
 	struct igt_live_test t;
 	unsigned int id;
 	int err;
@@ -956,12 +914,9 @@ static int live_sequential_engines(void *arg)
 	 * they are running on independent engines.
 	 */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	err = igt_live_test_begin(&t, i915, __func__, "");
 	if (err)
-		goto out_unlock;
+		return err;
 
 	for_each_engine(engine, i915, id) {
 		struct i915_vma *batch;
@@ -971,7 +926,7 @@ static int live_sequential_engines(void *arg)
 			err = PTR_ERR(batch);
 			pr_err("%s: Unable to create batch for %s, err=%d\n",
 			       __func__, engine->name, err);
-			goto out_unlock;
+			return err;
 		}
 
 		request[id] = i915_request_create(engine->kernel_context);
@@ -1063,9 +1018,6 @@ out_request:
 		i915_vma_put(request[id]->batch);
 		i915_request_put(request[id]);
 	}
-out_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
@@ -1080,16 +1032,12 @@ static int __live_parallel_engine1(void *arg)
 		struct i915_request *rq;
 		int err;
 
-		mutex_lock(&engine->i915->drm.struct_mutex);
 		rq = i915_request_create(engine->kernel_context);
-		if (IS_ERR(rq)) {
-			mutex_unlock(&engine->i915->drm.struct_mutex);
+		if (IS_ERR(rq))
 			return PTR_ERR(rq);
-		}
 
 		i915_request_get(rq);
 		i915_request_add(rq);
-		mutex_unlock(&engine->i915->drm.struct_mutex);
 
 		err = 0;
 		if (i915_request_wait(rq, 0, HZ / 5) < 0)
@@ -1115,16 +1063,11 @@ static int __live_parallel_engineN(void *arg)
 	do {
 		struct i915_request *rq;
 
-		mutex_lock(&engine->i915->drm.struct_mutex);
 		rq = i915_request_create(engine->kernel_context);
-		if (IS_ERR(rq)) {
-			mutex_unlock(&engine->i915->drm.struct_mutex);
+		if (IS_ERR(rq))
 			return PTR_ERR(rq);
-		}
 
 		i915_request_add(rq);
-		mutex_unlock(&engine->i915->drm.struct_mutex);
-
 		count++;
 	} while (!__igt_timeout(end_time, NULL));
 
@@ -1154,9 +1097,7 @@ static int live_parallel_engines(void *arg)
 		struct task_struct *tsk[I915_NUM_ENGINES] = {};
 		struct igt_live_test t;
 
-		mutex_lock(&i915->drm.struct_mutex);
 		err = igt_live_test_begin(&t, i915, __func__, "");
-		mutex_unlock(&i915->drm.struct_mutex);
 		if (err)
 			break;
 
@@ -1184,10 +1125,8 @@ static int live_parallel_engines(void *arg)
 			put_task_struct(tsk[id]);
 		}
 
-		mutex_lock(&i915->drm.struct_mutex);
 		if (igt_live_test_end(&t))
 			err = -EIO;
-		mutex_unlock(&i915->drm.struct_mutex);
 	}
 
 	return err;
@@ -1280,9 +1219,10 @@ static int live_breadcrumbs_smoketest(void *arg)
 		goto out_threads;
 	}
 
-	mutex_lock(&i915->drm.struct_mutex);
 	for (n = 0; n < t[0].ncontexts; n++) {
+		mutex_lock(&i915->drm.struct_mutex);
 		t[0].contexts[n] = live_context(i915, file);
+		mutex_unlock(&i915->drm.struct_mutex);
 		if (!t[0].contexts[n]) {
 			ret = -ENOMEM;
 			goto out_contexts;
@@ -1299,7 +1239,6 @@ static int live_breadcrumbs_smoketest(void *arg)
 		t[id].max_batch = max_batches(t[0].contexts[0], engine);
 		if (t[id].max_batch < 0) {
 			ret = t[id].max_batch;
-			mutex_unlock(&i915->drm.struct_mutex);
 			goto out_flush;
 		}
 		/* One ring interleaved between requests from all cpus */
@@ -1314,7 +1253,6 @@ static int live_breadcrumbs_smoketest(void *arg)
 					  &t[id], "igt/%d.%d", id, n);
 			if (IS_ERR(tsk)) {
 				ret = PTR_ERR(tsk);
-				mutex_unlock(&i915->drm.struct_mutex);
 				goto out_flush;
 			}
 
@@ -1322,7 +1260,6 @@ static int live_breadcrumbs_smoketest(void *arg)
 			threads[id * ncpus + n] = tsk;
 		}
 	}
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	msleep(jiffies_to_msecs(i915_selftest.timeout_jiffies));
 
@@ -1350,10 +1287,8 @@ out_flush:
 	pr_info("Completed %lu waits for %lu fences across %d engines and %d cpus\n",
 		num_waits, num_fences, RUNTIME_INFO(i915)->num_engines, ncpus);
 
-	mutex_lock(&i915->drm.struct_mutex);
 	ret = igt_live_test_end(&live) ?: ret;
 out_contexts:
-	mutex_unlock(&i915->drm.struct_mutex);
 	kfree(t[0].contexts);
 out_threads:
 	kfree(threads);
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index 438ea0eaa416..825a8286cbe8 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -263,10 +263,8 @@ int __i915_live_teardown(int err, void *data)
 {
 	struct drm_i915_private *i915 = data;
 
-	mutex_lock(&i915->drm.struct_mutex);
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		err = -EIO;
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	i915_gem_drain_freed_objects(i915);
 
@@ -284,10 +282,8 @@ int __intel_gt_live_teardown(int err, void *data)
 {
 	struct intel_gt *gt = data;
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
-	if (igt_flush_test(gt->i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(gt->i915))
 		err = -EIO;
-	mutex_unlock(&gt->i915->drm.struct_mutex);
 
 	i915_gem_drain_freed_objects(gt->i915);
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index 0e4f66312b39..1c9db08f7c28 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -833,12 +833,8 @@ int i915_vma_mock_selftests(void)
 
 	err = i915_subtests(tests, ggtt);
 
-	mutex_lock(&i915->drm.struct_mutex);
 	mock_device_flush(i915);
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	i915_gem_drain_freed_objects(i915);
-
 	mock_fini_ggtt(ggtt);
 	kfree(ggtt);
 out_put:
diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
index d3b5eb402d33..2a5fbe46ea9f 100644
--- a/drivers/gpu/drm/i915/selftests/igt_flush_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
@@ -12,31 +12,25 @@
 
 #include "igt_flush_test.h"
 
-int igt_flush_test(struct drm_i915_private *i915, unsigned int flags)
+int igt_flush_test(struct drm_i915_private *i915)
 {
 	int ret = intel_gt_is_wedged(&i915->gt) ? -EIO : 0;
-	int repeat = !!(flags & I915_WAIT_LOCKED);
 
 	cond_resched();
 
-	do {
-		if (i915_gem_wait_for_idle(i915, flags, HZ / 5) == -ETIME) {
-			pr_err("%pS timed out, cancelling all further testing.\n",
-			       __builtin_return_address(0));
+	i915_retire_requests(i915);
+	if (i915_gem_wait_for_idle(i915, 0, HZ / 5) == -ETIME) {
+		pr_err("%pS timed out, cancelling all further testing.\n",
+		       __builtin_return_address(0));
 
-			GEM_TRACE("%pS timed out.\n",
-				  __builtin_return_address(0));
-			GEM_TRACE_DUMP();
+		GEM_TRACE("%pS timed out.\n",
+			  __builtin_return_address(0));
+		GEM_TRACE_DUMP();
 
-			intel_gt_set_wedged(&i915->gt);
-			repeat = 0;
-			ret = -EIO;
-		}
-
-		/* Ensure we also flush after wedging. */
-		if (flags & I915_WAIT_LOCKED)
-			i915_retire_requests(i915);
-	} while (repeat--);
+		intel_gt_set_wedged(&i915->gt);
+		ret = -EIO;
+	}
+	i915_retire_requests(i915);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.h b/drivers/gpu/drm/i915/selftests/igt_flush_test.h
index 63e009927c43..7541fa74e641 100644
--- a/drivers/gpu/drm/i915/selftests/igt_flush_test.h
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.h
@@ -9,6 +9,6 @@
 
 struct drm_i915_private;
 
-int igt_flush_test(struct drm_i915_private *i915, unsigned int flags);
+int igt_flush_test(struct drm_i915_private *i915);
 
 #endif /* IGT_FLUSH_TEST_H */
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c
index 3e902761cd16..04a6f88fdf64 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c
@@ -19,15 +19,12 @@ int igt_live_test_begin(struct igt_live_test *t,
 	enum intel_engine_id id;
 	int err;
 
-	lockdep_assert_held(&i915->drm.struct_mutex);
-
 	t->i915 = i915;
 	t->func = func;
 	t->name = name;
 
 	err = i915_gem_wait_for_idle(i915,
-				     I915_WAIT_INTERRUPTIBLE |
-				     I915_WAIT_LOCKED,
+				     I915_WAIT_INTERRUPTIBLE,
 				     MAX_SCHEDULE_TIMEOUT);
 	if (err) {
 		pr_err("%s(%s): failed to idle before, with err=%d!",
@@ -50,9 +47,7 @@ int igt_live_test_end(struct igt_live_test *t)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	lockdep_assert_held(&i915->drm.struct_mutex);
-
-	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+	if (igt_flush_test(i915))
 		return -EIO;
 
 	if (t->reset_global != i915_reset_count(&i915->gpu_error)) {
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 2448067822af..622bb2127453 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -41,8 +41,6 @@ void mock_device_flush(struct drm_i915_private *i915)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	lockdep_assert_held(&i915->drm.struct_mutex);
-
 	do {
 		for_each_engine(engine, i915, id)
 			mock_engine_flush(engine);
@@ -55,9 +53,7 @@ static void mock_device_release(struct drm_device *dev)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	mutex_lock(&i915->drm.struct_mutex);
 	mock_device_flush(i915);
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	flush_work(&i915->gem.idle_work);
 	i915_gem_drain_workqueue(i915);
-- 
cgit v1.2.3


From 33d856445b3ef6f00466cd9fbb04d69061143077 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:03 +0100
Subject: drm/i915: Remove the GEM idle worker

Nothing inside the idle worker now requires struct_mutex, so we can
remove the indirection of using our own worker.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-9-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_pm.c             | 28 ++--------------------
 drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c |  3 ---
 drivers/gpu/drm/i915/i915_debugfs.c                |  5 ----
 drivers/gpu/drm/i915/i915_drv.h                    |  9 -------
 drivers/gpu/drm/i915/selftests/mock_gem_device.c   |  6 -----
 5 files changed, 2 insertions(+), 49 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 2ddc3aeaac9d..26f325bbfe4d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -13,36 +13,13 @@
 
 static void i915_gem_park(struct drm_i915_private *i915)
 {
-	lockdep_assert_held(&i915->drm.struct_mutex);
+	cancel_delayed_work(&i915->gem.retire_work);
 
 	i915_vma_parked(i915);
 
 	i915_globals_park();
 }
 
-static void idle_work_handler(struct work_struct *work)
-{
-	struct drm_i915_private *i915 =
-		container_of(work, typeof(*i915), gem.idle_work);
-	bool park;
-
-	cancel_delayed_work_sync(&i915->gem.retire_work);
-	mutex_lock(&i915->drm.struct_mutex);
-
-	intel_wakeref_lock(&i915->gt.wakeref);
-	park = (!intel_wakeref_is_active(&i915->gt.wakeref) &&
-		!work_pending(work));
-	intel_wakeref_unlock(&i915->gt.wakeref);
-	if (park)
-		i915_gem_park(i915);
-	else
-		queue_delayed_work(i915->wq,
-				   &i915->gem.retire_work,
-				   round_jiffies_up_relative(HZ));
-
-	mutex_unlock(&i915->drm.struct_mutex);
-}
-
 static void retire_work_handler(struct work_struct *work)
 {
 	struct drm_i915_private *i915 =
@@ -71,7 +48,7 @@ static int pm_notifier(struct notifier_block *nb,
 		break;
 
 	case INTEL_GT_PARK:
-		queue_work(i915->wq, &i915->gem.idle_work);
+		i915_gem_park(i915);
 		break;
 	}
 
@@ -264,7 +241,6 @@ err_wedged:
 
 void i915_gem_init__pm(struct drm_i915_private *i915)
 {
-	INIT_WORK(&i915->gem.idle_work, idle_work_handler);
 	INIT_DELAYED_WORK(&i915->gem.retire_work, retire_work_handler);
 
 	i915->gem.pm_notifier.notifier_call = pm_notifier;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 856b8e467ee8..4ba6ed5c8313 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -572,11 +572,8 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
 static void disable_retire_worker(struct drm_i915_private *i915)
 {
 	i915_gem_driver_unregister__shrinker(i915);
-
 	intel_gt_pm_get(&i915->gt);
-
 	cancel_delayed_work_sync(&i915->gem.retire_work);
-	flush_work(&i915->gem.idle_work);
 }
 
 static void restore_retire_worker(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 385289895107..7c4bba21adcd 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3662,11 +3662,6 @@ i915_drop_caches_set(void *data, u64 val)
 		i915_gem_shrink_all(i915);
 	fs_reclaim_release(GFP_KERNEL);
 
-	if (val & DROP_IDLE) {
-		flush_delayed_work(&i915->gem.retire_work);
-		flush_work(&i915->gem.idle_work);
-	}
-
 	if (val & DROP_FREED)
 		i915_gem_drain_freed_objects(i915);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 337d8306416a..ad31852e4309 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1719,15 +1719,6 @@ struct drm_i915_private {
 		 * fires, go retire requests.
 		 */
 		struct delayed_work retire_work;
-
-		/**
-		 * When we detect an idle GPU, we want to turn on
-		 * powersaving features. So once we see that there
-		 * are no more requests outstanding and no more
-		 * arrive within a small period of time, we fire
-		 * off the idle_work.
-		 */
-		struct work_struct idle_work;
 	} gem;
 
 	/* For i945gm vblank irq vs. C3 workaround */
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 622bb2127453..a8be5da2b3cf 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -55,7 +55,6 @@ static void mock_device_release(struct drm_device *dev)
 
 	mock_device_flush(i915);
 
-	flush_work(&i915->gem.idle_work);
 	i915_gem_drain_workqueue(i915);
 
 	mutex_lock(&i915->drm.struct_mutex);
@@ -103,10 +102,6 @@ static void mock_retire_work_handler(struct work_struct *work)
 {
 }
 
-static void mock_idle_work_handler(struct work_struct *work)
-{
-}
-
 static int pm_domain_resume(struct device *dev)
 {
 	return pm_generic_runtime_resume(dev);
@@ -187,7 +182,6 @@ struct drm_i915_private *mock_gem_device(void)
 	mock_init_contexts(i915);
 
 	INIT_DELAYED_WORK(&i915->gem.retire_work, mock_retire_work_handler);
-	INIT_WORK(&i915->gem.idle_work, mock_idle_work_handler);
 
 	intel_timelines_init(i915);
 
-- 
cgit v1.2.3


From f33a8a51602c84cc7d5cadd2655835ba3b7d03f9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:04 +0100
Subject: drm/i915: Merge wait_for_timelines with retire_request

wait_for_timelines is essentially the same loop as retiring requests
(with an extra timeout), so merge the two into one routine.

v2: i915_retire_requests_timeout and keep VT'd w/a as !interruptible

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-10-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_mman.c           |  4 +-
 drivers/gpu/drm/i915/gem/i915_gem_pm.c             |  4 +-
 .../gpu/drm/i915/gem/selftests/i915_gem_context.c  |  2 +-
 drivers/gpu/drm/i915/gt/intel_gt_pm.c              |  3 +-
 drivers/gpu/drm/i915/i915_debugfs.c                |  4 +-
 drivers/gpu/drm/i915/i915_drv.h                    |  3 +-
 drivers/gpu/drm/i915/i915_gem.c                    | 67 ++--------------------
 drivers/gpu/drm/i915/i915_gem_evict.c              | 12 ++--
 drivers/gpu/drm/i915/i915_gem_gtt.c                |  4 +-
 drivers/gpu/drm/i915/i915_request.c                | 26 ++++++++-
 drivers/gpu/drm/i915/i915_request.h                |  7 ++-
 drivers/gpu/drm/i915/selftests/igt_flush_test.c    |  4 +-
 drivers/gpu/drm/i915/selftests/igt_live_test.c     |  4 +-
 drivers/gpu/drm/i915/selftests/mock_gem_device.c   |  2 +-
 14 files changed, 50 insertions(+), 96 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index c19431d609fc..418d0d2b5fa9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -432,9 +432,7 @@ static int create_mmap_offset(struct drm_i915_gem_object *obj)
 
 	/* Attempt to reap some mmap space from dead objects */
 	do {
-		err = i915_gem_wait_for_idle(i915,
-					     I915_WAIT_INTERRUPTIBLE,
-					     MAX_SCHEDULE_TIMEOUT);
+		err = i915_gem_wait_for_idle(i915, MAX_SCHEDULE_TIMEOUT);
 		if (err)
 			break;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 26f325bbfe4d..90b211257f2d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -59,9 +59,7 @@ static bool switch_to_kernel_context_sync(struct intel_gt *gt)
 {
 	bool result = !intel_gt_is_wedged(gt);
 
-	if (i915_gem_wait_for_idle(gt->i915,
-				   I915_WAIT_FOR_IDLE_BOOST,
-				   I915_GEM_IDLE_TIMEOUT) == -ETIME) {
+	if (i915_gem_wait_for_idle(gt->i915, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
 		/* XXX hide warning from gem_eio */
 		if (i915_modparams.reset) {
 			dev_err(gt->i915->drm.dev,
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index f5402aad9b5a..f902aeee1755 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -1137,7 +1137,7 @@ out:
 
 	if ((flags & TEST_IDLE) && ret == 0) {
 		ret = i915_gem_wait_for_idle(ce->engine->i915,
-					     0, MAX_SCHEDULE_TIMEOUT);
+					     MAX_SCHEDULE_TIMEOUT);
 		if (ret)
 			return ret;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index d4cefdd38431..bdb34f03ec47 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -196,8 +196,7 @@ int intel_gt_resume(struct intel_gt *gt)
 
 static void wait_for_idle(struct intel_gt *gt)
 {
-	if (i915_gem_wait_for_idle(gt->i915, 0,
-				   I915_GEM_IDLE_TIMEOUT) == -ETIME) {
+	if (i915_gem_wait_for_idle(gt->i915, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
 		/*
 		 * Forcibly cancel outstanding work and leave
 		 * the gpu quiet.
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 7c4bba21adcd..5888a658e2b7 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3635,9 +3635,7 @@ i915_drop_caches_set(void *data, u64 val)
 		i915_retire_requests(i915);
 
 	if (val & (DROP_IDLE | DROP_ACTIVE)) {
-		ret = i915_gem_wait_for_idle(i915,
-					     I915_WAIT_INTERRUPTIBLE,
-					     MAX_SCHEDULE_TIMEOUT);
+		ret = i915_gem_wait_for_idle(i915, MAX_SCHEDULE_TIMEOUT);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ad31852e4309..44f3463ff9f1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2321,8 +2321,7 @@ void i915_gem_driver_register(struct drm_i915_private *i915);
 void i915_gem_driver_unregister(struct drm_i915_private *i915);
 void i915_gem_driver_remove(struct drm_i915_private *dev_priv);
 void i915_gem_driver_release(struct drm_i915_private *dev_priv);
-int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv,
-			   unsigned int flags, long timeout);
+int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv, long timeout);
 void i915_gem_suspend(struct drm_i915_private *dev_priv);
 void i915_gem_suspend_late(struct drm_i915_private *dev_priv);
 void i915_gem_resume(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 83c2c7bf1e34..12d21e5cf3ed 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -883,61 +883,7 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915)
 	}
 }
 
-static long
-wait_for_timelines(struct intel_gt *gt, unsigned int wait, long timeout)
-{
-	struct intel_gt_timelines *timelines = &gt->timelines;
-	struct intel_timeline *tl;
-	unsigned long flags;
-
-	spin_lock_irqsave(&timelines->lock, flags);
-	list_for_each_entry(tl, &timelines->active_list, link) {
-		struct dma_fence *fence;
-
-		fence = i915_active_fence_get(&tl->last_request);
-		if (!fence)
-			continue;
-
-		spin_unlock_irqrestore(&timelines->lock, flags);
-
-		if (!dma_fence_is_i915(fence)) {
-			timeout = dma_fence_wait_timeout(fence,
-							 flags & I915_WAIT_INTERRUPTIBLE,
-							 timeout);
-		} else {
-			struct i915_request *rq = to_request(fence);
-
-			/*
-			 * "Race-to-idle".
-			 *
-			 * Switching to the kernel context is often used as
-			 * a synchronous step prior to idling, e.g. in suspend
-			 * for flushing all current operations to memory before
-			 * sleeping. These we want to complete as quickly as
-			 * possible to avoid prolonged stalls, so allow the gpu
-			 * to boost to maximum clocks.
-			 */
-			if (flags & I915_WAIT_FOR_IDLE_BOOST)
-				gen6_rps_boost(rq);
-
-			timeout = i915_request_wait(rq, flags, timeout);
-		}
-
-		dma_fence_put(fence);
-		if (timeout < 0)
-			return timeout;
-
-		/* restart after reacquiring the lock */
-		spin_lock_irqsave(&timelines->lock, flags);
-		tl = list_entry(&timelines->active_list, typeof(*tl), link);
-	}
-	spin_unlock_irqrestore(&timelines->lock, flags);
-
-	return timeout;
-}
-
-int i915_gem_wait_for_idle(struct drm_i915_private *i915,
-			   unsigned int flags, long timeout)
+int i915_gem_wait_for_idle(struct drm_i915_private *i915, long timeout)
 {
 	struct intel_gt *gt = &i915->gt;
 
@@ -945,18 +891,13 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915,
 	if (!intel_gt_pm_is_awake(gt))
 		return 0;
 
-	do {
-		timeout = wait_for_timelines(gt, flags, timeout);
-		if (timeout < 0)
-			return timeout;
-
+	while ((timeout = i915_retire_requests_timeout(i915, timeout)) > 0) {
 		cond_resched();
 		if (signal_pending(current))
 			return -EINTR;
+	}
 
-	} while (i915_retire_requests(i915));
-
-	return 0;
+	return timeout;
 }
 
 struct i915_vma *
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 0552bf93eea3..0a412f6d01d7 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -46,9 +46,7 @@ static int ggtt_flush(struct drm_i915_private *i915)
 	 * the hopes that we can then remove contexts and the like only
 	 * bound by their active reference.
 	 */
-	return i915_gem_wait_for_idle(i915,
-				      I915_WAIT_INTERRUPTIBLE,
-				      MAX_SCHEDULE_TIMEOUT);
+	return i915_gem_wait_for_idle(i915, MAX_SCHEDULE_TIMEOUT);
 }
 
 static bool
@@ -126,6 +124,8 @@ i915_gem_evict_something(struct i915_address_space *vm,
 				    min_size, alignment, color,
 				    start, end, mode);
 
+	i915_retire_requests(vm->i915);
+
 search_again:
 	active = NULL;
 	INIT_LIST_HEAD(&eviction_list);
@@ -264,13 +264,13 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 
 	trace_i915_gem_evict_node(vm, target, flags);
 
-	/* Retire before we search the active list. Although we have
+	/*
+	 * Retire before we search the active list. Although we have
 	 * reasonable accuracy in our retirement lists, we may have
 	 * a stray pin (preventing eviction) that can only be resolved by
 	 * retiring.
 	 */
-	if (!(flags & PIN_NONBLOCK))
-		i915_retire_requests(vm->i915);
+	i915_retire_requests(vm->i915);
 
 	if (i915_vm_has_cache_coloring(vm)) {
 		/* Expand search to cover neighbouring guard pages (or lack!) */
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 7462d87f7a48..082fcf9085a6 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2528,7 +2528,9 @@ void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 
 	if (unlikely(ggtt->do_idle_maps)) {
-		if (i915_gem_wait_for_idle(dev_priv, 0, MAX_SCHEDULE_TIMEOUT)) {
+		/* XXX This does not prevent more requests being submitted! */
+		if (i915_retire_requests_timeout(dev_priv,
+						 -MAX_SCHEDULE_TIMEOUT)) {
 			DRM_ERROR("Failed to wait for idle; VT'd may hang.\n");
 			/* Wait a bit, in hopes it avoids the hang */
 			udelay(10);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 4ffe62a42186..52f7c4e5b644 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1508,13 +1508,19 @@ out:
 	return timeout;
 }
 
-bool i915_retire_requests(struct drm_i915_private *i915)
+long i915_retire_requests_timeout(struct drm_i915_private *i915, long timeout)
 {
 	struct intel_gt_timelines *timelines = &i915->gt.timelines;
 	struct intel_timeline *tl, *tn;
+	unsigned long active_count = 0;
 	unsigned long flags;
+	bool interruptible;
 	LIST_HEAD(free);
 
+	interruptible = true;
+	if (timeout < 0)
+		timeout = -timeout, interruptible = false;
+
 	spin_lock_irqsave(&timelines->lock, flags);
 	list_for_each_entry_safe(tl, tn, &timelines->active_list, link) {
 		if (!mutex_trylock(&tl->mutex))
@@ -1525,13 +1531,27 @@ bool i915_retire_requests(struct drm_i915_private *i915)
 		tl->active_count++; /* pin the list element */
 		spin_unlock_irqrestore(&timelines->lock, flags);
 
+		if (timeout > 0) {
+			struct dma_fence *fence;
+
+			fence = i915_active_fence_get(&tl->last_request);
+			if (fence) {
+				timeout = dma_fence_wait_timeout(fence,
+								 interruptible,
+								 timeout);
+				dma_fence_put(fence);
+			}
+		}
+
 		retire_requests(tl);
 
 		spin_lock_irqsave(&timelines->lock, flags);
 
 		/* Resume iteration after dropping lock */
 		list_safe_reset_next(tl, tn, link);
-		if (!--tl->active_count)
+		if (--tl->active_count)
+			active_count += !!rcu_access_pointer(tl->last_request.fence);
+		else
 			list_del(&tl->link);
 
 		mutex_unlock(&tl->mutex);
@@ -1547,7 +1567,7 @@ bool i915_retire_requests(struct drm_i915_private *i915)
 	list_for_each_entry_safe(tl, tn, &free, link)
 		__intel_timeline_free(&tl->kref);
 
-	return !list_empty(&timelines->active_list);
+	return active_count ? timeout : 0;
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 621fb33cda30..256b0715180f 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -310,7 +310,6 @@ long i915_request_wait(struct i915_request *rq,
 #define I915_WAIT_INTERRUPTIBLE	BIT(0)
 #define I915_WAIT_PRIORITY	BIT(1) /* small priority bump for the request */
 #define I915_WAIT_ALL		BIT(2) /* used by i915_gem_object_wait() */
-#define I915_WAIT_FOR_IDLE_BOOST BIT(3)
 
 static inline bool i915_request_signaled(const struct i915_request *rq)
 {
@@ -460,6 +459,10 @@ i915_request_active_timeline(struct i915_request *rq)
 					 lockdep_is_held(&rq->engine->active.lock));
 }
 
-bool i915_retire_requests(struct drm_i915_private *i915);
+long i915_retire_requests_timeout(struct drm_i915_private *i915, long timeout);
+static inline void i915_retire_requests(struct drm_i915_private *i915)
+{
+	i915_retire_requests_timeout(i915, 0);
+}
 
 #endif /* I915_REQUEST_H */
diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
index 2a5fbe46ea9f..ed496bd6d84f 100644
--- a/drivers/gpu/drm/i915/selftests/igt_flush_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
@@ -18,8 +18,7 @@ int igt_flush_test(struct drm_i915_private *i915)
 
 	cond_resched();
 
-	i915_retire_requests(i915);
-	if (i915_gem_wait_for_idle(i915, 0, HZ / 5) == -ETIME) {
+	if (i915_gem_wait_for_idle(i915, HZ / 5) == -ETIME) {
 		pr_err("%pS timed out, cancelling all further testing.\n",
 		       __builtin_return_address(0));
 
@@ -30,7 +29,6 @@ int igt_flush_test(struct drm_i915_private *i915)
 		intel_gt_set_wedged(&i915->gt);
 		ret = -EIO;
 	}
-	i915_retire_requests(i915);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c
index 04a6f88fdf64..eae90f97df6c 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c
@@ -23,9 +23,7 @@ int igt_live_test_begin(struct igt_live_test *t,
 	t->func = func;
 	t->name = name;
 
-	err = i915_gem_wait_for_idle(i915,
-				     I915_WAIT_INTERRUPTIBLE,
-				     MAX_SCHEDULE_TIMEOUT);
+	err = i915_gem_wait_for_idle(i915, MAX_SCHEDULE_TIMEOUT);
 	if (err) {
 		pr_err("%s(%s): failed to idle before, with err=%d!",
 		       func, name, err);
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index a8be5da2b3cf..3b589bbb2c2d 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -44,7 +44,7 @@ void mock_device_flush(struct drm_i915_private *i915)
 	do {
 		for_each_engine(engine, i915, id)
 			mock_engine_flush(engine);
-	} while (i915_retire_requests(i915));
+	} while (i915_retire_requests_timeout(i915, MAX_SCHEDULE_TIMEOUT));
 }
 
 static void mock_device_release(struct drm_device *dev)
-- 
cgit v1.2.3


From 789ed955215d6f925008cb2381aa9f64cd635dd2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:05 +0100
Subject: drm/i915/gem: Retire directly for mmap-offset shrinking

Now that we can retire without taking struct_mutex, we can do so to
handle shrinking the mmap-offset space after an allocation failure.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-11-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_mman.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 418d0d2b5fa9..45bbd22c14f1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -431,19 +431,12 @@ static int create_mmap_offset(struct drm_i915_gem_object *obj)
 		return 0;
 
 	/* Attempt to reap some mmap space from dead objects */
-	do {
-		err = i915_gem_wait_for_idle(i915, MAX_SCHEDULE_TIMEOUT);
-		if (err)
-			break;
+	err = i915_retire_requests_timeout(i915, MAX_SCHEDULE_TIMEOUT);
+	if (err)
+		return err;
 
-		i915_gem_drain_freed_objects(i915);
-		err = drm_gem_create_mmap_offset(&obj->base);
-		if (!err)
-			break;
-
-	} while (flush_delayed_work(&i915->gem.retire_work));
-
-	return err;
+	i915_gem_drain_freed_objects(i915);
+	return drm_gem_create_mmap_offset(&obj->base);
 }
 
 int
-- 
cgit v1.2.3


From 661019754202d610203a9cf09d26fdd8677e41c6 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:06 +0100
Subject: drm/i915: Move request runtime management onto gt

Requests are run from the gt and are tided into the gt runtime power
management, so pull the runtime request management under gt/

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-12-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/Makefile                      |   1 +
 drivers/gpu/drm/i915/gem/i915_gem_mman.c           |   4 +-
 drivers/gpu/drm/i915/gem/i915_gem_pm.c             |  28 +----
 .../gpu/drm/i915/gem/selftests/i915_gem_context.c  |   5 +-
 drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c |   2 +-
 drivers/gpu/drm/i915/gt/intel_gt.c                 |   2 +
 drivers/gpu/drm/i915/gt/intel_gt_pm.c              |   5 +-
 drivers/gpu/drm/i915/gt/intel_gt_requests.c        | 123 +++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_gt_requests.h        |  24 ++++
 drivers/gpu/drm/i915/gt/intel_gt_types.h           |  11 ++
 drivers/gpu/drm/i915/gt/selftest_timeline.c        |   8 +-
 drivers/gpu/drm/i915/i915_debugfs.c                |  17 +--
 drivers/gpu/drm/i915/i915_drv.h                    |  10 --
 drivers/gpu/drm/i915/i915_gem.c                    |  17 ---
 drivers/gpu/drm/i915/i915_gem_evict.c              |  14 +--
 drivers/gpu/drm/i915/i915_gem_gtt.c                |   5 +-
 drivers/gpu/drm/i915/i915_request.c                |  64 +----------
 drivers/gpu/drm/i915/i915_request.h                |   7 +-
 drivers/gpu/drm/i915/selftests/igt_flush_test.c    |   9 +-
 drivers/gpu/drm/i915/selftests/igt_live_test.c     |   5 +-
 drivers/gpu/drm/i915/selftests/mock_gem_device.c   |  10 +-
 21 files changed, 213 insertions(+), 158 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/gt/intel_gt_requests.c
 create mode 100644 drivers/gpu/drm/i915/gt/intel_gt_requests.h

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index b020b024286d..4e23f1a5c39f 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -83,6 +83,7 @@ gt-y += \
 	gt/intel_gt_irq.o \
 	gt/intel_gt_pm.o \
 	gt/intel_gt_pm_irq.o \
+	gt/intel_gt_requests.o \
 	gt/intel_hangcheck.o \
 	gt/intel_lrc.o \
 	gt/intel_rc6.o \
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 45bbd22c14f1..fd4122d8c0a9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -8,6 +8,7 @@
 #include <linux/sizes.h>
 
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_requests.h"
 
 #include "i915_drv.h"
 #include "i915_gem_gtt.h"
@@ -424,6 +425,7 @@ out:
 static int create_mmap_offset(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct intel_gt *gt = &i915->gt;
 	int err;
 
 	err = drm_gem_create_mmap_offset(&obj->base);
@@ -431,7 +433,7 @@ static int create_mmap_offset(struct drm_i915_gem_object *obj)
 		return 0;
 
 	/* Attempt to reap some mmap space from dead objects */
-	err = i915_retire_requests_timeout(i915, MAX_SCHEDULE_TIMEOUT);
+	err = intel_gt_retire_requests_timeout(gt, MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 90b211257f2d..9194d8464bf7 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -7,31 +7,18 @@
 #include "gem/i915_gem_pm.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
+#include "gt/intel_gt_requests.h"
 
 #include "i915_drv.h"
 #include "i915_globals.h"
 
 static void i915_gem_park(struct drm_i915_private *i915)
 {
-	cancel_delayed_work(&i915->gem.retire_work);
-
 	i915_vma_parked(i915);
 
 	i915_globals_park();
 }
 
-static void retire_work_handler(struct work_struct *work)
-{
-	struct drm_i915_private *i915 =
-		container_of(work, typeof(*i915), gem.retire_work.work);
-
-	i915_retire_requests(i915);
-
-	queue_delayed_work(i915->wq,
-			   &i915->gem.retire_work,
-			   round_jiffies_up_relative(HZ));
-}
-
 static int pm_notifier(struct notifier_block *nb,
 		       unsigned long action,
 		       void *data)
@@ -42,9 +29,6 @@ static int pm_notifier(struct notifier_block *nb,
 	switch (action) {
 	case INTEL_GT_UNPARK:
 		i915_globals_unpark();
-		queue_delayed_work(i915->wq,
-				   &i915->gem.retire_work,
-				   round_jiffies_up_relative(HZ));
 		break;
 
 	case INTEL_GT_PARK:
@@ -59,7 +43,7 @@ static bool switch_to_kernel_context_sync(struct intel_gt *gt)
 {
 	bool result = !intel_gt_is_wedged(gt);
 
-	if (i915_gem_wait_for_idle(gt->i915, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
+	if (intel_gt_wait_for_idle(gt, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
 		/* XXX hide warning from gem_eio */
 		if (i915_modparams.reset) {
 			dev_err(gt->i915->drm.dev,
@@ -122,14 +106,12 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	 * state. Fortunately, the kernel_context is disposable and we do
 	 * not rely on its state.
 	 */
-	switch_to_kernel_context_sync(&i915->gt);
+	intel_gt_suspend(&i915->gt);
+	intel_uc_suspend(&i915->gt.uc);
 
 	cancel_delayed_work_sync(&i915->gt.hangcheck.work);
 
 	i915_gem_drain_freed_objects(i915);
-
-	intel_uc_suspend(&i915->gt.uc);
-	intel_gt_suspend(&i915->gt);
 }
 
 static struct drm_i915_gem_object *first_mm_object(struct list_head *list)
@@ -239,8 +221,6 @@ err_wedged:
 
 void i915_gem_init__pm(struct drm_i915_private *i915)
 {
-	INIT_DELAYED_WORK(&i915->gem.retire_work, retire_work_handler);
-
 	i915->gem.pm_notifier.notifier_call = pm_notifier;
 	blocking_notifier_chain_register(&i915->gt.pm_notifications,
 					 &i915->gem.pm_notifier);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index f902aeee1755..2288757808ae 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -8,6 +8,7 @@
 
 #include "gem/i915_gem_pm.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_requests.h"
 #include "gt/intel_reset.h"
 #include "i915_selftest.h"
 
@@ -518,7 +519,7 @@ create_test_object(struct i915_address_space *vm,
 	int err;
 
 	/* Keep in GEM's good graces */
-	i915_retire_requests(vm->i915);
+	intel_gt_retire_requests(vm->gt);
 
 	size = min(vm->total / 2, 1024ull * DW_PER_PAGE * PAGE_SIZE);
 	size = round_down(size, DW_PER_PAGE * PAGE_SIZE);
@@ -1136,7 +1137,7 @@ out:
 		igt_spinner_end(spin);
 
 	if ((flags & TEST_IDLE) && ret == 0) {
-		ret = i915_gem_wait_for_idle(ce->engine->i915,
+		ret = intel_gt_wait_for_idle(ce->engine->gt,
 					     MAX_SCHEDULE_TIMEOUT);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 4ba6ed5c8313..1cd25cfd0246 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -573,7 +573,7 @@ static void disable_retire_worker(struct drm_i915_private *i915)
 {
 	i915_gem_driver_unregister__shrinker(i915);
 	intel_gt_pm_get(&i915->gt);
-	cancel_delayed_work_sync(&i915->gem.retire_work);
+	cancel_delayed_work_sync(&i915->gt.requests.retire_work);
 }
 
 static void restore_retire_worker(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 7205595369be..53220741e49e 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -6,6 +6,7 @@
 #include "i915_drv.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
+#include "intel_gt_requests.h"
 #include "intel_mocs.h"
 #include "intel_rc6.h"
 #include "intel_uncore.h"
@@ -23,6 +24,7 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 
 	intel_gt_init_hangcheck(gt);
 	intel_gt_init_reset(gt);
+	intel_gt_init_requests(gt);
 	intel_gt_pm_init_early(gt);
 	intel_uc_init_early(&gt->uc);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index bdb34f03ec47..d2e80ba64d69 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -10,6 +10,7 @@
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
+#include "intel_gt_requests.h"
 #include "intel_pm.h"
 #include "intel_rc6.h"
 #include "intel_wakeref.h"
@@ -49,6 +50,7 @@ static int __gt_unpark(struct intel_wakeref *wf)
 	i915_pmu_gt_unparked(i915);
 
 	intel_gt_queue_hangcheck(gt);
+	intel_gt_unpark_requests(gt);
 
 	pm_notify(gt, INTEL_GT_UNPARK);
 
@@ -64,6 +66,7 @@ static int __gt_park(struct intel_wakeref *wf)
 	GEM_TRACE("\n");
 
 	pm_notify(gt, INTEL_GT_PARK);
+	intel_gt_park_requests(gt);
 
 	i915_pmu_gt_parked(i915);
 	if (INTEL_GEN(i915) >= 6)
@@ -196,7 +199,7 @@ int intel_gt_resume(struct intel_gt *gt)
 
 static void wait_for_idle(struct intel_gt *gt)
 {
-	if (i915_gem_wait_for_idle(gt->i915, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
+	if (intel_gt_wait_for_idle(gt, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
 		/*
 		 * Forcibly cancel outstanding work and leave
 		 * the gpu quiet.
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
new file mode 100644
index 000000000000..8aed89fd2cdc
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -0,0 +1,123 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "i915_request.h"
+#include "intel_gt.h"
+#include "intel_gt_pm.h"
+#include "intel_gt_requests.h"
+#include "intel_timeline.h"
+
+static void retire_requests(struct intel_timeline *tl)
+{
+	struct i915_request *rq, *rn;
+
+	list_for_each_entry_safe(rq, rn, &tl->requests, link)
+		if (!i915_request_retire(rq))
+			break;
+}
+
+long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
+{
+	struct intel_gt_timelines *timelines = &gt->timelines;
+	struct intel_timeline *tl, *tn;
+	unsigned long active_count = 0;
+	unsigned long flags;
+	bool interruptible;
+	LIST_HEAD(free);
+
+	interruptible = true;
+	if (unlikely(timeout < 0))
+		timeout = -timeout, interruptible = false;
+
+	spin_lock_irqsave(&timelines->lock, flags);
+	list_for_each_entry_safe(tl, tn, &timelines->active_list, link) {
+		if (!mutex_trylock(&tl->mutex))
+			continue;
+
+		intel_timeline_get(tl);
+		GEM_BUG_ON(!tl->active_count);
+		tl->active_count++; /* pin the list element */
+		spin_unlock_irqrestore(&timelines->lock, flags);
+
+		if (timeout > 0) {
+			struct dma_fence *fence;
+
+			fence = i915_active_fence_get(&tl->last_request);
+			if (fence) {
+				timeout = dma_fence_wait_timeout(fence,
+								 true,
+								 timeout);
+				dma_fence_put(fence);
+			}
+		}
+
+		retire_requests(tl);
+
+		spin_lock_irqsave(&timelines->lock, flags);
+
+		/* Resume iteration after dropping lock */
+		list_safe_reset_next(tl, tn, link);
+		if (--tl->active_count)
+			active_count += !!rcu_access_pointer(tl->last_request.fence);
+		else
+			list_del(&tl->link);
+
+		mutex_unlock(&tl->mutex);
+
+		/* Defer the final release to after the spinlock */
+		if (refcount_dec_and_test(&tl->kref.refcount)) {
+			GEM_BUG_ON(tl->active_count);
+			list_add(&tl->link, &free);
+		}
+	}
+	spin_unlock_irqrestore(&timelines->lock, flags);
+
+	list_for_each_entry_safe(tl, tn, &free, link)
+		__intel_timeline_free(&tl->kref);
+
+	return active_count ? timeout : 0;
+}
+
+int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout)
+{
+	/* If the device is asleep, we have no requests outstanding */
+	if (!intel_gt_pm_is_awake(gt))
+		return 0;
+
+	while ((timeout = intel_gt_retire_requests_timeout(gt, timeout)) > 0) {
+		cond_resched();
+		if (signal_pending(current))
+			return -EINTR;
+	}
+
+	return timeout;
+}
+
+static void retire_work_handler(struct work_struct *work)
+{
+	struct intel_gt *gt =
+		container_of(work, typeof(*gt), requests.retire_work.work);
+
+	intel_gt_retire_requests(gt);
+	schedule_delayed_work(&gt->requests.retire_work,
+			      round_jiffies_up_relative(HZ));
+}
+
+void intel_gt_init_requests(struct intel_gt *gt)
+{
+	INIT_DELAYED_WORK(&gt->requests.retire_work, retire_work_handler);
+}
+
+void intel_gt_park_requests(struct intel_gt *gt)
+{
+	cancel_delayed_work(&gt->requests.retire_work);
+}
+
+void intel_gt_unpark_requests(struct intel_gt *gt)
+{
+	schedule_delayed_work(&gt->requests.retire_work,
+			      round_jiffies_up_relative(HZ));
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.h b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
new file mode 100644
index 000000000000..bd31cbce47e0
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
@@ -0,0 +1,24 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_GT_REQUESTS_H
+#define INTEL_GT_REQUESTS_H
+
+struct intel_gt;
+
+long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout);
+static inline void intel_gt_retire_requests(struct intel_gt *gt)
+{
+	intel_gt_retire_requests_timeout(gt, 0);
+}
+
+int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout);
+
+void intel_gt_init_requests(struct intel_gt *gt);
+void intel_gt_park_requests(struct intel_gt *gt);
+void intel_gt_unpark_requests(struct intel_gt *gt);
+
+#endif /* INTEL_GT_REQUESTS_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index 7134f1319bbe..802f516a3430 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -50,6 +50,17 @@ struct intel_gt {
 		struct list_head hwsp_free_list;
 	} timelines;
 
+	struct intel_gt_requests {
+		/**
+		 * We leave the user IRQ off as much as possible,
+		 * but this means that requests will finish and never
+		 * be retired once the system goes idle. Set a timer to
+		 * fire periodically while the ring is running. When it
+		 * fires, go retire requests.
+		 */
+		struct delayed_work retire_work;
+	} requests;
+
 	struct intel_wakeref wakeref;
 	atomic_t user_wakeref;
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index 16abfabf08c7..d6df40cdc8a6 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -8,6 +8,7 @@
 
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
+#include "intel_gt_requests.h"
 
 #include "../selftests/i915_random.h"
 #include "../i915_selftest.h"
@@ -641,6 +642,7 @@ out:
 static int live_hwsp_wrap(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = &i915->gt;
 	struct intel_engine_cs *engine;
 	struct intel_timeline *tl;
 	enum intel_engine_id id;
@@ -651,7 +653,7 @@ static int live_hwsp_wrap(void *arg)
 	 * foreign GPU references.
 	 */
 
-	tl = intel_timeline_create(&i915->gt, NULL);
+	tl = intel_timeline_create(gt, NULL);
 	if (IS_ERR(tl))
 		return PTR_ERR(tl);
 
@@ -662,7 +664,7 @@ static int live_hwsp_wrap(void *arg)
 	if (err)
 		goto out_free;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		const u32 *hwsp_seqno[2];
 		struct i915_request *rq;
 		u32 seqno[2];
@@ -734,7 +736,7 @@ static int live_hwsp_wrap(void *arg)
 			goto out;
 		}
 
-		i915_retire_requests(i915); /* recycle HWSP */
+		intel_gt_retire_requests(gt); /* recycle HWSP */
 	}
 
 out:
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 5888a658e2b7..2afc41e43b6e 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -41,6 +41,7 @@
 
 #include "gem/i915_gem_context.h"
 #include "gt/intel_gt_pm.h"
+#include "gt/intel_gt_requests.h"
 #include "gt/intel_reset.h"
 #include "gt/intel_rc6.h"
 #include "gt/uc/intel_guc_submission.h"
@@ -3621,33 +3622,33 @@ static int
 i915_drop_caches_set(void *data, u64 val)
 {
 	struct drm_i915_private *i915 = data;
+	struct intel_gt *gt = &i915->gt;
 	int ret;
 
 	DRM_DEBUG("Dropping caches: 0x%08llx [0x%08llx]\n",
 		  val, val & DROP_ALL);
 
 	if (val & DROP_RESET_ACTIVE &&
-	    wait_for(intel_engines_are_idle(&i915->gt),
-		     I915_IDLE_ENGINES_TIMEOUT))
-		intel_gt_set_wedged(&i915->gt);
+	    wait_for(intel_engines_are_idle(gt), I915_IDLE_ENGINES_TIMEOUT))
+		intel_gt_set_wedged(gt);
 
 	if (val & DROP_RETIRE)
-		i915_retire_requests(i915);
+		intel_gt_retire_requests(gt);
 
 	if (val & (DROP_IDLE | DROP_ACTIVE)) {
-		ret = i915_gem_wait_for_idle(i915, MAX_SCHEDULE_TIMEOUT);
+		ret = intel_gt_wait_for_idle(gt, MAX_SCHEDULE_TIMEOUT);
 		if (ret)
 			return ret;
 	}
 
 	if (val & DROP_IDLE) {
-		ret = intel_gt_pm_wait_for_idle(&i915->gt);
+		ret = intel_gt_pm_wait_for_idle(gt);
 		if (ret)
 			return ret;
 	}
 
-	if (val & DROP_RESET_ACTIVE && intel_gt_terminally_wedged(&i915->gt))
-		intel_gt_handle_error(&i915->gt, ALL_ENGINES, 0, NULL);
+	if (val & DROP_RESET_ACTIVE && intel_gt_terminally_wedged(gt))
+		intel_gt_handle_error(gt, ALL_ENGINES, 0, NULL);
 
 	fs_reclaim_acquire(GFP_KERNEL);
 	if (val & DROP_BOUND)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 44f3463ff9f1..cb63b2bd0ce8 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1710,15 +1710,6 @@ struct drm_i915_private {
 
 	struct {
 		struct notifier_block pm_notifier;
-
-		/**
-		 * We leave the user IRQ off as much as possible,
-		 * but this means that requests will finish and never
-		 * be retired once the system goes idle. Set a timer to
-		 * fire periodically while the ring is running. When it
-		 * fires, go retire requests.
-		 */
-		struct delayed_work retire_work;
 	} gem;
 
 	/* For i945gm vblank irq vs. C3 workaround */
@@ -2321,7 +2312,6 @@ void i915_gem_driver_register(struct drm_i915_private *i915);
 void i915_gem_driver_unregister(struct drm_i915_private *i915);
 void i915_gem_driver_remove(struct drm_i915_private *dev_priv);
 void i915_gem_driver_release(struct drm_i915_private *dev_priv);
-int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv, long timeout);
 void i915_gem_suspend(struct drm_i915_private *dev_priv);
 void i915_gem_suspend_late(struct drm_i915_private *dev_priv);
 void i915_gem_resume(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 12d21e5cf3ed..a1077919b16a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -883,23 +883,6 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915)
 	}
 }
 
-int i915_gem_wait_for_idle(struct drm_i915_private *i915, long timeout)
-{
-	struct intel_gt *gt = &i915->gt;
-
-	/* If the device is asleep, we have no requests outstanding */
-	if (!intel_gt_pm_is_awake(gt))
-		return 0;
-
-	while ((timeout = i915_retire_requests_timeout(i915, timeout)) > 0) {
-		cond_resched();
-		if (signal_pending(current))
-			return -EINTR;
-	}
-
-	return timeout;
-}
-
 struct i915_vma *
 i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			 const struct i915_ggtt_view *view,
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 0a412f6d01d7..7e62c310290f 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -29,6 +29,7 @@
 #include <drm/i915_drm.h>
 
 #include "gem/i915_gem_context.h"
+#include "gt/intel_gt_requests.h"
 
 #include "i915_drv.h"
 #include "i915_trace.h"
@@ -37,7 +38,7 @@ I915_SELFTEST_DECLARE(static struct igt_evict_ctl {
 	bool fail_if_busy:1;
 } igt_evict_ctl;)
 
-static int ggtt_flush(struct drm_i915_private *i915)
+static int ggtt_flush(struct intel_gt *gt)
 {
 	/*
 	 * Not everything in the GGTT is tracked via vma (otherwise we
@@ -46,7 +47,7 @@ static int ggtt_flush(struct drm_i915_private *i915)
 	 * the hopes that we can then remove contexts and the like only
 	 * bound by their active reference.
 	 */
-	return i915_gem_wait_for_idle(i915, MAX_SCHEDULE_TIMEOUT);
+	return intel_gt_wait_for_idle(gt, MAX_SCHEDULE_TIMEOUT);
 }
 
 static bool
@@ -92,7 +93,6 @@ i915_gem_evict_something(struct i915_address_space *vm,
 			 u64 start, u64 end,
 			 unsigned flags)
 {
-	struct drm_i915_private *dev_priv = vm->i915;
 	struct drm_mm_scan scan;
 	struct list_head eviction_list;
 	struct i915_vma *vma, *next;
@@ -124,7 +124,7 @@ i915_gem_evict_something(struct i915_address_space *vm,
 				    min_size, alignment, color,
 				    start, end, mode);
 
-	i915_retire_requests(vm->i915);
+	intel_gt_retire_requests(vm->gt);
 
 search_again:
 	active = NULL;
@@ -197,7 +197,7 @@ search_again:
 	if (I915_SELFTEST_ONLY(igt_evict_ctl.fail_if_busy))
 		return -EBUSY;
 
-	ret = ggtt_flush(dev_priv);
+	ret = ggtt_flush(vm->gt);
 	if (ret)
 		return ret;
 
@@ -270,7 +270,7 @@ int i915_gem_evict_for_node(struct i915_address_space *vm,
 	 * a stray pin (preventing eviction) that can only be resolved by
 	 * retiring.
 	 */
-	i915_retire_requests(vm->i915);
+	intel_gt_retire_requests(vm->gt);
 
 	if (i915_vm_has_cache_coloring(vm)) {
 		/* Expand search to cover neighbouring guard pages (or lack!) */
@@ -372,7 +372,7 @@ int i915_gem_evict_vm(struct i915_address_space *vm)
 	 * switch otherwise is ineffective.
 	 */
 	if (i915_is_ggtt(vm)) {
-		ret = ggtt_flush(vm->i915);
+		ret = ggtt_flush(vm->gt);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 082fcf9085a6..1d26634ca597 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -38,6 +38,7 @@
 
 #include "display/intel_frontbuffer.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_requests.h"
 
 #include "i915_drv.h"
 #include "i915_scatterlist.h"
@@ -2529,8 +2530,8 @@ void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
 
 	if (unlikely(ggtt->do_idle_maps)) {
 		/* XXX This does not prevent more requests being submitted! */
-		if (i915_retire_requests_timeout(dev_priv,
-						 -MAX_SCHEDULE_TIMEOUT)) {
+		if (intel_gt_retire_requests_timeout(ggtt->vm.gt,
+						     -MAX_SCHEDULE_TIMEOUT)) {
 			DRM_ERROR("Failed to wait for idle; VT'd may hang.\n");
 			/* Wait a bit, in hopes it avoids the hang */
 			udelay(10);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 52f7c4e5b644..437f9fc6282e 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -216,7 +216,7 @@ static void remove_from_engine(struct i915_request *rq)
 	spin_unlock(&locked->active.lock);
 }
 
-static bool i915_request_retire(struct i915_request *rq)
+bool i915_request_retire(struct i915_request *rq)
 {
 	if (!i915_request_completed(rq))
 		return false;
@@ -1508,68 +1508,6 @@ out:
 	return timeout;
 }
 
-long i915_retire_requests_timeout(struct drm_i915_private *i915, long timeout)
-{
-	struct intel_gt_timelines *timelines = &i915->gt.timelines;
-	struct intel_timeline *tl, *tn;
-	unsigned long active_count = 0;
-	unsigned long flags;
-	bool interruptible;
-	LIST_HEAD(free);
-
-	interruptible = true;
-	if (timeout < 0)
-		timeout = -timeout, interruptible = false;
-
-	spin_lock_irqsave(&timelines->lock, flags);
-	list_for_each_entry_safe(tl, tn, &timelines->active_list, link) {
-		if (!mutex_trylock(&tl->mutex))
-			continue;
-
-		intel_timeline_get(tl);
-		GEM_BUG_ON(!tl->active_count);
-		tl->active_count++; /* pin the list element */
-		spin_unlock_irqrestore(&timelines->lock, flags);
-
-		if (timeout > 0) {
-			struct dma_fence *fence;
-
-			fence = i915_active_fence_get(&tl->last_request);
-			if (fence) {
-				timeout = dma_fence_wait_timeout(fence,
-								 interruptible,
-								 timeout);
-				dma_fence_put(fence);
-			}
-		}
-
-		retire_requests(tl);
-
-		spin_lock_irqsave(&timelines->lock, flags);
-
-		/* Resume iteration after dropping lock */
-		list_safe_reset_next(tl, tn, link);
-		if (--tl->active_count)
-			active_count += !!rcu_access_pointer(tl->last_request.fence);
-		else
-			list_del(&tl->link);
-
-		mutex_unlock(&tl->mutex);
-
-		/* Defer the final release to after the spinlock */
-		if (refcount_dec_and_test(&tl->kref.refcount)) {
-			GEM_BUG_ON(tl->active_count);
-			list_add(&tl->link, &free);
-		}
-	}
-	spin_unlock_irqrestore(&timelines->lock, flags);
-
-	list_for_each_entry_safe(tl, tn, &free, link)
-		__intel_timeline_free(&tl->kref);
-
-	return active_count ? timeout : 0;
-}
-
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_request.c"
 #include "selftests/i915_request.c"
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 256b0715180f..6a95242b280d 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -250,6 +250,7 @@ struct i915_request *__i915_request_commit(struct i915_request *request);
 void __i915_request_queue(struct i915_request *rq,
 			  const struct i915_sched_attr *attr);
 
+bool i915_request_retire(struct i915_request *rq);
 void i915_request_retire_upto(struct i915_request *rq);
 
 static inline struct i915_request *
@@ -459,10 +460,4 @@ i915_request_active_timeline(struct i915_request *rq)
 					 lockdep_is_held(&rq->engine->active.lock));
 }
 
-long i915_retire_requests_timeout(struct drm_i915_private *i915, long timeout);
-static inline void i915_retire_requests(struct drm_i915_private *i915)
-{
-	i915_retire_requests_timeout(i915, 0);
-}
-
 #endif /* I915_REQUEST_H */
diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
index ed496bd6d84f..7b0939e3f007 100644
--- a/drivers/gpu/drm/i915/selftests/igt_flush_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
@@ -4,8 +4,8 @@
  * Copyright © 2018 Intel Corporation
  */
 
-#include "gem/i915_gem_context.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_requests.h"
 
 #include "i915_drv.h"
 #include "i915_selftest.h"
@@ -14,11 +14,12 @@
 
 int igt_flush_test(struct drm_i915_private *i915)
 {
-	int ret = intel_gt_is_wedged(&i915->gt) ? -EIO : 0;
+	struct intel_gt *gt = &i915->gt;
+	int ret = intel_gt_is_wedged(gt) ? -EIO : 0;
 
 	cond_resched();
 
-	if (i915_gem_wait_for_idle(i915, HZ / 5) == -ETIME) {
+	if (intel_gt_wait_for_idle(gt, HZ / 5) == -ETIME) {
 		pr_err("%pS timed out, cancelling all further testing.\n",
 		       __builtin_return_address(0));
 
@@ -26,7 +27,7 @@ int igt_flush_test(struct drm_i915_private *i915)
 			  __builtin_return_address(0));
 		GEM_TRACE_DUMP();
 
-		intel_gt_set_wedged(&i915->gt);
+		intel_gt_set_wedged(gt);
 		ret = -EIO;
 	}
 
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c
index eae90f97df6c..810b60100c2c 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c
@@ -4,7 +4,8 @@
  * Copyright © 2018 Intel Corporation
  */
 
-#include "../i915_drv.h"
+#include "i915_drv.h"
+#include "gt/intel_gt_requests.h"
 
 #include "../i915_selftest.h"
 #include "igt_flush_test.h"
@@ -23,7 +24,7 @@ int igt_live_test_begin(struct igt_live_test *t,
 	t->func = func;
 	t->name = name;
 
-	err = i915_gem_wait_for_idle(i915, MAX_SCHEDULE_TIMEOUT);
+	err = intel_gt_wait_for_idle(&i915->gt, MAX_SCHEDULE_TIMEOUT);
 	if (err) {
 		pr_err("%s(%s): failed to idle before, with err=%d!",
 		       func, name, err);
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 3b589bbb2c2d..4e6cde0d4859 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -26,6 +26,7 @@
 #include <linux/pm_runtime.h>
 
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_requests.h"
 #include "gt/mock_engine.h"
 
 #include "mock_request.h"
@@ -44,7 +45,8 @@ void mock_device_flush(struct drm_i915_private *i915)
 	do {
 		for_each_engine(engine, i915, id)
 			mock_engine_flush(engine);
-	} while (i915_retire_requests_timeout(i915, MAX_SCHEDULE_TIMEOUT));
+	} while (intel_gt_retire_requests_timeout(&i915->gt,
+						  MAX_SCHEDULE_TIMEOUT));
 }
 
 static void mock_device_release(struct drm_device *dev)
@@ -98,10 +100,6 @@ static void release_dev(struct device *dev)
 	kfree(pdev);
 }
 
-static void mock_retire_work_handler(struct work_struct *work)
-{
-}
-
 static int pm_domain_resume(struct device *dev)
 {
 	return pm_generic_runtime_resume(dev);
@@ -181,8 +179,6 @@ struct drm_i915_private *mock_gem_device(void)
 
 	mock_init_contexts(i915);
 
-	INIT_DELAYED_WORK(&i915->gem.retire_work, mock_retire_work_handler);
-
 	intel_timelines_init(i915);
 
 	mutex_lock(&i915->drm.struct_mutex);
-- 
cgit v1.2.3


From a2b4dead98ef1241498ff8769c85154995938087 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:07 +0100
Subject: drm/i915: Move global activity tracking from GEM to GT

As our global unpark/park keep track of the number of active users, we
can simply move the accounting from the GEM layer to the base GT layer.
It was placed originally inside GEM to benefit from the 100ms extra
delay on idleness, but that has been eliminated and now there is no
substantive difference between the layers. In moving it, we move another
piece of the puzzle out from underneath struct_mutex.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-13-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_pm.c | 11 +----------
 drivers/gpu/drm/i915/gt/intel_gt_pm.c  |  5 +++++
 2 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 9194d8464bf7..7c316d4633db 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -10,14 +10,6 @@
 #include "gt/intel_gt_requests.h"
 
 #include "i915_drv.h"
-#include "i915_globals.h"
-
-static void i915_gem_park(struct drm_i915_private *i915)
-{
-	i915_vma_parked(i915);
-
-	i915_globals_park();
-}
 
 static int pm_notifier(struct notifier_block *nb,
 		       unsigned long action,
@@ -28,11 +20,10 @@ static int pm_notifier(struct notifier_block *nb,
 
 	switch (action) {
 	case INTEL_GT_UNPARK:
-		i915_globals_unpark();
 		break;
 
 	case INTEL_GT_PARK:
-		i915_gem_park(i915);
+		i915_vma_parked(i915);
 		break;
 	}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index d2e80ba64d69..b52e2ba3d092 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -5,6 +5,7 @@
  */
 
 #include "i915_drv.h"
+#include "i915_globals.h"
 #include "i915_params.h"
 #include "intel_context.h"
 #include "intel_engine_pm.h"
@@ -27,6 +28,8 @@ static int __gt_unpark(struct intel_wakeref *wf)
 
 	GEM_TRACE("\n");
 
+	i915_globals_unpark();
+
 	/*
 	 * It seems that the DMC likes to transition between the DC states a lot
 	 * when there are no connected displays (no active power domains) during
@@ -78,6 +81,8 @@ static int __gt_park(struct intel_wakeref *wf)
 	GEM_BUG_ON(!wakeref);
 	intel_display_power_put(i915, POWER_DOMAIN_GT_IRQ, wakeref);
 
+	i915_globals_park();
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 2935ed5339c495066d901b97de384d86c55a3f6d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:08 +0100
Subject: drm/i915: Remove logical HW ID

With the introduction of ctx->engines[] we allow multiple logical
contexts to be used on the same engine (e.g. with virtual engines).
According to bspec, aach logical context requires a unique tag in order
for context-switching to occur correctly between them. [Simple
experiments show that it is not so easy to trick the HW into performing
a lite-restore with matching logical IDs, though my memory from early
Broadwell experiments do suggest that it should be generating
lite-restores.]

We only need to keep a unique tag for the active lifetime of the
context, and for as long as we need to identify that context. The HW
uses the tag to determine if it should use a lite-restore (why not the
LRCA?) and passes the tag back for various status identifies. The only
status we need to track is for OA, so when using perf, we assign the
specific context a unique tag.

v2: Calculate required number of tags to fill ELSP.

Fixes: 976b55f0e1db ("drm/i915: Allow a context to define its set of engines")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111895
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-14-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c        | 153 ---------------------
 drivers/gpu/drm/i915/gem/i915_gem_context.h        |  15 --
 drivers/gpu/drm/i915/gem/i915_gem_context_types.h  |  18 ---
 .../gpu/drm/i915/gem/selftests/i915_gem_context.c  |  13 +-
 drivers/gpu/drm/i915/gem/selftests/mock_context.c  |   8 --
 drivers/gpu/drm/i915/gt/intel_context_types.h      |   1 +
 drivers/gpu/drm/i915/gt/intel_engine_types.h       |   4 +-
 drivers/gpu/drm/i915/gt/intel_lrc.c                |  32 ++---
 drivers/gpu/drm/i915/gt/intel_lrc.h                |   6 +
 drivers/gpu/drm/i915/gvt/kvmgt.c                   |  17 ---
 drivers/gpu/drm/i915/i915_debugfs.c                |   3 -
 drivers/gpu/drm/i915/i915_drv.h                    |  12 --
 drivers/gpu/drm/i915/i915_gpu_error.c              |   7 +-
 drivers/gpu/drm/i915/i915_gpu_error.h              |   1 -
 drivers/gpu/drm/i915/i915_perf.c                   |  25 ++--
 drivers/gpu/drm/i915/i915_trace.h                  |  38 ++---
 drivers/gpu/drm/i915/selftests/i915_gem_evict.c    |   4 +-
 drivers/gpu/drm/i915/selftests/i915_vma.c          |   2 +-
 18 files changed, 57 insertions(+), 302 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 0ab416887fc2..cd4f327b23bd 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -167,97 +167,6 @@ lookup_user_engine(struct i915_gem_context *ctx,
 	return i915_gem_context_get_engine(ctx, idx);
 }
 
-static inline int new_hw_id(struct drm_i915_private *i915, gfp_t gfp)
-{
-	unsigned int max;
-
-	lockdep_assert_held(&i915->contexts.mutex);
-
-	if (INTEL_GEN(i915) >= 12)
-		max = GEN12_MAX_CONTEXT_HW_ID;
-	else if (INTEL_GEN(i915) >= 11)
-		max = GEN11_MAX_CONTEXT_HW_ID;
-	else if (USES_GUC_SUBMISSION(i915))
-		/*
-		 * When using GuC in proxy submission, GuC consumes the
-		 * highest bit in the context id to indicate proxy submission.
-		 */
-		max = MAX_GUC_CONTEXT_HW_ID;
-	else
-		max = MAX_CONTEXT_HW_ID;
-
-	return ida_simple_get(&i915->contexts.hw_ida, 0, max, gfp);
-}
-
-static int steal_hw_id(struct drm_i915_private *i915)
-{
-	struct i915_gem_context *ctx, *cn;
-	LIST_HEAD(pinned);
-	int id = -ENOSPC;
-
-	lockdep_assert_held(&i915->contexts.mutex);
-
-	list_for_each_entry_safe(ctx, cn,
-				 &i915->contexts.hw_id_list, hw_id_link) {
-		if (atomic_read(&ctx->hw_id_pin_count)) {
-			list_move_tail(&ctx->hw_id_link, &pinned);
-			continue;
-		}
-
-		GEM_BUG_ON(!ctx->hw_id); /* perma-pinned kernel context */
-		list_del_init(&ctx->hw_id_link);
-		id = ctx->hw_id;
-		break;
-	}
-
-	/*
-	 * Remember how far we got up on the last repossesion scan, so the
-	 * list is kept in a "least recently scanned" order.
-	 */
-	list_splice_tail(&pinned, &i915->contexts.hw_id_list);
-	return id;
-}
-
-static int assign_hw_id(struct drm_i915_private *i915, unsigned int *out)
-{
-	int ret;
-
-	lockdep_assert_held(&i915->contexts.mutex);
-
-	/*
-	 * We prefer to steal/stall ourselves and our users over that of the
-	 * entire system. That may be a little unfair to our users, and
-	 * even hurt high priority clients. The choice is whether to oomkill
-	 * something else, or steal a context id.
-	 */
-	ret = new_hw_id(i915, GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
-	if (unlikely(ret < 0)) {
-		ret = steal_hw_id(i915);
-		if (ret < 0) /* once again for the correct errno code */
-			ret = new_hw_id(i915, GFP_KERNEL);
-		if (ret < 0)
-			return ret;
-	}
-
-	*out = ret;
-	return 0;
-}
-
-static void release_hw_id(struct i915_gem_context *ctx)
-{
-	struct drm_i915_private *i915 = ctx->i915;
-
-	if (list_empty(&ctx->hw_id_link))
-		return;
-
-	mutex_lock(&i915->contexts.mutex);
-	if (!list_empty(&ctx->hw_id_link)) {
-		ida_simple_remove(&i915->contexts.hw_ida, ctx->hw_id);
-		list_del_init(&ctx->hw_id_link);
-	}
-	mutex_unlock(&i915->contexts.mutex);
-}
-
 static void __free_engines(struct i915_gem_engines *e, unsigned int count)
 {
 	while (count--) {
@@ -312,8 +221,6 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
 	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
 	GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
 
-	release_hw_id(ctx);
-
 	free_engines(rcu_access_pointer(ctx->engines));
 	mutex_destroy(&ctx->engines_mutex);
 
@@ -386,12 +293,6 @@ static void context_close(struct i915_gem_context *ctx)
 
 	ctx->file_priv = ERR_PTR(-EBADF);
 
-	/*
-	 * This context will never again be assinged to HW, so we can
-	 * reuse its ID for the next context.
-	 */
-	release_hw_id(ctx);
-
 	/*
 	 * The LUT uses the VMA as a backpointer to unref the object,
 	 * so we need to clear the LUT before we close all the VMA (inside
@@ -430,7 +331,6 @@ __create_context(struct drm_i915_private *i915)
 	RCU_INIT_POINTER(ctx->engines, e);
 
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
-	INIT_LIST_HEAD(&ctx->hw_id_link);
 
 	/* NB: Mark all slices as needing a remap so that when the context first
 	 * loads it will restore whatever remap state already exists. If there
@@ -584,18 +484,11 @@ struct i915_gem_context *
 i915_gem_context_create_kernel(struct drm_i915_private *i915, int prio)
 {
 	struct i915_gem_context *ctx;
-	int err;
 
 	ctx = i915_gem_create_context(i915, 0);
 	if (IS_ERR(ctx))
 		return ctx;
 
-	err = i915_gem_context_pin_hw_id(ctx);
-	if (err) {
-		destroy_kernel_context(&ctx);
-		return ERR_PTR(err);
-	}
-
 	i915_gem_context_clear_bannable(ctx);
 	ctx->sched.priority = I915_USER_PRIORITY(prio);
 
@@ -609,12 +502,6 @@ static void init_contexts(struct drm_i915_private *i915)
 	mutex_init(&i915->contexts.mutex);
 	INIT_LIST_HEAD(&i915->contexts.list);
 
-	/* Using the simple ida interface, the max is limited by sizeof(int) */
-	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > INT_MAX);
-	BUILD_BUG_ON(GEN11_MAX_CONTEXT_HW_ID > INT_MAX);
-	ida_init(&i915->contexts.hw_ida);
-	INIT_LIST_HEAD(&i915->contexts.hw_id_list);
-
 	INIT_WORK(&i915->contexts.free_work, contexts_free_worker);
 	init_llist_head(&i915->contexts.free_list);
 }
@@ -634,15 +521,6 @@ int i915_gem_contexts_init(struct drm_i915_private *dev_priv)
 		DRM_ERROR("Failed to create default global context\n");
 		return PTR_ERR(ctx);
 	}
-	/*
-	 * For easy recognisablity, we want the kernel context to be 0 and then
-	 * all user contexts will have non-zero hw_id. Kernel contexts are
-	 * permanently pinned, so that we never suffer a stall and can
-	 * use them from any allocation context (e.g. for evicting other
-	 * contexts and from inside the shrinker).
-	 */
-	GEM_BUG_ON(ctx->hw_id);
-	GEM_BUG_ON(!atomic_read(&ctx->hw_id_pin_count));
 	dev_priv->kernel_context = ctx;
 
 	DRM_DEBUG_DRIVER("%s context support initialized\n",
@@ -656,10 +534,6 @@ void i915_gem_contexts_fini(struct drm_i915_private *i915)
 	lockdep_assert_held(&i915->drm.struct_mutex);
 
 	destroy_kernel_context(&i915->kernel_context);
-
-	/* Must free all deferred contexts (via flush_workqueue) first */
-	GEM_BUG_ON(!list_empty(&i915->contexts.hw_id_list));
-	ida_destroy(&i915->contexts.hw_ida);
 }
 
 static int context_idr_cleanup(int id, void *p, void *data)
@@ -2316,33 +2190,6 @@ out:
 	return ret;
 }
 
-int __i915_gem_context_pin_hw_id(struct i915_gem_context *ctx)
-{
-	struct drm_i915_private *i915 = ctx->i915;
-	int err = 0;
-
-	mutex_lock(&i915->contexts.mutex);
-
-	GEM_BUG_ON(i915_gem_context_is_closed(ctx));
-
-	if (list_empty(&ctx->hw_id_link)) {
-		GEM_BUG_ON(atomic_read(&ctx->hw_id_pin_count));
-
-		err = assign_hw_id(i915, &ctx->hw_id);
-		if (err)
-			goto out_unlock;
-
-		list_add_tail(&ctx->hw_id_link, &i915->contexts.hw_id_list);
-	}
-
-	GEM_BUG_ON(atomic_read(&ctx->hw_id_pin_count) == ~0u);
-	atomic_inc(&ctx->hw_id_pin_count);
-
-out_unlock:
-	mutex_unlock(&i915->contexts.mutex);
-	return err;
-}
-
 /* GEM context-engines iterator: for_each_gem_engine() */
 struct intel_context *
 i915_gem_engines_iter_next(struct i915_gem_engines_iter *it)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h
index 176978608b6f..50bc27d30c03 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h
@@ -112,21 +112,6 @@ i915_gem_context_clear_user_engines(struct i915_gem_context *ctx)
 	clear_bit(CONTEXT_USER_ENGINES, &ctx->flags);
 }
 
-int __i915_gem_context_pin_hw_id(struct i915_gem_context *ctx);
-static inline int i915_gem_context_pin_hw_id(struct i915_gem_context *ctx)
-{
-	if (atomic_inc_not_zero(&ctx->hw_id_pin_count))
-		return 0;
-
-	return __i915_gem_context_pin_hw_id(ctx);
-}
-
-static inline void i915_gem_context_unpin_hw_id(struct i915_gem_context *ctx)
-{
-	GEM_BUG_ON(atomic_read(&ctx->hw_id_pin_count) == 0u);
-	atomic_dec(&ctx->hw_id_pin_count);
-}
-
 static inline bool i915_gem_context_is_kernel(struct i915_gem_context *ctx)
 {
 	return !ctx->file_priv;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index 260d59cc3de8..87be27877e22 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -147,24 +147,6 @@ struct i915_gem_context {
 #define CONTEXT_FORCE_SINGLE_SUBMISSION	2
 #define CONTEXT_USER_ENGINES		3
 
-	/**
-	 * @hw_id: - unique identifier for the context
-	 *
-	 * The hardware needs to uniquely identify the context for a few
-	 * functions like fault reporting, PASID, scheduling. The
-	 * &drm_i915_private.context_hw_ida is used to assign a unqiue
-	 * id for the lifetime of the context.
-	 *
-	 * @hw_id_pin_count: - number of times this context had been pinned
-	 * for use (should be, at most, once per engine).
-	 *
-	 * @hw_id_link: - all contexts with an assigned id are tracked
-	 * for possible repossession.
-	 */
-	unsigned int hw_id;
-	atomic_t hw_id_pin_count;
-	struct list_head hw_id_link;
-
 	struct mutex mutex;
 
 	struct i915_sched_attr sched;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 2288757808ae..2fb31ada2fa7 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -660,9 +660,9 @@ static int igt_ctx_exec(void *arg)
 
 			err = gpu_fill(ce, obj, dw);
 			if (err) {
-				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
+				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
-				       engine->name, ctx->hw_id,
+				       engine->name,
 				       yesno(!!ctx->vm), err);
 				intel_context_put(ce);
 				kernel_context_close(ctx);
@@ -798,9 +798,9 @@ static int igt_shared_ctx_exec(void *arg)
 
 			err = gpu_fill(ce, obj, dw);
 			if (err) {
-				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
+				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
-				       engine->name, ctx->hw_id,
+				       engine->name,
 				       yesno(!!ctx->vm), err);
 				intel_context_put(ce);
 				kernel_context_close(ctx);
@@ -1382,10 +1382,9 @@ static int igt_ctx_readonly(void *arg)
 
 			err = gpu_fill(ce, obj, dw);
 			if (err) {
-				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
+				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
-				       ce->engine->name, ctx->hw_id,
-				       yesno(!!ctx->vm), err);
+				       ce->engine->name, yesno(!!ctx->vm), err);
 				i915_gem_context_unlock_engines(ctx);
 				goto out_unlock;
 			}
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
index be8974ccff24..0104f16b1327 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
@@ -13,7 +13,6 @@ mock_context(struct drm_i915_private *i915,
 {
 	struct i915_gem_context *ctx;
 	struct i915_gem_engines *e;
-	int ret;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
@@ -30,13 +29,8 @@ mock_context(struct drm_i915_private *i915,
 	RCU_INIT_POINTER(ctx->engines, e);
 
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
-	INIT_LIST_HEAD(&ctx->hw_id_link);
 	mutex_init(&ctx->mutex);
 
-	ret = i915_gem_context_pin_hw_id(ctx);
-	if (ret < 0)
-		goto err_engines;
-
 	if (name) {
 		struct i915_ppgtt *ppgtt;
 
@@ -54,8 +48,6 @@ mock_context(struct drm_i915_private *i915,
 
 	return ctx;
 
-err_engines:
-	free_engines(rcu_access_pointer(ctx->engines));
 err_free:
 	kfree(ctx);
 	return NULL;
diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
index bf9cedfccbf0..6959b05ae5f8 100644
--- a/drivers/gpu/drm/i915/gt/intel_context_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
@@ -58,6 +58,7 @@ struct intel_context {
 
 	u32 *lrc_reg_state;
 	u64 lrc_desc;
+	u32 tag; /* cookie passed to HW to track this context on submission */
 
 	unsigned int active_count; /* protected by timeline->mutex */
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 943f0663837e..6199064f332b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -303,10 +303,12 @@ struct intel_engine_cs {
 	u8 uabi_class;
 	u8 uabi_instance;
 
+	u32 uabi_capabilities;
 	u32 context_size;
 	u32 mmio_base;
 
-	u32 uabi_capabilities;
+	unsigned int context_tag;
+#define NUM_CONTEXT_TAG roundup_pow_of_two(2 * EXECLIST_MAX_PORTS)
 
 	struct rb_node uabi_node;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 3cfea1758fd2..468438fb47af 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -440,12 +440,8 @@ assert_priority_queue(const struct i915_request *prev,
 static u64
 lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 {
-	struct i915_gem_context *ctx = ce->gem_context;
 	u64 desc;
 
-	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > (BIT(GEN8_CTX_ID_WIDTH)));
-	BUILD_BUG_ON(GEN11_MAX_CONTEXT_HW_ID > (BIT(GEN11_SW_CTX_ID_WIDTH)));
-
 	desc = INTEL_LEGACY_32B_CONTEXT;
 	if (i915_vm_is_4lvl(ce->vm))
 		desc = INTEL_LEGACY_64B_CONTEXT;
@@ -463,20 +459,11 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 	 * anything below.
 	 */
 	if (INTEL_GEN(engine->i915) >= 11) {
-		GEM_BUG_ON(ctx->hw_id >= BIT(GEN11_SW_CTX_ID_WIDTH));
-		desc |= (u64)ctx->hw_id << GEN11_SW_CTX_ID_SHIFT;
-								/* bits 37-47 */
-
 		desc |= (u64)engine->instance << GEN11_ENGINE_INSTANCE_SHIFT;
 								/* bits 48-53 */
 
-		/* TODO: decide what to do with SW counter (bits 55-60) */
-
 		desc |= (u64)engine->class << GEN11_ENGINE_CLASS_SHIFT;
 								/* bits 61-63 */
-	} else {
-		GEM_BUG_ON(ctx->hw_id >= BIT(GEN8_CTX_ID_WIDTH));
-		desc |= (u64)ctx->hw_id << GEN8_CTX_ID_SHIFT;	/* bits 32-52 */
 	}
 
 	return desc;
@@ -985,6 +972,18 @@ __execlists_schedule_in(struct i915_request *rq)
 
 	intel_context_get(ce);
 
+	if (ce->tag) {
+		/* Use a fixed tag for OA and friends */
+		ce->lrc_desc |= (u64)ce->tag << 32;
+	} else {
+		/* We don't need a strict matching tag, just different values */
+		ce->lrc_desc &= ~GENMASK_ULL(47, 37);
+		ce->lrc_desc |=
+			(u64)(engine->context_tag++ % NUM_CONTEXT_TAG) <<
+			GEN11_SW_CTX_ID_SHIFT;
+		BUILD_BUG_ON(NUM_CONTEXT_TAG > GEN12_MAX_CONTEXT_HW_ID);
+	}
+
 	intel_gt_pm_get(engine->gt);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
 	intel_engine_context_in(engine);
@@ -2114,7 +2113,6 @@ static void execlists_context_unpin(struct intel_context *ce)
 	check_redzone((void *)ce->lrc_reg_state - LRC_STATE_PN * PAGE_SIZE,
 		      ce->engine);
 
-	i915_gem_context_unpin_hw_id(ce->gem_context);
 	i915_gem_object_unpin_map(ce->state->obj);
 	intel_ring_reset(ce->ring, ce->ring->tail);
 }
@@ -2164,18 +2162,12 @@ __execlists_context_pin(struct intel_context *ce,
 		goto unpin_active;
 	}
 
-	ret = i915_gem_context_pin_hw_id(ce->gem_context);
-	if (ret)
-		goto unpin_map;
-
 	ce->lrc_desc = lrc_descriptor(ce, engine);
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	__execlists_update_reg_state(ce, engine);
 
 	return 0;
 
-unpin_map:
-	i915_gem_object_unpin_map(ce->state->obj);
 unpin_active:
 	intel_context_active_release(ce);
 err:
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index 66ac616361c1..99dc576a4e25 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -66,6 +66,12 @@ struct intel_engine_cs;
 #define GEN11_CSB_READ_PTR_MASK (GEN11_CSB_PTR_MASK << 8)
 #define GEN11_CSB_WRITE_PTR_MASK (GEN11_CSB_PTR_MASK << 0)
 
+#define MAX_CONTEXT_HW_ID (1<<21) /* exclusive */
+#define MAX_GUC_CONTEXT_HW_ID (1 << 20) /* exclusive */
+#define GEN11_MAX_CONTEXT_HW_ID (1<<11) /* exclusive */
+/* in Gen12 ID 0x7FF is reserved to indicate idle */
+#define GEN12_MAX_CONTEXT_HW_ID	(GEN11_MAX_CONTEXT_HW_ID - 1)
+
 enum {
 	INTEL_CONTEXT_SCHEDULE_IN = 0,
 	INTEL_CONTEXT_SCHEDULE_OUT,
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 343d79c1cb7e..04a5a0d90823 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1564,27 +1564,10 @@ vgpu_id_show(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "\n");
 }
 
-static ssize_t
-hw_id_show(struct device *dev, struct device_attribute *attr,
-	   char *buf)
-{
-	struct mdev_device *mdev = mdev_from_dev(dev);
-
-	if (mdev) {
-		struct intel_vgpu *vgpu = (struct intel_vgpu *)
-			mdev_get_drvdata(mdev);
-		return sprintf(buf, "%u\n",
-			       vgpu->submission.shadow[0]->gem_context->hw_id);
-	}
-	return sprintf(buf, "\n");
-}
-
 static DEVICE_ATTR_RO(vgpu_id);
-static DEVICE_ATTR_RO(hw_id);
 
 static struct attribute *intel_vgpu_attrs[] = {
 	&dev_attr_vgpu_id.attr,
-	&dev_attr_hw_id.attr,
 	NULL
 };
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 2afc41e43b6e..0e90ac608e07 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1593,9 +1593,6 @@ static int i915_context_status(struct seq_file *m, void *unused)
 		struct intel_context *ce;
 
 		seq_puts(m, "HW context ");
-		if (!list_empty(&ctx->hw_id_link))
-			seq_printf(m, "%x [pin %u]", ctx->hw_id,
-				   atomic_read(&ctx->hw_id_pin_count));
 		if (ctx->pid) {
 			struct task_struct *task;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index cb63b2bd0ce8..6bdcffbf1b9b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1541,18 +1541,6 @@ struct drm_i915_private {
 		struct list_head list;
 		struct llist_head free_list;
 		struct work_struct free_work;
-
-		/* The hw wants to have a stable context identifier for the
-		 * lifetime of the context (for OA, PASID, faults, etc).
-		 * This is limited in execlists to 21 bits.
-		 */
-		struct ida hw_ida;
-#define MAX_CONTEXT_HW_ID (1<<21) /* exclusive */
-#define MAX_GUC_CONTEXT_HW_ID (1 << 20) /* exclusive */
-#define GEN11_MAX_CONTEXT_HW_ID (1<<11) /* exclusive */
-/* in Gen12 ID 0x7FF is reserved to indicate idle */
-#define GEN12_MAX_CONTEXT_HW_ID	(GEN11_MAX_CONTEXT_HW_ID - 1)
-		struct list_head hw_id_list;
 	} contexts;
 
 	u32 fdi_rx_config;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index a28ee754b7b4..5cf4eed5add8 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -471,9 +471,9 @@ static void error_print_context(struct drm_i915_error_state_buf *m,
 				const char *header,
 				const struct drm_i915_error_context *ctx)
 {
-	err_printf(m, "%s%s[%d] hw_id %d, prio %d, guilty %d active %d\n",
-		   header, ctx->comm, ctx->pid, ctx->hw_id,
-		   ctx->sched_attr.priority, ctx->guilty, ctx->active);
+	err_printf(m, "%s%s[%d] prio %d, guilty %d active %d\n",
+		   header, ctx->comm, ctx->pid, ctx->sched_attr.priority,
+		   ctx->guilty, ctx->active);
 }
 
 static void error_print_engine(struct drm_i915_error_state_buf *m,
@@ -1271,7 +1271,6 @@ static bool record_context(struct drm_i915_error_context *e,
 		rcu_read_unlock();
 	}
 
-	e->hw_id = ctx->hw_id;
 	e->sched_attr = ctx->sched;
 	e->guilty = atomic_read(&ctx->guilty_count);
 	e->active = atomic_read(&ctx->active_count);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 63cf387411e0..7f1cd0b1fef7 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -119,7 +119,6 @@ struct i915_gpu_state {
 		struct drm_i915_error_context {
 			char comm[TASK_COMM_LEN];
 			pid_t pid;
-			u32 hw_id;
 			int active;
 			int guilty;
 			struct i915_sched_attr sched_attr;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 80055501eccb..ecfbc37b738b 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1283,22 +1283,15 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		} else {
 			stream->specific_ctx_id_mask =
 				(1U << GEN8_CTX_ID_WIDTH) - 1;
-			stream->specific_ctx_id =
-				upper_32_bits(ce->lrc_desc);
-			stream->specific_ctx_id &=
-				stream->specific_ctx_id_mask;
+			stream->specific_ctx_id = stream->specific_ctx_id_mask;
 		}
 		break;
 
 	case 11:
 	case 12: {
 		stream->specific_ctx_id_mask =
-			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32) |
-			((1U << GEN11_ENGINE_INSTANCE_WIDTH) - 1) << (GEN11_ENGINE_INSTANCE_SHIFT - 32) |
-			((1 << GEN11_ENGINE_CLASS_WIDTH) - 1) << (GEN11_ENGINE_CLASS_SHIFT - 32);
-		stream->specific_ctx_id = upper_32_bits(ce->lrc_desc);
-		stream->specific_ctx_id &=
-			stream->specific_ctx_id_mask;
+			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32);
+		stream->specific_ctx_id = stream->specific_ctx_id_mask;
 		break;
 	}
 
@@ -1306,6 +1299,8 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		MISSING_CASE(INTEL_GEN(i915));
 	}
 
+	ce->tag = stream->specific_ctx_id_mask;
+
 	DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
 			 stream->specific_ctx_id,
 			 stream->specific_ctx_id_mask);
@@ -1324,12 +1319,14 @@ static void oa_put_render_ctx_id(struct i915_perf_stream *stream)
 {
 	struct intel_context *ce;
 
-	stream->specific_ctx_id = INVALID_CTX_ID;
-	stream->specific_ctx_id_mask = 0;
-
 	ce = fetch_and_zero(&stream->pinned_ctx);
-	if (ce)
+	if (ce) {
+		ce->tag = 0; /* recomputed on next submission after parking */
 		intel_context_unpin(ce);
+	}
+
+	stream->specific_ctx_id = INVALID_CTX_ID;
+	stream->specific_ctx_id_mask = 0;
 }
 
 static void
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 24f2944da09d..1f2cf6cfafb5 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -665,7 +665,6 @@ TRACE_EVENT(i915_request_queue,
 
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
-			     __field(u32, hw_id)
 			     __field(u64, ctx)
 			     __field(u16, class)
 			     __field(u16, instance)
@@ -675,7 +674,6 @@ TRACE_EVENT(i915_request_queue,
 
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->gem_context->hw_id;
 			   __entry->class = rq->engine->uabi_class;
 			   __entry->instance = rq->engine->uabi_instance;
 			   __entry->ctx = rq->fence.context;
@@ -683,10 +681,9 @@ TRACE_EVENT(i915_request_queue,
 			   __entry->flags = flags;
 			   ),
 
-	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, flags=0x%x",
+	    TP_printk("dev=%u, engine=%u:%u, ctx=%llu, seqno=%u, flags=0x%x",
 		      __entry->dev, __entry->class, __entry->instance,
-		      __entry->hw_id, __entry->ctx, __entry->seqno,
-		      __entry->flags)
+		      __entry->ctx, __entry->seqno, __entry->flags)
 );
 
 DECLARE_EVENT_CLASS(i915_request,
@@ -695,7 +692,6 @@ DECLARE_EVENT_CLASS(i915_request,
 
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
-			     __field(u32, hw_id)
 			     __field(u64, ctx)
 			     __field(u16, class)
 			     __field(u16, instance)
@@ -704,16 +700,15 @@ DECLARE_EVENT_CLASS(i915_request,
 
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->gem_context->hw_id;
 			   __entry->class = rq->engine->uabi_class;
 			   __entry->instance = rq->engine->uabi_instance;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
 			   ),
 
-	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u",
+	    TP_printk("dev=%u, engine=%u:%u, ctx=%llu, seqno=%u",
 		      __entry->dev, __entry->class, __entry->instance,
-		      __entry->hw_id, __entry->ctx, __entry->seqno)
+		      __entry->ctx, __entry->seqno)
 );
 
 DEFINE_EVENT(i915_request, i915_request_add,
@@ -738,7 +733,6 @@ TRACE_EVENT(i915_request_in,
 
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
-			     __field(u32, hw_id)
 			     __field(u64, ctx)
 			     __field(u16, class)
 			     __field(u16, instance)
@@ -749,7 +743,6 @@ TRACE_EVENT(i915_request_in,
 
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->gem_context->hw_id;
 			   __entry->class = rq->engine->uabi_class;
 			   __entry->instance = rq->engine->uabi_instance;
 			   __entry->ctx = rq->fence.context;
@@ -758,9 +751,9 @@ TRACE_EVENT(i915_request_in,
 			   __entry->port = port;
 			   ),
 
-	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, prio=%u, port=%u",
+	    TP_printk("dev=%u, engine=%u:%u, ctx=%llu, seqno=%u, prio=%u, port=%u",
 		      __entry->dev, __entry->class, __entry->instance,
-		      __entry->hw_id, __entry->ctx, __entry->seqno,
+		      __entry->ctx, __entry->seqno,
 		      __entry->prio, __entry->port)
 );
 
@@ -770,7 +763,6 @@ TRACE_EVENT(i915_request_out,
 
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
-			     __field(u32, hw_id)
 			     __field(u64, ctx)
 			     __field(u16, class)
 			     __field(u16, instance)
@@ -780,7 +772,6 @@ TRACE_EVENT(i915_request_out,
 
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->gem_context->hw_id;
 			   __entry->class = rq->engine->uabi_class;
 			   __entry->instance = rq->engine->uabi_instance;
 			   __entry->ctx = rq->fence.context;
@@ -788,10 +779,9 @@ TRACE_EVENT(i915_request_out,
 			   __entry->completed = i915_request_completed(rq);
 			   ),
 
-		    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, completed?=%u",
+		    TP_printk("dev=%u, engine=%u:%u, ctx=%llu, seqno=%u, completed?=%u",
 			      __entry->dev, __entry->class, __entry->instance,
-			      __entry->hw_id, __entry->ctx, __entry->seqno,
-			      __entry->completed)
+			      __entry->ctx, __entry->seqno, __entry->completed)
 );
 
 #else
@@ -829,7 +819,6 @@ TRACE_EVENT(i915_request_wait_begin,
 
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
-			     __field(u32, hw_id)
 			     __field(u64, ctx)
 			     __field(u16, class)
 			     __field(u16, instance)
@@ -845,7 +834,6 @@ TRACE_EVENT(i915_request_wait_begin,
 	     */
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->gem_context->hw_id;
 			   __entry->class = rq->engine->uabi_class;
 			   __entry->instance = rq->engine->uabi_instance;
 			   __entry->ctx = rq->fence.context;
@@ -853,9 +841,9 @@ TRACE_EVENT(i915_request_wait_begin,
 			   __entry->flags = flags;
 			   ),
 
-	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, flags=0x%x",
+	    TP_printk("dev=%u, engine=%u:%u, ctx=%llu, seqno=%u, flags=0x%x",
 		      __entry->dev, __entry->class, __entry->instance,
-		      __entry->hw_id, __entry->ctx, __entry->seqno,
+		      __entry->ctx, __entry->seqno,
 		      __entry->flags)
 );
 
@@ -958,19 +946,17 @@ DECLARE_EVENT_CLASS(i915_context,
 	TP_STRUCT__entry(
 			__field(u32, dev)
 			__field(struct i915_gem_context *, ctx)
-			__field(u32, hw_id)
 			__field(struct i915_address_space *, vm)
 	),
 
 	TP_fast_assign(
 			__entry->dev = ctx->i915->drm.primary->index;
 			__entry->ctx = ctx;
-			__entry->hw_id = ctx->hw_id;
 			__entry->vm = ctx->vm;
 	),
 
-	TP_printk("dev=%u, ctx=%p, ctx_vm=%p, hw_id=%u",
-		  __entry->dev, __entry->ctx, __entry->vm, __entry->hw_id)
+	TP_printk("dev=%u, ctx=%p, ctx_vm=%p",
+		  __entry->dev, __entry->ctx, __entry->vm)
 )
 
 DEFINE_EVENT(i915_context, i915_context_create,
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index 52d2df843148..f39f0282e78c 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -491,8 +491,8 @@ static int igt_evict_contexts(void *arg)
 			if (IS_ERR(rq)) {
 				/* When full, fail_if_busy will trigger EBUSY */
 				if (PTR_ERR(rq) != -EBUSY) {
-					pr_err("Unexpected error from request alloc (ctx hw id %u, on %s): %d\n",
-					       ctx->hw_id, engine->name,
+					pr_err("Unexpected error from request alloc (on %s): %d\n",
+					       engine->name,
 					       (int)PTR_ERR(rq));
 					err = PTR_ERR(rq);
 				}
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index 1c9db08f7c28..ac1ff558eb90 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -170,7 +170,7 @@ static int igt_vma_create(void *arg)
 		}
 
 		nc = 0;
-		for_each_prime_number(num_ctx, MAX_CONTEXT_HW_ID) {
+		for_each_prime_number(num_ctx, 2 * NUM_CONTEXT_TAG) {
 			for (; nc < num_ctx; nc++) {
 				ctx = mock_context(i915, "mock");
 				if (!ctx)
-- 
cgit v1.2.3


From a4e7ccdac38ec8335d9e4e2656c1a041c77feae1 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:09 +0100
Subject: drm/i915: Move context management under GEM

Keep track of the GEM contexts underneath i915->gem.contexts and assign
them their own lock for the purposes of list management.

v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex
v3: Correct split with removal of logical HW ID

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-15-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c        | 177 ++++++++++-----------
 drivers/gpu/drm/i915/gem/i915_gem_context.h        |  27 +++-
 drivers/gpu/drm/i915/gem/i915_gem_context_types.h  |   2 +-
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c     |   2 +-
 drivers/gpu/drm/i915/gem/i915_gem_userptr.c        |   3 +-
 drivers/gpu/drm/i915/gem/selftests/huge_pages.c    |  36 +++--
 .../gpu/drm/i915/gem/selftests/i915_gem_context.c  | 168 +++++++++----------
 drivers/gpu/drm/i915/gem/selftests/mock_context.c  |   7 +-
 drivers/gpu/drm/i915/gt/intel_context.c            |  10 +-
 drivers/gpu/drm/i915/gt/selftest_context.c         |  24 +--
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c       |  39 +++--
 drivers/gpu/drm/i915/gt/selftest_lrc.c             |   6 +-
 drivers/gpu/drm/i915/gt/selftest_workarounds.c     |  22 ++-
 drivers/gpu/drm/i915/gvt/scheduler.c               |  24 +--
 drivers/gpu/drm/i915/i915_debugfs.c                |  50 +++---
 drivers/gpu/drm/i915/i915_drv.c                    |   2 -
 drivers/gpu/drm/i915/i915_drv.h                    |  15 +-
 drivers/gpu/drm/i915/i915_gem.c                    |  10 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c                |   4 +-
 drivers/gpu/drm/i915/i915_perf.c                   |  24 ++-
 drivers/gpu/drm/i915/i915_sysfs.c                  |  43 +++--
 drivers/gpu/drm/i915/i915_trace.h                  |   2 +-
 drivers/gpu/drm/i915/selftests/i915_gem.c          |   8 -
 drivers/gpu/drm/i915/selftests/i915_gem_evict.c    |   3 -
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c      |  15 +-
 drivers/gpu/drm/i915/selftests/i915_request.c      |  12 +-
 drivers/gpu/drm/i915/selftests/i915_vma.c          |   7 +-
 drivers/gpu/drm/i915/selftests/mock_gem_device.c   |   6 +-
 28 files changed, 394 insertions(+), 354 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index cd4f327b23bd..5d8221c7ba83 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -218,9 +218,12 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx)
 
 static void i915_gem_context_free(struct i915_gem_context *ctx)
 {
-	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
 	GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
 
+	spin_lock(&ctx->i915->gem.contexts.lock);
+	list_del(&ctx->link);
+	spin_unlock(&ctx->i915->gem.contexts.lock);
+
 	free_engines(rcu_access_pointer(ctx->engines));
 	mutex_destroy(&ctx->engines_mutex);
 
@@ -230,67 +233,54 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
 	kfree(ctx->name);
 	put_pid(ctx->pid);
 
-	list_del(&ctx->link);
 	mutex_destroy(&ctx->mutex);
 
 	kfree_rcu(ctx, rcu);
 }
 
-static void contexts_free(struct drm_i915_private *i915)
+static void contexts_free_all(struct llist_node *list)
 {
-	struct llist_node *freed = llist_del_all(&i915->contexts.free_list);
 	struct i915_gem_context *ctx, *cn;
 
-	lockdep_assert_held(&i915->drm.struct_mutex);
-
-	llist_for_each_entry_safe(ctx, cn, freed, free_link)
+	llist_for_each_entry_safe(ctx, cn, list, free_link)
 		i915_gem_context_free(ctx);
 }
 
-static void contexts_free_first(struct drm_i915_private *i915)
+static void contexts_flush_free(struct i915_gem_contexts *gc)
 {
-	struct i915_gem_context *ctx;
-	struct llist_node *freed;
-
-	lockdep_assert_held(&i915->drm.struct_mutex);
-
-	freed = llist_del_first(&i915->contexts.free_list);
-	if (!freed)
-		return;
-
-	ctx = container_of(freed, typeof(*ctx), free_link);
-	i915_gem_context_free(ctx);
+	contexts_free_all(llist_del_all(&gc->free_list));
 }
 
 static void contexts_free_worker(struct work_struct *work)
 {
-	struct drm_i915_private *i915 =
-		container_of(work, typeof(*i915), contexts.free_work);
+	struct i915_gem_contexts *gc =
+		container_of(work, typeof(*gc), free_work);
 
-	mutex_lock(&i915->drm.struct_mutex);
-	contexts_free(i915);
-	mutex_unlock(&i915->drm.struct_mutex);
+	contexts_flush_free(gc);
 }
 
 void i915_gem_context_release(struct kref *ref)
 {
 	struct i915_gem_context *ctx = container_of(ref, typeof(*ctx), ref);
-	struct drm_i915_private *i915 = ctx->i915;
+	struct i915_gem_contexts *gc = &ctx->i915->gem.contexts;
 
 	trace_i915_context_free(ctx);
-	if (llist_add(&ctx->free_link, &i915->contexts.free_list))
-		queue_work(i915->wq, &i915->contexts.free_work);
+	if (llist_add(&ctx->free_link, &gc->free_list))
+		schedule_work(&gc->free_work);
 }
 
 static void context_close(struct i915_gem_context *ctx)
 {
-	i915_gem_context_set_closed(ctx);
+	struct i915_address_space *vm;
 
-	if (ctx->vm)
-		i915_vm_close(ctx->vm);
+	i915_gem_context_set_closed(ctx);
 
 	mutex_lock(&ctx->mutex);
 
+	vm = i915_gem_context_vm(ctx);
+	if (vm)
+		i915_vm_close(vm);
+
 	ctx->file_priv = ERR_PTR(-EBADF);
 
 	/*
@@ -317,7 +307,6 @@ __create_context(struct drm_i915_private *i915)
 		return ERR_PTR(-ENOMEM);
 
 	kref_init(&ctx->ref);
-	list_add_tail(&ctx->link, &i915->contexts.list);
 	ctx->i915 = i915;
 	ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_NORMAL);
 	mutex_init(&ctx->mutex);
@@ -343,6 +332,10 @@ __create_context(struct drm_i915_private *i915)
 	for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
 		ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
 
+	spin_lock(&i915->gem.contexts.lock);
+	list_add_tail(&ctx->link, &i915->gem.contexts.list);
+	spin_unlock(&i915->gem.contexts.lock);
+
 	return ctx;
 
 err_free:
@@ -372,11 +365,11 @@ static void __apply_ppgtt(struct intel_context *ce, void *vm)
 static struct i915_address_space *
 __set_ppgtt(struct i915_gem_context *ctx, struct i915_address_space *vm)
 {
-	struct i915_address_space *old = ctx->vm;
+	struct i915_address_space *old = i915_gem_context_vm(ctx);
 
 	GEM_BUG_ON(old && i915_vm_is_4lvl(vm) != i915_vm_is_4lvl(old));
 
-	ctx->vm = i915_vm_open(vm);
+	rcu_assign_pointer(ctx->vm, i915_vm_open(vm));
 	context_apply_all(ctx, __apply_ppgtt, vm);
 
 	return old;
@@ -385,7 +378,7 @@ __set_ppgtt(struct i915_gem_context *ctx, struct i915_address_space *vm)
 static void __assign_ppgtt(struct i915_gem_context *ctx,
 			   struct i915_address_space *vm)
 {
-	if (vm == ctx->vm)
+	if (vm == rcu_access_pointer(ctx->vm))
 		return;
 
 	vm = __set_ppgtt(ctx, vm);
@@ -417,27 +410,25 @@ static void __assign_timeline(struct i915_gem_context *ctx,
 }
 
 static struct i915_gem_context *
-i915_gem_create_context(struct drm_i915_private *dev_priv, unsigned int flags)
+i915_gem_create_context(struct drm_i915_private *i915, unsigned int flags)
 {
 	struct i915_gem_context *ctx;
 
-	lockdep_assert_held(&dev_priv->drm.struct_mutex);
-
 	if (flags & I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE &&
-	    !HAS_EXECLISTS(dev_priv))
+	    !HAS_EXECLISTS(i915))
 		return ERR_PTR(-EINVAL);
 
-	/* Reap the most stale context */
-	contexts_free_first(dev_priv);
+	/* Reap the stale contexts */
+	contexts_flush_free(&i915->gem.contexts);
 
-	ctx = __create_context(dev_priv);
+	ctx = __create_context(i915);
 	if (IS_ERR(ctx))
 		return ctx;
 
-	if (HAS_FULL_PPGTT(dev_priv)) {
+	if (HAS_FULL_PPGTT(i915)) {
 		struct i915_ppgtt *ppgtt;
 
-		ppgtt = i915_ppgtt_create(dev_priv);
+		ppgtt = i915_ppgtt_create(i915);
 		if (IS_ERR(ppgtt)) {
 			DRM_DEBUG_DRIVER("PPGTT setup failed (%ld)\n",
 					 PTR_ERR(ppgtt));
@@ -445,14 +436,17 @@ i915_gem_create_context(struct drm_i915_private *dev_priv, unsigned int flags)
 			return ERR_CAST(ppgtt);
 		}
 
+		mutex_lock(&ctx->mutex);
 		__assign_ppgtt(ctx, &ppgtt->vm);
+		mutex_unlock(&ctx->mutex);
+
 		i915_vm_put(&ppgtt->vm);
 	}
 
 	if (flags & I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE) {
 		struct intel_timeline *timeline;
 
-		timeline = intel_timeline_create(&dev_priv->gt, NULL);
+		timeline = intel_timeline_create(&i915->gt, NULL);
 		if (IS_ERR(timeline)) {
 			context_close(ctx);
 			return ERR_CAST(timeline);
@@ -497,42 +491,40 @@ i915_gem_context_create_kernel(struct drm_i915_private *i915, int prio)
 	return ctx;
 }
 
-static void init_contexts(struct drm_i915_private *i915)
+static void init_contexts(struct i915_gem_contexts *gc)
 {
-	mutex_init(&i915->contexts.mutex);
-	INIT_LIST_HEAD(&i915->contexts.list);
+	spin_lock_init(&gc->lock);
+	INIT_LIST_HEAD(&gc->list);
 
-	INIT_WORK(&i915->contexts.free_work, contexts_free_worker);
-	init_llist_head(&i915->contexts.free_list);
+	INIT_WORK(&gc->free_work, contexts_free_worker);
+	init_llist_head(&gc->free_list);
 }
 
-int i915_gem_contexts_init(struct drm_i915_private *dev_priv)
+int i915_gem_init_contexts(struct drm_i915_private *i915)
 {
 	struct i915_gem_context *ctx;
 
 	/* Reassure ourselves we are only called once */
-	GEM_BUG_ON(dev_priv->kernel_context);
+	GEM_BUG_ON(i915->kernel_context);
 
-	init_contexts(dev_priv);
+	init_contexts(&i915->gem.contexts);
 
 	/* lowest priority; idle task */
-	ctx = i915_gem_context_create_kernel(dev_priv, I915_PRIORITY_MIN);
+	ctx = i915_gem_context_create_kernel(i915, I915_PRIORITY_MIN);
 	if (IS_ERR(ctx)) {
 		DRM_ERROR("Failed to create default global context\n");
 		return PTR_ERR(ctx);
 	}
-	dev_priv->kernel_context = ctx;
+	i915->kernel_context = ctx;
 
 	DRM_DEBUG_DRIVER("%s context support initialized\n",
-			 DRIVER_CAPS(dev_priv)->has_logical_contexts ?
+			 DRIVER_CAPS(i915)->has_logical_contexts ?
 			 "logical" : "fake");
 	return 0;
 }
 
-void i915_gem_contexts_fini(struct drm_i915_private *i915)
+void i915_gem_driver_release__contexts(struct drm_i915_private *i915)
 {
-	lockdep_assert_held(&i915->drm.struct_mutex);
-
 	destroy_kernel_context(&i915->kernel_context);
 }
 
@@ -551,11 +543,16 @@ static int vm_idr_cleanup(int id, void *p, void *data)
 static int gem_context_register(struct i915_gem_context *ctx,
 				struct drm_i915_file_private *fpriv)
 {
+	struct i915_address_space *vm;
 	int ret;
 
 	ctx->file_priv = fpriv;
-	if (ctx->vm)
-		ctx->vm->file = fpriv;
+
+	mutex_lock(&ctx->mutex);
+	vm = i915_gem_context_vm(ctx);
+	if (vm)
+		WRITE_ONCE(vm->file, fpriv); /* XXX */
+	mutex_unlock(&ctx->mutex);
 
 	ctx->pid = get_task_pid(current, PIDTYPE_PID);
 	ctx->name = kasprintf(GFP_KERNEL, "%s[%d]",
@@ -592,9 +589,7 @@ int i915_gem_context_open(struct drm_i915_private *i915,
 	idr_init(&file_priv->context_idr);
 	idr_init_base(&file_priv->vm_idr, 1);
 
-	mutex_lock(&i915->drm.struct_mutex);
 	ctx = i915_gem_create_context(i915, 0);
-	mutex_unlock(&i915->drm.struct_mutex);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto err;
@@ -622,6 +617,7 @@ err:
 void i915_gem_context_close(struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
+	struct drm_i915_private *i915 = file_priv->dev_priv;
 
 	idr_for_each(&file_priv->context_idr, context_idr_cleanup, NULL);
 	idr_destroy(&file_priv->context_idr);
@@ -630,6 +626,8 @@ void i915_gem_context_close(struct drm_file *file)
 	idr_for_each(&file_priv->vm_idr, vm_idr_cleanup, NULL);
 	idr_destroy(&file_priv->vm_idr);
 	mutex_destroy(&file_priv->vm_idr_lock);
+
+	contexts_flush_free(&i915->gem.contexts);
 }
 
 int i915_gem_vm_create_ioctl(struct drm_device *dev, void *data,
@@ -808,16 +806,12 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv,
 	struct i915_address_space *vm;
 	int ret;
 
-	if (!ctx->vm)
+	if (!rcu_access_pointer(ctx->vm))
 		return -ENODEV;
 
-	/* XXX rcu acquire? */
-	ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
-	if (ret)
-		return ret;
-
+	rcu_read_lock();
 	vm = i915_vm_get(ctx->vm);
-	mutex_unlock(&ctx->i915->drm.struct_mutex);
+	rcu_read_unlock();
 
 	ret = mutex_lock_interruptible(&file_priv->vm_idr_lock);
 	if (ret)
@@ -926,7 +920,7 @@ static int set_ppgtt(struct drm_i915_file_private *file_priv,
 	if (args->size)
 		return -EINVAL;
 
-	if (!ctx->vm)
+	if (!rcu_access_pointer(ctx->vm))
 		return -ENODEV;
 
 	if (upper_32_bits(args->value))
@@ -940,17 +934,20 @@ static int set_ppgtt(struct drm_i915_file_private *file_priv,
 	if (!vm)
 		return -ENOENT;
 
-	err = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex);
+	err = mutex_lock_interruptible(&ctx->mutex);
 	if (err)
 		goto out;
 
-	if (vm == ctx->vm)
+	if (i915_gem_context_is_closed(ctx)) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	if (vm == rcu_access_pointer(ctx->vm))
 		goto unlock;
 
 	/* Teardown the existing obj:vma cache, it will have to be rebuilt. */
-	mutex_lock(&ctx->mutex);
 	lut_close(ctx);
-	mutex_unlock(&ctx->mutex);
 
 	old = __set_ppgtt(ctx, vm);
 
@@ -970,8 +967,7 @@ static int set_ppgtt(struct drm_i915_file_private *file_priv,
 	}
 
 unlock:
-	mutex_unlock(&ctx->i915->drm.struct_mutex);
-
+	mutex_unlock(&ctx->mutex);
 out:
 	i915_vm_put(vm);
 	return err;
@@ -1827,10 +1823,11 @@ static int clone_vm(struct i915_gem_context *dst,
 		    struct i915_gem_context *src)
 {
 	struct i915_address_space *vm;
+	int err = 0;
 
 	rcu_read_lock();
 	do {
-		vm = READ_ONCE(src->vm);
+		vm = rcu_dereference(src->vm);
 		if (!vm)
 			break;
 
@@ -1852,7 +1849,7 @@ static int clone_vm(struct i915_gem_context *dst,
 		 * it cannot be reallocated elsewhere.
 		 */
 
-		if (vm == READ_ONCE(src->vm))
+		if (vm == rcu_access_pointer(src->vm))
 			break;
 
 		i915_vm_put(vm);
@@ -1860,11 +1857,16 @@ static int clone_vm(struct i915_gem_context *dst,
 	rcu_read_unlock();
 
 	if (vm) {
-		__assign_ppgtt(dst, vm);
+		if (!mutex_lock_interruptible(&dst->mutex)) {
+			__assign_ppgtt(dst, vm);
+			mutex_unlock(&dst->mutex);
+		} else {
+			err = -EINTR;
+		}
 		i915_vm_put(vm);
 	}
 
-	return 0;
+	return err;
 }
 
 static int create_clone(struct i915_user_extension __user *ext, void *data)
@@ -1954,12 +1956,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 		return -EIO;
 	}
 
-	ret = i915_mutex_lock_interruptible(dev);
-	if (ret)
-		return ret;
-
 	ext_data.ctx = i915_gem_create_context(i915, args->flags);
-	mutex_unlock(&dev->struct_mutex);
 	if (IS_ERR(ext_data.ctx))
 		return PTR_ERR(ext_data.ctx);
 
@@ -2086,10 +2083,12 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 
 	case I915_CONTEXT_PARAM_GTT_SIZE:
 		args->size = 0;
-		if (ctx->vm)
-			args->value = ctx->vm->total;
+		rcu_read_lock();
+		if (rcu_access_pointer(ctx->vm))
+			args->value = rcu_dereference(ctx->vm)->total;
 		else
 			args->value = to_i915(dev)->ggtt.vm.total;
+		rcu_read_unlock();
 		break;
 
 	case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
@@ -2155,7 +2154,7 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 int i915_gem_context_reset_stats_ioctl(struct drm_device *dev,
 				       void *data, struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_reset_stats *args = data;
 	struct i915_gem_context *ctx;
 	int ret;
@@ -2177,7 +2176,7 @@ int i915_gem_context_reset_stats_ioctl(struct drm_device *dev,
 	 */
 
 	if (capable(CAP_SYS_ADMIN))
-		args->reset_count = i915_reset_count(&dev_priv->gpu_error);
+		args->reset_count = i915_reset_count(&i915->gpu_error);
 	else
 		args->reset_count = 0;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h
index 50bc27d30c03..9234586830d1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h
@@ -11,7 +11,9 @@
 
 #include "gt/intel_context.h"
 
+#include "i915_drv.h"
 #include "i915_gem.h"
+#include "i915_gem_gtt.h"
 #include "i915_scheduler.h"
 #include "intel_device_info.h"
 
@@ -118,8 +120,8 @@ static inline bool i915_gem_context_is_kernel(struct i915_gem_context *ctx)
 }
 
 /* i915_gem_context.c */
-int __must_check i915_gem_contexts_init(struct drm_i915_private *dev_priv);
-void i915_gem_contexts_fini(struct drm_i915_private *dev_priv);
+int __must_check i915_gem_init_contexts(struct drm_i915_private *i915);
+void i915_gem_driver_release__contexts(struct drm_i915_private *i915);
 
 int i915_gem_context_open(struct drm_i915_private *i915,
 			  struct drm_file *file);
@@ -158,6 +160,27 @@ static inline void i915_gem_context_put(struct i915_gem_context *ctx)
 	kref_put(&ctx->ref, i915_gem_context_release);
 }
 
+static inline struct i915_address_space *
+i915_gem_context_vm(struct i915_gem_context *ctx)
+{
+	return rcu_dereference_protected(ctx->vm, lockdep_is_held(&ctx->mutex));
+}
+
+static inline struct i915_address_space *
+i915_gem_context_get_vm_rcu(struct i915_gem_context *ctx)
+{
+	struct i915_address_space *vm;
+
+	rcu_read_lock();
+	vm = rcu_dereference(ctx->vm);
+	if (!vm)
+		vm = &ctx->i915->ggtt.vm;
+	vm = i915_vm_get(vm);
+	rcu_read_unlock();
+
+	return vm;
+}
+
 static inline struct i915_gem_engines *
 i915_gem_context_engines(struct i915_gem_context *ctx)
 {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index 87be27877e22..ab8e1367dfc8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -88,7 +88,7 @@ struct i915_gem_context {
 	 * In other modes, this is a NULL pointer with the expectation that
 	 * the caller uses the shared global GTT.
 	 */
-	struct i915_address_space *vm;
+	struct i915_address_space __rcu *vm;
 
 	/**
 	 * @pid: process id of creator
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 42c15e8bf166..580c15e74a0a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -728,7 +728,7 @@ static int eb_select_context(struct i915_execbuffer *eb)
 		return -ENOENT;
 
 	eb->gem_context = ctx;
-	if (ctx->vm)
+	if (rcu_access_pointer(ctx->vm))
 		eb->invalid_flags |= EXEC_OBJECT_NEEDS_GTT;
 
 	eb->context_flags = 0;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 3798502097b4..ef5e723fd057 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -766,7 +766,8 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 		 * On almost all of the older hw, we cannot tell the GPU that
 		 * a page is readonly.
 		 */
-		vm = dev_priv->kernel_context->vm;
+		vm = rcu_dereference_protected(dev_priv->kernel_context->vm,
+					       true); /* static vm */
 		if (!vm || !vm->has_read_only)
 			return -ENODEV;
 	}
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 98b2a6ccfcc1..3314858f3046 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -1322,15 +1322,15 @@ static int igt_ppgtt_pin_update(void *arg)
 	struct i915_gem_context *ctx = arg;
 	struct drm_i915_private *dev_priv = ctx->i915;
 	unsigned long supported = INTEL_INFO(dev_priv)->page_sizes;
-	struct i915_address_space *vm = ctx->vm;
 	struct drm_i915_gem_object *obj;
 	struct i915_gem_engines_iter it;
+	struct i915_address_space *vm;
 	struct intel_context *ce;
 	struct i915_vma *vma;
 	unsigned int flags = PIN_USER | PIN_OFFSET_FIXED;
 	unsigned int n;
 	int first, last;
-	int err;
+	int err = 0;
 
 	/*
 	 * Make sure there's no funny business when doing a PIN_UPDATE -- in the
@@ -1340,9 +1340,10 @@ static int igt_ppgtt_pin_update(void *arg)
 	 * huge-gtt-pages.
 	 */
 
-	if (!vm || !i915_vm_is_4lvl(vm)) {
+	vm = i915_gem_context_get_vm_rcu(ctx);
+	if (!i915_vm_is_4lvl(vm)) {
 		pr_info("48b PPGTT not supported, skipping\n");
-		return 0;
+		goto out_vm;
 	}
 
 	first = ilog2(I915_GTT_PAGE_SIZE_64K);
@@ -1451,6 +1452,8 @@ out_close:
 	i915_vma_close(vma);
 out_put:
 	i915_gem_object_put(obj);
+out_vm:
+	i915_vm_put(vm);
 
 	return err;
 }
@@ -1460,7 +1463,7 @@ static int igt_tmpfs_fallback(void *arg)
 	struct i915_gem_context *ctx = arg;
 	struct drm_i915_private *i915 = ctx->i915;
 	struct vfsmount *gemfs = i915->mm.gemfs;
-	struct i915_address_space *vm = ctx->vm ?: &i915->ggtt.vm;
+	struct i915_address_space *vm = i915_gem_context_get_vm_rcu(ctx);
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 	u32 *vaddr;
@@ -1510,6 +1513,7 @@ out_put:
 out_restore:
 	i915->mm.gemfs = gemfs;
 
+	i915_vm_put(vm);
 	return err;
 }
 
@@ -1517,14 +1521,14 @@ static int igt_shrink_thp(void *arg)
 {
 	struct i915_gem_context *ctx = arg;
 	struct drm_i915_private *i915 = ctx->i915;
-	struct i915_address_space *vm = ctx->vm ?: &i915->ggtt.vm;
+	struct i915_address_space *vm = i915_gem_context_get_vm_rcu(ctx);
 	struct drm_i915_gem_object *obj;
 	struct i915_gem_engines_iter it;
 	struct intel_context *ce;
 	struct i915_vma *vma;
 	unsigned int flags = PIN_USER;
 	unsigned int n;
-	int err;
+	int err = 0;
 
 	/*
 	 * Sanity check shrinking huge-paged object -- make sure nothing blows
@@ -1533,12 +1537,14 @@ static int igt_shrink_thp(void *arg)
 
 	if (!igt_can_allocate_thp(i915)) {
 		pr_info("missing THP support, skipping\n");
-		return 0;
+		goto out_vm;
 	}
 
 	obj = i915_gem_object_create_shmem(i915, SZ_2M);
-	if (IS_ERR(obj))
-		return PTR_ERR(obj);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto out_vm;
+	}
 
 	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma)) {
@@ -1607,6 +1613,8 @@ out_close:
 	i915_vma_close(vma);
 out_put:
 	i915_gem_object_put(obj);
+out_vm:
+	i915_vm_put(vm);
 
 	return err;
 }
@@ -1675,6 +1683,7 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 	};
 	struct drm_file *file;
 	struct i915_gem_context *ctx;
+	struct i915_address_space *vm;
 	intel_wakeref_t wakeref;
 	int err;
 
@@ -1699,8 +1708,11 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 		goto out_unlock;
 	}
 
-	if (ctx->vm)
-		ctx->vm->scrub_64K = true;
+	mutex_lock(&ctx->mutex);
+	vm = i915_gem_context_vm(ctx);
+	if (vm)
+		WRITE_ONCE(vm->scrub_64K, true);
+	mutex_unlock(&ctx->mutex);
 
 	err = i915_subtests(tests, ctx);
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index 2fb31ada2fa7..d44fa9d356f1 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -53,19 +53,17 @@ static int live_nop_switch(void *arg)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	ctx = kcalloc(nctx, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx) {
 		err = -ENOMEM;
-		goto out_unlock;
+		goto out_file;
 	}
 
 	for (n = 0; n < nctx; n++) {
 		ctx[n] = live_context(i915, file);
 		if (IS_ERR(ctx[n])) {
 			err = PTR_ERR(ctx[n]);
-			goto out_unlock;
+			goto out_file;
 		}
 	}
 
@@ -79,7 +77,7 @@ static int live_nop_switch(void *arg)
 			rq = igt_request_alloc(ctx[n], engine);
 			if (IS_ERR(rq)) {
 				err = PTR_ERR(rq);
-				goto out_unlock;
+				goto out_file;
 			}
 			i915_request_add(rq);
 		}
@@ -87,7 +85,7 @@ static int live_nop_switch(void *arg)
 			pr_err("Failed to populated %d contexts\n", nctx);
 			intel_gt_set_wedged(&i915->gt);
 			err = -EIO;
-			goto out_unlock;
+			goto out_file;
 		}
 
 		times[1] = ktime_get_raw();
@@ -97,7 +95,7 @@ static int live_nop_switch(void *arg)
 
 		err = igt_live_test_begin(&t, i915, __func__, engine->name);
 		if (err)
-			goto out_unlock;
+			goto out_file;
 
 		end_time = jiffies + i915_selftest.timeout_jiffies;
 		for_each_prime_number_from(prime, 2, 8192) {
@@ -107,7 +105,7 @@ static int live_nop_switch(void *arg)
 				rq = igt_request_alloc(ctx[n % nctx], engine);
 				if (IS_ERR(rq)) {
 					err = PTR_ERR(rq);
-					goto out_unlock;
+					goto out_file;
 				}
 
 				/*
@@ -143,7 +141,7 @@ static int live_nop_switch(void *arg)
 
 		err = igt_live_test_end(&t);
 		if (err)
-			goto out_unlock;
+			goto out_file;
 
 		pr_info("Switch latencies on %s: 1 = %lluns, %lu = %lluns\n",
 			engine->name,
@@ -151,8 +149,7 @@ static int live_nop_switch(void *arg)
 			prime - 1, div64_u64(ktime_to_ns(times[1]), prime - 1));
 	}
 
-out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
+out_file:
 	mock_file_free(i915, file);
 	return err;
 }
@@ -253,12 +250,10 @@ static int live_parallel_switch(void *arg)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	ctx = live_context(i915, file);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
-		goto out_locked;
+		goto out_file;
 	}
 
 	engines = i915_gem_context_lock_engines(ctx);
@@ -268,7 +263,7 @@ static int live_parallel_switch(void *arg)
 	if (!data) {
 		i915_gem_context_unlock_engines(ctx);
 		err = -ENOMEM;
-		goto out_locked;
+		goto out;
 	}
 
 	m = 0; /* Use the first context as our template for the engines */
@@ -276,7 +271,7 @@ static int live_parallel_switch(void *arg)
 		err = intel_context_pin(ce);
 		if (err) {
 			i915_gem_context_unlock_engines(ctx);
-			goto out_locked;
+			goto out;
 		}
 		data[m++].ce[0] = intel_context_get(ce);
 	}
@@ -287,7 +282,7 @@ static int live_parallel_switch(void *arg)
 		ctx = live_context(i915, file);
 		if (IS_ERR(ctx)) {
 			err = PTR_ERR(ctx);
-			goto out_locked;
+			goto out;
 		}
 
 		for (m = 0; m < count; m++) {
@@ -296,20 +291,18 @@ static int live_parallel_switch(void *arg)
 
 			ce = intel_context_create(ctx, data[m].ce[0]->engine);
 			if (IS_ERR(ce))
-				goto out_locked;
+				goto out;
 
 			err = intel_context_pin(ce);
 			if (err) {
 				intel_context_put(ce);
-				goto out_locked;
+				goto out;
 			}
 
 			data[m].ce[n] = ce;
 		}
 	}
 
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	for (fn = func; !err && *fn; fn++) {
 		struct igt_live_test t;
 		int n;
@@ -354,8 +347,7 @@ static int live_parallel_switch(void *arg)
 		mutex_unlock(&i915->drm.struct_mutex);
 	}
 
-	mutex_lock(&i915->drm.struct_mutex);
-out_locked:
+out:
 	for (n = 0; n < count; n++) {
 		for (m = 0; m < ARRAY_SIZE(data->ce); m++) {
 			if (!data[n].ce[m])
@@ -365,8 +357,8 @@ out_locked:
 			intel_context_put(data[n].ce[m]);
 		}
 	}
-	mutex_unlock(&i915->drm.struct_mutex);
 	kfree(data);
+out_file:
 	mock_file_free(i915, file);
 	return err;
 }
@@ -626,11 +618,9 @@ static int igt_ctx_exec(void *arg)
 		if (IS_ERR(file))
 			return PTR_ERR(file);
 
-		mutex_lock(&i915->drm.struct_mutex);
-
 		err = igt_live_test_begin(&t, i915, __func__, engine->name);
 		if (err)
-			goto out_unlock;
+			goto out_file;
 
 		ncontexts = 0;
 		ndwords = 0;
@@ -642,7 +632,7 @@ static int igt_ctx_exec(void *arg)
 			ctx = kernel_context(i915);
 			if (IS_ERR(ctx)) {
 				err = PTR_ERR(ctx);
-				goto out_unlock;
+				goto out_file;
 			}
 
 			ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
@@ -654,7 +644,7 @@ static int igt_ctx_exec(void *arg)
 					err = PTR_ERR(obj);
 					intel_context_put(ce);
 					kernel_context_close(ctx);
-					goto out_unlock;
+					goto out_file;
 				}
 			}
 
@@ -663,17 +653,18 @@ static int igt_ctx_exec(void *arg)
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
 				       engine->name,
-				       yesno(!!ctx->vm), err);
+				       yesno(!!rcu_access_pointer(ctx->vm)),
+				       err);
 				intel_context_put(ce);
 				kernel_context_close(ctx);
-				goto out_unlock;
+				goto out_file;
 			}
 
 			err = throttle(ce, tq, ARRAY_SIZE(tq));
 			if (err) {
 				intel_context_put(ce);
 				kernel_context_close(ctx);
-				goto out_unlock;
+				goto out_file;
 			}
 
 			if (++dw == max_dwords(obj)) {
@@ -703,11 +694,10 @@ static int igt_ctx_exec(void *arg)
 			dw += rem;
 		}
 
-out_unlock:
+out_file:
 		throttle_release(tq, ARRAY_SIZE(tq));
 		if (igt_live_test_end(&t))
 			err = -EIO;
-		mutex_unlock(&i915->drm.struct_mutex);
 
 		mock_file_free(i915, file);
 		if (err)
@@ -742,22 +732,20 @@ static int igt_shared_ctx_exec(void *arg)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	parent = live_context(i915, file);
 	if (IS_ERR(parent)) {
 		err = PTR_ERR(parent);
-		goto out_unlock;
+		goto out_file;
 	}
 
 	if (!parent->vm) { /* not full-ppgtt; nothing to share */
 		err = 0;
-		goto out_unlock;
+		goto out_file;
 	}
 
 	err = igt_live_test_begin(&t, i915, __func__, "");
 	if (err)
-		goto out_unlock;
+		goto out_file;
 
 	for_each_engine(engine, i915, id) {
 		unsigned long ncontexts, ndwords, dw;
@@ -781,7 +769,9 @@ static int igt_shared_ctx_exec(void *arg)
 				goto out_test;
 			}
 
+			mutex_lock(&ctx->mutex);
 			__assign_ppgtt(ctx, parent->vm);
+			mutex_unlock(&ctx->mutex);
 
 			ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
 			GEM_BUG_ON(IS_ERR(ce));
@@ -801,7 +791,8 @@ static int igt_shared_ctx_exec(void *arg)
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
 				       engine->name,
-				       yesno(!!ctx->vm), err);
+				       yesno(!!rcu_access_pointer(ctx->vm)),
+				       err);
 				intel_context_put(ce);
 				kernel_context_close(ctx);
 				goto out_test;
@@ -840,17 +831,13 @@ static int igt_shared_ctx_exec(void *arg)
 			dw += rem;
 		}
 
-		mutex_unlock(&i915->drm.struct_mutex);
 		i915_gem_drain_freed_objects(i915);
-		mutex_lock(&i915->drm.struct_mutex);
 	}
 out_test:
 	throttle_release(tq, ARRAY_SIZE(tq));
 	if (igt_live_test_end(&t))
 		err = -EIO;
-out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
-
+out_file:
 	mock_file_free(i915, file);
 	return err;
 }
@@ -1222,8 +1209,6 @@ __igt_ctx_sseu(struct drm_i915_private *i915,
 	if (flags & TEST_RESET)
 		igt_global_reset_lock(&i915->gt);
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	ctx = live_context(i915, file);
 	if (IS_ERR(ctx)) {
 		ret = PTR_ERR(ctx);
@@ -1278,8 +1263,6 @@ out_put:
 	i915_gem_object_put(obj);
 
 out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	if (flags & TEST_RESET)
 		igt_global_reset_unlock(&i915->gt);
 
@@ -1339,23 +1322,24 @@ static int igt_ctx_readonly(void *arg)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	err = igt_live_test_begin(&t, i915, __func__, "");
 	if (err)
-		goto out_unlock;
+		goto out_file;
 
 	ctx = live_context(i915, file);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
-		goto out_unlock;
+		goto out_file;
 	}
 
-	vm = ctx->vm ?: &i915->ggtt.alias->vm;
+	rcu_read_lock();
+	vm = rcu_dereference(ctx->vm) ?: &i915->ggtt.alias->vm;
 	if (!vm || !vm->has_read_only) {
+		rcu_read_unlock();
 		err = 0;
-		goto out_unlock;
+		goto out_file;
 	}
+	rcu_read_unlock();
 
 	ndwords = 0;
 	dw = 0;
@@ -1373,7 +1357,7 @@ static int igt_ctx_readonly(void *arg)
 				if (IS_ERR(obj)) {
 					err = PTR_ERR(obj);
 					i915_gem_context_unlock_engines(ctx);
-					goto out_unlock;
+					goto out_file;
 				}
 
 				if (prandom_u32_state(&prng) & 1)
@@ -1384,15 +1368,17 @@ static int igt_ctx_readonly(void *arg)
 			if (err) {
 				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) [full-ppgtt? %s], err=%d\n",
 				       ndwords, dw, max_dwords(obj),
-				       ce->engine->name, yesno(!!ctx->vm), err);
+				       ce->engine->name,
+				       yesno(!!rcu_access_pointer(ctx->vm)),
+				       err);
 				i915_gem_context_unlock_engines(ctx);
-				goto out_unlock;
+				goto out_file;
 			}
 
 			err = throttle(ce, tq, ARRAY_SIZE(tq));
 			if (err) {
 				i915_gem_context_unlock_engines(ctx);
-				goto out_unlock;
+				goto out_file;
 			}
 
 			if (++dw == max_dwords(obj)) {
@@ -1424,20 +1410,19 @@ static int igt_ctx_readonly(void *arg)
 		dw += rem;
 	}
 
-out_unlock:
+out_file:
 	throttle_release(tq, ARRAY_SIZE(tq));
 	if (igt_live_test_end(&t))
 		err = -EIO;
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	mock_file_free(i915, file);
 	return err;
 }
 
-static int check_scratch(struct i915_gem_context *ctx, u64 offset)
+static int check_scratch(struct i915_address_space *vm, u64 offset)
 {
 	struct drm_mm_node *node =
-		__drm_mm_interval_first(&ctx->vm->mm,
+		__drm_mm_interval_first(&vm->mm,
 					offset, offset + sizeof(u32) - 1);
 	if (!node || node->start > offset)
 		return 0;
@@ -1455,6 +1440,7 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 {
 	struct drm_i915_private *i915 = ctx->i915;
 	struct drm_i915_gem_object *obj;
+	struct i915_address_space *vm;
 	struct i915_request *rq;
 	struct i915_vma *vma;
 	u32 *cmd;
@@ -1487,17 +1473,18 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 
 	intel_gt_chipset_flush(engine->gt);
 
-	vma = i915_vma_instance(obj, ctx->vm, NULL);
+	vm = i915_gem_context_get_vm_rcu(ctx);
+	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
-		goto err;
+		goto err_vm;
 	}
 
 	err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_OFFSET_FIXED);
 	if (err)
-		goto err;
+		goto err_vm;
 
-	err = check_scratch(ctx, offset);
+	err = check_scratch(vm, offset);
 	if (err)
 		goto err_unpin;
 
@@ -1523,6 +1510,7 @@ static int write_to_scratch(struct i915_gem_context *ctx,
 
 	i915_request_add(rq);
 
+	i915_vm_put(vm);
 	return 0;
 
 skip_request:
@@ -1531,6 +1519,8 @@ err_request:
 	i915_request_add(rq);
 err_unpin:
 	i915_vma_unpin(vma);
+err_vm:
+	i915_vm_put(vm);
 err:
 	i915_gem_object_put(obj);
 	return err;
@@ -1542,6 +1532,7 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 {
 	struct drm_i915_private *i915 = ctx->i915;
 	struct drm_i915_gem_object *obj;
+	struct i915_address_space *vm;
 	const u32 RCS_GPR0 = 0x2600; /* not all engines have their own GPR! */
 	const u32 result = 0x100;
 	struct i915_request *rq;
@@ -1586,17 +1577,18 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 
 	intel_gt_chipset_flush(engine->gt);
 
-	vma = i915_vma_instance(obj, ctx->vm, NULL);
+	vm = i915_gem_context_get_vm_rcu(ctx);
+	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
-		goto err;
+		goto err_vm;
 	}
 
 	err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_OFFSET_FIXED);
 	if (err)
-		goto err;
+		goto err_vm;
 
-	err = check_scratch(ctx, offset);
+	err = check_scratch(vm, offset);
 	if (err)
 		goto err_unpin;
 
@@ -1627,12 +1619,12 @@ static int read_from_scratch(struct i915_gem_context *ctx,
 	err = i915_gem_object_set_to_cpu_domain(obj, false);
 	i915_gem_object_unlock(obj);
 	if (err)
-		goto err;
+		goto err_vm;
 
 	cmd = i915_gem_object_pin_map(obj, I915_MAP_WB);
 	if (IS_ERR(cmd)) {
 		err = PTR_ERR(cmd);
-		goto err;
+		goto err_vm;
 	}
 
 	*value = cmd[result / sizeof(*cmd)];
@@ -1647,6 +1639,8 @@ err_request:
 	i915_request_add(rq);
 err_unpin:
 	i915_vma_unpin(vma);
+err_vm:
+	i915_vm_put(vm);
 err:
 	i915_gem_object_put(obj);
 	return err;
@@ -1677,27 +1671,25 @@ static int igt_vm_isolation(void *arg)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	err = igt_live_test_begin(&t, i915, __func__, "");
 	if (err)
-		goto out_unlock;
+		goto out_file;
 
 	ctx_a = live_context(i915, file);
 	if (IS_ERR(ctx_a)) {
 		err = PTR_ERR(ctx_a);
-		goto out_unlock;
+		goto out_file;
 	}
 
 	ctx_b = live_context(i915, file);
 	if (IS_ERR(ctx_b)) {
 		err = PTR_ERR(ctx_b);
-		goto out_unlock;
+		goto out_file;
 	}
 
 	/* We can only test vm isolation, if the vm are distinct */
 	if (ctx_a->vm == ctx_b->vm)
-		goto out_unlock;
+		goto out_file;
 
 	vm_total = ctx_a->vm->total;
 	GEM_BUG_ON(ctx_b->vm->total != vm_total);
@@ -1726,7 +1718,7 @@ static int igt_vm_isolation(void *arg)
 				err = read_from_scratch(ctx_b, engine,
 							offset, &value);
 			if (err)
-				goto out_unlock;
+				goto out_file;
 
 			if (value) {
 				pr_err("%s: Read %08x from scratch (offset 0x%08x_%08x), after %lu reads!\n",
@@ -1735,7 +1727,7 @@ static int igt_vm_isolation(void *arg)
 				       lower_32_bits(offset),
 				       this);
 				err = -EINVAL;
-				goto out_unlock;
+				goto out_file;
 			}
 
 			this++;
@@ -1745,11 +1737,9 @@ static int igt_vm_isolation(void *arg)
 	pr_info("Checked %lu scratch offsets across %d engines\n",
 		count, RUNTIME_INFO(i915)->num_engines);
 
-out_unlock:
+out_file:
 	if (igt_live_test_end(&t))
 		err = -EIO;
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	mock_file_free(i915, file);
 	return err;
 }
@@ -1781,13 +1771,9 @@ static int mock_context_barrier(void *arg)
 	 * a request; useful for retiring old state after loading new.
 	 */
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	ctx = mock_context(i915, "mock");
-	if (!ctx) {
-		err = -ENOMEM;
-		goto unlock;
-	}
+	if (!ctx)
+		return -ENOMEM;
 
 	counter = 0;
 	err = context_barrier_task(ctx, 0,
@@ -1860,8 +1846,6 @@ static int mock_context_barrier(void *arg)
 
 out:
 	mock_context_close(ctx);
-unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 #undef pr_fmt
 #define pr_fmt(x) x
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
index 0104f16b1327..74ddd682c9cd 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
@@ -42,7 +42,10 @@ mock_context(struct drm_i915_private *i915,
 		if (!ppgtt)
 			goto err_put;
 
+		mutex_lock(&ctx->mutex);
 		__set_ppgtt(ctx, &ppgtt->vm);
+		mutex_unlock(&ctx->mutex);
+
 		i915_vm_put(&ppgtt->vm);
 	}
 
@@ -65,7 +68,7 @@ void mock_context_close(struct i915_gem_context *ctx)
 
 void mock_init_contexts(struct drm_i915_private *i915)
 {
-	init_contexts(i915);
+	init_contexts(&i915->gem.contexts);
 }
 
 struct i915_gem_context *
@@ -74,8 +77,6 @@ live_context(struct drm_i915_private *i915, struct drm_file *file)
 	struct i915_gem_context *ctx;
 	int err;
 
-	lockdep_assert_held(&i915->drm.struct_mutex);
-
 	ctx = i915_gem_create_context(i915, 0);
 	if (IS_ERR(ctx))
 		return ctx;
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 35a40c2820a2..be34d97ac18f 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -221,12 +221,20 @@ intel_context_init(struct intel_context *ce,
 		   struct i915_gem_context *ctx,
 		   struct intel_engine_cs *engine)
 {
+	struct i915_address_space *vm;
+
 	GEM_BUG_ON(!engine->cops);
 
 	kref_init(&ce->ref);
 
 	ce->gem_context = ctx;
-	ce->vm = i915_vm_get(ctx->vm ?: &engine->gt->ggtt->vm);
+	rcu_read_lock();
+	vm = rcu_dereference(ctx->vm);
+	if (vm)
+		ce->vm = i915_vm_get(vm);
+	else
+		ce->vm = i915_vm_get(&engine->gt->ggtt->vm);
+	rcu_read_unlock();
 	if (ctx->timeline)
 		ce->timeline = intel_timeline_get(ctx->timeline);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index 86cffbb0a9cb..7c838a57e174 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -155,13 +155,9 @@ static int live_context_size(void *arg)
 	 * HW tries to write past the end of one.
 	 */
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
-
 	fixme = kernel_context(gt->i915);
-	if (IS_ERR(fixme)) {
-		err = PTR_ERR(fixme);
-		goto unlock;
-	}
+	if (IS_ERR(fixme))
+		return PTR_ERR(fixme);
 
 	for_each_engine(engine, gt->i915, id) {
 		struct {
@@ -201,8 +197,6 @@ static int live_context_size(void *arg)
 	}
 
 	kernel_context_close(fixme);
-unlock:
-	mutex_unlock(&gt->i915->drm.struct_mutex);
 	return err;
 }
 
@@ -305,12 +299,10 @@ static int live_active_context(void *arg)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
-
 	fixme = live_context(gt->i915, file);
 	if (IS_ERR(fixme)) {
 		err = PTR_ERR(fixme);
-		goto unlock;
+		goto out_file;
 	}
 
 	for_each_engine(engine, gt->i915, id) {
@@ -323,8 +315,7 @@ static int live_active_context(void *arg)
 			break;
 	}
 
-unlock:
-	mutex_unlock(&gt->i915->drm.struct_mutex);
+out_file:
 	mock_file_free(gt->i915, file);
 	return err;
 }
@@ -418,12 +409,10 @@ static int live_remote_context(void *arg)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
-
 	fixme = live_context(gt->i915, file);
 	if (IS_ERR(fixme)) {
 		err = PTR_ERR(fixme);
-		goto unlock;
+		goto out_file;
 	}
 
 	for_each_engine(engine, gt->i915, id) {
@@ -436,8 +425,7 @@ static int live_remote_context(void *arg)
 			break;
 	}
 
-unlock:
-	mutex_unlock(&gt->i915->drm.struct_mutex);
+out_file:
 	mock_file_free(gt->i915, file);
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index ffbb3d23b887..e8a40df79bd0 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -58,9 +58,7 @@ static int hang_init(struct hang *h, struct intel_gt *gt)
 	memset(h, 0, sizeof(*h));
 	h->gt = gt;
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
 	h->ctx = kernel_context(gt->i915);
-	mutex_unlock(&gt->i915->drm.struct_mutex);
 	if (IS_ERR(h->ctx))
 		return PTR_ERR(h->ctx);
 
@@ -133,7 +131,7 @@ static struct i915_request *
 hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 {
 	struct intel_gt *gt = h->gt;
-	struct i915_address_space *vm = h->ctx->vm ?: &engine->gt->ggtt->vm;
+	struct i915_address_space *vm = i915_gem_context_get_vm_rcu(h->ctx);
 	struct drm_i915_gem_object *obj;
 	struct i915_request *rq = NULL;
 	struct i915_vma *hws, *vma;
@@ -143,12 +141,15 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 	int err;
 
 	obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
-	if (IS_ERR(obj))
+	if (IS_ERR(obj)) {
+		i915_vm_put(vm);
 		return ERR_CAST(obj);
+	}
 
 	vaddr = i915_gem_object_pin_map(obj, i915_coherent_map_type(gt->i915));
 	if (IS_ERR(vaddr)) {
 		i915_gem_object_put(obj);
+		i915_vm_put(vm);
 		return ERR_CAST(vaddr);
 	}
 
@@ -159,16 +160,22 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 	h->batch = vaddr;
 
 	vma = i915_vma_instance(h->obj, vm, NULL);
-	if (IS_ERR(vma))
+	if (IS_ERR(vma)) {
+		i915_vm_put(vm);
 		return ERR_CAST(vma);
+	}
 
 	hws = i915_vma_instance(h->hws, vm, NULL);
-	if (IS_ERR(hws))
+	if (IS_ERR(hws)) {
+		i915_vm_put(vm);
 		return ERR_CAST(hws);
+	}
 
 	err = i915_vma_pin(vma, 0, 0, PIN_USER);
-	if (err)
+	if (err) {
+		i915_vm_put(vm);
 		return ERR_PTR(err);
+	}
 
 	err = i915_vma_pin(hws, 0, 0, PIN_USER);
 	if (err)
@@ -266,6 +273,7 @@ unpin_hws:
 	i915_vma_unpin(hws);
 unpin_vma:
 	i915_vma_unpin(vma);
+	i915_vm_put(vm);
 	return err ? ERR_PTR(err) : rq;
 }
 
@@ -382,9 +390,7 @@ static int igt_reset_nop(void *arg)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
 	ctx = live_context(gt->i915, file);
-	mutex_unlock(&gt->i915->drm.struct_mutex);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto out;
@@ -458,9 +464,7 @@ static int igt_reset_nop_engine(void *arg)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
 	ctx = live_context(gt->i915, file);
-	mutex_unlock(&gt->i915->drm.struct_mutex);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto out;
@@ -705,9 +709,7 @@ static int active_engine(void *data)
 		return PTR_ERR(file);
 
 	for (count = 0; count < ARRAY_SIZE(ctx); count++) {
-		mutex_lock(&engine->i915->drm.struct_mutex);
 		ctx[count] = live_context(engine->i915, file);
-		mutex_unlock(&engine->i915->drm.struct_mutex);
 		if (IS_ERR(ctx[count])) {
 			err = PTR_ERR(ctx[count]);
 			while (--count)
@@ -1291,6 +1293,7 @@ static int igt_reset_evict_ppgtt(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct i915_gem_context *ctx;
+	struct i915_address_space *vm;
 	struct drm_file *file;
 	int err;
 
@@ -1298,18 +1301,20 @@ static int igt_reset_evict_ppgtt(void *arg)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&gt->i915->drm.struct_mutex);
 	ctx = live_context(gt->i915, file);
-	mutex_unlock(&gt->i915->drm.struct_mutex);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto out;
 	}
 
 	err = 0;
-	if (ctx->vm) /* aliasing == global gtt locking, covered above */
-		err = __igt_reset_evict_vma(gt, ctx->vm,
+	vm = i915_gem_context_get_vm_rcu(ctx);
+	if (!i915_is_ggtt(vm)) {
+		/* aliasing == global gtt locking, covered above */
+		err = __igt_reset_evict_vma(gt, vm,
 					    evict_vma, EXEC_OBJECT_WRITE);
+	}
+	i915_vm_put(vm);
 
 out:
 	mock_file_free(gt->i915, file);
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 04c1cf573642..8dc42c5c7569 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -1631,7 +1631,11 @@ static int smoke_submit(struct preempt_smoke *smoke,
 	int err = 0;
 
 	if (batch) {
-		vma = i915_vma_instance(batch, ctx->vm, NULL);
+		struct i915_address_space *vm;
+
+		vm = i915_gem_context_get_vm_rcu(ctx);
+		vma = i915_vma_instance(batch, vm, NULL);
+		i915_vm_put(vm);
 		if (IS_ERR(vma))
 			return PTR_ERR(vma);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 4ee2e2babd0d..7c7aceb85a74 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -260,7 +260,6 @@ switch_to_scratch_context(struct intel_engine_cs *engine,
 		rq = igt_spinner_create_request(spin, ce, MI_NOOP);
 
 	intel_context_put(ce);
-	kernel_context_close(ctx);
 
 	if (IS_ERR(rq)) {
 		spin = NULL;
@@ -279,6 +278,7 @@ err:
 	if (err && spin)
 		igt_spinner_end(spin);
 
+	kernel_context_close(ctx);
 	return err;
 }
 
@@ -355,6 +355,7 @@ out_ctx:
 static struct i915_vma *create_batch(struct i915_gem_context *ctx)
 {
 	struct drm_i915_gem_object *obj;
+	struct i915_address_space *vm;
 	struct i915_vma *vma;
 	int err;
 
@@ -362,7 +363,9 @@ static struct i915_vma *create_batch(struct i915_gem_context *ctx)
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
-	vma = i915_vma_instance(obj, ctx->vm, NULL);
+	vm = i915_gem_context_get_vm_rcu(ctx);
+	vma = i915_vma_instance(obj, vm, NULL);
+	i915_vm_put(vm);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err_obj;
@@ -463,12 +466,15 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 		0xffff00ff,
 		0xffffffff,
 	};
+	struct i915_address_space *vm;
 	struct i915_vma *scratch;
 	struct i915_vma *batch;
 	int err = 0, i, v;
 	u32 *cs, *results;
 
-	scratch = create_scratch(ctx->vm, 2 * ARRAY_SIZE(values) + 1);
+	vm = i915_gem_context_get_vm_rcu(ctx);
+	scratch = create_scratch(vm, 2 * ARRAY_SIZE(values) + 1);
+	i915_vm_put(vm);
 	if (IS_ERR(scratch))
 		return PTR_ERR(scratch);
 
@@ -1010,6 +1016,7 @@ static int live_isolated_whitelist(void *arg)
 		return 0;
 
 	for (i = 0; i < ARRAY_SIZE(client); i++) {
+		struct i915_address_space *vm;
 		struct i915_gem_context *c;
 
 		c = kernel_context(i915);
@@ -1018,22 +1025,27 @@ static int live_isolated_whitelist(void *arg)
 			goto err;
 		}
 
-		client[i].scratch[0] = create_scratch(c->vm, 1024);
+		vm = i915_gem_context_get_vm_rcu(c);
+
+		client[i].scratch[0] = create_scratch(vm, 1024);
 		if (IS_ERR(client[i].scratch[0])) {
 			err = PTR_ERR(client[i].scratch[0]);
+			i915_vm_put(vm);
 			kernel_context_close(c);
 			goto err;
 		}
 
-		client[i].scratch[1] = create_scratch(c->vm, 1024);
+		client[i].scratch[1] = create_scratch(vm, 1024);
 		if (IS_ERR(client[i].scratch[1])) {
 			err = PTR_ERR(client[i].scratch[1]);
 			i915_vma_unpin_and_release(&client[i].scratch[0], 0);
+			i915_vm_put(vm);
 			kernel_context_close(c);
 			goto err;
 		}
 
 		client[i].ctx = c;
+		i915_vm_put(vm);
 	}
 
 	for_each_engine(engine, i915, id) {
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 7052c90d937f..f6419f0bd4fd 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -365,7 +365,8 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 					  struct i915_gem_context *ctx)
 {
 	struct intel_vgpu_mm *mm = workload->shadow_mm;
-	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(ctx->vm);
+	struct i915_ppgtt *ppgtt =
+		i915_vm_to_ppgtt(i915_gem_context_get_vm_rcu(ctx));
 	int i = 0;
 
 	if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) {
@@ -378,6 +379,8 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 			px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i];
 		}
 	}
+
+	i915_vm_put(&ppgtt->vm);
 }
 
 static int
@@ -1213,20 +1216,18 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx;
+	struct i915_ppgtt *ppgtt;
 	enum intel_engine_id i;
 	int ret;
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	ctx = i915_gem_context_create_kernel(i915, I915_PRIORITY_MAX);
-	if (IS_ERR(ctx)) {
-		ret = PTR_ERR(ctx);
-		goto out_unlock;
-	}
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
 
 	i915_gem_context_set_force_single_submission(ctx);
 
-	i915_context_ppgtt_root_save(s, i915_vm_to_ppgtt(ctx->vm));
+	ppgtt = i915_vm_to_ppgtt(i915_gem_context_get_vm_rcu(ctx));
+	i915_context_ppgtt_root_save(s, ppgtt);
 
 	for_each_engine(engine, i915, i) {
 		struct intel_context *ce;
@@ -1271,12 +1272,12 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu)
 	atomic_set(&s->running_workload_num, 0);
 	bitmap_zero(s->tlb_handle_pending, I915_NUM_ENGINES);
 
+	i915_vm_put(&ppgtt->vm);
 	i915_gem_context_put(ctx);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return 0;
 
 out_shadow_ctx:
-	i915_context_ppgtt_root_restore(s, i915_vm_to_ppgtt(ctx->vm));
+	i915_context_ppgtt_root_restore(s, ppgtt);
 	for_each_engine(engine, i915, i) {
 		if (IS_ERR(s->shadow[i]))
 			break;
@@ -1284,9 +1285,8 @@ out_shadow_ctx:
 		intel_context_unpin(s->shadow[i]);
 		intel_context_put(s->shadow[i]);
 	}
+	i915_vm_put(&ppgtt->vm);
 	i915_gem_context_put(ctx);
-out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 0e90ac608e07..b04cebc26eca 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -316,12 +316,18 @@ static void print_context_stats(struct seq_file *m,
 				struct drm_i915_private *i915)
 {
 	struct file_stats kstats = {};
-	struct i915_gem_context *ctx;
+	struct i915_gem_context *ctx, *cn;
 
-	list_for_each_entry(ctx, &i915->contexts.list, link) {
+	spin_lock(&i915->gem.contexts.lock);
+	list_for_each_entry_safe(ctx, cn, &i915->gem.contexts.list, link) {
 		struct i915_gem_engines_iter it;
 		struct intel_context *ce;
 
+		if (!kref_get_unless_zero(&ctx->ref))
+			continue;
+
+		spin_unlock(&i915->gem.contexts.lock);
+
 		for_each_gem_engine(ce,
 				    i915_gem_context_lock_engines(ctx), it) {
 			intel_context_lock_pinned(ce);
@@ -338,7 +344,9 @@ static void print_context_stats(struct seq_file *m,
 		i915_gem_context_unlock_engines(ctx);
 
 		if (!IS_ERR_OR_NULL(ctx->file_priv)) {
-			struct file_stats stats = { .vm = ctx->vm, };
+			struct file_stats stats = {
+				.vm = rcu_access_pointer(ctx->vm),
+			};
 			struct drm_file *file = ctx->file_priv->file;
 			struct task_struct *task;
 			char name[80];
@@ -355,7 +363,12 @@ static void print_context_stats(struct seq_file *m,
 
 			print_file_stats(m, name, stats);
 		}
+
+		spin_lock(&i915->gem.contexts.lock);
+		list_safe_reset_next(ctx, cn, link);
+		i915_gem_context_put(ctx);
 	}
+	spin_unlock(&i915->gem.contexts.lock);
 
 	print_file_stats(m, "[k]contexts", kstats);
 }
@@ -363,7 +376,6 @@ static void print_context_stats(struct seq_file *m,
 static int i915_gem_object_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *i915 = node_to_i915(m->private);
-	int ret;
 
 	seq_printf(m, "%u shrinkable [%u free] objects, %llu bytes\n",
 		   i915->mm.shrink_count,
@@ -372,12 +384,7 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 
 	seq_putc(m, '\n');
 
-	ret = mutex_lock_interruptible(&i915->drm.struct_mutex);
-	if (ret)
-		return ret;
-
 	print_context_stats(m, i915);
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	return 0;
 }
@@ -1579,19 +1586,19 @@ static void describe_ctx_ring(struct seq_file *m, struct intel_ring *ring)
 
 static int i915_context_status(struct seq_file *m, void *unused)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct i915_gem_context *ctx;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
+	struct drm_i915_private *i915 = node_to_i915(m->private);
+	struct i915_gem_context *ctx, *cn;
 
-	list_for_each_entry(ctx, &dev_priv->contexts.list, link) {
+	spin_lock(&i915->gem.contexts.lock);
+	list_for_each_entry_safe(ctx, cn, &i915->gem.contexts.list, link) {
 		struct i915_gem_engines_iter it;
 		struct intel_context *ce;
 
+		if (!kref_get_unless_zero(&ctx->ref))
+			continue;
+
+		spin_unlock(&i915->gem.contexts.lock);
+
 		seq_puts(m, "HW context ");
 		if (ctx->pid) {
 			struct task_struct *task;
@@ -1626,9 +1633,12 @@ static int i915_context_status(struct seq_file *m, void *unused)
 		i915_gem_context_unlock_engines(ctx);
 
 		seq_putc(m, '\n');
-	}
 
-	mutex_unlock(&dev->struct_mutex);
+		spin_lock(&i915->gem.contexts.lock);
+		list_safe_reset_next(ctx, cn, link);
+		i915_gem_context_put(ctx);
+	}
+	spin_unlock(&i915->gem.contexts.lock);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index b711324ca294..5183a40d3860 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1702,10 +1702,8 @@ static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv = file->driver_priv;
 
-	mutex_lock(&dev->struct_mutex);
 	i915_gem_context_close(file);
 	i915_gem_release(dev, file);
-	mutex_unlock(&dev->struct_mutex);
 
 	kfree_rcu(file_priv, rcu);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 6bdcffbf1b9b..35b610d52379 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1536,13 +1536,6 @@ struct drm_i915_private {
 	int audio_power_refcount;
 	u32 audio_freq_cntrl;
 
-	struct {
-		struct mutex mutex;
-		struct list_head list;
-		struct llist_head free_list;
-		struct work_struct free_work;
-	} contexts;
-
 	u32 fdi_rx_config;
 
 	/* Shadow for DISPLAY_PHY_CONTROL which can't be safely read */
@@ -1698,6 +1691,14 @@ struct drm_i915_private {
 
 	struct {
 		struct notifier_block pm_notifier;
+
+		struct i915_gem_contexts {
+			spinlock_t lock; /* locks list */
+			struct list_head list;
+
+			struct llist_head free_list;
+			struct work_struct free_work;
+		} contexts;
 	} gem;
 
 	/* For i945gm vblank irq vs. C3 workaround */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index a1077919b16a..b6d279987b71 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1266,7 +1266,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 		goto err_unlock;
 	}
 
-	ret = i915_gem_contexts_init(dev_priv);
+	ret = i915_gem_init_contexts(dev_priv);
 	if (ret) {
 		GEM_BUG_ON(ret == -EIO);
 		goto err_scratch;
@@ -1348,7 +1348,7 @@ err_uc_init:
 	}
 err_context:
 	if (ret != -EIO)
-		i915_gem_contexts_fini(dev_priv);
+		i915_gem_driver_release__contexts(dev_priv);
 err_scratch:
 	intel_gt_driver_release(&dev_priv->gt);
 err_unlock:
@@ -1416,11 +1416,9 @@ void i915_gem_driver_remove(struct drm_i915_private *dev_priv)
 
 void i915_gem_driver_release(struct drm_i915_private *dev_priv)
 {
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_engines_cleanup(dev_priv);
-	i915_gem_contexts_fini(dev_priv);
+	i915_gem_driver_release__contexts(dev_priv);
 	intel_gt_driver_release(&dev_priv->gt);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	intel_wa_list_free(&dev_priv->gt_wa_list);
 
@@ -1430,7 +1428,7 @@ void i915_gem_driver_release(struct drm_i915_private *dev_priv)
 
 	i915_gem_drain_freed_objects(dev_priv);
 
-	WARN_ON(!list_empty(&dev_priv->contexts.list));
+	WARN_ON(!list_empty(&dev_priv->gem.contexts.list));
 }
 
 void i915_gem_init_mmio(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 1d26634ca597..7b15bb891970 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1366,7 +1366,9 @@ static int gen8_init_scratch(struct i915_address_space *vm)
 	if (vm->has_read_only &&
 	    vm->i915->kernel_context &&
 	    vm->i915->kernel_context->vm) {
-		struct i915_address_space *clone = vm->i915->kernel_context->vm;
+		struct i915_address_space *clone =
+			rcu_dereference_protected(vm->i915->kernel_context->vm,
+						  true); /* static */
 
 		GEM_BUG_ON(!clone->has_read_only);
 
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index ecfbc37b738b..231388d06c82 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1853,8 +1853,8 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 	};
 #undef ctx_flexeuN
 	struct intel_engine_cs *engine;
-	struct i915_gem_context *ctx;
-	int i;
+	struct i915_gem_context *ctx, *cn;
+	int i, err;
 
 	for (i = 2; i < ARRAY_SIZE(regs); i++)
 		regs[i].value = oa_config_flex_reg(oa_config, regs[i].reg);
@@ -1877,16 +1877,27 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 	 * context. Contexts idle at the time of reconfiguration are not
 	 * trapped behind the barrier.
 	 */
-	list_for_each_entry(ctx, &i915->contexts.list, link) {
-		int err;
-
+	spin_lock(&i915->gem.contexts.lock);
+	list_for_each_entry_safe(ctx, cn, &i915->gem.contexts.list, link) {
 		if (ctx == i915->kernel_context)
 			continue;
 
+		if (!kref_get_unless_zero(&ctx->ref))
+			continue;
+
+		spin_unlock(&i915->gem.contexts.lock);
+
 		err = gen8_configure_context(ctx, regs, ARRAY_SIZE(regs));
-		if (err)
+		if (err) {
+			i915_gem_context_put(ctx);
 			return err;
+		}
+
+		spin_lock(&i915->gem.contexts.lock);
+		list_safe_reset_next(ctx, cn, link);
+		i915_gem_context_put(ctx);
 	}
+	spin_unlock(&i915->gem.contexts.lock);
 
 	/*
 	 * After updating all other contexts, we need to modify ourselves.
@@ -1895,7 +1906,6 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 	 */
 	for_each_uabi_engine(engine, i915) {
 		struct intel_context *ce = engine->kernel_context;
-		int err;
 
 		if (engine->class != RENDER_CLASS)
 			continue;
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index 1e08c5961535..bf039b8ba593 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -176,16 +176,12 @@ i915_l3_read(struct file *filp, struct kobject *kobj,
 	count = min_t(size_t, GEN7_L3LOG_SIZE - offset, count);
 	memset(buf, 0, count);
 
-	ret = i915_mutex_lock_interruptible(&i915->drm);
-	if (ret)
-		return ret;
-
+	spin_lock(&i915->gem.contexts.lock);
 	if (i915->l3_parity.remap_info[slice])
 		memcpy(buf,
 		       i915->l3_parity.remap_info[slice] + offset / sizeof(u32),
 		       count);
-
-	mutex_unlock(&i915->drm.struct_mutex);
+	spin_unlock(&i915->gem.contexts.lock);
 
 	return count;
 }
@@ -198,8 +194,8 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	struct device *kdev = kobj_to_dev(kobj);
 	struct drm_i915_private *i915 = kdev_minor_to_i915(kdev);
 	int slice = (int)(uintptr_t)attr->private;
+	u32 *remap_info, *freeme = NULL;
 	struct i915_gem_context *ctx;
-	u32 **remap_info;
 	int ret;
 
 	ret = l3_access_valid(i915, offset);
@@ -209,37 +205,36 @@ i915_l3_write(struct file *filp, struct kobject *kobj,
 	if (count < sizeof(u32))
 		return -EINVAL;
 
-	ret = i915_mutex_lock_interruptible(&i915->drm);
-	if (ret)
-		return ret;
+	remap_info = kzalloc(GEN7_L3LOG_SIZE, GFP_KERNEL);
+	if (!remap_info)
+		return -ENOMEM;
 
-	remap_info = &i915->l3_parity.remap_info[slice];
-	if (!*remap_info) {
-		*remap_info = kzalloc(GEN7_L3LOG_SIZE, GFP_KERNEL);
-		if (!*remap_info) {
-			ret = -ENOMEM;
-			goto out;
-		}
+	spin_lock(&i915->gem.contexts.lock);
+
+	if (i915->l3_parity.remap_info[slice]) {
+		freeme = remap_info;
+		remap_info = i915->l3_parity.remap_info[slice];
+	} else {
+		i915->l3_parity.remap_info[slice] = remap_info;
 	}
 
 	count = round_down(count, sizeof(u32));
-	memcpy(*remap_info + offset / sizeof(u32), buf, count);
+	memcpy(remap_info + offset / sizeof(u32), buf, count);
 
 	/* NB: We defer the remapping until we switch to the context */
-	list_for_each_entry(ctx, &i915->contexts.list, link)
+	list_for_each_entry(ctx, &i915->gem.contexts.list, link)
 		ctx->remap_slice |= BIT(slice);
 
+	spin_unlock(&i915->gem.contexts.lock);
+	kfree(freeme);
+
 	/*
 	 * TODO: Ideally we really want a GPU reset here to make sure errors
 	 * aren't propagated. Since I cannot find a stable way to reset the GPU
 	 * at this point it is left as a TODO.
 	*/
 
-	ret = count;
-out:
-	mutex_unlock(&i915->drm.struct_mutex);
-
-	return ret;
+	return count;
 }
 
 static const struct bin_attribute dpf_attrs = {
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 1f2cf6cfafb5..7ef7a1e1664c 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -952,7 +952,7 @@ DECLARE_EVENT_CLASS(i915_context,
 	TP_fast_assign(
 			__entry->dev = ctx->i915->drm.primary->index;
 			__entry->ctx = ctx;
-			__entry->vm = ctx->vm;
+			__entry->vm = rcu_access_pointer(ctx->vm);
 	),
 
 	TP_printk("dev=%u, ctx=%p, ctx_vm=%p",
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index 0346c3e5b6b6..bfa40a5b6d98 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -138,11 +138,9 @@ static int igt_gem_suspend(void *arg)
 		return PTR_ERR(file);
 
 	err = -ENOMEM;
-	mutex_lock(&i915->drm.struct_mutex);
 	ctx = live_context(i915, file);
 	if (!IS_ERR(ctx))
 		err = switch_to_context(i915, ctx);
-	mutex_unlock(&i915->drm.struct_mutex);
 	if (err)
 		goto out;
 
@@ -157,9 +155,7 @@ static int igt_gem_suspend(void *arg)
 
 	pm_resume(i915);
 
-	mutex_lock(&i915->drm.struct_mutex);
 	err = switch_to_context(i915, ctx);
-	mutex_unlock(&i915->drm.struct_mutex);
 out:
 	mock_file_free(i915, file);
 	return err;
@@ -177,11 +173,9 @@ static int igt_gem_hibernate(void *arg)
 		return PTR_ERR(file);
 
 	err = -ENOMEM;
-	mutex_lock(&i915->drm.struct_mutex);
 	ctx = live_context(i915, file);
 	if (!IS_ERR(ctx))
 		err = switch_to_context(i915, ctx);
-	mutex_unlock(&i915->drm.struct_mutex);
 	if (err)
 		goto out;
 
@@ -196,9 +190,7 @@ static int igt_gem_hibernate(void *arg)
 
 	pm_resume(i915);
 
-	mutex_lock(&i915->drm.struct_mutex);
 	err = switch_to_context(i915, ctx);
-	mutex_unlock(&i915->drm.struct_mutex);
 out:
 	mock_file_free(i915, file);
 	return err;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index f39f0282e78c..0af9a58d011d 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -473,7 +473,6 @@ static int igt_evict_contexts(void *arg)
 		}
 
 		count = 0;
-		mutex_lock(&i915->drm.struct_mutex);
 		onstack_fence_init(&fence);
 		do {
 			struct i915_request *rq;
@@ -510,8 +509,6 @@ static int igt_evict_contexts(void *arg)
 			count++;
 			err = 0;
 		} while(1);
-		mutex_unlock(&i915->drm.struct_mutex);
-
 		onstack_fence_fini(&fence);
 		pr_info("Submitted %lu contexts/requests on %s\n",
 			count, engine->name);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index e40e6cfa51f1..8d8121c02161 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1246,6 +1246,7 @@ static int exercise_mock(struct drm_i915_private *i915,
 				     unsigned long end_time))
 {
 	const u64 limit = totalram_pages() << PAGE_SHIFT;
+	struct i915_address_space *vm;
 	struct i915_gem_context *ctx;
 	IGT_TIMEOUT(end_time);
 	int err;
@@ -1254,7 +1255,9 @@ static int exercise_mock(struct drm_i915_private *i915,
 	if (!ctx)
 		return -ENOMEM;
 
-	err = func(i915, ctx->vm, 0, min(ctx->vm->total, limit), end_time);
+	vm = i915_gem_context_get_vm_rcu(ctx);
+	err = func(i915, vm, 0, min(vm->total, limit), end_time);
+	i915_vm_put(vm);
 
 	mock_context_close(ctx);
 	return err;
@@ -1801,15 +1804,15 @@ static int igt_cs_tlb(void *arg)
 		goto out_unlock;
 	}
 
-	vm = ctx->vm;
-	if (!vm)
-		goto out_unlock;
+	vm = i915_gem_context_get_vm_rcu(ctx);
+	if (i915_is_ggtt(vm))
+		goto out_vm;
 
 	/* Create two pages; dummy we prefill the TLB, and intended */
 	bbe = i915_gem_object_create_internal(i915, PAGE_SIZE);
 	if (IS_ERR(bbe)) {
 		err = PTR_ERR(bbe);
-		goto out_unlock;
+		goto out_vm;
 	}
 
 	batch = i915_gem_object_pin_map(bbe, I915_MAP_WC);
@@ -2014,6 +2017,8 @@ out_put_act:
 	i915_gem_object_put(act);
 out_put_bbe:
 	i915_gem_object_put(bbe);
+out_vm:
+	i915_vm_put(vm);
 out_unlock:
 	mutex_unlock(&i915->drm.struct_mutex);
 	mock_file_free(i915, file);
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index d7d68c6a6bd5..0897a7b04944 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -181,9 +181,7 @@ static int igt_request_rewind(void *arg)
 	struct intel_context *ce;
 	int err = -EINVAL;
 
-	mutex_lock(&i915->drm.struct_mutex);
 	ctx[0] = mock_context(i915, "A");
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	ce = i915_gem_context_get_engine(ctx[0], RCS0);
 	GEM_BUG_ON(IS_ERR(ce));
@@ -197,9 +195,7 @@ static int igt_request_rewind(void *arg)
 	i915_request_get(request);
 	i915_request_add(request);
 
-	mutex_lock(&i915->drm.struct_mutex);
 	ctx[1] = mock_context(i915, "B");
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	ce = i915_gem_context_get_engine(ctx[1], RCS0);
 	GEM_BUG_ON(IS_ERR(ce));
@@ -438,9 +434,7 @@ static int mock_breadcrumbs_smoketest(void *arg)
 	}
 
 	for (n = 0; n < t.ncontexts; n++) {
-		mutex_lock(&t.engine->i915->drm.struct_mutex);
 		t.contexts[n] = mock_context(t.engine->i915, "mock");
-		mutex_unlock(&t.engine->i915->drm.struct_mutex);
 		if (!t.contexts[n]) {
 			ret = -ENOMEM;
 			goto out_contexts;
@@ -734,9 +728,9 @@ out_batch:
 static struct i915_vma *recursive_batch(struct drm_i915_private *i915)
 {
 	struct i915_gem_context *ctx = i915->kernel_context;
-	struct i915_address_space *vm = ctx->vm ?: &i915->ggtt.vm;
 	struct drm_i915_gem_object *obj;
 	const int gen = INTEL_GEN(i915);
+	struct i915_address_space *vm;
 	struct i915_vma *vma;
 	u32 *cmd;
 	int err;
@@ -745,7 +739,9 @@ static struct i915_vma *recursive_batch(struct drm_i915_private *i915)
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
+	vm = i915_gem_context_get_vm_rcu(ctx);
 	vma = i915_vma_instance(obj, vm, NULL);
+	i915_vm_put(vm);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err;
@@ -1220,9 +1216,7 @@ static int live_breadcrumbs_smoketest(void *arg)
 	}
 
 	for (n = 0; n < t[0].ncontexts; n++) {
-		mutex_lock(&i915->drm.struct_mutex);
 		t[0].contexts[n] = live_context(i915, file);
-		mutex_unlock(&i915->drm.struct_mutex);
 		if (!t[0].contexts[n]) {
 			ret = -ENOMEM;
 			goto out_contexts;
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index ac1ff558eb90..58b5f40a07dd 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -24,6 +24,7 @@
 
 #include <linux/prime_numbers.h>
 
+#include "gem/i915_gem_context.h"
 #include "gem/selftests/mock_context.h"
 
 #include "i915_scatterlist.h"
@@ -38,7 +39,7 @@ static bool assert_vma(struct i915_vma *vma,
 {
 	bool ok = true;
 
-	if (vma->vm != ctx->vm) {
+	if (vma->vm != rcu_access_pointer(ctx->vm)) {
 		pr_err("VMA created with wrong VM\n");
 		ok = false;
 	}
@@ -113,11 +114,13 @@ static int create_vmas(struct drm_i915_private *i915,
 	list_for_each_entry(obj, objects, st_link) {
 		for (pinned = 0; pinned <= 1; pinned++) {
 			list_for_each_entry(ctx, contexts, link) {
-				struct i915_address_space *vm = ctx->vm;
+				struct i915_address_space *vm;
 				struct i915_vma *vma;
 				int err;
 
+				vm = i915_gem_context_get_vm_rcu(ctx);
 				vma = checked_vma_instance(obj, vm, NULL);
+				i915_vm_put(vm);
 				if (IS_ERR(vma))
 					return PTR_ERR(vma);
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 4e6cde0d4859..335f37ba98de 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -59,11 +59,9 @@ static void mock_device_release(struct drm_device *dev)
 
 	i915_gem_drain_workqueue(i915);
 
-	mutex_lock(&i915->drm.struct_mutex);
 	for_each_engine(engine, i915, id)
 		mock_engine_free(engine);
-	i915_gem_contexts_fini(i915);
-	mutex_unlock(&i915->drm.struct_mutex);
+	i915_gem_driver_release__contexts(i915);
 
 	intel_timelines_fini(i915);
 
@@ -206,7 +204,7 @@ struct drm_i915_private *mock_gem_device(void)
 	return i915;
 
 err_context:
-	i915_gem_contexts_fini(i915);
+	i915_gem_driver_release__contexts(i915);
 err_engine:
 	mock_engine_free(i915->engine[RCS0]);
 err_unlock:
-- 
cgit v1.2.3


From cb5eb072788faea188bfabcee0bfb90ecc717e82 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:10 +0100
Subject: drm/i915/overlay: Drop struct_mutex guard

The overlay uses the modeset mutex to control itself and only required
the struct_mutex for requests, which is now obsolete.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-16-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/display/intel_display.c |  7 +------
 drivers/gpu/drm/i915/display/intel_overlay.c | 13 -------------
 drivers/gpu/drm/i915/gt/intel_reset.c        |  4 ----
 3 files changed, 1 insertion(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 8f7365b8dffb..f3a94a9cff16 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -5738,13 +5738,8 @@ void hsw_disable_ips(const struct intel_crtc_state *crtc_state)
 
 static void intel_crtc_dpms_overlay_disable(struct intel_crtc *intel_crtc)
 {
-	if (intel_crtc->overlay) {
-		struct drm_device *dev = intel_crtc->base.dev;
-
-		mutex_lock(&dev->struct_mutex);
+	if (intel_crtc->overlay)
 		(void) intel_overlay_switch_off(intel_crtc->overlay);
-		mutex_unlock(&dev->struct_mutex);
-	}
 
 	/* Let userspace switch the overlay on again. In most cases userspace
 	 * has to recompute where to put it anyway.
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index e12e1a753af0..daea112cbb87 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -439,8 +439,6 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
 	struct i915_request *rq;
 	u32 *cs;
 
-	lockdep_assert_held(&dev_priv->drm.struct_mutex);
-
 	/*
 	 * Only wait if there is actually an old frame to release to
 	 * guarantee forward progress.
@@ -751,7 +749,6 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	struct i915_vma *vma;
 	int ret, tmp_width;
 
-	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 	WARN_ON(!drm_modeset_is_locked(&dev_priv->drm.mode_config.connection_mutex));
 
 	ret = intel_overlay_release_old_vid(overlay);
@@ -852,7 +849,6 @@ int intel_overlay_switch_off(struct intel_overlay *overlay)
 	struct drm_i915_private *dev_priv = overlay->i915;
 	int ret;
 
-	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 	WARN_ON(!drm_modeset_is_locked(&dev_priv->drm.mode_config.connection_mutex));
 
 	ret = intel_overlay_recover_from_interrupt(overlay);
@@ -1068,11 +1064,7 @@ int intel_overlay_put_image_ioctl(struct drm_device *dev, void *data,
 
 	if (!(params->flags & I915_OVERLAY_ENABLE)) {
 		drm_modeset_lock_all(dev);
-		mutex_lock(&dev->struct_mutex);
-
 		ret = intel_overlay_switch_off(overlay);
-
-		mutex_unlock(&dev->struct_mutex);
 		drm_modeset_unlock_all(dev);
 
 		return ret;
@@ -1088,7 +1080,6 @@ int intel_overlay_put_image_ioctl(struct drm_device *dev, void *data,
 		return -ENOENT;
 
 	drm_modeset_lock_all(dev);
-	mutex_lock(&dev->struct_mutex);
 
 	if (i915_gem_object_is_tiled(new_bo)) {
 		DRM_DEBUG_KMS("buffer used for overlay image can not be tiled\n");
@@ -1152,14 +1143,12 @@ int intel_overlay_put_image_ioctl(struct drm_device *dev, void *data,
 	if (ret != 0)
 		goto out_unlock;
 
-	mutex_unlock(&dev->struct_mutex);
 	drm_modeset_unlock_all(dev);
 	i915_gem_object_put(new_bo);
 
 	return 0;
 
 out_unlock:
-	mutex_unlock(&dev->struct_mutex);
 	drm_modeset_unlock_all(dev);
 	i915_gem_object_put(new_bo);
 
@@ -1233,7 +1222,6 @@ int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data,
 	}
 
 	drm_modeset_lock_all(dev);
-	mutex_lock(&dev->struct_mutex);
 
 	ret = -EINVAL;
 	if (!(attrs->flags & I915_OVERLAY_UPDATE_ATTRS)) {
@@ -1290,7 +1278,6 @@ int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data,
 
 	ret = 0;
 out_unlock:
-	mutex_unlock(&dev->struct_mutex);
 	drm_modeset_unlock_all(dev);
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 055496f0825f..7b3d9d4517a0 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -1288,10 +1288,6 @@ int intel_gt_terminally_wedged(struct intel_gt *gt)
 	if (!test_bit(I915_RESET_BACKOFF, &gt->reset.flags))
 		return -EIO;
 
-	/* XXX intel_reset_finish() still takes struct_mutex!!! */
-	if (mutex_is_locked(&gt->i915->drm.struct_mutex))
-		return -EAGAIN;
-
 	if (wait_event_interruptible(gt->reset.queue,
 				     !test_bit(I915_RESET_BACKOFF,
 					       &gt->reset.flags)))
-- 
cgit v1.2.3


From ba198a10bfbeb1137d8c25fa569b562e8b626b05 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:11 +0100
Subject: drm/i915: Drop struct_mutex guard from debugfs/framebuffer_info

It protects nothing being accessed for the intel_framebuffer, so it's
own locking had better be sufficient.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-17-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_debugfs.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index b04cebc26eca..77933b23070e 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1534,11 +1534,6 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 	struct drm_device *dev = &dev_priv->drm;
 	struct intel_framebuffer *fbdev_fb = NULL;
 	struct drm_framebuffer *drm_fb;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 #ifdef CONFIG_DRM_FBDEV_EMULATION
 	if (dev_priv->fbdev && dev_priv->fbdev->helper.fb) {
@@ -1573,7 +1568,6 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 		seq_putc(m, '\n');
 	}
 	mutex_unlock(&dev->mode_config.fb_lock);
-	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 6c3828ab098a8091c0fa8a24d1af8a5b779b6b4d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:12 +0100
Subject: drm/i915: Remove struct_mutex guard for debugfs/opregion

Having a struct_mutex around the read of a BIOS blob serves no purpose.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-18-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_debugfs.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 77933b23070e..298a3e879e65 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1500,21 +1500,11 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 
 static int i915_opregion(struct seq_file *m, void *unused)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct intel_opregion *opregion = &dev_priv->opregion;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		goto out;
+	struct intel_opregion *opregion = &node_to_i915(m->private)->opregion;
 
 	if (opregion->header)
 		seq_write(m, opregion->header, OPREGION_SIZE);
 
-	mutex_unlock(&dev->struct_mutex);
-
-out:
 	return 0;
 }
 
-- 
cgit v1.2.3


From 3d88f76dec55321d27bd37204ea9eaa44f7485b8 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:13 +0100
Subject: drm/i915: Drop struct_mutex from suspend state save/restore

struct_mutex provides no serialisation of the registers and data
structures being saved and restored across suspend/resume. It is
completely superfluous here.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-19-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_suspend.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index 2b2086def0f1..8812cdd9007f 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -66,8 +66,6 @@ int i915_save_state(struct drm_i915_private *dev_priv)
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	int i;
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
-
 	i915_save_display(dev_priv);
 
 	if (IS_GEN(dev_priv, 4))
@@ -101,8 +99,6 @@ int i915_save_state(struct drm_i915_private *dev_priv)
 			dev_priv->regfile.saveSWF3[i] = I915_READ(SWF3(i));
 	}
 
-	mutex_unlock(&dev_priv->drm.struct_mutex);
-
 	return 0;
 }
 
@@ -111,8 +107,6 @@ int i915_restore_state(struct drm_i915_private *dev_priv)
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	int i;
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
-
 	if (IS_GEN(dev_priv, 4))
 		pci_write_config_word(pdev, GCDGMBUS,
 				      dev_priv->regfile.saveGCDGMBUS);
@@ -146,8 +140,6 @@ int i915_restore_state(struct drm_i915_private *dev_priv)
 			I915_WRITE(SWF3(i), dev_priv->regfile.saveSWF3[i]);
 	}
 
-	mutex_unlock(&dev_priv->drm.struct_mutex);
-
 	intel_gmbus_reset(dev_priv);
 
 	return 0;
-- 
cgit v1.2.3


From 2af402982ab38223356250d81741ae041c831a79 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:14 +0100
Subject: drm/i915/selftests: Drop vestigal struct_mutex guards

We no longer need struct_mutex to serialise request emission, so remove
it from the gt selftests.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-20-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/selftests/huge_pages.c    |  15 +--
 .../gpu/drm/i915/gem/selftests/i915_gem_context.c  |   4 -
 drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c |   2 -
 drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c |   2 -
 drivers/gpu/drm/i915/gt/selftest_lrc.c             | 148 ++++-----------------
 drivers/gpu/drm/i915/gt/selftest_workarounds.c     |  11 +-
 drivers/gpu/drm/i915/gt/uc/selftest_guc.c          |   4 -
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c      |   2 -
 8 files changed, 27 insertions(+), 161 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 3314858f3046..e42abddd4a36 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -1639,7 +1639,6 @@ int i915_gem_huge_page_mock_selftests(void)
 	mkwrite_device_info(dev_priv)->ppgtt_type = INTEL_PPGTT_FULL;
 	mkwrite_device_info(dev_priv)->ppgtt_size = 48;
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	ppgtt = i915_ppgtt_create(dev_priv);
 	if (IS_ERR(ppgtt)) {
 		err = PTR_ERR(ppgtt);
@@ -1665,9 +1664,7 @@ out_close:
 	i915_vm_put(&ppgtt->vm);
 
 out_unlock:
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 	drm_dev_put(&dev_priv->drm);
-
 	return err;
 }
 
@@ -1684,7 +1681,6 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 	struct drm_file *file;
 	struct i915_gem_context *ctx;
 	struct i915_address_space *vm;
-	intel_wakeref_t wakeref;
 	int err;
 
 	if (!HAS_PPGTT(i915)) {
@@ -1699,13 +1695,10 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	ctx = live_context(i915, file);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
-		goto out_unlock;
+		goto out_file;
 	}
 
 	mutex_lock(&ctx->mutex);
@@ -1716,11 +1709,7 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 
 	err = i915_subtests(tests, ctx);
 
-out_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
-
+out_file:
 	mock_file_free(i915, file);
-
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index d44fa9d356f1..fb58c0919ea1 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -307,9 +307,7 @@ static int live_parallel_switch(void *arg)
 		struct igt_live_test t;
 		int n;
 
-		mutex_lock(&i915->drm.struct_mutex);
 		err = igt_live_test_begin(&t, i915, __func__, "");
-		mutex_unlock(&i915->drm.struct_mutex);
 		if (err)
 			break;
 
@@ -341,10 +339,8 @@ static int live_parallel_switch(void *arg)
 			data[n].tsk = NULL;
 		}
 
-		mutex_lock(&i915->drm.struct_mutex);
 		if (igt_live_test_end(&t))
 			err = -EIO;
-		mutex_unlock(&i915->drm.struct_mutex);
 	}
 
 out:
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 1cd25cfd0246..cfa52c525691 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -669,9 +669,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 			goto out;
 		}
 
-		mutex_lock(&i915->drm.struct_mutex);
 		err = make_obj_busy(obj);
-		mutex_unlock(&i915->drm.struct_mutex);
 		if (err) {
 			pr_err("[loop %d] Failed to busy the object\n", loop);
 			goto err_obj;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c
index 94a15e3f6db8..34932871b3a5 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_phys.c
@@ -25,9 +25,7 @@ static int mock_phys_object(void *arg)
 		goto out;
 	}
 
-	mutex_lock(&i915->drm.struct_mutex);
 	err = i915_gem_object_attach_phys(obj, PAGE_SIZE);
-	mutex_unlock(&i915->drm.struct_mutex);
 	if (err) {
 		pr_err("i915_gem_object_attach_phys failed, err=%d\n", err);
 		goto out_obj;
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 8dc42c5c7569..393ae5321e1d 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -26,17 +26,13 @@ static int live_sanitycheck(void *arg)
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
 	struct igt_spinner spin;
-	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 
 	if (!HAS_LOGICAL_RING_CONTEXTS(i915))
 		return 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	if (igt_spinner_init(&spin, &i915->gt))
-		goto err_unlock;
+		return -ENOMEM;
 
 	ctx = kernel_context(i915);
 	if (!ctx)
@@ -73,9 +69,6 @@ err_ctx:
 	kernel_context_close(ctx);
 err_spin:
 	igt_spinner_fini(&spin);
-err_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
@@ -402,7 +395,6 @@ static int live_timeslice_preempt(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct drm_i915_gem_object *obj;
-	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	void *vaddr;
 	int err = 0;
@@ -417,14 +409,9 @@ static int live_timeslice_preempt(void *arg)
 	 * ready task.
 	 */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
-	if (IS_ERR(obj)) {
-		err = PTR_ERR(obj);
-		goto err_unlock;
-	}
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
 
 	vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
@@ -469,10 +456,6 @@ err_map:
 	i915_gem_object_unpin_map(obj);
 err_obj:
 	i915_gem_object_put(obj);
-err_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	return err;
 }
 
@@ -484,7 +467,6 @@ static int live_busywait_preempt(void *arg)
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 	u32 *map;
 
@@ -493,12 +475,9 @@ static int live_busywait_preempt(void *arg)
 	 * preempt the busywaits used to synchronise between rings.
 	 */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	ctx_hi = kernel_context(i915);
 	if (!ctx_hi)
-		goto err_unlock;
+		return -ENOMEM;
 	ctx_hi->sched.priority =
 		I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
 
@@ -652,9 +631,6 @@ err_ctx_lo:
 	kernel_context_close(ctx_lo);
 err_ctx_hi:
 	kernel_context_close(ctx_hi);
-err_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
@@ -683,7 +659,6 @@ static int live_preempt(void *arg)
 	struct igt_spinner spin_hi, spin_lo;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 
 	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
@@ -692,11 +667,8 @@ static int live_preempt(void *arg)
 	if (!(i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
 		pr_err("Logical preemption supported, but not exposed\n");
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	if (igt_spinner_init(&spin_hi, &i915->gt))
-		goto err_unlock;
+		return -ENOMEM;
 
 	if (igt_spinner_init(&spin_lo, &i915->gt))
 		goto err_spin_hi;
@@ -776,9 +748,6 @@ err_spin_lo:
 	igt_spinner_fini(&spin_lo);
 err_spin_hi:
 	igt_spinner_fini(&spin_hi);
-err_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
@@ -790,17 +759,13 @@ static int live_late_preempt(void *arg)
 	struct intel_engine_cs *engine;
 	struct i915_sched_attr attr = {};
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 
 	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
 		return 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	if (igt_spinner_init(&spin_hi, &i915->gt))
-		goto err_unlock;
+		return -ENOMEM;
 
 	if (igt_spinner_init(&spin_lo, &i915->gt))
 		goto err_spin_hi;
@@ -882,9 +847,6 @@ err_spin_lo:
 	igt_spinner_fini(&spin_lo);
 err_spin_hi:
 	igt_spinner_fini(&spin_hi);
-err_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 
 err_wedged:
@@ -929,7 +891,6 @@ static int live_nopreempt(void *arg)
 	struct intel_engine_cs *engine;
 	struct preempt_client a, b;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 
 	/*
@@ -940,11 +901,8 @@ static int live_nopreempt(void *arg)
 	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
 		return 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	if (preempt_client_init(i915, &a))
-		goto err_unlock;
+		return -ENOMEM;
 	if (preempt_client_init(i915, &b))
 		goto err_client_a;
 	b.ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX);
@@ -1018,9 +976,6 @@ err_client_b:
 	preempt_client_fini(&b);
 err_client_a:
 	preempt_client_fini(&a);
-err_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 
 err_wedged:
@@ -1040,7 +995,6 @@ static int live_suppress_self_preempt(void *arg)
 	};
 	struct preempt_client a, b;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 
 	/*
@@ -1059,11 +1013,8 @@ static int live_suppress_self_preempt(void *arg)
 	if (intel_vgpu_active(i915))
 		return 0; /* GVT forces single port & request submission */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	if (preempt_client_init(i915, &a))
-		goto err_unlock;
+		return -ENOMEM;
 	if (preempt_client_init(i915, &b))
 		goto err_client_a;
 
@@ -1144,9 +1095,6 @@ err_client_b:
 	preempt_client_fini(&b);
 err_client_a:
 	preempt_client_fini(&a);
-err_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 
 err_wedged:
@@ -1216,7 +1164,6 @@ static int live_suppress_wait_preempt(void *arg)
 	struct preempt_client client[4];
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 	int i;
 
@@ -1229,11 +1176,8 @@ static int live_suppress_wait_preempt(void *arg)
 	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
 		return 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	if (preempt_client_init(i915, &client[0])) /* ELSP[0] */
-		goto err_unlock;
+		return -ENOMEM;
 	if (preempt_client_init(i915, &client[1])) /* ELSP[1] */
 		goto err_client_0;
 	if (preempt_client_init(i915, &client[2])) /* head of queue */
@@ -1319,9 +1263,6 @@ err_client_1:
 	preempt_client_fini(&client[1]);
 err_client_0:
 	preempt_client_fini(&client[0]);
-err_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 
 err_wedged:
@@ -1338,7 +1279,6 @@ static int live_chain_preempt(void *arg)
 	struct intel_engine_cs *engine;
 	struct preempt_client hi, lo;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 
 	/*
@@ -1350,11 +1290,8 @@ static int live_chain_preempt(void *arg)
 	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
 		return 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	if (preempt_client_init(i915, &hi))
-		goto err_unlock;
+		return -ENOMEM;
 
 	if (preempt_client_init(i915, &lo))
 		goto err_client_hi;
@@ -1465,9 +1402,6 @@ err_client_lo:
 	preempt_client_fini(&lo);
 err_client_hi:
 	preempt_client_fini(&hi);
-err_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 
 err_wedged:
@@ -1485,7 +1419,6 @@ static int live_preempt_hang(void *arg)
 	struct igt_spinner spin_hi, spin_lo;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	int err = -ENOMEM;
 
 	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
@@ -1494,11 +1427,8 @@ static int live_preempt_hang(void *arg)
 	if (!intel_has_reset_engine(&i915->gt))
 		return 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	if (igt_spinner_init(&spin_hi, &i915->gt))
-		goto err_unlock;
+		return -ENOMEM;
 
 	if (igt_spinner_init(&spin_lo, &i915->gt))
 		goto err_spin_hi;
@@ -1590,9 +1520,6 @@ err_spin_lo:
 	igt_spinner_fini(&spin_lo);
 err_spin_hi:
 	igt_spinner_fini(&spin_hi);
-err_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
@@ -1684,11 +1611,9 @@ static int smoke_crescendo_thread(void *arg)
 		struct i915_gem_context *ctx = smoke_context(smoke);
 		int err;
 
-		mutex_lock(&smoke->i915->drm.struct_mutex);
 		err = smoke_submit(smoke,
 				   ctx, count % I915_PRIORITY_MAX,
 				   smoke->batch);
-		mutex_unlock(&smoke->i915->drm.struct_mutex);
 		if (err)
 			return err;
 
@@ -1709,8 +1634,6 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 	unsigned long count;
 	int err = 0;
 
-	mutex_unlock(&smoke->i915->drm.struct_mutex);
-
 	for_each_engine(engine, smoke->i915, id) {
 		arg[id] = *smoke;
 		arg[id].engine = engine;
@@ -1743,8 +1666,6 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 		put_task_struct(tsk[id]);
 	}
 
-	mutex_lock(&smoke->i915->drm.struct_mutex);
-
 	pr_info("Submitted %lu crescendo:%x requests across %d engines and %d contexts\n",
 		count, flags,
 		RUNTIME_INFO(smoke->i915)->num_engines, smoke->ncontext);
@@ -1787,7 +1708,6 @@ static int live_preempt_smoke(void *arg)
 		.ncontext = 1024,
 	};
 	const unsigned int phase[] = { 0, BATCH };
-	intel_wakeref_t wakeref;
 	struct igt_live_test t;
 	int err = -ENOMEM;
 	u32 *cs;
@@ -1802,13 +1722,10 @@ static int live_preempt_smoke(void *arg)
 	if (!smoke.contexts)
 		return -ENOMEM;
 
-	mutex_lock(&smoke.i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&smoke.i915->runtime_pm);
-
 	smoke.batch = i915_gem_object_create_internal(smoke.i915, PAGE_SIZE);
 	if (IS_ERR(smoke.batch)) {
 		err = PTR_ERR(smoke.batch);
-		goto err_unlock;
+		goto err_free;
 	}
 
 	cs = i915_gem_object_pin_map(smoke.batch, I915_MAP_WB);
@@ -1855,9 +1772,7 @@ err_ctx:
 
 err_batch:
 	i915_gem_object_put(smoke.batch);
-err_unlock:
-	intel_runtime_pm_put(&smoke.i915->runtime_pm, wakeref);
-	mutex_unlock(&smoke.i915->drm.struct_mutex);
+err_free:
 	kfree(smoke.contexts);
 
 	return err;
@@ -1995,19 +1910,17 @@ static int live_virtual_engine(void *arg)
 	struct intel_gt *gt = &i915->gt;
 	enum intel_engine_id id;
 	unsigned int class, inst;
-	int err = -ENODEV;
+	int err;
 
 	if (USES_GUC_SUBMISSION(i915))
 		return 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	for_each_engine(engine, i915, id) {
 		err = nop_virtual_engine(i915, &engine, 1, 1, 0);
 		if (err) {
 			pr_err("Failed to wrap engine %s: err=%d\n",
 			       engine->name, err);
-			goto out_unlock;
+			return err;
 		}
 	}
 
@@ -2028,17 +1941,15 @@ static int live_virtual_engine(void *arg)
 			err = nop_virtual_engine(i915, siblings, nsibling,
 						 n, 0);
 			if (err)
-				goto out_unlock;
+				return err;
 		}
 
 		err = nop_virtual_engine(i915, siblings, nsibling, n, CHAIN);
 		if (err)
-			goto out_unlock;
+			return err;
 	}
 
-out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
-	return err;
+	return 0;
 }
 
 static int mask_virtual_engine(struct drm_i915_private *i915,
@@ -2117,9 +2028,6 @@ static int mask_virtual_engine(struct drm_i915_private *i915,
 	}
 
 	err = igt_live_test_end(&t);
-	if (err)
-		goto out;
-
 out:
 	if (igt_flush_test(i915))
 		err = -EIO;
@@ -2142,13 +2050,11 @@ static int live_virtual_mask(void *arg)
 	struct intel_engine_cs *siblings[MAX_ENGINE_INSTANCE + 1];
 	struct intel_gt *gt = &i915->gt;
 	unsigned int class, inst;
-	int err = 0;
+	int err;
 
 	if (USES_GUC_SUBMISSION(i915))
 		return 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	for (class = 0; class <= MAX_ENGINE_CLASS; class++) {
 		unsigned int nsibling;
 
@@ -2164,12 +2070,10 @@ static int live_virtual_mask(void *arg)
 
 		err = mask_virtual_engine(i915, siblings, nsibling);
 		if (err)
-			goto out_unlock;
+			return err;
 	}
 
-out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
-	return err;
+	return 0;
 }
 
 static int bond_virtual_engine(struct drm_i915_private *i915,
@@ -2320,13 +2224,11 @@ static int live_virtual_bond(void *arg)
 	struct intel_engine_cs *siblings[MAX_ENGINE_INSTANCE + 1];
 	struct intel_gt *gt = &i915->gt;
 	unsigned int class, inst;
-	int err = 0;
+	int err;
 
 	if (USES_GUC_SUBMISSION(i915))
 		return 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	for (class = 0; class <= MAX_ENGINE_CLASS; class++) {
 		const struct phase *p;
 		int nsibling;
@@ -2349,14 +2251,12 @@ static int live_virtual_bond(void *arg)
 			if (err) {
 				pr_err("%s(%s): failed class=%d, nsibling=%d, err=%d\n",
 				       __func__, p->name, class, nsibling, err);
-				goto out_unlock;
+				return err;
 			}
 		}
 	}
 
-out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
-	return err;
+	return 0;
 }
 
 int intel_execlists_live_selftests(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 7c7aceb85a74..95627e80f246 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -708,9 +708,7 @@ static int live_dirty_whitelist(void *arg)
 
 	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
 
-	mutex_unlock(&i915->drm.struct_mutex);
 	file = mock_file(i915);
-	mutex_lock(&i915->drm.struct_mutex);
 	if (IS_ERR(file)) {
 		err = PTR_ERR(file);
 		goto out_rpm;
@@ -732,9 +730,7 @@ static int live_dirty_whitelist(void *arg)
 	}
 
 out_file:
-	mutex_unlock(&i915->drm.struct_mutex);
 	mock_file_free(i915, file);
-	mutex_lock(&i915->drm.struct_mutex);
 out_rpm:
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 	return err;
@@ -1274,14 +1270,9 @@ int intel_workarounds_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_gpu_reset_workarounds),
 		SUBTEST(live_engine_reset_workarounds),
 	};
-	int err;
 
 	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
-	mutex_lock(&i915->drm.struct_mutex);
-	err = i915_subtests(tests, i915);
-	mutex_unlock(&i915->drm.struct_mutex);
-
-	return err;
+	return i915_subtests(tests, i915);
 }
diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
index bba0eafe1cdb..f927f851aadf 100644
--- a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
@@ -116,7 +116,6 @@ static int igt_guc_clients(void *args)
 	int err = 0;
 
 	GEM_BUG_ON(!HAS_GT_UC(dev_priv));
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
 
 	guc = &dev_priv->gt.uc.guc;
@@ -190,7 +189,6 @@ out:
 	guc_clients_enable(guc);
 unlock:
 	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 	return err;
 }
 
@@ -208,7 +206,6 @@ static int igt_guc_doorbells(void *arg)
 	u16 db_id;
 
 	GEM_BUG_ON(!HAS_GT_UC(dev_priv));
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
 
 	guc = &dev_priv->gt.uc.guc;
@@ -299,7 +296,6 @@ out:
 		}
 unlock:
 	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 8d8121c02161..165b3a7f9744 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1797,7 +1797,6 @@ static int igt_cs_tlb(void *arg)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	mutex_lock(&i915->drm.struct_mutex);
 	ctx = live_context(i915, file);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
@@ -2020,7 +2019,6 @@ out_put_bbe:
 out_vm:
 	i915_vm_put(vm);
 out_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
 	mock_file_free(i915, file);
 	return err;
 }
-- 
cgit v1.2.3


From 7842793330ce96ac1d20d22901fb4009c21676f2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 14:40:15 +0100
Subject: drm/i915: Drop struct_mutex from around GEM initialisation

We no longer need to placate lockdep by holding struct_mutex for our
initialisation, so don't.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-21-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_pm.c           | 2 --
 drivers/gpu/drm/i915/i915_gem.c                  | 9 ---------
 drivers/gpu/drm/i915/selftests/mock_gem_device.c | 7 -------
 3 files changed, 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 7c316d4633db..7987b54fb1f5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -174,7 +174,6 @@ void i915_gem_resume(struct drm_i915_private *i915)
 {
 	GEM_TRACE("\n");
 
-	mutex_lock(&i915->drm.struct_mutex);
 	intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
 
 	if (intel_gt_init_hw(&i915->gt))
@@ -198,7 +197,6 @@ void i915_gem_resume(struct drm_i915_private *i915)
 
 out_unlock:
 	intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return;
 
 err_wedged:
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b6d279987b71..80f3153c48dc 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1249,7 +1249,6 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	 * we hold the forcewake during initialisation these problems
 	 * just magically go away.
 	 */
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
 
 	ret = i915_init_ggtt(dev_priv);
@@ -1319,7 +1318,6 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 		goto err_gt;
 
 	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	return 0;
 
@@ -1330,15 +1328,11 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	 * driver doesn't explode during runtime.
 	 */
 err_gt:
-	mutex_unlock(&dev_priv->drm.struct_mutex);
-
 	intel_gt_set_wedged_on_init(&dev_priv->gt);
 	i915_gem_suspend(dev_priv);
 	i915_gem_suspend_late(dev_priv);
 
 	i915_gem_drain_workqueue(dev_priv);
-
-	mutex_lock(&dev_priv->drm.struct_mutex);
 err_init_hw:
 	intel_uc_fini_hw(&dev_priv->gt.uc);
 err_uc_init:
@@ -1353,7 +1347,6 @@ err_scratch:
 	intel_gt_driver_release(&dev_priv->gt);
 err_unlock:
 	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	if (ret != -EIO) {
 		intel_uc_cleanup_firmwares(&dev_priv->gt.uc);
@@ -1406,10 +1399,8 @@ void i915_gem_driver_remove(struct drm_i915_private *dev_priv)
 	/* Flush any outstanding unpin_work. */
 	i915_gem_drain_workqueue(dev_priv);
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_uc_fini_hw(&dev_priv->gt.uc);
 	intel_uc_fini(&dev_priv->gt.uc);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	i915_gem_drain_freed_objects(dev_priv);
 }
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 335f37ba98de..70a7026db08d 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -68,10 +68,7 @@ static void mock_device_release(struct drm_device *dev)
 	drain_workqueue(i915->wq);
 	i915_gem_drain_freed_objects(i915);
 
-	mutex_lock(&i915->drm.struct_mutex);
 	mock_fini_ggtt(&i915->ggtt);
-	mutex_unlock(&i915->drm.struct_mutex);
-
 	destroy_workqueue(i915->wq);
 
 	i915_gemfs_fini(i915);
@@ -179,8 +176,6 @@ struct drm_i915_private *mock_gem_device(void)
 
 	intel_timelines_init(i915);
 
-	mutex_lock(&i915->drm.struct_mutex);
-
 	mock_init_ggtt(i915, &i915->ggtt);
 
 	mkwrite_device_info(i915)->engine_mask = BIT(0);
@@ -197,7 +192,6 @@ struct drm_i915_private *mock_gem_device(void)
 		goto err_context;
 
 	intel_engines_driver_register(i915);
-	mutex_unlock(&i915->drm.struct_mutex);
 
 	WARN_ON(i915_gemfs_init(i915));
 
@@ -208,7 +202,6 @@ err_context:
 err_engine:
 	mock_engine_free(i915->engine[RCS0]);
 err_unlock:
-	mutex_unlock(&i915->drm.struct_mutex);
 	intel_timelines_fini(i915);
 	destroy_workqueue(i915->wq);
 err_drv:
-- 
cgit v1.2.3


From f8204f0ddd62966a0e79c2804963a21e3540dd82 Mon Sep 17 00:00:00 2001
From: Alexander Usyskin <alexander.usyskin@intel.com>
Date: Fri, 4 Oct 2019 21:17:22 +0300
Subject: mei: avoid FW version request on Ibex Peak and earlier

The fixed MKHI client on PCH 6 gen platforms
does not support fw version retrieval.
The error is not fatal, but it fills up the kernel logs and
slows down the driver start.
This patch disables requesting FW version on GEN6 and earlier platforms.

Fixes warning:
[   15.964298] mei mei::55213584-9a29-4916-badf-0fb7ed682aeb:01: Could not read FW version
[   15.964301] mei mei::55213584-9a29-4916-badf-0fb7ed682aeb:01: version command failed -5

Cc: <stable@vger.kernel.org> +v4.18
Cc: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Link: https://lore.kernel.org/r/20191004181722.31374-1-tomas.winkler@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/bus-fixup.c | 14 +++++++++++---
 drivers/misc/mei/hw-me.c     | 21 ++++++++++++++++++---
 drivers/misc/mei/hw-me.h     |  8 ++++++--
 drivers/misc/mei/mei_dev.h   |  4 ++++
 drivers/misc/mei/pci-me.c    | 10 +++++-----
 5 files changed, 44 insertions(+), 13 deletions(-)

diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c
index 32e9b1aed2ca..0a2b99e1af45 100644
--- a/drivers/misc/mei/bus-fixup.c
+++ b/drivers/misc/mei/bus-fixup.c
@@ -218,13 +218,21 @@ static void mei_mkhi_fix(struct mei_cl_device *cldev)
 {
 	int ret;
 
+	/* No need to enable the client if nothing is needed from it */
+	if (!cldev->bus->fw_f_fw_ver_supported &&
+	    !cldev->bus->hbm_f_os_supported)
+		return;
+
 	ret = mei_cldev_enable(cldev);
 	if (ret)
 		return;
 
-	ret = mei_fwver(cldev);
-	if (ret < 0)
-		dev_err(&cldev->dev, "FW version command failed %d\n", ret);
+	if (cldev->bus->fw_f_fw_ver_supported) {
+		ret = mei_fwver(cldev);
+		if (ret < 0)
+			dev_err(&cldev->dev, "FW version command failed %d\n",
+				ret);
+	}
 
 	if (cldev->bus->hbm_f_os_supported) {
 		ret = mei_osver(cldev);
diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index abe1b1f4362f..c4f6991d3028 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -1355,6 +1355,8 @@ static bool mei_me_fw_type_sps(struct pci_dev *pdev)
 #define MEI_CFG_FW_SPS                           \
 	.quirk_probe = mei_me_fw_type_sps
 
+#define MEI_CFG_FW_VER_SUPP                     \
+	.fw_ver_supported = 1
 
 #define MEI_CFG_ICH_HFS                      \
 	.fw_status.count = 0
@@ -1392,31 +1394,41 @@ static const struct mei_cfg mei_me_ich10_cfg = {
 	MEI_CFG_ICH10_HFS,
 };
 
-/* PCH devices */
-static const struct mei_cfg mei_me_pch_cfg = {
+/* PCH6 devices */
+static const struct mei_cfg mei_me_pch6_cfg = {
 	MEI_CFG_PCH_HFS,
 };
 
+/* PCH7 devices */
+static const struct mei_cfg mei_me_pch7_cfg = {
+	MEI_CFG_PCH_HFS,
+	MEI_CFG_FW_VER_SUPP,
+};
+
 /* PCH Cougar Point and Patsburg with quirk for Node Manager exclusion */
 static const struct mei_cfg mei_me_pch_cpt_pbg_cfg = {
 	MEI_CFG_PCH_HFS,
+	MEI_CFG_FW_VER_SUPP,
 	MEI_CFG_FW_NM,
 };
 
 /* PCH8 Lynx Point and newer devices */
 static const struct mei_cfg mei_me_pch8_cfg = {
 	MEI_CFG_PCH8_HFS,
+	MEI_CFG_FW_VER_SUPP,
 };
 
 /* PCH8 Lynx Point with quirk for SPS Firmware exclusion */
 static const struct mei_cfg mei_me_pch8_sps_cfg = {
 	MEI_CFG_PCH8_HFS,
+	MEI_CFG_FW_VER_SUPP,
 	MEI_CFG_FW_SPS,
 };
 
 /* Cannon Lake and newer devices */
 static const struct mei_cfg mei_me_pch12_cfg = {
 	MEI_CFG_PCH8_HFS,
+	MEI_CFG_FW_VER_SUPP,
 	MEI_CFG_DMA_128,
 };
 
@@ -1428,7 +1440,8 @@ static const struct mei_cfg *const mei_cfg_list[] = {
 	[MEI_ME_UNDEF_CFG] = NULL,
 	[MEI_ME_ICH_CFG] = &mei_me_ich_cfg,
 	[MEI_ME_ICH10_CFG] = &mei_me_ich10_cfg,
-	[MEI_ME_PCH_CFG] = &mei_me_pch_cfg,
+	[MEI_ME_PCH6_CFG] = &mei_me_pch6_cfg,
+	[MEI_ME_PCH7_CFG] = &mei_me_pch7_cfg,
 	[MEI_ME_PCH_CPT_PBG_CFG] = &mei_me_pch_cpt_pbg_cfg,
 	[MEI_ME_PCH8_CFG] = &mei_me_pch8_cfg,
 	[MEI_ME_PCH8_SPS_CFG] = &mei_me_pch8_sps_cfg,
@@ -1473,6 +1486,8 @@ struct mei_device *mei_me_dev_init(struct pci_dev *pdev,
 	mei_device_init(dev, &pdev->dev, &mei_me_hw_ops);
 	hw->cfg = cfg;
 
+	dev->fw_f_fw_ver_supported = cfg->fw_ver_supported;
+
 	return dev;
 }
 
diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h
index 08c84a0de4a8..1d8794828cbc 100644
--- a/drivers/misc/mei/hw-me.h
+++ b/drivers/misc/mei/hw-me.h
@@ -20,11 +20,13 @@
  * @fw_status: FW status
  * @quirk_probe: device exclusion quirk
  * @dma_size: device DMA buffers size
+ * @fw_ver_supported: is fw version retrievable from FW
  */
 struct mei_cfg {
 	const struct mei_fw_status fw_status;
 	bool (*quirk_probe)(struct pci_dev *pdev);
 	size_t dma_size[DMA_DSCR_NUM];
+	u32 fw_ver_supported:1;
 };
 
 
@@ -62,7 +64,8 @@ struct mei_me_hw {
  * @MEI_ME_UNDEF_CFG:      Lower sentinel.
  * @MEI_ME_ICH_CFG:        I/O Controller Hub legacy devices.
  * @MEI_ME_ICH10_CFG:      I/O Controller Hub platforms Gen10
- * @MEI_ME_PCH_CFG:        Platform Controller Hub platforms (Up to Gen8).
+ * @MEI_ME_PCH6_CFG:       Platform Controller Hub platforms (Gen6).
+ * @MEI_ME_PCH7_CFG:       Platform Controller Hub platforms (Gen7).
  * @MEI_ME_PCH_CPT_PBG_CFG:Platform Controller Hub workstations
  *                         with quirk for Node Manager exclusion.
  * @MEI_ME_PCH8_CFG:       Platform Controller Hub Gen8 and newer
@@ -77,7 +80,8 @@ enum mei_cfg_idx {
 	MEI_ME_UNDEF_CFG,
 	MEI_ME_ICH_CFG,
 	MEI_ME_ICH10_CFG,
-	MEI_ME_PCH_CFG,
+	MEI_ME_PCH6_CFG,
+	MEI_ME_PCH7_CFG,
 	MEI_ME_PCH_CPT_PBG_CFG,
 	MEI_ME_PCH8_CFG,
 	MEI_ME_PCH8_SPS_CFG,
diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h
index f71a023aed3c..0f2141178299 100644
--- a/drivers/misc/mei/mei_dev.h
+++ b/drivers/misc/mei/mei_dev.h
@@ -426,6 +426,8 @@ struct mei_fw_version {
  *
  * @fw_ver : FW versions
  *
+ * @fw_f_fw_ver_supported : fw feature: fw version supported
+ *
  * @me_clients_rwsem: rw lock over me_clients list
  * @me_clients  : list of FW clients
  * @me_clients_map : FW clients bit map
@@ -506,6 +508,8 @@ struct mei_device {
 
 	struct mei_fw_version fw_ver[MEI_MAX_FW_VER_BLOCKS];
 
+	unsigned int fw_f_fw_ver_supported:1;
+
 	struct rw_semaphore me_clients_rwsem;
 	struct list_head me_clients;
 	DECLARE_BITMAP(me_clients_map, MEI_CLIENTS_MAX);
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 775a2090c2ac..3dca63eddaa0 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -61,13 +61,13 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 	{MEI_PCI_DEVICE(MEI_DEV_ID_ICH10_3, MEI_ME_ICH10_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_ICH10_4, MEI_ME_ICH10_CFG)},
 
-	{MEI_PCI_DEVICE(MEI_DEV_ID_IBXPK_1, MEI_ME_PCH_CFG)},
-	{MEI_PCI_DEVICE(MEI_DEV_ID_IBXPK_2, MEI_ME_PCH_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_IBXPK_1, MEI_ME_PCH6_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_IBXPK_2, MEI_ME_PCH6_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_CPT_1, MEI_ME_PCH_CPT_PBG_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_PBG_1, MEI_ME_PCH_CPT_PBG_CFG)},
-	{MEI_PCI_DEVICE(MEI_DEV_ID_PPT_1, MEI_ME_PCH_CFG)},
-	{MEI_PCI_DEVICE(MEI_DEV_ID_PPT_2, MEI_ME_PCH_CFG)},
-	{MEI_PCI_DEVICE(MEI_DEV_ID_PPT_3, MEI_ME_PCH_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_PPT_1, MEI_ME_PCH7_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_PPT_2, MEI_ME_PCH7_CFG)},
+	{MEI_PCI_DEVICE(MEI_DEV_ID_PPT_3, MEI_ME_PCH7_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_LPT_H, MEI_ME_PCH8_SPS_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_LPT_W, MEI_ME_PCH8_SPS_CFG)},
 	{MEI_PCI_DEVICE(MEI_DEV_ID_LPT_LP, MEI_ME_PCH8_CFG)},
-- 
cgit v1.2.3


From 7d423af9bfb172c3802cc1ca6591ac608c26a311 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 3 Oct 2019 17:02:31 +0300
Subject: drm/i915: Implement a better i945gm vblank irq vs. C-states
 workaround
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The current "disable C3+" workaround for the delayed vblank
irqs on i945gm no longer works. I'm not sure what changed, but
now I need to also disable C2. I also got my hands on a i915gm
machine that suffers from the same issue.

After some furious poking of registers I managed to find a
better workaround: The "Do not Turn off Core Render Clock in C
states" bit. With that I no longer have to disable any C-states,
and as a nice bonus the power cost is only ~1/4 of the
"disable C3+" method (which mind you doesn't even work anymore,
and so would have an even higher power cost if we made it work
by also disabling C2).

So let's throw out all the cpuidle/qos crap and just toggle
the magic bit as needed. And we extend the workaround to cover
i915gm as well.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191003140231.24408-1-ville.syrjala@linux.intel.com
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/display/intel_display.c | 10 ++--
 drivers/gpu/drm/i915/i915_drv.h              |  9 +---
 drivers/gpu/drm/i915/i915_irq.c              | 79 +++++-----------------------
 drivers/gpu/drm/i915/i915_irq.h              |  4 +-
 drivers/gpu/drm/i915/i915_reg.h              |  1 +
 5 files changed, 22 insertions(+), 81 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index f3a94a9cff16..5acc39f32d0c 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -15060,12 +15060,12 @@ static const struct drm_crtc_funcs i965_crtc_funcs = {
 	.disable_vblank = i965_disable_vblank,
 };
 
-static const struct drm_crtc_funcs i945gm_crtc_funcs = {
+static const struct drm_crtc_funcs i915gm_crtc_funcs = {
 	INTEL_CRTC_FUNCS,
 
 	.get_vblank_counter = i915_get_vblank_counter,
-	.enable_vblank = i945gm_enable_vblank,
-	.disable_vblank = i945gm_disable_vblank,
+	.enable_vblank = i915gm_enable_vblank,
+	.disable_vblank = i915gm_disable_vblank,
 };
 
 static const struct drm_crtc_funcs i915_crtc_funcs = {
@@ -15136,8 +15136,8 @@ static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 			funcs = &g4x_crtc_funcs;
 		else if (IS_GEN(dev_priv, 4))
 			funcs = &i965_crtc_funcs;
-		else if (IS_I945GM(dev_priv))
-			funcs = &i945gm_crtc_funcs;
+		else if (IS_I945GM(dev_priv) || IS_I915GM(dev_priv))
+			funcs = &i915gm_crtc_funcs;
 		else if (IS_GEN(dev_priv, 3))
 			funcs = &i915_crtc_funcs;
 		else
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 35b610d52379..cde4c7fb5570 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1701,13 +1701,8 @@ struct drm_i915_private {
 		} contexts;
 	} gem;
 
-	/* For i945gm vblank irq vs. C3 workaround */
-	struct {
-		struct work_struct work;
-		struct pm_qos_request pm_qos;
-		u8 c3_disable_latency;
-		u8 enabled;
-	} i945gm_vblank;
+	/* For i915gm/i945gm vblank irq workaround */
+	u8 vblank_enabled;
 
 	/* perform PHY state sanity checks? */
 	bool chv_phy_assert[2];
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index bc83f094065a..f2371b6083c6 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -29,7 +29,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/circ_buf.h>
-#include <linux/cpuidle.h>
 #include <linux/slab.h>
 #include <linux/sysrq.h>
 
@@ -2910,12 +2909,18 @@ int i8xx_enable_vblank(struct drm_crtc *crtc)
 	return 0;
 }
 
-int i945gm_enable_vblank(struct drm_crtc *crtc)
+int i915gm_enable_vblank(struct drm_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 
-	if (dev_priv->i945gm_vblank.enabled++ == 0)
-		schedule_work(&dev_priv->i945gm_vblank.work);
+	/*
+	 * Vblank interrupts fail to wake the device up from C2+.
+	 * Disabling render clock gating during C-states avoids
+	 * the problem. There is a small power cost so we do this
+	 * only when vblank interrupts are actually enabled.
+	 */
+	if (dev_priv->vblank_enabled++ == 0)
+		I915_WRITE(SCPD0, _MASKED_BIT_ENABLE(CSTATE_RENDER_CLOCK_GATE_DISABLE));
 
 	return i8xx_enable_vblank(crtc);
 }
@@ -2988,14 +2993,14 @@ void i8xx_disable_vblank(struct drm_crtc *crtc)
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
-void i945gm_disable_vblank(struct drm_crtc *crtc)
+void i915gm_disable_vblank(struct drm_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 
 	i8xx_disable_vblank(crtc);
 
-	if (--dev_priv->i945gm_vblank.enabled == 0)
-		schedule_work(&dev_priv->i945gm_vblank.work);
+	if (--dev_priv->vblank_enabled == 0)
+		I915_WRITE(SCPD0, _MASKED_BIT_DISABLE(CSTATE_RENDER_CLOCK_GATE_DISABLE));
 }
 
 void i965_disable_vblank(struct drm_crtc *crtc)
@@ -3034,60 +3039,6 @@ void bdw_disable_vblank(struct drm_crtc *crtc)
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
-static void i945gm_vblank_work_func(struct work_struct *work)
-{
-	struct drm_i915_private *dev_priv =
-		container_of(work, struct drm_i915_private, i945gm_vblank.work);
-
-	/*
-	 * Vblank interrupts fail to wake up the device from C3,
-	 * hence we want to prevent C3 usage while vblank interrupts
-	 * are enabled.
-	 */
-	pm_qos_update_request(&dev_priv->i945gm_vblank.pm_qos,
-			      READ_ONCE(dev_priv->i945gm_vblank.enabled) ?
-			      dev_priv->i945gm_vblank.c3_disable_latency :
-			      PM_QOS_DEFAULT_VALUE);
-}
-
-static int cstate_disable_latency(const char *name)
-{
-	const struct cpuidle_driver *drv;
-	int i;
-
-	drv = cpuidle_get_driver();
-	if (!drv)
-		return 0;
-
-	for (i = 0; i < drv->state_count; i++) {
-		const struct cpuidle_state *state = &drv->states[i];
-
-		if (!strcmp(state->name, name))
-			return state->exit_latency ?
-				state->exit_latency - 1 : 0;
-	}
-
-	return 0;
-}
-
-static void i945gm_vblank_work_init(struct drm_i915_private *dev_priv)
-{
-	INIT_WORK(&dev_priv->i945gm_vblank.work,
-		  i945gm_vblank_work_func);
-
-	dev_priv->i945gm_vblank.c3_disable_latency =
-		cstate_disable_latency("C3");
-	pm_qos_add_request(&dev_priv->i945gm_vblank.pm_qos,
-			   PM_QOS_CPU_DMA_LATENCY,
-			   PM_QOS_DEFAULT_VALUE);
-}
-
-static void i945gm_vblank_work_fini(struct drm_i915_private *dev_priv)
-{
-	cancel_work_sync(&dev_priv->i945gm_vblank.work);
-	pm_qos_remove_request(&dev_priv->i945gm_vblank.pm_qos);
-}
-
 static void ibx_irq_reset(struct drm_i915_private *dev_priv)
 {
 	struct intel_uncore *uncore = &dev_priv->uncore;
@@ -4298,9 +4249,6 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	int i;
 
-	if (IS_I945GM(dev_priv))
-		i945gm_vblank_work_init(dev_priv);
-
 	intel_hpd_init_work(dev_priv);
 
 	INIT_WORK(&rps->work, gen6_pm_rps_work);
@@ -4388,9 +4336,6 @@ void intel_irq_fini(struct drm_i915_private *i915)
 {
 	int i;
 
-	if (IS_I945GM(i915))
-		i945gm_vblank_work_fini(i915);
-
 	for (i = 0; i < MAX_L3_SLICES; ++i)
 		kfree(i915->l3_parity.remap_info[i]);
 }
diff --git a/drivers/gpu/drm/i915/i915_irq.h b/drivers/gpu/drm/i915/i915_irq.h
index 8e7e6071777e..19a3bc019535 100644
--- a/drivers/gpu/drm/i915/i915_irq.h
+++ b/drivers/gpu/drm/i915/i915_irq.h
@@ -122,12 +122,12 @@ u32 i915_get_vblank_counter(struct drm_crtc *crtc);
 u32 g4x_get_vblank_counter(struct drm_crtc *crtc);
 
 int i8xx_enable_vblank(struct drm_crtc *crtc);
-int i945gm_enable_vblank(struct drm_crtc *crtc);
+int i915gm_enable_vblank(struct drm_crtc *crtc);
 int i965_enable_vblank(struct drm_crtc *crtc);
 int ilk_enable_vblank(struct drm_crtc *crtc);
 int bdw_enable_vblank(struct drm_crtc *crtc);
 void i8xx_disable_vblank(struct drm_crtc *crtc);
-void i945gm_disable_vblank(struct drm_crtc *crtc);
+void i915gm_disable_vblank(struct drm_crtc *crtc);
 void i965_disable_vblank(struct drm_crtc *crtc);
 void ilk_disable_vblank(struct drm_crtc *crtc);
 void bdw_disable_vblank(struct drm_crtc *crtc);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 813ddea3f9f1..6d67bd238cfe 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2709,6 +2709,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define VLV_GU_CTL0	_MMIO(VLV_DISPLAY_BASE + 0x2030)
 #define VLV_GU_CTL1	_MMIO(VLV_DISPLAY_BASE + 0x2034)
 #define SCPD0		_MMIO(0x209c) /* 915+ only */
+#define  CSTATE_RENDER_CLOCK_GATE_DISABLE	(1 << 5)
 #define GEN2_IER	_MMIO(0x20a0)
 #define GEN2_IIR	_MMIO(0x20a4)
 #define GEN2_IMR	_MMIO(0x20a8)
-- 
cgit v1.2.3


From 41e086e1550646344dd47d3462ca2d19caabb943 Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus@microchip.com>
Date: Fri, 4 Oct 2019 10:47:55 +0000
Subject: mtd: spi-nor: Fix direction of the write_sr() transfer

write_sr() sends data to the SPI memory, fix the direction.

Fixes: b35b9a10362d ("mtd: spi-nor: Move m25p80 code in spi-nor.c")
Reported-by: John Garry <john.garry@huawei.com>
Signed-off-by: Tudor Ambarus <tudor.ambarus@microchip.com>
Tested-by: John Garry <john.garry@huawei.com>
Acked-by: Vignesh Raghavendra <vigneshr@ti.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/spi-nor/spi-nor.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 1d8621d43160..7acf4a93b592 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -487,7 +487,7 @@ static int write_sr(struct spi_nor *nor, u8 val)
 			SPI_MEM_OP(SPI_MEM_OP_CMD(SPINOR_OP_WRSR, 1),
 				   SPI_MEM_OP_NO_ADDR,
 				   SPI_MEM_OP_NO_DUMMY,
-				   SPI_MEM_OP_DATA_IN(1, nor->bouncebuf, 1));
+				   SPI_MEM_OP_DATA_OUT(1, nor->bouncebuf, 1));
 
 		return spi_mem_exec_op(nor->spimem, &op);
 	}
-- 
cgit v1.2.3


From fc739a058d99c9297ef6bfd923b809d85855b9a9 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Wed, 25 Sep 2019 10:27:41 -0500
Subject: misc: fastrpc: prevent memory leak in fastrpc_dma_buf_attach

In fastrpc_dma_buf_attach if dma_get_sgtable fails the allocated memory
for a should be released.

Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Link: https://lore.kernel.org/r/20190925152742.16258-1-navid.emamdoost@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/fastrpc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 47ae84afac2e..1b1a794d639d 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -527,6 +527,7 @@ static int fastrpc_dma_buf_attach(struct dma_buf *dmabuf,
 			      FASTRPC_PHYS(buffer->phys), buffer->size);
 	if (ret < 0) {
 		dev_err(buffer->dev, "failed to get scatterlist from DMA API\n");
+		kfree(a);
 		return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From 60c1b3e25728e0485f08e72e61c3cad5331925a3 Mon Sep 17 00:00:00 2001
From: Patrice Chotard <patrice.chotard@st.com>
Date: Fri, 4 Oct 2019 14:40:25 +0200
Subject: ARM: multi_v7_defconfig: Fix SPI_STM32_QSPI support

SPI_STM32_QSPI must be set in buildin as rootfs can be
located on QSPI memory device.

Link: https://lore.kernel.org/r/20191004124025.17394-1-patrice.chotard@st.com
Signed-off-by: Patrice Chotard <patrice.chotard@st.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
---
 arch/arm/configs/multi_v7_defconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 198de8e36d92..e4c8def9a0a5 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -415,7 +415,7 @@ CONFIG_SPI_SH_MSIOF=m
 CONFIG_SPI_SH_HSPI=y
 CONFIG_SPI_SIRF=y
 CONFIG_SPI_STM32=m
-CONFIG_SPI_STM32_QSPI=m
+CONFIG_SPI_STM32_QSPI=y
 CONFIG_SPI_SUN4I=y
 CONFIG_SPI_SUN6I=y
 CONFIG_SPI_TEGRA114=y
-- 
cgit v1.2.3


From ee4e4040ab6191f9431afad9a2deec76f6759cad Mon Sep 17 00:00:00 2001
From: "Shiraz, Saleem" <shiraz.saleem@intel.com>
Date: Wed, 25 Sep 2019 11:45:24 -0500
Subject: RDMA/i40iw: Associate ibdev to netdev before IB device registration

i40iw IB device registration fails with ENODEV.

ib_register_device
 setup_device/setup_port_data
  i40iw_port_immutable
   ib_query_port
     iw_query_port
      ib_device_get_netdev(ENODEV)

ib_device_get_netdev() does not have a netdev associated
with the ibdev and thus fails.
Use ib_device_set_netdev() to associate netdev to ibdev
in i40iw before IB device registration.

Fixes: 4929116bdf72 ("RDMA/core: Add common iWARP query port")
Link: https://lore.kernel.org/r/20190925164524.856-1-shiraz.saleem@intel.com
Signed-off-by: Shiraz, Saleem <shiraz.saleem@intel.com>
Reviewed-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/i40iw/i40iw_verbs.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 8056930bbe2c..cd9ee1664a69 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -2773,6 +2773,10 @@ int i40iw_register_rdma_device(struct i40iw_device *iwdev)
 		return -ENOMEM;
 	iwibdev = iwdev->iwibdev;
 	rdma_set_device_sysfs_group(&iwibdev->ibdev, &i40iw_attr_group);
+	ret = ib_device_set_netdev(&iwibdev->ibdev, iwdev->netdev, 1);
+	if (ret)
+		goto error;
+
 	ret = ib_register_device(&iwibdev->ibdev, "i40iw%d");
 	if (ret)
 		goto error;
-- 
cgit v1.2.3


From ab59ca3eb4e7059727df85eee68bda169d26c8f8 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 18 Aug 2019 11:10:44 +0200
Subject: RDMA/core: Fix an error handling path in 'res_get_common_doit()'

According to surrounding error paths, it is likely that 'goto err_get;' is
expected here. Otherwise, a call to 'rdma_restrack_put(res);' would be
missing.

Fixes: c5dfe0ea6ffa ("RDMA/nldev: Add resource tracker doit callback")
Link: https://lore.kernel.org/r/20190818091044.8845-1-christophe.jaillet@wanadoo.fr
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/nldev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 7a7474000100..3e84981e5e57 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1230,7 +1230,7 @@ static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg) {
 		ret = -ENOMEM;
-		goto err;
+		goto err_get;
 	}
 
 	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
-- 
cgit v1.2.3


From 94635c36f3854934a46d9e812e028d4721bbb0e6 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Mon, 16 Sep 2019 10:11:51 +0300
Subject: RDMA/cm: Fix memory leak in cm_add/remove_one

In the process of moving the debug counters sysfs entries, the commit
mentioned below eliminated the cm_infiniband sysfs directory.

This sysfs directory was tied to the cm_port object allocated in procedure
cm_add_one().

Before the commit below, this cm_port object was freed via a call to
kobject_put(port->kobj) in procedure cm_remove_port_fs().

Since port no longer uses its kobj, kobject_put(port->kobj) was eliminated.
This, however, meant that kfree was never called for the cm_port buffers.

Fix this by adding explicit kfree(port) calls to functions cm_add_one()
and cm_remove_one().

Note: the kfree call in the first chunk below (in the cm_add_one error
flow) fixes an old, undetected memory leak.

Fixes: c87e65cfb97c ("RDMA/cm: Move debug counters to be under relevant IB device")
Link: https://lore.kernel.org/r/20190916071154.20383-2-leon@kernel.org
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/cm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index da10e6ccb43c..5920c0085d35 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -4399,6 +4399,7 @@ error2:
 error1:
 	port_modify.set_port_cap_mask = 0;
 	port_modify.clr_port_cap_mask = IB_PORT_CM_SUP;
+	kfree(port);
 	while (--i) {
 		if (!rdma_cap_ib_cm(ib_device, i))
 			continue;
@@ -4407,6 +4408,7 @@ error1:
 		ib_modify_port(ib_device, port->port_num, 0, &port_modify);
 		ib_unregister_mad_agent(port->mad_agent);
 		cm_remove_port_fs(port);
+		kfree(port);
 	}
 free:
 	kfree(cm_dev);
@@ -4460,6 +4462,7 @@ static void cm_remove_one(struct ib_device *ib_device, void *client_data)
 		spin_unlock_irq(&cm.state_lock);
 		ib_unregister_mad_agent(cur_mad_agent);
 		cm_remove_port_fs(port);
+		kfree(port);
 	}
 
 	kfree(cm_dev);
-- 
cgit v1.2.3


From 3840c5b78803b2b6cc1ff820100a74a092c40cbb Mon Sep 17 00:00:00 2001
From: Greg KH <gregkh@linuxfoundation.org>
Date: Tue, 1 Oct 2019 18:56:11 +0200
Subject: RDMA/cxgb4: Do not dma memory off of the stack

Nicolas pointed out that the cxgb4 driver is doing dma off of the stack,
which is generally considered a very bad thing.  On some architectures it
could be a security problem, but odds are none of them actually run this
driver, so it's just a "normal" bug.

Resolve this by allocating the memory for a message off of the heap
instead of the stack.  kmalloc() always will give us a proper memory
location that DMA will work correctly from.

Link: https://lore.kernel.org/r/20191001165611.GA3542072@kroah.com
Reported-by: Nicolas Waisman <nico@semmle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tested-by: Potnuri Bharat Teja <bharat@chelsio.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/cxgb4/mem.c | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index aa772ee0706f..35c284af574d 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -275,13 +275,17 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry,
 			   struct sk_buff *skb, struct c4iw_wr_wait *wr_waitp)
 {
 	int err;
-	struct fw_ri_tpte tpt;
+	struct fw_ri_tpte *tpt;
 	u32 stag_idx;
 	static atomic_t key;
 
 	if (c4iw_fatal_error(rdev))
 		return -EIO;
 
+	tpt = kmalloc(sizeof(*tpt), GFP_KERNEL);
+	if (!tpt)
+		return -ENOMEM;
+
 	stag_state = stag_state > 0;
 	stag_idx = (*stag) >> 8;
 
@@ -291,6 +295,7 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry,
 			mutex_lock(&rdev->stats.lock);
 			rdev->stats.stag.fail++;
 			mutex_unlock(&rdev->stats.lock);
+			kfree(tpt);
 			return -ENOMEM;
 		}
 		mutex_lock(&rdev->stats.lock);
@@ -305,28 +310,28 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry,
 
 	/* write TPT entry */
 	if (reset_tpt_entry)
-		memset(&tpt, 0, sizeof(tpt));
+		memset(tpt, 0, sizeof(*tpt));
 	else {
-		tpt.valid_to_pdid = cpu_to_be32(FW_RI_TPTE_VALID_F |
+		tpt->valid_to_pdid = cpu_to_be32(FW_RI_TPTE_VALID_F |
 			FW_RI_TPTE_STAGKEY_V((*stag & FW_RI_TPTE_STAGKEY_M)) |
 			FW_RI_TPTE_STAGSTATE_V(stag_state) |
 			FW_RI_TPTE_STAGTYPE_V(type) | FW_RI_TPTE_PDID_V(pdid));
-		tpt.locread_to_qpid = cpu_to_be32(FW_RI_TPTE_PERM_V(perm) |
+		tpt->locread_to_qpid = cpu_to_be32(FW_RI_TPTE_PERM_V(perm) |
 			(bind_enabled ? FW_RI_TPTE_MWBINDEN_F : 0) |
 			FW_RI_TPTE_ADDRTYPE_V((zbva ? FW_RI_ZERO_BASED_TO :
 						      FW_RI_VA_BASED_TO))|
 			FW_RI_TPTE_PS_V(page_size));
-		tpt.nosnoop_pbladdr = !pbl_size ? 0 : cpu_to_be32(
+		tpt->nosnoop_pbladdr = !pbl_size ? 0 : cpu_to_be32(
 			FW_RI_TPTE_PBLADDR_V(PBL_OFF(rdev, pbl_addr)>>3));
-		tpt.len_lo = cpu_to_be32((u32)(len & 0xffffffffUL));
-		tpt.va_hi = cpu_to_be32((u32)(to >> 32));
-		tpt.va_lo_fbo = cpu_to_be32((u32)(to & 0xffffffffUL));
-		tpt.dca_mwbcnt_pstag = cpu_to_be32(0);
-		tpt.len_hi = cpu_to_be32((u32)(len >> 32));
+		tpt->len_lo = cpu_to_be32((u32)(len & 0xffffffffUL));
+		tpt->va_hi = cpu_to_be32((u32)(to >> 32));
+		tpt->va_lo_fbo = cpu_to_be32((u32)(to & 0xffffffffUL));
+		tpt->dca_mwbcnt_pstag = cpu_to_be32(0);
+		tpt->len_hi = cpu_to_be32((u32)(len >> 32));
 	}
 	err = write_adapter_mem(rdev, stag_idx +
 				(rdev->lldi.vr->stag.start >> 5),
-				sizeof(tpt), &tpt, skb, wr_waitp);
+				sizeof(*tpt), tpt, skb, wr_waitp);
 
 	if (reset_tpt_entry) {
 		c4iw_put_resource(&rdev->resource.tpt_table, stag_idx);
@@ -334,6 +339,7 @@ static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry,
 		rdev->stats.stag.cur -= 32;
 		mutex_unlock(&rdev->stats.lock);
 	}
+	kfree(tpt);
 	return err;
 }
 
-- 
cgit v1.2.3


From 0e5493cab5ef90fb91f89a2dc84259c7a7d7fd50 Mon Sep 17 00:00:00 2001
From: CQ Tang <cq.tang@intel.com>
Date: Fri, 4 Oct 2019 18:04:32 +0100
Subject: drm/i915/stolen: make the object creation interface consistent

Our other backends return an actual error value upon failure. Do the
same for stolen objects, which currently just return NULL on failure.

Signed-off-by: CQ Tang <cq.tang@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004170452.15410-2-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c |  2 +-
 drivers/gpu/drm/i915/display/intel_fbdev.c   |  4 +--
 drivers/gpu/drm/i915/display/intel_overlay.c |  2 +-
 drivers/gpu/drm/i915/gem/i915_gem_stolen.c   | 45 ++++++++++++++++------------
 drivers/gpu/drm/i915/gt/intel_gt.c           |  2 +-
 drivers/gpu/drm/i915/gt/intel_rc6.c          |  8 ++---
 drivers/gpu/drm/i915/gt/intel_ringbuffer.c   |  2 +-
 7 files changed, 36 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 5acc39f32d0c..c15975a410bc 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3066,7 +3066,7 @@ intel_alloc_initial_plane_obj(struct intel_crtc *crtc,
 							     base_aligned,
 							     base_aligned,
 							     size_aligned);
-	if (!obj)
+	if (IS_ERR(obj))
 		return false;
 
 	switch (plane_config->tiling) {
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index 97cde017670a..3d1061470e76 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -141,10 +141,10 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 	/* If the FB is too big, just don't use it since fbdev is not very
 	 * important and we should probably use that space with FBC or other
 	 * features. */
-	obj = NULL;
+	obj = ERR_PTR(-ENODEV);
 	if (size * 2 < dev_priv->stolen_usable_size)
 		obj = i915_gem_object_create_stolen(dev_priv, size);
-	if (obj == NULL)
+	if (IS_ERR(obj))
 		obj = i915_gem_object_create_shmem(dev_priv, size);
 	if (IS_ERR(obj)) {
 		DRM_ERROR("failed to allocate framebuffer\n");
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index daea112cbb87..2360f19f9694 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -1291,7 +1291,7 @@ static int get_registers(struct intel_overlay *overlay, bool use_phys)
 	int err;
 
 	obj = i915_gem_object_create_stolen(i915, PAGE_SIZE);
-	if (obj == NULL)
+	if (IS_ERR(obj))
 		obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index fad98a921cde..c76260ce13e3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -553,10 +553,11 @@ _i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
 {
 	struct drm_i915_gem_object *obj;
 	unsigned int cache_level;
+	int err = -ENOMEM;
 
 	obj = i915_gem_object_alloc();
-	if (obj == NULL)
-		return NULL;
+	if (!obj)
+		goto err;
 
 	drm_gem_private_object_init(&dev_priv->drm, &obj->base, stolen->size);
 	i915_gem_object_init(obj, &i915_gem_object_stolen_ops);
@@ -566,14 +567,16 @@ _i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
 	cache_level = HAS_LLC(dev_priv) ? I915_CACHE_LLC : I915_CACHE_NONE;
 	i915_gem_object_set_cache_coherency(obj, cache_level);
 
-	if (i915_gem_object_pin_pages(obj))
+	err = i915_gem_object_pin_pages(obj);
+	if (err)
 		goto cleanup;
 
 	return obj;
 
 cleanup:
 	i915_gem_object_free(obj);
-	return NULL;
+err:
+	return ERR_PTR(err);
 }
 
 struct drm_i915_gem_object *
@@ -585,28 +588,32 @@ i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
 	int ret;
 
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	if (size == 0)
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
 	if (!stolen)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	ret = i915_gem_stolen_insert_node(dev_priv, stolen, size, 4096);
 	if (ret) {
-		kfree(stolen);
-		return NULL;
+		obj = ERR_PTR(ret);
+		goto err_free;
 	}
 
 	obj = _i915_gem_object_create_stolen(dev_priv, stolen);
-	if (obj)
-		return obj;
+	if (IS_ERR(obj))
+		goto err_remove;
 
+	return obj;
+
+err_remove:
 	i915_gem_stolen_remove_node(dev_priv, stolen);
+err_free:
 	kfree(stolen);
-	return NULL;
+	return obj;
 }
 
 struct drm_i915_gem_object *
@@ -622,7 +629,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	int ret;
 
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	DRM_DEBUG_DRIVER("creating preallocated stolen object: stolen_offset=%pa, gtt_offset=%pa, size=%pa\n",
 			 &stolen_offset, &gtt_offset, &size);
@@ -631,11 +638,11 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	if (WARN_ON(size == 0) ||
 	    WARN_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE)) ||
 	    WARN_ON(!IS_ALIGNED(stolen_offset, I915_GTT_MIN_ALIGNMENT)))
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
 	if (!stolen)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	stolen->start = stolen_offset;
 	stolen->size = size;
@@ -645,15 +652,15 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	if (ret) {
 		DRM_DEBUG_DRIVER("failed to allocate stolen space\n");
 		kfree(stolen);
-		return NULL;
+		return ERR_PTR(ret);
 	}
 
 	obj = _i915_gem_object_create_stolen(dev_priv, stolen);
-	if (obj == NULL) {
+	if (IS_ERR(obj)) {
 		DRM_DEBUG_DRIVER("failed to allocate stolen object\n");
 		i915_gem_stolen_remove_node(dev_priv, stolen);
 		kfree(stolen);
-		return NULL;
+		return obj;
 	}
 
 	/* Some objects just need physical mem from stolen space */
@@ -706,5 +713,5 @@ err_pages:
 	i915_gem_object_unpin_pages(obj);
 err:
 	i915_gem_object_put(obj);
-	return NULL;
+	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 53220741e49e..8f44cf8c79b2 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -334,7 +334,7 @@ static int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size)
 	int ret;
 
 	obj = i915_gem_object_create_stolen(i915, size);
-	if (!obj)
+	if (IS_ERR(obj))
 		obj = i915_gem_object_create_internal(i915, size);
 	if (IS_ERR(obj)) {
 		DRM_ERROR("Failed to allocate scratch page\n");
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index d6167dd592e9..71184aa72896 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -299,8 +299,8 @@ static int vlv_rc6_init(struct intel_rc6 *rc6)
 								      pcbr_offset,
 								      I915_GTT_OFFSET_NONE,
 								      pctx_size);
-		if (!pctx)
-			return -ENOMEM;
+		if (IS_ERR(pctx))
+			return PTR_ERR(pctx);
 
 		goto out;
 	}
@@ -316,9 +316,9 @@ static int vlv_rc6_init(struct intel_rc6 *rc6)
 	 * memory, or any other relevant ranges.
 	 */
 	pctx = i915_gem_object_create_stolen(i915, pctx_size);
-	if (!pctx) {
+	if (IS_ERR(pctx)) {
 		DRM_DEBUG("not enough stolen space for PCTX, disabling\n");
-		return -ENOMEM;
+		return PTR_ERR(pctx);
 	}
 
 	GEM_BUG_ON(range_overflows_t(u64,
diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index ec32996254c0..311fdc0a21bc 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -1274,7 +1274,7 @@ static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size)
 	struct i915_vma *vma;
 
 	obj = i915_gem_object_create_stolen(i915, size);
-	if (!obj)
+	if (IS_ERR(obj))
 		obj = i915_gem_object_create_internal(i915, size);
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
-- 
cgit v1.2.3


From 594e6c5d41ed2471ab0b90f3f0b66cdf618b7ac9 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 2 Oct 2019 14:56:27 +0300
Subject: RDMA/nldev: Reshuffle the code to avoid need to rebind QP in error
 path

Properly unwind QP counter rebinding in case of failure.

Trying to rebind the counter after unbiding it is not going to work
reliably, move the unbind to the end so it doesn't have to be unwound.

Fixes: b389327df905 ("RDMA/nldev: Allow counter manual mode configration through RDMA netlink")
Link: https://lore.kernel.org/r/20191002115627.16740-1-leon@kernel.org
Reviewed-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/nldev.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 3e84981e5e57..65b36548bc17 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1787,10 +1787,6 @@ static int nldev_stat_del_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	cntn = nla_get_u32(tb[RDMA_NLDEV_ATTR_STAT_COUNTER_ID]);
 	qpn = nla_get_u32(tb[RDMA_NLDEV_ATTR_RES_LQPN]);
-	ret = rdma_counter_unbind_qpn(device, port, qpn, cntn);
-	if (ret)
-		goto err_unbind;
-
 	if (fill_nldev_handle(msg, device) ||
 	    nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) ||
 	    nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_COUNTER_ID, cntn) ||
@@ -1799,13 +1795,15 @@ static int nldev_stat_del_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto err_fill;
 	}
 
+	ret = rdma_counter_unbind_qpn(device, port, qpn, cntn);
+	if (ret)
+		goto err_fill;
+
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
 	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_fill:
-	rdma_counter_bind_qpn(device, port, qpn, cntn);
-err_unbind:
 	nlmsg_free(msg);
 err:
 	ib_device_put(device);
-- 
cgit v1.2.3


From 6822c29ddbbdeafd8d1b79ebe6c51b83efd55ae1 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 4 Oct 2019 17:41:02 +0000
Subject: MIPS: fw/arc: Remove unused addr variable

The addr variable in prom_free_prom_memory() has been unused since
commit 0df1007677d5 ("MIPS: fw: Record prom memory"), leading to a
compiler warning:

  arch/mips/fw/arc/memory.c:163:16:
    warning: unused variable 'addr' [-Wunused-variable]

Fix this by removing the unused variable.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Fixes: 0df1007677d5 ("MIPS: fw: Record prom memory")
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: linux-mips@vger.kernel.org
---
 arch/mips/fw/arc/memory.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c
index af44b35d79a1..b4328b3b5288 100644
--- a/arch/mips/fw/arc/memory.c
+++ b/arch/mips/fw/arc/memory.c
@@ -160,7 +160,6 @@ void __init prom_meminit(void)
 
 void __init prom_free_prom_memory(void)
 {
-	unsigned long addr;
 	int i;
 
 	if (prom_flags & PROM_FLAG_DONT_FREE_TEMP)
-- 
cgit v1.2.3


From 1cbe866cbcb53338de33cf67262e73f9315a9725 Mon Sep 17 00:00:00 2001
From: Mohamad Heib <mohamadh@mellanox.com>
Date: Wed, 2 Oct 2019 15:21:27 +0300
Subject: IB/core: Fix wrong iterating on ports

rdma_for_each_port is already incrementing the iterator's value it
receives therefore, after the first iteration the iterator is increased by
2 which eventually causing wrong queries and possible traces.

Fix the above by removing the old redundant incrementation that was used
before rdma_for_each_port() macro.

Cc: <stable@vger.kernel.org>
Fixes: ea1075edcbab ("RDMA: Add and use rdma_for_each_port")
Link: https://lore.kernel.org/r/20191002122127.17571-1-leon@kernel.org
Signed-off-by: Mohamad Heib <mohamadh@mellanox.com>
Reviewed-by: Erez Alfasi <ereza@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/security.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c
index 1ab423b19f77..6eb6d2717ca5 100644
--- a/drivers/infiniband/core/security.c
+++ b/drivers/infiniband/core/security.c
@@ -426,7 +426,7 @@ int ib_create_qp_security(struct ib_qp *qp, struct ib_device *dev)
 	int ret;
 
 	rdma_for_each_port (dev, i) {
-		is_ib = rdma_protocol_ib(dev, i++);
+		is_ib = rdma_protocol_ib(dev, i);
 		if (is_ib)
 			break;
 	}
-- 
cgit v1.2.3


From 880505cfef1d086d18b59d2920eb2160429ffa1f Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Tue, 1 Oct 2019 12:38:16 -0300
Subject: RDMA/mlx5: Do not allow rereg of a ODP MR

This code is completely broken, the umem of a ODP MR simply cannot be
discarded without a lot more locking, nor can an ODP mkey be blithely
destroyed via destroy_mkey().

Fixes: 6aec21f6a832 ("IB/mlx5: Page faults handling infrastructure")
Link: https://lore.kernel.org/r/20191001153821.23621-2-jgg@ziepe.ca
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/mr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 1eff031ef048..e7f840f306e4 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1441,6 +1441,9 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 	if (!mr->umem)
 		return -EINVAL;
 
+	if (is_odp_mr(mr))
+		return -EOPNOTSUPP;
+
 	if (flags & IB_MR_REREG_TRANS) {
 		addr = virt_addr;
 		len = length;
@@ -1486,8 +1489,6 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 		}
 
 		mr->allocated_from_cache = 0;
-		if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING))
-			mr->live = 1;
 	} else {
 		/*
 		 * Send a UMR WQE
@@ -1516,7 +1517,6 @@ int mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start,
 
 	set_mr_fields(dev, mr, npages, len, access_flags);
 
-	update_odp_mr(mr);
 	return 0;
 
 err:
-- 
cgit v1.2.3


From f28b1932eaae183b80bd8c7abecae167a0e5c61a Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Tue, 1 Oct 2019 12:38:17 -0300
Subject: RDMA/mlx5: Fix a race with mlx5_ib_update_xlt on an implicit MR

mlx5_ib_update_xlt() must be protected against parallel free of the MR it
is accessing, also it must be called single threaded while updating the
HW. Otherwise we can have races of the form:

    CPU0                               CPU1
  mlx5_ib_update_xlt()
   mlx5_odp_populate_klm()
     odp_lookup() == NULL
     pklm = ZAP
                                      implicit_mr_get_data()
 				        implicit_mr_alloc()
 					  <update interval tree>
					mlx5_ib_update_xlt
					  mlx5_odp_populate_klm()
					    odp_lookup() != NULL
					    pklm = VALID
					   mlx5_ib_post_send_wait()

    mlx5_ib_post_send_wait() // Replaces VALID with ZAP

This can be solved by putting both the SRCU and the umem_mutex lock around
every call to mlx5_ib_update_xlt(). This ensures that the content of the
interval tree relavent to mlx5_odp_populate_klm() (ie mr->parent == mr)
will not change while it is running, and thus the posted WRs to update the
KLM will always reflect the correct information.

The race above will resolve by either having CPU1 wait till CPU0 completes
the ZAP or CPU0 will run after the add and instead store VALID.

The pagefault path adding children already holds the umem_mutex and SRCU,
so the only missed lock is during MR destruction.

Fixes: 81713d3788d2 ("IB/mlx5: Add implicit MR support")
Link: https://lore.kernel.org/r/20191001153821.23621-3-jgg@ziepe.ca
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/odp.c | 34 ++++++++++++++++++++++++++++++++--
 1 file changed, 32 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 2e9b43061797..3401c06b7e54 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -178,6 +178,29 @@ void mlx5_odp_populate_klm(struct mlx5_klm *pklm, size_t offset,
 		return;
 	}
 
+	/*
+	 * The locking here is pretty subtle. Ideally the implicit children
+	 * list would be protected by the umem_mutex, however that is not
+	 * possible. Instead this uses a weaker update-then-lock pattern:
+	 *
+	 *  srcu_read_lock()
+	 *    <change children list>
+	 *    mutex_lock(umem_mutex)
+	 *     mlx5_ib_update_xlt()
+	 *    mutex_unlock(umem_mutex)
+	 *    destroy lkey
+	 *
+	 * ie any change the children list must be followed by the locked
+	 * update_xlt before destroying.
+	 *
+	 * The umem_mutex provides the acquire/release semantic needed to make
+	 * the children list visible to a racing thread. While SRCU is not
+	 * technically required, using it gives consistent use of the SRCU
+	 * locking around the children list.
+	 */
+	lockdep_assert_held(&to_ib_umem_odp(mr->umem)->umem_mutex);
+	lockdep_assert_held(&mr->dev->mr_srcu);
+
 	odp = odp_lookup(offset * MLX5_IMR_MTT_SIZE,
 			 nentries * MLX5_IMR_MTT_SIZE, mr);
 
@@ -202,15 +225,22 @@ static void mr_leaf_free_action(struct work_struct *work)
 	struct ib_umem_odp *odp = container_of(work, struct ib_umem_odp, work);
 	int idx = ib_umem_start(odp) >> MLX5_IMR_MTT_SHIFT;
 	struct mlx5_ib_mr *mr = odp->private, *imr = mr->parent;
+	struct ib_umem_odp *odp_imr = to_ib_umem_odp(imr->umem);
+	int srcu_key;
 
 	mr->parent = NULL;
 	synchronize_srcu(&mr->dev->mr_srcu);
 
-	ib_umem_odp_release(odp);
-	if (imr->live)
+	if (imr->live) {
+		srcu_key = srcu_read_lock(&mr->dev->mr_srcu);
+		mutex_lock(&odp_imr->umem_mutex);
 		mlx5_ib_update_xlt(imr, idx, 1, 0,
 				   MLX5_IB_UPD_XLT_INDIRECT |
 				   MLX5_IB_UPD_XLT_ATOMIC);
+		mutex_unlock(&odp_imr->umem_mutex);
+		srcu_read_unlock(&mr->dev->mr_srcu, srcu_key);
+	}
+	ib_umem_odp_release(odp);
 	mlx5_mr_cache_free(mr->dev, mr);
 
 	if (atomic_dec_and_test(&imr->num_leaf_free))
-- 
cgit v1.2.3


From 9dc775e7f5508f848661bbfb2e15683affb85f24 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Tue, 1 Oct 2019 12:38:18 -0300
Subject: RDMA/odp: Lift umem_mutex out of ib_umem_odp_unmap_dma_pages()

This fixes a race of the form:
    CPU0                               CPU1
mlx5_ib_invalidate_range()     mlx5_ib_invalidate_range()
				 // This one actually makes npages == 0
				 ib_umem_odp_unmap_dma_pages()
				 if (npages == 0 && !dying)
  // This one does nothing
  ib_umem_odp_unmap_dma_pages()
  if (npages == 0 && !dying)
     dying = 1;
                                    dying = 1;
				    schedule_work(&umem_odp->work);
     // Double schedule of the same work
     schedule_work(&umem_odp->work);  // BOOM

npages and dying must be read and written under the umem_mutex lock.

Since whenever ib_umem_odp_unmap_dma_pages() is called mlx5 must also call
mlx5_ib_update_xlt, and both need to be done in the same locking region,
hoist the lock out of unmap.

This avoids an expensive double critical section in
mlx5_ib_invalidate_range().

Fixes: 81713d3788d2 ("IB/mlx5: Add implicit MR support")
Link: https://lore.kernel.org/r/20191001153821.23621-4-jgg@ziepe.ca
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/core/umem_odp.c |  6 ++++--
 drivers/infiniband/hw/mlx5/odp.c   | 12 ++++++++----
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index f67a30fda1ed..163ff7ba92b7 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -451,8 +451,10 @@ void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
 	 * that the hardware will not attempt to access the MR any more.
 	 */
 	if (!umem_odp->is_implicit_odp) {
+		mutex_lock(&umem_odp->umem_mutex);
 		ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp),
 					    ib_umem_end(umem_odp));
+		mutex_unlock(&umem_odp->umem_mutex);
 		kvfree(umem_odp->dma_list);
 		kvfree(umem_odp->page_list);
 	}
@@ -719,6 +721,8 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt,
 	u64 addr;
 	struct ib_device *dev = umem_odp->umem.ibdev;
 
+	lockdep_assert_held(&umem_odp->umem_mutex);
+
 	virt = max_t(u64, virt, ib_umem_start(umem_odp));
 	bound = min_t(u64, bound, ib_umem_end(umem_odp));
 	/* Note that during the run of this function, the
@@ -726,7 +730,6 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt,
 	 * faults from completion. We might be racing with other
 	 * invalidations, so we must make sure we free each page only
 	 * once. */
-	mutex_lock(&umem_odp->umem_mutex);
 	for (addr = virt; addr < bound; addr += BIT(umem_odp->page_shift)) {
 		idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
 		if (umem_odp->page_list[idx]) {
@@ -757,7 +760,6 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 virt,
 			umem_odp->npages--;
 		}
 	}
-	mutex_unlock(&umem_odp->umem_mutex);
 }
 EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages);
 
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 3401c06b7e54..1930d78c3091 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -308,7 +308,6 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
 				   idx - blk_start_idx + 1, 0,
 				   MLX5_IB_UPD_XLT_ZAP |
 				   MLX5_IB_UPD_XLT_ATOMIC);
-	mutex_unlock(&umem_odp->umem_mutex);
 	/*
 	 * We are now sure that the device will not access the
 	 * memory. We can safely unmap it, and mark it as dirty if
@@ -319,10 +318,11 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
 
 	if (unlikely(!umem_odp->npages && mr->parent &&
 		     !umem_odp->dying)) {
-		WRITE_ONCE(umem_odp->dying, 1);
+		umem_odp->dying = 1;
 		atomic_inc(&mr->parent->num_leaf_free);
 		schedule_work(&umem_odp->work);
 	}
+	mutex_unlock(&umem_odp->umem_mutex);
 }
 
 void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
@@ -585,15 +585,19 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr)
 		if (mr->parent != imr)
 			continue;
 
+		mutex_lock(&umem_odp->umem_mutex);
 		ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp),
 					    ib_umem_end(umem_odp));
 
-		if (umem_odp->dying)
+		if (umem_odp->dying) {
+			mutex_unlock(&umem_odp->umem_mutex);
 			continue;
+		}
 
-		WRITE_ONCE(umem_odp->dying, 1);
+		umem_odp->dying = 1;
 		atomic_inc(&imr->num_leaf_free);
 		schedule_work(&umem_odp->work);
+		mutex_unlock(&umem_odp->umem_mutex);
 	}
 	up_read(&per_mm->umem_rwsem);
 
-- 
cgit v1.2.3


From aa116b810ac9077a263ed8679fb4d595f180e0eb Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Tue, 1 Oct 2019 12:38:19 -0300
Subject: RDMA/mlx5: Order num_pending_prefetch properly with synchronize_srcu

During destroy setting live = 0 and then synchronize_srcu() prevents
num_pending_prefetch from incrementing, and also, ensures that all work
holding that count is queued on the WQ. Testing before causes races of the
form:

    CPU0                                         CPU1
  dereg_mr()
                                          mlx5_ib_advise_mr_prefetch()
            				   srcu_read_lock()
                                            num_pending_prefetch_inc()
					      if (!live)
   live = 0
   atomic_read() == 0
     // skip flush_workqueue()
                                              atomic_inc()
 					      queue_work();
            				   srcu_read_unlock()
   WARN_ON(atomic_read())  // Fails

Swap the order so that the synchronize_srcu() prevents this.

Fixes: a6bc3875f176 ("IB/mlx5: Protect against prefetch of invalid MR")
Link: https://lore.kernel.org/r/20191001153821.23621-5-jgg@ziepe.ca
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/mr.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index e7f840f306e4..0ee8fa01177f 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1609,13 +1609,14 @@ static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 		 */
 		mr->live = 0;
 
+		/* Wait for all running page-fault handlers to finish. */
+		synchronize_srcu(&dev->mr_srcu);
+
 		/* dequeue pending prefetch requests for the mr */
 		if (atomic_read(&mr->num_pending_prefetch))
 			flush_workqueue(system_unbound_wq);
 		WARN_ON(atomic_read(&mr->num_pending_prefetch));
 
-		/* Wait for all running page-fault handlers to finish. */
-		synchronize_srcu(&dev->mr_srcu);
 		/* Destroy all page mappings */
 		if (!umem_odp->is_implicit_odp)
 			mlx5_ib_invalidate_range(umem_odp,
-- 
cgit v1.2.3


From aa603815c7f8a8f368d6d8ea6ebf601429883439 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Tue, 1 Oct 2019 12:38:20 -0300
Subject: RDMA/mlx5: Put live in the correct place for ODP MRs

live is used to signal to the pagefault thread that the MR is initialized
and ready for use. It should be after the umem is assigned and all other
setup is completed. This prevents races (at least) of the form:

    CPU0                                     CPU1
mlx5_ib_alloc_implicit_mr()
 implicit_mr_alloc()
  live = 1
 imr->umem = umem
                                    num_pending_prefetch_inc()
                                      if (live)
				        atomic_inc(num_pending_prefetch)
 atomic_set(num_pending_prefetch,0) // Overwrites other thread's store

Further, live is being used with SRCU as the 'update' in an
acquire/release fashion, so it can not be read and written raw.

Move all live = 1's to after MR initialization is completed and use
smp_store_release/smp_load_acquire() for manipulating it.

Add a missing live = 0 when an implicit MR child is deleted, before
queuing work to do synchronize_srcu().

The barriers in update_odp_mr() were some broken attempt to create a
acquire/release, but were not even applied consistently and missed the
point, delete it as well.

Fixes: 6aec21f6a832 ("IB/mlx5: Page faults handling infrastructure")
Link: https://lore.kernel.org/r/20191001153821.23621-6-jgg@ziepe.ca
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  2 +-
 drivers/infiniband/hw/mlx5/mr.c      | 36 +++++-------------------------------
 drivers/infiniband/hw/mlx5/odp.c     | 14 ++++++++------
 3 files changed, 14 insertions(+), 38 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 2ceaef3ea3fb..15e42825cc97 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -606,7 +606,7 @@ struct mlx5_ib_mr {
 	struct mlx5_ib_dev     *dev;
 	u32 out[MLX5_ST_SZ_DW(create_mkey_out)];
 	struct mlx5_core_sig_ctx    *sig;
-	int			live;
+	unsigned int		live;
 	void			*descs_alloc;
 	int			access_flags; /* Needed for rereg MR */
 
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 0ee8fa01177f..3a27bddfcf31 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -84,32 +84,6 @@ static bool use_umr_mtt_update(struct mlx5_ib_mr *mr, u64 start, u64 length)
 		length + (start & (MLX5_ADAPTER_PAGE_SIZE - 1));
 }
 
-static void update_odp_mr(struct mlx5_ib_mr *mr)
-{
-	if (is_odp_mr(mr)) {
-		/*
-		 * This barrier prevents the compiler from moving the
-		 * setting of umem->odp_data->private to point to our
-		 * MR, before reg_umr finished, to ensure that the MR
-		 * initialization have finished before starting to
-		 * handle invalidations.
-		 */
-		smp_wmb();
-		to_ib_umem_odp(mr->umem)->private = mr;
-		/*
-		 * Make sure we will see the new
-		 * umem->odp_data->private value in the invalidation
-		 * routines, before we can get page faults on the
-		 * MR. Page faults can happen once we put the MR in
-		 * the tree, below this line. Without the barrier,
-		 * there can be a fault handling and an invalidation
-		 * before umem->odp_data->private == mr is visible to
-		 * the invalidation handler.
-		 */
-		smp_wmb();
-	}
-}
-
 static void reg_mr_callback(int status, struct mlx5_async_work *context)
 {
 	struct mlx5_ib_mr *mr =
@@ -1346,8 +1320,6 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	mr->umem = umem;
 	set_mr_fields(dev, mr, npages, length, access_flags);
 
-	update_odp_mr(mr);
-
 	if (use_umr) {
 		int update_xlt_flags = MLX5_IB_UPD_XLT_ENABLE;
 
@@ -1363,10 +1335,12 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		}
 	}
 
-	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
-		mr->live = 1;
+	if (is_odp_mr(mr)) {
+		to_ib_umem_odp(mr->umem)->private = mr;
 		atomic_set(&mr->num_pending_prefetch, 0);
 	}
+	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING))
+		smp_store_release(&mr->live, 1);
 
 	return &mr->ibmr;
 error:
@@ -1607,7 +1581,7 @@ static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 		/* Prevent new page faults and
 		 * prefetch requests from succeeding
 		 */
-		mr->live = 0;
+		WRITE_ONCE(mr->live, 0);
 
 		/* Wait for all running page-fault handlers to finish. */
 		synchronize_srcu(&dev->mr_srcu);
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 1930d78c3091..3f9478d19376 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -231,7 +231,7 @@ static void mr_leaf_free_action(struct work_struct *work)
 	mr->parent = NULL;
 	synchronize_srcu(&mr->dev->mr_srcu);
 
-	if (imr->live) {
+	if (smp_load_acquire(&imr->live)) {
 		srcu_key = srcu_read_lock(&mr->dev->mr_srcu);
 		mutex_lock(&odp_imr->umem_mutex);
 		mlx5_ib_update_xlt(imr, idx, 1, 0,
@@ -318,6 +318,7 @@ void mlx5_ib_invalidate_range(struct ib_umem_odp *umem_odp, unsigned long start,
 
 	if (unlikely(!umem_odp->npages && mr->parent &&
 		     !umem_odp->dying)) {
+		WRITE_ONCE(mr->live, 0);
 		umem_odp->dying = 1;
 		atomic_inc(&mr->parent->num_leaf_free);
 		schedule_work(&umem_odp->work);
@@ -459,8 +460,6 @@ static struct mlx5_ib_mr *implicit_mr_alloc(struct ib_pd *pd,
 	mr->ibmr.lkey = mr->mmkey.key;
 	mr->ibmr.rkey = mr->mmkey.key;
 
-	mr->live = 1;
-
 	mlx5_ib_dbg(dev, "key %x dev %p mr %p\n",
 		    mr->mmkey.key, dev->mdev, mr);
 
@@ -514,6 +513,8 @@ next_mr:
 		mtt->parent = mr;
 		INIT_WORK(&odp->work, mr_leaf_free_action);
 
+		smp_store_release(&mtt->live, 1);
+
 		if (!nentries)
 			start_idx = addr >> MLX5_IMR_MTT_SHIFT;
 		nentries++;
@@ -566,6 +567,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd,
 	init_waitqueue_head(&imr->q_leaf_free);
 	atomic_set(&imr->num_leaf_free, 0);
 	atomic_set(&imr->num_pending_prefetch, 0);
+	smp_store_release(&imr->live, 1);
 
 	return imr;
 }
@@ -807,7 +809,7 @@ next_mr:
 	switch (mmkey->type) {
 	case MLX5_MKEY_MR:
 		mr = container_of(mmkey, struct mlx5_ib_mr, mmkey);
-		if (!mr->live || !mr->ibmr.pd) {
+		if (!smp_load_acquire(&mr->live) || !mr->ibmr.pd) {
 			mlx5_ib_dbg(dev, "got dead MR\n");
 			ret = -EFAULT;
 			goto srcu_unlock;
@@ -1675,12 +1677,12 @@ static bool num_pending_prefetch_inc(struct ib_pd *pd,
 
 		mr = container_of(mmkey, struct mlx5_ib_mr, mmkey);
 
-		if (mr->ibmr.pd != pd) {
+		if (!smp_load_acquire(&mr->live)) {
 			ret = false;
 			break;
 		}
 
-		if (!mr->live) {
+		if (mr->ibmr.pd != pd) {
 			ret = false;
 			break;
 		}
-- 
cgit v1.2.3


From 0417791536ae1e28d7f0418f1d20048ec4d3c6cf Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Tue, 1 Oct 2019 12:38:21 -0300
Subject: RDMA/mlx5: Add missing synchronize_srcu() for MW cases

While MR uses live as the SRCU 'update', the MW case uses the xarray
directly, xa_erase() causes the MW to become inaccessible to the pagefault
thread.

Thus whenever a MW is removed from the xarray we must synchronize_srcu()
before freeing it.

This must be done before freeing the mkey as re-use of the mkey while the
pagefault thread is using the stale mkey is undesirable.

Add the missing synchronizes to MW and DEVX indirect mkey and delete the
bogus protection against double destroy in mlx5_core_destroy_mkey()

Fixes: 534fd7aac56a ("IB/mlx5: Manage indirection mkey upon DEVX flow for ODP")
Fixes: 6aec21f6a832 ("IB/mlx5: Page faults handling infrastructure")
Link: https://lore.kernel.org/r/20191001153821.23621-7-jgg@ziepe.ca
Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
---
 drivers/infiniband/hw/mlx5/devx.c            | 58 ++++++++--------------------
 drivers/infiniband/hw/mlx5/mlx5_ib.h         |  1 -
 drivers/infiniband/hw/mlx5/mr.c              | 21 +++++++---
 drivers/net/ethernet/mellanox/mlx5/core/mr.c |  8 +---
 4 files changed, 33 insertions(+), 55 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 59022b744144..d609f4659afb 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1298,29 +1298,6 @@ static int devx_handle_mkey_create(struct mlx5_ib_dev *dev,
 	return 0;
 }
 
-static void devx_free_indirect_mkey(struct rcu_head *rcu)
-{
-	kfree(container_of(rcu, struct devx_obj, devx_mr.rcu));
-}
-
-/* This function to delete from the radix tree needs to be called before
- * destroying the underlying mkey. Otherwise a race might occur in case that
- * other thread will get the same mkey before this one will be deleted,
- * in that case it will fail via inserting to the tree its own data.
- *
- * Note:
- * An error in the destroy is not expected unless there is some other indirect
- * mkey which points to this one. In a kernel cleanup flow it will be just
- * destroyed in the iterative destruction call. In a user flow, in case
- * the application didn't close in the expected order it's its own problem,
- * the mkey won't be part of the tree, in both cases the kernel is safe.
- */
-static void devx_cleanup_mkey(struct devx_obj *obj)
-{
-	xa_erase(&obj->ib_dev->mdev->priv.mkey_table,
-		 mlx5_base_mkey(obj->devx_mr.mmkey.key));
-}
-
 static void devx_cleanup_subscription(struct mlx5_ib_dev *dev,
 				      struct devx_event_subscription *sub)
 {
@@ -1362,8 +1339,16 @@ static int devx_obj_cleanup(struct ib_uobject *uobject,
 	int ret;
 
 	dev = mlx5_udata_to_mdev(&attrs->driver_udata);
-	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY)
-		devx_cleanup_mkey(obj);
+	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) {
+		/*
+		 * The pagefault_single_data_segment() does commands against
+		 * the mmkey, we must wait for that to stop before freeing the
+		 * mkey, as another allocation could get the same mkey #.
+		 */
+		xa_erase(&obj->ib_dev->mdev->priv.mkey_table,
+			 mlx5_base_mkey(obj->devx_mr.mmkey.key));
+		synchronize_srcu(&dev->mr_srcu);
+	}
 
 	if (obj->flags & DEVX_OBJ_FLAGS_DCT)
 		ret = mlx5_core_destroy_dct(obj->ib_dev->mdev, &obj->core_dct);
@@ -1382,12 +1367,6 @@ static int devx_obj_cleanup(struct ib_uobject *uobject,
 		devx_cleanup_subscription(dev, sub_entry);
 	mutex_unlock(&devx_event_table->event_xa_lock);
 
-	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) {
-		call_srcu(&dev->mr_srcu, &obj->devx_mr.rcu,
-			  devx_free_indirect_mkey);
-		return ret;
-	}
-
 	kfree(obj);
 	return ret;
 }
@@ -1491,26 +1470,21 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)(
 				   &obj_id);
 	WARN_ON(obj->dinlen > MLX5_MAX_DESTROY_INBOX_SIZE_DW * sizeof(u32));
 
-	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) {
-		err = devx_handle_mkey_indirect(obj, dev, cmd_in, cmd_out);
-		if (err)
-			goto obj_destroy;
-	}
-
 	err = uverbs_copy_to(attrs, MLX5_IB_ATTR_DEVX_OBJ_CREATE_CMD_OUT, cmd_out, cmd_out_len);
 	if (err)
-		goto err_copy;
+		goto obj_destroy;
 
 	if (opcode == MLX5_CMD_OP_CREATE_GENERAL_OBJECT)
 		obj_type = MLX5_GET(general_obj_in_cmd_hdr, cmd_in, obj_type);
-
 	obj->obj_id = get_enc_obj_id(opcode | obj_type << 16, obj_id);
 
+	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) {
+		err = devx_handle_mkey_indirect(obj, dev, cmd_in, cmd_out);
+		if (err)
+			goto obj_destroy;
+	}
 	return 0;
 
-err_copy:
-	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY)
-		devx_cleanup_mkey(obj);
 obj_destroy:
 	if (obj->flags & DEVX_OBJ_FLAGS_DCT)
 		mlx5_core_destroy_dct(obj->ib_dev->mdev, &obj->core_dct);
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 15e42825cc97..1a98ee2e01c4 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -639,7 +639,6 @@ struct mlx5_ib_mw {
 struct mlx5_ib_devx_mr {
 	struct mlx5_core_mkey	mmkey;
 	int			ndescs;
-	struct rcu_head		rcu;
 };
 
 struct mlx5_ib_umr_context {
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 3a27bddfcf31..630599311586 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1962,14 +1962,25 @@ free:
 
 int mlx5_ib_dealloc_mw(struct ib_mw *mw)
 {
+	struct mlx5_ib_dev *dev = to_mdev(mw->device);
 	struct mlx5_ib_mw *mmw = to_mmw(mw);
 	int err;
 
-	err =  mlx5_core_destroy_mkey((to_mdev(mw->device))->mdev,
-				      &mmw->mmkey);
-	if (!err)
-		kfree(mmw);
-	return err;
+	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
+		xa_erase(&dev->mdev->priv.mkey_table,
+			 mlx5_base_mkey(mmw->mmkey.key));
+		/*
+		 * pagefault_single_data_segment() may be accessing mmw under
+		 * SRCU if the user bound an ODP MR to this MW.
+		 */
+		synchronize_srcu(&dev->mr_srcu);
+	}
+
+	err = mlx5_core_destroy_mkey(dev->mdev, &mmw->mmkey);
+	if (err)
+		return err;
+	kfree(mmw);
+	return 0;
 }
 
 int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 9231b39d18b2..c501bf2a0252 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -112,17 +112,11 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev,
 	u32 out[MLX5_ST_SZ_DW(destroy_mkey_out)] = {0};
 	u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)]   = {0};
 	struct xarray *mkeys = &dev->priv.mkey_table;
-	struct mlx5_core_mkey *deleted_mkey;
 	unsigned long flags;
 
 	xa_lock_irqsave(mkeys, flags);
-	deleted_mkey = __xa_erase(mkeys, mlx5_base_mkey(mkey->key));
+	__xa_erase(mkeys, mlx5_base_mkey(mkey->key));
 	xa_unlock_irqrestore(mkeys, flags);
-	if (!deleted_mkey) {
-		mlx5_core_dbg(dev, "failed xarray delete of mkey 0x%x\n",
-			      mlx5_base_mkey(mkey->key));
-		return -ENOENT;
-	}
 
 	MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY);
 	MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key));
-- 
cgit v1.2.3


From cf74ac6db25d4002089e85cc623ad149ecc25614 Mon Sep 17 00:00:00 2001
From: Reinhard Speyerer <rspmn@arcor.de>
Date: Thu, 3 Oct 2019 18:34:39 +0200
Subject: qmi_wwan: add support for Cinterion CLS8 devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for Cinterion CLS8 devices.
Use QMI_QUIRK_SET_DTR as required for Qualcomm MDM9x07 chipsets.

T:  Bus=01 Lev=03 Prnt=05 Port=01 Cnt=02 Dev#= 25 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1e2d ProdID=00b0 Rev= 3.18
S:  Manufacturer=GEMALTO
S:  Product=USB Modem
C:* #Ifs= 5 Cfg#= 1 Atr=80 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=83(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=85(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=87(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=89(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Signed-off-by: Reinhard Speyerer <rspmn@arcor.de>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index b6dc5d714b5e..3d77cd402ba9 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1350,6 +1350,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x1e2d, 0x0082, 4)},	/* Cinterion PHxx,PXxx (2 RmNet) */
 	{QMI_FIXED_INTF(0x1e2d, 0x0082, 5)},	/* Cinterion PHxx,PXxx (2 RmNet) */
 	{QMI_FIXED_INTF(0x1e2d, 0x0083, 4)},	/* Cinterion PHxx,PXxx (1 RmNet + USB Audio)*/
+	{QMI_QUIRK_SET_DTR(0x1e2d, 0x00b0, 4)},	/* Cinterion CLS8 */
 	{QMI_FIXED_INTF(0x413c, 0x81a2, 8)},	/* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a3, 8)},	/* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a4, 8)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
-- 
cgit v1.2.3


From db9b2e0af605e7c994784527abfd9276cabd718a Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 3 Oct 2019 17:44:44 +0100
Subject: rxrpc: Fix rxrpc_recvmsg tracepoint

Fix the rxrpc_recvmsg tracepoint to handle being called with a NULL call
parameter.

Fixes: a25e21f0bcd2 ("rxrpc, afs: Use debug_ids rather than pointers in traces")
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/rxrpc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index a13a62db3565..edc5c887a44c 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -1068,7 +1068,7 @@ TRACE_EVENT(rxrpc_recvmsg,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call->debug_id;
+		    __entry->call = call ? call->debug_id : 0;
 		    __entry->why = why;
 		    __entry->seq = seq;
 		    __entry->offset = offset;
-- 
cgit v1.2.3


From 7a512eb865aa5fcfb396c71047bc9c3b046836b3 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Fri, 4 Oct 2019 00:44:40 +0300
Subject: net: make sock_prot_memory_pressure() return "const char *"

This function returns string literals which are "const char *".

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index e23ec80a67bf..fac2b4d80de5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3497,7 +3497,7 @@ static long sock_prot_memory_allocated(struct proto *proto)
 	return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L;
 }
 
-static char *sock_prot_memory_pressure(struct proto *proto)
+static const char *sock_prot_memory_pressure(struct proto *proto)
 {
 	return proto->memory_pressure != NULL ?
 	proto_memory_pressure(proto) ? "yes" : "no" : "NI";
-- 
cgit v1.2.3


From 8ae72cbf62d2c1879456c0c5872f958e18f53711 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Thu, 3 Oct 2019 14:46:15 -0700
Subject: Revert "ipv6: Handle race in addrconf_dad_work"

This reverts commit a3ce2a21bb8969ae27917281244fa91bf5f286d7.

Eric reported tests failings with commit. After digging into it,
the bottom line is that the DAD sequence is not to be messed with.
There are too many cases that are expected to proceed regardless
of whether a device is up.

Revert the patch and I will send a different solution for the
problem Rajendra reported.

Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index dd3be06d5a06..6a576ff92c39 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4032,12 +4032,6 @@ static void addrconf_dad_work(struct work_struct *w)
 
 	rtnl_lock();
 
-	/* check if device was taken down before this delayed work
-	 * function could be canceled
-	 */
-	if (idev->dead || !(idev->if_flags & IF_READY))
-		goto out;
-
 	spin_lock_bh(&ifp->lock);
 	if (ifp->state == INET6_IFADDR_STATE_PREDAD) {
 		action = DAD_BEGIN;
@@ -4083,6 +4077,11 @@ static void addrconf_dad_work(struct work_struct *w)
 		goto out;
 
 	write_lock_bh(&idev->lock);
+	if (idev->dead || !(idev->if_flags & IF_READY)) {
+		write_unlock_bh(&idev->lock);
+		goto out;
+	}
+
 	spin_lock(&ifp->lock);
 	if (ifp->state == INET6_IFADDR_STATE_DEAD) {
 		spin_unlock(&ifp->lock);
-- 
cgit v1.2.3


From 6b517374f4ea5a3c6e307e1219ec5f35d42e6d00 Mon Sep 17 00:00:00 2001
From: Vishal Kulkarni <vishal@chelsio.com>
Date: Fri, 4 Oct 2019 04:06:15 +0530
Subject: cxgb4:Fix out-of-bounds MSI-X info array access

When fetching free MSI-X vectors for ULDs, check for the error code
before accessing MSI-X info array. Otherwise, an out-of-bounds access is
attempted, which results in kernel panic.

Fixes: 94cdb8bb993a ("cxgb4: Add support for dynamic allocation of resources for ULD")
Signed-off-by: Shahjada Abul Husain <shahjada@chelsio.com>
Signed-off-by: Vishal Kulkarni <vishal@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index 5b602243d573..a4dead4ab0ed 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -137,13 +137,12 @@ static int uldrx_handler(struct sge_rspq *q, const __be64 *rsp,
 static int alloc_uld_rxqs(struct adapter *adap,
 			  struct sge_uld_rxq_info *rxq_info, bool lro)
 {
-	struct sge *s = &adap->sge;
 	unsigned int nq = rxq_info->nrxq + rxq_info->nciq;
+	int i, err, msi_idx, que_idx = 0, bmap_idx = 0;
 	struct sge_ofld_rxq *q = rxq_info->uldrxq;
 	unsigned short *ids = rxq_info->rspq_id;
-	unsigned int bmap_idx = 0;
+	struct sge *s = &adap->sge;
 	unsigned int per_chan;
-	int i, err, msi_idx, que_idx = 0;
 
 	per_chan = rxq_info->nrxq / adap->params.nports;
 
@@ -161,6 +160,10 @@ static int alloc_uld_rxqs(struct adapter *adap,
 
 		if (msi_idx >= 0) {
 			bmap_idx = get_msix_idx_from_bmap(adap);
+			if (bmap_idx < 0) {
+				err = -ENOSPC;
+				goto freeout;
+			}
 			msi_idx = adap->msix_info_ulds[bmap_idx].idx;
 		}
 		err = t4_sge_alloc_rxq(adap, &q->rspq, false,
-- 
cgit v1.2.3


From fffa6af94894126994a7600c6f6f09b892e89fa9 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Wed, 2 Oct 2019 14:28:23 +0200
Subject: gpio: max77620: Use correct unit for debounce times

The gpiod_set_debounce() function takes the debounce time in
microseconds. Adjust the switch/case values in the MAX77620 GPIO to use
the correct unit.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://lore.kernel.org/r/20191002122825.3948322-1-thierry.reding@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-max77620.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/gpio-max77620.c b/drivers/gpio/gpio-max77620.c
index 47d05e357e61..faf86ea9c51a 100644
--- a/drivers/gpio/gpio-max77620.c
+++ b/drivers/gpio/gpio-max77620.c
@@ -192,13 +192,13 @@ static int max77620_gpio_set_debounce(struct max77620_gpio *mgpio,
 	case 0:
 		val = MAX77620_CNFG_GPIO_DBNC_None;
 		break;
-	case 1 ... 8:
+	case 1000 ... 8000:
 		val = MAX77620_CNFG_GPIO_DBNC_8ms;
 		break;
-	case 9 ... 16:
+	case 9000 ... 16000:
 		val = MAX77620_CNFG_GPIO_DBNC_16ms;
 		break;
-	case 17 ... 32:
+	case 17000 ... 32000:
 		val = MAX77620_CNFG_GPIO_DBNC_32ms;
 		break;
 	default:
-- 
cgit v1.2.3


From 6abff1b9f7b8884a46b7bd80b49e7af0b5625aeb Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Wed, 2 Oct 2019 10:52:25 -0700
Subject: nvme: fix possible deadlock when nvme_update_formats fails

nvme_update_formats may fail to revalidate the namespace and
attempt to remove the namespace. This may lead to a deadlock
as nvme_ns_remove will attempt to acquire the subsystem lock
which is already acquired by the passthru command with effects.

Move the invalid namepsace removal to after the passthru command
releases the subsystem lock.

Reported-by: Judy Brock <judy.brock@samsung.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index fd7dea36c3b6..ef1d8f81f69e 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1306,8 +1306,6 @@ static void nvme_update_formats(struct nvme_ctrl *ctrl)
 		if (ns->disk && nvme_revalidate_disk(ns->disk))
 			nvme_set_queue_dying(ns);
 	up_read(&ctrl->namespaces_rwsem);
-
-	nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
 }
 
 static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
@@ -1323,6 +1321,7 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
 		nvme_unfreeze(ctrl);
 		nvme_mpath_unfreeze(ctrl->subsys);
 		mutex_unlock(&ctrl->subsys->lock);
+		nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
 		mutex_unlock(&ctrl->scan_lock);
 	}
 	if (effects & NVME_CMD_EFFECTS_CCC)
-- 
cgit v1.2.3


From 3a8ecc935efabdad106b5e06d07b150c394b4465 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Thu, 3 Oct 2019 13:57:29 +0200
Subject: nvme: retain split access workaround for capability reads

Commit 7fd8930f26be4

  "nvme: add a common helper to read Identify Controller data"

has re-introduced an issue that we have attempted to work around in the
past, in commit a310acd7a7ea ("NVMe: use split lo_hi_{read,write}q").

The problem is that some PCIe NVMe controllers do not implement 64-bit
outbound accesses correctly, which is why the commit above switched
to using lo_hi_[read|write]q for all 64-bit BAR accesses occuring in
the code.

In the mean time, the NVMe subsystem has been refactored, and now calls
into the PCIe support layer for NVMe via a .reg_read64() method, which
fails to use lo_hi_readq(), and thus reintroduces the problem that the
workaround above aimed to address.

Given that, at the moment, .reg_read64() is only used to read the
capability register [which is known to tolerate split reads], let's
switch .reg_read64() to lo_hi_readq() as well.

This fixes a boot issue on some ARM boxes with NVMe behind a Synopsys
DesignWare PCIe host controller.

Fixes: 7fd8930f26be4 ("nvme: add a common helper to read Identify Controller data")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 drivers/nvme/host/pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index bb88681f4dc3..78e403823646 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2672,7 +2672,7 @@ static int nvme_pci_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 
 static int nvme_pci_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 {
-	*val = readq(to_nvme_dev(ctrl)->bar + off);
+	*val = lo_hi_readq(to_nvme_dev(ctrl)->bar + off);
 	return 0;
 }
 
-- 
cgit v1.2.3


From a54cdeeb04fc719e4c7f19d6e28dba7ea86cee5b Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Fri, 4 Oct 2019 20:51:04 +0800
Subject: r8152: Set macpassthru in reset_resume callback

r8152 may fail to establish network connection after resume from system
suspend.

If the USB port connects to r8152 lost its power during system suspend,
the MAC address was written before is lost. The reason is that The MAC
address doesn't get written again in its reset_resume callback.

So let's set MAC address again in reset_resume callback. Also remove
unnecessary lock as no other locking attempt will happen during
reset_resume.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 08726090570e..cee9fef925cd 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -4799,10 +4799,9 @@ static int rtl8152_reset_resume(struct usb_interface *intf)
 	struct r8152 *tp = usb_get_intfdata(intf);
 
 	clear_bit(SELECTIVE_SUSPEND, &tp->flags);
-	mutex_lock(&tp->control);
 	tp->rtl_ops.init(tp);
 	queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
-	mutex_unlock(&tp->control);
+	set_ethernet_addr(tp);
 	return rtl8152_resume(intf);
 }
 
-- 
cgit v1.2.3


From b406472b5ad79ede8d10077f0c8f05505ace8b6d Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 4 Oct 2019 15:11:17 +0200
Subject: net: ipv4: avoid mixed n_redirects and rate_tokens usage

Since commit c09551c6ff7f ("net: ipv4: use a dedicated counter
for icmp_v4 redirect packets") we use 'n_redirects' to account
for redirect packets, but we still use 'rate_tokens' to compute
the redirect packets exponential backoff.

If the device sent to the relevant peer any ICMP error packet
after sending a redirect, it will also update 'rate_token' according
to the leaking bucket schema; typically 'rate_token' will raise
above BITS_PER_LONG and the redirect packets backoff algorithm
will produce undefined behavior.

Fix the issue using 'n_redirects' to compute the exponential backoff
in ip_rt_send_redirect().

Note that we still clear rate_tokens after a redirect silence period,
to avoid changing an established behaviour.

The root cause predates git history; before the mentioned commit in
the critical scenario, the kernel stopped sending redirects, after
the mentioned commit the behavior more randomic.

Reported-by: Xiumei Mu <xmu@redhat.com>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Fixes: c09551c6ff7f ("net: ipv4: use a dedicated counter for icmp_v4 redirect packets")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7dcce724c78b..14654876127e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -916,16 +916,15 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	if (peer->rate_tokens == 0 ||
 	    time_after(jiffies,
 		       (peer->rate_last +
-			(ip_rt_redirect_load << peer->rate_tokens)))) {
+			(ip_rt_redirect_load << peer->n_redirects)))) {
 		__be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr);
 
 		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
 		peer->rate_last = jiffies;
-		++peer->rate_tokens;
 		++peer->n_redirects;
 #ifdef CONFIG_IP_ROUTE_VERBOSE
 		if (log_martians &&
-		    peer->rate_tokens == ip_rt_redirect_number)
+		    peer->n_redirects == ip_rt_redirect_number)
 			net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
 					     &ip_hdr(skb)->saddr, inet_iif(skb),
 					     &ip_hdr(skb)->daddr, &gw);
-- 
cgit v1.2.3


From ea977d19d918324ad5b66953f051a6ed07d0a3c5 Mon Sep 17 00:00:00 2001
From: Andrea Merello <andrea.merello@gmail.com>
Date: Fri, 4 Oct 2019 15:53:32 +0200
Subject: net: phy: allow for reset line to be tied to a sleepy GPIO controller

mdio_device_reset() makes use of the atomic-pretending API flavor for
handling the PHY reset GPIO line.

I found no hint that mdio_device_reset() is called from atomic context
and indeed it uses usleep_range() since long time, so I would assume that
it is OK to sleep there.

This patch switch to gpiod_set_value_cansleep() in mdio_device_reset().
This is relevant if e.g. the PHY reset line is tied to a I2C GPIO
controller.

This has been tested on a ZynqMP board running an upstream 4.19 kernel and
then hand-ported on current kernel tree.

Signed-off-by: Andrea Merello <andrea.merello@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c
index e282600bd83e..c1d345c3cab3 100644
--- a/drivers/net/phy/mdio_device.c
+++ b/drivers/net/phy/mdio_device.c
@@ -121,7 +121,7 @@ void mdio_device_reset(struct mdio_device *mdiodev, int value)
 		return;
 
 	if (mdiodev->reset_gpio)
-		gpiod_set_value(mdiodev->reset_gpio, value);
+		gpiod_set_value_cansleep(mdiodev->reset_gpio, value);
 
 	if (mdiodev->reset_ctrl) {
 		if (value)
-- 
cgit v1.2.3


From 2d819d250a1393a3e725715425ab70a0e0772a71 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 4 Oct 2019 08:03:09 -0700
Subject: ipv6: Handle missing host route in __ipv6_ifa_notify

Rajendra reported a kernel panic when a link was taken down:

    [ 6870.263084] BUG: unable to handle kernel NULL pointer dereference at 00000000000000a8
    [ 6870.271856] IP: [<ffffffff8efc5764>] __ipv6_ifa_notify+0x154/0x290

    <snip>

    [ 6870.570501] Call Trace:
    [ 6870.573238] [<ffffffff8efc58c6>] ? ipv6_ifa_notify+0x26/0x40
    [ 6870.579665] [<ffffffff8efc98ec>] ? addrconf_dad_completed+0x4c/0x2c0
    [ 6870.586869] [<ffffffff8efe70c6>] ? ipv6_dev_mc_inc+0x196/0x260
    [ 6870.593491] [<ffffffff8efc9c6a>] ? addrconf_dad_work+0x10a/0x430
    [ 6870.600305] [<ffffffff8f01ade4>] ? __switch_to_asm+0x34/0x70
    [ 6870.606732] [<ffffffff8ea93a7a>] ? process_one_work+0x18a/0x430
    [ 6870.613449] [<ffffffff8ea93d6d>] ? worker_thread+0x4d/0x490
    [ 6870.619778] [<ffffffff8ea93d20>] ? process_one_work+0x430/0x430
    [ 6870.626495] [<ffffffff8ea99dd9>] ? kthread+0xd9/0xf0
    [ 6870.632145] [<ffffffff8f01ade4>] ? __switch_to_asm+0x34/0x70
    [ 6870.638573] [<ffffffff8ea99d00>] ? kthread_park+0x60/0x60
    [ 6870.644707] [<ffffffff8f01ae77>] ? ret_from_fork+0x57/0x70
    [ 6870.650936] Code: 31 c0 31 d2 41 b9 20 00 08 02 b9 09 00 00 0

addrconf_dad_work is kicked to be scheduled when a device is brought
up. There is a race between addrcond_dad_work getting scheduled and
taking the rtnl lock and a process taking the link down (under rtnl).
The latter removes the host route from the inet6_addr as part of
addrconf_ifdown which is run for NETDEV_DOWN. The former attempts
to use the host route in __ipv6_ifa_notify. If the down event removes
the host route due to the race to the rtnl, then the BUG listed above
occurs.

Since the DAD sequence can not be aborted, add a check for the missing
host route in __ipv6_ifa_notify. The only way this should happen is due
to the previously mentioned race. The host route is created when the
address is added to an interface; it is only removed on a down event
where the address is kept. Add a warning if the host route is missing
AND the device is up; this is a situation that should never happen.

Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional")
Reported-by: Rajendra Dendukuri <rajendra.dendukuri@broadcom.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 6a576ff92c39..34ccef18b40e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5964,13 +5964,20 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
 	switch (event) {
 	case RTM_NEWADDR:
 		/*
-		 * If the address was optimistic
-		 * we inserted the route at the start of
-		 * our DAD process, so we don't need
-		 * to do it again
+		 * If the address was optimistic we inserted the route at the
+		 * start of our DAD process, so we don't need to do it again.
+		 * If the device was taken down in the middle of the DAD
+		 * cycle there is a race where we could get here without a
+		 * host route, so nothing to insert. That will be fixed when
+		 * the device is brought up.
 		 */
-		if (!rcu_access_pointer(ifp->rt->fib6_node))
+		if (ifp->rt && !rcu_access_pointer(ifp->rt->fib6_node)) {
 			ip6_ins_rt(net, ifp->rt);
+		} else if (!ifp->rt && (ifp->idev->dev->flags & IFF_UP)) {
+			pr_warn("BUG: Address %pI6c on device %s is missing its host route.\n",
+				&ifp->addr, ifp->idev->dev->name);
+		}
+
 		if (ifp->idev->cnf.forwarding)
 			addrconf_join_anycast(ifp);
 		if (!ipv6_addr_any(&ifp->peer_addr))
-- 
cgit v1.2.3


From 4cf6c57e61fee954f7b7685de31b80ec26843d27 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Fri, 4 Oct 2019 17:05:58 +0100
Subject: net: phy: fix write to mii-ctrl1000 register

When userspace writes to the MII_ADVERTISE register, we update phylib's
advertising mask and trigger a renegotiation.  However, writing to the
MII_CTRL1000 register, which contains the gigabit advertisement, does
neither.  This can lead to phylib's copy of the advertisement becoming
de-synced with the values in the PHY register set, which can result in
incorrect negotiation resolution.

Fixes: 5502b218e001 ("net: phy: use phy_resolve_aneg_linkmode in genphy_read_status")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 5 +++++
 include/linux/mii.h   | 9 +++++++++
 2 files changed, 14 insertions(+)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 7c92afd36bbe..119e6f466056 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -457,6 +457,11 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 							   val);
 				change_autoneg = true;
 				break;
+			case MII_CTRL1000:
+				mii_ctrl1000_mod_linkmode_adv_t(phydev->advertising,
+							        val);
+				change_autoneg = true;
+				break;
 			default:
 				/* do nothing */
 				break;
diff --git a/include/linux/mii.h b/include/linux/mii.h
index 5cd824c1c0ca..4ce8901a1af6 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -455,6 +455,15 @@ static inline void mii_lpa_mod_linkmode_lpa_t(unsigned long *lp_advertising,
 			 lp_advertising, lpa & LPA_LPACK);
 }
 
+static inline void mii_ctrl1000_mod_linkmode_adv_t(unsigned long *advertising,
+						   u32 ctrl1000)
+{
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, advertising,
+			 ctrl1000 & ADVERTISE_1000HALF);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, advertising,
+			 ctrl1000 & ADVERTISE_1000FULL);
+}
+
 /**
  * linkmode_adv_to_lcl_adv_t
  * @advertising:pointer to linkmode advertising
-- 
cgit v1.2.3


From 8d3dc3ac9dd6801c732a72ca6979698c38451b4f Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Fri, 4 Oct 2019 17:06:04 +0100
Subject: net: phy: extract link partner advertisement reading

Move reading the link partner advertisement out of genphy_read_status()
into its own separate function.  This will allow re-use of this code by
PHY drivers that are able to read the resolved status from the PHY.

Tested-by: tinywrkb <tinywrkb@gmail.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 65 +++++++++++++++++++++++++++-----------------
 include/linux/phy.h          |  1 +
 2 files changed, 41 insertions(+), 25 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index d347ddcac45b..9d2bbb13293e 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1783,32 +1783,9 @@ done:
 }
 EXPORT_SYMBOL(genphy_update_link);
 
-/**
- * genphy_read_status - check the link status and update current link state
- * @phydev: target phy_device struct
- *
- * Description: Check the link, then figure out the current state
- *   by comparing what we advertise with what the link partner
- *   advertises.  Start by checking the gigabit possibilities,
- *   then move on to 10/100.
- */
-int genphy_read_status(struct phy_device *phydev)
+int genphy_read_lpa(struct phy_device *phydev)
 {
-	int lpa, lpagb, err, old_link = phydev->link;
-
-	/* Update the link, but return if there was an error */
-	err = genphy_update_link(phydev);
-	if (err)
-		return err;
-
-	/* why bother the PHY if nothing can have changed */
-	if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link)
-		return 0;
-
-	phydev->speed = SPEED_UNKNOWN;
-	phydev->duplex = DUPLEX_UNKNOWN;
-	phydev->pause = 0;
-	phydev->asym_pause = 0;
+	int lpa, lpagb;
 
 	if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) {
 		if (phydev->is_gigabit_capable) {
@@ -1838,6 +1815,44 @@ int genphy_read_status(struct phy_device *phydev)
 			return lpa;
 
 		mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, lpa);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(genphy_read_lpa);
+
+/**
+ * genphy_read_status - check the link status and update current link state
+ * @phydev: target phy_device struct
+ *
+ * Description: Check the link, then figure out the current state
+ *   by comparing what we advertise with what the link partner
+ *   advertises.  Start by checking the gigabit possibilities,
+ *   then move on to 10/100.
+ */
+int genphy_read_status(struct phy_device *phydev)
+{
+	int err, old_link = phydev->link;
+
+	/* Update the link, but return if there was an error */
+	err = genphy_update_link(phydev);
+	if (err)
+		return err;
+
+	/* why bother the PHY if nothing can have changed */
+	if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link)
+		return 0;
+
+	phydev->speed = SPEED_UNKNOWN;
+	phydev->duplex = DUPLEX_UNKNOWN;
+	phydev->pause = 0;
+	phydev->asym_pause = 0;
+
+	err = genphy_read_lpa(phydev);
+	if (err < 0)
+		return err;
+
+	if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) {
 		phy_resolve_aneg_linkmode(phydev);
 	} else if (phydev->autoneg == AUTONEG_DISABLE) {
 		int bmcr = phy_read(phydev, MII_BMCR);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index a7ecbe0e55aa..7abee820d05c 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1076,6 +1076,7 @@ int genphy_config_eee_advert(struct phy_device *phydev);
 int __genphy_config_aneg(struct phy_device *phydev, bool changed);
 int genphy_aneg_done(struct phy_device *phydev);
 int genphy_update_link(struct phy_device *phydev);
+int genphy_read_lpa(struct phy_device *phydev);
 int genphy_read_status(struct phy_device *phydev);
 int genphy_suspend(struct phy_device *phydev);
 int genphy_resume(struct phy_device *phydev);
-- 
cgit v1.2.3


From 2d880b8709c013d47472f85a9d42ea1aca3bce47 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Fri, 4 Oct 2019 17:06:09 +0100
Subject: net: phy: extract pause mode

Extract the update of phylib's software pause mode state from
genphy_read_status(), so that we can re-use this functionality with
PHYs that have alternative ways to read the negotiation results.

Tested-by: tinywrkb <tinywrkb@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-core.c | 20 +++++++++++++-------
 include/linux/phy.h        |  1 +
 2 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 369903d9b6ec..9412669b579c 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -283,6 +283,18 @@ void of_set_phy_eee_broken(struct phy_device *phydev)
 	phydev->eee_broken_modes = broken;
 }
 
+void phy_resolve_aneg_pause(struct phy_device *phydev)
+{
+	if (phydev->duplex == DUPLEX_FULL) {
+		phydev->pause = linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+						  phydev->lp_advertising);
+		phydev->asym_pause = linkmode_test_bit(
+			ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+			phydev->lp_advertising);
+	}
+}
+EXPORT_SYMBOL_GPL(phy_resolve_aneg_pause);
+
 /**
  * phy_resolve_aneg_linkmode - resolve the advertisements into phy settings
  * @phydev: The phy_device struct
@@ -305,13 +317,7 @@ void phy_resolve_aneg_linkmode(struct phy_device *phydev)
 			break;
 		}
 
-	if (phydev->duplex == DUPLEX_FULL) {
-		phydev->pause = linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
-						  phydev->lp_advertising);
-		phydev->asym_pause = linkmode_test_bit(
-			ETHTOOL_LINK_MODE_Asym_Pause_BIT,
-			phydev->lp_advertising);
-	}
+	phy_resolve_aneg_pause(phydev);
 }
 EXPORT_SYMBOL_GPL(phy_resolve_aneg_linkmode);
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 7abee820d05c..9a0e981df502 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -678,6 +678,7 @@ static inline bool phy_is_started(struct phy_device *phydev)
 	return phydev->state >= PHY_UP;
 }
 
+void phy_resolve_aneg_pause(struct phy_device *phydev);
 void phy_resolve_aneg_linkmode(struct phy_device *phydev);
 
 /**
-- 
cgit v1.2.3


From 06d5f3441b2e80eeb6deb0885aefa00589e463c1 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Fri, 4 Oct 2019 17:06:14 +0100
Subject: net: phy: at803x: use operating parameters from PHY-specific status

Read the PHY-specific status register for the current operating mode
(speed and duplex) of the PHY.  This register reflects the actual
mode that the PHY has resolved depending on either the advertisements
of autoneg is enabled, or the forced mode if autoneg is disabled.

This ensures that phylib's software state always tracks the hardware
state.

It seems both AR8033 (which uses the AR8031 ID) and AR8035 support
this status register.  AR8030 is not known at the present time.

This patch depends on "net: phy: extract pause mode" and "net: phy:
extract link partner advertisement reading".

Reported-by: tinywrkb <tinywrkb@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: tinywrkb <tinywrkb@gmail.com>
Fixes: 5502b218e001 ("net: phy: use phy_resolve_aneg_linkmode in genphy_read_status")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/at803x.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 69 insertions(+)

diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c
index 2aa7b2e60046..1eb5d4fb8925 100644
--- a/drivers/net/phy/at803x.c
+++ b/drivers/net/phy/at803x.c
@@ -15,6 +15,15 @@
 #include <linux/of_gpio.h>
 #include <linux/gpio/consumer.h>
 
+#define AT803X_SPECIFIC_STATUS			0x11
+#define AT803X_SS_SPEED_MASK			(3 << 14)
+#define AT803X_SS_SPEED_1000			(2 << 14)
+#define AT803X_SS_SPEED_100			(1 << 14)
+#define AT803X_SS_SPEED_10			(0 << 14)
+#define AT803X_SS_DUPLEX			BIT(13)
+#define AT803X_SS_SPEED_DUPLEX_RESOLVED		BIT(11)
+#define AT803X_SS_MDIX				BIT(6)
+
 #define AT803X_INTR_ENABLE			0x12
 #define AT803X_INTR_ENABLE_AUTONEG_ERR		BIT(15)
 #define AT803X_INTR_ENABLE_SPEED_CHANGED	BIT(14)
@@ -357,6 +366,64 @@ static int at803x_aneg_done(struct phy_device *phydev)
 	return aneg_done;
 }
 
+static int at803x_read_status(struct phy_device *phydev)
+{
+	int ss, err, old_link = phydev->link;
+
+	/* Update the link, but return if there was an error */
+	err = genphy_update_link(phydev);
+	if (err)
+		return err;
+
+	/* why bother the PHY if nothing can have changed */
+	if (phydev->autoneg == AUTONEG_ENABLE && old_link && phydev->link)
+		return 0;
+
+	phydev->speed = SPEED_UNKNOWN;
+	phydev->duplex = DUPLEX_UNKNOWN;
+	phydev->pause = 0;
+	phydev->asym_pause = 0;
+
+	err = genphy_read_lpa(phydev);
+	if (err < 0)
+		return err;
+
+	/* Read the AT8035 PHY-Specific Status register, which indicates the
+	 * speed and duplex that the PHY is actually using, irrespective of
+	 * whether we are in autoneg mode or not.
+	 */
+	ss = phy_read(phydev, AT803X_SPECIFIC_STATUS);
+	if (ss < 0)
+		return ss;
+
+	if (ss & AT803X_SS_SPEED_DUPLEX_RESOLVED) {
+		switch (ss & AT803X_SS_SPEED_MASK) {
+		case AT803X_SS_SPEED_10:
+			phydev->speed = SPEED_10;
+			break;
+		case AT803X_SS_SPEED_100:
+			phydev->speed = SPEED_100;
+			break;
+		case AT803X_SS_SPEED_1000:
+			phydev->speed = SPEED_1000;
+			break;
+		}
+		if (ss & AT803X_SS_DUPLEX)
+			phydev->duplex = DUPLEX_FULL;
+		else
+			phydev->duplex = DUPLEX_HALF;
+		if (ss & AT803X_SS_MDIX)
+			phydev->mdix = ETH_TP_MDI_X;
+		else
+			phydev->mdix = ETH_TP_MDI;
+	}
+
+	if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete)
+		phy_resolve_aneg_pause(phydev);
+
+	return 0;
+}
+
 static struct phy_driver at803x_driver[] = {
 {
 	/* ATHEROS 8035 */
@@ -370,6 +437,7 @@ static struct phy_driver at803x_driver[] = {
 	.suspend		= at803x_suspend,
 	.resume			= at803x_resume,
 	/* PHY_GBIT_FEATURES */
+	.read_status		= at803x_read_status,
 	.ack_interrupt		= at803x_ack_interrupt,
 	.config_intr		= at803x_config_intr,
 }, {
@@ -399,6 +467,7 @@ static struct phy_driver at803x_driver[] = {
 	.suspend		= at803x_suspend,
 	.resume			= at803x_resume,
 	/* PHY_GBIT_FEATURES */
+	.read_status		= at803x_read_status,
 	.aneg_done		= at803x_aneg_done,
 	.ack_interrupt		= &at803x_ack_interrupt,
 	.config_intr		= &at803x_config_intr,
-- 
cgit v1.2.3


From 474f0813a3002cb299bb73a5a93aa1f537a80ca8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Oct 2019 10:34:45 -0700
Subject: sch_dsmark: fix potential NULL deref in dsmark_init()

Make sure TCA_DSMARK_INDICES was provided by the user.

syzbot reported :

kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 8799 Comm: syz-executor235 Not tainted 5.3.0+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:nla_get_u16 include/net/netlink.h:1501 [inline]
RIP: 0010:dsmark_init net/sched/sch_dsmark.c:364 [inline]
RIP: 0010:dsmark_init+0x193/0x640 net/sched/sch_dsmark.c:339
Code: 85 db 58 0f 88 7d 03 00 00 e8 e9 1a ac fb 48 8b 9d 70 ff ff ff 48 b8 00 00 00 00 00 fc ff df 48 8d 7b 04 48 89 fa 48 c1 ea 03 <0f> b6 14 02 48 89 f8 83 e0 07 83 c0 01 38 d0 7c 08 84 d2 0f 85 ca
RSP: 0018:ffff88809426f3b8 EFLAGS: 00010247
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffffff85c6eb09
RDX: 0000000000000000 RSI: ffffffff85c6eb17 RDI: 0000000000000004
RBP: ffff88809426f4b0 R08: ffff88808c4085c0 R09: ffffed1015d26159
R10: ffffed1015d26158 R11: ffff8880ae930ac7 R12: ffff8880a7e96940
R13: dffffc0000000000 R14: ffff88809426f8c0 R15: 0000000000000000
FS:  0000000001292880(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000020000080 CR3: 000000008ca1b000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 qdisc_create+0x4ee/0x1210 net/sched/sch_api.c:1237
 tc_modify_qdisc+0x524/0x1c50 net/sched/sch_api.c:1653
 rtnetlink_rcv_msg+0x463/0xb00 net/core/rtnetlink.c:5223
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5241
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x531/0x710 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x8a5/0xd60 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:657
 ___sys_sendmsg+0x803/0x920 net/socket.c:2311
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2356
 __do_sys_sendmsg net/socket.c:2365 [inline]
 __se_sys_sendmsg net/socket.c:2363 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2363
 do_syscall_64+0xfa/0x760 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x440369

Fixes: 758cc43c6d73 ("[PKT_SCHED]: Fix dsmark to apply changes consistent")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_dsmark.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index bad1cbe59a56..05605b30bef3 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -361,6 +361,8 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt,
 		goto errout;
 
 	err = -EINVAL;
+	if (!tb[TCA_DSMARK_INDICES])
+		goto errout;
 	indices = nla_get_u16(tb[TCA_DSMARK_INDICES]);
 
 	if (hweight32(indices) != 1)
-- 
cgit v1.2.3


From a0c2dc1fe63e2869b74c1c7f6a81d1745c8a695d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 4 Oct 2019 11:08:34 -0700
Subject: nfc: fix memory leak in llcp_sock_bind()

sysbot reported a memory leak after a bind() has failed.

While we are at it, abort the operation if kmemdup() has failed.

BUG: memory leak
unreferenced object 0xffff888105d83ec0 (size 32):
  comm "syz-executor067", pid 7207, jiffies 4294956228 (age 19.430s)
  hex dump (first 32 bytes):
    00 69 6c 65 20 72 65 61 64 00 6e 65 74 3a 5b 34  .ile read.net:[4
    30 32 36 35 33 33 30 39 37 5d 00 00 00 00 00 00  026533097]......
  backtrace:
    [<0000000036bac473>] kmemleak_alloc_recursive /./include/linux/kmemleak.h:43 [inline]
    [<0000000036bac473>] slab_post_alloc_hook /mm/slab.h:522 [inline]
    [<0000000036bac473>] slab_alloc /mm/slab.c:3319 [inline]
    [<0000000036bac473>] __do_kmalloc /mm/slab.c:3653 [inline]
    [<0000000036bac473>] __kmalloc_track_caller+0x169/0x2d0 /mm/slab.c:3670
    [<000000000cd39d07>] kmemdup+0x27/0x60 /mm/util.c:120
    [<000000008e57e5fc>] kmemdup /./include/linux/string.h:432 [inline]
    [<000000008e57e5fc>] llcp_sock_bind+0x1b3/0x230 /net/nfc/llcp_sock.c:107
    [<000000009cb0b5d3>] __sys_bind+0x11c/0x140 /net/socket.c:1647
    [<00000000492c3bbc>] __do_sys_bind /net/socket.c:1658 [inline]
    [<00000000492c3bbc>] __se_sys_bind /net/socket.c:1656 [inline]
    [<00000000492c3bbc>] __x64_sys_bind+0x1e/0x30 /net/socket.c:1656
    [<0000000008704b2a>] do_syscall_64+0x76/0x1a0 /arch/x86/entry/common.c:296
    [<000000009f4c57a4>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: 30cc4587659e ("NFC: Move LLCP code to the NFC top level diirectory")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/nfc/llcp_sock.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 8dfea26536c9..ccdd790e163a 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -107,9 +107,14 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen)
 	llcp_sock->service_name = kmemdup(llcp_addr.service_name,
 					  llcp_sock->service_name_len,
 					  GFP_KERNEL);
-
+	if (!llcp_sock->service_name) {
+		ret = -ENOMEM;
+		goto put_dev;
+	}
 	llcp_sock->ssap = nfc_llcp_get_sdp_ssap(local, llcp_sock);
 	if (llcp_sock->ssap == LLCP_SAP_MAX) {
+		kfree(llcp_sock->service_name);
+		llcp_sock->service_name = NULL;
 		ret = -EADDRINUSE;
 		goto put_dev;
 	}
-- 
cgit v1.2.3


From 1acb8f2a7a9f10543868ddd737e37424d5c36cf4 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Fri, 4 Oct 2019 15:24:39 -0500
Subject: net: qlogic: Fix memory leak in ql_alloc_large_buffers

In ql_alloc_large_buffers, a new skb is allocated via netdev_alloc_skb.
This skb should be released if pci_dma_mapping_error fails.

Fixes: 0f8ab89e825f ("qla3xxx: Check return code from pci_map_single() in ql_release_to_lrg_buf_free_list(), ql_populate_free_queue(), ql_alloc_large_buffers(), and ql3xxx_send()")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qla3xxx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 457444894d80..b4b8ba00ee01 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -2787,6 +2787,7 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev)
 				netdev_err(qdev->ndev,
 					   "PCI mapping failed with error: %d\n",
 					   err);
+				dev_kfree_skb_irq(skb);
 				ql_free_large_buffers(qdev);
 				return -ENOMEM;
 			}
-- 
cgit v1.2.3


From ef129d34149ea23d0d442844fc25ae26a85589fc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 4 Oct 2019 17:36:50 -0700
Subject: selftests/net: add nettest to .gitignore

nettest is missing from gitignore.

Fixes: acda655fefae ("selftests: Add nettest")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/.gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index c7cced739c34..8aefd81fbc86 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -21,3 +21,4 @@ ipv6_flowlabel
 ipv6_flowlabel_mgr
 so_txtime
 tcp_fastopen_backup_key
+nettest
-- 
cgit v1.2.3


From 6b190d3ce0a693750517256ba67011a9fa04a12a Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 26 Jul 2019 11:10:54 +0900
Subject: integrity: remove unneeded, broken attempt to add -fshort-wchar

I guess commit 15ea0e1e3e18 ("efi: Import certificates from UEFI Secure
Boot") attempted to add -fshort-wchar for building load_uefi.o, but it
has never worked as intended.

load_uefi.o is created in the platform_certs/ sub-directory. If you
really want to add -fshort-wchar, the correct code is:

  $(obj)/platform_certs/load_uefi.o: KBUILD_CFLAGS += -fshort-wchar

But, you do not need to fix it.

Commit 8c97023cf051 ("Kbuild: use -fshort-wchar globally") had already
added -fshort-wchar globally. This code was unneeded in the first place.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 security/integrity/Makefile | 1 -
 1 file changed, 1 deletion(-)

diff --git a/security/integrity/Makefile b/security/integrity/Makefile
index 19faace69644..b6d6273a4176 100644
--- a/security/integrity/Makefile
+++ b/security/integrity/Makefile
@@ -13,7 +13,6 @@ integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyrin
 integrity-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/efi_parser.o \
 					platform_certs/load_uefi.o
 integrity-$(CONFIG_LOAD_IPL_KEYS) += platform_certs/load_ipl_s390.o
-$(obj)/load_uefi.o: KBUILD_CFLAGS += -fshort-wchar
 
 subdir-$(CONFIG_IMA)			+= ima
 obj-$(CONFIG_IMA)			+= ima/
-- 
cgit v1.2.3


From 7a8beb7ad51551babd17331f3c0f58af25916f67 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 26 Jul 2019 11:10:55 +0900
Subject: integrity: remove pointless subdir-$(CONFIG_...)

The ima/ and evm/ sub-directories contain built-in objects, so
obj-$(CONFIG_...) is the correct way to descend into them.

subdir-$(CONFIG_...) is redundant.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 security/integrity/Makefile | 2 --
 1 file changed, 2 deletions(-)

diff --git a/security/integrity/Makefile b/security/integrity/Makefile
index b6d6273a4176..35e6ca773734 100644
--- a/security/integrity/Makefile
+++ b/security/integrity/Makefile
@@ -14,7 +14,5 @@ integrity-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/efi_parser.o \
 					platform_certs/load_uefi.o
 integrity-$(CONFIG_LOAD_IPL_KEYS) += platform_certs/load_ipl_s390.o
 
-subdir-$(CONFIG_IMA)			+= ima
 obj-$(CONFIG_IMA)			+= ima/
-subdir-$(CONFIG_EVM)			+= evm
 obj-$(CONFIG_EVM)			+= evm/
-- 
cgit v1.2.3


From a9bbe79fd5cb2411d69ab8a2e94bb701ca45e133 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Wed, 21 Aug 2019 13:12:34 +0900
Subject: video/logo: remove unneeded *.o pattern from clean-files

The pattern *.o is cleaned up globally by the top Makefile.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 drivers/video/logo/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/video/logo/Makefile b/drivers/video/logo/Makefile
index 228a89b9bdd1..10b75ce3ce09 100644
--- a/drivers/video/logo/Makefile
+++ b/drivers/video/logo/Makefile
@@ -56,4 +56,4 @@ $(obj)/%_gray256.c: $(src)/%_gray256.pgm $(pnmtologo) FORCE
 	$(call if_changed,logo)
 
 # Files generated that shall be removed upon make clean
-clean-files := *.o *_mono.c *_vga16.c *_clut224.c *_gray256.c
+clean-files := *_mono.c *_vga16.c *_clut224.c *_gray256.c
-- 
cgit v1.2.3


From 01bb25156d856e3efb887a273c03f8ba66f8fb0f Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Wed, 21 Aug 2019 13:12:35 +0900
Subject: video/logo: do not generate unneeded logo C files

Currently, all the logo C files are generated irrespective of the
CONFIG options. Adding them to extra-y is wrong. What we need to do
here is to add them to 'targets' so that if_changed works properly.

Files listed in 'targets' are cleaned, so clean-files is unneeded.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 drivers/video/logo/Makefile | 21 ++-------------------
 1 file changed, 2 insertions(+), 19 deletions(-)

diff --git a/drivers/video/logo/Makefile b/drivers/video/logo/Makefile
index 10b75ce3ce09..16f60c1e1766 100644
--- a/drivers/video/logo/Makefile
+++ b/drivers/video/logo/Makefile
@@ -18,23 +18,6 @@ obj-$(CONFIG_SPU_BASE)			+= logo_spe_clut224.o
 
 # How to generate logo's
 
-# Use logo-cfiles to retrieve list of .c files to be built
-logo-cfiles = $(notdir $(patsubst %.$(2), %.c, \
-              $(wildcard $(srctree)/$(src)/*$(1).$(2))))
-
-
-# Mono logos
-extra-y += $(call logo-cfiles,_mono,pbm)
-
-# VGA16 logos
-extra-y += $(call logo-cfiles,_vga16,ppm)
-
-# 224 Logos
-extra-y += $(call logo-cfiles,_clut224,ppm)
-
-# Gray 256
-extra-y += $(call logo-cfiles,_gray256,pgm)
-
 pnmtologo := scripts/pnmtologo
 
 # Create commands like "pnmtologo -t mono -n logo_mac_mono -o ..."
@@ -55,5 +38,5 @@ $(obj)/%_clut224.c: $(src)/%_clut224.ppm $(pnmtologo) FORCE
 $(obj)/%_gray256.c: $(src)/%_gray256.pgm $(pnmtologo) FORCE
 	$(call if_changed,logo)
 
-# Files generated that shall be removed upon make clean
-clean-files := *_mono.c *_vga16.c *_clut224.c *_gray256.c
+# generated C files
+targets += *_mono.c *_vga16.c *_clut224.c *_gray256.c
-- 
cgit v1.2.3


From 82fdd12b95727640c9a8233c09d602e4518e71f7 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Fri, 27 Sep 2019 16:30:27 -0700
Subject: namespace: fix namespace.pl script to support relative paths

The namespace.pl script does not work properly if objtree is not set to
an absolute path. The do_nm function is run from within the find
function, which changes directories.

Because of this, appending objtree, $File::Find::dir, and $source, will
return a path which is not valid from the current directory.

This used to work when objtree was set to an absolute path when using
"make namespacecheck". It appears to have not worked when calling
./scripts/namespace.pl directly.

This behavior was changed in 7e1c04779efd ("kbuild: Use relative path
for $(objtree)", 2014-05-14)

Rather than fixing the Makefile to set objtree to an absolute path, just
fix namespace.pl to work when srctree and objtree are relative. Also fix
the script to use an absolute path for these by default.

Use the File::Spec module for this purpose. It's been part of perl
5 since 5.005.

The curdir() function is used to get the current directory when the
objtree and srctree aren't set in the environment.

rel2abs() is used to convert possibly relative objtree and srctree
environment variables to absolute paths.

Finally, the catfile() function is used instead of string appending
paths together, since this is more robust when joining paths together.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/namespace.pl | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/scripts/namespace.pl b/scripts/namespace.pl
index 6135574a6f39..1da7bca201a4 100755
--- a/scripts/namespace.pl
+++ b/scripts/namespace.pl
@@ -65,13 +65,14 @@
 use warnings;
 use strict;
 use File::Find;
+use File::Spec;
 
 my $nm = ($ENV{'NM'} || "nm") . " -p";
 my $objdump = ($ENV{'OBJDUMP'} || "objdump") . " -s -j .comment";
-my $srctree = "";
-my $objtree = "";
-$srctree = "$ENV{'srctree'}/" if (exists($ENV{'srctree'}));
-$objtree = "$ENV{'objtree'}/" if (exists($ENV{'objtree'}));
+my $srctree = File::Spec->curdir();
+my $objtree = File::Spec->curdir();
+$srctree = File::Spec->rel2abs($ENV{'srctree'}) if (exists($ENV{'srctree'}));
+$objtree = File::Spec->rel2abs($ENV{'objtree'}) if (exists($ENV{'objtree'}));
 
 if ($#ARGV != -1) {
 	print STDERR "usage: $0 takes no parameters\n";
@@ -231,9 +232,9 @@ sub do_nm
 	}
 	($source = $basename) =~ s/\.o$//;
 	if (-e "$source.c" || -e "$source.S") {
-		$source = "$objtree$File::Find::dir/$source";
+		$source = File::Spec->catfile($objtree, $File::Find::dir, $source)
 	} else {
-		$source = "$srctree$File::Find::dir/$source";
+		$source = File::Spec->catfile($srctree, $File::Find::dir, $source)
 	}
 	if (! -e "$source.c" && ! -e "$source.S") {
 		# No obvious source, exclude the object if it is conglomerate
-- 
cgit v1.2.3


From 7a82e3fa28f174ba23c9faca544c65986e3025f1 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Tue, 1 Oct 2019 21:17:24 +0900
Subject: scripts/setlocalversion: clear local variable to make it work for sh

Geert Uytterhoeven reports a strange side-effect of commit 858805b336be
("kbuild: add $(BASH) to run scripts with bash-extension"), which
inserts the contents of a localversion file in the build directory twice.

[Steps to Reproduce]
  $ echo bar > localversion
  $ mkdir build
  $ cd build/
  $ echo foo > localversion
  $ make -s -f ../Makefile defconfig include/config/kernel.release
  $ cat include/config/kernel.release
  5.4.0-rc1foofoobar

This comes down to the behavior change of local variables.

The 'man sh' on my Ubuntu machine, where sh is an alias to dash,
explains as follows:
  When a variable is made local, it inherits the initial value and
  exported and readonly flags from the variable with the same name
  in the surrounding scope, if there is one. Otherwise, the variable
  is initially unset.

[Test Code]

  foo ()
  {
          local res
          echo "res: $res"
  }

  res=1
  foo

[Result]

  $ sh test.sh
  res: 1
  $ bash test.sh
  res:

So, scripts/setlocalversion correctly works only for bash in spite of
its hashbang being #!/bin/sh. Nobody had noticed it before because
CONFIG_SHELL was previously set to bash almost all the time.

Now that CONFIG_SHELL is set to sh, we must write portable and correct
code. I gave the Fixes tag to the commit that uncovered the issue.

Clear the variable 'res' in collect_files() to make it work for sh
(and it also works on distributions where sh is an alias to bash).

Fixes: 858805b336be ("kbuild: add $(BASH) to run scripts with bash-extension")
Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 scripts/setlocalversion | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/setlocalversion b/scripts/setlocalversion
index 365b3c2b8f43..220dae0db3f1 100755
--- a/scripts/setlocalversion
+++ b/scripts/setlocalversion
@@ -126,7 +126,7 @@ scm_version()
 
 collect_files()
 {
-	local file res
+	local file res=
 
 	for file; do
 		case "$file" in
-- 
cgit v1.2.3


From 43496709f166aeb87ac0bdcc6f7bb2bedafb17c9 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 3 Oct 2019 19:29:12 +0900
Subject: kbuild: two minor updates for Documentation/kbuild/modules.rst

Capitalize the first word in the sentence.

Use obj-m instead of obj-y. obj-y still works, but we have no built-in
objects in external module builds. So, obj-m is better IMHO.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Documentation/kbuild/modules.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/kbuild/modules.rst b/Documentation/kbuild/modules.rst
index 33a17121d11d..774a998dcf37 100644
--- a/Documentation/kbuild/modules.rst
+++ b/Documentation/kbuild/modules.rst
@@ -502,7 +502,7 @@ build.
 ----------------------------------------
 
 	Sometimes, an external module uses exported symbols from
-	another external module. kbuild needs to have full knowledge of
+	another external module. Kbuild needs to have full knowledge of
 	all symbols to avoid spitting out warnings about undefined
 	symbols. Three solutions exist for this situation.
 
@@ -522,7 +522,7 @@ build.
 		The top-level kbuild file would then look like::
 
 			#./Kbuild (or ./Makefile):
-				obj-y := foo/ bar/
+				obj-m := foo/ bar/
 
 		And executing::
 
-- 
cgit v1.2.3


From d188b8c901bb4966ab035ce90af02426f062e9e1 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 3 Oct 2019 11:36:29 +0900
Subject: kbuild: update compile-test header list for v5.4-rc2

Commit 6dc280ebeed2 ("coda: remove uapi/linux/coda_psdev.h") removed
a header in question. Some more build errors were fixed. Add more
headers into the test coverage.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 usr/include/Makefile | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/usr/include/Makefile b/usr/include/Makefile
index c9449aaf438d..57b20f7b6729 100644
--- a/usr/include/Makefile
+++ b/usr/include/Makefile
@@ -29,13 +29,11 @@ header-test- += linux/android/binderfs.h
 header-test-$(CONFIG_CPU_BIG_ENDIAN) += linux/byteorder/big_endian.h
 header-test-$(CONFIG_CPU_LITTLE_ENDIAN) += linux/byteorder/little_endian.h
 header-test- += linux/coda.h
-header-test- += linux/coda_psdev.h
 header-test- += linux/elfcore.h
 header-test- += linux/errqueue.h
 header-test- += linux/fsmap.h
 header-test- += linux/hdlc/ioctl.h
 header-test- += linux/ivtv.h
-header-test- += linux/jffs2.h
 header-test- += linux/kexec.h
 header-test- += linux/matroxfb.h
 header-test- += linux/netfilter_ipv4/ipt_LOG.h
@@ -55,20 +53,12 @@ header-test- += linux/v4l2-mediabus.h
 header-test- += linux/v4l2-subdev.h
 header-test- += linux/videodev2.h
 header-test- += linux/vm_sockets.h
-header-test- += scsi/scsi_bsg_fc.h
-header-test- += scsi/scsi_netlink.h
-header-test- += scsi/scsi_netlink_fc.h
 header-test- += sound/asequencer.h
 header-test- += sound/asoc.h
 header-test- += sound/asound.h
 header-test- += sound/compress_offload.h
 header-test- += sound/emu10k1.h
 header-test- += sound/sfnt_info.h
-header-test- += sound/sof/eq.h
-header-test- += sound/sof/fw.h
-header-test- += sound/sof/header.h
-header-test- += sound/sof/manifest.h
-header-test- += sound/sof/trace.h
 header-test- += xen/evtchn.h
 header-test- += xen/gntdev.h
 header-test- += xen/privcmd.h
-- 
cgit v1.2.3


From 86cdd2fdc4e39c388d39c7ba2396d1a9dfd66226 Mon Sep 17 00:00:00 2001
From: Dmitry Goldin <dgoldin+lkml@protonmail.ch>
Date: Fri, 4 Oct 2019 10:40:07 +0000
Subject: kheaders: make headers archive reproducible

In commit 43d8ce9d65a5 ("Provide in-kernel headers to make
extending kernel easier") a new mechanism was introduced, for kernels
>=5.2, which embeds the kernel headers in the kernel image or a module
and exposes them in procfs for use by userland tools.

The archive containing the header files has nondeterminism caused by
header files metadata. This patch normalizes the metadata and utilizes
KBUILD_BUILD_TIMESTAMP if provided and otherwise falls back to the
default behaviour.

In commit f7b101d33046 ("kheaders: Move from proc to sysfs") it was
modified to use sysfs and the script for generation of the archive was
renamed to what is being patched.

Signed-off-by: Dmitry Goldin <dgoldin+lkml@protonmail.ch>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Documentation/kbuild/reproducible-builds.rst | 13 +++++++++----
 kernel/gen_kheaders.sh                       |  5 ++++-
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst
index ab92e98c89c8..503393854e2e 100644
--- a/Documentation/kbuild/reproducible-builds.rst
+++ b/Documentation/kbuild/reproducible-builds.rst
@@ -16,16 +16,21 @@ the kernel may be unreproducible, and how to avoid them.
 Timestamps
 ----------
 
-The kernel embeds a timestamp in two places:
+The kernel embeds timestamps in three places:
 
 * The version string exposed by ``uname()`` and included in
   ``/proc/version``
 
 * File timestamps in the embedded initramfs
 
-By default the timestamp is the current time.  This must be overridden
-using the `KBUILD_BUILD_TIMESTAMP`_ variable.  If you are building
-from a git commit, you could use its commit date.
+* If enabled via ``CONFIG_IKHEADERS``, file timestamps of kernel
+  headers embedded in the kernel or respective module,
+  exposed via ``/sys/kernel/kheaders.tar.xz``
+
+By default the timestamp is the current time and in the case of
+``kheaders`` the various files' modification times. This must
+be overridden using the `KBUILD_BUILD_TIMESTAMP`_ variable.
+If you are building from a git commit, you could use its commit date.
 
 The kernel does *not* use the ``__DATE__`` and ``__TIME__`` macros,
 and enables warnings if they are used.  If you incorporate external
diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh
index 9ff449888d9c..aff79e461fc9 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -71,7 +71,10 @@ done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1
 find $cpio_dir -type f -print0 |
 	xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;'
 
-tar -Jcf $tarfile -C $cpio_dir/ . > /dev/null
+# Create archive and try to normalize metadata for reproducibility
+tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \
+    --owner=0 --group=0 --sort=name --numeric-owner \
+    -Jcf $tarfile -C $cpio_dir/ . > /dev/null
 
 echo "$src_files_md5" >  kernel/kheaders.md5
 echo "$obj_files_md5" >> kernel/kheaders.md5
-- 
cgit v1.2.3


From 2cf2aa6a69db0b17b3979144287af8775c1c1534 Mon Sep 17 00:00:00 2001
From: Andrey Smirnov <andrew.smirnov@gmail.com>
Date: Sat, 5 Oct 2019 10:23:30 +0200
Subject: dma-mapping: fix false positivse warnings in dma_common_free_remap()

Commit 5cf4537975bb ("dma-mapping: introduce a dma_common_find_pages
helper") changed invalid input check in dma_common_free_remap() from:

    if (!area || !area->flags != VM_DMA_COHERENT)

to

    if (!area || !area->flags != VM_DMA_COHERENT || !area->pages)

which seem to produce false positives for memory obtained via
dma_common_contiguous_remap()

This triggers the following warning message when doing "reboot" on ZII
VF610 Dev Board Rev B:

WARNING: CPU: 0 PID: 1 at kernel/dma/remap.c:112 dma_common_free_remap+0x88/0x8c
trying to free invalid coherent area: 9ef82980
Modules linked in:
CPU: 0 PID: 1 Comm: systemd-shutdow Not tainted 5.3.0-rc6-next-20190820 #119
Hardware name: Freescale Vybrid VF5xx/VF6xx (Device Tree)
Backtrace:
[<8010d1ec>] (dump_backtrace) from [<8010d588>] (show_stack+0x20/0x24)
 r7:8015ed78 r6:00000009 r5:00000000 r4:9f4d9b14
[<8010d568>] (show_stack) from [<8077e3f0>] (dump_stack+0x24/0x28)
[<8077e3cc>] (dump_stack) from [<801197a0>] (__warn.part.3+0xcc/0xe4)
[<801196d4>] (__warn.part.3) from [<80119830>] (warn_slowpath_fmt+0x78/0x94)
 r6:00000070 r5:808e540c r4:81c03048
[<801197bc>] (warn_slowpath_fmt) from [<8015ed78>] (dma_common_free_remap+0x88/0x8c)
 r3:9ef82980 r2:808e53e0
 r7:00001000 r6:a0b1e000 r5:a0b1e000 r4:00001000
[<8015ecf0>] (dma_common_free_remap) from [<8010fa9c>] (remap_allocator_free+0x60/0x68)
 r5:81c03048 r4:9f4d9b78
[<8010fa3c>] (remap_allocator_free) from [<801100d0>] (__arm_dma_free.constprop.3+0xf8/0x148)
 r5:81c03048 r4:9ef82900
[<8010ffd8>] (__arm_dma_free.constprop.3) from [<80110144>] (arm_dma_free+0x24/0x2c)
 r5:9f563410 r4:80110120
[<80110120>] (arm_dma_free) from [<8015d80c>] (dma_free_attrs+0xa0/0xdc)
[<8015d76c>] (dma_free_attrs) from [<8020f3e4>] (dma_pool_destroy+0xc0/0x154)
 r8:9efa8860 r7:808f02f0 r6:808f02d0 r5:9ef82880 r4:9ef82780
[<8020f324>] (dma_pool_destroy) from [<805525d0>] (ehci_mem_cleanup+0x6c/0x150)
 r7:9f563410 r6:9efa8810 r5:00000000 r4:9efd0148
[<80552564>] (ehci_mem_cleanup) from [<80558e0c>] (ehci_stop+0xac/0xc0)
 r5:9efd0148 r4:9efd0000
[<80558d60>] (ehci_stop) from [<8053c4bc>] (usb_remove_hcd+0xf4/0x1b0)
 r7:9f563410 r6:9efd0074 r5:81c03048 r4:9efd0000
[<8053c3c8>] (usb_remove_hcd) from [<8056361c>] (host_stop+0x48/0xb8)
 r7:9f563410 r6:9efd0000 r5:9f5f4040 r4:9f5f5040
[<805635d4>] (host_stop) from [<80563d0c>] (ci_hdrc_host_destroy+0x34/0x38)
 r7:9f563410 r6:9f5f5040 r5:9efa8800 r4:9f5f4040
[<80563cd8>] (ci_hdrc_host_destroy) from [<8055ef18>] (ci_hdrc_remove+0x50/0x10c)
[<8055eec8>] (ci_hdrc_remove) from [<804a2ed8>] (platform_drv_remove+0x34/0x4c)
 r7:9f563410 r6:81c4f99c r5:9efa8810 r4:9efa8810
[<804a2ea4>] (platform_drv_remove) from [<804a18a8>] (device_release_driver_internal+0xec/0x19c)
 r5:00000000 r4:9efa8810
[<804a17bc>] (device_release_driver_internal) from [<804a1978>] (device_release_driver+0x20/0x24)
 r7:9f563410 r6:81c41ed0 r5:9efa8810 r4:9f4a1dac
[<804a1958>] (device_release_driver) from [<804a01b8>] (bus_remove_device+0xdc/0x108)
[<804a00dc>] (bus_remove_device) from [<8049c204>] (device_del+0x150/0x36c)
 r7:9f563410 r6:81c03048 r5:9efa8854 r4:9efa8810
[<8049c0b4>] (device_del) from [<804a3368>] (platform_device_del.part.2+0x20/0x84)
 r10:9f563414 r9:809177e0 r8:81cb07dc r7:81c78320 r6:9f563454 r5:9efa8800
 r4:9efa8800
[<804a3348>] (platform_device_del.part.2) from [<804a3420>] (platform_device_unregister+0x28/0x34)
 r5:9f563400 r4:9efa8800
[<804a33f8>] (platform_device_unregister) from [<8055dce0>] (ci_hdrc_remove_device+0x1c/0x30)
 r5:9f563400 r4:00000001
[<8055dcc4>] (ci_hdrc_remove_device) from [<805652ac>] (ci_hdrc_imx_remove+0x38/0x118)
 r7:81c78320 r6:9f563454 r5:9f563410 r4:9f541010
[<8056538c>] (ci_hdrc_imx_shutdown) from [<804a2970>] (platform_drv_shutdown+0x2c/0x30)
[<804a2944>] (platform_drv_shutdown) from [<8049e4fc>] (device_shutdown+0x158/0x1f0)
[<8049e3a4>] (device_shutdown) from [<8013ac80>] (kernel_restart_prepare+0x44/0x48)
 r10:00000058 r9:9f4d8000 r8:fee1dead r7:379ce700 r6:81c0b280 r5:81c03048
 r4:00000000
[<8013ac3c>] (kernel_restart_prepare) from [<8013ad14>] (kernel_restart+0x1c/0x60)
[<8013acf8>] (kernel_restart) from [<8013af84>] (__do_sys_reboot+0xe0/0x1d8)
 r5:81c03048 r4:00000000
[<8013aea4>] (__do_sys_reboot) from [<8013b0ec>] (sys_reboot+0x18/0x1c)
 r8:80101204 r7:00000058 r6:00000000 r5:00000000 r4:00000000
[<8013b0d4>] (sys_reboot) from [<80101000>] (ret_fast_syscall+0x0/0x54)
Exception stack(0x9f4d9fa8 to 0x9f4d9ff0)
9fa0:                   00000000 00000000 fee1dead 28121969 01234567 379ce700
9fc0: 00000000 00000000 00000000 00000058 00000000 00000000 00000000 00016d04
9fe0: 00028e0c 7ec87c64 000135ec 76c1f410

Restore original invalid input check in dma_common_free_remap() to
avoid this problem.

Fixes: 5cf4537975bb ("dma-mapping: introduce a dma_common_find_pages helper")
Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com>
[hch: just revert the offending hunk instead of creating a new helper]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 kernel/dma/remap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index ca4e5d44b571..c00b9258fa6a 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -87,9 +87,9 @@ void *dma_common_contiguous_remap(struct page *page, size_t size,
  */
 void dma_common_free_remap(void *cpu_addr, size_t size)
 {
-	struct page **pages = dma_common_find_pages(cpu_addr);
+	struct vm_struct *area = find_vm_area(cpu_addr);
 
-	if (!pages) {
+	if (!area || area->flags != VM_DMA_COHERENT) {
 		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
 		return;
 	}
-- 
cgit v1.2.3


From b1c41ac3ce569b04644bb1e3fd28926604637da3 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 2 Oct 2019 14:24:47 +0200
Subject: KVM: s390: fix __insn32_query() inline assembly

The inline assembly constraints of __insn32_query() tell the compiler
that only the first byte of "query" is being written to. Intended was
probably that 32 bytes are written to.

Fix and simplify the code and just use a "memory" clobber.

Fixes: d668139718a9 ("KVM: s390: provide query function for instructions returning 32 byte")
Cc: stable@vger.kernel.org # v5.2+
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f6db0f1bc867..74e1a22786e8 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -332,7 +332,7 @@ static inline int plo_test_bit(unsigned char nr)
 	return cc == 0;
 }
 
-static inline void __insn32_query(unsigned int opcode, u8 query[32])
+static inline void __insn32_query(unsigned int opcode, u8 *query)
 {
 	register unsigned long r0 asm("0") = 0;	/* query function */
 	register unsigned long r1 asm("1") = (unsigned long) query;
@@ -340,9 +340,9 @@ static inline void __insn32_query(unsigned int opcode, u8 query[32])
 	asm volatile(
 		/* Parameter regs are ignored */
 		"	.insn	rrf,%[opc] << 16,2,4,6,0\n"
-		: "=m" (*query)
+		:
 		: "d" (r0), "a" (r1), [opc] "i" (opcode)
-		: "cc");
+		: "cc", "memory");
 }
 
 #define INSN_SORTL 0xb938
-- 
cgit v1.2.3


From d0dea733f60efe94257d08ae6eba81d0b511d0a9 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Wed, 2 Oct 2019 14:34:37 +0200
Subject: KVM: s390: mark __insn32_query() as __always_inline

__insn32_query() will not compile if the compiler decides to not
inline it, since it contains an inline assembly with an "i" constraint
with variable contents.

Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kvm/kvm-s390.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 74e1a22786e8..d047e846e1b9 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -332,7 +332,7 @@ static inline int plo_test_bit(unsigned char nr)
 	return cc == 0;
 }
 
-static inline void __insn32_query(unsigned int opcode, u8 *query)
+static __always_inline void __insn32_query(unsigned int opcode, u8 *query)
 {
 	register unsigned long r0 asm("0") = 0;	/* query function */
 	register unsigned long r1 asm("1") = (unsigned long) query;
-- 
cgit v1.2.3


From 9f79b78ef74436c7507bac6bfb7b8b989263bccb Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sat, 21 May 2016 21:59:07 -0700
Subject: Convert filldir[64]() from __put_user() to unsafe_put_user()

We really should avoid the "__{get,put}_user()" functions entirely,
because they can easily be mis-used and the original intent of being
used for simple direct user accesses no longer holds in a post-SMAP/PAN
world.

Manually optimizing away the user access range check makes no sense any
more, when the range check is generally much cheaper than the "enable
user accesses" code that the __{get,put}_user() functions still need.

So instead of __put_user(), use the unsafe_put_user() interface with
user_access_{begin,end}() that really does generate better code these
days, and which is generally a nicer interface.  Under some loads, the
multiple user writes that filldir() does are actually quite noticeable.

This also makes the dirent name copy use unsafe_put_user() with a couple
of macros.  We do not want to make function calls with SMAP/PAN
disabled, and the code this generates is quite good when the
architecture uses "asm goto" for unsafe_put_user() like x86 does.

Note that this doesn't bother with the legacy cases.  Nobody should use
them anyway, so performance doesn't really matter there.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/readdir.c | 128 +++++++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 93 insertions(+), 35 deletions(-)

diff --git a/fs/readdir.c b/fs/readdir.c
index 2f6a4534e0df..579c8ea894ae 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -20,9 +20,63 @@
 #include <linux/syscalls.h>
 #include <linux/unistd.h>
 #include <linux/compat.h>
-
 #include <linux/uaccess.h>
 
+#include <asm/unaligned.h>
+
+/*
+ * Note the "unsafe_put_user() semantics: we goto a
+ * label for errors.
+ *
+ * Also note how we use a "while()" loop here, even though
+ * only the biggest size needs to loop. The compiler (well,
+ * at least gcc) is smart enough to turn the smaller sizes
+ * into just if-statements, and this way we don't need to
+ * care whether 'u64' or 'u32' is the biggest size.
+ */
+#define unsafe_copy_loop(dst, src, len, type, label) 		\
+	while (len >= sizeof(type)) {				\
+		unsafe_put_user(get_unaligned((type *)src),	\
+			(type __user *)dst, label);		\
+		dst += sizeof(type);				\
+		src += sizeof(type);				\
+		len -= sizeof(type);				\
+	}
+
+/*
+ * We avoid doing 64-bit copies on 32-bit architectures. They
+ * might be better, but the component names are mostly small,
+ * and the 64-bit cases can end up being much more complex and
+ * put much more register pressure on the code, so it's likely
+ * not worth the pain of unaligned accesses etc.
+ *
+ * So limit the copies to "unsigned long" size. I did verify
+ * that at least the x86-32 case is ok without this limiting,
+ * but I worry about random other legacy 32-bit cases that
+ * might not do as well.
+ */
+#define unsafe_copy_type(dst, src, len, type, label) do {	\
+	if (sizeof(type) <= sizeof(unsigned long))		\
+		unsafe_copy_loop(dst, src, len, type, label);	\
+} while (0)
+
+/*
+ * Copy the dirent name to user space, and NUL-terminate
+ * it. This should not be a function call, since we're doing
+ * the copy inside a "user_access_begin/end()" section.
+ */
+#define unsafe_copy_dirent_name(_dst, _src, _len, label) do {	\
+	char __user *dst = (_dst);				\
+	const char *src = (_src);				\
+	size_t len = (_len);					\
+	unsafe_copy_type(dst, src, len, u64, label);	 	\
+	unsafe_copy_type(dst, src, len, u32, label);		\
+	unsafe_copy_type(dst, src, len, u16, label);		\
+	unsafe_copy_type(dst, src, len, u8,  label);		\
+	unsafe_put_user(0, dst, label);				\
+} while (0)
+
+
 int iterate_dir(struct file *file, struct dir_context *ctx)
 {
 	struct inode *inode = file_inode(file);
@@ -182,28 +236,31 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen,
 		return -EOVERFLOW;
 	}
 	dirent = buf->previous;
-	if (dirent) {
-		if (signal_pending(current))
-			return -EINTR;
-		if (__put_user(offset, &dirent->d_off))
-			goto efault;
-	}
-	dirent = buf->current_dir;
-	if (__put_user(d_ino, &dirent->d_ino))
-		goto efault;
-	if (__put_user(reclen, &dirent->d_reclen))
-		goto efault;
-	if (copy_to_user(dirent->d_name, name, namlen))
-		goto efault;
-	if (__put_user(0, dirent->d_name + namlen))
-		goto efault;
-	if (__put_user(d_type, (char __user *) dirent + reclen - 1))
+	if (dirent && signal_pending(current))
+		return -EINTR;
+
+	/*
+	 * Note! This range-checks 'previous' (which may be NULL).
+	 * The real range was checked in getdents
+	 */
+	if (!user_access_begin(dirent, sizeof(*dirent)))
 		goto efault;
+	if (dirent)
+		unsafe_put_user(offset, &dirent->d_off, efault_end);
+	dirent = buf->current_dir;
+	unsafe_put_user(d_ino, &dirent->d_ino, efault_end);
+	unsafe_put_user(reclen, &dirent->d_reclen, efault_end);
+	unsafe_put_user(d_type, (char __user *) dirent + reclen - 1, efault_end);
+	unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end);
+	user_access_end();
+
 	buf->previous = dirent;
 	dirent = (void __user *)dirent + reclen;
 	buf->current_dir = dirent;
 	buf->count -= reclen;
 	return 0;
+efault_end:
+	user_access_end();
 efault:
 	buf->error = -EFAULT;
 	return -EFAULT;
@@ -263,30 +320,31 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen,
 	if (reclen > buf->count)
 		return -EINVAL;
 	dirent = buf->previous;
-	if (dirent) {
-		if (signal_pending(current))
-			return -EINTR;
-		if (__put_user(offset, &dirent->d_off))
-			goto efault;
-	}
-	dirent = buf->current_dir;
-	if (__put_user(ino, &dirent->d_ino))
-		goto efault;
-	if (__put_user(0, &dirent->d_off))
-		goto efault;
-	if (__put_user(reclen, &dirent->d_reclen))
-		goto efault;
-	if (__put_user(d_type, &dirent->d_type))
-		goto efault;
-	if (copy_to_user(dirent->d_name, name, namlen))
-		goto efault;
-	if (__put_user(0, dirent->d_name + namlen))
+	if (dirent && signal_pending(current))
+		return -EINTR;
+
+	/*
+	 * Note! This range-checks 'previous' (which may be NULL).
+	 * The real range was checked in getdents
+	 */
+	if (!user_access_begin(dirent, sizeof(*dirent)))
 		goto efault;
+	if (dirent)
+		unsafe_put_user(offset, &dirent->d_off, efault_end);
+	dirent = buf->current_dir;
+	unsafe_put_user(ino, &dirent->d_ino, efault_end);
+	unsafe_put_user(reclen, &dirent->d_reclen, efault_end);
+	unsafe_put_user(d_type, &dirent->d_type, efault_end);
+	unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end);
+	user_access_end();
+
 	buf->previous = dirent;
 	dirent = (void __user *)dirent + reclen;
 	buf->current_dir = dirent;
 	buf->count -= reclen;
 	return 0;
+efault_end:
+	user_access_end();
 efault:
 	buf->error = -EFAULT;
 	return -EFAULT;
-- 
cgit v1.2.3


From 8a23eb804ca4f2be909e372cf5a9e7b30ae476cd Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sat, 5 Oct 2019 11:32:52 -0700
Subject: Make filldir[64]() verify the directory entry filename is valid

This has been discussed several times, and now filesystem people are
talking about doing it individually at the filesystem layer, so head
that off at the pass and just do it in getdents{64}().

This is partially based on a patch by Jann Horn, but checks for NUL
bytes as well, and somewhat simplified.

There's also commentary about how it might be better if invalid names
due to filesystem corruption don't cause an immediate failure, but only
an error at the end of the readdir(), so that people can still see the
filenames that are ok.

There's also been discussion about just how much POSIX strictly speaking
requires this since it's about filesystem corruption.  It's really more
"protect user space from bad behavior" as pointed out by Jann.  But
since Eric Biederman looked up the POSIX wording, here it is for context:

 "From readdir:

   The readdir() function shall return a pointer to a structure
   representing the directory entry at the current position in the
   directory stream specified by the argument dirp, and position the
   directory stream at the next entry. It shall return a null pointer
   upon reaching the end of the directory stream. The structure dirent
   defined in the <dirent.h> header describes a directory entry.

  From definitions:

   3.129 Directory Entry (or Link)

   An object that associates a filename with a file. Several directory
   entries can associate names with the same file.

  ...

   3.169 Filename

   A name consisting of 1 to {NAME_MAX} bytes used to name a file. The
   characters composing the name may be selected from the set of all
   character values excluding the slash character and the null byte. The
   filenames dot and dot-dot have special meaning. A filename is
   sometimes referred to as a 'pathname component'."

Note that I didn't bother adding the checks to any legacy interfaces
that nobody uses.

Also note that if this ends up being noticeable as a performance
regression, we can fix that to do a much more optimized model that
checks for both NUL and '/' at the same time one word at a time.

We haven't really tended to optimize 'memchr()', and it only checks for
one pattern at a time anyway, and we really _should_ check for NUL too
(but see the comment about "soft errors" in the code about why it
currently only checks for '/')

See the CONFIG_DCACHE_WORD_ACCESS case of hash_name() for how the name
lookup code looks for pathname terminating characters in parallel.

Link: https://lore.kernel.org/lkml/20190118161440.220134-2-jannh@google.com/
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jann Horn <jannh@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/readdir.c | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/fs/readdir.c b/fs/readdir.c
index 579c8ea894ae..19bea591c3f1 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -118,6 +118,40 @@ out:
 }
 EXPORT_SYMBOL(iterate_dir);
 
+/*
+ * POSIX says that a dirent name cannot contain NULL or a '/'.
+ *
+ * It's not 100% clear what we should really do in this case.
+ * The filesystem is clearly corrupted, but returning a hard
+ * error means that you now don't see any of the other names
+ * either, so that isn't a perfect alternative.
+ *
+ * And if you return an error, what error do you use? Several
+ * filesystems seem to have decided on EUCLEAN being the error
+ * code for EFSCORRUPTED, and that may be the error to use. Or
+ * just EIO, which is perhaps more obvious to users.
+ *
+ * In order to see the other file names in the directory, the
+ * caller might want to make this a "soft" error: skip the
+ * entry, and return the error at the end instead.
+ *
+ * Note that this should likely do a "memchr(name, 0, len)"
+ * check too, since that would be filesystem corruption as
+ * well. However, that case can't actually confuse user space,
+ * which has to do a strlen() on the name anyway to find the
+ * filename length, and the above "soft error" worry means
+ * that it's probably better left alone until we have that
+ * issue clarified.
+ */
+static int verify_dirent_name(const char *name, int len)
+{
+	if (WARN_ON_ONCE(!len))
+		return -EIO;
+	if (WARN_ON_ONCE(memchr(name, '/', len)))
+		return -EIO;
+	return 0;
+}
+
 /*
  * Traditional linux readdir() handling..
  *
@@ -227,6 +261,9 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen,
 	int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2,
 		sizeof(long));
 
+	buf->error = verify_dirent_name(name, namlen);
+	if (unlikely(buf->error))
+		return buf->error;
 	buf->error = -EINVAL;	/* only used if we fail.. */
 	if (reclen > buf->count)
 		return -EINVAL;
@@ -316,6 +353,9 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen,
 	int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
 		sizeof(u64));
 
+	buf->error = verify_dirent_name(name, namlen);
+	if (unlikely(buf->error))
+		return buf->error;
 	buf->error = -EINVAL;	/* only used if we fail.. */
 	if (reclen > buf->count)
 		return -EINVAL;
-- 
cgit v1.2.3


From 7fd296024c3cd06773a1df712b2c50932aeea60b Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 4 Oct 2019 15:20:17 +0300
Subject: drm/i915/vga: rename intel_vga_msr_write() to
 intel_vga_reset_io_mem()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename the function per Ville's suggestion. No functional changes.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Suggested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004122019.12009-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/display/intel_display_power.c | 2 +-
 drivers/gpu/drm/i915/display/intel_vga.c           | 2 +-
 drivers/gpu/drm/i915/display/intel_vga.h           | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index bb642a1a0dd4..0616284c6da6 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -267,7 +267,7 @@ static void hsw_power_well_post_enable(struct drm_i915_private *dev_priv,
 				       u8 irq_pipe_mask, bool has_vga)
 {
 	if (has_vga)
-		intel_vga_msr_write(dev_priv);
+		intel_vga_reset_io_mem(dev_priv);
 
 	if (irq_pipe_mask)
 		gen8_irq_power_well_post_enable(dev_priv, irq_pipe_mask);
diff --git a/drivers/gpu/drm/i915/display/intel_vga.c b/drivers/gpu/drm/i915/display/intel_vga.c
index 732568eaa988..2ff7293986d4 100644
--- a/drivers/gpu/drm/i915/display/intel_vga.c
+++ b/drivers/gpu/drm/i915/display/intel_vga.c
@@ -72,7 +72,7 @@ void intel_vga_redisable(struct drm_i915_private *i915)
 	intel_display_power_put(i915, POWER_DOMAIN_VGA, wakeref);
 }
 
-void intel_vga_msr_write(struct drm_i915_private *i915)
+void intel_vga_reset_io_mem(struct drm_i915_private *i915)
 {
 	struct pci_dev *pdev = i915->drm.pdev;
 
diff --git a/drivers/gpu/drm/i915/display/intel_vga.h b/drivers/gpu/drm/i915/display/intel_vga.h
index 3517872e62ac..ba5b55b917f0 100644
--- a/drivers/gpu/drm/i915/display/intel_vga.h
+++ b/drivers/gpu/drm/i915/display/intel_vga.h
@@ -8,7 +8,7 @@
 
 struct drm_i915_private;
 
-void intel_vga_msr_write(struct drm_i915_private *i915);
+void intel_vga_reset_io_mem(struct drm_i915_private *i915);
 void intel_vga_disable(struct drm_i915_private *i915);
 void intel_vga_redisable(struct drm_i915_private *i915);
 void intel_vga_redisable_power_on(struct drm_i915_private *i915);
-- 
cgit v1.2.3


From 63bf8301aac492d4c5fdf7b0ec42b142c05080e3 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 4 Oct 2019 15:20:18 +0300
Subject: drm/i915: split out i915_switcheroo.[ch] from i915_drv.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Split out code related to vga switcheroo register/unregister and state
handling from i915_drv.c into new i915_switcheroo.[ch] files.

It's a bit difficult to draw the line how much to move to the new file
from i915_drv.c, but it seemed to me keeping i915_suspend_switcheroo()
and i915_resume_switcheroo() in place was the cleanest.

No functional changes.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004122019.12009-2-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/Makefile          |  1 +
 drivers/gpu/drm/i915/i915_drv.c        | 63 ++++----------------------------
 drivers/gpu/drm/i915/i915_drv.h        |  3 ++
 drivers/gpu/drm/i915/i915_switcheroo.c | 67 ++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_switcheroo.h | 14 +++++++
 5 files changed, 92 insertions(+), 56 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/i915_switcheroo.c
 create mode 100644 drivers/gpu/drm/i915/i915_switcheroo.h

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 4e23f1a5c39f..45d3be12359d 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -46,6 +46,7 @@ i915-y += i915_drv.o \
 	  i915_pci.o \
 	  i915_scatterlist.o \
 	  i915_suspend.o \
+	  i915_switcheroo.o \
 	  i915_sysfs.o \
 	  i915_utils.o \
 	  intel_csr.o \
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 5183a40d3860..902a54bb46e0 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -72,6 +72,7 @@
 #include "i915_perf.h"
 #include "i915_query.h"
 #include "i915_suspend.h"
+#include "i915_switcheroo.h"
 #include "i915_sysfs.h"
 #include "i915_trace.h"
 #include "i915_vgpu.h"
@@ -269,56 +270,8 @@ intel_teardown_mchbar(struct drm_i915_private *dev_priv)
 		release_resource(&dev_priv->mch_res);
 }
 
-static int i915_resume_switcheroo(struct drm_i915_private *i915);
-static int i915_suspend_switcheroo(struct drm_i915_private *i915,
-				   pm_message_t state);
-
-static void i915_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_state state)
-{
-	struct drm_i915_private *i915 = pdev_to_i915(pdev);
-	pm_message_t pmm = { .event = PM_EVENT_SUSPEND };
-
-	if (!i915) {
-		dev_err(&pdev->dev, "DRM not initialized, aborting switch.\n");
-		return;
-	}
-
-	if (state == VGA_SWITCHEROO_ON) {
-		pr_info("switched on\n");
-		i915->drm.switch_power_state = DRM_SWITCH_POWER_CHANGING;
-		/* i915 resume handler doesn't set to D0 */
-		pci_set_power_state(pdev, PCI_D0);
-		i915_resume_switcheroo(i915);
-		i915->drm.switch_power_state = DRM_SWITCH_POWER_ON;
-	} else {
-		pr_info("switched off\n");
-		i915->drm.switch_power_state = DRM_SWITCH_POWER_CHANGING;
-		i915_suspend_switcheroo(i915, pmm);
-		i915->drm.switch_power_state = DRM_SWITCH_POWER_OFF;
-	}
-}
-
-static bool i915_switcheroo_can_switch(struct pci_dev *pdev)
-{
-	struct drm_i915_private *i915 = pdev_to_i915(pdev);
-
-	/*
-	 * FIXME: open_count is protected by drm_global_mutex but that would lead to
-	 * locking inversion with the driver load path. And the access here is
-	 * completely racy anyway. So don't bother with locking for now.
-	 */
-	return i915 && i915->drm.open_count == 0;
-}
-
-static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {
-	.set_gpu_state = i915_switcheroo_set_state,
-	.reprobe = NULL,
-	.can_switch = i915_switcheroo_can_switch,
-};
-
 static int i915_driver_modeset_probe(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = i915->drm.pdev;
 	int ret;
 
 	if (i915_inject_probe_failure(i915))
@@ -339,7 +292,7 @@ static int i915_driver_modeset_probe(struct drm_i915_private *i915)
 
 	intel_register_dsm_handler();
 
-	ret = vga_switcheroo_register_client(pdev, &i915_switcheroo_ops, false);
+	ret = i915_switcheroo_register(i915);
 	if (ret)
 		goto cleanup_vga_client;
 
@@ -394,7 +347,7 @@ cleanup_irq:
 cleanup_csr:
 	intel_csr_ucode_fini(i915);
 	intel_power_domains_driver_remove(i915);
-	vga_switcheroo_unregister_client(pdev);
+	i915_switcheroo_unregister(i915);
 cleanup_vga_client:
 	intel_vga_unregister(i915);
 out:
@@ -428,13 +381,12 @@ static int i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv)
 
 static void i915_driver_modeset_remove(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = i915->drm.pdev;
-
 	intel_modeset_driver_remove(i915);
 
 	intel_bios_driver_remove(i915);
 
-	vga_switcheroo_unregister_client(pdev);
+	i915_switcheroo_unregister(i915);
+
 	intel_vga_unregister(i915);
 
 	intel_csr_ucode_fini(i915);
@@ -1860,8 +1812,7 @@ out:
 	return ret;
 }
 
-static int
-i915_suspend_switcheroo(struct drm_i915_private *i915, pm_message_t state)
+int i915_suspend_switcheroo(struct drm_i915_private *i915, pm_message_t state)
 {
 	int error;
 
@@ -2027,7 +1978,7 @@ static int i915_drm_resume_early(struct drm_device *dev)
 	return ret;
 }
 
-static int i915_resume_switcheroo(struct drm_i915_private *i915)
+int i915_resume_switcheroo(struct drm_i915_private *i915)
 {
 	int ret;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index cde4c7fb5570..b367467b03c2 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2189,6 +2189,9 @@ extern const struct dev_pm_ops i915_pm_ops;
 int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent);
 void i915_driver_remove(struct drm_i915_private *i915);
 
+int i915_resume_switcheroo(struct drm_i915_private *i915);
+int i915_suspend_switcheroo(struct drm_i915_private *i915, pm_message_t state);
+
 void intel_engine_init_hangcheck(struct intel_engine_cs *engine);
 int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on);
 
diff --git a/drivers/gpu/drm/i915/i915_switcheroo.c b/drivers/gpu/drm/i915/i915_switcheroo.c
new file mode 100644
index 000000000000..39c79e1c5b52
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_switcheroo.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/vga_switcheroo.h>
+
+#include "i915_drv.h"
+#include "i915_switcheroo.h"
+
+static void i915_switcheroo_set_state(struct pci_dev *pdev,
+				      enum vga_switcheroo_state state)
+{
+	struct drm_i915_private *i915 = pdev_to_i915(pdev);
+	pm_message_t pmm = { .event = PM_EVENT_SUSPEND };
+
+	if (!i915) {
+		dev_err(&pdev->dev, "DRM not initialized, aborting switch.\n");
+		return;
+	}
+
+	if (state == VGA_SWITCHEROO_ON) {
+		pr_info("switched on\n");
+		i915->drm.switch_power_state = DRM_SWITCH_POWER_CHANGING;
+		/* i915 resume handler doesn't set to D0 */
+		pci_set_power_state(pdev, PCI_D0);
+		i915_resume_switcheroo(i915);
+		i915->drm.switch_power_state = DRM_SWITCH_POWER_ON;
+	} else {
+		pr_info("switched off\n");
+		i915->drm.switch_power_state = DRM_SWITCH_POWER_CHANGING;
+		i915_suspend_switcheroo(i915, pmm);
+		i915->drm.switch_power_state = DRM_SWITCH_POWER_OFF;
+	}
+}
+
+static bool i915_switcheroo_can_switch(struct pci_dev *pdev)
+{
+	struct drm_i915_private *i915 = pdev_to_i915(pdev);
+
+	/*
+	 * FIXME: open_count is protected by drm_global_mutex but that would lead to
+	 * locking inversion with the driver load path. And the access here is
+	 * completely racy anyway. So don't bother with locking for now.
+	 */
+	return i915 && i915->drm.open_count == 0;
+}
+
+static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {
+	.set_gpu_state = i915_switcheroo_set_state,
+	.reprobe = NULL,
+	.can_switch = i915_switcheroo_can_switch,
+};
+
+int i915_switcheroo_register(struct drm_i915_private *i915)
+{
+	struct pci_dev *pdev = i915->drm.pdev;
+
+	return vga_switcheroo_register_client(pdev, &i915_switcheroo_ops, false);
+}
+
+void i915_switcheroo_unregister(struct drm_i915_private *i915)
+{
+	struct pci_dev *pdev = i915->drm.pdev;
+
+	vga_switcheroo_unregister_client(pdev);
+}
diff --git a/drivers/gpu/drm/i915/i915_switcheroo.h b/drivers/gpu/drm/i915/i915_switcheroo.h
new file mode 100644
index 000000000000..59b6c1e07d75
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_switcheroo.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __I915_SWITCHEROO__
+#define __I915_SWITCHEROO__
+
+struct drm_i915_private;
+
+int i915_switcheroo_register(struct drm_i915_private *i915);
+void i915_switcheroo_unregister(struct drm_i915_private *i915);
+
+#endif /* __I915_SWITCHEROO__ */
-- 
cgit v1.2.3


From 9bfcf1941302c471e8c8138b6b01f7b84d4f5ba4 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 4 Oct 2019 15:20:19 +0300
Subject: drm/i915: move gmbus setup down to intel_modeset_init()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Pair the gmbus setup and teardown in the same layer. This also fixes the
double gmbus teardown on the i915_driver_modeset_probe() error path.

Move the gmbus setup a bit later in the sequence to make the follow-up
refactoring easier, and to pinpoint any unexpected consequences of this
change right here, instead of the later refactoring.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004122019.12009-3-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 2 ++
 drivers/gpu/drm/i915/i915_drv.c              | 4 ----
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index c15975a410bc..05fb672a00b9 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -16216,6 +16216,8 @@ int intel_modeset_init(struct drm_i915_private *i915)
 
 	intel_panel_sanitize_ssc(i915);
 
+	intel_gmbus_setup(i915);
+
 	DRM_DEBUG_KMS("%d display pipe%s available.\n",
 		      INTEL_NUM_PIPES(i915),
 		      INTEL_NUM_PIPES(i915) > 1 ? "s" : "");
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 902a54bb46e0..15abad5c2d62 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -53,7 +53,6 @@
 #include "display/intel_display_types.h"
 #include "display/intel_dp.h"
 #include "display/intel_fbdev.h"
-#include "display/intel_gmbus.h"
 #include "display/intel_hotplug.h"
 #include "display/intel_overlay.h"
 #include "display/intel_pipe_crc.h"
@@ -307,8 +306,6 @@ static int i915_driver_modeset_probe(struct drm_i915_private *i915)
 	if (ret)
 		goto cleanup_csr;
 
-	intel_gmbus_setup(i915);
-
 	/* Important: The output setup functions called by modeset_init need
 	 * working irqs for e.g. gmbus and dp aux transfers. */
 	ret = intel_modeset_init(i915);
@@ -343,7 +340,6 @@ cleanup_modeset:
 	intel_modeset_driver_remove(i915);
 cleanup_irq:
 	intel_irq_uninstall(i915);
-	intel_gmbus_teardown(i915);
 cleanup_csr:
 	intel_csr_ucode_fini(i915);
 	intel_power_domains_driver_remove(i915);
-- 
cgit v1.2.3


From c763ac436b668d7417f0979430ec0312ede4093d Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sat, 5 Oct 2019 15:05:18 -0700
Subject: net: dsa: b53: Do not clear existing mirrored port mask

Clearing the existing bitmask of mirrored ports essentially prevents us
from capturing more than one port at any given time. This is clearly
wrong, do not clear the bitmask prior to setting up the new port.

Reported-by: Hubert Feurstein <h.feurstein@gmail.com>
Fixes: ed3af5fd08eb ("net: dsa: b53: Add support for port mirroring")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_common.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 526ba2ab66f1..cc3536315eff 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -1845,7 +1845,6 @@ int b53_mirror_add(struct dsa_switch *ds, int port,
 		loc = B53_EG_MIR_CTL;
 
 	b53_read16(dev, B53_MGMT_PAGE, loc, &reg);
-	reg &= ~MIRROR_MASK;
 	reg |= BIT(port);
 	b53_write16(dev, B53_MGMT_PAGE, loc, reg);
 
-- 
cgit v1.2.3


From a2b90f11217790ec0964ba9c93a4abb369758c26 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Fri, 4 Oct 2019 13:00:24 +0300
Subject: bdi: Do not use freezable workqueue

A removable block device, such as NVMe or SSD connected over Thunderbolt
can be hot-removed any time including when the system is suspended. When
device is hot-removed during suspend and the system gets resumed, kernel
first resumes devices and then thaws the userspace including freezable
workqueues. What happens in that case is that the NVMe driver notices
that the device is unplugged and removes it from the system. This ends
up calling bdi_unregister() for the gendisk which then schedules
wb_workfn() to be run one more time.

However, since the bdi_wq is still frozen flush_delayed_work() call in
wb_shutdown() blocks forever halting system resume process. User sees
this as hang as nothing is happening anymore.

Triggering sysrq-w reveals this:

  Workqueue: nvme-wq nvme_remove_dead_ctrl_work [nvme]
  Call Trace:
   ? __schedule+0x2c5/0x630
   ? wait_for_completion+0xa4/0x120
   schedule+0x3e/0xc0
   schedule_timeout+0x1c9/0x320
   ? resched_curr+0x1f/0xd0
   ? wait_for_completion+0xa4/0x120
   wait_for_completion+0xc3/0x120
   ? wake_up_q+0x60/0x60
   __flush_work+0x131/0x1e0
   ? flush_workqueue_prep_pwqs+0x130/0x130
   bdi_unregister+0xb9/0x130
   del_gendisk+0x2d2/0x2e0
   nvme_ns_remove+0xed/0x110 [nvme_core]
   nvme_remove_namespaces+0x96/0xd0 [nvme_core]
   nvme_remove+0x5b/0x160 [nvme]
   pci_device_remove+0x36/0x90
   device_release_driver_internal+0xdf/0x1c0
   nvme_remove_dead_ctrl_work+0x14/0x30 [nvme]
   process_one_work+0x1c2/0x3f0
   worker_thread+0x48/0x3e0
   kthread+0x100/0x140
   ? current_work+0x30/0x30
   ? kthread_park+0x80/0x80
   ret_from_fork+0x35/0x40

This is not limited to NVMes so exactly same issue can be reproduced by
hot-removing SSD (over Thunderbolt) while the system is suspended.

Prevent this from happening by removing WQ_FREEZABLE from bdi_wq.

Reported-by: AceLan Kao <acelan.kao@canonical.com>
Link: https://marc.info/?l=linux-kernel&m=138695698516487
Link: https://bugzilla.kernel.org/show_bug.cgi?id=204385
Link: https://lore.kernel.org/lkml/20191002122136.GD2819@lahna.fi.intel.com/#t
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 mm/backing-dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index d9daa3e422d0..c360f6a6c844 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -239,8 +239,8 @@ static int __init default_bdi_init(void)
 {
 	int err;
 
-	bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_FREEZABLE |
-					      WQ_UNBOUND | WQ_SYSFS, 0);
+	bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND |
+				 WQ_SYSFS, 0);
 	if (!bdi_wq)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From 0e48f51cbbfbdb79149806de14dcb8bf0f01ca94 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Fri, 4 Oct 2019 13:00:25 +0300
Subject: Revert "libata, freezer: avoid block device removal while system is
 frozen"

This reverts commit 85fbd722ad0f5d64d1ad15888cd1eb2188bfb557.

The commit was added as a quick band-aid for a hang that happened when a
block device was removed during system suspend. Now that bdi_wq is not
freezable anymore the hang should not be possible and we can get rid of
this hack by reverting it.

Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/ata/libata-scsi.c | 21 ---------------------
 kernel/freezer.c          |  6 ------
 2 files changed, 27 deletions(-)

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 76d0f9de767b..58e09ffe8b9c 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -4791,27 +4791,6 @@ void ata_scsi_hotplug(struct work_struct *work)
 		return;
 	}
 
-	/*
-	 * XXX - UGLY HACK
-	 *
-	 * The block layer suspend/resume path is fundamentally broken due
-	 * to freezable kthreads and workqueue and may deadlock if a block
-	 * device gets removed while resume is in progress.  I don't know
-	 * what the solution is short of removing freezable kthreads and
-	 * workqueues altogether.
-	 *
-	 * The following is an ugly hack to avoid kicking off device
-	 * removal while freezer is active.  This is a joke but does avoid
-	 * this particular deadlock scenario.
-	 *
-	 * https://bugzilla.kernel.org/show_bug.cgi?id=62801
-	 * http://marc.info/?l=linux-kernel&m=138695698516487
-	 */
-#ifdef CONFIG_FREEZER
-	while (pm_freezing)
-		msleep(10);
-#endif
-
 	DPRINTK("ENTER\n");
 	mutex_lock(&ap->scsi_scan_mutex);
 
diff --git a/kernel/freezer.c b/kernel/freezer.c
index c0738424bb43..dc520f01f99d 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -22,12 +22,6 @@ EXPORT_SYMBOL(system_freezing_cnt);
 bool pm_freezing;
 bool pm_nosig_freezing;
 
-/*
- * Temporary export for the deadlock workaround in ata_scsi_hotplug().
- * Remove once the hack becomes unnecessary.
- */
-EXPORT_SYMBOL_GPL(pm_freezing);
-
 /* protects freezing and frozen transitions */
 static DEFINE_SPINLOCK(freezer_lock);
 
-- 
cgit v1.2.3


From b84477d3ebb96294f87dc3161e53fa8fe22d9bfd Mon Sep 17 00:00:00 2001
From: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Date: Sat, 5 Oct 2019 11:59:27 -0700
Subject: blk-wbt: fix performance regression in wbt scale_up/scale_down

scale_up wakes up waiters after scaling up. But after scaling max, it
should not wake up more waiters as waiters will not have anything to
do. This patch fixes this by making scale_up (and also scale_down)
return when threshold is reached.

This bug causes increased fdatasync latency when fdatasync and dd
conv=sync are performed in parallel on 4.19 compared to 4.14. This
bug was introduced during refactoring of blk-wbt code.

Fixes: a79050434b45 ("blk-rq-qos: refactor out common elements of blk-wbt")
Cc: stable@vger.kernel.org
Cc: Josef Bacik <jbacik@fb.com>
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-rq-qos.c | 14 +++++++++-----
 block/blk-rq-qos.h |  4 ++--
 block/blk-wbt.c    |  6 ++++--
 3 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index 61b635bc2a31..656460636ad3 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -160,24 +160,27 @@ bool rq_depth_calc_max_depth(struct rq_depth *rqd)
 	return ret;
 }
 
-void rq_depth_scale_up(struct rq_depth *rqd)
+/* Returns true on success and false if scaling up wasn't possible */
+bool rq_depth_scale_up(struct rq_depth *rqd)
 {
 	/*
 	 * Hit max in previous round, stop here
 	 */
 	if (rqd->scaled_max)
-		return;
+		return false;
 
 	rqd->scale_step--;
 
 	rqd->scaled_max = rq_depth_calc_max_depth(rqd);
+	return true;
 }
 
 /*
  * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
- * had a latency violation.
+ * had a latency violation. Returns true on success and returns false if
+ * scaling down wasn't possible.
  */
-void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
+bool rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
 {
 	/*
 	 * Stop scaling down when we've hit the limit. This also prevents
@@ -185,7 +188,7 @@ void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
 	 * keep up.
 	 */
 	if (rqd->max_depth == 1)
-		return;
+		return false;
 
 	if (rqd->scale_step < 0 && hard_throttle)
 		rqd->scale_step = 0;
@@ -194,6 +197,7 @@ void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
 
 	rqd->scaled_max = false;
 	rq_depth_calc_max_depth(rqd);
+	return true;
 }
 
 struct rq_qos_wait_data {
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index 08a09dbe0f4b..e8cb68f6958a 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -130,8 +130,8 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data,
 		 acquire_inflight_cb_t *acquire_inflight_cb,
 		 cleanup_cb_t *cleanup_cb);
 bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit);
-void rq_depth_scale_up(struct rq_depth *rqd);
-void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
+bool rq_depth_scale_up(struct rq_depth *rqd);
+bool rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
 bool rq_depth_calc_max_depth(struct rq_depth *rqd);
 
 void __rq_qos_cleanup(struct rq_qos *rqos, struct bio *bio);
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 8af553a0ba00..8641ba9793c5 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -308,7 +308,8 @@ static void calc_wb_limits(struct rq_wb *rwb)
 
 static void scale_up(struct rq_wb *rwb)
 {
-	rq_depth_scale_up(&rwb->rq_depth);
+	if (!rq_depth_scale_up(&rwb->rq_depth))
+		return;
 	calc_wb_limits(rwb);
 	rwb->unknown_cnt = 0;
 	rwb_wake_all(rwb);
@@ -317,7 +318,8 @@ static void scale_up(struct rq_wb *rwb)
 
 static void scale_down(struct rq_wb *rwb, bool hard_throttle)
 {
-	rq_depth_scale_down(&rwb->rq_depth, hard_throttle);
+	if (!rq_depth_scale_down(&rwb->rq_depth, hard_throttle))
+		return;
 	calc_wb_limits(rwb);
 	rwb->unknown_cnt = 0;
 	rwb_trace_step(rwb, "scale down");
-- 
cgit v1.2.3


From b870b0f867c77b92d7fd17ace8421904270d3c6a Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Sun, 6 Oct 2019 13:08:55 +0200
Subject: net: stmmac: selftests: Check if filtering is available before
 running

We need to check if the number of available Hash Filters is enough to
run the test, otherwise we will get false failures.

Fixes: 091810dbded9 ("net: stmmac: Introduce selftests support")
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
index cc76a42c7466..ed3926d4471d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -496,6 +496,9 @@ static int stmmac_test_hfilt(struct stmmac_priv *priv)
 	if (ret)
 		return ret;
 
+	if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins)
+		return -EOPNOTSUPP;
+
 	ret = dev_mc_add(priv->dev, gd_addr);
 	if (ret)
 		return ret;
@@ -573,6 +576,8 @@ static int stmmac_test_mcfilt(struct stmmac_priv *priv)
 
 	if (stmmac_filter_check(priv))
 		return -EOPNOTSUPP;
+	if (!priv->hw->multicast_filter_bins)
+		return -EOPNOTSUPP;
 
 	/* Remove all MC addresses */
 	__dev_mc_unsync(priv->dev, NULL);
@@ -611,6 +616,8 @@ static int stmmac_test_ucfilt(struct stmmac_priv *priv)
 
 	if (stmmac_filter_check(priv))
 		return -EOPNOTSUPP;
+	if (!priv->hw->multicast_filter_bins)
+		return -EOPNOTSUPP;
 
 	/* Remove all UC addresses */
 	__dev_uc_unsync(priv->dev, NULL);
-- 
cgit v1.2.3


From 25683bab09a70542b9f8e3e28f79b3369e56701f Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Sun, 6 Oct 2019 13:08:56 +0200
Subject: net: stmmac: gmac4+: Not all Unicast addresses may be available

Some setups may not have all Unicast addresses filters available. Check
the number of available filters before trying to setup it.

Fixes: 477286b53f55 ("stmmac: add GMAC4 core support")
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 2cb9c53f93b8..5a7b0aca1d31 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -448,7 +448,7 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 	value |= GMAC_PACKET_FILTER_HPF;
 
 	/* Handle multiple unicast addresses */
-	if (netdev_uc_count(dev) > GMAC_MAX_PERFECT_ADDRESSES) {
+	if (netdev_uc_count(dev) > hw->unicast_filter_entries) {
 		/* Switch to promiscuous mode if more than 128 addrs
 		 * are required
 		 */
-- 
cgit v1.2.3


From 2809fc13163f4946d7cde092807bea44bbae4478 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Sun, 6 Oct 2019 13:08:57 +0200
Subject: net: stmmac: selftests: Fix L2 Hash Filter test

With the current MAC addresses hard-coded in the test we can get some
false positives as we use the Hash Filtering method. Let's change the
MAC addresses in the tests to be unique when hashed.

Fixes: 091810dbded9 ("net: stmmac: Introduce selftests support")
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
index ed3926d4471d..e4ac3c401432 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -487,8 +487,8 @@ static int stmmac_filter_check(struct stmmac_priv *priv)
 
 static int stmmac_test_hfilt(struct stmmac_priv *priv)
 {
-	unsigned char gd_addr[ETH_ALEN] = {0x01, 0x00, 0xcc, 0xcc, 0xdd, 0xdd};
-	unsigned char bd_addr[ETH_ALEN] = {0x09, 0x00, 0xaa, 0xaa, 0xbb, 0xbb};
+	unsigned char gd_addr[ETH_ALEN] = {0x01, 0xee, 0xdd, 0xcc, 0xbb, 0xaa};
+	unsigned char bd_addr[ETH_ALEN] = {0x01, 0x01, 0x02, 0x03, 0x04, 0x05};
 	struct stmmac_packet_attrs attr = { };
 	int ret;
 
-- 
cgit v1.2.3


From b212921b13bda088a004328457c5c21458262fe2 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 6 Oct 2019 13:53:27 -0700
Subject: elf: don't use MAP_FIXED_NOREPLACE for elf executable mappings

In commit 4ed28639519c ("fs, elf: drop MAP_FIXED usage from elf_map") we
changed elf to use MAP_FIXED_NOREPLACE instead of MAP_FIXED for the
executable mappings.

Then, people reported that it broke some binaries that had overlapping
segments from the same file, and commit ad55eac74f20 ("elf: enforce
MAP_FIXED on overlaying elf segments") re-instated MAP_FIXED for some
overlaying elf segment cases.  But only some - despite the summary line
of that commit, it only did it when it also does a temporary brk vma for
one obvious overlapping case.

Now Russell King reports another overlapping case with old 32-bit x86
binaries, which doesn't trigger that limited case.  End result: we had
better just drop MAP_FIXED_NOREPLACE entirely, and go back to MAP_FIXED.

Yes, it's a sign of old binaries generated with old tool-chains, but we
do pride ourselves on not breaking existing setups.

This still leaves MAP_FIXED_NOREPLACE in place for the load_elf_interp()
and the old load_elf_library() use-cases, because nobody has reported
breakage for those. Yet.

Note that in all the cases seen so far, the overlapping elf sections
seem to be just re-mapping of the same executable with different section
attributes.  We could possibly introduce a new MAP_FIXED_NOFILECHANGE
flag or similar, which acts like NOREPLACE, but allows just remapping
the same executable file using different protection flags.

It's not clear that would make a huge difference to anything, but if
people really hate that "elf remaps over previous maps" behavior, maybe
at least a more limited form of remapping would alleviate some concerns.

Alternatively, we should take a look at our elf_map() logic to see if we
end up not mapping things properly the first time.

In the meantime, this is the minimal "don't do that then" patch while
people hopefully think about it more.

Reported-by: Russell King <linux@armlinux.org.uk>
Fixes: 4ed28639519c ("fs, elf: drop MAP_FIXED usage from elf_map")
Fixes: ad55eac74f20 ("elf: enforce  MAP_FIXED on overlaying elf segments")
Cc: Michal Hocko <mhocko@suse.com>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/binfmt_elf.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index ad4c6b1d5074..c5642bcb6b46 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -879,7 +879,7 @@ out_free_interp:
 	   the correct location in memory. */
 	for(i = 0, elf_ppnt = elf_phdata;
 	    i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
-		int elf_prot, elf_flags, elf_fixed = MAP_FIXED_NOREPLACE;
+		int elf_prot, elf_flags;
 		unsigned long k, vaddr;
 		unsigned long total_size = 0;
 
@@ -911,13 +911,6 @@ out_free_interp:
 					 */
 				}
 			}
-
-			/*
-			 * Some binaries have overlapping elf segments and then
-			 * we have to forcefully map over an existing mapping
-			 * e.g. over this newly established brk mapping.
-			 */
-			elf_fixed = MAP_FIXED;
 		}
 
 		elf_prot = make_prot(elf_ppnt->p_flags);
@@ -930,7 +923,7 @@ out_free_interp:
 		 * the ET_DYN load_addr calculations, proceed normally.
 		 */
 		if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
-			elf_flags |= elf_fixed;
+			elf_flags |= MAP_FIXED;
 		} else if (loc->elf_ex.e_type == ET_DYN) {
 			/*
 			 * This logic is run once for the first LOAD Program
@@ -966,7 +959,7 @@ out_free_interp:
 				load_bias = ELF_ET_DYN_BASE;
 				if (current->flags & PF_RANDOMIZE)
 					load_bias += arch_mmap_rnd();
-				elf_flags |= elf_fixed;
+				elf_flags |= MAP_FIXED;
 			} else
 				load_bias = 0;
 
-- 
cgit v1.2.3


From da0c9ea146cbe92b832f1b0f694840ea8eb33cce Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 6 Oct 2019 14:27:30 -0700
Subject: Linux 5.4-rc2

---
 Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index 779c9c9b9820..f47dfdec7086 100644
--- a/Makefile
+++ b/Makefile
@@ -2,8 +2,8 @@
 VERSION = 5
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
-NAME = Bobtail Squid
+EXTRAVERSION = -rc2
+NAME = Nesting Opossum
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
-- 
cgit v1.2.3


From e093c4be760ebf46c131ae0dd6138865a22f46fa Mon Sep 17 00:00:00 2001
From: Max Reitz <mreitz@redhat.com>
Date: Mon, 30 Sep 2019 11:29:44 -0700
Subject: xfs: Fix tail rounding in xfs_alloc_file_space()

To ensure that all blocks touched by the range [offset, offset + count)
are allocated, we need to calculate the block count from the difference
of the range end (rounded up) and the range start (rounded down).

Before this patch, we just round up the byte count, which may lead to
unaligned ranges not being fully allocated:

$ touch test_file
$ block_size=$(stat -fc '%S' test_file)
$ fallocate -o $((block_size / 2)) -l $block_size test_file
$ xfs_bmap test_file
test_file:
        0: [0..7]: 1396264..1396271
        1: [8..15]: hole

There should not be a hole there.  Instead, the first two blocks should
be fully allocated.

With this patch applied, the result is something like this:

$ touch test_file
$ block_size=$(stat -fc '%S' test_file)
$ fallocate -o $((block_size / 2)) -l $block_size test_file
$ xfs_bmap test_file
test_file:
        0: [0..15]: 11024..11039

Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_bmap_util.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 0910cb75b65d..4f443703065e 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -864,6 +864,7 @@ xfs_alloc_file_space(
 	xfs_filblks_t		allocatesize_fsb;
 	xfs_extlen_t		extsz, temp;
 	xfs_fileoff_t		startoffset_fsb;
+	xfs_fileoff_t		endoffset_fsb;
 	int			nimaps;
 	int			quota_flag;
 	int			rt;
@@ -891,7 +892,8 @@ xfs_alloc_file_space(
 	imapp = &imaps[0];
 	nimaps = 1;
 	startoffset_fsb	= XFS_B_TO_FSBT(mp, offset);
-	allocatesize_fsb = XFS_B_TO_FSB(mp, count);
+	endoffset_fsb = XFS_B_TO_FSB(mp, offset + count);
+	allocatesize_fsb = endoffset_fsb - startoffset_fsb;
 
 	/*
 	 * Allocate file space until done or until there is an error
-- 
cgit v1.2.3


From 6374ca03975ab0a2b1a5ced222e0ef2ea6e22f9e Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@redhat.com>
Date: Mon, 30 Sep 2019 11:31:12 -0700
Subject: xfs: remove unused flags arg from xfs_get_aghdr_buf()

The flags arg is always passed as zero, so remove it.

(xfs_buf_get_uncached takes flags to support XBF_NO_IOACCT for
the sb, but that should never be relevant for xfs_get_aghdr_buf)

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_ag.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 5de296b34ab1..14fbdf22b7e7 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -28,12 +28,11 @@ xfs_get_aghdr_buf(
 	struct xfs_mount	*mp,
 	xfs_daddr_t		blkno,
 	size_t			numblks,
-	int			flags,
 	const struct xfs_buf_ops *ops)
 {
 	struct xfs_buf		*bp;
 
-	bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, flags);
+	bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, 0);
 	if (!bp)
 		return NULL;
 
@@ -345,7 +344,7 @@ xfs_ag_init_hdr(
 {
 	struct xfs_buf		*bp;
 
-	bp = xfs_get_aghdr_buf(mp, id->daddr, id->numblks, 0, ops);
+	bp = xfs_get_aghdr_buf(mp, id->daddr, id->numblks, ops);
 	if (!bp)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From d5cc14d9f92833bd71219bf7fff180f097c3816d Mon Sep 17 00:00:00 2001
From: Aliasgar Surti <aliasgar.surti500@gmail.com>
Date: Mon, 30 Sep 2019 11:31:48 -0700
Subject: xfs: removed unused error variable from xchk_refcountbt_rec

Removed unused error variable. Instead of using error variable,
returned the value directly as it wasn't updated.

Signed-off-by: Aliasgar Surti <aliasgar.surti500@gmail.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/scrub/refcount.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 93b3793bc5b3..0cab11a5d390 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -341,7 +341,6 @@ xchk_refcountbt_rec(
 	xfs_extlen_t		len;
 	xfs_nlink_t		refcount;
 	bool			has_cowflag;
-	int			error = 0;
 
 	bno = be32_to_cpu(rec->refc.rc_startblock);
 	len = be32_to_cpu(rec->refc.rc_blockcount);
@@ -366,7 +365,7 @@ xchk_refcountbt_rec(
 
 	xchk_refcountbt_xref(bs->sc, bno, len, refcount);
 
-	return error;
+	return 0;
 }
 
 /* Make sure we have as many refc blocks as the rmap says. */
-- 
cgit v1.2.3


From 3219e8cf0dade9884d3c6cb432d433b4ca56875d Mon Sep 17 00:00:00 2001
From: Bill O'Donnell <billodo@redhat.com>
Date: Fri, 4 Oct 2019 16:38:44 -0700
Subject: xfs: assure zeroed memory buffers for certain kmem allocations

Guarantee zeroed memory buffers for cases where potential memory
leak to disk can occur. In these cases, kmem_alloc is used and
doesn't zero the buffer, opening the possibility of information
leakage to disk.

Use existing infrastucture (xfs_buf_allocate_memory) to obtain
the already zeroed buffer from kernel memory.

This solution avoids the performance issue that would occur if a
wholesale change to replace kmem_alloc with kmem_zalloc was done.

Signed-off-by: Bill O'Donnell <billodo@redhat.com>
[darrick: fix bitwise complaint about kmflag_mask]
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_buf.c         | 12 +++++++++++-
 fs/xfs/xfs_log.c         |  2 +-
 fs/xfs/xfs_log_recover.c |  2 +-
 3 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 21c243622a79..0abba171aa89 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -345,6 +345,15 @@ xfs_buf_allocate_memory(
 	unsigned short		page_count, i;
 	xfs_off_t		start, end;
 	int			error;
+	xfs_km_flags_t		kmflag_mask = 0;
+
+	/*
+	 * assure zeroed buffer for non-read cases.
+	 */
+	if (!(flags & XBF_READ)) {
+		kmflag_mask |= KM_ZERO;
+		gfp_mask |= __GFP_ZERO;
+	}
 
 	/*
 	 * for buffers that are contained within a single page, just allocate
@@ -354,7 +363,8 @@ xfs_buf_allocate_memory(
 	size = BBTOB(bp->b_length);
 	if (size < PAGE_SIZE) {
 		int align_mask = xfs_buftarg_dma_alignment(bp->b_target);
-		bp->b_addr = kmem_alloc_io(size, align_mask, KM_NOFS);
+		bp->b_addr = kmem_alloc_io(size, align_mask,
+					   KM_NOFS | kmflag_mask);
 		if (!bp->b_addr) {
 			/* low memory - use alloc_page loop instead */
 			goto use_alloc_page;
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index a2beee9f74da..641d07f30a27 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1443,7 +1443,7 @@ xlog_alloc_log(
 		prev_iclog = iclog;
 
 		iclog->ic_data = kmem_alloc_io(log->l_iclog_size, align_mask,
-						KM_MAYFAIL);
+						KM_MAYFAIL | KM_ZERO);
 		if (!iclog->ic_data)
 			goto out_free_iclog;
 #ifdef DEBUG
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 508319039dce..c1a514ffff55 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -127,7 +127,7 @@ xlog_alloc_buffer(
 	if (nbblks > 1 && log->l_sectBBsize > 1)
 		nbblks += log->l_sectBBsize;
 	nbblks = round_up(nbblks, log->l_sectBBsize);
-	return kmem_alloc_io(BBTOB(nbblks), align_mask, KM_MAYFAIL);
+	return kmem_alloc_io(BBTOB(nbblks), align_mask, KM_MAYFAIL | KM_ZERO);
 }
 
 /*
-- 
cgit v1.2.3


From c90012ac85c24547e5c3468ef00aabf44aa7332d Mon Sep 17 00:00:00 2001
From: Aleksa Sarai <cyphar@cyphar.com>
Date: Sun, 6 Oct 2019 10:30:28 +1100
Subject: lib: test_user_copy: style cleanup

While writing the tests for copy_struct_from_user(), I used a construct
that Linus doesn't appear to be too fond of:

On 2019-10-04, Linus Torvalds <torvalds@linux-foundation.org> wrote:
> Hmm. That code is ugly, both before and after the fix.
>
> This just doesn't make sense for so many reasons:
>
>         if ((ret |= test(umem_src == NULL, "kmalloc failed")))
>
> where the insanity comes from
>
>  - why "|=" when you know that "ret" was zero before (and it had to
>    be, for the test to make sense)
>
>  - why do this as a single line anyway?
>
>  - don't do the stupid "double parenthesis" to hide a warning. Make it
>    use an actual comparison if you add a layer of parentheses.

So instead, use a bog-standard check that isn't nearly as ugly.

Fixes: 341115822f88 ("usercopy: Add parentheses around assignment in test_copy_struct_from_user")
Fixes: f5a1a536fa14 ("lib: introduce copy_struct_from_user() helper")
Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20191005233028.18566-1-cyphar@cyphar.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 lib/test_user_copy.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c
index e365ace06538..ad2372727b1b 100644
--- a/lib/test_user_copy.c
+++ b/lib/test_user_copy.c
@@ -52,13 +52,14 @@ static int test_check_nonzero_user(char *kmem, char __user *umem, size_t size)
 	size_t zero_end = size - zero_start;
 
 	/*
-	 * We conduct a series of check_nonzero_user() tests on a block of memory
-	 * with the following byte-pattern (trying every possible [start,end]
-	 * pair):
+	 * We conduct a series of check_nonzero_user() tests on a block of
+	 * memory with the following byte-pattern (trying every possible
+	 * [start,end] pair):
 	 *
 	 *   [ 00 ff 00 ff ... 00 00 00 00 ... ff 00 ff 00 ]
 	 *
-	 * And we verify that check_nonzero_user() acts identically to memchr_inv().
+	 * And we verify that check_nonzero_user() acts identically to
+	 * memchr_inv().
 	 */
 
 	memset(kmem, 0x0, size);
@@ -93,11 +94,13 @@ static int test_copy_struct_from_user(char *kmem, char __user *umem,
 	size_t ksize, usize;
 
 	umem_src = kmalloc(size, GFP_KERNEL);
-	if ((ret |= test(umem_src == NULL, "kmalloc failed")))
+	ret = test(umem_src == NULL, "kmalloc failed");
+	if (ret)
 		goto out_free;
 
 	expected = kmalloc(size, GFP_KERNEL);
-	if ((ret |= test(expected == NULL, "kmalloc failed")))
+	ret = test(expected == NULL, "kmalloc failed");
+	if (ret)
 		goto out_free;
 
 	/* Fill umem with a fixed byte pattern. */
-- 
cgit v1.2.3


From 1099f48457d06b816359fb43ac32a4a07e33219b Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Thu, 3 Oct 2019 12:39:19 +0800
Subject: ALSA: hda/realtek: Reduce the Headphone static noise on XPS 9350/9360

Headphone on XPS 9350/9360 produces a background white noise. The The
noise level somehow correlates with "Headphone Mic Boost", when it sets
to 1 the noise disappears. However, doing this has a side effect, which
also decreases the overall headphone volume so I didn't send the patch
upstream.

The noise was bearable back then, but after commit 717f43d81afc ("ALSA:
hda/realtek - Update headset mode for ALC256") the noise exacerbates to
a point it starts hurting ears.

So let's use the workaround to set "Headphone Mic Boost" to 1 and lock
it so it's not touchable by userspace.

Fixes: 717f43d81afc ("ALSA: hda/realtek - Update headset mode for ALC256")
BugLink: https://bugs.launchpad.net/bugs/1654448
BugLink: https://bugs.launchpad.net/bugs/1845810
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Link: https://lore.kernel.org/r/20191003043919.10960-1-kai.heng.feng@canonical.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index b000b36ac3c6..b5c225a56b98 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5358,6 +5358,17 @@ static void alc271_hp_gate_mic_jack(struct hda_codec *codec,
 	}
 }
 
+static void alc256_fixup_dell_xps_13_headphone_noise2(struct hda_codec *codec,
+						      const struct hda_fixup *fix,
+						      int action)
+{
+	if (action != HDA_FIXUP_ACT_PRE_PROBE)
+		return;
+
+	snd_hda_codec_amp_stereo(codec, 0x1a, HDA_INPUT, 0, HDA_AMP_VOLMASK, 1);
+	snd_hda_override_wcaps(codec, 0x1a, get_wcaps(codec, 0x1a) & ~AC_WCAP_IN_AMP);
+}
+
 static void alc269_fixup_limit_int_mic_boost(struct hda_codec *codec,
 					     const struct hda_fixup *fix,
 					     int action)
@@ -5822,6 +5833,7 @@ enum {
 	ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE,
 	ALC275_FIXUP_DELL_XPS,
 	ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE,
+	ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE2,
 	ALC293_FIXUP_LENOVO_SPK_NOISE,
 	ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY,
 	ALC255_FIXUP_DELL_SPK_NOISE,
@@ -6558,6 +6570,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
 	},
+	[ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE2] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc256_fixup_dell_xps_13_headphone_noise2,
+		.chained = true,
+		.chain_id = ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE
+	},
 	[ALC293_FIXUP_LENOVO_SPK_NOISE] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_disable_aamix,
@@ -7001,17 +7019,17 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x06de, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
 	SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
 	SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
-	SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13 9350", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+	SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13 9350", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE2),
 	SND_PCI_QUIRK(0x1028, 0x0706, "Dell Inspiron 7559", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
 	SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x0738, "Dell Precision 5820", ALC269_FIXUP_NO_SHUTUP),
-	SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+	SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE2),
 	SND_PCI_QUIRK(0x1028, 0x075c, "Dell XPS 27 7760", ALC298_FIXUP_SPK_VOLUME),
 	SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME),
 	SND_PCI_QUIRK(0x1028, 0x07b0, "Dell Precision 7520", ALC295_FIXUP_DISABLE_DAC3),
 	SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
 	SND_PCI_QUIRK(0x1028, 0x080c, "Dell WYSE", ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+	SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE2),
 	SND_PCI_QUIRK(0x1028, 0x084b, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB),
 	SND_PCI_QUIRK(0x1028, 0x084e, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB),
 	SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC),
-- 
cgit v1.2.3


From 130bce3afbbbbe585cba8604f2124c28e8d86fb0 Mon Sep 17 00:00:00 2001
From: Rander Wang <rander.wang@linux.intel.com>
Date: Mon, 30 Sep 2019 09:29:45 -0500
Subject: ALSA: hdac: clear link output stream mapping

Fix potential DMA hang upon starting playback on devices in HDA mode
on Intel platforms (Gemini Lake/Whiskey Lake/Comet Lake/Ice Lake). It
doesn't affect platforms before Gemini Lake or any Intel device in
non-HDA mode.

The reset value for the LOSDIV register is all output streams valid.
Clear this register to invalidate non-existent streams when the bus
is powered up.

Signed-off-by: Rander Wang <rander.wang@linux.intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Link: https://lore.kernel.org/r/20190930142945.7805-1-pierre-louis.bossart@linux.intel.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hda_register.h        | 3 +++
 sound/hda/ext/hdac_ext_controller.c | 5 +++++
 2 files changed, 8 insertions(+)

diff --git a/include/sound/hda_register.h b/include/sound/hda_register.h
index 0fd39295b426..057d2a2d0bd0 100644
--- a/include/sound/hda_register.h
+++ b/include/sound/hda_register.h
@@ -264,6 +264,9 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 };
 #define AZX_REG_ML_LOUTPAY		0x20
 #define AZX_REG_ML_LINPAY		0x30
 
+/* bit0 is reserved, with BIT(1) mapping to stream1 */
+#define ML_LOSIDV_STREAM_MASK		0xFFFE
+
 #define ML_LCTL_SCF_MASK			0xF
 #define AZX_MLCTL_SPA				(0x1 << 16)
 #define AZX_MLCTL_CPA				(0x1 << 23)
diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c
index 211ca85acd8c..cfab60d88c92 100644
--- a/sound/hda/ext/hdac_ext_controller.c
+++ b/sound/hda/ext/hdac_ext_controller.c
@@ -270,6 +270,11 @@ int snd_hdac_ext_bus_link_get(struct hdac_bus *bus,
 
 		ret = snd_hdac_ext_bus_link_power_up(link);
 
+		/*
+		 * clear the register to invalidate all the output streams
+		 */
+		snd_hdac_updatew(link->ml_addr, AZX_REG_ML_LOSIDV,
+				 ML_LOSIDV_STREAM_MASK, 0);
 		/*
 		 *  wait for 521usec for codec to report status
 		 *  HDA spec section 4.3 - Codec Discovery
-- 
cgit v1.2.3


From 52870d5048919004b6629d1a2f2b0a99c23b9960 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Tue, 1 Oct 2019 21:25:46 -0500
Subject: smb3: cleanup some recent endian errors spotted by updated sparse

Now that sparse has been fixed, it spotted a couple recent minor
endian errors (and removed one additional sparse warning).

Thanks to Luc Van Oostenryck for his help fixing sparse.

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
---
 fs/cifs/connect.c   | 2 +-
 fs/cifs/smb2pdu.c   | 3 ++-
 fs/cifs/smb2proto.h | 4 ++++
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 2850c3ce4391..b724227b853c 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -4264,7 +4264,7 @@ static int mount_get_conns(struct smb_vol *vol, struct cifs_sb_info *cifs_sb,
 		server->ops->qfs_tcon(*xid, tcon);
 		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE) {
 			if (tcon->fsDevInfo.DeviceCharacteristics &
-			    FILE_READ_ONLY_DEVICE)
+			    cpu_to_le32(FILE_READ_ONLY_DEVICE))
 				cifs_dbg(VFS, "mounted to read only share\n");
 			else if ((cifs_sb->mnt_cifs_flags &
 				  CIFS_MOUNT_RW_CACHE) == 0)
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 85f9d614d968..fd5f2b4b7582 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -3217,7 +3217,8 @@ SMB2_notify_init(const unsigned int xid, struct smb_rqst *rqst,
 
 	req->PersistentFileId = persistent_fid;
 	req->VolatileFileId = volatile_fid;
-	req->OutputBufferLength = SMB2_MAX_BUFFER_SIZE - MAX_SMB2_HDR_SIZE;
+	req->OutputBufferLength =
+		cpu_to_le32(SMB2_MAX_BUFFER_SIZE - MAX_SMB2_HDR_SIZE);
 	req->CompletionFilter = cpu_to_le32(completion_filter);
 	if (watch_tree)
 		req->Flags = cpu_to_le16(SMB2_WATCH_TREE);
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index da3a6d580808..71b2930b8e0b 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -150,6 +150,10 @@ extern int SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
 			   bool is_fsctl, char *in_data, u32 indatalen,
 			   __u32 max_response_size);
 extern void SMB2_ioctl_free(struct smb_rqst *rqst);
+extern int SMB2_change_notify(const unsigned int xid, struct cifs_tcon *tcon,
+			u64 persistent_fid, u64 volatile_fid, bool watch_tree,
+			u32 completion_filter);
+
 extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 		      u64 persistent_file_id, u64 volatile_file_id);
 extern int SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
-- 
cgit v1.2.3


From dd19c106a36690b47bb1acc68372f2b472b495b8 Mon Sep 17 00:00:00 2001
From: Austin Kim <austindh.kim@gmail.com>
Date: Tue, 1 Oct 2019 16:34:13 +0900
Subject: fs: cifs: mute -Wunused-const-variable message

After 'Initial git repository build' commit,
'mapping_table_ERRHRD' variable has not been used.

So 'mapping_table_ERRHRD' const variable could be removed
to mute below warning message:

   fs/cifs/netmisc.c:120:40: warning: unused variable 'mapping_table_ERRHRD' [-Wunused-const-variable]
   static const struct smb_to_posix_error mapping_table_ERRHRD[] = {
                                           ^
Signed-off-by: Austin Kim <austindh.kim@gmail.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/netmisc.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index 49c17ee18254..9b41436fb8db 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -117,10 +117,6 @@ static const struct smb_to_posix_error mapping_table_ERRSRV[] = {
 	{0, 0}
 };
 
-static const struct smb_to_posix_error mapping_table_ERRHRD[] = {
-	{0, 0}
-};
-
 /*
  * Convert a string containing text IPv4 or IPv6 address to binary form.
  *
-- 
cgit v1.2.3


From cb248819d209d113e45fed459773991518e8e80b Mon Sep 17 00:00:00 2001
From: Dave Wysochanski <dwysocha@redhat.com>
Date: Thu, 3 Oct 2019 15:16:27 +1000
Subject: cifs: use cifsInodeInfo->open_file_lock while iterating to avoid a
 panic

Commit 487317c99477 ("cifs: add spinlock for the openFileList to
cifsInodeInfo") added cifsInodeInfo->open_file_lock spin_lock to protect
the openFileList, but missed a few places where cifs_inode->openFileList
was enumerated.  Change these remaining tcon->open_file_lock to
cifsInodeInfo->open_file_lock to avoid panic in is_size_safe_to_change.

[17313.245641] RIP: 0010:is_size_safe_to_change+0x57/0xb0 [cifs]
[17313.245645] Code: 68 40 48 89 ef e8 19 67 b7 f1 48 8b 43 40 48 8d 4b 40 48 8d 50 f0 48 39 c1 75 0f eb 47 48 8b 42 10 48 8d 50 f0 48 39 c1 74 3a <8b> 80 88 00 00 00 83 c0 01 a8 02 74 e6 48 89 ef c6 07 00 0f 1f 40
[17313.245649] RSP: 0018:ffff94ae1baefa30 EFLAGS: 00010202
[17313.245654] RAX: dead000000000100 RBX: ffff88dc72243300 RCX: ffff88dc72243340
[17313.245657] RDX: dead0000000000f0 RSI: 00000000098f7940 RDI: ffff88dd3102f040
[17313.245659] RBP: ffff88dd3102f040 R08: 0000000000000000 R09: ffff94ae1baefc40
[17313.245661] R10: ffffcdc8bb1c4e80 R11: ffffcdc8b50adb08 R12: 00000000098f7940
[17313.245663] R13: ffff88dc72243300 R14: ffff88dbc8f19600 R15: ffff88dc72243428
[17313.245667] FS:  00007fb145485700(0000) GS:ffff88dd3e000000(0000) knlGS:0000000000000000
[17313.245670] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[17313.245672] CR2: 0000026bb46c6000 CR3: 0000004edb110003 CR4: 00000000007606e0
[17313.245753] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[17313.245756] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[17313.245759] PKRU: 55555554
[17313.245761] Call Trace:
[17313.245803]  cifs_fattr_to_inode+0x16b/0x580 [cifs]
[17313.245838]  cifs_get_inode_info+0x35c/0xa60 [cifs]
[17313.245852]  ? kmem_cache_alloc_trace+0x151/0x1d0
[17313.245885]  cifs_open+0x38f/0x990 [cifs]
[17313.245921]  ? cifs_revalidate_dentry_attr+0x3e/0x350 [cifs]
[17313.245953]  ? cifsFileInfo_get+0x30/0x30 [cifs]
[17313.245960]  ? do_dentry_open+0x132/0x330
[17313.245963]  do_dentry_open+0x132/0x330
[17313.245969]  path_openat+0x573/0x14d0
[17313.245974]  do_filp_open+0x93/0x100
[17313.245979]  ? __check_object_size+0xa3/0x181
[17313.245986]  ? audit_alloc_name+0x7e/0xd0
[17313.245992]  do_sys_open+0x184/0x220
[17313.245999]  do_syscall_64+0x5b/0x1b0

Fixes: 487317c99477 ("cifs: add spinlock for the openFileList to cifsInodeInfo")

CC: Stable <stable@vger.kernel.org>
Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/file.c | 27 +++++++++++----------------
 1 file changed, 11 insertions(+), 16 deletions(-)

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 4b95700c507c..3758237bf951 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1840,13 +1840,12 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 {
 	struct cifsFileInfo *open_file = NULL;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb);
-	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 
 	/* only filter by fsuid on multiuser mounts */
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
 		fsuid_only = false;
 
-	spin_lock(&tcon->open_file_lock);
+	spin_lock(&cifs_inode->open_file_lock);
 	/* we could simply get the first_list_entry since write-only entries
 	   are always at the end of the list but since the first entry might
 	   have a close pending, we go through the whole list */
@@ -1858,7 +1857,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 				/* found a good file */
 				/* lock it so it will not be closed on us */
 				cifsFileInfo_get(open_file);
-				spin_unlock(&tcon->open_file_lock);
+				spin_unlock(&cifs_inode->open_file_lock);
 				return open_file;
 			} /* else might as well continue, and look for
 			     another, or simply have the caller reopen it
@@ -1866,7 +1865,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
 		} else /* write only file */
 			break; /* write only files are last so must be done */
 	}
-	spin_unlock(&tcon->open_file_lock);
+	spin_unlock(&cifs_inode->open_file_lock);
 	return NULL;
 }
 
@@ -1877,7 +1876,6 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only,
 {
 	struct cifsFileInfo *open_file, *inv_file = NULL;
 	struct cifs_sb_info *cifs_sb;
-	struct cifs_tcon *tcon;
 	bool any_available = false;
 	int rc = -EBADF;
 	unsigned int refind = 0;
@@ -1897,16 +1895,15 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only,
 	}
 
 	cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb);
-	tcon = cifs_sb_master_tcon(cifs_sb);
 
 	/* only filter by fsuid on multiuser mounts */
 	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
 		fsuid_only = false;
 
-	spin_lock(&tcon->open_file_lock);
+	spin_lock(&cifs_inode->open_file_lock);
 refind_writable:
 	if (refind > MAX_REOPEN_ATT) {
-		spin_unlock(&tcon->open_file_lock);
+		spin_unlock(&cifs_inode->open_file_lock);
 		return rc;
 	}
 	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
@@ -1918,7 +1915,7 @@ refind_writable:
 			if (!open_file->invalidHandle) {
 				/* found a good writable file */
 				cifsFileInfo_get(open_file);
-				spin_unlock(&tcon->open_file_lock);
+				spin_unlock(&cifs_inode->open_file_lock);
 				*ret_file = open_file;
 				return 0;
 			} else {
@@ -1938,7 +1935,7 @@ refind_writable:
 		cifsFileInfo_get(inv_file);
 	}
 
-	spin_unlock(&tcon->open_file_lock);
+	spin_unlock(&cifs_inode->open_file_lock);
 
 	if (inv_file) {
 		rc = cifs_reopen_file(inv_file, false);
@@ -1953,7 +1950,7 @@ refind_writable:
 		cifsFileInfo_put(inv_file);
 		++refind;
 		inv_file = NULL;
-		spin_lock(&tcon->open_file_lock);
+		spin_lock(&cifs_inode->open_file_lock);
 		goto refind_writable;
 	}
 
@@ -4461,17 +4458,15 @@ static int cifs_readpage(struct file *file, struct page *page)
 static int is_inode_writable(struct cifsInodeInfo *cifs_inode)
 {
 	struct cifsFileInfo *open_file;
-	struct cifs_tcon *tcon =
-		cifs_sb_master_tcon(CIFS_SB(cifs_inode->vfs_inode.i_sb));
 
-	spin_lock(&tcon->open_file_lock);
+	spin_lock(&cifs_inode->open_file_lock);
 	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
 		if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
-			spin_unlock(&tcon->open_file_lock);
+			spin_unlock(&cifs_inode->open_file_lock);
 			return 1;
 		}
 	}
-	spin_unlock(&tcon->open_file_lock);
+	spin_unlock(&cifs_inode->open_file_lock);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 30573a82fb179420b8aac30a3a3595aa96a93156 Mon Sep 17 00:00:00 2001
From: Pavel Shilovsky <piastryyy@gmail.com>
Date: Mon, 30 Sep 2019 10:06:18 -0700
Subject: CIFS: Gracefully handle QueryInfo errors during open

Currently if the client identifies problems when processing
metadata returned in CREATE response, the open handle is being
leaked. This causes multiple problems like a file missing a lease
break by that client which causes high latencies to other clients
accessing the file. Another side-effect of this is that the file
can't be deleted.

Fix this by closing the file after the client hits an error after
the file was opened and the open descriptor wasn't returned to
the user space. Also convert -ESTALE to -EOPENSTALE to allow
the VFS to revalidate a dentry and retry the open.

Cc: <stable@vger.kernel.org>
Signed-off-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/file.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 3758237bf951..5ad15de2bb4f 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -253,6 +253,12 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb,
 		rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb,
 					 xid, fid);
 
+	if (rc) {
+		server->ops->close(xid, tcon, fid);
+		if (rc == -ESTALE)
+			rc = -EOPENSTALE;
+	}
+
 out:
 	kfree(buf);
 	return rc;
-- 
cgit v1.2.3


From f92013259d32c903d360039ff26a659f8f1552f5 Mon Sep 17 00:00:00 2001
From: Jitao Shi <jitao.shi@mediatek.com>
Date: Wed, 7 Aug 2019 16:46:43 +0800
Subject: dt-bindings: display: mediatek: update dsi supported chips

Update device tree binding documentation for the dsi for
Mediatek MT8183 SoCs.

Signed-off-by: Jitao Shi <jitao.shi@mediatek.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.txt
index fadf327c7cdf..a19a6cc375ed 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.txt
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.txt
@@ -7,7 +7,7 @@ channel output.
 
 Required properties:
 - compatible: "mediatek,<chip>-dsi"
-  the supported chips are mt2701 and mt8173.
+  the supported chips are mt2701, mt8173 and mt8183.
 - reg: Physical base address and length of the controller's registers
 - interrupts: The interrupt signal from the function block.
 - clocks: device clocks
@@ -26,7 +26,7 @@ The MIPI TX configuration module controls the MIPI D-PHY.
 
 Required properties:
 - compatible: "mediatek,<chip>-mipi-tx"
-  the supported chips are mt2701 and mt8173.
+  the supported chips are mt2701, mt8173 and mt8183.
 - reg: Physical base address and length of the controller's registers
 - clocks: PLL reference clock
 - clock-output-names: name of the output clock line to the DSI encoder
-- 
cgit v1.2.3


From 78e01a8d0f4662a9de4ef21bff254bf4f833d05a Mon Sep 17 00:00:00 2001
From: Jitao Shi <jitao.shi@mediatek.com>
Date: Wed, 7 Aug 2019 16:46:44 +0800
Subject: drm/mediatek: separate mipi_tx to different file

Different IC has different mipi_tx setting of dsi.
This patch separates the mipi_tx hardware relate part for mt8173.

Signed-off-by: Jitao Shi <jitao.shi@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/Makefile             |   1 +
 drivers/gpu/drm/mediatek/mtk_mipi_tx.c        | 336 ++------------------------
 drivers/gpu/drm/mediatek/mtk_mipi_tx.h        |  48 ++++
 drivers/gpu/drm/mediatek/mtk_mt8173_mipi_tx.c | 288 ++++++++++++++++++++++
 4 files changed, 358 insertions(+), 315 deletions(-)
 create mode 100644 drivers/gpu/drm/mediatek/mtk_mipi_tx.h
 create mode 100644 drivers/gpu/drm/mediatek/mtk_mt8173_mipi_tx.c

diff --git a/drivers/gpu/drm/mediatek/Makefile b/drivers/gpu/drm/mediatek/Makefile
index 82ae49c64221..2c8de1f5a5ee 100644
--- a/drivers/gpu/drm/mediatek/Makefile
+++ b/drivers/gpu/drm/mediatek/Makefile
@@ -12,6 +12,7 @@ mediatek-drm-y := mtk_disp_color.o \
 		  mtk_drm_plane.o \
 		  mtk_dsi.o \
 		  mtk_mipi_tx.o \
+		  mtk_mt8173_mipi_tx.o \
 		  mtk_dpi.o
 
 obj-$(CONFIG_DRM_MEDIATEK) += mediatek-drm.o
diff --git a/drivers/gpu/drm/mediatek/mtk_mipi_tx.c b/drivers/gpu/drm/mediatek/mtk_mipi_tx.c
index 1842dc2caae9..77b9a185e970 100644
--- a/drivers/gpu/drm/mediatek/mtk_mipi_tx.c
+++ b/drivers/gpu/drm/mediatek/mtk_mipi_tx.c
@@ -3,292 +3,39 @@
  * Copyright (c) 2015 MediaTek Inc.
  */
 
-#include <linux/clk.h>
-#include <linux/clk-provider.h>
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/module.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
-#include <linux/phy/phy.h>
-
-#define MIPITX_DSI_CON		0x00
-#define RG_DSI_LDOCORE_EN		BIT(0)
-#define RG_DSI_CKG_LDOOUT_EN		BIT(1)
-#define RG_DSI_BCLK_SEL			(3 << 2)
-#define RG_DSI_LD_IDX_SEL		(7 << 4)
-#define RG_DSI_PHYCLK_SEL		(2 << 8)
-#define RG_DSI_DSICLK_FREQ_SEL		BIT(10)
-#define RG_DSI_LPTX_CLMP_EN		BIT(11)
-
-#define MIPITX_DSI_CLOCK_LANE	0x04
-#define MIPITX_DSI_DATA_LANE0	0x08
-#define MIPITX_DSI_DATA_LANE1	0x0c
-#define MIPITX_DSI_DATA_LANE2	0x10
-#define MIPITX_DSI_DATA_LANE3	0x14
-#define RG_DSI_LNTx_LDOOUT_EN		BIT(0)
-#define RG_DSI_LNTx_CKLANE_EN		BIT(1)
-#define RG_DSI_LNTx_LPTX_IPLUS1		BIT(2)
-#define RG_DSI_LNTx_LPTX_IPLUS2		BIT(3)
-#define RG_DSI_LNTx_LPTX_IMINUS		BIT(4)
-#define RG_DSI_LNTx_LPCD_IPLUS		BIT(5)
-#define RG_DSI_LNTx_LPCD_IMINUS		BIT(6)
-#define RG_DSI_LNTx_RT_CODE		(0xf << 8)
-
-#define MIPITX_DSI_TOP_CON	0x40
-#define RG_DSI_LNT_INTR_EN		BIT(0)
-#define RG_DSI_LNT_HS_BIAS_EN		BIT(1)
-#define RG_DSI_LNT_IMP_CAL_EN		BIT(2)
-#define RG_DSI_LNT_TESTMODE_EN		BIT(3)
-#define RG_DSI_LNT_IMP_CAL_CODE		(0xf << 4)
-#define RG_DSI_LNT_AIO_SEL		(7 << 8)
-#define RG_DSI_PAD_TIE_LOW_EN		BIT(11)
-#define RG_DSI_DEBUG_INPUT_EN		BIT(12)
-#define RG_DSI_PRESERVE			(7 << 13)
-
-#define MIPITX_DSI_BG_CON	0x44
-#define RG_DSI_BG_CORE_EN		BIT(0)
-#define RG_DSI_BG_CKEN			BIT(1)
-#define RG_DSI_BG_DIV			(0x3 << 2)
-#define RG_DSI_BG_FAST_CHARGE		BIT(4)
-#define RG_DSI_VOUT_MSK			(0x3ffff << 5)
-#define RG_DSI_V12_SEL			(7 << 5)
-#define RG_DSI_V10_SEL			(7 << 8)
-#define RG_DSI_V072_SEL			(7 << 11)
-#define RG_DSI_V04_SEL			(7 << 14)
-#define RG_DSI_V032_SEL			(7 << 17)
-#define RG_DSI_V02_SEL			(7 << 20)
-#define RG_DSI_BG_R1_TRIM		(0xf << 24)
-#define RG_DSI_BG_R2_TRIM		(0xf << 28)
-
-#define MIPITX_DSI_PLL_CON0	0x50
-#define RG_DSI_MPPLL_PLL_EN		BIT(0)
-#define RG_DSI_MPPLL_DIV_MSK		(0x1ff << 1)
-#define RG_DSI_MPPLL_PREDIV		(3 << 1)
-#define RG_DSI_MPPLL_TXDIV0		(3 << 3)
-#define RG_DSI_MPPLL_TXDIV1		(3 << 5)
-#define RG_DSI_MPPLL_POSDIV		(7 << 7)
-#define RG_DSI_MPPLL_MONVC_EN		BIT(10)
-#define RG_DSI_MPPLL_MONREF_EN		BIT(11)
-#define RG_DSI_MPPLL_VOD_EN		BIT(12)
-
-#define MIPITX_DSI_PLL_CON1	0x54
-#define RG_DSI_MPPLL_SDM_FRA_EN		BIT(0)
-#define RG_DSI_MPPLL_SDM_SSC_PH_INIT	BIT(1)
-#define RG_DSI_MPPLL_SDM_SSC_EN		BIT(2)
-#define RG_DSI_MPPLL_SDM_SSC_PRD	(0xffff << 16)
-
-#define MIPITX_DSI_PLL_CON2	0x58
-
-#define MIPITX_DSI_PLL_TOP	0x64
-#define RG_DSI_MPPLL_PRESERVE		(0xff << 8)
-
-#define MIPITX_DSI_PLL_PWR	0x68
-#define RG_DSI_MPPLL_SDM_PWR_ON		BIT(0)
-#define RG_DSI_MPPLL_SDM_ISO_EN		BIT(1)
-#define RG_DSI_MPPLL_SDM_PWR_ACK	BIT(8)
-
-#define MIPITX_DSI_SW_CTRL	0x80
-#define SW_CTRL_EN			BIT(0)
-
-#define MIPITX_DSI_SW_CTRL_CON0	0x84
-#define SW_LNTC_LPTX_PRE_OE		BIT(0)
-#define SW_LNTC_LPTX_OE			BIT(1)
-#define SW_LNTC_LPTX_P			BIT(2)
-#define SW_LNTC_LPTX_N			BIT(3)
-#define SW_LNTC_HSTX_PRE_OE		BIT(4)
-#define SW_LNTC_HSTX_OE			BIT(5)
-#define SW_LNTC_HSTX_ZEROCLK		BIT(6)
-#define SW_LNT0_LPTX_PRE_OE		BIT(7)
-#define SW_LNT0_LPTX_OE			BIT(8)
-#define SW_LNT0_LPTX_P			BIT(9)
-#define SW_LNT0_LPTX_N			BIT(10)
-#define SW_LNT0_HSTX_PRE_OE		BIT(11)
-#define SW_LNT0_HSTX_OE			BIT(12)
-#define SW_LNT0_LPRX_EN			BIT(13)
-#define SW_LNT1_LPTX_PRE_OE		BIT(14)
-#define SW_LNT1_LPTX_OE			BIT(15)
-#define SW_LNT1_LPTX_P			BIT(16)
-#define SW_LNT1_LPTX_N			BIT(17)
-#define SW_LNT1_HSTX_PRE_OE		BIT(18)
-#define SW_LNT1_HSTX_OE			BIT(19)
-#define SW_LNT2_LPTX_PRE_OE		BIT(20)
-#define SW_LNT2_LPTX_OE			BIT(21)
-#define SW_LNT2_LPTX_P			BIT(22)
-#define SW_LNT2_LPTX_N			BIT(23)
-#define SW_LNT2_HSTX_PRE_OE		BIT(24)
-#define SW_LNT2_HSTX_OE			BIT(25)
-
-struct mtk_mipitx_data {
-	const u32 mppll_preserve;
-};
-
-struct mtk_mipi_tx {
-	struct device *dev;
-	void __iomem *regs;
-	u32 data_rate;
-	const struct mtk_mipitx_data *driver_data;
-	struct clk_hw pll_hw;
-	struct clk *pll;
-};
+#include "mtk_mipi_tx.h"
 
-static inline struct mtk_mipi_tx *mtk_mipi_tx_from_clk_hw(struct clk_hw *hw)
+inline struct mtk_mipi_tx *mtk_mipi_tx_from_clk_hw(struct clk_hw *hw)
 {
 	return container_of(hw, struct mtk_mipi_tx, pll_hw);
 }
 
-static void mtk_mipi_tx_clear_bits(struct mtk_mipi_tx *mipi_tx, u32 offset,
-				   u32 bits)
+void mtk_mipi_tx_clear_bits(struct mtk_mipi_tx *mipi_tx, u32 offset,
+			    u32 bits)
 {
 	u32 temp = readl(mipi_tx->regs + offset);
 
 	writel(temp & ~bits, mipi_tx->regs + offset);
 }
 
-static void mtk_mipi_tx_set_bits(struct mtk_mipi_tx *mipi_tx, u32 offset,
-				 u32 bits)
+void mtk_mipi_tx_set_bits(struct mtk_mipi_tx *mipi_tx, u32 offset,
+			  u32 bits)
 {
 	u32 temp = readl(mipi_tx->regs + offset);
 
 	writel(temp | bits, mipi_tx->regs + offset);
 }
 
-static void mtk_mipi_tx_update_bits(struct mtk_mipi_tx *mipi_tx, u32 offset,
-				    u32 mask, u32 data)
+void mtk_mipi_tx_update_bits(struct mtk_mipi_tx *mipi_tx, u32 offset,
+			     u32 mask, u32 data)
 {
 	u32 temp = readl(mipi_tx->regs + offset);
 
 	writel((temp & ~mask) | (data & mask), mipi_tx->regs + offset);
 }
 
-static int mtk_mipi_tx_pll_prepare(struct clk_hw *hw)
-{
-	struct mtk_mipi_tx *mipi_tx = mtk_mipi_tx_from_clk_hw(hw);
-	u8 txdiv, txdiv0, txdiv1;
-	u64 pcw;
-
-	dev_dbg(mipi_tx->dev, "prepare: %u Hz\n", mipi_tx->data_rate);
-
-	if (mipi_tx->data_rate >= 500000000) {
-		txdiv = 1;
-		txdiv0 = 0;
-		txdiv1 = 0;
-	} else if (mipi_tx->data_rate >= 250000000) {
-		txdiv = 2;
-		txdiv0 = 1;
-		txdiv1 = 0;
-	} else if (mipi_tx->data_rate >= 125000000) {
-		txdiv = 4;
-		txdiv0 = 2;
-		txdiv1 = 0;
-	} else if (mipi_tx->data_rate > 62000000) {
-		txdiv = 8;
-		txdiv0 = 2;
-		txdiv1 = 1;
-	} else if (mipi_tx->data_rate >= 50000000) {
-		txdiv = 16;
-		txdiv0 = 2;
-		txdiv1 = 2;
-	} else {
-		return -EINVAL;
-	}
-
-	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_BG_CON,
-				RG_DSI_VOUT_MSK |
-				RG_DSI_BG_CKEN | RG_DSI_BG_CORE_EN,
-				(4 << 20) | (4 << 17) | (4 << 14) |
-				(4 << 11) | (4 << 8) | (4 << 5) |
-				RG_DSI_BG_CKEN | RG_DSI_BG_CORE_EN);
-
-	usleep_range(30, 100);
-
-	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_TOP_CON,
-				RG_DSI_LNT_IMP_CAL_CODE | RG_DSI_LNT_HS_BIAS_EN,
-				(8 << 4) | RG_DSI_LNT_HS_BIAS_EN);
-
-	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_DSI_CON,
-			     RG_DSI_CKG_LDOOUT_EN | RG_DSI_LDOCORE_EN);
-
-	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_PLL_PWR,
-				RG_DSI_MPPLL_SDM_PWR_ON |
-				RG_DSI_MPPLL_SDM_ISO_EN,
-				RG_DSI_MPPLL_SDM_PWR_ON);
-
-	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_PLL_CON0,
-			       RG_DSI_MPPLL_PLL_EN);
-
-	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_PLL_CON0,
-				RG_DSI_MPPLL_TXDIV0 | RG_DSI_MPPLL_TXDIV1 |
-				RG_DSI_MPPLL_PREDIV,
-				(txdiv0 << 3) | (txdiv1 << 5));
-
-	/*
-	 * PLL PCW config
-	 * PCW bit 24~30 = integer part of pcw
-	 * PCW bit 0~23 = fractional part of pcw
-	 * pcw = data_Rate*4*txdiv/(Ref_clk*2);
-	 * Post DIV =4, so need data_Rate*4
-	 * Ref_clk is 26MHz
-	 */
-	pcw = div_u64(((u64)mipi_tx->data_rate * 2 * txdiv) << 24,
-		      26000000);
-	writel(pcw, mipi_tx->regs + MIPITX_DSI_PLL_CON2);
-
-	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_DSI_PLL_CON1,
-			     RG_DSI_MPPLL_SDM_FRA_EN);
-
-	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_DSI_PLL_CON0, RG_DSI_MPPLL_PLL_EN);
-
-	usleep_range(20, 100);
-
-	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_PLL_CON1,
-			       RG_DSI_MPPLL_SDM_SSC_EN);
-
-	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_PLL_TOP,
-				RG_DSI_MPPLL_PRESERVE,
-				mipi_tx->driver_data->mppll_preserve);
-
-	return 0;
-}
-
-static void mtk_mipi_tx_pll_unprepare(struct clk_hw *hw)
-{
-	struct mtk_mipi_tx *mipi_tx = mtk_mipi_tx_from_clk_hw(hw);
-
-	dev_dbg(mipi_tx->dev, "unprepare\n");
-
-	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_PLL_CON0,
-			       RG_DSI_MPPLL_PLL_EN);
-
-	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_PLL_TOP,
-				RG_DSI_MPPLL_PRESERVE, 0);
-
-	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_PLL_PWR,
-				RG_DSI_MPPLL_SDM_ISO_EN |
-				RG_DSI_MPPLL_SDM_PWR_ON,
-				RG_DSI_MPPLL_SDM_ISO_EN);
-
-	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_TOP_CON,
-			       RG_DSI_LNT_HS_BIAS_EN);
-
-	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_CON,
-			       RG_DSI_CKG_LDOOUT_EN | RG_DSI_LDOCORE_EN);
-
-	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_BG_CON,
-			       RG_DSI_BG_CKEN | RG_DSI_BG_CORE_EN);
-
-	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_PLL_CON0,
-			       RG_DSI_MPPLL_DIV_MSK);
-}
-
-static long mtk_mipi_tx_pll_round_rate(struct clk_hw *hw, unsigned long rate,
-				       unsigned long *prate)
-{
-	return clamp_val(rate, 50000000, 1250000000);
-}
-
-static int mtk_mipi_tx_pll_set_rate(struct clk_hw *hw, unsigned long rate,
-				    unsigned long parent_rate)
+int mtk_mipi_tx_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+			     unsigned long parent_rate)
 {
 	struct mtk_mipi_tx *mipi_tx = mtk_mipi_tx_from_clk_hw(hw);
 
@@ -299,37 +46,14 @@ static int mtk_mipi_tx_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
-static unsigned long mtk_mipi_tx_pll_recalc_rate(struct clk_hw *hw,
-						 unsigned long parent_rate)
+unsigned long mtk_mipi_tx_pll_recalc_rate(struct clk_hw *hw,
+					  unsigned long parent_rate)
 {
 	struct mtk_mipi_tx *mipi_tx = mtk_mipi_tx_from_clk_hw(hw);
 
 	return mipi_tx->data_rate;
 }
 
-static const struct clk_ops mtk_mipi_tx_pll_ops = {
-	.prepare = mtk_mipi_tx_pll_prepare,
-	.unprepare = mtk_mipi_tx_pll_unprepare,
-	.round_rate = mtk_mipi_tx_pll_round_rate,
-	.set_rate = mtk_mipi_tx_pll_set_rate,
-	.recalc_rate = mtk_mipi_tx_pll_recalc_rate,
-};
-
-static int mtk_mipi_tx_power_on_signal(struct phy *phy)
-{
-	struct mtk_mipi_tx *mipi_tx = phy_get_drvdata(phy);
-	u32 reg;
-
-	for (reg = MIPITX_DSI_CLOCK_LANE;
-	     reg <= MIPITX_DSI_DATA_LANE3; reg += 4)
-		mtk_mipi_tx_set_bits(mipi_tx, reg, RG_DSI_LNTx_LDOOUT_EN);
-
-	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_TOP_CON,
-			       RG_DSI_PAD_TIE_LOW_EN);
-
-	return 0;
-}
-
 static int mtk_mipi_tx_power_on(struct phy *phy)
 {
 	struct mtk_mipi_tx *mipi_tx = phy_get_drvdata(phy);
@@ -341,30 +65,16 @@ static int mtk_mipi_tx_power_on(struct phy *phy)
 		return ret;
 
 	/* Enable DSI Lane LDO outputs, disable pad tie low */
-	mtk_mipi_tx_power_on_signal(phy);
-
+	mipi_tx->driver_data->mipi_tx_enable_signal(phy);
 	return 0;
 }
 
-static void mtk_mipi_tx_power_off_signal(struct phy *phy)
-{
-	struct mtk_mipi_tx *mipi_tx = phy_get_drvdata(phy);
-	u32 reg;
-
-	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_DSI_TOP_CON,
-			     RG_DSI_PAD_TIE_LOW_EN);
-
-	for (reg = MIPITX_DSI_CLOCK_LANE;
-	     reg <= MIPITX_DSI_DATA_LANE3; reg += 4)
-		mtk_mipi_tx_clear_bits(mipi_tx, reg, RG_DSI_LNTx_LDOOUT_EN);
-}
-
 static int mtk_mipi_tx_power_off(struct phy *phy)
 {
 	struct mtk_mipi_tx *mipi_tx = phy_get_drvdata(phy);
 
 	/* Enable pad tie low, disable DSI Lane LDO outputs */
-	mtk_mipi_tx_power_off_signal(phy);
+	mipi_tx->driver_data->mipi_tx_disable_signal(phy);
 
 	/* Disable PLL and power down core */
 	clk_disable_unprepare(mipi_tx->pll);
@@ -383,10 +93,9 @@ static int mtk_mipi_tx_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct mtk_mipi_tx *mipi_tx;
 	struct resource *mem;
-	struct clk *ref_clk;
 	const char *ref_clk_name;
+	struct clk *ref_clk;
 	struct clk_init_data clk_init = {
-		.ops = &mtk_mipi_tx_pll_ops,
 		.num_parents = 1,
 		.parent_names = (const char * const *)&ref_clk_name,
 		.flags = CLK_SET_RATE_GATE,
@@ -400,6 +109,7 @@ static int mtk_mipi_tx_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	mipi_tx->driver_data = of_device_get_match_data(dev);
+
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	mipi_tx->regs = devm_ioremap_resource(dev, mem);
 	if (IS_ERR(mipi_tx->regs)) {
@@ -414,6 +124,7 @@ static int mtk_mipi_tx_probe(struct platform_device *pdev)
 		dev_err(dev, "Failed to get reference clock: %d\n", ret);
 		return ret;
 	}
+
 	ref_clk_name = __clk_get_name(ref_clk);
 
 	ret = of_property_read_string(dev->of_node, "clock-output-names",
@@ -423,6 +134,8 @@ static int mtk_mipi_tx_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	clk_init.ops = mipi_tx->driver_data->mipi_tx_clk_ops;
+
 	mipi_tx->pll_hw.init = &clk_init;
 	mipi_tx->pll = devm_clk_register(dev, &mipi_tx->pll_hw);
 	if (IS_ERR(mipi_tx->pll)) {
@@ -457,20 +170,12 @@ static int mtk_mipi_tx_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct mtk_mipitx_data mt2701_mipitx_data = {
-	.mppll_preserve = (3 << 8)
-};
-
-static const struct mtk_mipitx_data mt8173_mipitx_data = {
-	.mppll_preserve = (0 << 8)
-};
-
 static const struct of_device_id mtk_mipi_tx_match[] = {
 	{ .compatible = "mediatek,mt2701-mipi-tx",
 	  .data = &mt2701_mipitx_data },
 	{ .compatible = "mediatek,mt8173-mipi-tx",
 	  .data = &mt8173_mipitx_data },
-	{},
+	{ },
 };
 
 struct platform_driver mtk_mipi_tx_driver = {
@@ -481,3 +186,4 @@ struct platform_driver mtk_mipi_tx_driver = {
 		.of_match_table = mtk_mipi_tx_match,
 	},
 };
+
diff --git a/drivers/gpu/drm/mediatek/mtk_mipi_tx.h b/drivers/gpu/drm/mediatek/mtk_mipi_tx.h
new file mode 100644
index 000000000000..4f905313564f
--- /dev/null
+++ b/drivers/gpu/drm/mediatek/mtk_mipi_tx.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2019 MediaTek Inc.
+ * Author: Jitao Shi <jitao.shi@mediatek.com>
+ */
+
+#ifndef _MTK_MIPI_TX_H
+#define _MTK_MIPI_TX_H
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/phy/phy.h>
+
+struct mtk_mipitx_data {
+	const u32 mppll_preserve;
+	const struct clk_ops *mipi_tx_clk_ops;
+	void (*mipi_tx_enable_signal)(struct phy *phy);
+	void (*mipi_tx_disable_signal)(struct phy *phy);
+};
+
+struct mtk_mipi_tx {
+	struct device *dev;
+	void __iomem *regs;
+	u32 data_rate;
+	const struct mtk_mipitx_data *driver_data;
+	struct clk_hw pll_hw;
+	struct clk *pll;
+};
+
+struct mtk_mipi_tx *mtk_mipi_tx_from_clk_hw(struct clk_hw *hw);
+void mtk_mipi_tx_clear_bits(struct mtk_mipi_tx *mipi_tx, u32 offset, u32 bits);
+void mtk_mipi_tx_set_bits(struct mtk_mipi_tx *mipi_tx, u32 offset, u32 bits);
+void mtk_mipi_tx_update_bits(struct mtk_mipi_tx *mipi_tx, u32 offset, u32 mask,
+			     u32 data);
+int mtk_mipi_tx_pll_set_rate(struct clk_hw *hw, unsigned long rate,
+			     unsigned long parent_rate);
+unsigned long mtk_mipi_tx_pll_recalc_rate(struct clk_hw *hw,
+					  unsigned long parent_rate);
+
+extern const struct mtk_mipitx_data mt2701_mipitx_data;
+extern const struct mtk_mipitx_data mt8173_mipitx_data;
+
+#endif
diff --git a/drivers/gpu/drm/mediatek/mtk_mt8173_mipi_tx.c b/drivers/gpu/drm/mediatek/mtk_mt8173_mipi_tx.c
new file mode 100644
index 000000000000..f18db14d8b63
--- /dev/null
+++ b/drivers/gpu/drm/mediatek/mtk_mt8173_mipi_tx.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 MediaTek Inc.
+ * Author: jitao.shi <jitao.shi@mediatek.com>
+ */
+
+#include "mtk_mipi_tx.h"
+
+#define MIPITX_DSI_CON		0x00
+#define RG_DSI_LDOCORE_EN		BIT(0)
+#define RG_DSI_CKG_LDOOUT_EN		BIT(1)
+#define RG_DSI_BCLK_SEL			(3 << 2)
+#define RG_DSI_LD_IDX_SEL		(7 << 4)
+#define RG_DSI_PHYCLK_SEL		(2 << 8)
+#define RG_DSI_DSICLK_FREQ_SEL		BIT(10)
+#define RG_DSI_LPTX_CLMP_EN		BIT(11)
+
+#define MIPITX_DSI_CLOCK_LANE	0x04
+#define MIPITX_DSI_DATA_LANE0	0x08
+#define MIPITX_DSI_DATA_LANE1	0x0c
+#define MIPITX_DSI_DATA_LANE2	0x10
+#define MIPITX_DSI_DATA_LANE3	0x14
+#define RG_DSI_LNTx_LDOOUT_EN		BIT(0)
+#define RG_DSI_LNTx_CKLANE_EN		BIT(1)
+#define RG_DSI_LNTx_LPTX_IPLUS1		BIT(2)
+#define RG_DSI_LNTx_LPTX_IPLUS2		BIT(3)
+#define RG_DSI_LNTx_LPTX_IMINUS		BIT(4)
+#define RG_DSI_LNTx_LPCD_IPLUS		BIT(5)
+#define RG_DSI_LNTx_LPCD_IMINUS		BIT(6)
+#define RG_DSI_LNTx_RT_CODE		(0xf << 8)
+
+#define MIPITX_DSI_TOP_CON	0x40
+#define RG_DSI_LNT_INTR_EN		BIT(0)
+#define RG_DSI_LNT_HS_BIAS_EN		BIT(1)
+#define RG_DSI_LNT_IMP_CAL_EN		BIT(2)
+#define RG_DSI_LNT_TESTMODE_EN		BIT(3)
+#define RG_DSI_LNT_IMP_CAL_CODE		(0xf << 4)
+#define RG_DSI_LNT_AIO_SEL		(7 << 8)
+#define RG_DSI_PAD_TIE_LOW_EN		BIT(11)
+#define RG_DSI_DEBUG_INPUT_EN		BIT(12)
+#define RG_DSI_PRESERVE			(7 << 13)
+
+#define MIPITX_DSI_BG_CON	0x44
+#define RG_DSI_BG_CORE_EN		BIT(0)
+#define RG_DSI_BG_CKEN			BIT(1)
+#define RG_DSI_BG_DIV			(0x3 << 2)
+#define RG_DSI_BG_FAST_CHARGE		BIT(4)
+#define RG_DSI_VOUT_MSK			(0x3ffff << 5)
+#define RG_DSI_V12_SEL			(7 << 5)
+#define RG_DSI_V10_SEL			(7 << 8)
+#define RG_DSI_V072_SEL			(7 << 11)
+#define RG_DSI_V04_SEL			(7 << 14)
+#define RG_DSI_V032_SEL			(7 << 17)
+#define RG_DSI_V02_SEL			(7 << 20)
+#define RG_DSI_BG_R1_TRIM		(0xf << 24)
+#define RG_DSI_BG_R2_TRIM		(0xf << 28)
+
+#define MIPITX_DSI_PLL_CON0	0x50
+#define RG_DSI_MPPLL_PLL_EN		BIT(0)
+#define RG_DSI_MPPLL_DIV_MSK		(0x1ff << 1)
+#define RG_DSI_MPPLL_PREDIV		(3 << 1)
+#define RG_DSI_MPPLL_TXDIV0		(3 << 3)
+#define RG_DSI_MPPLL_TXDIV1		(3 << 5)
+#define RG_DSI_MPPLL_POSDIV		(7 << 7)
+#define RG_DSI_MPPLL_MONVC_EN		BIT(10)
+#define RG_DSI_MPPLL_MONREF_EN		BIT(11)
+#define RG_DSI_MPPLL_VOD_EN		BIT(12)
+
+#define MIPITX_DSI_PLL_CON1	0x54
+#define RG_DSI_MPPLL_SDM_FRA_EN		BIT(0)
+#define RG_DSI_MPPLL_SDM_SSC_PH_INIT	BIT(1)
+#define RG_DSI_MPPLL_SDM_SSC_EN		BIT(2)
+#define RG_DSI_MPPLL_SDM_SSC_PRD	(0xffff << 16)
+
+#define MIPITX_DSI_PLL_CON2	0x58
+
+#define MIPITX_DSI_PLL_TOP	0x64
+#define RG_DSI_MPPLL_PRESERVE		(0xff << 8)
+
+#define MIPITX_DSI_PLL_PWR	0x68
+#define RG_DSI_MPPLL_SDM_PWR_ON		BIT(0)
+#define RG_DSI_MPPLL_SDM_ISO_EN		BIT(1)
+#define RG_DSI_MPPLL_SDM_PWR_ACK	BIT(8)
+
+#define MIPITX_DSI_SW_CTRL	0x80
+#define SW_CTRL_EN			BIT(0)
+
+#define MIPITX_DSI_SW_CTRL_CON0	0x84
+#define SW_LNTC_LPTX_PRE_OE		BIT(0)
+#define SW_LNTC_LPTX_OE			BIT(1)
+#define SW_LNTC_LPTX_P			BIT(2)
+#define SW_LNTC_LPTX_N			BIT(3)
+#define SW_LNTC_HSTX_PRE_OE		BIT(4)
+#define SW_LNTC_HSTX_OE			BIT(5)
+#define SW_LNTC_HSTX_ZEROCLK		BIT(6)
+#define SW_LNT0_LPTX_PRE_OE		BIT(7)
+#define SW_LNT0_LPTX_OE			BIT(8)
+#define SW_LNT0_LPTX_P			BIT(9)
+#define SW_LNT0_LPTX_N			BIT(10)
+#define SW_LNT0_HSTX_PRE_OE		BIT(11)
+#define SW_LNT0_HSTX_OE			BIT(12)
+#define SW_LNT0_LPRX_EN			BIT(13)
+#define SW_LNT1_LPTX_PRE_OE		BIT(14)
+#define SW_LNT1_LPTX_OE			BIT(15)
+#define SW_LNT1_LPTX_P			BIT(16)
+#define SW_LNT1_LPTX_N			BIT(17)
+#define SW_LNT1_HSTX_PRE_OE		BIT(18)
+#define SW_LNT1_HSTX_OE			BIT(19)
+#define SW_LNT2_LPTX_PRE_OE		BIT(20)
+#define SW_LNT2_LPTX_OE			BIT(21)
+#define SW_LNT2_LPTX_P			BIT(22)
+#define SW_LNT2_LPTX_N			BIT(23)
+#define SW_LNT2_HSTX_PRE_OE		BIT(24)
+#define SW_LNT2_HSTX_OE			BIT(25)
+
+static int mtk_mipi_tx_pll_prepare(struct clk_hw *hw)
+{
+	struct mtk_mipi_tx *mipi_tx = mtk_mipi_tx_from_clk_hw(hw);
+	u8 txdiv, txdiv0, txdiv1;
+	u64 pcw;
+
+	dev_dbg(mipi_tx->dev, "prepare: %u Hz\n", mipi_tx->data_rate);
+
+	if (mipi_tx->data_rate >= 500000000) {
+		txdiv = 1;
+		txdiv0 = 0;
+		txdiv1 = 0;
+	} else if (mipi_tx->data_rate >= 250000000) {
+		txdiv = 2;
+		txdiv0 = 1;
+		txdiv1 = 0;
+	} else if (mipi_tx->data_rate >= 125000000) {
+		txdiv = 4;
+		txdiv0 = 2;
+		txdiv1 = 0;
+	} else if (mipi_tx->data_rate > 62000000) {
+		txdiv = 8;
+		txdiv0 = 2;
+		txdiv1 = 1;
+	} else if (mipi_tx->data_rate >= 50000000) {
+		txdiv = 16;
+		txdiv0 = 2;
+		txdiv1 = 2;
+	} else {
+		return -EINVAL;
+	}
+
+	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_BG_CON,
+				RG_DSI_VOUT_MSK |
+				RG_DSI_BG_CKEN | RG_DSI_BG_CORE_EN,
+				(4 << 20) | (4 << 17) | (4 << 14) |
+				(4 << 11) | (4 << 8) | (4 << 5) |
+				RG_DSI_BG_CKEN | RG_DSI_BG_CORE_EN);
+
+	usleep_range(30, 100);
+
+	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_TOP_CON,
+				RG_DSI_LNT_IMP_CAL_CODE | RG_DSI_LNT_HS_BIAS_EN,
+				(8 << 4) | RG_DSI_LNT_HS_BIAS_EN);
+
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_DSI_CON,
+			     RG_DSI_CKG_LDOOUT_EN | RG_DSI_LDOCORE_EN);
+
+	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_PLL_PWR,
+				RG_DSI_MPPLL_SDM_PWR_ON |
+				RG_DSI_MPPLL_SDM_ISO_EN,
+				RG_DSI_MPPLL_SDM_PWR_ON);
+
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_PLL_CON0,
+			       RG_DSI_MPPLL_PLL_EN);
+
+	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_PLL_CON0,
+				RG_DSI_MPPLL_TXDIV0 | RG_DSI_MPPLL_TXDIV1 |
+				RG_DSI_MPPLL_PREDIV,
+				(txdiv0 << 3) | (txdiv1 << 5));
+
+	/*
+	 * PLL PCW config
+	 * PCW bit 24~30 = integer part of pcw
+	 * PCW bit 0~23 = fractional part of pcw
+	 * pcw = data_Rate*4*txdiv/(Ref_clk*2);
+	 * Post DIV =4, so need data_Rate*4
+	 * Ref_clk is 26MHz
+	 */
+	pcw = div_u64(((u64)mipi_tx->data_rate * 2 * txdiv) << 24,
+		      26000000);
+	writel(pcw, mipi_tx->regs + MIPITX_DSI_PLL_CON2);
+
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_DSI_PLL_CON1,
+			     RG_DSI_MPPLL_SDM_FRA_EN);
+
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_DSI_PLL_CON0, RG_DSI_MPPLL_PLL_EN);
+
+	usleep_range(20, 100);
+
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_PLL_CON1,
+			       RG_DSI_MPPLL_SDM_SSC_EN);
+
+	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_PLL_TOP,
+				RG_DSI_MPPLL_PRESERVE,
+				mipi_tx->driver_data->mppll_preserve);
+
+	return 0;
+}
+
+static void mtk_mipi_tx_pll_unprepare(struct clk_hw *hw)
+{
+	struct mtk_mipi_tx *mipi_tx = mtk_mipi_tx_from_clk_hw(hw);
+
+	dev_dbg(mipi_tx->dev, "unprepare\n");
+
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_PLL_CON0,
+			       RG_DSI_MPPLL_PLL_EN);
+
+	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_PLL_TOP,
+				RG_DSI_MPPLL_PRESERVE, 0);
+
+	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_DSI_PLL_PWR,
+				RG_DSI_MPPLL_SDM_ISO_EN |
+				RG_DSI_MPPLL_SDM_PWR_ON,
+				RG_DSI_MPPLL_SDM_ISO_EN);
+
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_TOP_CON,
+			       RG_DSI_LNT_HS_BIAS_EN);
+
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_CON,
+			       RG_DSI_CKG_LDOOUT_EN | RG_DSI_LDOCORE_EN);
+
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_BG_CON,
+			       RG_DSI_BG_CKEN | RG_DSI_BG_CORE_EN);
+
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_PLL_CON0,
+			       RG_DSI_MPPLL_DIV_MSK);
+}
+
+static long mtk_mipi_tx_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+				       unsigned long *prate)
+{
+	return clamp_val(rate, 50000000, 1250000000);
+}
+
+static const struct clk_ops mtk_mipi_tx_pll_ops = {
+	.prepare = mtk_mipi_tx_pll_prepare,
+	.unprepare = mtk_mipi_tx_pll_unprepare,
+	.round_rate = mtk_mipi_tx_pll_round_rate,
+	.set_rate = mtk_mipi_tx_pll_set_rate,
+	.recalc_rate = mtk_mipi_tx_pll_recalc_rate,
+};
+
+static void mtk_mipi_tx_power_on_signal(struct phy *phy)
+{
+	struct mtk_mipi_tx *mipi_tx = phy_get_drvdata(phy);
+	u32 reg;
+
+	for (reg = MIPITX_DSI_CLOCK_LANE;
+	     reg <= MIPITX_DSI_DATA_LANE3; reg += 4)
+		mtk_mipi_tx_set_bits(mipi_tx, reg, RG_DSI_LNTx_LDOOUT_EN);
+
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_DSI_TOP_CON,
+			       RG_DSI_PAD_TIE_LOW_EN);
+}
+
+static void mtk_mipi_tx_power_off_signal(struct phy *phy)
+{
+	struct mtk_mipi_tx *mipi_tx = phy_get_drvdata(phy);
+	u32 reg;
+
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_DSI_TOP_CON,
+			     RG_DSI_PAD_TIE_LOW_EN);
+
+	for (reg = MIPITX_DSI_CLOCK_LANE;
+	     reg <= MIPITX_DSI_DATA_LANE3; reg += 4)
+		mtk_mipi_tx_clear_bits(mipi_tx, reg, RG_DSI_LNTx_LDOOUT_EN);
+}
+
+const struct mtk_mipitx_data mt2701_mipitx_data = {
+	.mppll_preserve = (3 << 8),
+	.mipi_tx_clk_ops = &mtk_mipi_tx_pll_ops,
+	.mipi_tx_enable_signal = mtk_mipi_tx_power_on_signal,
+	.mipi_tx_disable_signal = mtk_mipi_tx_power_off_signal,
+};
+
+const struct mtk_mipitx_data mt8173_mipitx_data = {
+	.mppll_preserve = (0 << 8),
+	.mipi_tx_clk_ops = &mtk_mipi_tx_pll_ops,
+	.mipi_tx_enable_signal = mtk_mipi_tx_power_on_signal,
+	.mipi_tx_disable_signal = mtk_mipi_tx_power_off_signal,
+};
-- 
cgit v1.2.3


From efda51a58b4ae8a0584dc785e0ef24a71677503c Mon Sep 17 00:00:00 2001
From: Jitao Shi <jitao.shi@mediatek.com>
Date: Wed, 7 Aug 2019 16:46:45 +0800
Subject: drm/mediatek: add mipi_tx driver for mt8183

This patch add mt8183 mipi_tx driver.
And also support other chips that use the same binding and driver.

Signed-off-by: Jitao Shi <jitao.shi@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/Makefile             |   1 +
 drivers/gpu/drm/mediatek/mtk_mipi_tx.c        |   2 +
 drivers/gpu/drm/mediatek/mtk_mipi_tx.h        |   1 +
 drivers/gpu/drm/mediatek/mtk_mt8183_mipi_tx.c | 149 ++++++++++++++++++++++++++
 4 files changed, 153 insertions(+)
 create mode 100644 drivers/gpu/drm/mediatek/mtk_mt8183_mipi_tx.c

diff --git a/drivers/gpu/drm/mediatek/Makefile b/drivers/gpu/drm/mediatek/Makefile
index 2c8de1f5a5ee..8067a4be8311 100644
--- a/drivers/gpu/drm/mediatek/Makefile
+++ b/drivers/gpu/drm/mediatek/Makefile
@@ -13,6 +13,7 @@ mediatek-drm-y := mtk_disp_color.o \
 		  mtk_dsi.o \
 		  mtk_mipi_tx.o \
 		  mtk_mt8173_mipi_tx.o \
+		  mtk_mt8183_mipi_tx.o \
 		  mtk_dpi.o
 
 obj-$(CONFIG_DRM_MEDIATEK) += mediatek-drm.o
diff --git a/drivers/gpu/drm/mediatek/mtk_mipi_tx.c b/drivers/gpu/drm/mediatek/mtk_mipi_tx.c
index 77b9a185e970..e4d34484ecc8 100644
--- a/drivers/gpu/drm/mediatek/mtk_mipi_tx.c
+++ b/drivers/gpu/drm/mediatek/mtk_mipi_tx.c
@@ -175,6 +175,8 @@ static const struct of_device_id mtk_mipi_tx_match[] = {
 	  .data = &mt2701_mipitx_data },
 	{ .compatible = "mediatek,mt8173-mipi-tx",
 	  .data = &mt8173_mipitx_data },
+	{ .compatible = "mediatek,mt8183-mipi-tx",
+	  .data = &mt8183_mipitx_data },
 	{ },
 };
 
diff --git a/drivers/gpu/drm/mediatek/mtk_mipi_tx.h b/drivers/gpu/drm/mediatek/mtk_mipi_tx.h
index 4f905313564f..413f35d86219 100644
--- a/drivers/gpu/drm/mediatek/mtk_mipi_tx.h
+++ b/drivers/gpu/drm/mediatek/mtk_mipi_tx.h
@@ -44,5 +44,6 @@ unsigned long mtk_mipi_tx_pll_recalc_rate(struct clk_hw *hw,
 
 extern const struct mtk_mipitx_data mt2701_mipitx_data;
 extern const struct mtk_mipitx_data mt8173_mipitx_data;
+extern const struct mtk_mipitx_data mt8183_mipitx_data;
 
 #endif
diff --git a/drivers/gpu/drm/mediatek/mtk_mt8183_mipi_tx.c b/drivers/gpu/drm/mediatek/mtk_mt8183_mipi_tx.c
new file mode 100644
index 000000000000..91f08a351fd0
--- /dev/null
+++ b/drivers/gpu/drm/mediatek/mtk_mt8183_mipi_tx.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019 MediaTek Inc.
+ * Author: jitao.shi <jitao.shi@mediatek.com>
+ */
+
+#include "mtk_mipi_tx.h"
+
+#define MIPITX_LANE_CON		0x000c
+#define RG_DSI_CPHY_T1DRV_EN		BIT(0)
+#define RG_DSI_ANA_CK_SEL		BIT(1)
+#define RG_DSI_PHY_CK_SEL		BIT(2)
+#define RG_DSI_CPHY_EN			BIT(3)
+#define RG_DSI_PHYCK_INV_EN		BIT(4)
+#define RG_DSI_PWR04_EN			BIT(5)
+#define RG_DSI_BG_LPF_EN		BIT(6)
+#define RG_DSI_BG_CORE_EN		BIT(7)
+#define RG_DSI_PAD_TIEL_SEL		BIT(8)
+
+#define MIPITX_PLL_PWR		0x0028
+#define MIPITX_PLL_CON0		0x002c
+#define MIPITX_PLL_CON1		0x0030
+#define MIPITX_PLL_CON2		0x0034
+#define MIPITX_PLL_CON3		0x0038
+#define MIPITX_PLL_CON4		0x003c
+#define RG_DSI_PLL_IBIAS		(3 << 10)
+
+#define MIPITX_D2_SW_CTL_EN	0x0144
+#define MIPITX_D0_SW_CTL_EN	0x0244
+#define MIPITX_CK_CKMODE_EN	0x0328
+#define DSI_CK_CKMODE_EN		BIT(0)
+#define MIPITX_CK_SW_CTL_EN	0x0344
+#define MIPITX_D1_SW_CTL_EN	0x0444
+#define MIPITX_D3_SW_CTL_EN	0x0544
+#define DSI_SW_CTL_EN			BIT(0)
+#define AD_DSI_PLL_SDM_PWR_ON		BIT(0)
+#define AD_DSI_PLL_SDM_ISO_EN		BIT(1)
+
+#define RG_DSI_PLL_EN			BIT(4)
+#define RG_DSI_PLL_POSDIV		(0x7 << 8)
+
+static int mtk_mipi_tx_pll_enable(struct clk_hw *hw)
+{
+	struct mtk_mipi_tx *mipi_tx = mtk_mipi_tx_from_clk_hw(hw);
+	unsigned int txdiv, txdiv0;
+	u64 pcw;
+
+	dev_dbg(mipi_tx->dev, "enable: %u bps\n", mipi_tx->data_rate);
+
+	if (mipi_tx->data_rate >= 2000000000) {
+		txdiv = 1;
+		txdiv0 = 0;
+	} else if (mipi_tx->data_rate >= 1000000000) {
+		txdiv = 2;
+		txdiv0 = 1;
+	} else if (mipi_tx->data_rate >= 500000000) {
+		txdiv = 4;
+		txdiv0 = 2;
+	} else if (mipi_tx->data_rate > 250000000) {
+		txdiv = 8;
+		txdiv0 = 3;
+	} else if (mipi_tx->data_rate >= 125000000) {
+		txdiv = 16;
+		txdiv0 = 4;
+	} else {
+		return -EINVAL;
+	}
+
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_PLL_CON4, RG_DSI_PLL_IBIAS);
+
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_PLL_PWR, AD_DSI_PLL_SDM_PWR_ON);
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_PLL_CON1, RG_DSI_PLL_EN);
+	udelay(1);
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_PLL_PWR, AD_DSI_PLL_SDM_ISO_EN);
+	pcw = div_u64(((u64)mipi_tx->data_rate * txdiv) << 24, 26000000);
+	writel(pcw, mipi_tx->regs + MIPITX_PLL_CON0);
+	mtk_mipi_tx_update_bits(mipi_tx, MIPITX_PLL_CON1, RG_DSI_PLL_POSDIV,
+				txdiv0 << 8);
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_PLL_CON1, RG_DSI_PLL_EN);
+
+	return 0;
+}
+
+static void mtk_mipi_tx_pll_disable(struct clk_hw *hw)
+{
+	struct mtk_mipi_tx *mipi_tx = mtk_mipi_tx_from_clk_hw(hw);
+
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_PLL_CON1, RG_DSI_PLL_EN);
+
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_PLL_PWR, AD_DSI_PLL_SDM_ISO_EN);
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_PLL_PWR, AD_DSI_PLL_SDM_PWR_ON);
+}
+
+static long mtk_mipi_tx_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+				       unsigned long *prate)
+{
+	return clamp_val(rate, 50000000, 1600000000);
+}
+
+static const struct clk_ops mtk_mipi_tx_pll_ops = {
+	.enable = mtk_mipi_tx_pll_enable,
+	.disable = mtk_mipi_tx_pll_disable,
+	.round_rate = mtk_mipi_tx_pll_round_rate,
+	.set_rate = mtk_mipi_tx_pll_set_rate,
+	.recalc_rate = mtk_mipi_tx_pll_recalc_rate,
+};
+
+static void mtk_mipi_tx_power_on_signal(struct phy *phy)
+{
+	struct mtk_mipi_tx *mipi_tx = phy_get_drvdata(phy);
+
+	/* BG_LPF_EN / BG_CORE_EN */
+	writel(RG_DSI_PAD_TIEL_SEL | RG_DSI_BG_CORE_EN,
+	       mipi_tx->regs + MIPITX_LANE_CON);
+	usleep_range(30, 100);
+	writel(RG_DSI_BG_CORE_EN | RG_DSI_BG_LPF_EN,
+	       mipi_tx->regs + MIPITX_LANE_CON);
+
+	/* Switch OFF each Lane */
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_D0_SW_CTL_EN, DSI_SW_CTL_EN);
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_D1_SW_CTL_EN, DSI_SW_CTL_EN);
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_D2_SW_CTL_EN, DSI_SW_CTL_EN);
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_D3_SW_CTL_EN, DSI_SW_CTL_EN);
+	mtk_mipi_tx_clear_bits(mipi_tx, MIPITX_CK_SW_CTL_EN, DSI_SW_CTL_EN);
+
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_CK_CKMODE_EN, DSI_CK_CKMODE_EN);
+}
+
+static void mtk_mipi_tx_power_off_signal(struct phy *phy)
+{
+	struct mtk_mipi_tx *mipi_tx = phy_get_drvdata(phy);
+
+	/* Switch ON each Lane */
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_D0_SW_CTL_EN, DSI_SW_CTL_EN);
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_D1_SW_CTL_EN, DSI_SW_CTL_EN);
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_D2_SW_CTL_EN, DSI_SW_CTL_EN);
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_D3_SW_CTL_EN, DSI_SW_CTL_EN);
+	mtk_mipi_tx_set_bits(mipi_tx, MIPITX_CK_SW_CTL_EN, DSI_SW_CTL_EN);
+
+	writel(RG_DSI_PAD_TIEL_SEL | RG_DSI_BG_CORE_EN,
+	       mipi_tx->regs + MIPITX_LANE_CON);
+	writel(RG_DSI_PAD_TIEL_SEL, mipi_tx->regs + MIPITX_LANE_CON);
+}
+
+const struct mtk_mipitx_data mt8183_mipitx_data = {
+	.mipi_tx_clk_ops = &mtk_mipi_tx_pll_ops,
+	.mipi_tx_enable_signal = mtk_mipi_tx_power_on_signal,
+	.mipi_tx_disable_signal = mtk_mipi_tx_power_off_signal,
+};
-- 
cgit v1.2.3


From b3218e74367aacefeb4975bd0b69c8cb897bcb6a Mon Sep 17 00:00:00 2001
From: Jitao Shi <jitao.shi@mediatek.com>
Date: Sun, 11 Aug 2019 18:40:02 +0800
Subject: drm/mediatek: move mipi_dsi_host_register to probe

DSI panel driver need attach function which is include in
mipi_dsi_host_ops.

If mipi_dsi_host_register is not in probe, dsi panel will
probe more delay.

So move the mipi_dsi_host_register to probe from bind.

Signed-off-by: Jitao Shi <jitao.shi@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_dsi.c | 53 ++++++++++++++++++++++----------------
 1 file changed, 31 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 224afb666881..a696509aac90 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -522,7 +522,7 @@ static s32 mtk_dsi_switch_to_cmd_mode(struct mtk_dsi *dsi, u8 irq_flag, u32 t)
 
 static int mtk_dsi_poweron(struct mtk_dsi *dsi)
 {
-	struct device *dev = dsi->dev;
+	struct device *dev = dsi->host.dev;
 	int ret;
 	u64 pixel_clock, total_bits;
 	u32 htotal, htotal_bits, bit_per_pixel, overhead_cycles, overhead_bits;
@@ -1049,12 +1049,6 @@ static int mtk_dsi_bind(struct device *dev, struct device *master, void *data)
 		return ret;
 	}
 
-	ret = mipi_dsi_host_register(&dsi->host);
-	if (ret < 0) {
-		dev_err(dev, "failed to register DSI host: %d\n", ret);
-		goto err_ddp_comp_unregister;
-	}
-
 	ret = mtk_dsi_create_conn_enc(drm, dsi);
 	if (ret) {
 		DRM_ERROR("Encoder create failed with %d\n", ret);
@@ -1064,8 +1058,6 @@ static int mtk_dsi_bind(struct device *dev, struct device *master, void *data)
 	return 0;
 
 err_unregister:
-	mipi_dsi_host_unregister(&dsi->host);
-err_ddp_comp_unregister:
 	mtk_ddp_comp_unregister(drm, &dsi->ddp_comp);
 	return ret;
 }
@@ -1077,7 +1069,6 @@ static void mtk_dsi_unbind(struct device *dev, struct device *master,
 	struct mtk_dsi *dsi = dev_get_drvdata(dev);
 
 	mtk_dsi_destroy_conn_enc(dsi);
-	mipi_dsi_host_unregister(&dsi->host);
 	mtk_ddp_comp_unregister(drm, &dsi->ddp_comp);
 }
 
@@ -1101,31 +1092,36 @@ static int mtk_dsi_probe(struct platform_device *pdev)
 
 	dsi->host.ops = &mtk_dsi_ops;
 	dsi->host.dev = dev;
+	ret = mipi_dsi_host_register(&dsi->host);
+	if (ret < 0) {
+		dev_err(dev, "failed to register DSI host: %d\n", ret);
+		return ret;
+	}
 
 	ret = drm_of_find_panel_or_bridge(dev->of_node, 0, 0,
 					  &dsi->panel, &dsi->bridge);
 	if (ret)
-		return ret;
+		goto err_unregister_host;
 
 	dsi->engine_clk = devm_clk_get(dev, "engine");
 	if (IS_ERR(dsi->engine_clk)) {
 		ret = PTR_ERR(dsi->engine_clk);
 		dev_err(dev, "Failed to get engine clock: %d\n", ret);
-		return ret;
+		goto err_unregister_host;
 	}
 
 	dsi->digital_clk = devm_clk_get(dev, "digital");
 	if (IS_ERR(dsi->digital_clk)) {
 		ret = PTR_ERR(dsi->digital_clk);
 		dev_err(dev, "Failed to get digital clock: %d\n", ret);
-		return ret;
+		goto err_unregister_host;
 	}
 
 	dsi->hs_clk = devm_clk_get(dev, "hs");
 	if (IS_ERR(dsi->hs_clk)) {
 		ret = PTR_ERR(dsi->hs_clk);
 		dev_err(dev, "Failed to get hs clock: %d\n", ret);
-		return ret;
+		goto err_unregister_host;
 	}
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1133,33 +1129,35 @@ static int mtk_dsi_probe(struct platform_device *pdev)
 	if (IS_ERR(dsi->regs)) {
 		ret = PTR_ERR(dsi->regs);
 		dev_err(dev, "Failed to ioremap memory: %d\n", ret);
-		return ret;
+		goto err_unregister_host;
 	}
 
 	dsi->phy = devm_phy_get(dev, "dphy");
 	if (IS_ERR(dsi->phy)) {
 		ret = PTR_ERR(dsi->phy);
 		dev_err(dev, "Failed to get MIPI-DPHY: %d\n", ret);
-		return ret;
+		goto err_unregister_host;
 	}
 
 	comp_id = mtk_ddp_comp_get_id(dev->of_node, MTK_DSI);
 	if (comp_id < 0) {
 		dev_err(dev, "Failed to identify by alias: %d\n", comp_id);
-		return comp_id;
+		ret = comp_id;
+		goto err_unregister_host;
 	}
 
 	ret = mtk_ddp_comp_init(dev, dev->of_node, &dsi->ddp_comp, comp_id,
 				&mtk_dsi_funcs);
 	if (ret) {
 		dev_err(dev, "Failed to initialize component: %d\n", ret);
-		return ret;
+		goto err_unregister_host;
 	}
 
 	irq_num = platform_get_irq(pdev, 0);
 	if (irq_num < 0) {
-		dev_err(&pdev->dev, "failed to request dsi irq resource\n");
-		return -EPROBE_DEFER;
+		dev_err(&pdev->dev, "failed to get dsi irq_num: %d\n", irq_num);
+		ret = irq_num;
+		goto err_unregister_host;
 	}
 
 	irq_set_status_flags(irq_num, IRQ_TYPE_LEVEL_LOW);
@@ -1167,14 +1165,24 @@ static int mtk_dsi_probe(struct platform_device *pdev)
 			       IRQF_TRIGGER_LOW, dev_name(&pdev->dev), dsi);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to request mediatek dsi irq\n");
-		return -EPROBE_DEFER;
+		goto err_unregister_host;
 	}
 
 	init_waitqueue_head(&dsi->irq_wait_queue);
 
 	platform_set_drvdata(pdev, dsi);
 
-	return component_add(&pdev->dev, &mtk_dsi_component_ops);
+	ret = component_add(&pdev->dev, &mtk_dsi_component_ops);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to add component: %d\n", ret);
+		goto err_unregister_host;
+	}
+
+	return 0;
+
+err_unregister_host:
+	mipi_dsi_host_unregister(&dsi->host);
+	return ret;
 }
 
 static int mtk_dsi_remove(struct platform_device *pdev)
@@ -1183,6 +1191,7 @@ static int mtk_dsi_remove(struct platform_device *pdev)
 
 	mtk_output_dsi_disable(dsi);
 	component_del(&pdev->dev, &mtk_dsi_component_ops);
+	mipi_dsi_host_unregister(&dsi->host);
 
 	return 0;
 }
-- 
cgit v1.2.3


From bb6bc2982a28d5d8e83c3bf0887949be1cc6bb5d Mon Sep 17 00:00:00 2001
From: Jitao Shi <jitao.shi@mediatek.com>
Date: Thu, 19 Sep 2019 14:57:59 +0800
Subject: drm/mediatek: fixes CMDQ reg address of mt8173 is different with
 mt2701

Config the different CMDQ reg address in driver data.

Signed-off-by: Jitao Shi <jitao.shi@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_dsi.c | 27 ++++++++++++++++++++++-----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index a696509aac90..f165ec52b66a 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -125,7 +125,6 @@
 #define VM_CMD_EN			BIT(0)
 #define TS_VFP_EN			BIT(5)
 
-#define DSI_CMDQ0		0x180
 #define CONFIG				(0xff << 0)
 #define SHORT_PACKET			0
 #define LONG_PACKET			2
@@ -150,6 +149,10 @@
 
 struct phy;
 
+struct mtk_dsi_driver_data {
+	const u32 reg_cmdq_off;
+};
+
 struct mtk_dsi {
 	struct mtk_ddp_comp ddp_comp;
 	struct device *dev;
@@ -176,6 +179,7 @@ struct mtk_dsi {
 	bool enabled;
 	u32 irq_data;
 	wait_queue_head_t irq_wait_queue;
+	const struct mtk_dsi_driver_data *driver_data;
 };
 
 static inline struct mtk_dsi *encoder_to_dsi(struct drm_encoder *e)
@@ -938,6 +942,7 @@ static void mtk_dsi_cmdq(struct mtk_dsi *dsi, const struct mipi_dsi_msg *msg)
 	const char *tx_buf = msg->tx_buf;
 	u8 config, cmdq_size, cmdq_off, type = msg->type;
 	u32 reg_val, cmdq_mask, i;
+	u32 reg_cmdq_off = dsi->driver_data->reg_cmdq_off;
 
 	if (MTK_DSI_HOST_IS_READ(type))
 		config = BTA;
@@ -957,9 +962,9 @@ static void mtk_dsi_cmdq(struct mtk_dsi *dsi, const struct mipi_dsi_msg *msg)
 	}
 
 	for (i = 0; i < msg->tx_len; i++)
-		writeb(tx_buf[i], dsi->regs + DSI_CMDQ0 + cmdq_off + i);
+		writeb(tx_buf[i], dsi->regs + reg_cmdq_off + cmdq_off + i);
 
-	mtk_dsi_mask(dsi, DSI_CMDQ0, cmdq_mask, reg_val);
+	mtk_dsi_mask(dsi, reg_cmdq_off, cmdq_mask, reg_val);
 	mtk_dsi_mask(dsi, DSI_CMDQ_SIZE, CMDQ_SIZE, cmdq_size);
 }
 
@@ -1103,6 +1108,8 @@ static int mtk_dsi_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_unregister_host;
 
+	dsi->driver_data = of_device_get_match_data(dev);
+
 	dsi->engine_clk = devm_clk_get(dev, "engine");
 	if (IS_ERR(dsi->engine_clk)) {
 		ret = PTR_ERR(dsi->engine_clk);
@@ -1196,9 +1203,19 @@ static int mtk_dsi_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct mtk_dsi_driver_data mt8173_dsi_driver_data = {
+	.reg_cmdq_off = 0x200,
+};
+
+static const struct mtk_dsi_driver_data mt2701_dsi_driver_data = {
+	.reg_cmdq_off = 0x180,
+};
+
 static const struct of_device_id mtk_dsi_of_match[] = {
-	{ .compatible = "mediatek,mt2701-dsi" },
-	{ .compatible = "mediatek,mt8173-dsi" },
+	{ .compatible = "mediatek,mt2701-dsi",
+	  .data = &mt2701_dsi_driver_data },
+	{ .compatible = "mediatek,mt8173-dsi",
+	  .data = &mt8173_dsi_driver_data },
 	{ },
 };
 
-- 
cgit v1.2.3


From 89d0e3f8825822ca20f3af2d61e5e1e6df4c2476 Mon Sep 17 00:00:00 2001
From: Jitao Shi <jitao.shi@mediatek.com>
Date: Thu, 19 Sep 2019 14:58:00 +0800
Subject: drm/mediatek: replace writeb() with mtk_dsi_mask()

The writeb() is unavailable in mt8173. Because the mt8173 dsi module
doesn't support 8bit mode access.

Signed-off-by: Jitao Shi <jitao.shi@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_dsi.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index f165ec52b66a..a7caf75fb971 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -962,7 +962,9 @@ static void mtk_dsi_cmdq(struct mtk_dsi *dsi, const struct mipi_dsi_msg *msg)
 	}
 
 	for (i = 0; i < msg->tx_len; i++)
-		writeb(tx_buf[i], dsi->regs + reg_cmdq_off + cmdq_off + i);
+		mtk_dsi_mask(dsi, (reg_cmdq_off + cmdq_off + i) & (~0x3U),
+			     (0xffUL << (((i + cmdq_off) & 3U) * 8U)),
+			     tx_buf[i] << (((i + cmdq_off) & 3U) * 8U));
 
 	mtk_dsi_mask(dsi, reg_cmdq_off, cmdq_mask, reg_val);
 	mtk_dsi_mask(dsi, DSI_CMDQ_SIZE, CMDQ_SIZE, cmdq_size);
-- 
cgit v1.2.3


From 3c6bd94d32c45d47a0fce49e9cd64d72ff612bb5 Mon Sep 17 00:00:00 2001
From: Jitao Shi <jitao.shi@mediatek.com>
Date: Sun, 11 Aug 2019 18:40:04 +0800
Subject: drm/mediatek: add dsi reg commit disable control

New DSI IP has shadow register and working reg. The register
values are writen to shadow register. And then trigger with
commit reg, the register values will be moved working register.

This function is default on. But this driver doesn't use this
function. So add the disable control.

Signed-off-by: Jitao Shi <jitao.shi@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_dsi.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index a7caf75fb971..881c0afabf17 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -125,6 +125,10 @@
 #define VM_CMD_EN			BIT(0)
 #define TS_VFP_EN			BIT(5)
 
+#define DSI_SHADOW_DEBUG	0x190U
+#define FORCE_COMMIT			BIT(0)
+#define BYPASS_SHADOW			BIT(1)
+
 #define CONFIG				(0xff << 0)
 #define SHORT_PACKET			0
 #define LONG_PACKET			2
@@ -151,6 +155,7 @@ struct phy;
 
 struct mtk_dsi_driver_data {
 	const u32 reg_cmdq_off;
+	bool has_shadow_ctl;
 };
 
 struct mtk_dsi {
@@ -588,6 +593,11 @@ static int mtk_dsi_poweron(struct mtk_dsi *dsi)
 	}
 
 	mtk_dsi_enable(dsi);
+
+	if (dsi->driver_data->has_shadow_ctl)
+		writel(FORCE_COMMIT | BYPASS_SHADOW,
+		       dsi->regs + DSI_SHADOW_DEBUG);
+
 	mtk_dsi_reset_engine(dsi);
 	mtk_dsi_phy_timconfig(dsi);
 
-- 
cgit v1.2.3


From 7bf54afec961504d9618074539ec9ae2b8de8554 Mon Sep 17 00:00:00 2001
From: Jitao Shi <jitao.shi@mediatek.com>
Date: Sun, 11 Aug 2019 18:40:05 +0800
Subject: drm/mediatek: add frame size control

Our new DSI chip has frame size control.
So add the driver data to control for different chips.

Signed-off-by: Jitao Shi <jitao.shi@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_dsi.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 881c0afabf17..ac1a24035fef 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -72,6 +72,7 @@
 #define DSI_VBP_NL		0x24
 #define DSI_VFP_NL		0x28
 #define DSI_VACT_NL		0x2C
+#define DSI_SIZE_CON		0x38
 #define DSI_HSA_WC		0x50
 #define DSI_HBP_WC		0x54
 #define DSI_HFP_WC		0x58
@@ -156,6 +157,7 @@ struct phy;
 struct mtk_dsi_driver_data {
 	const u32 reg_cmdq_off;
 	bool has_shadow_ctl;
+	bool has_size_ctl;
 };
 
 struct mtk_dsi {
@@ -424,6 +426,10 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi)
 	writel(vm->vfront_porch, dsi->regs + DSI_VFP_NL);
 	writel(vm->vactive, dsi->regs + DSI_VACT_NL);
 
+	if (dsi->driver_data->has_size_ctl)
+		writel(vm->vactive << 16 | vm->hactive,
+		       dsi->regs + DSI_SIZE_CON);
+
 	horizontal_sync_active_byte = (vm->hsync_len * dsi_tmp_buf_bpp - 10);
 
 	if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE)
-- 
cgit v1.2.3


From e249e3e86b33386738e1ce4a37374aaea019a7e0 Mon Sep 17 00:00:00 2001
From: Jitao Shi <jitao.shi@mediatek.com>
Date: Sun, 11 Aug 2019 18:40:06 +0800
Subject: drm/mediatek: add mt8183 dsi driver support

Add mt8183 dsi driver data. Enable size control and
reg commit control.

Signed-off-by: Jitao Shi <jitao.shi@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_dsi.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index ac1a24035fef..793deef5bf06 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -1229,11 +1229,19 @@ static const struct mtk_dsi_driver_data mt2701_dsi_driver_data = {
 	.reg_cmdq_off = 0x180,
 };
 
+static const struct mtk_dsi_driver_data mt8183_dsi_driver_data = {
+	.reg_cmdq_off = 0x200,
+	.has_shadow_ctl = true,
+	.has_size_ctl = true,
+};
+
 static const struct of_device_id mtk_dsi_of_match[] = {
 	{ .compatible = "mediatek,mt2701-dsi",
 	  .data = &mt2701_dsi_driver_data },
 	{ .compatible = "mediatek,mt8173-dsi",
 	  .data = &mt8173_dsi_driver_data },
+	{ .compatible = "mediatek,mt8183-dsi",
+	  .data = &mt8183_dsi_driver_data },
 	{ },
 };
 
-- 
cgit v1.2.3


From 7a5bc4e22ecfd74dc3662342beaa909770a3b786 Mon Sep 17 00:00:00 2001
From: Jitao Shi <jitao.shi@mediatek.com>
Date: Thu, 19 Sep 2019 14:58:04 +0800
Subject: drm/mediatek: change the dsi phytiming calculate method

Change the method of frame rate calc which can get more accurate
frame rate.

data rate = pixel_clock * bit_per_pixel / lanes
Adjust hfp_wc to adapt the additional phy_data

if MIPI_DSI_MODE_VIDEO_BURST
	hfp_wc = hfp * bpp - data_phy_cycles * lanes - 12 - 6;
else
	hfp_wc = hfp * bpp - data_phy_cycles * lanes - 12;

Note:
//(2: 1 for sync, 1 for phy idle)
data_phy_cycles = T_hs_exit + T_lpx + T_hs_prepare + T_hs_zero + 2;

bpp: bit per pixel

Signed-off-by: Jitao Shi <jitao.shi@mediatek.com>
Tested-by: Ryan Case <ryandcase@chromium.org>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_dsi.c | 118 +++++++++++++++++++++++++------------
 1 file changed, 81 insertions(+), 37 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 793deef5bf06..989e55f3e0c0 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -138,12 +138,6 @@
 #define DATA_0				(0xff << 16)
 #define DATA_1				(0xff << 24)
 
-#define T_LPX		5
-#define T_HS_PREP	6
-#define T_HS_TRAIL	8
-#define T_HS_EXIT	7
-#define T_HS_ZERO	10
-
 #define NS_TO_CYCLE(n, c)    ((n) / (c) + (((n) % (c)) ? 1 : 0))
 
 #define MTK_DSI_HOST_IS_READ(type) \
@@ -152,6 +146,25 @@
 	(type == MIPI_DSI_GENERIC_READ_REQUEST_2_PARAM) || \
 	(type == MIPI_DSI_DCS_READ))
 
+struct mtk_phy_timing {
+	u32 lpx;
+	u32 da_hs_prepare;
+	u32 da_hs_zero;
+	u32 da_hs_trail;
+
+	u32 ta_go;
+	u32 ta_sure;
+	u32 ta_get;
+	u32 da_hs_exit;
+
+	u32 clk_hs_zero;
+	u32 clk_hs_trail;
+
+	u32 clk_hs_prepare;
+	u32 clk_hs_post;
+	u32 clk_hs_exit;
+};
+
 struct phy;
 
 struct mtk_dsi_driver_data {
@@ -182,6 +195,7 @@ struct mtk_dsi {
 	enum mipi_dsi_pixel_format format;
 	unsigned int lanes;
 	struct videomode vm;
+	struct mtk_phy_timing phy_timing;
 	int refcount;
 	bool enabled;
 	u32 irq_data;
@@ -215,17 +229,36 @@ static void mtk_dsi_phy_timconfig(struct mtk_dsi *dsi)
 {
 	u32 timcon0, timcon1, timcon2, timcon3;
 	u32 ui, cycle_time;
+	struct mtk_phy_timing *timing = &dsi->phy_timing;
+
+	ui = DIV_ROUND_UP(1000000000, dsi->data_rate);
+	cycle_time = div_u64(8000000000ULL, dsi->data_rate);
+
+	timing->lpx = NS_TO_CYCLE(60, cycle_time);
+	timing->da_hs_prepare = NS_TO_CYCLE(50 + 5 * ui, cycle_time);
+	timing->da_hs_zero = NS_TO_CYCLE(110 + 6 * ui, cycle_time);
+	timing->da_hs_trail = NS_TO_CYCLE(77 + 4 * ui, cycle_time);
 
-	ui = 1000 / dsi->data_rate + 0x01;
-	cycle_time = 8000 / dsi->data_rate + 0x01;
+	timing->ta_go = 4 * timing->lpx;
+	timing->ta_sure = 3 * timing->lpx / 2;
+	timing->ta_get = 5 * timing->lpx;
+	timing->da_hs_exit = 2 * timing->lpx;
 
-	timcon0 = T_LPX | T_HS_PREP << 8 | T_HS_ZERO << 16 | T_HS_TRAIL << 24;
-	timcon1 = 4 * T_LPX | (3 * T_LPX / 2) << 8 | 5 * T_LPX << 16 |
-		  T_HS_EXIT << 24;
-	timcon2 = ((NS_TO_CYCLE(0x64, cycle_time) + 0xa) << 24) |
-		  (NS_TO_CYCLE(0x150, cycle_time) << 16);
-	timcon3 = NS_TO_CYCLE(0x40, cycle_time) | (2 * T_LPX) << 16 |
-		  NS_TO_CYCLE(80 + 52 * ui, cycle_time) << 8;
+	timing->clk_hs_zero = NS_TO_CYCLE(336, cycle_time);
+	timing->clk_hs_trail = NS_TO_CYCLE(100, cycle_time) + 10;
+
+	timing->clk_hs_prepare = NS_TO_CYCLE(64, cycle_time);
+	timing->clk_hs_post = NS_TO_CYCLE(80 + 52 * ui, cycle_time);
+	timing->clk_hs_exit = 2 * timing->lpx;
+
+	timcon0 = timing->lpx | timing->da_hs_prepare << 8 |
+		  timing->da_hs_zero << 16 | timing->da_hs_trail << 24;
+	timcon1 = timing->ta_go | timing->ta_sure << 8 |
+		  timing->ta_get << 16 | timing->da_hs_exit << 24;
+	timcon2 = 1 << 8 | timing->clk_hs_zero << 16 |
+		  timing->clk_hs_trail << 24;
+	timcon3 = timing->clk_hs_prepare | timing->clk_hs_post << 8 |
+		  timing->clk_hs_exit << 16;
 
 	writel(timcon0, dsi->regs + DSI_PHY_TIMECON0);
 	writel(timcon1, dsi->regs + DSI_PHY_TIMECON1);
@@ -412,7 +445,8 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi)
 	u32 horizontal_sync_active_byte;
 	u32 horizontal_backporch_byte;
 	u32 horizontal_frontporch_byte;
-	u32 dsi_tmp_buf_bpp;
+	u32 dsi_tmp_buf_bpp, data_phy_cycles;
+	struct mtk_phy_timing *timing = &dsi->phy_timing;
 
 	struct videomode *vm = &dsi->vm;
 
@@ -439,7 +473,34 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi)
 		horizontal_backporch_byte = ((vm->hback_porch + vm->hsync_len) *
 			dsi_tmp_buf_bpp - 10);
 
-	horizontal_frontporch_byte = (vm->hfront_porch * dsi_tmp_buf_bpp - 12);
+	data_phy_cycles = timing->lpx + timing->da_hs_prepare +
+				  timing->da_hs_zero + timing->da_hs_exit + 2;
+
+	if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) {
+		if (vm->hfront_porch * dsi_tmp_buf_bpp >
+		    data_phy_cycles * dsi->lanes + 18) {
+			horizontal_frontporch_byte = vm->hfront_porch *
+						     dsi_tmp_buf_bpp -
+						     data_phy_cycles *
+						     dsi->lanes - 18;
+		} else {
+			DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n");
+			horizontal_frontporch_byte = vm->hfront_porch *
+						     dsi_tmp_buf_bpp;
+		}
+	} else {
+		if (vm->hfront_porch * dsi_tmp_buf_bpp >
+		    data_phy_cycles * dsi->lanes + 12) {
+			horizontal_frontporch_byte = vm->hfront_porch *
+						     dsi_tmp_buf_bpp -
+						     data_phy_cycles *
+						     dsi->lanes - 12;
+		} else {
+			DRM_WARN("HFP less than d-phy, FPS will under 60Hz\n");
+			horizontal_frontporch_byte = vm->hfront_porch *
+						     dsi_tmp_buf_bpp;
+		}
+	}
 
 	writel(horizontal_sync_active_byte, dsi->regs + DSI_HSA_WC);
 	writel(horizontal_backporch_byte, dsi->regs + DSI_HBP_WC);
@@ -539,8 +600,7 @@ static int mtk_dsi_poweron(struct mtk_dsi *dsi)
 {
 	struct device *dev = dsi->host.dev;
 	int ret;
-	u64 pixel_clock, total_bits;
-	u32 htotal, htotal_bits, bit_per_pixel, overhead_cycles, overhead_bits;
+	u32 bit_per_pixel;
 
 	if (++dsi->refcount != 1)
 		return 0;
@@ -559,24 +619,8 @@ static int mtk_dsi_poweron(struct mtk_dsi *dsi)
 		break;
 	}
 
-	/**
-	 * htotal_time = htotal * byte_per_pixel / num_lanes
-	 * overhead_time = lpx + hs_prepare + hs_zero + hs_trail + hs_exit
-	 * mipi_ratio = (htotal_time + overhead_time) / htotal_time
-	 * data_rate = pixel_clock * bit_per_pixel * mipi_ratio / num_lanes;
-	 */
-	pixel_clock = dsi->vm.pixelclock;
-	htotal = dsi->vm.hactive + dsi->vm.hback_porch + dsi->vm.hfront_porch +
-			dsi->vm.hsync_len;
-	htotal_bits = htotal * bit_per_pixel;
-
-	overhead_cycles = T_LPX + T_HS_PREP + T_HS_ZERO + T_HS_TRAIL +
-			T_HS_EXIT;
-	overhead_bits = overhead_cycles * dsi->lanes * 8;
-	total_bits = htotal_bits + overhead_bits;
-
-	dsi->data_rate = DIV_ROUND_UP_ULL(pixel_clock * total_bits,
-					  htotal * dsi->lanes);
+	dsi->data_rate = DIV_ROUND_UP_ULL(dsi->vm.pixelclock * bit_per_pixel,
+					  dsi->lanes);
 
 	ret = clk_set_rate(dsi->hs_clk, dsi->data_rate);
 	if (ret < 0) {
-- 
cgit v1.2.3


From 2f501cc0b020b9d991128a70e26c84552121a31d Mon Sep 17 00:00:00 2001
From: Jitao Shi <jitao.shi@mediatek.com>
Date: Sun, 11 Aug 2019 18:40:08 +0800
Subject: drm/mediatek: adjust dsi and mipi_tx probe sequence

mtk_mipi_tx is the phy of mtk_dsi.
mtk_dsi get the phy(mtk_mipi_tx) in probe().

So,  mtk_mipi_tx init should be ahead of mtk_dsi. Or mtk_dsi will
defer to wait mtk_mipi_tx probe done.

Signed-off-by: Jitao Shi <jitao.shi@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 352b81a7a670..62845ad4f542 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -669,8 +669,8 @@ static struct platform_driver * const mtk_drm_drivers[] = {
 	&mtk_disp_rdma_driver,
 	&mtk_dpi_driver,
 	&mtk_drm_platform_driver,
-	&mtk_dsi_driver,
 	&mtk_mipi_tx_driver,
+	&mtk_dsi_driver,
 };
 
 static int __init mtk_drm_init(void)
-- 
cgit v1.2.3


From 75374fc2c152ef42c45c6bf716743d5f5bb6d24d Mon Sep 17 00:00:00 2001
From: Jitao Shi <jitao.shi@mediatek.com>
Date: Thu, 19 Sep 2019 14:58:06 +0800
Subject: drm/mediatek: add dphy reset after setting lanes number

Add dphy reset after setting lanes number to avoid dphy fifo effor.

Signed-off-by: Jitao Shi <jitao.shi@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_dsi.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 989e55f3e0c0..c62b9b496036 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -39,6 +39,7 @@
 #define DSI_CON_CTRL		0x10
 #define DSI_RESET			BIT(0)
 #define DSI_EN				BIT(1)
+#define DPHY_RESET			BIT(2)
 
 #define DSI_MODE_CTRL		0x14
 #define MODE				(3)
@@ -282,6 +283,12 @@ static void mtk_dsi_reset_engine(struct mtk_dsi *dsi)
 	mtk_dsi_mask(dsi, DSI_CON_CTRL, DSI_RESET, 0);
 }
 
+static void mtk_dsi_reset_dphy(struct mtk_dsi *dsi)
+{
+	mtk_dsi_mask(dsi, DSI_CON_CTRL, DPHY_RESET, DPHY_RESET);
+	mtk_dsi_mask(dsi, DSI_CON_CTRL, DPHY_RESET, 0);
+}
+
 static void mtk_dsi_clk_ulp_mode_enter(struct mtk_dsi *dsi)
 {
 	mtk_dsi_mask(dsi, DSI_PHY_LCCON, LC_HS_TX_EN, 0);
@@ -652,6 +659,8 @@ static int mtk_dsi_poweron(struct mtk_dsi *dsi)
 	mtk_dsi_phy_timconfig(dsi);
 
 	mtk_dsi_rxtx_control(dsi);
+	usleep_range(30, 100);
+	mtk_dsi_reset_dphy(dsi);
 	mtk_dsi_ps_control_vact(dsi);
 	mtk_dsi_set_vm_cmd(dsi);
 	mtk_dsi_config_vdo_timing(dsi);
-- 
cgit v1.2.3


From ccfcaa5234e5cdadc0c6db8da6e9c486bb248a26 Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:24 +0800
Subject: dt-bindings: mediatek: add ovl_2l description for mt8183 display

Update device tree binding documention for the display subsystem for
Mediatek MT8183 SOCs

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 .../bindings/display/mediatek/mediatek,disp.txt    | 27 +++++++++++-----------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
index 8469de510001..c2dbc9efe10b 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
@@ -27,19 +27,20 @@ Documentation/devicetree/bindings/display/mediatek/mediatek,dpi.txt.
 
 Required properties (all function blocks):
 - compatible: "mediatek,<chip>-disp-<function>", one of
-	"mediatek,<chip>-disp-ovl"   - overlay (4 layers, blending, csc)
-	"mediatek,<chip>-disp-rdma"  - read DMA / line buffer
-	"mediatek,<chip>-disp-wdma"  - write DMA
-	"mediatek,<chip>-disp-color" - color processor
-	"mediatek,<chip>-disp-aal"   - adaptive ambient light controller
-	"mediatek,<chip>-disp-gamma" - gamma correction
-	"mediatek,<chip>-disp-merge" - merge streams from two RDMA sources
-	"mediatek,<chip>-disp-split" - split stream to two encoders
-	"mediatek,<chip>-disp-ufoe"  - data compression engine
-	"mediatek,<chip>-dsi"        - DSI controller, see mediatek,dsi.txt
-	"mediatek,<chip>-dpi"        - DPI controller, see mediatek,dpi.txt
-	"mediatek,<chip>-disp-mutex" - display mutex
-	"mediatek,<chip>-disp-od"    - overdrive
+	"mediatek,<chip>-disp-ovl"   		- overlay (4 layers, blending, csc)
+	"mediatek,<chip>-disp-ovl-2l"           - overlay (2 layers, blending, csc)
+	"mediatek,<chip>-disp-rdma"  		- read DMA / line buffer
+	"mediatek,<chip>-disp-wdma"  		- write DMA
+	"mediatek,<chip>-disp-color" 		- color processor
+	"mediatek,<chip>-disp-aal"   		- adaptive ambient light controller
+	"mediatek,<chip>-disp-gamma" 		- gamma correction
+	"mediatek,<chip>-disp-merge" 		- merge streams from two RDMA sources
+	"mediatek,<chip>-disp-split" 		- split stream to two encoders
+	"mediatek,<chip>-disp-ufoe"  		- data compression engine
+	"mediatek,<chip>-dsi"        		- DSI controller, see mediatek,dsi.txt
+	"mediatek,<chip>-dpi"        		- DPI controller, see mediatek,dpi.txt
+	"mediatek,<chip>-disp-mutex" 		- display mutex
+	"mediatek,<chip>-disp-od"    		- overdrive
   the supported chips are mt2701, mt2712 and mt8173.
 - reg: Physical base address and length of the function block register space
 - interrupts: The interrupt signal from the function block (required, except for
-- 
cgit v1.2.3


From 6e031636d1f13905e225aa1be3b58d426ede2d90 Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:25 +0800
Subject: dt-bindings: mediatek: add ccorr description for mt8183 display

Update device tree binding documention for the display subsystem for
Mediatek MT8183 SOCs

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Reviewed-by: Rob Herring <robh at kernel.org>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
index c2dbc9efe10b..cdf375556614 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
@@ -31,6 +31,7 @@ Required properties (all function blocks):
 	"mediatek,<chip>-disp-ovl-2l"           - overlay (2 layers, blending, csc)
 	"mediatek,<chip>-disp-rdma"  		- read DMA / line buffer
 	"mediatek,<chip>-disp-wdma"  		- write DMA
+	"mediatek,<chip>-disp-ccorr"            - color correction
 	"mediatek,<chip>-disp-color" 		- color processor
 	"mediatek,<chip>-disp-aal"   		- adaptive ambient light controller
 	"mediatek,<chip>-disp-gamma" 		- gamma correction
-- 
cgit v1.2.3


From 4df74719066788fb9ae9cf5385df02893b46bbbe Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:26 +0800
Subject: dt-bindings: mediatek: add dither description for mt8183 display

Update device tree binding documention for the display subsystem for
Mediatek MT8183 SOCs

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Reviewed-by: Rob Herring <robh at kernel.org>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
index cdf375556614..1c454eab5b37 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
@@ -33,6 +33,7 @@ Required properties (all function blocks):
 	"mediatek,<chip>-disp-wdma"  		- write DMA
 	"mediatek,<chip>-disp-ccorr"            - color correction
 	"mediatek,<chip>-disp-color" 		- color processor
+	"mediatek,<chip>-disp-dither"           - dither
 	"mediatek,<chip>-disp-aal"   		- adaptive ambient light controller
 	"mediatek,<chip>-disp-gamma" 		- gamma correction
 	"mediatek,<chip>-disp-merge" 		- merge streams from two RDMA sources
-- 
cgit v1.2.3


From 41ee3b815a35afec8f03a3c7f3e5cf462725db62 Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:27 +0800
Subject: dt-bindings: mediatek: add mutex description for mt8183 display

This patch add mutex description for mt8183 display

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
index 1c454eab5b37..b91e709db7a4 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
@@ -52,6 +52,7 @@ Required properties (all function blocks):
   For most function blocks this is just a single clock input. Only the DSI and
   DPI controller nodes have multiple clock inputs. These are documented in
   mediatek,dsi.txt and mediatek,dpi.txt, respectively.
+  An exception is that the mt8183 mutex is always free running with no clocks property.
 
 Required properties (DMA function blocks):
 - compatible: Should be one of
-- 
cgit v1.2.3


From df8fed831cbcdce7b283b2d9c1aadadcf8940d05 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 4 Oct 2019 18:41:30 +0000
Subject: mtd: rawnand: au1550nd: Fix au_read_buf16() prototype

Commit 7e534323c416 ("mtd: rawnand: Pass a nand_chip object to
chip->read_xxx() hooks") modified the prototype of the struct nand_chip
read_buf function pointer. In the au1550nd driver we have 2
implementations of read_buf. The previously mentioned commit modified
the au_read_buf() implementation to match the function pointer, but not
au_read_buf16(). This results in a compiler warning for MIPS
db1xxx_defconfig builds:

  drivers/mtd/nand/raw/au1550nd.c:443:57:
    warning: pointer type mismatch in conditional expression

Fix this by updating the prototype of au_read_buf16() to take a struct
nand_chip pointer as its first argument, as is expected after commit
7e534323c416 ("mtd: rawnand: Pass a nand_chip object to chip->read_xxx()
hooks").

Note that this shouldn't have caused any functional issues at runtime,
since the offset of the struct mtd_info within struct nand_chip is 0
making mtd_to_nand() effectively a type-cast.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Fixes: 7e534323c416 ("mtd: rawnand: Pass a nand_chip object to chip->read_xxx() hooks")
Cc: stable@vger.kernel.org # v4.20+
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/au1550nd.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c
index 97a97a9ccc36..e10b76089048 100644
--- a/drivers/mtd/nand/raw/au1550nd.c
+++ b/drivers/mtd/nand/raw/au1550nd.c
@@ -134,16 +134,15 @@ static void au_write_buf16(struct nand_chip *this, const u_char *buf, int len)
 
 /**
  * au_read_buf16 -  read chip data into buffer
- * @mtd:	MTD device structure
+ * @this:	NAND chip object
  * @buf:	buffer to store date
  * @len:	number of bytes to read
  *
  * read function for 16bit buswidth
  */
-static void au_read_buf16(struct mtd_info *mtd, u_char *buf, int len)
+static void au_read_buf16(struct nand_chip *this, u_char *buf, int len)
 {
 	int i;
-	struct nand_chip *this = mtd_to_nand(mtd);
 	u16 *p = (u16 *) buf;
 	len >>= 1;
 
-- 
cgit v1.2.3


From c48fc11b69e95007109206311b0187a3090591f3 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 7 Oct 2019 10:58:28 +0100
Subject: rxrpc: Fix call ref leak

When sendmsg() finds a call to continue on with, if the call is in an
inappropriate state, it doesn't release the ref it just got on that call
before returning an error.

This causes the following symptom to show up with kasan:

	BUG: KASAN: use-after-free in rxrpc_send_keepalive+0x8a2/0x940
	net/rxrpc/output.c:635
	Read of size 8 at addr ffff888064219698 by task kworker/0:3/11077

where line 635 is:

	whdr.epoch	= htonl(peer->local->rxnet->epoch);

The local endpoint (which cannot be pinned by the call) has been released,
but not the peer (which is pinned by the call).

Fix this by releasing the call in the error path.

Fixes: 37411cad633f ("rxrpc: Fix potential NULL-pointer exception")
Reported-by: syzbot+d850c266e3df14da1d31@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/sendmsg.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 6a1547b270fe..22f51a7e356e 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -661,6 +661,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
 		case RXRPC_CALL_SERVER_PREALLOC:
 		case RXRPC_CALL_SERVER_SECURING:
 		case RXRPC_CALL_SERVER_ACCEPTING:
+			rxrpc_put_call(call, rxrpc_call_put);
 			ret = -EBUSY;
 			goto error_release_sock;
 		default:
-- 
cgit v1.2.3


From 55f6c98e3674ce16038a1949c3f9ca5a9a99f289 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 7 Oct 2019 10:58:29 +0100
Subject: rxrpc: Fix trace-after-put looking at the put peer record

rxrpc_put_peer() calls trace_rxrpc_peer() after it has done the decrement
of the refcount - which looks at the debug_id in the peer record.  But
unless the refcount was reduced to zero, we no longer have the right to
look in the record and, indeed, it may be deleted by some other thread.

Fix this by getting the debug_id out before decrementing the refcount and
then passing that into the tracepoint.

This can cause the following symptoms:

    BUG: KASAN: use-after-free in __rxrpc_put_peer net/rxrpc/peer_object.c:411
    [inline]
    BUG: KASAN: use-after-free in rxrpc_put_peer+0x685/0x6a0
    net/rxrpc/peer_object.c:435
    Read of size 8 at addr ffff888097ec0058 by task syz-executor823/24216

Fixes: 1159d4b496f5 ("rxrpc: Add a tracepoint to track rxrpc_peer refcounting")
Reported-by: syzbot+b9be979c55f2bea8ed30@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/trace/events/rxrpc.h |  6 +++---
 net/rxrpc/peer_object.c      | 11 +++++++----
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index edc5c887a44c..45556fe771c3 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -519,10 +519,10 @@ TRACE_EVENT(rxrpc_local,
 	    );
 
 TRACE_EVENT(rxrpc_peer,
-	    TP_PROTO(struct rxrpc_peer *peer, enum rxrpc_peer_trace op,
+	    TP_PROTO(unsigned int peer_debug_id, enum rxrpc_peer_trace op,
 		     int usage, const void *where),
 
-	    TP_ARGS(peer, op, usage, where),
+	    TP_ARGS(peer_debug_id, op, usage, where),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,	peer		)
@@ -532,7 +532,7 @@ TRACE_EVENT(rxrpc_peer,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->peer = peer->debug_id;
+		    __entry->peer = peer_debug_id;
 		    __entry->op = op;
 		    __entry->usage = usage;
 		    __entry->where = where;
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 9c3ac96f71cb..b700b7ecaa3d 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -382,7 +382,7 @@ struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer)
 	int n;
 
 	n = atomic_inc_return(&peer->usage);
-	trace_rxrpc_peer(peer, rxrpc_peer_got, n, here);
+	trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n, here);
 	return peer;
 }
 
@@ -396,7 +396,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
 	if (peer) {
 		int n = atomic_fetch_add_unless(&peer->usage, 1, 0);
 		if (n > 0)
-			trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here);
+			trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n + 1, here);
 		else
 			peer = NULL;
 	}
@@ -426,11 +426,13 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer)
 void rxrpc_put_peer(struct rxrpc_peer *peer)
 {
 	const void *here = __builtin_return_address(0);
+	unsigned int debug_id;
 	int n;
 
 	if (peer) {
+		debug_id = peer->debug_id;
 		n = atomic_dec_return(&peer->usage);
-		trace_rxrpc_peer(peer, rxrpc_peer_put, n, here);
+		trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here);
 		if (n == 0)
 			__rxrpc_put_peer(peer);
 	}
@@ -443,10 +445,11 @@ void rxrpc_put_peer(struct rxrpc_peer *peer)
 void rxrpc_put_peer_locked(struct rxrpc_peer *peer)
 {
 	const void *here = __builtin_return_address(0);
+	unsigned int debug_id = peer->debug_id;
 	int n;
 
 	n = atomic_dec_return(&peer->usage);
-	trace_rxrpc_peer(peer, rxrpc_peer_put, n, here);
+	trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here);
 	if (n == 0) {
 		hash_del_rcu(&peer->hash_link);
 		list_del_init(&peer->keepalive_link);
-- 
cgit v1.2.3


From 4c1295dccc0afe0905b6ca4c62ade7f2406f2cfb Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 7 Oct 2019 10:58:29 +0100
Subject: rxrpc: Fix trace-after-put looking at the put connection record

rxrpc_put_*conn() calls trace_rxrpc_conn() after they have done the
decrement of the refcount - which looks at the debug_id in the connection
record.  But unless the refcount was reduced to zero, we no longer have the
right to look in the record and, indeed, it may be deleted by some other
thread.

Fix this by getting the debug_id out before decrementing the refcount and
then passing that into the tracepoint.

Fixes: 363deeab6d0f ("rxrpc: Add connection tracepoint and client conn state tracepoint")
Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/trace/events/rxrpc.h |  6 +++---
 net/rxrpc/call_accept.c      |  2 +-
 net/rxrpc/conn_client.c      |  6 ++++--
 net/rxrpc/conn_object.c      | 13 +++++++------
 net/rxrpc/conn_service.c     |  2 +-
 5 files changed, 16 insertions(+), 13 deletions(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 45556fe771c3..38a97e890cb6 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -546,10 +546,10 @@ TRACE_EVENT(rxrpc_peer,
 	    );
 
 TRACE_EVENT(rxrpc_conn,
-	    TP_PROTO(struct rxrpc_connection *conn, enum rxrpc_conn_trace op,
+	    TP_PROTO(unsigned int conn_debug_id, enum rxrpc_conn_trace op,
 		     int usage, const void *where),
 
-	    TP_ARGS(conn, op, usage, where),
+	    TP_ARGS(conn_debug_id, op, usage, where),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,	conn		)
@@ -559,7 +559,7 @@ TRACE_EVENT(rxrpc_conn,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->conn = conn->debug_id;
+		    __entry->conn = conn_debug_id;
 		    __entry->op = op;
 		    __entry->usage = usage;
 		    __entry->where = where;
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 00c095d74145..c1b1b7dd2924 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -84,7 +84,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 		smp_store_release(&b->conn_backlog_head,
 				  (head + 1) & (size - 1));
 
-		trace_rxrpc_conn(conn, rxrpc_conn_new_service,
+		trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service,
 				 atomic_read(&conn->usage), here);
 	}
 
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 3f1da1b49f69..700eb77173fc 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -212,7 +212,8 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp)
 	rxrpc_get_local(conn->params.local);
 	key_get(conn->params.key);
 
-	trace_rxrpc_conn(conn, rxrpc_conn_new_client, atomic_read(&conn->usage),
+	trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client,
+			 atomic_read(&conn->usage),
 			 __builtin_return_address(0));
 	trace_rxrpc_client(conn, -1, rxrpc_client_alloc);
 	_leave(" = %p", conn);
@@ -985,11 +986,12 @@ rxrpc_put_one_client_conn(struct rxrpc_connection *conn)
 void rxrpc_put_client_conn(struct rxrpc_connection *conn)
 {
 	const void *here = __builtin_return_address(0);
+	unsigned int debug_id = conn->debug_id;
 	int n;
 
 	do {
 		n = atomic_dec_return(&conn->usage);
-		trace_rxrpc_conn(conn, rxrpc_conn_put_client, n, here);
+		trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here);
 		if (n > 0)
 			return;
 		ASSERTCMP(n, >=, 0);
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index ed05b6922132..38d718e90dc6 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -269,7 +269,7 @@ bool rxrpc_queue_conn(struct rxrpc_connection *conn)
 	if (n == 0)
 		return false;
 	if (rxrpc_queue_work(&conn->processor))
-		trace_rxrpc_conn(conn, rxrpc_conn_queued, n + 1, here);
+		trace_rxrpc_conn(conn->debug_id, rxrpc_conn_queued, n + 1, here);
 	else
 		rxrpc_put_connection(conn);
 	return true;
@@ -284,7 +284,7 @@ void rxrpc_see_connection(struct rxrpc_connection *conn)
 	if (conn) {
 		int n = atomic_read(&conn->usage);
 
-		trace_rxrpc_conn(conn, rxrpc_conn_seen, n, here);
+		trace_rxrpc_conn(conn->debug_id, rxrpc_conn_seen, n, here);
 	}
 }
 
@@ -296,7 +296,7 @@ void rxrpc_get_connection(struct rxrpc_connection *conn)
 	const void *here = __builtin_return_address(0);
 	int n = atomic_inc_return(&conn->usage);
 
-	trace_rxrpc_conn(conn, rxrpc_conn_got, n, here);
+	trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n, here);
 }
 
 /*
@@ -310,7 +310,7 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn)
 	if (conn) {
 		int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
 		if (n > 0)
-			trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here);
+			trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n + 1, here);
 		else
 			conn = NULL;
 	}
@@ -333,10 +333,11 @@ static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet,
 void rxrpc_put_service_conn(struct rxrpc_connection *conn)
 {
 	const void *here = __builtin_return_address(0);
+	unsigned int debug_id = conn->debug_id;
 	int n;
 
 	n = atomic_dec_return(&conn->usage);
-	trace_rxrpc_conn(conn, rxrpc_conn_put_service, n, here);
+	trace_rxrpc_conn(debug_id, rxrpc_conn_put_service, n, here);
 	ASSERTCMP(n, >=, 0);
 	if (n == 1)
 		rxrpc_set_service_reap_timer(conn->params.local->rxnet,
@@ -420,7 +421,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work)
 		 */
 		if (atomic_cmpxchg(&conn->usage, 1, 0) != 1)
 			continue;
-		trace_rxrpc_conn(conn, rxrpc_conn_reap_service, 0, NULL);
+		trace_rxrpc_conn(conn->debug_id, rxrpc_conn_reap_service, 0, NULL);
 
 		if (rxrpc_conn_is_client(conn))
 			BUG();
diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c
index b30e13f6d95f..123d6ceab15c 100644
--- a/net/rxrpc/conn_service.c
+++ b/net/rxrpc/conn_service.c
@@ -134,7 +134,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn
 		list_add_tail(&conn->proc_link, &rxnet->conn_proc_list);
 		write_unlock(&rxnet->conn_lock);
 
-		trace_rxrpc_conn(conn, rxrpc_conn_new_service,
+		trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service,
 				 atomic_read(&conn->usage),
 				 __builtin_return_address(0));
 	}
-- 
cgit v1.2.3


From 48c9e0ec7cbbb7370448f859ccc8e3b7eb69e755 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 7 Oct 2019 10:58:29 +0100
Subject: rxrpc: Fix trace-after-put looking at the put call record

rxrpc_put_call() calls trace_rxrpc_call() after it has done the decrement
of the refcount - which looks at the debug_id in the call record.  But
unless the refcount was reduced to zero, we no longer have the right to
look in the record and, indeed, it may be deleted by some other thread.

Fix this by getting the debug_id out before decrementing the refcount and
then passing that into the tracepoint.

Fixes: e34d4234b0b7 ("rxrpc: Trace rxrpc_call usage")
Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/trace/events/rxrpc.h |  6 +++---
 net/rxrpc/call_accept.c      |  2 +-
 net/rxrpc/call_object.c      | 28 +++++++++++++++++-----------
 3 files changed, 21 insertions(+), 15 deletions(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 38a97e890cb6..191fe447f990 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -606,10 +606,10 @@ TRACE_EVENT(rxrpc_client,
 	    );
 
 TRACE_EVENT(rxrpc_call,
-	    TP_PROTO(struct rxrpc_call *call, enum rxrpc_call_trace op,
+	    TP_PROTO(unsigned int call_debug_id, enum rxrpc_call_trace op,
 		     int usage, const void *where, const void *aux),
 
-	    TP_ARGS(call, op, usage, where, aux),
+	    TP_ARGS(call_debug_id, op, usage, where, aux),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		call		)
@@ -620,7 +620,7 @@ TRACE_EVENT(rxrpc_call,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call->debug_id;
+		    __entry->call = call_debug_id;
 		    __entry->op = op;
 		    __entry->usage = usage;
 		    __entry->where = where;
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index c1b1b7dd2924..1f778102ed8d 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -97,7 +97,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
 	call->flags |= (1 << RXRPC_CALL_IS_SERVICE);
 	call->state = RXRPC_CALL_SERVER_PREALLOC;
 
-	trace_rxrpc_call(call, rxrpc_call_new_service,
+	trace_rxrpc_call(call->debug_id, rxrpc_call_new_service,
 			 atomic_read(&call->usage),
 			 here, (const void *)user_call_ID);
 
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 32d8dc677142..6dace078971a 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -240,7 +240,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	if (p->intr)
 		__set_bit(RXRPC_CALL_IS_INTR, &call->flags);
 	call->tx_total_len = p->tx_total_len;
-	trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage),
+	trace_rxrpc_call(call->debug_id, rxrpc_call_new_client,
+			 atomic_read(&call->usage),
 			 here, (const void *)p->user_call_ID);
 
 	/* We need to protect a partially set up call against the user as we
@@ -290,8 +291,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	if (ret < 0)
 		goto error;
 
-	trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage),
-			 here, NULL);
+	trace_rxrpc_call(call->debug_id, rxrpc_call_connected,
+			 atomic_read(&call->usage), here, NULL);
 
 	rxrpc_start_call_timer(call);
 
@@ -313,8 +314,8 @@ error_dup_user_ID:
 error:
 	__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
 				    RX_CALL_DEAD, ret);
-	trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage),
-			 here, ERR_PTR(ret));
+	trace_rxrpc_call(call->debug_id, rxrpc_call_error,
+			 atomic_read(&call->usage), here, ERR_PTR(ret));
 	rxrpc_release_call(rx, call);
 	mutex_unlock(&call->user_mutex);
 	rxrpc_put_call(call, rxrpc_call_put);
@@ -376,7 +377,8 @@ bool rxrpc_queue_call(struct rxrpc_call *call)
 	if (n == 0)
 		return false;
 	if (rxrpc_queue_work(&call->processor))
-		trace_rxrpc_call(call, rxrpc_call_queued, n + 1, here, NULL);
+		trace_rxrpc_call(call->debug_id, rxrpc_call_queued, n + 1,
+				 here, NULL);
 	else
 		rxrpc_put_call(call, rxrpc_call_put_noqueue);
 	return true;
@@ -391,7 +393,8 @@ bool __rxrpc_queue_call(struct rxrpc_call *call)
 	int n = atomic_read(&call->usage);
 	ASSERTCMP(n, >=, 1);
 	if (rxrpc_queue_work(&call->processor))
-		trace_rxrpc_call(call, rxrpc_call_queued_ref, n, here, NULL);
+		trace_rxrpc_call(call->debug_id, rxrpc_call_queued_ref, n,
+				 here, NULL);
 	else
 		rxrpc_put_call(call, rxrpc_call_put_noqueue);
 	return true;
@@ -406,7 +409,8 @@ void rxrpc_see_call(struct rxrpc_call *call)
 	if (call) {
 		int n = atomic_read(&call->usage);
 
-		trace_rxrpc_call(call, rxrpc_call_seen, n, here, NULL);
+		trace_rxrpc_call(call->debug_id, rxrpc_call_seen, n,
+				 here, NULL);
 	}
 }
 
@@ -418,7 +422,7 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
 	const void *here = __builtin_return_address(0);
 	int n = atomic_inc_return(&call->usage);
 
-	trace_rxrpc_call(call, op, n, here, NULL);
+	trace_rxrpc_call(call->debug_id, op, n, here, NULL);
 }
 
 /*
@@ -445,7 +449,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
 
 	_enter("{%d,%d}", call->debug_id, atomic_read(&call->usage));
 
-	trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage),
+	trace_rxrpc_call(call->debug_id, rxrpc_call_release,
+			 atomic_read(&call->usage),
 			 here, (const void *)call->flags);
 
 	ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
@@ -534,12 +539,13 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
 {
 	struct rxrpc_net *rxnet = call->rxnet;
 	const void *here = __builtin_return_address(0);
+	unsigned int debug_id = call->debug_id;
 	int n;
 
 	ASSERT(call != NULL);
 
 	n = atomic_dec_return(&call->usage);
-	trace_rxrpc_call(call, op, n, here, NULL);
+	trace_rxrpc_call(debug_id, op, n, here, NULL);
 	ASSERTCMP(n, >=, 0);
 	if (n == 0) {
 		_debug("call %d dead", call->debug_id);
-- 
cgit v1.2.3


From 9ebeddef58c41bd700419cdcece24cf64ce32276 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 7 Oct 2019 10:58:29 +0100
Subject: rxrpc: rxrpc_peer needs to hold a ref on the rxrpc_local record

The rxrpc_peer record needs to hold a reference on the rxrpc_local record
it points as the peer is used as a base to access information in the
rxrpc_local record.

This can cause problems in __rxrpc_put_peer(), where we need the network
namespace pointer, and in rxrpc_send_keepalive(), where we need to access
the UDP socket, leading to symptoms like:

    BUG: KASAN: use-after-free in __rxrpc_put_peer net/rxrpc/peer_object.c:411
    [inline]
    BUG: KASAN: use-after-free in rxrpc_put_peer+0x685/0x6a0
    net/rxrpc/peer_object.c:435
    Read of size 8 at addr ffff888097ec0058 by task syz-executor823/24216

Fix this by taking a ref on the local record for the peer record.

Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive")
Fixes: 2baec2c3f854 ("rxrpc: Support network namespacing")
Reported-by: syzbot+b9be979c55f2bea8ed30@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/peer_object.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index b700b7ecaa3d..64830d8c1fdb 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -216,7 +216,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
 	peer = kzalloc(sizeof(struct rxrpc_peer), gfp);
 	if (peer) {
 		atomic_set(&peer->usage, 1);
-		peer->local = local;
+		peer->local = rxrpc_get_local(local);
 		INIT_HLIST_HEAD(&peer->error_targets);
 		peer->service_conns = RB_ROOT;
 		seqlock_init(&peer->service_conn_lock);
@@ -307,7 +307,6 @@ void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local,
 	unsigned long hash_key;
 
 	hash_key = rxrpc_peer_hash_key(local, &peer->srx);
-	peer->local = local;
 	rxrpc_init_peer(rx, peer, hash_key);
 
 	spin_lock(&rxnet->peer_hash_lock);
@@ -417,6 +416,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer)
 	list_del_init(&peer->keepalive_link);
 	spin_unlock_bh(&rxnet->peer_hash_lock);
 
+	rxrpc_put_local(peer->local);
 	kfree_rcu(peer, rcu);
 }
 
@@ -453,6 +453,7 @@ void rxrpc_put_peer_locked(struct rxrpc_peer *peer)
 	if (n == 0) {
 		hash_del_rcu(&peer->hash_link);
 		list_del_init(&peer->keepalive_link);
+		rxrpc_put_local(peer->local);
 		kfree_rcu(peer, rcu);
 	}
 }
-- 
cgit v1.2.3


From 91fcfbe8852edb929ff8702534525031a15d0aa6 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 7 Oct 2019 10:58:29 +0100
Subject: rxrpc: Fix call crypto state cleanup

Fix the cleanup of the crypto state on a call after the call has been
disconnected.  As the call has been disconnected, its connection ref has
been discarded and so we can't go through that to get to the security ops
table.

Fix this by caching the security ops pointer in the rxrpc_call struct and
using that when freeing the call security state.  Also use this in other
places we're dealing with call-specific security.

The symptoms look like:

    BUG: KASAN: use-after-free in rxrpc_release_call+0xb2d/0xb60
    net/rxrpc/call_object.c:481
    Read of size 8 at addr ffff888062ffeb50 by task syz-executor.5/4764

Fixes: 1db88c534371 ("rxrpc: Fix -Wframe-larger-than= warnings from on-stack crypto")
Reported-by: syzbot+eed305768ece6682bb7f@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/ar-internal.h | 1 +
 net/rxrpc/call_accept.c | 1 +
 net/rxrpc/call_object.c | 6 +++---
 net/rxrpc/conn_client.c | 3 +++
 net/rxrpc/recvmsg.c     | 6 +++---
 net/rxrpc/sendmsg.c     | 2 +-
 6 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 1091bf35a199..ecc17dabec8f 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -556,6 +556,7 @@ struct rxrpc_call {
 	struct rxrpc_peer	*peer;		/* Peer record for remote address */
 	struct rxrpc_sock __rcu	*socket;	/* socket responsible */
 	struct rxrpc_net	*rxnet;		/* Network namespace to which call belongs */
+	const struct rxrpc_security *security;	/* applied security module */
 	struct mutex		user_mutex;	/* User access mutex */
 	unsigned long		ack_at;		/* When deferred ACK needs to happen */
 	unsigned long		ack_lost_at;	/* When ACK is figured as lost */
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 1f778102ed8d..135bf5cd8dd5 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -307,6 +307,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
 
 	rxrpc_see_call(call);
 	call->conn = conn;
+	call->security = conn->security;
 	call->peer = rxrpc_get_peer(conn->params.peer);
 	call->cong_cwnd = call->peer->cong_cwnd;
 	return call;
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 6dace078971a..a31c18c09894 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -493,10 +493,10 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
 
 	_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
 
-	if (conn) {
+	if (conn)
 		rxrpc_disconnect_call(call);
-		conn->security->free_call_crypto(call);
-	}
+	if (call->security)
+		call->security->free_call_crypto(call);
 
 	rxrpc_cleanup_ring(call);
 	_leave("");
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 700eb77173fc..376370cd9285 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -353,6 +353,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx,
 
 	if (cp->exclusive) {
 		call->conn = candidate;
+		call->security = candidate->security;
 		call->security_ix = candidate->security_ix;
 		call->service_id = candidate->service_id;
 		_leave(" = 0 [exclusive %d]", candidate->debug_id);
@@ -404,6 +405,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx,
 candidate_published:
 	set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags);
 	call->conn = candidate;
+	call->security = candidate->security;
 	call->security_ix = candidate->security_ix;
 	call->service_id = candidate->service_id;
 	spin_unlock(&local->client_conns_lock);
@@ -426,6 +428,7 @@ found_extant_conn:
 
 	spin_lock(&conn->channel_lock);
 	call->conn = conn;
+	call->security = conn->security;
 	call->security_ix = conn->security_ix;
 	call->service_id = conn->service_id;
 	list_add_tail(&call->chan_wait_link, &conn->waiting_calls);
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 3b0becb12041..a4090797c9b2 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -251,8 +251,8 @@ static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
 		seq += subpacket;
 	}
 
-	return call->conn->security->verify_packet(call, skb, offset, len,
-						   seq, cksum);
+	return call->security->verify_packet(call, skb, offset, len,
+					     seq, cksum);
 }
 
 /*
@@ -291,7 +291,7 @@ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb,
 
 	*_offset = offset;
 	*_len = len;
-	call->conn->security->locate_data(call, skb, _offset, _len);
+	call->security->locate_data(call, skb, _offset, _len);
 	return 0;
 }
 
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 22f51a7e356e..813fd6888142 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -419,7 +419,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 				 call->tx_winsize)
 				sp->hdr.flags |= RXRPC_MORE_PACKETS;
 
-			ret = conn->security->secure_packet(
+			ret = call->security->secure_packet(
 				call, skb, skb->mark, skb->head);
 			if (ret < 0)
 				goto out;
-- 
cgit v1.2.3


From 308c51561720547a90767a2f367f5390052c51da Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Fri, 4 Oct 2019 14:58:47 +0100
Subject: arm64: mm: fix spurious fault detection

When detecting a spurious EL1 translation fault, we attempt to compare
ESR_EL1.DFSC with PAR_EL1.FST. We erroneously use FIELD_PREP() to
extract PAR_EL1.FST, when we should be using FIELD_GET().

In the wise words of Robin Murphy:

| FIELD_GET() is a UBFX, FIELD_PREP() is a BFI

Using FIELD_PREP() means that that dfsc & ESR_ELx_FSC_TYPE is always
zero, and hence not equal to ESR_ELx_FSC_FAULT. Thus we detect any
unhandled translation fault as spurious.

... so let's use FIELD_GET() to ensure we don't decide all translation
faults are spurious. ESR_EL1.DFSC occupies bits [5:0], and requires no
shifting.

Fixes: 42f91093b043332a ("arm64: mm: Ignore spurious translation faults taken from the kernel")
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reported-by: Robin Murphy <robin.murphy@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Will Deacon <will.deacon@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/fault.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 6acd866f31fd..855f2a7954e6 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -275,7 +275,7 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr,
 	 * If we got a different type of fault from the AT instruction,
 	 * treat the translation fault as spurious.
 	 */
-	dfsc = FIELD_PREP(SYS_PAR_EL1_FST, par);
+	dfsc = FIELD_GET(SYS_PAR_EL1_FST, par);
 	return (dfsc & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT;
 }
 
-- 
cgit v1.2.3


From e0de01aafc3dd7b73308106b056ead2d48391905 Mon Sep 17 00:00:00 2001
From: Vincenzo Frascino <vincenzo.frascino@arm.com>
Date: Thu, 3 Oct 2019 18:48:33 +0100
Subject: arm64: vdso32: Fix broken compat vDSO build warnings

The .config file and the generated include/config/auto.conf can
end up out of sync after a set of commands since
CONFIG_CROSS_COMPILE_COMPAT_VDSO is not updated correctly.

The sequence can be reproduced as follows:

$ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- defconfig
[...]
$ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- menuconfig
[set CONFIG_CROSS_COMPILE_COMPAT_VDSO="arm-linux-gnueabihf-"]
$ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu-

Which results in:

arch/arm64/Makefile:62: CROSS_COMPILE_COMPAT not defined or empty,
the compat vDSO will not be built

even though the compat vDSO has been built:

$ file arch/arm64/kernel/vdso32/vdso.so
arch/arm64/kernel/vdso32/vdso.so: ELF 32-bit LSB pie executable, ARM,
EABI5 version 1 (SYSV), dynamically linked,
BuildID[sha1]=c67f6c786f2d2d6f86c71f708595594aa25247f6, stripped

A similar case that involves changing the configuration parameter
multiple times can be reconducted to the same family of problems.

Remove the use of CONFIG_CROSS_COMPILE_COMPAT_VDSO altogether and
instead rely on the cross-compiler prefix coming from the environment
via CROSS_COMPILE_COMPAT, much like we do for the rest of the kernel.

Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: Will Deacon <will@kernel.org>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig                |  2 +-
 arch/arm64/Makefile               | 18 +++++-------------
 arch/arm64/kernel/vdso32/Makefile |  2 --
 3 files changed, 6 insertions(+), 16 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 41a9b4257b72..ba12b3a11e55 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -110,7 +110,7 @@ config ARM64
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_GETTIMEOFDAY
-	select GENERIC_COMPAT_VDSO if (!CPU_BIG_ENDIAN && COMPAT)
+	select GENERIC_COMPAT_VDSO if (!CPU_BIG_ENDIAN && COMPAT && "$(CROSS_COMPILE_COMPAT)" != "")
 	select HANDLE_DOMAIN_IRQ
 	select HARDIRQS_SW_RESEND
 	select HAVE_PCI
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 84a3d502c5a5..dfa6a5cb99e4 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -53,20 +53,12 @@ $(warning Detected assembler with broken .inst; disassembly will be unreliable)
   endif
 endif
 
+COMPATCC ?= $(CROSS_COMPILE_COMPAT)gcc
+export COMPATCC
+
 ifeq ($(CONFIG_GENERIC_COMPAT_VDSO), y)
-  CROSS_COMPILE_COMPAT ?= $(CONFIG_CROSS_COMPILE_COMPAT_VDSO:"%"=%)
-
-  ifeq ($(CONFIG_CC_IS_CLANG), y)
-    $(warning CROSS_COMPILE_COMPAT is clang, the compat vDSO will not be built)
-  else ifeq ($(strip $(CROSS_COMPILE_COMPAT)),)
-    $(warning CROSS_COMPILE_COMPAT not defined or empty, the compat vDSO will not be built)
-  else ifeq ($(shell which $(CROSS_COMPILE_COMPAT)gcc 2> /dev/null),)
-    $(error $(CROSS_COMPILE_COMPAT)gcc not found, check CROSS_COMPILE_COMPAT)
-  else
-    export CROSS_COMPILE_COMPAT
-    export CONFIG_COMPAT_VDSO := y
-    compat_vdso := -DCONFIG_COMPAT_VDSO=1
-  endif
+  export CONFIG_COMPAT_VDSO := y
+  compat_vdso := -DCONFIG_COMPAT_VDSO=1
 endif
 
 KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr) $(brokengasinst)	\
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 1fba0776ed40..19e0d3115ffe 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -8,8 +8,6 @@
 ARCH_REL_TYPE_ABS := R_ARM_JUMP_SLOT|R_ARM_GLOB_DAT|R_ARM_ABS32
 include $(srctree)/lib/vdso/Makefile
 
-COMPATCC := $(CROSS_COMPILE_COMPAT)gcc
-
 # Same as cc-*option, but using COMPATCC instead of CC
 cc32-option = $(call try-run,\
         $(COMPATCC) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
-- 
cgit v1.2.3


From 37a5076098c17f40913c772b017ff8e48e449656 Mon Sep 17 00:00:00 2001
From: Vincenzo Frascino <vincenzo.frascino@arm.com>
Date: Thu, 3 Oct 2019 18:48:35 +0100
Subject: arm64: vdso: Remove stale files from old assembly implementation

Moving over to the generic C implementation of the vDSO inadvertently
left some stale files behind which are no longer used. Remove them.

Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/vdso_datapage.h | 33 ---------------------------------
 arch/arm64/kernel/vdso/gettimeofday.S  |  0
 2 files changed, 33 deletions(-)
 delete mode 100644 arch/arm64/include/asm/vdso_datapage.h
 delete mode 100644 arch/arm64/kernel/vdso/gettimeofday.S

diff --git a/arch/arm64/include/asm/vdso_datapage.h b/arch/arm64/include/asm/vdso_datapage.h
deleted file mode 100644
index 1f38bf330a6e..000000000000
--- a/arch/arm64/include/asm/vdso_datapage.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2012 ARM Limited
- */
-#ifndef __ASM_VDSO_DATAPAGE_H
-#define __ASM_VDSO_DATAPAGE_H
-
-#ifndef __ASSEMBLY__
-
-struct vdso_data {
-	__u64 cs_cycle_last;	/* Timebase at clocksource init */
-	__u64 raw_time_sec;	/* Raw time */
-	__u64 raw_time_nsec;
-	__u64 xtime_clock_sec;	/* Kernel time */
-	__u64 xtime_clock_nsec;
-	__u64 xtime_coarse_sec;	/* Coarse time */
-	__u64 xtime_coarse_nsec;
-	__u64 wtm_clock_sec;	/* Wall to monotonic time */
-	__u64 wtm_clock_nsec;
-	__u32 tb_seq_count;	/* Timebase sequence counter */
-	/* cs_* members must be adjacent and in this order (ldp accesses) */
-	__u32 cs_mono_mult;	/* NTP-adjusted clocksource multiplier */
-	__u32 cs_shift;		/* Clocksource shift (mono = raw) */
-	__u32 cs_raw_mult;	/* Raw clocksource multiplier */
-	__u32 tz_minuteswest;	/* Whacky timezone stuff */
-	__u32 tz_dsttime;
-	__u32 use_syscall;
-	__u32 hrtimer_res;
-};
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __ASM_VDSO_DATAPAGE_H */
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
deleted file mode 100644
index e69de29bb2d1..000000000000
-- 
cgit v1.2.3


From 0df2c90eba60791148cee1823c0bf5fc66e3465c Mon Sep 17 00:00:00 2001
From: Vincenzo Frascino <vincenzo.frascino@arm.com>
Date: Thu, 3 Oct 2019 18:48:34 +0100
Subject: arm64: vdso32: Detect binutils support for dmb ishld

Older versions of binutils (prior to 2.24) do not support the "ISHLD"
option for memory barrier instructions, which leads to a build failure
when assembling the vdso32 library.

Add a compilation time mechanism that detects if binutils supports those
instructions and configure the kernel accordingly.

Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: Will Deacon <will@kernel.org>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/vdso/compat_barrier.h | 2 +-
 arch/arm64/kernel/vdso32/Makefile            | 9 +++++++++
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/vdso/compat_barrier.h b/arch/arm64/include/asm/vdso/compat_barrier.h
index fb60a88b5ed4..3fd8fd6d8fc2 100644
--- a/arch/arm64/include/asm/vdso/compat_barrier.h
+++ b/arch/arm64/include/asm/vdso/compat_barrier.h
@@ -20,7 +20,7 @@
 
 #define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory")
 
-#if __LINUX_ARM_ARCH__ >= 8
+#if __LINUX_ARM_ARCH__ >= 8 && defined(CONFIG_AS_DMB_ISHLD)
 #define aarch32_smp_mb()	dmb(ish)
 #define aarch32_smp_rmb()	dmb(ishld)
 #define aarch32_smp_wmb()	dmb(ishst)
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 19e0d3115ffe..77aa61340374 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -15,6 +15,8 @@ cc32-disable-warning = $(call try-run,\
 	$(COMPATCC) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
 cc32-ldoption = $(call try-run,\
         $(COMPATCC) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2))
+cc32-as-instr = $(call try-run,\
+	printf "%b\n" "$(1)" | $(COMPATCC) $(VDSO_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3))
 
 # We cannot use the global flags to compile the vDSO files, the main reason
 # being that the 32-bit compiler may be older than the main (64-bit) compiler
@@ -53,6 +55,7 @@ endif
 VDSO_CAFLAGS += -fPIC -fno-builtin -fno-stack-protector
 VDSO_CAFLAGS += -DDISABLE_BRANCH_PROFILING
 
+
 # Try to compile for ARMv8. If the compiler is too old and doesn't support it,
 # fall back to v7. There is no easy way to check for what architecture the code
 # is being compiled, so define a macro specifying that (see arch/arm/Makefile).
@@ -89,6 +92,12 @@ VDSO_CFLAGS += -Wno-int-to-pointer-cast
 VDSO_AFLAGS := $(VDSO_CAFLAGS)
 VDSO_AFLAGS += -D__ASSEMBLY__
 
+# Check for binutils support for dmb ishld
+dmbinstr := $(call cc32-as-instr,dmb ishld,-DCONFIG_AS_DMB_ISHLD=1)
+
+VDSO_CFLAGS += $(dmbinstr)
+VDSO_AFLAGS += $(dmbinstr)
+
 VDSO_LDFLAGS := $(VDSO_CPPFLAGS)
 # From arm vDSO Makefile
 VDSO_LDFLAGS += -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1
-- 
cgit v1.2.3


From a7f93103f86e2bbc5646831707d2fa565315004d Mon Sep 17 00:00:00 2001
From: Vincenzo Frascino <vincenzo.frascino@arm.com>
Date: Thu, 3 Oct 2019 18:48:36 +0100
Subject: arm64: vdso32: Remove jump label config option in Makefile

The jump labels are not used in vdso32 since it is not possible to run
runtime patching on them.

Remove the configuration option from the Makefile.

Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/vdso32/Makefile | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 77aa61340374..038357a1e835 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -38,9 +38,6 @@ VDSO_CAFLAGS += $(call cc32-option,-fno-PIE)
 ifdef CONFIG_DEBUG_INFO
 VDSO_CAFLAGS += -g
 endif
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(COMPATCC)), y)
-VDSO_CAFLAGS += -DCC_HAVE_ASM_GOTO
-endif
 
 # From arm Makefile
 VDSO_CAFLAGS += $(call cc32-option,-fno-dwarf2-cfi-asm)
-- 
cgit v1.2.3


From 50a2610adec9d796b25e262734edb56ef324ce15 Mon Sep 17 00:00:00 2001
From: Vincenzo Frascino <vincenzo.frascino@arm.com>
Date: Thu, 3 Oct 2019 18:48:38 +0100
Subject: lib: vdso: Remove CROSS_COMPILE_COMPAT_VDSO

arm64 was the last architecture using CROSS_COMPILE_COMPAT_VDSO config
option. With this patch series the dependency in the architecture has
been removed.

Remove CROSS_COMPILE_COMPAT_VDSO from the Unified vDSO library code.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 lib/vdso/Kconfig | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig
index cc00364bd2c2..9fe698ff62ec 100644
--- a/lib/vdso/Kconfig
+++ b/lib/vdso/Kconfig
@@ -24,13 +24,4 @@ config GENERIC_COMPAT_VDSO
 	help
 	  This config option enables the compat VDSO layer.
 
-config CROSS_COMPILE_COMPAT_VDSO
-	string "32 bit Toolchain prefix for compat vDSO"
-	default ""
-	depends on GENERIC_COMPAT_VDSO
-	help
-	  Defines the cross-compiler prefix for compiling compat vDSO.
-	  If a 64 bit compiler (i.e. x86_64) can compile the VDSO for
-	  32 bit, it does not need to define this parameter.
-
 endif
-- 
cgit v1.2.3


From 80b15db5e1e9c3300de299b2d43d1aafb593e6ac Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Fri, 4 Oct 2019 15:03:15 -0500
Subject: staging: vt6655: Fix memory leak in vt6655_probe

In vt6655_probe, if vnt_init() fails the cleanup code needs to be called
like other error handling cases. The call to device_free_info() is
added.

Fixes: 67013f2c0e58 ("staging: vt6655: mac80211 conversion add main mac80211 functions")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20191004200319.22394-1-navid.emamdoost@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/vt6655/device_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index c6bb4aaf9bd0..082302944c37 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -1748,8 +1748,10 @@ vt6655_probe(struct pci_dev *pcid, const struct pci_device_id *ent)
 
 	priv->hw->max_signal = 100;
 
-	if (vnt_init(priv))
+	if (vnt_init(priv)) {
+		device_free_info(priv);
 		return -ENODEV;
+	}
 
 	device_print_info(priv);
 	pci_set_drvdata(pcid, priv);
-- 
cgit v1.2.3


From f1da567f1dc1b55d178b8f2d0cfe8353858aac19 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sat, 5 Oct 2019 23:04:47 +0200
Subject: driver core: platform: Add platform_get_irq_byname_optional()

Some drivers (e.g dwc3) first try to get an IRQ byname and then fall
back to the one at index 0. In this case we do not want the error(s)
printed by platform_get_irq_byname(). This commit adds a new
platform_get_irq_byname_optional(), which does not print errors, for this.

While at it also improve the kdoc text for platform_get_irq_byname() a bit.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=205037
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20191005210449.3926-2-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/platform.c         | 46 ++++++++++++++++++++++++++++++++++-------
 include/linux/platform_device.h |  2 ++
 2 files changed, 41 insertions(+), 7 deletions(-)

diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index b6c6c7d97d5b..b230beb6ccb4 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -241,12 +241,8 @@ struct resource *platform_get_resource_byname(struct platform_device *dev,
 }
 EXPORT_SYMBOL_GPL(platform_get_resource_byname);
 
-/**
- * platform_get_irq_byname - get an IRQ for a device by name
- * @dev: platform device
- * @name: IRQ name
- */
-int platform_get_irq_byname(struct platform_device *dev, const char *name)
+static int __platform_get_irq_byname(struct platform_device *dev,
+				     const char *name)
 {
 	struct resource *r;
 
@@ -262,11 +258,47 @@ int platform_get_irq_byname(struct platform_device *dev, const char *name)
 	if (r)
 		return r->start;
 
-	dev_err(&dev->dev, "IRQ %s not found\n", name);
 	return -ENXIO;
 }
+
+/**
+ * platform_get_irq_byname - get an IRQ for a device by name
+ * @dev: platform device
+ * @name: IRQ name
+ *
+ * Get an IRQ like platform_get_irq(), but then by name rather then by index.
+ *
+ * Return: IRQ number on success, negative error number on failure.
+ */
+int platform_get_irq_byname(struct platform_device *dev, const char *name)
+{
+	int ret;
+
+	ret = __platform_get_irq_byname(dev, name);
+	if (ret < 0 && ret != -EPROBE_DEFER)
+		dev_err(&dev->dev, "IRQ %s not found\n", name);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(platform_get_irq_byname);
 
+/**
+ * platform_get_irq_byname_optional - get an optional IRQ for a device by name
+ * @dev: platform device
+ * @name: IRQ name
+ *
+ * Get an optional IRQ by name like platform_get_irq_byname(). Except that it
+ * does not print an error message if an IRQ can not be obtained.
+ *
+ * Return: IRQ number on success, negative error number on failure.
+ */
+int platform_get_irq_byname_optional(struct platform_device *dev,
+				     const char *name)
+{
+	return __platform_get_irq_byname(dev, name);
+}
+EXPORT_SYMBOL_GPL(platform_get_irq_byname_optional);
+
 /**
  * platform_add_devices - add a numbers of platform devices
  * @devs: array of platform devices to add
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 1b5cec067533..f2688404d1cd 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -64,6 +64,8 @@ extern struct resource *platform_get_resource_byname(struct platform_device *,
 						     unsigned int,
 						     const char *);
 extern int platform_get_irq_byname(struct platform_device *, const char *);
+extern int platform_get_irq_byname_optional(struct platform_device *dev,
+					    const char *name);
 extern int platform_add_devices(struct platform_device **, int);
 
 struct platform_device_info {
-- 
cgit v1.2.3


From f146b40ba1f0f689ca3cbd594a78b2424c459ddc Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sat, 5 Oct 2019 23:04:48 +0200
Subject: usb: dwc3: Switch to platform_get_irq_byname_optional()

The dwc3 code to get the "peripheral" / "host" / "otg" IRQ first tries
platform_get_irq_byname() and then falls back to the IRQ at index 0 if
the platform_get_irq_byname().

In this case we do not want platform_get_irq_byname() to print an error
on failure, so switch to platform_get_irq_byname_optional() instead which
does not print an error.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=205037
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Felipe Balbi <felipe.balbi@linux.intel.com>
Link: https://lore.kernel.org/r/20191005210449.3926-3-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/drd.c    | 4 ++--
 drivers/usb/dwc3/gadget.c | 4 ++--
 drivers/usb/dwc3/host.c   | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c
index 726100d1ac0d..b1f76628b313 100644
--- a/drivers/usb/dwc3/drd.c
+++ b/drivers/usb/dwc3/drd.c
@@ -139,14 +139,14 @@ static int dwc3_otg_get_irq(struct dwc3 *dwc)
 	struct platform_device *dwc3_pdev = to_platform_device(dwc->dev);
 	int irq;
 
-	irq = platform_get_irq_byname(dwc3_pdev, "otg");
+	irq = platform_get_irq_byname_optional(dwc3_pdev, "otg");
 	if (irq > 0)
 		goto out;
 
 	if (irq == -EPROBE_DEFER)
 		goto out;
 
-	irq = platform_get_irq_byname(dwc3_pdev, "dwc_usb3");
+	irq = platform_get_irq_byname_optional(dwc3_pdev, "dwc_usb3");
 	if (irq > 0)
 		goto out;
 
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 8adb59f8e4f1..13c97ff21dba 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -3264,14 +3264,14 @@ static int dwc3_gadget_get_irq(struct dwc3 *dwc)
 	struct platform_device *dwc3_pdev = to_platform_device(dwc->dev);
 	int irq;
 
-	irq = platform_get_irq_byname(dwc3_pdev, "peripheral");
+	irq = platform_get_irq_byname_optional(dwc3_pdev, "peripheral");
 	if (irq > 0)
 		goto out;
 
 	if (irq == -EPROBE_DEFER)
 		goto out;
 
-	irq = platform_get_irq_byname(dwc3_pdev, "dwc_usb3");
+	irq = platform_get_irq_byname_optional(dwc3_pdev, "dwc_usb3");
 	if (irq > 0)
 		goto out;
 
diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c
index 8deea8c91e03..534a49609779 100644
--- a/drivers/usb/dwc3/host.c
+++ b/drivers/usb/dwc3/host.c
@@ -16,14 +16,14 @@ static int dwc3_host_get_irq(struct dwc3 *dwc)
 	struct platform_device	*dwc3_pdev = to_platform_device(dwc->dev);
 	int irq;
 
-	irq = platform_get_irq_byname(dwc3_pdev, "host");
+	irq = platform_get_irq_byname_optional(dwc3_pdev, "host");
 	if (irq > 0)
 		goto out;
 
 	if (irq == -EPROBE_DEFER)
 		goto out;
 
-	irq = platform_get_irq_byname(dwc3_pdev, "dwc_usb3");
+	irq = platform_get_irq_byname_optional(dwc3_pdev, "dwc_usb3");
 	if (irq > 0)
 		goto out;
 
-- 
cgit v1.2.3


From d819f6584c201b7797daa33f0cff7247be14f2a8 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sat, 5 Oct 2019 23:04:49 +0200
Subject: usb: dwc3: Remove dev_err() on platform_get_irq() failure

Since commit 7723f4c5ecdb ("driver core: platform: Add an error message to
platform_get_irq*()"), platform_get_irq() will call dev_err() itself on
failure, so there is no need for the driver to also do this.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Felipe Balbi <felipe.balbi@linux.intel.com>
Link: https://lore.kernel.org/r/20191005210449.3926-4-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/drd.c    | 3 ---
 drivers/usb/dwc3/gadget.c | 3 ---
 drivers/usb/dwc3/host.c   | 3 ---
 3 files changed, 9 deletions(-)

diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c
index b1f76628b313..c946d64142ad 100644
--- a/drivers/usb/dwc3/drd.c
+++ b/drivers/usb/dwc3/drd.c
@@ -157,9 +157,6 @@ static int dwc3_otg_get_irq(struct dwc3 *dwc)
 	if (irq > 0)
 		goto out;
 
-	if (irq != -EPROBE_DEFER)
-		dev_err(dwc->dev, "missing OTG IRQ\n");
-
 	if (!irq)
 		irq = -EINVAL;
 
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 13c97ff21dba..86dc1db788a9 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -3282,9 +3282,6 @@ static int dwc3_gadget_get_irq(struct dwc3 *dwc)
 	if (irq > 0)
 		goto out;
 
-	if (irq != -EPROBE_DEFER)
-		dev_err(dwc->dev, "missing peripheral IRQ\n");
-
 	if (!irq)
 		irq = -EINVAL;
 
diff --git a/drivers/usb/dwc3/host.c b/drivers/usb/dwc3/host.c
index 534a49609779..5567ed2cddbe 100644
--- a/drivers/usb/dwc3/host.c
+++ b/drivers/usb/dwc3/host.c
@@ -34,9 +34,6 @@ static int dwc3_host_get_irq(struct dwc3 *dwc)
 	if (irq > 0)
 		goto out;
 
-	if (irq != -EPROBE_DEFER)
-		dev_err(dwc->dev, "missing host IRQ\n");
-
 	if (!irq)
 		irq = -EINVAL;
 
-- 
cgit v1.2.3


From 623170ff59710474d2db3dfb0ebb7577f44abd33 Mon Sep 17 00:00:00 2001
From: Pawel Laszczak <pawell@cadence.com>
Date: Mon, 7 Oct 2019 07:39:11 +0100
Subject: usb:cdns3: Fix for CV CH9 running with g_zero driver.

Patch fixes issue with Halt Endnpoint Test observed during using g_zero
driver as DUT. Bug occurred only on some testing board.

Endpoint can defer transition to Halted state if endpoint has pending
requests.
Patch add additional condition that allows to return correct endpoint
status during Get Endpoint Status request even if the halting endpoint
is in progress.

Reported-by: Rahul Kumar <kurahul@cadence.com>
Signed-off-by: Rahul Kumar <kurahul@cadence.com>
Signed-off-by: Pawel Laszczak <pawell@cadence.com>
Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver")
Tested-by: Roger Quadros <rogerq@ti.com>
Link: https://lore.kernel.org/r/1570430355-26118-1-git-send-email-pawell@cadence.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/ep0.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/cdns3/ep0.c b/drivers/usb/cdns3/ep0.c
index 0445da0a5a0c..e71240b386b4 100644
--- a/drivers/usb/cdns3/ep0.c
+++ b/drivers/usb/cdns3/ep0.c
@@ -234,9 +234,11 @@ static int cdns3_req_ep0_set_address(struct cdns3_device *priv_dev,
 static int cdns3_req_ep0_get_status(struct cdns3_device *priv_dev,
 				    struct usb_ctrlrequest *ctrl)
 {
+	struct cdns3_endpoint *priv_ep;
 	__le16 *response_pkt;
 	u16 usb_status = 0;
 	u32 recip;
+	u8 index;
 
 	recip = ctrl->bRequestType & USB_RECIP_MASK;
 
@@ -262,9 +264,13 @@ static int cdns3_req_ep0_get_status(struct cdns3_device *priv_dev,
 	case USB_RECIP_INTERFACE:
 		return cdns3_ep0_delegate_req(priv_dev, ctrl);
 	case USB_RECIP_ENDPOINT:
-		/* check if endpoint is stalled */
+		index = cdns3_ep_addr_to_index(ctrl->wIndex);
+		priv_ep = priv_dev->eps[index];
+
+		/* check if endpoint is stalled or stall is pending */
 		cdns3_select_ep(priv_dev, ctrl->wIndex);
-		if (EP_STS_STALL(readl(&priv_dev->regs->ep_sts)))
+		if (EP_STS_STALL(readl(&priv_dev->regs->ep_sts)) ||
+		    (priv_ep->flags & EP_STALL_PENDING))
 			usb_status =  BIT(USB_ENDPOINT_HALT);
 		break;
 	default:
-- 
cgit v1.2.3


From 5df884d4b8a5bf2ec5e0b92394e40112d0a0a520 Mon Sep 17 00:00:00 2001
From: Andrey Smirnov <andrew.smirnov@gmail.com>
Date: Fri, 4 Oct 2019 14:55:37 -0700
Subject: tty: serial: fsl_lpuart: Fix lpuart_flush_buffer()

Fix incorrect read-modify-write sequence in lpuart_flush_buffer() that
was reading from UARTPFIFO and writing to UARTCFIFO instead of
operating solely on the latter.

Fixes: 9bc19af9dacb ("tty: serial: fsl_lpuart: Flush HW FIFOs in .flush_buffer")
Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com>
Reported-by: Vivien Didelot <vivien.didelot@gmail.com>
Tested-by: Vivien Didelot <vivien.didelot@gmail.com>
Tested-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Cc: Stefan Agner <stefan@agner.ch>
Cc: Chris Healy <cphealy@gmail.com>
Cc: Cory Tusar <cory.tusar@zii.aero>
Cc: Lucas Stach <l.stach@pengutronix.de>
Cc: Jiri Slaby <jslaby@suse.com>
Link: https://lore.kernel.org/r/20191004215537.5308-1-andrew.smirnov@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/fsl_lpuart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
index 3e17bb8a0b16..537896c4d887 100644
--- a/drivers/tty/serial/fsl_lpuart.c
+++ b/drivers/tty/serial/fsl_lpuart.c
@@ -548,7 +548,7 @@ static void lpuart_flush_buffer(struct uart_port *port)
 		val |= UARTFIFO_TXFLUSH | UARTFIFO_RXFLUSH;
 		lpuart32_write(&sport->port, val, UARTFIFO);
 	} else {
-		val = readb(sport->port.membase + UARTPFIFO);
+		val = readb(sport->port.membase + UARTCFIFO);
 		val |= UARTCFIFO_TXFLUSH | UARTCFIFO_RXFLUSH;
 		writeb(val, sport->port.membase + UARTCFIFO);
 	}
-- 
cgit v1.2.3


From 37e3ab00e4734acc15d96b2926aab55c894f4d9c Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Sun, 6 Oct 2019 11:33:11 -0500
Subject: serial: mctrl_gpio: Check for NULL pointer

When using mctrl_gpio_to_gpiod, it dereferences gpios into a single
requested GPIO.  This dereferencing can break if gpios is NULL,
so this patch adds a NULL check before dereferencing it.  If
gpios is NULL, this function will also return NULL.

Signed-off-by: Adam Ford <aford173@gmail.com>
Reviewed-by: Yegor Yefremov <yegorslists@googlemail.com>
Link: https://lore.kernel.org/r/20191006163314.23191-1-aford173@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_mctrl_gpio.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/tty/serial/serial_mctrl_gpio.c b/drivers/tty/serial/serial_mctrl_gpio.c
index d9074303c88e..fb4781292d40 100644
--- a/drivers/tty/serial/serial_mctrl_gpio.c
+++ b/drivers/tty/serial/serial_mctrl_gpio.c
@@ -66,6 +66,9 @@ EXPORT_SYMBOL_GPL(mctrl_gpio_set);
 struct gpio_desc *mctrl_gpio_to_gpiod(struct mctrl_gpios *gpios,
 				      enum mctrl_gpio_idx gidx)
 {
+	if (gpios == NULL)
+		return NULL;
+
 	return gpios->gpio[gidx];
 }
 EXPORT_SYMBOL_GPL(mctrl_gpio_to_gpiod);
-- 
cgit v1.2.3


From fc64f7abbef2dae7ee4c94702fb3cf9a2be5431a Mon Sep 17 00:00:00 2001
From: Adam Ford <aford173@gmail.com>
Date: Sun, 6 Oct 2019 11:33:12 -0500
Subject: serial: 8250_omap: Fix gpio check for auto RTS/CTS

There are two checks to see if the manual gpio is configured, but
these the check is seeing if the structure is NULL instead it
should check to see if there are CTS and/or RTS pins defined.

This patch uses checks for those individual pins instead of
checking for the structure itself to restore auto RTS/CTS.

Signed-off-by: Adam Ford <aford173@gmail.com>
Reviewed-by: Yegor Yefremov <yegorslists@googlemail.com>
Link: https://lore.kernel.org/r/20191006163314.23191-2-aford173@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/8250/8250_omap.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
index c68e2b3a1634..836e736ae188 100644
--- a/drivers/tty/serial/8250/8250_omap.c
+++ b/drivers/tty/serial/8250/8250_omap.c
@@ -141,7 +141,7 @@ static void omap8250_set_mctrl(struct uart_port *port, unsigned int mctrl)
 
 	serial8250_do_set_mctrl(port, mctrl);
 
-	if (!up->gpios) {
+	if (!mctrl_gpio_to_gpiod(up->gpios, UART_GPIO_RTS)) {
 		/*
 		 * Turn off autoRTS if RTS is lowered and restore autoRTS
 		 * setting if RTS is raised
@@ -456,7 +456,8 @@ static void omap_8250_set_termios(struct uart_port *port,
 	up->port.status &= ~(UPSTAT_AUTOCTS | UPSTAT_AUTORTS | UPSTAT_AUTOXOFF);
 
 	if (termios->c_cflag & CRTSCTS && up->port.flags & UPF_HARD_FLOW &&
-	    !up->gpios) {
+	    !mctrl_gpio_to_gpiod(up->gpios, UART_GPIO_RTS) &&
+	    !mctrl_gpio_to_gpiod(up->gpios, UART_GPIO_CTS)) {
 		/* Enable AUTOCTS (autoRTS is enabled when RTS is raised) */
 		up->port.status |= UPSTAT_AUTOCTS | UPSTAT_AUTORTS;
 		priv->efr |= UART_EFR_CTS;
-- 
cgit v1.2.3


From 9445ad17109b6fe7864acc33f0c62bd9d866b722 Mon Sep 17 00:00:00 2001
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Date: Mon, 7 Oct 2019 15:24:47 +0300
Subject: drm/i915: Update DRIVER_DATE to 20191007

Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b367467b03c2..1da67b242113 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -106,8 +106,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20190927"
-#define DRIVER_TIMESTAMP	1569587154
+#define DRIVER_DATE		"20191007"
+#define DRIVER_TIMESTAMP	1570451087
 
 struct drm_i915_gem_object;
 
-- 
cgit v1.2.3


From 24ee01a927bfe56c66429ec4b1df6955a814adc8 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 4 Oct 2019 14:08:13 +0100
Subject: arm64: Default to building compat vDSO with clang when
 CONFIG_CC_IS_CLANG

Rather than force the use of GCC for the compat cross-compiler, instead
extract the target from CROSS_COMPILE_COMPAT and pass it to clang if the
main compiler is clang.

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Makefile | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index dfa6a5cb99e4..12229cc5d908 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -53,7 +53,11 @@ $(warning Detected assembler with broken .inst; disassembly will be unreliable)
   endif
 endif
 
+ifeq ($(CONFIG_CC_IS_CLANG), y)
+COMPATCC ?= $(CC) --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
+else
 COMPATCC ?= $(CROSS_COMPILE_COMPAT)gcc
+endif
 export COMPATCC
 
 ifeq ($(CONFIG_GENERIC_COMPAT_VDSO), y)
-- 
cgit v1.2.3


From bcaf9b57e4884e86717c1f4cee8157fd68189aa7 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 4 Oct 2019 15:43:53 +0100
Subject: arm64: vdso32: Move definition of COMPATCC into vdso32/Makefile

There's no need to export COMPATCC, so just define it locally in the
vdso32/Makefile, which is the only place where it is used.

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Makefile               | 7 -------
 arch/arm64/kernel/vdso32/Makefile | 6 ++++++
 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 12229cc5d908..34f53eb11878 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -53,13 +53,6 @@ $(warning Detected assembler with broken .inst; disassembly will be unreliable)
   endif
 endif
 
-ifeq ($(CONFIG_CC_IS_CLANG), y)
-COMPATCC ?= $(CC) --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
-else
-COMPATCC ?= $(CROSS_COMPILE_COMPAT)gcc
-endif
-export COMPATCC
-
 ifeq ($(CONFIG_GENERIC_COMPAT_VDSO), y)
   export CONFIG_COMPAT_VDSO := y
   compat_vdso := -DCONFIG_COMPAT_VDSO=1
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 038357a1e835..f52d29027d8d 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -9,6 +9,12 @@ ARCH_REL_TYPE_ABS := R_ARM_JUMP_SLOT|R_ARM_GLOB_DAT|R_ARM_ABS32
 include $(srctree)/lib/vdso/Makefile
 
 # Same as cc-*option, but using COMPATCC instead of CC
+ifeq ($(CONFIG_CC_IS_CLANG), y)
+COMPATCC ?= $(CC) --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
+else
+COMPATCC ?= $(CROSS_COMPILE_COMPAT)gcc
+endif
+
 cc32-option = $(call try-run,\
         $(COMPATCC) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
 cc32-disable-warning = $(call try-run,\
-- 
cgit v1.2.3


From c71e88c437962c1ec43d4d23a0ebf4c9cf9bee0d Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 4 Oct 2019 15:44:45 +0100
Subject: arm64: vdso32: Don't use KBUILD_CPPFLAGS unconditionally

KBUILD_CPPFLAGS is defined differently depending on whether the main
compiler is clang or not. This means that it is not possible to build
the compat vDSO with GCC if the rest of the kernel is built with clang.

Define VDSO_CPPFLAGS directly to break this dependency and allow a clang
kernel to build a compat vDSO with GCC:

  $ make ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- \
    CROSS_COMPILE_COMPAT=arm-linux-gnueabihf- CC=clang \
    COMPATCC=arm-linux-gnueabihf-gcc

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/vdso32/Makefile | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index f52d29027d8d..7de96a6a56f9 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -31,11 +31,9 @@ cc32-as-instr = $(call try-run,\
 # arm64 one.
 # As a result we set our own flags here.
 
-# From top-level Makefile
-# NOSTDINC_FLAGS
-VDSO_CPPFLAGS := -nostdinc -isystem $(shell $(COMPATCC) -print-file-name=include)
+# KBUILD_CPPFLAGS and NOSTDINC_FLAGS from top-level Makefile
+VDSO_CPPFLAGS := -D__KERNEL__ -nostdinc -isystem $(shell $(COMPATCC) -print-file-name=include)
 VDSO_CPPFLAGS += $(LINUXINCLUDE)
-VDSO_CPPFLAGS += $(KBUILD_CPPFLAGS)
 
 # Common C and assembly flags
 # From top-level Makefile
-- 
cgit v1.2.3


From 7424ee2b1617de62c3761bdd6260857363e1e4d4 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Mon, 7 Oct 2019 12:27:59 +0100
Subject: arm64: vdso32: Pass '--target' option to clang via VDSO_CAFLAGS

Directly passing the '--target' option to clang by appending to
COMPATCC does not work if COMPATCC has been specified explicitly as
an argument to Make unless the 'override' directive is used, which is
ugly and different to what is done in the top-level Makefile.

Move the '--target' option for clang out of COMPATCC and into
VDSO_CAFLAGS, where it will be picked up when compiling and assembling
the 32-bit vDSO under clang.

Reported-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/vdso32/Makefile | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 7de96a6a56f9..60e19a3fc109 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -10,7 +10,7 @@ include $(srctree)/lib/vdso/Makefile
 
 # Same as cc-*option, but using COMPATCC instead of CC
 ifeq ($(CONFIG_CC_IS_CLANG), y)
-COMPATCC ?= $(CC) --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
+COMPATCC ?= $(CC)
 else
 COMPATCC ?= $(CROSS_COMPILE_COMPAT)gcc
 endif
@@ -38,6 +38,10 @@ VDSO_CPPFLAGS += $(LINUXINCLUDE)
 # Common C and assembly flags
 # From top-level Makefile
 VDSO_CAFLAGS := $(VDSO_CPPFLAGS)
+ifneq ($(shell $(COMPATCC) --version 2>&1 | head -n 1 | grep clang),)
+VDSO_CAFLAGS += --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
+endif
+
 VDSO_CAFLAGS += $(call cc32-option,-fno-PIE)
 ifdef CONFIG_DEBUG_INFO
 VDSO_CAFLAGS += -g
-- 
cgit v1.2.3


From eff9cb67be21346402ea07d7a48564909b4f0f25 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 4 Oct 2019 14:20:06 +0100
Subject: arm64: vdso32: Rename COMPATCC to CC_COMPAT

For consistency with CROSS_COMPILE_COMPAT, mechanically rename COMPATCC
to CC_COMPAT so that specifying aspects of the compat vDSO toolchain in
the environment isn't needlessly confusing.

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/vdso32/Makefile | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 60e19a3fc109..76b327f88fbb 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -8,21 +8,21 @@
 ARCH_REL_TYPE_ABS := R_ARM_JUMP_SLOT|R_ARM_GLOB_DAT|R_ARM_ABS32
 include $(srctree)/lib/vdso/Makefile
 
-# Same as cc-*option, but using COMPATCC instead of CC
+# Same as cc-*option, but using CC_COMPAT instead of CC
 ifeq ($(CONFIG_CC_IS_CLANG), y)
-COMPATCC ?= $(CC)
+CC_COMPAT ?= $(CC)
 else
-COMPATCC ?= $(CROSS_COMPILE_COMPAT)gcc
+CC_COMPAT ?= $(CROSS_COMPILE_COMPAT)gcc
 endif
 
 cc32-option = $(call try-run,\
-        $(COMPATCC) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
+        $(CC_COMPAT) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
 cc32-disable-warning = $(call try-run,\
-	$(COMPATCC) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
+	$(CC_COMPAT) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
 cc32-ldoption = $(call try-run,\
-        $(COMPATCC) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2))
+        $(CC_COMPAT) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2))
 cc32-as-instr = $(call try-run,\
-	printf "%b\n" "$(1)" | $(COMPATCC) $(VDSO_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3))
+	printf "%b\n" "$(1)" | $(CC_COMPAT) $(VDSO_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3))
 
 # We cannot use the global flags to compile the vDSO files, the main reason
 # being that the 32-bit compiler may be older than the main (64-bit) compiler
@@ -32,13 +32,13 @@ cc32-as-instr = $(call try-run,\
 # As a result we set our own flags here.
 
 # KBUILD_CPPFLAGS and NOSTDINC_FLAGS from top-level Makefile
-VDSO_CPPFLAGS := -D__KERNEL__ -nostdinc -isystem $(shell $(COMPATCC) -print-file-name=include)
+VDSO_CPPFLAGS := -D__KERNEL__ -nostdinc -isystem $(shell $(CC_COMPAT) -print-file-name=include)
 VDSO_CPPFLAGS += $(LINUXINCLUDE)
 
 # Common C and assembly flags
 # From top-level Makefile
 VDSO_CAFLAGS := $(VDSO_CPPFLAGS)
-ifneq ($(shell $(COMPATCC) --version 2>&1 | head -n 1 | grep clang),)
+ifneq ($(shell $(CC_COMPAT) --version 2>&1 | head -n 1 | grep clang),)
 VDSO_CAFLAGS += --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
 endif
 
@@ -171,14 +171,14 @@ quiet_cmd_vdsold_and_vdso_check = LD32    $@
       cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check)
 
 quiet_cmd_vdsold = LD32    $@
-      cmd_vdsold = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \
+      cmd_vdsold = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \
                    -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@
 quiet_cmd_vdsocc = CC32    $@
-      cmd_vdsocc = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $<
+      cmd_vdsocc = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $<
 quiet_cmd_vdsocc_gettimeofday = CC32    $@
-      cmd_vdsocc_gettimeofday = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $<
+      cmd_vdsocc_gettimeofday = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $<
 quiet_cmd_vdsoas = AS32    $@
-      cmd_vdsoas = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $<
+      cmd_vdsoas = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $<
 
 quiet_cmd_vdsomunge = MUNGE   $@
       cmd_vdsomunge = $(obj)/$(munge) $< $@
-- 
cgit v1.2.3


From 7c4791c9efca8c105a86022f7d5532aeaa819125 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Mon, 7 Oct 2019 13:03:12 +0100
Subject: arm64: Kconfig: Make CONFIG_COMPAT_VDSO a proper Kconfig option

CONFIG_COMPAT_VDSO is defined by passing '-DCONFIG_COMPAT_VDSO' to the
compiler when the generic compat vDSO code is in use. It's much cleaner
and simpler to expose this as a proper Kconfig option (like x86 does),
so do that and remove the bodge.

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/Kconfig  | 15 +++++++++++++--
 arch/arm64/Makefile |  5 -----
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index ba12b3a11e55..950a56b71ff0 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -110,7 +110,6 @@ config ARM64
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_GETTIMEOFDAY
-	select GENERIC_COMPAT_VDSO if (!CPU_BIG_ENDIAN && COMPAT && "$(CROSS_COMPILE_COMPAT)" != "")
 	select HANDLE_DOMAIN_IRQ
 	select HARDIRQS_SW_RESEND
 	select HAVE_PCI
@@ -1159,7 +1158,7 @@ menuconfig COMPAT
 if COMPAT
 
 config KUSER_HELPERS
-	bool "Enable kuser helpers page for 32 bit applications"
+	bool "Enable kuser helpers page for 32-bit applications"
 	default y
 	help
 	  Warning: disabling this option may break 32-bit user programs.
@@ -1185,6 +1184,18 @@ config KUSER_HELPERS
 	  Say N here only if you are absolutely certain that you do not
 	  need these helpers; otherwise, the safe option is to say Y.
 
+config COMPAT_VDSO
+	bool "Enable vDSO for 32-bit applications"
+	depends on !CPU_BIG_ENDIAN && "$(CROSS_COMPILE_COMPAT)" != ""
+	select GENERIC_COMPAT_VDSO
+	default y
+	help
+	  Place in the process address space of 32-bit applications an
+	  ELF shared object providing fast implementations of gettimeofday
+	  and clock_gettime.
+
+	  You must have a 32-bit build of glibc 2.22 or later for programs
+	  to seamlessly take advantage of this.
 
 menuconfig ARMV8_DEPRECATED
 	bool "Emulate deprecated/obsolete ARMv8 instructions"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 34f53eb11878..2c0238ce0551 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -53,11 +53,6 @@ $(warning Detected assembler with broken .inst; disassembly will be unreliable)
   endif
 endif
 
-ifeq ($(CONFIG_GENERIC_COMPAT_VDSO), y)
-  export CONFIG_COMPAT_VDSO := y
-  compat_vdso := -DCONFIG_COMPAT_VDSO=1
-endif
-
 KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr) $(brokengasinst)	\
 		   $(compat_vdso) $(cc_has_k_constraint)
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
-- 
cgit v1.2.3


From abc47ff61d3fae19d967d09876f1ced193dfcad2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sun, 6 Oct 2019 17:49:53 +0100
Subject: drm/i915/gt: Restore dropped 'interruptible' flag

Lost in the rebasing was Tvrtko's reminder that we need to keep an
uninterruptible wait around for the Ironlake VT-d w/a

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191006165002.30312-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_gt_requests.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 8aed89fd2cdc..d69e78478eea 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -48,7 +48,7 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 			fence = i915_active_fence_get(&tl->last_request);
 			if (fence) {
 				timeout = dma_fence_wait_timeout(fence,
-								 true,
+								 interruptible,
 								 timeout);
 				dma_fence_put(fence);
 			}
-- 
cgit v1.2.3


From 11c943a1a635d2c7141b5b6667ebb521ab4ecd58 Mon Sep 17 00:00:00 2001
From: Adam Zerella <adam.zerella@gmail.com>
Date: Mon, 7 Oct 2019 13:36:57 +1100
Subject: hwmon: docs: Extend inspur-ipsps1 title underline

Sphinx is generating a build warning as the title underline
of this file is too short.

Signed-off-by: Adam Zerella <adam.zerella@gmail.com>
Reviewed-by: Jean Delvare <jdelvare@suse.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/inspur-ipsps1.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/hwmon/inspur-ipsps1.rst b/Documentation/hwmon/inspur-ipsps1.rst
index 2b871ae3448f..292c0c26bdd1 100644
--- a/Documentation/hwmon/inspur-ipsps1.rst
+++ b/Documentation/hwmon/inspur-ipsps1.rst
@@ -1,5 +1,5 @@
 Kernel driver inspur-ipsps1
-=======================
+===========================
 
 Supported chips:
 
-- 
cgit v1.2.3


From 6fb9367a15d1a126d222d738b2702c7958594a5f Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Wed, 2 Oct 2019 18:58:58 +0200
Subject: efi/cper: Fix endianness of PCIe class code

The CPER parser assumes that the class code is big endian, but at least
on this edk2-derived Intel Purley platform it's little endian:

    efi: EFI v2.50 by EDK II BIOS ID:PLYDCRB1.86B.0119.R05.1701181843
    DMI: Intel Corporation PURLEY/PURLEY, BIOS PLYDCRB1.86B.0119.R05.1701181843 01/18/2017

    {1}[Hardware Error]:   device_id: 0000:5d:00.0
    {1}[Hardware Error]:   slot: 0
    {1}[Hardware Error]:   secondary_bus: 0x5e
    {1}[Hardware Error]:   vendor_id: 0x8086, device_id: 0x2030
    {1}[Hardware Error]:   class_code: 000406
                                       ^^^^^^ (should be 060400)

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ben Dooks <ben.dooks@codethink.co.uk>
Cc: Dave Young <dyoung@redhat.com>
Cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Cc: Jerry Snitselaar <jsnitsel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Matthew Garrett <mjg59@google.com>
Cc: Octavian Purdila <octavian.purdila@intel.com>
Cc: Peter Jones <pjones@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Talbert <swt@techie.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Cc: linux-integrity@vger.kernel.org
Link: https://lkml.kernel.org/r/20191002165904.8819-2-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/firmware/efi/cper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index addf0749dd8b..b1af0de2e100 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -381,7 +381,7 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie,
 		printk("%s""vendor_id: 0x%04x, device_id: 0x%04x\n", pfx,
 		       pcie->device_id.vendor_id, pcie->device_id.device_id);
 		p = pcie->device_id.class_code;
-		printk("%s""class_code: %02x%02x%02x\n", pfx, p[0], p[1], p[2]);
+		printk("%s""class_code: %02x%02x%02x\n", pfx, p[2], p[1], p[0]);
 	}
 	if (pcie->validation_bits & CPER_PCIE_VALID_SERIAL_NUMBER)
 		printk("%s""serial number: 0x%04x, 0x%04x\n", pfx,
-- 
cgit v1.2.3


From c05f8f92b701576b615f30aac31fabdc0648649b Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Wed, 2 Oct 2019 18:58:59 +0200
Subject: efivar/ssdt: Don't iterate over EFI vars if no SSDT override was
 specified

The kernel command line option efivar_ssdt= allows the name to be
specified of an EFI variable containing an ACPI SSDT table that should
be loaded into memory by the OS, and treated as if it was provided by
the firmware.

Currently, that code will always iterate over the EFI variables and
compare each name with the provided name, even if the command line
option wasn't set to begin with.

So bail early when no variable name was provided. This works around a
boot regression on the 2012 Mac Pro, as reported by Scott.

Tested-by: Scott Talbert <swt@techie.net>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: <stable@vger.kernel.org> # v4.9+
Cc: Ben Dooks <ben.dooks@codethink.co.uk>
Cc: Dave Young <dyoung@redhat.com>
Cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Cc: Jerry Snitselaar <jsnitsel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Matthew Garrett <mjg59@google.com>
Cc: Octavian Purdila <octavian.purdila@intel.com>
Cc: Peter Jones <pjones@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Cc: linux-integrity@vger.kernel.org
Fixes: 475fb4e8b2f4 ("efi / ACPI: load SSTDs from EFI variables")
Link: https://lkml.kernel.org/r/20191002165904.8819-3-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/firmware/efi/efi.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 8d3e778e988b..69f00f7453a3 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -267,6 +267,9 @@ static __init int efivar_ssdt_load(void)
 	void *data;
 	int ret;
 
+	if (!efivar_ssdt[0])
+		return 0;
+
 	ret = efivar_init(efivar_ssdt_iter, &entries, true, &entries);
 
 	list_for_each_entry_safe(entry, aux, &entries, list) {
-- 
cgit v1.2.3


From 047d50aee341d940350897c85799e56ae57c3849 Mon Sep 17 00:00:00 2001
From: Peter Jones <pjones@redhat.com>
Date: Wed, 2 Oct 2019 18:59:00 +0200
Subject: efi/tpm: Don't access event->count when it isn't mapped

Some machines generate a lot of event log entries.  When we're
iterating over them, the code removes the old mapping and adds a
new one, so once we cross the page boundary we're unmapping the page
with the count on it.  Hilarity ensues.

This patch keeps the info from the header in local variables so we don't
need to access that page again or keep track of if it's mapped.

Tested-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Peter Jones <pjones@redhat.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Acked-by: Matthew Garrett <mjg59@google.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ben Dooks <ben.dooks@codethink.co.uk>
Cc: Dave Young <dyoung@redhat.com>
Cc: Jerry Snitselaar <jsnitsel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Octavian Purdila <octavian.purdila@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Talbert <swt@techie.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Cc: linux-integrity@vger.kernel.org
Cc: stable@vger.kernel.org
Fixes: 44038bc514a2 ("tpm: Abstract crypto agile event size calculations")
Link: https://lkml.kernel.org/r/20191002165904.8819-4-ard.biesheuvel@linaro.org
[ Minor edits. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/tpm_eventlog.h | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h
index 63238c84dc0b..b50cc3adca18 100644
--- a/include/linux/tpm_eventlog.h
+++ b/include/linux/tpm_eventlog.h
@@ -170,6 +170,7 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
 	u16 halg;
 	int i;
 	int j;
+	u32 count, event_type;
 
 	marker = event;
 	marker_start = marker;
@@ -190,16 +191,22 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
 	}
 
 	event = (struct tcg_pcr_event2_head *)mapping;
+	/*
+	 * The loop below will unmap these fields if the log is larger than
+	 * one page, so save them here for reference:
+	 */
+	count = READ_ONCE(event->count);
+	event_type = READ_ONCE(event->event_type);
 
 	efispecid = (struct tcg_efi_specid_event_head *)event_header->event;
 
 	/* Check if event is malformed. */
-	if (event->count > efispecid->num_algs) {
+	if (count > efispecid->num_algs) {
 		size = 0;
 		goto out;
 	}
 
-	for (i = 0; i < event->count; i++) {
+	for (i = 0; i < count; i++) {
 		halg_size = sizeof(event->digests[i].alg_id);
 
 		/* Map the digest's algorithm identifier */
@@ -256,8 +263,9 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
 		+ event_field->event_size;
 	size = marker - marker_start;
 
-	if ((event->event_type == 0) && (event_field->event_size == 0))
+	if (event_type == 0 && event_field->event_size == 0)
 		size = 0;
+
 out:
 	if (do_mapping)
 		TPM_MEMUNMAP(mapping, mapping_size);
-- 
cgit v1.2.3


From 05c8c1ff81ed2eb9bad7c27cf92e55c864c16df8 Mon Sep 17 00:00:00 2001
From: Peter Jones <pjones@redhat.com>
Date: Wed, 2 Oct 2019 18:59:01 +0200
Subject: efi/tpm: Don't traverse an event log with no events

When there are no entries to put into the final event log, some machines
will return the template they would have populated anyway.  In this case
the nr_events field is 0, but the rest of the log is just garbage.

This patch stops us from trying to iterate the table with
__calc_tpm2_event_size() when the number of events in the table is 0.

Tested-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Peter Jones <pjones@redhat.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Acked-by: Matthew Garrett <mjg59@google.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ben Dooks <ben.dooks@codethink.co.uk>
Cc: Dave Young <dyoung@redhat.com>
Cc: Jerry Snitselaar <jsnitsel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Octavian Purdila <octavian.purdila@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Talbert <swt@techie.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Cc: linux-integrity@vger.kernel.org
Cc: stable@vger.kernel.org
Fixes: c46f3405692d ("tpm: Reserve the TPM final events table")
Link: https://lkml.kernel.org/r/20191002165904.8819-5-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/firmware/efi/tpm.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c
index 1d3f5ca3eaaf..b9ae5c6f9b9c 100644
--- a/drivers/firmware/efi/tpm.c
+++ b/drivers/firmware/efi/tpm.c
@@ -75,11 +75,16 @@ int __init efi_tpm_eventlog_init(void)
 		goto out;
 	}
 
-	tbl_size = tpm2_calc_event_log_size((void *)efi.tpm_final_log
-					    + sizeof(final_tbl->version)
-					    + sizeof(final_tbl->nr_events),
-					    final_tbl->nr_events,
-					    log_tbl->log);
+	tbl_size = 0;
+	if (final_tbl->nr_events != 0) {
+		void *events = (void *)efi.tpm_final_log
+				+ sizeof(final_tbl->version)
+				+ sizeof(final_tbl->nr_events);
+
+		tbl_size = tpm2_calc_event_log_size(events,
+						    final_tbl->nr_events,
+						    log_tbl->log);
+	}
 	memblock_reserve((unsigned long)final_tbl,
 			 tbl_size + sizeof(*final_tbl));
 	early_memunmap(final_tbl, sizeof(*final_tbl));
-- 
cgit v1.2.3


From e658c82be5561412c5e83b5e74e9da4830593f3e Mon Sep 17 00:00:00 2001
From: Jerry Snitselaar <jsnitsel@redhat.com>
Date: Wed, 2 Oct 2019 18:59:02 +0200
Subject: efi/tpm: Only set 'efi_tpm_final_log_size' after successful event log
 parsing

If __calc_tpm2_event_size() fails to parse an event it will return 0,
resulting tpm2_calc_event_log_size() returning -1. Currently there is
no check of this return value, and 'efi_tpm_final_log_size' can end up
being set to this negative value resulting in a crash like this one:

  BUG: unable to handle page fault for address: ffffbc8fc00866ad
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page

  RIP: 0010:memcpy_erms+0x6/0x10
  Call Trace:
   tpm_read_log_efi()
   tpm_bios_log_setup()
   tpm_chip_register()
   tpm_tis_core_init.cold.9+0x28c/0x466
   tpm_tis_plat_probe()
   platform_drv_probe()
   ...

Also __calc_tpm2_event_size() returns a size of 0 when it fails
to parse an event, so update function documentation to reflect this.

The root cause of the issue that caused the failure of event parsing
in this case is resolved by Peter Jone's patchset dealing with large
event logs where crossing over a page boundary causes the page with
the event count to be unmapped.

Signed-off-by: Jerry Snitselaar <jsnitsel@redhat.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ben Dooks <ben.dooks@codethink.co.uk>
Cc: Dave Young <dyoung@redhat.com>
Cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Matthew Garrett <mjg59@google.com>
Cc: Octavian Purdila <octavian.purdila@intel.com>
Cc: Peter Jones <pjones@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Talbert <swt@techie.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Cc: linux-integrity@vger.kernel.org
Cc: stable@vger.kernel.org
Fixes: c46f3405692de ("tpm: Reserve the TPM final events table")
Link: https://lkml.kernel.org/r/20191002165904.8819-6-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/firmware/efi/tpm.c   | 9 ++++++++-
 include/linux/tpm_eventlog.h | 2 +-
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c
index b9ae5c6f9b9c..703469c1ab8e 100644
--- a/drivers/firmware/efi/tpm.c
+++ b/drivers/firmware/efi/tpm.c
@@ -85,11 +85,18 @@ int __init efi_tpm_eventlog_init(void)
 						    final_tbl->nr_events,
 						    log_tbl->log);
 	}
+
+	if (tbl_size < 0) {
+		pr_err(FW_BUG "Failed to parse event in TPM Final Events Log\n");
+		goto out_calc;
+	}
+
 	memblock_reserve((unsigned long)final_tbl,
 			 tbl_size + sizeof(*final_tbl));
-	early_memunmap(final_tbl, sizeof(*final_tbl));
 	efi_tpm_final_log_size = tbl_size;
 
+out_calc:
+	early_memunmap(final_tbl, sizeof(*final_tbl));
 out:
 	early_memunmap(log_tbl, sizeof(*log_tbl));
 	return ret;
diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h
index b50cc3adca18..131ea1bad458 100644
--- a/include/linux/tpm_eventlog.h
+++ b/include/linux/tpm_eventlog.h
@@ -152,7 +152,7 @@ struct tcg_algorithm_info {
  * total. Once we've done this we know the offset of the data length field,
  * and can calculate the total size of the event.
  *
- * Return: size of the event on success, <0 on failure
+ * Return: size of the event on success, 0 on failure
  */
 
 static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
-- 
cgit v1.2.3


From 1ed121e61630fbf23fc0df1b8aa76debede5032b Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Wed, 2 Oct 2019 18:59:03 +0200
Subject: efi: Make unexported efi_rci2_sysfs_init() static

The efi_rci2_sysfs_init() is not used outside of rci2-table.c so
make it static to silence the following Sparse warning:

  drivers/firmware/efi/rci2-table.c:79:12: warning: symbol 'efi_rci2_sysfs_init' was not declared. Should it be static?

Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Dave Young <dyoung@redhat.com>
Cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Cc: Jerry Snitselaar <jsnitsel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Matthew Garrett <mjg59@google.com>
Cc: Octavian Purdila <octavian.purdila@intel.com>
Cc: Peter Jones <pjones@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Talbert <swt@techie.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Cc: linux-integrity@vger.kernel.org
Link: https://lkml.kernel.org/r/20191002165904.8819-7-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/firmware/efi/rci2-table.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/rci2-table.c b/drivers/firmware/efi/rci2-table.c
index 3e290f96620a..76b0c354a027 100644
--- a/drivers/firmware/efi/rci2-table.c
+++ b/drivers/firmware/efi/rci2-table.c
@@ -76,7 +76,7 @@ static u16 checksum(void)
 	return chksum;
 }
 
-int __init efi_rci2_sysfs_init(void)
+static int __init efi_rci2_sysfs_init(void)
 {
 	struct kobject *tables_kobj;
 	int ret = -ENOMEM;
-- 
cgit v1.2.3


From 2ecb7402cfc7f22764e7bbc80790e66eadb20560 Mon Sep 17 00:00:00 2001
From: Dave Young <dyoung@redhat.com>
Date: Wed, 2 Oct 2019 18:59:04 +0200
Subject: efi/x86: Do not clean dummy variable in kexec path

kexec reboot fails randomly in UEFI based KVM guest.  The firmware
just resets while calling efi_delete_dummy_variable();  Unfortunately
I don't know how to debug the firmware, it is also possible a potential
problem on real hardware as well although nobody reproduced it.

The intention of the efi_delete_dummy_variable is to trigger garbage collection
when entering virtual mode.  But SetVirtualAddressMap can only run once
for each physical reboot, thus kexec_enter_virtual_mode() is not necessarily
a good place to clean a dummy object.

Drop the efi_delete_dummy_variable so that kexec reboot can work.

Signed-off-by: Dave Young <dyoung@redhat.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Matthew Garrett <mjg59@google.com>
Cc: Ben Dooks <ben.dooks@codethink.co.uk>
Cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Cc: Jerry Snitselaar <jsnitsel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Lyude Paul <lyude@redhat.com>
Cc: Octavian Purdila <octavian.purdila@intel.com>
Cc: Peter Jones <pjones@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott Talbert <swt@techie.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Cc: linux-integrity@vger.kernel.org
Link: https://lkml.kernel.org/r/20191002165904.8819-8-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/platform/efi/efi.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index c202e1b07e29..425e025341db 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -917,9 +917,6 @@ static void __init kexec_enter_virtual_mode(void)
 
 	if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX))
 		runtime_code_page_mkexec();
-
-	/* clean DUMMY object */
-	efi_delete_dummy_variable();
 #endif
 }
 
-- 
cgit v1.2.3


From 4b5149365faa8fddf7dc58e47cfed51b19db051e Mon Sep 17 00:00:00 2001
From: Shannon Nelson <snelson@pensando.io>
Date: Sun, 6 Oct 2019 13:21:07 -0700
Subject: ionic: fix stats memory dereference

When the netdev is down, the queues and their debug stats
do not exist, so don't try using a pointer to them when
when printing the ethtool stats.

Fixes: e470355bd96a ("ionic: Add driver stats")
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.h   |  2 ++
 drivers/net/ethernet/pensando/ionic/ionic_stats.c | 29 +++++++++++++++--------
 2 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
index 812190e729c2..6a95b42a8d8c 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
@@ -182,6 +182,8 @@ struct ionic_lif {
 
 #define lif_to_txqcq(lif, i)	((lif)->txqcqs[i].qcq)
 #define lif_to_rxqcq(lif, i)	((lif)->rxqcqs[i].qcq)
+#define lif_to_txstats(lif, i)	((lif)->txqcqs[i].stats->tx)
+#define lif_to_rxstats(lif, i)	((lif)->rxqcqs[i].stats->rx)
 #define lif_to_txq(lif, i)	(&lif_to_txqcq((lif), i)->q)
 #define lif_to_rxq(lif, i)	(&lif_to_txqcq((lif), i)->q)
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c
index e2907884f843..03916b6d47f2 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_stats.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c
@@ -117,7 +117,8 @@ static u64 ionic_sw_stats_get_count(struct ionic_lif *lif)
 	/* rx stats */
 	total += MAX_Q(lif) * IONIC_NUM_RX_STATS;
 
-	if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+	if (test_bit(IONIC_LIF_UP, lif->state) &&
+	    test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
 		/* tx debug stats */
 		total += MAX_Q(lif) * (IONIC_NUM_DBG_CQ_STATS +
 				      IONIC_NUM_TX_Q_STATS +
@@ -149,7 +150,8 @@ static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf)
 			*buf += ETH_GSTRING_LEN;
 		}
 
-		if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+		if (test_bit(IONIC_LIF_UP, lif->state) &&
+		    test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
 			for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) {
 				snprintf(*buf, ETH_GSTRING_LEN,
 					 "txq_%d_%s",
@@ -187,7 +189,8 @@ static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf)
 			*buf += ETH_GSTRING_LEN;
 		}
 
-		if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+		if (test_bit(IONIC_LIF_UP, lif->state) &&
+		    test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
 			for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) {
 				snprintf(*buf, ETH_GSTRING_LEN,
 					 "rxq_%d_cq_%s",
@@ -223,6 +226,8 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf)
 {
 	struct ionic_lif_sw_stats lif_stats;
 	struct ionic_qcq *txqcq, *rxqcq;
+	struct ionic_tx_stats *txstats;
+	struct ionic_rx_stats *rxstats;
 	int i, q_num;
 
 	ionic_get_lif_stats(lif, &lif_stats);
@@ -233,15 +238,17 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf)
 	}
 
 	for (q_num = 0; q_num < MAX_Q(lif); q_num++) {
-		txqcq = lif_to_txqcq(lif, q_num);
+		txstats = &lif_to_txstats(lif, q_num);
 
 		for (i = 0; i < IONIC_NUM_TX_STATS; i++) {
-			**buf = IONIC_READ_STAT64(&txqcq->stats->tx,
+			**buf = IONIC_READ_STAT64(txstats,
 						  &ionic_tx_stats_desc[i]);
 			(*buf)++;
 		}
 
-		if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+		if (test_bit(IONIC_LIF_UP, lif->state) &&
+		    test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+			txqcq = lif_to_txqcq(lif, q_num);
 			for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) {
 				**buf = IONIC_READ_STAT64(&txqcq->q,
 						      &ionic_txq_stats_desc[i]);
@@ -258,22 +265,24 @@ static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf)
 				(*buf)++;
 			}
 			for (i = 0; i < IONIC_MAX_NUM_SG_CNTR; i++) {
-				**buf = txqcq->stats->tx.sg_cntr[i];
+				**buf = txstats->sg_cntr[i];
 				(*buf)++;
 			}
 		}
 	}
 
 	for (q_num = 0; q_num < MAX_Q(lif); q_num++) {
-		rxqcq = lif_to_rxqcq(lif, q_num);
+		rxstats = &lif_to_rxstats(lif, q_num);
 
 		for (i = 0; i < IONIC_NUM_RX_STATS; i++) {
-			**buf = IONIC_READ_STAT64(&rxqcq->stats->rx,
+			**buf = IONIC_READ_STAT64(rxstats,
 						  &ionic_rx_stats_desc[i]);
 			(*buf)++;
 		}
 
-		if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+		if (test_bit(IONIC_LIF_UP, lif->state) &&
+		    test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) {
+			rxqcq = lif_to_rxqcq(lif, q_num);
 			for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) {
 				**buf = IONIC_READ_STAT64(&rxqcq->cq,
 						   &ionic_dbg_cq_stats_desc[i]);
-- 
cgit v1.2.3


From 1d0f2ebf392ef11465cefb29d545ed9e3222b29e Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Mon, 9 Sep 2019 12:31:09 +0300
Subject: drm/i915/perf: move perf types to their own header

Following a pattern used throughout the driver.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190909093116.7747-7-lionel.g.landwerlin@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h        | 300 +-----------------------------
 drivers/gpu/drm/i915/i915_perf.h       |   2 +
 drivers/gpu/drm/i915/i915_perf_types.h | 327 +++++++++++++++++++++++++++++++++
 3 files changed, 330 insertions(+), 299 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/i915_perf_types.h

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 1da67b242113..1b8fd3a38c66 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -93,6 +93,7 @@
 #include "i915_gem_fence_reg.h"
 #include "i915_gem_gtt.h"
 #include "i915_gpu_error.h"
+#include "i915_perf_types.h"
 #include "i915_request.h"
 #include "i915_scheduler.h"
 #include "gt/intel_timeline.h"
@@ -974,305 +975,6 @@ struct intel_wm_config {
 	bool sprites_scaled;
 };
 
-struct i915_oa_format {
-	u32 format;
-	int size;
-};
-
-struct i915_oa_reg {
-	i915_reg_t addr;
-	u32 value;
-};
-
-struct i915_oa_config {
-	char uuid[UUID_STRING_LEN + 1];
-	int id;
-
-	const struct i915_oa_reg *mux_regs;
-	u32 mux_regs_len;
-	const struct i915_oa_reg *b_counter_regs;
-	u32 b_counter_regs_len;
-	const struct i915_oa_reg *flex_regs;
-	u32 flex_regs_len;
-
-	struct attribute_group sysfs_metric;
-	struct attribute *attrs[2];
-	struct device_attribute sysfs_metric_id;
-
-	atomic_t ref_count;
-};
-
-struct i915_perf_stream;
-
-/**
- * struct i915_perf_stream_ops - the OPs to support a specific stream type
- */
-struct i915_perf_stream_ops {
-	/**
-	 * @enable: Enables the collection of HW samples, either in response to
-	 * `I915_PERF_IOCTL_ENABLE` or implicitly called when stream is opened
-	 * without `I915_PERF_FLAG_DISABLED`.
-	 */
-	void (*enable)(struct i915_perf_stream *stream);
-
-	/**
-	 * @disable: Disables the collection of HW samples, either in response
-	 * to `I915_PERF_IOCTL_DISABLE` or implicitly called before destroying
-	 * the stream.
-	 */
-	void (*disable)(struct i915_perf_stream *stream);
-
-	/**
-	 * @poll_wait: Call poll_wait, passing a wait queue that will be woken
-	 * once there is something ready to read() for the stream
-	 */
-	void (*poll_wait)(struct i915_perf_stream *stream,
-			  struct file *file,
-			  poll_table *wait);
-
-	/**
-	 * @wait_unlocked: For handling a blocking read, wait until there is
-	 * something to ready to read() for the stream. E.g. wait on the same
-	 * wait queue that would be passed to poll_wait().
-	 */
-	int (*wait_unlocked)(struct i915_perf_stream *stream);
-
-	/**
-	 * @read: Copy buffered metrics as records to userspace
-	 * **buf**: the userspace, destination buffer
-	 * **count**: the number of bytes to copy, requested by userspace
-	 * **offset**: zero at the start of the read, updated as the read
-	 * proceeds, it represents how many bytes have been copied so far and
-	 * the buffer offset for copying the next record.
-	 *
-	 * Copy as many buffered i915 perf samples and records for this stream
-	 * to userspace as will fit in the given buffer.
-	 *
-	 * Only write complete records; returning -%ENOSPC if there isn't room
-	 * for a complete record.
-	 *
-	 * Return any error condition that results in a short read such as
-	 * -%ENOSPC or -%EFAULT, even though these may be squashed before
-	 * returning to userspace.
-	 */
-	int (*read)(struct i915_perf_stream *stream,
-		    char __user *buf,
-		    size_t count,
-		    size_t *offset);
-
-	/**
-	 * @destroy: Cleanup any stream specific resources.
-	 *
-	 * The stream will always be disabled before this is called.
-	 */
-	void (*destroy)(struct i915_perf_stream *stream);
-};
-
-/**
- * struct i915_perf_stream - state for a single open stream FD
- */
-struct i915_perf_stream {
-	/**
-	 * @dev_priv: i915 drm device
-	 */
-	struct drm_i915_private *dev_priv;
-
-	/**
-	 * @link: Links the stream into ``&drm_i915_private->streams``
-	 */
-	struct list_head link;
-
-	/**
-	 * @wakeref: As we keep the device awake while the perf stream is
-	 * active, we track our runtime pm reference for later release.
-	 */
-	intel_wakeref_t wakeref;
-
-	/**
-	 * @sample_flags: Flags representing the `DRM_I915_PERF_PROP_SAMPLE_*`
-	 * properties given when opening a stream, representing the contents
-	 * of a single sample as read() by userspace.
-	 */
-	u32 sample_flags;
-
-	/**
-	 * @sample_size: Considering the configured contents of a sample
-	 * combined with the required header size, this is the total size
-	 * of a single sample record.
-	 */
-	int sample_size;
-
-	/**
-	 * @ctx: %NULL if measuring system-wide across all contexts or a
-	 * specific context that is being monitored.
-	 */
-	struct i915_gem_context *ctx;
-
-	/**
-	 * @enabled: Whether the stream is currently enabled, considering
-	 * whether the stream was opened in a disabled state and based
-	 * on `I915_PERF_IOCTL_ENABLE` and `I915_PERF_IOCTL_DISABLE` calls.
-	 */
-	bool enabled;
-
-	/**
-	 * @ops: The callbacks providing the implementation of this specific
-	 * type of configured stream.
-	 */
-	const struct i915_perf_stream_ops *ops;
-
-	/**
-	 * @oa_config: The OA configuration used by the stream.
-	 */
-	struct i915_oa_config *oa_config;
-
-	/**
-	 * @pinned_ctx: The OA context specific information.
-	 */
-	struct intel_context *pinned_ctx;
-	u32 specific_ctx_id;
-	u32 specific_ctx_id_mask;
-
-	struct hrtimer poll_check_timer;
-	wait_queue_head_t poll_wq;
-	bool pollin;
-
-	bool periodic;
-	int period_exponent;
-
-	/**
-	 * @oa_buffer: State of the OA buffer.
-	 */
-	struct {
-		struct i915_vma *vma;
-		u8 *vaddr;
-		u32 last_ctx_id;
-		int format;
-		int format_size;
-		int size_exponent;
-
-		/**
-		 * @ptr_lock: Locks reads and writes to all head/tail state
-		 *
-		 * Consider: the head and tail pointer state needs to be read
-		 * consistently from a hrtimer callback (atomic context) and
-		 * read() fop (user context) with tail pointer updates happening
-		 * in atomic context and head updates in user context and the
-		 * (unlikely) possibility of read() errors needing to reset all
-		 * head/tail state.
-		 *
-		 * Note: Contention/performance aren't currently a significant
-		 * concern here considering the relatively low frequency of
-		 * hrtimer callbacks (5ms period) and that reads typically only
-		 * happen in response to a hrtimer event and likely complete
-		 * before the next callback.
-		 *
-		 * Note: This lock is not held *while* reading and copying data
-		 * to userspace so the value of head observed in htrimer
-		 * callbacks won't represent any partial consumption of data.
-		 */
-		spinlock_t ptr_lock;
-
-		/**
-		 * @tails: One 'aging' tail pointer and one 'aged' tail pointer ready to
-		 * used for reading.
-		 *
-		 * Initial values of 0xffffffff are invalid and imply that an
-		 * update is required (and should be ignored by an attempted
-		 * read)
-		 */
-		struct {
-			u32 offset;
-		} tails[2];
-
-		/**
-		 * @aged_tail_idx: Index for the aged tail ready to read() data up to.
-		 */
-		unsigned int aged_tail_idx;
-
-		/**
-		 * @aging_timestamp: A monotonic timestamp for when the current aging tail pointer
-		 * was read; used to determine when it is old enough to trust.
-		 */
-		u64 aging_timestamp;
-
-		/**
-		 * @head: Although we can always read back the head pointer register,
-		 * we prefer to avoid trusting the HW state, just to avoid any
-		 * risk that some hardware condition could * somehow bump the
-		 * head pointer unpredictably and cause us to forward the wrong
-		 * OA buffer data to userspace.
-		 */
-		u32 head;
-	} oa_buffer;
-};
-
-/**
- * struct i915_oa_ops - Gen specific implementation of an OA unit stream
- */
-struct i915_oa_ops {
-	/**
-	 * @is_valid_b_counter_reg: Validates register's address for
-	 * programming boolean counters for a particular platform.
-	 */
-	bool (*is_valid_b_counter_reg)(struct drm_i915_private *dev_priv,
-				       u32 addr);
-
-	/**
-	 * @is_valid_mux_reg: Validates register's address for programming mux
-	 * for a particular platform.
-	 */
-	bool (*is_valid_mux_reg)(struct drm_i915_private *dev_priv, u32 addr);
-
-	/**
-	 * @is_valid_flex_reg: Validates register's address for programming
-	 * flex EU filtering for a particular platform.
-	 */
-	bool (*is_valid_flex_reg)(struct drm_i915_private *dev_priv, u32 addr);
-
-	/**
-	 * @enable_metric_set: Selects and applies any MUX configuration to set
-	 * up the Boolean and Custom (B/C) counters that are part of the
-	 * counter reports being sampled. May apply system constraints such as
-	 * disabling EU clock gating as required.
-	 */
-	int (*enable_metric_set)(struct i915_perf_stream *stream);
-
-	/**
-	 * @disable_metric_set: Remove system constraints associated with using
-	 * the OA unit.
-	 */
-	void (*disable_metric_set)(struct i915_perf_stream *stream);
-
-	/**
-	 * @oa_enable: Enable periodic sampling
-	 */
-	void (*oa_enable)(struct i915_perf_stream *stream);
-
-	/**
-	 * @oa_disable: Disable periodic sampling
-	 */
-	void (*oa_disable)(struct i915_perf_stream *stream);
-
-	/**
-	 * @read: Copy data from the circular OA buffer into a given userspace
-	 * buffer.
-	 */
-	int (*read)(struct i915_perf_stream *stream,
-		    char __user *buf,
-		    size_t count,
-		    size_t *offset);
-
-	/**
-	 * @oa_hw_tail_read: read the OA tail pointer register
-	 *
-	 * In particular this enables us to share all the fiddly code for
-	 * handling the OA unit tail pointer race that affects multiple
-	 * generations.
-	 */
-	u32 (*oa_hw_tail_read)(struct i915_perf_stream *stream);
-};
-
 struct intel_cdclk_state {
 	unsigned int cdclk, vco, ref, bypass;
 	u8 voltage_level;
diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h
index f4fb311184b1..ff412fb0dbbf 100644
--- a/drivers/gpu/drm/i915/i915_perf.h
+++ b/drivers/gpu/drm/i915/i915_perf.h
@@ -8,6 +8,8 @@
 
 #include <linux/types.h>
 
+#include "i915_perf_types.h"
+
 struct drm_device;
 struct drm_file;
 struct drm_i915_private;
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
new file mode 100644
index 000000000000..edcab2df74fb
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -0,0 +1,327 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef _I915_PERF_TYPES_H_
+#define _I915_PERF_TYPES_H_
+
+#include <linux/atomic.h>
+#include <linux/device.h>
+#include <linux/hrtimer.h>
+#include <linux/list.h>
+#include <linux/poll.h>
+#include <linux/sysfs.h>
+#include <linux/uuid.h>
+#include <linux/wait.h>
+
+#include "i915_reg.h"
+#include "intel_wakeref.h"
+
+struct drm_i915_private;
+struct file;
+struct i915_gem_context;
+struct i915_vma;
+struct intel_context;
+struct intel_engine_cs;
+
+struct i915_oa_format {
+	u32 format;
+	int size;
+};
+
+struct i915_oa_reg {
+	i915_reg_t addr;
+	u32 value;
+};
+
+struct i915_oa_config {
+	char uuid[UUID_STRING_LEN + 1];
+	int id;
+
+	const struct i915_oa_reg *mux_regs;
+	u32 mux_regs_len;
+	const struct i915_oa_reg *b_counter_regs;
+	u32 b_counter_regs_len;
+	const struct i915_oa_reg *flex_regs;
+	u32 flex_regs_len;
+
+	struct attribute_group sysfs_metric;
+	struct attribute *attrs[2];
+	struct device_attribute sysfs_metric_id;
+
+	atomic_t ref_count;
+};
+
+struct i915_perf_stream;
+
+/**
+ * struct i915_perf_stream_ops - the OPs to support a specific stream type
+ */
+struct i915_perf_stream_ops {
+	/**
+	 * @enable: Enables the collection of HW samples, either in response to
+	 * `I915_PERF_IOCTL_ENABLE` or implicitly called when stream is opened
+	 * without `I915_PERF_FLAG_DISABLED`.
+	 */
+	void (*enable)(struct i915_perf_stream *stream);
+
+	/**
+	 * @disable: Disables the collection of HW samples, either in response
+	 * to `I915_PERF_IOCTL_DISABLE` or implicitly called before destroying
+	 * the stream.
+	 */
+	void (*disable)(struct i915_perf_stream *stream);
+
+	/**
+	 * @poll_wait: Call poll_wait, passing a wait queue that will be woken
+	 * once there is something ready to read() for the stream
+	 */
+	void (*poll_wait)(struct i915_perf_stream *stream,
+			  struct file *file,
+			  poll_table *wait);
+
+	/**
+	 * @wait_unlocked: For handling a blocking read, wait until there is
+	 * something to ready to read() for the stream. E.g. wait on the same
+	 * wait queue that would be passed to poll_wait().
+	 */
+	int (*wait_unlocked)(struct i915_perf_stream *stream);
+
+	/**
+	 * @read: Copy buffered metrics as records to userspace
+	 * **buf**: the userspace, destination buffer
+	 * **count**: the number of bytes to copy, requested by userspace
+	 * **offset**: zero at the start of the read, updated as the read
+	 * proceeds, it represents how many bytes have been copied so far and
+	 * the buffer offset for copying the next record.
+	 *
+	 * Copy as many buffered i915 perf samples and records for this stream
+	 * to userspace as will fit in the given buffer.
+	 *
+	 * Only write complete records; returning -%ENOSPC if there isn't room
+	 * for a complete record.
+	 *
+	 * Return any error condition that results in a short read such as
+	 * -%ENOSPC or -%EFAULT, even though these may be squashed before
+	 * returning to userspace.
+	 */
+	int (*read)(struct i915_perf_stream *stream,
+		    char __user *buf,
+		    size_t count,
+		    size_t *offset);
+
+	/**
+	 * @destroy: Cleanup any stream specific resources.
+	 *
+	 * The stream will always be disabled before this is called.
+	 */
+	void (*destroy)(struct i915_perf_stream *stream);
+};
+
+/**
+ * struct i915_perf_stream - state for a single open stream FD
+ */
+struct i915_perf_stream {
+	/**
+	 * @dev_priv: i915 drm device
+	 */
+	struct drm_i915_private *dev_priv;
+
+	/**
+	 * @link: Links the stream into ``&drm_i915_private->streams``
+	 */
+	struct list_head link;
+
+	/**
+	 * @wakeref: As we keep the device awake while the perf stream is
+	 * active, we track our runtime pm reference for later release.
+	 */
+	intel_wakeref_t wakeref;
+
+	/**
+	 * @sample_flags: Flags representing the `DRM_I915_PERF_PROP_SAMPLE_*`
+	 * properties given when opening a stream, representing the contents
+	 * of a single sample as read() by userspace.
+	 */
+	u32 sample_flags;
+
+	/**
+	 * @sample_size: Considering the configured contents of a sample
+	 * combined with the required header size, this is the total size
+	 * of a single sample record.
+	 */
+	int sample_size;
+
+	/**
+	 * @ctx: %NULL if measuring system-wide across all contexts or a
+	 * specific context that is being monitored.
+	 */
+	struct i915_gem_context *ctx;
+
+	/**
+	 * @enabled: Whether the stream is currently enabled, considering
+	 * whether the stream was opened in a disabled state and based
+	 * on `I915_PERF_IOCTL_ENABLE` and `I915_PERF_IOCTL_DISABLE` calls.
+	 */
+	bool enabled;
+
+	/**
+	 * @ops: The callbacks providing the implementation of this specific
+	 * type of configured stream.
+	 */
+	const struct i915_perf_stream_ops *ops;
+
+	/**
+	 * @oa_config: The OA configuration used by the stream.
+	 */
+	struct i915_oa_config *oa_config;
+
+	/**
+	 * @pinned_ctx: The OA context specific information.
+	 */
+	struct intel_context *pinned_ctx;
+	u32 specific_ctx_id;
+	u32 specific_ctx_id_mask;
+
+	struct hrtimer poll_check_timer;
+	wait_queue_head_t poll_wq;
+	bool pollin;
+
+	bool periodic;
+	int period_exponent;
+
+	/**
+	 * @oa_buffer: State of the OA buffer.
+	 */
+	struct {
+		struct i915_vma *vma;
+		u8 *vaddr;
+		u32 last_ctx_id;
+		int format;
+		int format_size;
+		int size_exponent;
+
+		/**
+		 * @ptr_lock: Locks reads and writes to all head/tail state
+		 *
+		 * Consider: the head and tail pointer state needs to be read
+		 * consistently from a hrtimer callback (atomic context) and
+		 * read() fop (user context) with tail pointer updates happening
+		 * in atomic context and head updates in user context and the
+		 * (unlikely) possibility of read() errors needing to reset all
+		 * head/tail state.
+		 *
+		 * Note: Contention/performance aren't currently a significant
+		 * concern here considering the relatively low frequency of
+		 * hrtimer callbacks (5ms period) and that reads typically only
+		 * happen in response to a hrtimer event and likely complete
+		 * before the next callback.
+		 *
+		 * Note: This lock is not held *while* reading and copying data
+		 * to userspace so the value of head observed in htrimer
+		 * callbacks won't represent any partial consumption of data.
+		 */
+		spinlock_t ptr_lock;
+
+		/**
+		 * @tails: One 'aging' tail pointer and one 'aged' tail pointer ready to
+		 * used for reading.
+		 *
+		 * Initial values of 0xffffffff are invalid and imply that an
+		 * update is required (and should be ignored by an attempted
+		 * read)
+		 */
+		struct {
+			u32 offset;
+		} tails[2];
+
+		/**
+		 * @aged_tail_idx: Index for the aged tail ready to read() data up to.
+		 */
+		unsigned int aged_tail_idx;
+
+		/**
+		 * @aging_timestamp: A monotonic timestamp for when the current aging tail pointer
+		 * was read; used to determine when it is old enough to trust.
+		 */
+		u64 aging_timestamp;
+
+		/**
+		 * @head: Although we can always read back the head pointer register,
+		 * we prefer to avoid trusting the HW state, just to avoid any
+		 * risk that some hardware condition could * somehow bump the
+		 * head pointer unpredictably and cause us to forward the wrong
+		 * OA buffer data to userspace.
+		 */
+		u32 head;
+	} oa_buffer;
+};
+
+/**
+ * struct i915_oa_ops - Gen specific implementation of an OA unit stream
+ */
+struct i915_oa_ops {
+	/**
+	 * @is_valid_b_counter_reg: Validates register's address for
+	 * programming boolean counters for a particular platform.
+	 */
+	bool (*is_valid_b_counter_reg)(struct drm_i915_private *dev_priv,
+				       u32 addr);
+
+	/**
+	 * @is_valid_mux_reg: Validates register's address for programming mux
+	 * for a particular platform.
+	 */
+	bool (*is_valid_mux_reg)(struct drm_i915_private *dev_priv, u32 addr);
+
+	/**
+	 * @is_valid_flex_reg: Validates register's address for programming
+	 * flex EU filtering for a particular platform.
+	 */
+	bool (*is_valid_flex_reg)(struct drm_i915_private *dev_priv, u32 addr);
+
+	/**
+	 * @enable_metric_set: Selects and applies any MUX configuration to set
+	 * up the Boolean and Custom (B/C) counters that are part of the
+	 * counter reports being sampled. May apply system constraints such as
+	 * disabling EU clock gating as required.
+	 */
+	int (*enable_metric_set)(struct i915_perf_stream *stream);
+
+	/**
+	 * @disable_metric_set: Remove system constraints associated with using
+	 * the OA unit.
+	 */
+	void (*disable_metric_set)(struct i915_perf_stream *stream);
+
+	/**
+	 * @oa_enable: Enable periodic sampling
+	 */
+	void (*oa_enable)(struct i915_perf_stream *stream);
+
+	/**
+	 * @oa_disable: Disable periodic sampling
+	 */
+	void (*oa_disable)(struct i915_perf_stream *stream);
+
+	/**
+	 * @read: Copy data from the circular OA buffer into a given userspace
+	 * buffer.
+	 */
+	int (*read)(struct i915_perf_stream *stream,
+		    char __user *buf,
+		    size_t count,
+		    size_t *offset);
+
+	/**
+	 * @oa_hw_tail_read: read the OA tail pointer register
+	 *
+	 * In particular this enables us to share all the fiddly code for
+	 * handling the OA unit tail pointer race that affects multiple
+	 * generations.
+	 */
+	u32 (*oa_hw_tail_read)(struct i915_perf_stream *stream);
+};
+
+#endif /* _I915_PERF_TYPES_H_ */
-- 
cgit v1.2.3


From c7c4e29fb5a422fd144b3fb0d3e32375d8f9b0ba Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Sun, 6 Oct 2019 12:44:56 +0800
Subject: scripts: add_namespace: Fix coccicheck failed

Now all scripts in scripts/coccinelle to be automatically called
by coccicheck. However new adding add_namespace.cocci does not
support report mode, which make coccicheck failed.
This add "virtual report" to  make the coccicheck go ahead smoothly.

Fixes: eb8305aecb95 ("scripts: Coccinelle script for namespace dependencies.")
Acked-by: Julia Lawall <julia.lawall@lip6.fr>
Acked-by: Matthias Maennich <maennich@google.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 scripts/coccinelle/misc/add_namespace.cocci | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/coccinelle/misc/add_namespace.cocci b/scripts/coccinelle/misc/add_namespace.cocci
index c832bb6445a8..99e93a6c2e24 100644
--- a/scripts/coccinelle/misc/add_namespace.cocci
+++ b/scripts/coccinelle/misc/add_namespace.cocci
@@ -6,6 +6,8 @@
 /// add a missing namespace tag to a module source file.
 ///
 
+virtual report
+
 @has_ns_import@
 declarer name MODULE_IMPORT_NS;
 identifier virtual.ns;
-- 
cgit v1.2.3


From f733c6b508bcaa3441ba1eacf16efb9abd47489f Mon Sep 17 00:00:00 2001
From: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Date: Fri, 4 Oct 2019 15:57:29 +0300
Subject: perf/core: Fix inheritance of aux_output groups

Commit:

  ab43762ef010 ("perf: Allow normal events to output AUX data")

forgets to configure aux_output relation in the inherited groups, which
results in child PEBS events forever failing to schedule.

Fix this by setting up the AUX output link in the inheritance path.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20191004125729.32397-1-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/events/core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 3f0cb82e4fbc..f953dd16a5e2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11862,6 +11862,10 @@ static int inherit_group(struct perf_event *parent_event,
 					    child, leader, child_ctx);
 		if (IS_ERR(child_ctr))
 			return PTR_ERR(child_ctr);
+
+		if (sub->aux_event == parent_event &&
+		    !perf_get_aux_event(child_ctr, leader))
+			return -EINVAL;
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From bf70b0503abd19194dba25fe383d143d0229dc6a Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 3 Oct 2019 16:58:21 +0900
Subject: module: swap the order of symbol.namespace

Currently, EXPORT_SYMBOL_NS(_GPL) constructs the kernel symbol as
follows:

  __ksymtab_SYMBOL.NAMESPACE

The sym_extract_namespace() in modpost allocates memory for the part
SYMBOL.NAMESPACE when '.' is contained. One problem is that the pointer
returned by strdup() is lost because the symbol name will be copied to
malloc'ed memory by alloc_symbol(). No one will keep track of the
pointer of strdup'ed memory.

sym->namespace still points to the NAMESPACE part. So, you can free it
with complicated code like this:

   free(sym->namespace - strlen(sym->name) - 1);

It complicates memory free.

To fix it elegantly, I swapped the order of the symbol and the
namespace as follows:

  __ksymtab_NAMESPACE.SYMBOL

then, simplified sym_extract_namespace() so that it allocates memory
only for the NAMESPACE part.

I prefer this order because it is intuitive and also matches to major
languages. For example, NAMESPACE::NAME in C++, MODULE.NAME in Python.

Reviewed-by: Matthias Maennich <maennich@google.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/export.h |  4 ++--
 scripts/mod/modpost.c  | 16 +++++++---------
 2 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/include/linux/export.h b/include/linux/export.h
index 95f55b7f83a0..0695d4e847d9 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -52,7 +52,7 @@ extern struct module __this_module;
 	__ADDRESSABLE(sym)						\
 	asm("	.section \"___ksymtab" sec "+" #sym "\", \"a\"	\n"	\
 	    "	.balign	4					\n"	\
-	    "__ksymtab_" #sym NS_SEPARATOR #ns ":		\n"	\
+	    "__ksymtab_" #ns NS_SEPARATOR #sym ":		\n"	\
 	    "	.long	" #sym "- .				\n"	\
 	    "	.long	__kstrtab_" #sym "- .			\n"	\
 	    "	.long	__kstrtab_ns_" #sym "- .		\n"	\
@@ -76,7 +76,7 @@ struct kernel_symbol {
 #else
 #define __KSYMTAB_ENTRY_NS(sym, sec, ns)				\
 	static const struct kernel_symbol __ksymtab_##sym##__##ns	\
-	asm("__ksymtab_" #sym NS_SEPARATOR #ns)				\
+	asm("__ksymtab_" #ns NS_SEPARATOR #sym)				\
 	__attribute__((section("___ksymtab" sec "+" #sym), used))	\
 	__aligned(sizeof(void *))					\
 	= { (unsigned long)&sym, __kstrtab_##sym, __kstrtab_ns_##sym }
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 3961941e8e7a..c4b536ac1327 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -350,18 +350,16 @@ static enum export export_from_sec(struct elf_info *elf, unsigned int sec)
 
 static const char *sym_extract_namespace(const char **symname)
 {
-	size_t n;
-	char *dupsymname;
+	char *namespace = NULL;
+	char *ns_separator;
 
-	n = strcspn(*symname, ".");
-	if (n < strlen(*symname) - 1) {
-		dupsymname = NOFAIL(strdup(*symname));
-		dupsymname[n] = '\0';
-		*symname = dupsymname;
-		return dupsymname + n + 1;
+	ns_separator = strchr(*symname, '.');
+	if (ns_separator) {
+		namespace = NOFAIL(strndup(*symname, ns_separator - *symname));
+		*symname = ns_separator + 1;
 	}
 
-	return NULL;
+	return namespace;
 }
 
 /**
-- 
cgit v1.2.3


From 389eb3f5f4abbdb9810458ac9b87427336ba5b91 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 3 Oct 2019 16:58:22 +0900
Subject: modpost: fix broken sym->namespace for external module builds

Currently, external module builds produce tons of false-positives:

  WARNING: module <mod> uses symbol <sym> from namespace <ns>, but does not import it.

Here, the <ns> part shows a random string.

When you build external modules, the symbol info of vmlinux and
in-kernel modules are read from $(objtree)/Module.symvers, but
read_dump() is buggy in multiple ways:

[1] When the modpost is run for vmlinux and in-kernel modules,
sym_extract_namespace() allocates memory for the namespace. On the
other hand, read_dump() does not, then sym->namespace will point to
somewhere in the line buffer of get_next_line(). The data in the
buffer will be replaced soon, and sym->namespace will end up with
pointing to unrelated data. As a result, check_exports() will show
random strings in the warning messages.

[2] When there is no namespace, sym_extract_namespace() returns NULL.
On the other hand, read_dump() sets namespace to an empty string "".
(but, it will be later replaced with unrelated data due to bug [1].)
The check_exports() shows a warning unless exp->namespace is NULL,
so every symbol read from read_dump() emits the warning, which is
mostly false positive.

To address [1], sym_add_exported() calls strdup() for s->namespace.
The namespace from sym_extract_namespace() must be freed to avoid
memory leak.

For [2], I changed the if-conditional in check_exports().

This commit also fixes sym_add_exported() to set s->namespace correctly
when the symbol is preloaded.

Reviewed-by: Matthias Maennich <maennich@google.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 scripts/mod/modpost.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index c4b536ac1327..4d2cdb4d71e3 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -166,7 +166,7 @@ struct symbol {
 	struct module *module;
 	unsigned int crc;
 	int crc_valid;
-	const char *namespace;
+	char *namespace;
 	unsigned int weak:1;
 	unsigned int vmlinux:1;    /* 1 if symbol is defined in vmlinux */
 	unsigned int kernel:1;     /* 1 if symbol is from kernel
@@ -348,7 +348,7 @@ static enum export export_from_sec(struct elf_info *elf, unsigned int sec)
 		return export_unknown;
 }
 
-static const char *sym_extract_namespace(const char **symname)
+static char *sym_extract_namespace(const char **symname)
 {
 	char *namespace = NULL;
 	char *ns_separator;
@@ -373,7 +373,6 @@ static struct symbol *sym_add_exported(const char *name, const char *namespace,
 
 	if (!s) {
 		s = new_symbol(name, mod, export);
-		s->namespace = namespace;
 	} else {
 		if (!s->preloaded) {
 			warn("%s: '%s' exported twice. Previous export was in %s%s\n",
@@ -384,6 +383,8 @@ static struct symbol *sym_add_exported(const char *name, const char *namespace,
 			s->module = mod;
 		}
 	}
+	free(s->namespace);
+	s->namespace = namespace ? strdup(namespace) : NULL;
 	s->preloaded = 0;
 	s->vmlinux   = is_vmlinux(mod->name);
 	s->kernel    = 0;
@@ -670,7 +671,8 @@ static void handle_modversions(struct module *mod, struct elf_info *info,
 	unsigned int crc;
 	enum export export;
 	bool is_crc = false;
-	const char *name, *namespace;
+	const char *name;
+	char *namespace;
 
 	if ((!is_vmlinux(mod->name) || mod->is_dot_o) &&
 	    strstarts(symname, "__ksymtab"))
@@ -745,6 +747,7 @@ static void handle_modversions(struct module *mod, struct elf_info *info,
 			name = symname + strlen("__ksymtab_");
 			namespace = sym_extract_namespace(&name);
 			sym_add_exported(name, namespace, mod, export);
+			free(namespace);
 		}
 		if (strcmp(symname, "init_module") == 0)
 			mod->has_init = 1;
@@ -2193,7 +2196,7 @@ static int check_exports(struct module *mod)
 		else
 			basename = mod->name;
 
-		if (exp->namespace) {
+		if (exp->namespace && exp->namespace[0]) {
 			add_namespace(&mod->required_namespaces,
 				      exp->namespace);
 
-- 
cgit v1.2.3


From fa6643cdc5cd726b10d30eec45ff8dca267de735 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 3 Oct 2019 16:58:23 +0900
Subject: module: rename __kstrtab_ns_* to __kstrtabns_* to avoid symbol
 conflict

The module namespace produces __strtab_ns_<sym> symbols to store
namespace strings, but it does not guarantee the name uniqueness.
This is a potential problem because we have exported symbols starting
with "ns_".

For example, kernel/capability.c exports the following symbols:

  EXPORT_SYMBOL(ns_capable);
  EXPORT_SYMBOL(capable);

Assume a situation where those are converted as follows:

  EXPORT_SYMBOL_NS(ns_capable, some_namespace);
  EXPORT_SYMBOL_NS(capable, some_namespace);

The former expands to "__kstrtab_ns_capable" and "__kstrtab_ns_ns_capable",
and the latter to "__kstrtab_capable" and "__kstrtab_ns_capable".
Then, we have the duplicated "__kstrtab_ns_capable".

To ensure the uniqueness, rename "__kstrtab_ns_*" to "__kstrtabns_*".

Reviewed-by: Matthias Maennich <maennich@google.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 include/linux/export.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/export.h b/include/linux/export.h
index 0695d4e847d9..621158ecd2e2 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -55,7 +55,7 @@ extern struct module __this_module;
 	    "__ksymtab_" #ns NS_SEPARATOR #sym ":		\n"	\
 	    "	.long	" #sym "- .				\n"	\
 	    "	.long	__kstrtab_" #sym "- .			\n"	\
-	    "	.long	__kstrtab_ns_" #sym "- .		\n"	\
+	    "	.long	__kstrtabns_" #sym "- .			\n"	\
 	    "	.previous					\n")
 
 #define __KSYMTAB_ENTRY(sym, sec)					\
@@ -79,7 +79,7 @@ struct kernel_symbol {
 	asm("__ksymtab_" #ns NS_SEPARATOR #sym)				\
 	__attribute__((section("___ksymtab" sec "+" #sym), used))	\
 	__aligned(sizeof(void *))					\
-	= { (unsigned long)&sym, __kstrtab_##sym, __kstrtab_ns_##sym }
+	= { (unsigned long)&sym, __kstrtab_##sym, __kstrtabns_##sym }
 
 #define __KSYMTAB_ENTRY(sym, sec)					\
 	static const struct kernel_symbol __ksymtab_##sym		\
@@ -112,7 +112,7 @@ struct kernel_symbol {
 /* For every exported symbol, place a struct in the __ksymtab section */
 #define ___EXPORT_SYMBOL_NS(sym, sec, ns)				\
 	___export_symbol_common(sym, sec);				\
-	static const char __kstrtab_ns_##sym[]				\
+	static const char __kstrtabns_##sym[]				\
 	__attribute__((section("__ksymtab_strings"), used, aligned(1)))	\
 	= #ns;								\
 	__KSYMTAB_ENTRY_NS(sym, sec, ns)
-- 
cgit v1.2.3


From d85103ac78a6d8573b21348b36f4cca2e1839a31 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 3 Oct 2019 16:58:24 +0900
Subject: kbuild: fix build error of 'make nsdeps' in clean tree

Running 'make nsdeps' in a clean source tree fails as follows:

$ make -s clean; make -s defconfig; make nsdeps
   [ snip ]
awk: fatal: cannot open file `init/modules.order' for reading (No such file or directory)
make: *** [Makefile;1307: modules.order] Error 2
make: *** Deleting file 'modules.order'
make: *** Waiting for unfinished jobs....

The cause of the error is 'make nsdeps' does not build modules at all.
Set KBUILD_MODULES to fix it.

Reviewed-by: Matthias Maennich <maennich@google.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 6f54f2f95743..d97f38ad5d9f 100644
--- a/Makefile
+++ b/Makefile
@@ -616,7 +616,7 @@ endif
 # in addition to whatever we do anyway.
 # Just "make" or "make all" shall build modules as well
 
-ifneq ($(filter all _all modules,$(MAKECMDGOALS)),)
+ifneq ($(filter all _all modules nsdeps,$(MAKECMDGOALS)),)
   KBUILD_MODULES := 1
 endif
 
-- 
cgit v1.2.3


From 40997fb8799dab048bd4fa538f62a11ed4224e2a Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 3 Oct 2019 16:58:25 +0900
Subject: nsdeps: fix hashbang of scripts/nsdeps

This script does not use bash-extension. I am guessing this hashbang
was copied from scripts/coccicheck, which really uses bash-extension.

/bin/sh is enough for this script.

Reviewed-by: Matthias Maennich <maennich@google.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 scripts/nsdeps | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/nsdeps b/scripts/nsdeps
index ac2b6031dd13..964b7fb8c546 100644
--- a/scripts/nsdeps
+++ b/scripts/nsdeps
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 # Linux kernel symbol namespace import generator
 #
-- 
cgit v1.2.3


From df6f0987e55fd08ad2e93370eea12b5290705d4b Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 3 Oct 2019 16:58:26 +0900
Subject: nsdeps: make generated patches independent of locale

scripts/nsdeps automatically generates a patch to add MODULE_IMPORT_NS
tags, and what is nicer, it sorts the lines alphabetically with the
'sort' command. However, the output from the 'sort' command depends on
locale.

For example, I got this:

$ { echo usbstorage; echo usb_storage; } | LANG=en_US.UTF-8 sort
usbstorage
usb_storage
$ { echo usbstorage; echo usb_storage; } | LANG=C sort
usb_storage
usbstorage

So, this means people might potentially send different patches.

This kind of issue was reported in the past, for example,
commit f55f2328bb28 ("kbuild: make sorting initramfs contents
independent of locale").

Adding 'LANG=C' is a conventional way of fixing when a deterministic
result is desirable.

I added 'LANG=C' very close to the 'sort' command since changing
locale affects the language of error messages etc. We should respect
users' choice as much as possible.

Reviewed-by: Matthias Maennich <maennich@google.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 scripts/nsdeps | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/nsdeps b/scripts/nsdeps
index 964b7fb8c546..3754dac13b31 100644
--- a/scripts/nsdeps
+++ b/scripts/nsdeps
@@ -41,7 +41,7 @@ generate_deps() {
 		for source_file in $mod_source_files; do
 			sed '/MODULE_IMPORT_NS/Q' $source_file > ${source_file}.tmp
 			offset=$(wc -l ${source_file}.tmp | awk '{print $1;}')
-			cat $source_file | grep MODULE_IMPORT_NS | sort -u >> ${source_file}.tmp
+			cat $source_file | grep MODULE_IMPORT_NS | LANG=C sort -u >> ${source_file}.tmp
 			tail -n +$((offset +1)) ${source_file} | grep -v MODULE_IMPORT_NS >> ${source_file}.tmp
 			if ! diff -q ${source_file} ${source_file}.tmp; then
 				mv ${source_file}.tmp ${source_file}
-- 
cgit v1.2.3


From 88356d09904bc606182c625575237269aeece22e Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Sun, 6 Oct 2019 15:12:32 +0200
Subject: MIPS: include: Mark __cmpxchg as __always_inline

Commit ac7c3e4ff401 ("compiler: enable CONFIG_OPTIMIZE_INLINING
forcibly") allows compiler to uninline functions marked as 'inline'.
In cace of cmpxchg this would cause to reference function
__cmpxchg_called_with_bad_pointer, which is a error case
for catching bugs and will not happen for correct code, if
__cmpxchg is inlined.

Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
[paul.burton@mips.com: s/__cmpxchd/__cmpxchg in subject]
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/include/asm/cmpxchg.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index 79bf34efbc04..012dcf7046ad 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -153,8 +153,9 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x,
 extern unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old,
 				     unsigned long new, unsigned int size);
 
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
-				      unsigned long new, unsigned int size)
+static __always_inline
+unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+			unsigned long new, unsigned int size)
 {
 	switch (size) {
 	case 1:
-- 
cgit v1.2.3


From 3aec2c6a4886276bcbc9ace9416ffae41643702c Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Wed, 2 Oct 2019 12:22:58 -0700
Subject: drm/i915/vbt: Child device size remains unchanged through VBT 229

The latest documented version of the VBT is 229, but no further data has
been added to the child device definition in block 2.  Update the child
device version test to eliminate the "Expected child device config size
for VBT version XXX not known; assuming 39" debug messages from the
logs.

Bspec: 20124
Bspec: 20157
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191002192258.1013-1-matthew.d.roper@intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_bios.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 1def550c68c8..9628b485b179 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1615,7 +1615,7 @@ parse_general_definitions(struct drm_i915_private *dev_priv,
 		expected_size = 37;
 	} else if (bdb->version <= 215) {
 		expected_size = 38;
-	} else if (bdb->version <= 216) {
+	} else if (bdb->version <= 229) {
 		expected_size = 39;
 	} else {
 		expected_size = sizeof(*child);
-- 
cgit v1.2.3


From 93be1bae759e1c9d610835469c631913bfa42001 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 7 Sep 2019 11:50:46 +0100
Subject: drm/i915/execlists: Remove incorrect BUG_ON for schedule-out

As we may unwind incomplete requests (for preemption) prior to
processing the CSB and the schedule-out events, we may update rq->engine
(resetting it to point back to the parent virtual engine) prior to
calling execlists_schedule_out(), invalidating the assertion that the
request still points to the inflight engine. (The likelihood of this is
increased if the CSB interrupt processing is pushed to the ksoftirqd for
being too slow and direct submission overtakes it.)

Tvrtko summarised it as:
"So unwind from direct submission resets rq->engine and races with
process_csb from the tasklet which notices request has actually
completed."

Reported-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Fixes: df403069029d ("drm/i915/execlists: Lift process_csb() out of the irq-off spinlock")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190907105046.19934-1-chris@chris-wilson.co.uk
(cherry picked from commit d810583fc2fcf139cc766eb2303500b2d9cf064d)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index d42584439f51..e09404f2de79 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -631,7 +631,6 @@ execlists_schedule_out(struct i915_request *rq)
 	struct intel_engine_cs *cur, *old;
 
 	trace_i915_request_out(rq);
-	GEM_BUG_ON(intel_context_inflight(ce) != rq->engine);
 
 	old = READ_ONCE(ce->inflight);
 	do
-- 
cgit v1.2.3


From 6c76a93c453643e11a1063906c7c39168dd8d163 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 9 Sep 2019 12:00:08 +0100
Subject: drm/i915: Perform GGTT restore much earlier during resume

As soon as we re-enable the various functions within the HW, they may go
off and read data via a GGTT offset. Hence, if we have not yet restored
the GGTT PTE before then, they may read and even *write* random locations
in memory.

Detected by DMAR faults during resume.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Martin Peres <martin.peres@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190909110011.8958-4-chris@chris-wilson.co.uk
(cherry picked from commit cec5ca08e36fd18d2939b98055346b3b06f56c6c)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_pm.c    | 3 ---
 drivers/gpu/drm/i915/i915_drv.c           | 5 +++++
 drivers/gpu/drm/i915/selftests/i915_gem.c | 6 ++++++
 3 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 92e53c25424c..ad2a63dbcac2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -241,9 +241,6 @@ void i915_gem_resume(struct drm_i915_private *i915)
 	mutex_lock(&i915->drm.struct_mutex);
 	intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
 
-	i915_gem_restore_gtt_mappings(i915);
-	i915_gem_restore_fences(i915);
-
 	if (i915_gem_init_hw(i915))
 		goto err_wedged;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 020696726f9e..bb6f86c7067a 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1924,6 +1924,11 @@ static int i915_drm_resume(struct drm_device *dev)
 	if (ret)
 		DRM_ERROR("failed to re-enable GGTT\n");
 
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	i915_gem_restore_gtt_mappings(dev_priv);
+	i915_gem_restore_fences(dev_priv);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
 	intel_csr_ucode_resume(dev_priv);
 
 	i915_restore_state(dev_priv);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index bb6dd54a6ff3..37593831b539 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -118,6 +118,12 @@ static void pm_resume(struct drm_i915_private *i915)
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
 		intel_gt_sanitize(&i915->gt, false);
 		i915_gem_sanitize(i915);
+
+		mutex_lock(&i915->drm.struct_mutex);
+		i915_gem_restore_gtt_mappings(i915);
+		i915_gem_restore_fences(i915);
+		mutex_unlock(&i915->drm.struct_mutex);
+
 		i915_gem_resume(i915);
 	}
 }
-- 
cgit v1.2.3


From 282b7fd5f5ab4eba499e1162c1e2802c6d0bb82e Mon Sep 17 00:00:00 2001
From: Kenneth Graunke <kenneth@whitecape.org>
Date: Tue, 10 Sep 2019 18:48:01 -0700
Subject: drm/i915: Whitelist COMMON_SLICE_CHICKEN2

This allows userspace to use "legacy" mode for push constants, where
they are committed at 3DPRIMITIVE or flush time, rather than being
committed at 3DSTATE_BINDING_TABLE_POINTERS_XS time.  Gen6-8 and Gen11
both use the "legacy" behavior - only Gen9 works in the "new" way.

Conflating push constants with binding tables is painful for userspace,
we would like to be able to avoid doing so.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Cc: stable@vger.kernel.org
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911014801.26821-1-kenneth@whitecape.org
(cherry picked from commit 0606259e3b3a1220a0f04a92a1654a3f674f47ee)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 45481eb1fa3c..5f6ec2fd29a0 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1063,6 +1063,9 @@ static void gen9_whitelist_build(struct i915_wa_list *w)
 
 	/* WaAllowUMDToModifyHDCChicken1:skl,bxt,kbl,glk,cfl */
 	whitelist_reg(w, GEN8_HDC_CHICKEN1);
+
+	/* WaSendPushConstantsFromMMIO:skl,bxt */
+	whitelist_reg(w, COMMON_SLICE_CHICKEN2);
 }
 
 static void skl_whitelist_build(struct intel_engine_cs *engine)
-- 
cgit v1.2.3


From fda9fa19b09067b6a3ee6ff8d93e977957e0655c Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Sep 2019 17:08:34 +0100
Subject: drm/i915: Don't mix srcu tag and negative error codes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While srcu may use an integer tag, it does not exclude potential error
codes and so may overlap with our own use of -EINTR. Use a separate
outparam to store the tag, and report the error code separately.

Fixes: 2caffbf11762 ("drm/i915: Revoke mmaps and prevent access to fence registers across reset")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190912160834.30601-1-chris@chris-wilson.co.uk
(cherry picked from commit eebab60f224fcfd560957715d08c31564d8672ed)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_mman.c | 6 ++----
 drivers/gpu/drm/i915/gt/intel_reset.c    | 8 +++-----
 drivers/gpu/drm/i915/gt/intel_reset.h    | 2 +-
 3 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 261c9bd83f51..1fd2081a905e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -245,11 +245,9 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 
 	wakeref = intel_runtime_pm_get(rpm);
 
-	srcu = intel_gt_reset_trylock(ggtt->vm.gt);
-	if (srcu < 0) {
-		ret = srcu;
+	ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu);
+	if (ret)
 		goto err_rpm;
-	}
 
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index b9d84d52e986..eeb3bd0c4d69 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -1214,10 +1214,8 @@ out:
 	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
 }
 
-int intel_gt_reset_trylock(struct intel_gt *gt)
+int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
 {
-	int srcu;
-
 	might_lock(&gt->reset.backoff_srcu);
 	might_sleep();
 
@@ -1232,10 +1230,10 @@ int intel_gt_reset_trylock(struct intel_gt *gt)
 
 		rcu_read_lock();
 	}
-	srcu = srcu_read_lock(&gt->reset.backoff_srcu);
+	*srcu = srcu_read_lock(&gt->reset.backoff_srcu);
 	rcu_read_unlock();
 
-	return srcu;
+	return 0;
 }
 
 void intel_gt_reset_unlock(struct intel_gt *gt, int tag)
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h
index 37a987b17108..52c00199e069 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.h
+++ b/drivers/gpu/drm/i915/gt/intel_reset.h
@@ -38,7 +38,7 @@ int intel_engine_reset(struct intel_engine_cs *engine,
 
 void __i915_request_reset(struct i915_request *rq, bool guilty);
 
-int __must_check intel_gt_reset_trylock(struct intel_gt *gt);
+int __must_check intel_gt_reset_trylock(struct intel_gt *gt, int *srcu);
 void intel_gt_reset_unlock(struct intel_gt *gt, int tag);
 
 void intel_gt_set_wedged(struct intel_gt *gt);
-- 
cgit v1.2.3


From c73cdbf804cf08fd8be83fcc4d6481f8fbc6a37d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 17 Sep 2019 20:47:46 +0100
Subject: drm/i915: Extend Haswell GT1 PSMI workaround to all

A few times in CI, we have detected a GPU hang on our Haswell GT2
systems with the characteristic IPEHR of 0x780c0000. When the PSMI w/a
was first introducted, it was applied to all Haswell, but later on we
found an erratum that supposedly restricted the issue to GT1 and so
constrained it only be applied on GT1. That may have been a mistake...

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111692
Fixes: 167bc759e823 ("drm/i915: Restrict PSMI context load w/a to Haswell GT1")
References: 2c550183476d ("drm/i915: Disable PSMI sleep messages on all rings around context switches")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190917194746.26710-1-chris@chris-wilson.co.uk
(cherry picked from commit 56c05de6bd773b96deca379370965c49042b5fbf)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index 601c16239fdf..bacaa7bb8c9a 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -1573,7 +1573,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 	struct intel_engine_cs *engine = rq->engine;
 	enum intel_engine_id id;
 	const int num_engines =
-		IS_HSW_GT1(i915) ? RUNTIME_INFO(i915)->num_engines - 1 : 0;
+		IS_HASWELL(i915) ? RUNTIME_INFO(i915)->num_engines - 1 : 0;
 	bool force_restore = false;
 	int len;
 	u32 *cs;
-- 
cgit v1.2.3


From abf5cdcf235aafceabe7ed9bd9553aa863cba1fb Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 18 Sep 2019 15:54:50 +0100
Subject: drm/i915: Verify the engine after acquiring the active.lock

When using virtual engines, the rq->engine is not stable until we hold
the engine->active.lock (as the virtual engine may be exchanged with the
sibling). Since commit 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
we may retire a request concurrently with resubmitting it to HW, we need
to be extra careful to verify we are holding the correct lock for the
request's active list. This is similar to the issue we saw with
rescheduling the virtual requests, see sched_lock_engine().

Or else:

<4> [876.736126] list_add corruption. prev->next should be next (ffff8883f931a1f8), but was dead000000000100. (prev=ffff888361ffa610).
<4> [876.736136] WARNING: CPU: 2 PID: 21 at lib/list_debug.c:28 __list_add_valid+0x4d/0x70
<4> [876.736137] Modules linked in: i915(+) amdgpu gpu_sched ttm vgem snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic mei_hdcp x86_pkg_temp_thermal coretemp crct10dif_pclmul crc32_pclmul snd_intel_nhlt snd_hda_codec snd_hwdep snd_hda_core ghash_clmulni_intel e1000e cdc_ether usbnet mii snd_pcm ptp pps_core mei_me mei prime_numbers btusb btrtl btbcm btintel bluetooth ecdh_generic ecc [last unloaded: i915]
<4> [876.736154] CPU: 2 PID: 21 Comm: ksoftirqd/2 Tainted: G     U            5.3.0-CI-CI_DRM_6898+ #1
<4> [876.736156] Hardware name: Intel Corporation Ice Lake Client Platform/IceLake U DDR4 SODIMM PD RVP TLC, BIOS ICLSFWR1.R00.3183.A00.1905020411 05/02/2019
<4> [876.736157] RIP: 0010:__list_add_valid+0x4d/0x70
<4> [876.736159] Code: c3 48 89 d1 48 c7 c7 20 33 0e 82 48 89 c2 e8 4a 4a bc ff 0f 0b 31 c0 c3 48 89 c1 4c 89 c6 48 c7 c7 70 33 0e 82 e8 33 4a bc ff <0f> 0b 31 c0 c3 48 89 f2 4c 89 c1 48 89 fe 48 c7 c7 c0 33 0e 82 e8
<4> [876.736160] RSP: 0018:ffffc9000018bd30 EFLAGS: 00010082
<4> [876.736162] RAX: 0000000000000000 RBX: ffff888361ffc840 RCX: 0000000000000104
<4> [876.736163] RDX: 0000000080000104 RSI: 0000000000000000 RDI: 00000000ffffffff
<4> [876.736164] RBP: ffffc9000018bd68 R08: 0000000000000000 R09: 0000000000000001
<4> [876.736165] R10: 00000000aed95de3 R11: 000000007fe927eb R12: ffff888361ffca10
<4> [876.736166] R13: ffff888361ffa610 R14: ffff888361ffc880 R15: ffff8883f931a1f8
<4> [876.736168] FS:  0000000000000000(0000) GS:ffff88849fd00000(0000) knlGS:0000000000000000
<4> [876.736169] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
<4> [876.736170] CR2: 00007f093a9173c0 CR3: 00000003bba08005 CR4: 0000000000760ee0
<4> [876.736171] PKRU: 55555554
<4> [876.736172] Call Trace:
<4> [876.736226]  __i915_request_submit+0x152/0x370 [i915]
<4> [876.736263]  __execlists_submission_tasklet+0x6da/0x1f50 [i915]
<4> [876.736293]  ? execlists_submission_tasklet+0x29/0x50 [i915]
<4> [876.736321]  execlists_submission_tasklet+0x34/0x50 [i915]
<4> [876.736325]  tasklet_action_common.isra.5+0x47/0xb0
<4> [876.736328]  __do_softirq+0xd8/0x4ae
<4> [876.736332]  ? smpboot_thread_fn+0x23/0x280
<4> [876.736334]  ? smpboot_thread_fn+0x6b/0x280
<4> [876.736336]  run_ksoftirqd+0x2b/0x50
<4> [876.736338]  smpboot_thread_fn+0x1d3/0x280
<4> [876.736341]  ? sort_range+0x20/0x20
<4> [876.736343]  kthread+0x119/0x130
<4> [876.736345]  ? kthread_park+0xa0/0xa0
<4> [876.736347]  ret_from_fork+0x24/0x50
<4> [876.736353] irq event stamp: 2290145
<4> [876.736356] hardirqs last  enabled at (2290144): [<ffffffff8123cde8>] __slab_free+0x3e8/0x500
<4> [876.736358] hardirqs last disabled at (2290145): [<ffffffff819cfb4d>] _raw_spin_lock_irqsave+0xd/0x50
<4> [876.736360] softirqs last  enabled at (2290114): [<ffffffff81c0033e>] __do_softirq+0x33e/0x4ae
<4> [876.736361] softirqs last disabled at (2290119): [<ffffffff810b815b>] run_ksoftirqd+0x2b/0x50
<4> [876.736363] WARNING: CPU: 2 PID: 21 at lib/list_debug.c:28 __list_add_valid+0x4d/0x70
<4> [876.736364] ---[ end trace 3e58d6c7356c65bf ]---
<4> [876.736406] ------------[ cut here ]------------
<4> [876.736415] list_del corruption. prev->next should be ffff888361ffca10, but was ffff88840ac2c730
<4> [876.736421] WARNING: CPU: 2 PID: 5490 at lib/list_debug.c:53 __list_del_entry_valid+0x79/0x90
<4> [876.736422] Modules linked in: i915(+) amdgpu gpu_sched ttm vgem snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic mei_hdcp x86_pkg_temp_thermal coretemp crct10dif_pclmul crc32_pclmul snd_intel_nhlt snd_hda_codec snd_hwdep snd_hda_core ghash_clmulni_intel e1000e cdc_ether usbnet mii snd_pcm ptp pps_core mei_me mei prime_numbers btusb btrtl btbcm btintel bluetooth ecdh_generic ecc [last unloaded: i915]
<4> [876.736433] CPU: 2 PID: 5490 Comm: i915_selftest Tainted: G     U  W         5.3.0-CI-CI_DRM_6898+ #1
<4> [876.736435] Hardware name: Intel Corporation Ice Lake Client Platform/IceLake U DDR4 SODIMM PD RVP TLC, BIOS ICLSFWR1.R00.3183.A00.1905020411 05/02/2019
<4> [876.736436] RIP: 0010:__list_del_entry_valid+0x79/0x90
<4> [876.736438] Code: 0b 31 c0 c3 48 89 fe 48 c7 c7 30 34 0e 82 e8 ae 49 bc ff 0f 0b 31 c0 c3 48 89 f2 48 89 fe 48 c7 c7 68 34 0e 82 e8 97 49 bc ff <0f> 0b 31 c0 c3 48 c7 c7 a8 34 0e 82 e8 86 49 bc ff 0f 0b 31 c0 c3
<4> [876.736439] RSP: 0018:ffffc900003ef758 EFLAGS: 00010086
<4> [876.736440] RAX: 0000000000000000 RBX: ffff888361ffc840 RCX: 0000000000000002
<4> [876.736442] RDX: 0000000080000002 RSI: 0000000000000000 RDI: 00000000ffffffff
<4> [876.736443] RBP: ffffc900003ef780 R08: 0000000000000000 R09: 0000000000000001
<4> [876.736444] R10: 000000001418e4b7 R11: 000000007f0ea93b R12: ffff888361ffcab8
<4> [876.736445] R13: ffff88843b6d0000 R14: 000000000000217c R15: 0000000000000001
<4> [876.736447] FS:  00007f4e6f255240(0000) GS:ffff88849fd00000(0000) knlGS:0000000000000000
<4> [876.736448] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
<4> [876.736449] CR2: 00007f093a9173c0 CR3: 00000003bba08005 CR4: 0000000000760ee0
<4> [876.736450] PKRU: 55555554
<4> [876.736451] Call Trace:
<4> [876.736488]  i915_request_retire+0x224/0x8e0 [i915]
<4> [876.736521]  i915_request_create+0x4b/0x1b0 [i915]
<4> [876.736550]  nop_virtual_engine+0x230/0x4d0 [i915]

Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111695
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190918145453.8800-1-chris@chris-wilson.co.uk
(cherry picked from commit 37fa0de3c137d5f54f7e64f53495c9d501d42a4d)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_request.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index a53777dd371c..8f88851a9306 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -194,6 +194,27 @@ static void free_capture_list(struct i915_request *request)
 	}
 }
 
+static void remove_from_engine(struct i915_request *rq)
+{
+	struct intel_engine_cs *engine, *locked;
+
+	/*
+	 * Virtual engines complicate acquiring the engine timeline lock,
+	 * as their rq->engine pointer is not stable until under that
+	 * engine lock. The simple ploy we use is to take the lock then
+	 * check that the rq still belongs to the newly locked engine.
+	 */
+	locked = READ_ONCE(rq->engine);
+	spin_lock(&locked->active.lock);
+	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
+		spin_unlock(&locked->active.lock);
+		spin_lock(&engine->active.lock);
+		locked = engine;
+	}
+	list_del(&rq->sched.link);
+	spin_unlock(&locked->active.lock);
+}
+
 static bool i915_request_retire(struct i915_request *rq)
 {
 	struct i915_active_request *active, *next;
@@ -259,9 +280,7 @@ static bool i915_request_retire(struct i915_request *rq)
 	 * request that we have removed from the HW and put back on a run
 	 * queue.
 	 */
-	spin_lock(&rq->engine->active.lock);
-	list_del(&rq->sched.link);
-	spin_unlock(&rq->engine->active.lock);
+	remove_from_engine(rq);
 
 	spin_lock(&rq->lock);
 	i915_request_mark_complete(rq);
-- 
cgit v1.2.3


From dc7890995e04bacb45ab21e0daaeae1e7c803eb3 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Sep 2019 16:50:43 +0300
Subject: drm/i915: Bump skl+ max plane width to 5k for linear/x-tiled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The officially validated plane width limit is 4k on skl+, however
we already had people using 5k displays before we started to enforce
the limit. Also it seems Windows allows 5k resolutions as well
(though not sure if they do it with one plane or two).

According to hw folks 5k should work with the possible
exception of the following features:
- Ytile (already limited to 4k)
- FP16 (already limited to 4k)
- render compression (already limited to 4k)
- KVMR sprite and cursor (don't care)
- horizontal panning (need to verify this)
- pipe and plane scaling (need to verify this)

So apart from last two items on that list we are already
fine. We should really verify what happens with those last
two items but I don't have a 5k display on hand atm so it'll
have to wait.

In the meantime let's just bump the limit back up to 5k since
several users have already been using it without apparent issues.
At least we'll be no worse off than we were prior to lowering
the limits.

Cc: stable@vger.kernel.org
Cc: Sean Paul <sean@poorly.run>
Cc: José Roberto de Souza <jose.souza@intel.com>
Tested-by: Leho Kraav <leho@kraav.com>
Fixes: 372b9ffb5799 ("drm/i915: Fix skl+ max plane width")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111501
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190905135044.2001-1-ville.syrjala@linux.intel.com
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Sean Paul <sean@poorly.run>
(cherry picked from commit bed34ef544f9ab37ab349c04cf4142282c4dcf5d)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index ce05e805b08f..aa54bb22796d 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3280,7 +3280,20 @@ static int skl_max_plane_width(const struct drm_framebuffer *fb,
 	switch (fb->modifier) {
 	case DRM_FORMAT_MOD_LINEAR:
 	case I915_FORMAT_MOD_X_TILED:
-		return 4096;
+		/*
+		 * Validated limit is 4k, but has 5k should
+		 * work apart from the following features:
+		 * - Ytile (already limited to 4k)
+		 * - FP16 (already limited to 4k)
+		 * - render compression (already limited to 4k)
+		 * - KVMR sprite and cursor (don't care)
+		 * - horizontal panning (TODO verify this)
+		 * - pipe and plane scaling (TODO verify this)
+		 */
+		if (cpp == 8)
+			return 4096;
+		else
+			return 5120;
 	case I915_FORMAT_MOD_Y_TILED_CCS:
 	case I915_FORMAT_MOD_Yf_TILED_CCS:
 		/* FIXME AUX plane? */
-- 
cgit v1.2.3


From 7d0eb51dd92c34d9bffdb24c1210907df49de89e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 16:28:44 +0100
Subject: drm/i915: Prevent bonded requests from overtaking each other on
 preemption

Force bonded requests to run on distinct engines so that they cannot be
shuffled onto the same engine where timeslicing will reverse the order.
A bonded request will often wait on a semaphore signaled by its master,
creating an implicit dependency -- if we ignore that implicit dependency
and allow the bonded request to run on the same engine and before its
master, we will cause a GPU hang. [Whether it will hang the GPU is
debatable, we should keep on timeslicing and each timeslice should be
"accidentally" counted as forward progress, in which case it should run
but at one-half to one-third speed.]

We can prevent this inversion by restricting which engines we allow
ourselves to jump to upon preemption, i.e. baking in the arrangement
established at first execution. (We should also consider capturing the
implicit dependency using i915_sched_add_dependency(), but first we need
to think about the constraints that requires on the execution/retirement
ordering.)

Fixes: 8ee36e048c98 ("drm/i915/execlists: Minimalistic timeslicing")
References: ee1136908e9b ("drm/i915/execlists: Virtual engine bonding")
Testcase: igt/gem_exec_balancer/bonded-slice
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923152844.8914-3-chris@chris-wilson.co.uk
(cherry picked from commit e2144503bf3b22275dd33cef2880e1cb5fb200c5)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index e09404f2de79..97d4f5c90287 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -3630,18 +3630,22 @@ static void
 virtual_bond_execute(struct i915_request *rq, struct dma_fence *signal)
 {
 	struct virtual_engine *ve = to_virtual_engine(rq->engine);
+	intel_engine_mask_t allowed, exec;
 	struct ve_bond *bond;
 
+	allowed = ~to_request(signal)->engine->mask;
+
 	bond = virtual_find_bond(ve, to_request(signal)->engine);
-	if (bond) {
-		intel_engine_mask_t old, new, cmp;
+	if (bond)
+		allowed &= bond->sibling_mask;
 
-		cmp = READ_ONCE(rq->execution_mask);
-		do {
-			old = cmp;
-			new = cmp & bond->sibling_mask;
-		} while ((cmp = cmpxchg(&rq->execution_mask, old, new)) != old);
-	}
+	/* Restrict the bonded request to run on only the available engines */
+	exec = READ_ONCE(rq->execution_mask);
+	while (!try_cmpxchg(&rq->execution_mask, &exec, exec & allowed))
+		;
+
+	/* Prevent the master from being re-run on the bonded engines */
+	to_request(signal)->execution_mask &= ~allowed;
 }
 
 struct intel_context *
-- 
cgit v1.2.3


From b925708f28c2b7a3a362d709bd7f77bc75c1daac Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 20 Sep 2019 13:18:21 +0100
Subject: drm/i915: Mark contents as dirty on a write fault
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since dropping the set-to-gtt-domain in commit a679f58d0510 ("drm/i915:
Flush pages on acquisition"), we no longer mark the contents as dirty on
a write fault. This has the issue of us then not marking the pages as
dirty on releasing the buffer, which means the contents are not written
out to the swap device (should we ever pick that buffer as a victim).
Notably, this is visible in the dumb buffer interface used for cursors.
Having updated the cursor contents via mmap, and swapped away, if the
shrinker should evict the old cursor, upon next reuse, the cursor would
be invisible.

E.g. echo 80 > /proc/sys/kernel/sysrq ; echo f > /proc/sysrq-trigger

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111541
Fixes: a679f58d0510 ("drm/i915: Flush pages on acquisition")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.2+
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190920121821.7223-1-chris@chris-wilson.co.uk
(cherry picked from commit 5028851cdfdf78dc22eacbc44a0ab0b3f599ee4a)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_mman.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 1fd2081a905e..91051e178021 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -316,7 +316,11 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 		intel_wakeref_auto(&i915->ggtt.userfault_wakeref,
 				   msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND));
 
-	i915_vma_set_ggtt_write(vma);
+	if (write) {
+		GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
+		i915_vma_set_ggtt_write(vma);
+		obj->mm.dirty = true;
+	}
 
 err_fence:
 	i915_vma_unpin_fence(vma);
-- 
cgit v1.2.3


From 503c9addef613c872679e24fc8a78f3febeb5a08 Mon Sep 17 00:00:00 2001
From: Antonio Borneo <antonio.borneo@st.com>
Date: Mon, 7 Oct 2019 17:43:02 +0200
Subject: ptp: fix typo of "mechanism" in Kconfig help text

Fix typo s/mechansim/mechanism/

Signed-off-by: Antonio Borneo <antonio.borneo@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index 960961fb0d7c..0517272a268e 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -97,8 +97,8 @@ config PTP_1588_CLOCK_PCH
 	help
 	  This driver adds support for using the PCH EG20T as a PTP
 	  clock. The hardware supports time stamping of PTP packets
-	  when using the end-to-end delay (E2E) mechansim. The peer
-	  delay mechansim (P2P) is not supported.
+	  when using the end-to-end delay (E2E) mechanism. The peer
+	  delay mechanism (P2P) is not supported.
 
 	  This clock is only useful if your PTP programs are getting
 	  hardware time stamps on the PTP Ethernet packets using the
-- 
cgit v1.2.3


From 1399c59fa92984836db90538cf92397fe7caaa57 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Fri, 4 Oct 2019 14:42:19 -0500
Subject: nl80211: fix memory leak in nl80211_get_ftm_responder_stats

In nl80211_get_ftm_responder_stats, a new skb is created via nlmsg_new
named msg. If nl80211hdr_put() fails, then msg should be released. The
return statement should be replace by goto to error handling code.

Fixes: 81e54d08d9d8 ("cfg80211: support FTM responder configuration/statistics")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Link: https://lore.kernel.org/r/20191004194220.19412-1-navid.emamdoost@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 141cdb171665..4453dd375de9 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -13682,7 +13682,7 @@ static int nl80211_get_ftm_responder_stats(struct sk_buff *skb,
 	hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0,
 			     NL80211_CMD_GET_FTM_RESPONDER_STATS);
 	if (!hdr)
-		return -ENOBUFS;
+		goto nla_put_failure;
 
 	if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex))
 		goto nla_put_failure;
-- 
cgit v1.2.3


From 461c4c2b4c0731d7452bad4e77c0cdbdcea1804c Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Fri, 4 Oct 2019 15:37:06 +0300
Subject: cfg80211: fix a bunch of RCU issues in multi-bssid code

cfg80211_update_notlisted_nontrans() leaves the RCU critical session
too early, while still using nontrans_ssid which is RCU protected. In
addition, it performs a bunch of RCU pointer update operations such
as rcu_access_pointer and rcu_assign_pointer.

The caller, cfg80211_inform_bss_frame_data(), also accesses the RCU
pointer without holding the lock.

Just wrap all of this with bss_lock.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/20191004123706.15768-3-luca@coelho.fi
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/scan.c | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index ff1016607f0b..aef240fdf8df 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1703,8 +1703,7 @@ cfg80211_parse_mbssid_frame_data(struct wiphy *wiphy,
 static void
 cfg80211_update_notlisted_nontrans(struct wiphy *wiphy,
 				   struct cfg80211_bss *nontrans_bss,
-				   struct ieee80211_mgmt *mgmt, size_t len,
-				   gfp_t gfp)
+				   struct ieee80211_mgmt *mgmt, size_t len)
 {
 	u8 *ie, *new_ie, *pos;
 	const u8 *nontrans_ssid, *trans_ssid, *mbssid;
@@ -1715,6 +1714,8 @@ cfg80211_update_notlisted_nontrans(struct wiphy *wiphy,
 	const struct cfg80211_bss_ies *old;
 	u8 cpy_len;
 
+	lockdep_assert_held(&wiphy_to_rdev(wiphy)->bss_lock);
+
 	ie = mgmt->u.probe_resp.variable;
 
 	new_ie_len = ielen;
@@ -1731,23 +1732,22 @@ cfg80211_update_notlisted_nontrans(struct wiphy *wiphy,
 	if (!mbssid || mbssid < trans_ssid)
 		return;
 	new_ie_len -= mbssid[1];
-	rcu_read_lock();
+
 	nontrans_ssid = ieee80211_bss_get_ie(nontrans_bss, WLAN_EID_SSID);
-	if (!nontrans_ssid) {
-		rcu_read_unlock();
+	if (!nontrans_ssid)
 		return;
-	}
+
 	new_ie_len += nontrans_ssid[1];
-	rcu_read_unlock();
 
 	/* generate new ie for nontrans BSS
 	 * 1. replace SSID with nontrans BSS' SSID
 	 * 2. skip MBSSID IE
 	 */
-	new_ie = kzalloc(new_ie_len, gfp);
+	new_ie = kzalloc(new_ie_len, GFP_ATOMIC);
 	if (!new_ie)
 		return;
-	new_ies = kzalloc(sizeof(*new_ies) + new_ie_len, gfp);
+
+	new_ies = kzalloc(sizeof(*new_ies) + new_ie_len, GFP_ATOMIC);
 	if (!new_ies)
 		goto out_free;
 
@@ -1901,6 +1901,8 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
 	cfg80211_parse_mbssid_frame_data(wiphy, data, mgmt, len,
 					 &non_tx_data, gfp);
 
+	spin_lock_bh(&wiphy_to_rdev(wiphy)->bss_lock);
+
 	/* check if the res has other nontransmitting bss which is not
 	 * in MBSSID IE
 	 */
@@ -1915,8 +1917,9 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
 		ies2 = rcu_access_pointer(tmp_bss->ies);
 		if (ies2->tsf < ies1->tsf)
 			cfg80211_update_notlisted_nontrans(wiphy, tmp_bss,
-							   mgmt, len, gfp);
+							   mgmt, len);
 	}
+	spin_unlock_bh(&wiphy_to_rdev(wiphy)->bss_lock);
 
 	return res;
 }
-- 
cgit v1.2.3


From c512c69187197fe08026cb5bbe7b9709f4f89b73 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 7 Oct 2019 12:56:48 -0700
Subject: uaccess: implement a proper unsafe_copy_to_user() and switch filldir
 over to it

In commit 9f79b78ef744 ("Convert filldir[64]() from __put_user() to
unsafe_put_user()") I made filldir() use unsafe_put_user(), which
improves code generation on x86 enormously.

But because we didn't have a "unsafe_copy_to_user()", the dirent name
copy was also done by hand with unsafe_put_user() in a loop, and it
turns out that a lot of other architectures didn't like that, because
unlike x86, they have various alignment issues.

Most non-x86 architectures trap and fix it up, and some (like xtensa)
will just fail unaligned put_user() accesses unconditionally.  Which
makes that "copy using put_user() in a loop" not work for them at all.

I could make that code do explicit alignment etc, but the architectures
that don't like unaligned accesses also don't really use the fancy
"user_access_begin/end()" model, so they might just use the regular old
__copy_to_user() interface.

So this commit takes that looping implementation, turns it into the x86
version of "unsafe_copy_to_user()", and makes other architectures
implement the unsafe copy version as __copy_to_user() (the same way they
do for the other unsafe_xyz() accessor functions).

Note that it only does this for the copying _to_ user space, and we
still don't have a unsafe version of copy_from_user().

That's partly because we have no current users of it, but also partly
because the copy_from_user() case is slightly different and cannot
efficiently be implemented in terms of a unsafe_get_user() loop (because
gcc can't do asm goto with outputs).

It would be trivial to do this using "rep movsb", which would work
really nicely on newer x86 cores, but really badly on some older ones.

Al Viro is looking at cleaning up all our user copy routines to make
this all a non-issue, but for now we have this simple-but-stupid version
for x86 that works fine for the dirent name copy case because those
names are short strings and we simply don't need anything fancier.

Fixes: 9f79b78ef744 ("Convert filldir[64]() from __put_user() to unsafe_put_user()")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Reported-and-tested-by: Tony Luck <tony.luck@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/uaccess.h | 23 ++++++++++++++++++++++
 fs/readdir.c                   | 44 ++----------------------------------------
 include/linux/uaccess.h        |  6 ++++--
 3 files changed, 29 insertions(+), 44 deletions(-)

diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 35c225ede0e4..61d93f062a36 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -734,5 +734,28 @@ do {										\
 	if (unlikely(__gu_err)) goto err_label;					\
 } while (0)
 
+/*
+ * We want the unsafe accessors to always be inlined and use
+ * the error labels - thus the macro games.
+ */
+#define unsafe_copy_loop(dst, src, len, type, label)			\
+	while (len >= sizeof(type)) {					\
+		unsafe_put_user(*(type *)src,(type __user *)dst,label);	\
+		dst += sizeof(type);					\
+		src += sizeof(type);					\
+		len -= sizeof(type);					\
+	}
+
+#define unsafe_copy_to_user(_dst,_src,_len,label)			\
+do {									\
+	char __user *__ucu_dst = (_dst);				\
+	const char *__ucu_src = (_src);					\
+	size_t __ucu_len = (_len);					\
+	unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u64, label);	\
+	unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u32, label);	\
+	unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u16, label);	\
+	unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u8, label);	\
+} while (0)
+
 #endif /* _ASM_X86_UACCESS_H */
 
diff --git a/fs/readdir.c b/fs/readdir.c
index 19bea591c3f1..6e2623e57b2e 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -27,53 +27,13 @@
 /*
  * Note the "unsafe_put_user() semantics: we goto a
  * label for errors.
- *
- * Also note how we use a "while()" loop here, even though
- * only the biggest size needs to loop. The compiler (well,
- * at least gcc) is smart enough to turn the smaller sizes
- * into just if-statements, and this way we don't need to
- * care whether 'u64' or 'u32' is the biggest size.
- */
-#define unsafe_copy_loop(dst, src, len, type, label) 		\
-	while (len >= sizeof(type)) {				\
-		unsafe_put_user(get_unaligned((type *)src),	\
-			(type __user *)dst, label);		\
-		dst += sizeof(type);				\
-		src += sizeof(type);				\
-		len -= sizeof(type);				\
-	}
-
-/*
- * We avoid doing 64-bit copies on 32-bit architectures. They
- * might be better, but the component names are mostly small,
- * and the 64-bit cases can end up being much more complex and
- * put much more register pressure on the code, so it's likely
- * not worth the pain of unaligned accesses etc.
- *
- * So limit the copies to "unsigned long" size. I did verify
- * that at least the x86-32 case is ok without this limiting,
- * but I worry about random other legacy 32-bit cases that
- * might not do as well.
- */
-#define unsafe_copy_type(dst, src, len, type, label) do {	\
-	if (sizeof(type) <= sizeof(unsigned long))		\
-		unsafe_copy_loop(dst, src, len, type, label);	\
-} while (0)
-
-/*
- * Copy the dirent name to user space, and NUL-terminate
- * it. This should not be a function call, since we're doing
- * the copy inside a "user_access_begin/end()" section.
  */
 #define unsafe_copy_dirent_name(_dst, _src, _len, label) do {	\
 	char __user *dst = (_dst);				\
 	const char *src = (_src);				\
 	size_t len = (_len);					\
-	unsafe_copy_type(dst, src, len, u64, label);	 	\
-	unsafe_copy_type(dst, src, len, u32, label);		\
-	unsafe_copy_type(dst, src, len, u16, label);		\
-	unsafe_copy_type(dst, src, len, u8,  label);		\
-	unsafe_put_user(0, dst, label);				\
+	unsafe_put_user(0, dst+len, label);			\
+	unsafe_copy_to_user(dst, src, len, label);		\
 } while (0)
 
 
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index e47d0522a1f4..d4ee6e942562 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -355,8 +355,10 @@ extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count);
 #ifndef user_access_begin
 #define user_access_begin(ptr,len) access_ok(ptr, len)
 #define user_access_end() do { } while (0)
-#define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0)
-#define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0)
+#define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0)
+#define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e)
+#define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e)
+#define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e)
 static inline unsigned long user_access_save(void) { return 0UL; }
 static inline void user_access_restore(unsigned long flags) { }
 #endif
-- 
cgit v1.2.3


From 8b04825ed205da38754f86f4c07ea8600d8c2a65 Mon Sep 17 00:00:00 2001
From: Vincent Chen <vincent.chen@sifive.com>
Date: Mon, 23 Sep 2019 08:45:14 +0800
Subject: riscv: avoid kernel hangs when trapped in BUG()

When the CONFIG_GENERIC_BUG is disabled by disabling CONFIG_BUG, if a
kernel thread is trapped by BUG(), the whole system will be in the
loop that infinitely handles the ebreak exception instead of entering the
die function. To fix this problem, the do_trap_break() will always call
the die() to deal with the break exception as the type of break is
BUG_TRAP_TYPE_BUG.

Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
---
 arch/riscv/kernel/traps.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 424eb72d56b1..055a937aca70 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -124,23 +124,23 @@ static inline unsigned long get_break_insn_length(unsigned long pc)
 
 asmlinkage void do_trap_break(struct pt_regs *regs)
 {
-#ifdef CONFIG_GENERIC_BUG
 	if (!user_mode(regs)) {
 		enum bug_trap_type type;
 
 		type = report_bug(regs->sepc, regs);
 		switch (type) {
+#ifdef CONFIG_GENERIC_BUG
 		case BUG_TRAP_TYPE_NONE:
 			break;
 		case BUG_TRAP_TYPE_WARN:
 			regs->sepc += get_break_insn_length(regs->sepc);
 			break;
 		case BUG_TRAP_TYPE_BUG:
+#endif /* CONFIG_GENERIC_BUG */
+		default:
 			die(regs, "Kernel BUG");
 		}
 	}
-#endif /* CONFIG_GENERIC_BUG */
-
 	force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)(regs->sepc));
 }
 
-- 
cgit v1.2.3


From e0c0fc18f10d5080cddde0e81505fd3e952c20c4 Mon Sep 17 00:00:00 2001
From: Vincent Chen <vincent.chen@sifive.com>
Date: Mon, 23 Sep 2019 08:45:15 +0800
Subject: riscv: avoid sending a SIGTRAP to a user thread trapped in WARN()

On RISC-V, when the kernel runs code on behalf of a user thread, and the
kernel executes a WARN() or WARN_ON(), the user thread will be sent
a bogus SIGTRAP.  Fix the RISC-V kernel code to not send a SIGTRAP when
a WARN()/WARN_ON() is executed.

Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
[paul.walmsley@sifive.com: fixed subject]
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
---
 arch/riscv/kernel/traps.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 055a937aca70..82f42a55451e 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -134,7 +134,7 @@ asmlinkage void do_trap_break(struct pt_regs *regs)
 			break;
 		case BUG_TRAP_TYPE_WARN:
 			regs->sepc += get_break_insn_length(regs->sepc);
-			break;
+			return;
 		case BUG_TRAP_TYPE_BUG:
 #endif /* CONFIG_GENERIC_BUG */
 		default:
-- 
cgit v1.2.3


From 8bb0daef64e5a92db63ad1d3bbf9e280a7b3612a Mon Sep 17 00:00:00 2001
From: Vincent Chen <vincent.chen@sifive.com>
Date: Mon, 23 Sep 2019 08:45:16 +0800
Subject: riscv: Correct the handling of unexpected ebreak in do_trap_break()

For the kernel space, all ebreak instructions are determined at compile
time because the kernel space debugging module is currently unsupported.
Hence, it should be treated as a bug if an ebreak instruction which does
not belong to BUG_TRAP_TYPE_WARN or BUG_TRAP_TYPE_BUG is executed in
kernel space. For the userspace, debugging module or user problem may
intentionally insert an ebreak instruction to trigger a SIGTRAP signal.
To approach the above two situations, the do_trap_break() will direct
the BUG_TRAP_TYPE_NONE ebreak exception issued in kernel space to die()
and will send a SIGTRAP to the trapped process only when the ebreak is
in userspace.

Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
[paul.walmsley@sifive.com: fixed checkpatch issue]
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
---
 arch/riscv/kernel/traps.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 82f42a55451e..93742df9067f 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -130,8 +130,6 @@ asmlinkage void do_trap_break(struct pt_regs *regs)
 		type = report_bug(regs->sepc, regs);
 		switch (type) {
 #ifdef CONFIG_GENERIC_BUG
-		case BUG_TRAP_TYPE_NONE:
-			break;
 		case BUG_TRAP_TYPE_WARN:
 			regs->sepc += get_break_insn_length(regs->sepc);
 			return;
@@ -140,8 +138,10 @@ asmlinkage void do_trap_break(struct pt_regs *regs)
 		default:
 			die(regs, "Kernel BUG");
 		}
+	} else {
+		force_sig_fault(SIGTRAP, TRAP_BRKPT,
+				(void __user *)(regs->sepc));
 	}
-	force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)(regs->sepc));
 }
 
 #ifdef CONFIG_GENERIC_BUG
-- 
cgit v1.2.3


From 95697f9907bfe3eab0ef20265a766b22e27dde64 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 4 Oct 2019 15:37:05 +0300
Subject: mac80211: accept deauth frames in IBSS mode

We can process deauth frames and all, but we drop them very
early in the RX path today - this could never have worked.

Fixes: 2cc59e784b54 ("mac80211: reply to AUTH with DEAUTH if sta allocation fails in IBSS")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Link: https://lore.kernel.org/r/20191004123706.15768-2-luca@coelho.fi
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/rx.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 768d14c9a716..0e05ff037672 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3467,9 +3467,18 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx)
 	case cpu_to_le16(IEEE80211_STYPE_PROBE_RESP):
 		/* process for all: mesh, mlme, ibss */
 		break;
+	case cpu_to_le16(IEEE80211_STYPE_DEAUTH):
+		if (is_multicast_ether_addr(mgmt->da) &&
+		    !is_broadcast_ether_addr(mgmt->da))
+			return RX_DROP_MONITOR;
+
+		/* process only for station/IBSS */
+		if (sdata->vif.type != NL80211_IFTYPE_STATION &&
+		    sdata->vif.type != NL80211_IFTYPE_ADHOC)
+			return RX_DROP_MONITOR;
+		break;
 	case cpu_to_le16(IEEE80211_STYPE_ASSOC_RESP):
 	case cpu_to_le16(IEEE80211_STYPE_REASSOC_RESP):
-	case cpu_to_le16(IEEE80211_STYPE_DEAUTH):
 	case cpu_to_le16(IEEE80211_STYPE_DISASSOC):
 		if (is_multicast_ether_addr(mgmt->da) &&
 		    !is_broadcast_ether_addr(mgmt->da))
-- 
cgit v1.2.3


From dc0c18ed229cdcca283dd78fefa38273ec37a42c Mon Sep 17 00:00:00 2001
From: Aaron Komisar <aaron.komisar@tandemg.com>
Date: Wed, 2 Oct 2019 13:59:07 +0000
Subject: mac80211: fix scan when operating on DFS channels in ETSI domains

In non-ETSI regulatory domains scan is blocked when operating channel
is a DFS channel. For ETSI, however, once DFS channel is marked as
available after the CAC, this channel will remain available (for some
time) even after leaving this channel.

Therefore a scan can be done without any impact on the availability
of the DFS channel as no new CAC is required after the scan.

Enable scan in mac80211 in these cases.

Signed-off-by: Aaron Komisar <aaron.komisar@tandemg.com>
Link: https://lore.kernel.org/r/1570024728-17284-1-git-send-email-aaron.komisar@tandemg.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h |  8 ++++++++
 net/mac80211/scan.c    | 30 ++++++++++++++++++++++++++++--
 net/wireless/reg.c     |  1 +
 net/wireless/reg.h     |  8 --------
 4 files changed, 37 insertions(+), 10 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index ff45c3e1abff..4ab2c49423dc 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5549,6 +5549,14 @@ const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy,
  */
 const char *reg_initiator_name(enum nl80211_reg_initiator initiator);
 
+/**
+ * regulatory_pre_cac_allowed - check if pre-CAC allowed in the current regdom
+ * @wiphy: wiphy for which pre-CAC capability is checked.
+ *
+ * Pre-CAC is allowed only in some regdomains (notable ETSI).
+ */
+bool regulatory_pre_cac_allowed(struct wiphy *wiphy);
+
 /**
  * DOC: Internal regulatory db functions
  *
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index adf94ba1ed77..4d31d9688dc2 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -520,10 +520,33 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local,
 	return 0;
 }
 
+static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_sub_if_data *sdata_iter;
+
+	if (!ieee80211_is_radar_required(local))
+		return true;
+
+	if (!regulatory_pre_cac_allowed(local->hw.wiphy))
+		return false;
+
+	mutex_lock(&local->iflist_mtx);
+	list_for_each_entry(sdata_iter, &local->interfaces, list) {
+		if (sdata_iter->wdev.cac_started) {
+			mutex_unlock(&local->iflist_mtx);
+			return false;
+		}
+	}
+	mutex_unlock(&local->iflist_mtx);
+
+	return true;
+}
+
 static bool ieee80211_can_scan(struct ieee80211_local *local,
 			       struct ieee80211_sub_if_data *sdata)
 {
-	if (ieee80211_is_radar_required(local))
+	if (!__ieee80211_can_leave_ch(sdata))
 		return false;
 
 	if (!list_empty(&local->roc_list))
@@ -630,7 +653,10 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 
 	lockdep_assert_held(&local->mtx);
 
-	if (local->scan_req || ieee80211_is_radar_required(local))
+	if (local->scan_req)
+		return -EBUSY;
+
+	if (!__ieee80211_can_leave_ch(sdata))
 		return -EBUSY;
 
 	if (!ieee80211_can_scan(local, sdata)) {
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 420c4207ab59..446c76d44e65 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -3883,6 +3883,7 @@ bool regulatory_pre_cac_allowed(struct wiphy *wiphy)
 
 	return pre_cac_allowed;
 }
+EXPORT_SYMBOL(regulatory_pre_cac_allowed);
 
 void regulatory_propagate_dfs_state(struct wiphy *wiphy,
 				    struct cfg80211_chan_def *chandef,
diff --git a/net/wireless/reg.h b/net/wireless/reg.h
index 504133d76de4..dc8f689bd469 100644
--- a/net/wireless/reg.h
+++ b/net/wireless/reg.h
@@ -155,14 +155,6 @@ bool regulatory_indoor_allowed(void);
  */
 #define REG_PRE_CAC_EXPIRY_GRACE_MS 2000
 
-/**
- * regulatory_pre_cac_allowed - if pre-CAC allowed in the current dfs domain
- * @wiphy: wiphy for which pre-CAC capability is checked.
-
- * Pre-CAC is allowed only in ETSI domain.
- */
-bool regulatory_pre_cac_allowed(struct wiphy *wiphy);
-
 /**
  * regulatory_propagate_dfs_state - Propagate DFS channel state to other wiphys
  * @wiphy - wiphy on which radar is detected and the event will be propagated
-- 
cgit v1.2.3


From b9dcb97b6c8076af3469c62feb1174ef525b81f7 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 7 Oct 2019 16:41:51 +0100
Subject: drm/i915: make array hw_engine_mask static, makes object smaller

Don't populate the array hw_engine_mask on the stack but instead make it
static. Makes the object code smaller by 316 bytes.

Before:
   text	   data	    bss	    dec	    hex	filename
  34004	   4388	    320	  38712	   9738	gpu/drm/i915/gt/intel_reset.o

After:
   text	   data	    bss	    dec	    hex	filename
  33528	   4548	    320	  38396	   95fc	gpu/drm/i915/gt/intel_reset.o

(gcc version 9.2.1, amd64)

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191007154151.23245-1-colin.king@canonical.com
---
 drivers/gpu/drm/i915/gt/intel_reset.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 7b3d9d4517a0..ae8f9cef6b13 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -282,14 +282,14 @@ static int gen6_reset_engines(struct intel_gt *gt,
 			      intel_engine_mask_t engine_mask,
 			      unsigned int retry)
 {
-	struct intel_engine_cs *engine;
-	const u32 hw_engine_mask[] = {
+	static const u32 hw_engine_mask[] = {
 		[RCS0]  = GEN6_GRDOM_RENDER,
 		[BCS0]  = GEN6_GRDOM_BLT,
 		[VCS0]  = GEN6_GRDOM_MEDIA,
 		[VCS1]  = GEN8_GRDOM_MEDIA2,
 		[VECS0] = GEN6_GRDOM_VECS,
 	};
+	struct intel_engine_cs *engine;
 	u32 hw_mask;
 
 	if (engine_mask == ALL_ENGINES) {
@@ -413,7 +413,7 @@ static int gen11_reset_engines(struct intel_gt *gt,
 			       intel_engine_mask_t engine_mask,
 			       unsigned int retry)
 {
-	const u32 hw_engine_mask[] = {
+	static const u32 hw_engine_mask[] = {
 		[RCS0]  = GEN11_GRDOM_RENDER,
 		[BCS0]  = GEN11_GRDOM_BLT,
 		[VCS0]  = GEN11_GRDOM_MEDIA,
-- 
cgit v1.2.3


From cd6a851385be878f086204aa0e7cd3bec9ea909f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 7 Oct 2019 16:45:31 +0100
Subject: drm/i915/gt: Prefer local path to runtime powermanagement

Avoid going to the base i915 device when we already have a path from gt
to the runtime powermanagement interface. The benefit is that it looks a
bit more self-consistent to always be acquiring the gt->uncore->rpm for
use with the gt->uncore.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191007154531.1750-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_context.c        | 2 +-
 drivers/gpu/drm/i915/gt/intel_engine_cs.c      | 4 ++--
 drivers/gpu/drm/i915/gt/intel_engine_pm.c      | 2 +-
 drivers/gpu/drm/i915/gt/intel_gt.c             | 7 +++----
 drivers/gpu/drm/i915/gt/intel_gt_pm.c          | 4 ++--
 drivers/gpu/drm/i915/gt/intel_hangcheck.c      | 4 ++--
 drivers/gpu/drm/i915/gt/intel_reset.c          | 6 +++---
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c   | 4 ++--
 drivers/gpu/drm/i915/gt/selftest_reset.c       | 8 ++++----
 drivers/gpu/drm/i915/gt/selftest_workarounds.c | 4 ++--
 drivers/gpu/drm/i915/gt/uc/intel_guc_log.c     | 3 +--
 drivers/gpu/drm/i915/gt/uc/intel_huc.c         | 2 +-
 drivers/gpu/drm/i915/gt/uc/intel_uc.c          | 2 +-
 drivers/gpu/drm/i915/i915_irq.c                | 6 +++---
 14 files changed, 28 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index be34d97ac18f..59c3083c1ec1 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -62,7 +62,7 @@ int __intel_context_do_pin(struct intel_context *ce)
 		}
 
 		err = 0;
-		with_intel_runtime_pm(&ce->engine->i915->runtime_pm, wakeref)
+		with_intel_runtime_pm(ce->engine->uncore->rpm, wakeref)
 			err = ce->ops->pin(ce);
 		if (err)
 			goto err;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 80fd072ac719..6220b7151bb9 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1458,10 +1458,10 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	spin_unlock_irqrestore(&engine->active.lock, flags);
 
 	drm_printf(m, "\tMMIO base:  0x%08x\n", engine->mmio_base);
-	wakeref = intel_runtime_pm_get_if_in_use(&engine->i915->runtime_pm);
+	wakeref = intel_runtime_pm_get_if_in_use(engine->uncore->rpm);
 	if (wakeref) {
 		intel_engine_print_registers(engine, m);
-		intel_runtime_pm_put(&engine->i915->runtime_pm, wakeref);
+		intel_runtime_pm_put(engine->uncore->rpm, wakeref);
 	} else {
 		drm_printf(m, "\tDevice is asleep; skipping register dump\n");
 	}
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 8e5e513eddc9..67eb6183648a 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -185,7 +185,7 @@ static const struct intel_wakeref_ops wf_ops = {
 
 void intel_engine_init__pm(struct intel_engine_cs *engine)
 {
-	struct intel_runtime_pm *rpm = &engine->i915->runtime_pm;
+	struct intel_runtime_pm *rpm = engine->uncore->rpm;
 
 	intel_wakeref_init(&engine->wakeref, rpm, &wf_ops);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 8f44cf8c79b2..b3619a2a5d0e 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -273,7 +273,7 @@ void intel_gt_check_and_clear_faults(struct intel_gt *gt)
 
 void intel_gt_flush_ggtt_writes(struct intel_gt *gt)
 {
-	struct drm_i915_private *i915 = gt->i915;
+	struct intel_uncore *uncore = gt->uncore;
 	intel_wakeref_t wakeref;
 
 	/*
@@ -297,13 +297,12 @@ void intel_gt_flush_ggtt_writes(struct intel_gt *gt)
 
 	wmb();
 
-	if (INTEL_INFO(i915)->has_coherent_ggtt)
+	if (INTEL_INFO(gt->i915)->has_coherent_ggtt)
 		return;
 
 	intel_gt_chipset_flush(gt);
 
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
-		struct intel_uncore *uncore = gt->uncore;
+	with_intel_runtime_pm(uncore->rpm, wakeref) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&uncore->lock, flags);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index b52e2ba3d092..87e34e0b6427 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -94,7 +94,7 @@ static const struct intel_wakeref_ops wf_ops = {
 
 void intel_gt_pm_init_early(struct intel_gt *gt)
 {
-	intel_wakeref_init(&gt->wakeref, &gt->i915->runtime_pm, &wf_ops);
+	intel_wakeref_init(&gt->wakeref, gt->uncore->rpm, &wf_ops);
 
 	BLOCKING_INIT_NOTIFIER_HEAD(&gt->pm_notifications);
 }
@@ -222,7 +222,7 @@ void intel_gt_suspend(struct intel_gt *gt)
 	/* We expect to be idle already; but also want to be independent */
 	wait_for_idle(gt);
 
-	with_intel_runtime_pm(&gt->i915->runtime_pm, wakeref)
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref)
 		intel_rc6_disable(&gt->rc6);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_hangcheck.c b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
index 9814b18b32ad..c14dbeb3ccc3 100644
--- a/drivers/gpu/drm/i915/gt/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
@@ -271,7 +271,7 @@ static void hangcheck_elapsed(struct work_struct *work)
 	if (intel_gt_is_wedged(gt))
 		return;
 
-	wakeref = intel_runtime_pm_get_if_in_use(&gt->i915->runtime_pm);
+	wakeref = intel_runtime_pm_get_if_in_use(gt->uncore->rpm);
 	if (!wakeref)
 		return;
 
@@ -322,7 +322,7 @@ static void hangcheck_elapsed(struct work_struct *work)
 	if (hung)
 		hangcheck_declare_hang(gt, hung, stuck);
 
-	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 
 	/* Reset timer in case GPU hangs without another request being added */
 	intel_gt_queue_hangcheck(gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index ae8f9cef6b13..34791fc79dea 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -811,7 +811,7 @@ void intel_gt_set_wedged(struct intel_gt *gt)
 	intel_wakeref_t wakeref;
 
 	mutex_lock(&gt->reset.mutex);
-	with_intel_runtime_pm(&gt->i915->runtime_pm, wakeref)
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref)
 		__intel_gt_set_wedged(gt);
 	mutex_unlock(&gt->reset.mutex);
 }
@@ -1186,7 +1186,7 @@ void intel_gt_handle_error(struct intel_gt *gt,
 	 * isn't the case at least when we get here by doing a
 	 * simulated reset via debugfs, so get an RPM reference.
 	 */
-	wakeref = intel_runtime_pm_get(&gt->i915->runtime_pm);
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 
 	engine_mask &= INTEL_INFO(gt->i915)->engine_mask;
 
@@ -1246,7 +1246,7 @@ void intel_gt_handle_error(struct intel_gt *gt,
 	wake_up_all(&gt->reset.queue);
 
 out:
-	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 }
 
 int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index e8a40df79bd0..569a4105d49e 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -1695,14 +1695,14 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 	if (intel_gt_is_wedged(gt))
 		return -EIO; /* we're long past hope of a successful reset */
 
-	wakeref = intel_runtime_pm_get(&gt->i915->runtime_pm);
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 	saved_hangcheck = fetch_and_zero(&i915_modparams.enable_hangcheck);
 	drain_delayed_work(&gt->hangcheck.work); /* flush param */
 
 	err = intel_gt_live_subtests(tests, gt);
 
 	i915_modparams.enable_hangcheck = saved_hangcheck;
-	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c
index d79482db7fe8..419b38fa7828 100644
--- a/drivers/gpu/drm/i915/gt/selftest_reset.c
+++ b/drivers/gpu/drm/i915/gt/selftest_reset.c
@@ -17,7 +17,7 @@ static int igt_global_reset(void *arg)
 	/* Check that we can issue a global GPU reset */
 
 	igt_global_reset_lock(gt);
-	wakeref = intel_runtime_pm_get(&gt->i915->runtime_pm);
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 
 	reset_count = i915_reset_count(&gt->i915->gpu_error);
 
@@ -28,7 +28,7 @@ static int igt_global_reset(void *arg)
 		err = -EINVAL;
 	}
 
-	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 	igt_global_reset_unlock(gt);
 
 	if (intel_gt_is_wedged(gt))
@@ -45,14 +45,14 @@ static int igt_wedged_reset(void *arg)
 	/* Check that we can recover a wedged device with a GPU reset */
 
 	igt_global_reset_lock(gt);
-	wakeref = intel_runtime_pm_get(&gt->i915->runtime_pm);
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 
 	intel_gt_set_wedged(gt);
 
 	GEM_BUG_ON(!intel_gt_is_wedged(gt));
 	intel_gt_reset(gt, ALL_ENGINES, NULL);
 
-	intel_runtime_pm_put(&gt->i915->runtime_pm, wakeref);
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 	igt_global_reset_unlock(gt);
 
 	return intel_gt_is_wedged(gt) ? -EIO : 0;
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 95627e80f246..74952bda9256 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -256,7 +256,7 @@ switch_to_scratch_context(struct intel_engine_cs *engine,
 	GEM_BUG_ON(IS_ERR(ce));
 
 	rq = ERR_PTR(-ENODEV);
-	with_intel_runtime_pm(&engine->i915->runtime_pm, wakeref)
+	with_intel_runtime_pm(engine->uncore->rpm, wakeref)
 		rq = igt_spinner_create_request(spin, ce, MI_NOOP);
 
 	intel_context_put(ce);
@@ -313,7 +313,7 @@ static int check_whitelist_across_reset(struct intel_engine_cs *engine,
 	if (err)
 		goto out_spin;
 
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+	with_intel_runtime_pm(engine->uncore->rpm, wakeref)
 		err = reset(engine);
 
 	igt_spinner_end(&spin);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
index 36332064de9c..2cf2d3314f62 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
@@ -607,7 +607,6 @@ out_unlock:
 void intel_guc_log_relay_flush(struct intel_guc_log *log)
 {
 	struct intel_guc *guc = log_to_guc(log);
-	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
 	intel_wakeref_t wakeref;
 
 	/*
@@ -616,7 +615,7 @@ void intel_guc_log_relay_flush(struct intel_guc_log *log)
 	 */
 	flush_work(&log->relay.flush_work);
 
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+	with_intel_runtime_pm(guc_to_gt(guc)->uncore->rpm, wakeref)
 		guc_action_flush_log(guc);
 
 	/* GuC would have updated log buffer by now, so capture it */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index d4625c97b4f9..33608a114d4e 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -185,7 +185,7 @@ int intel_huc_check_status(struct intel_huc *huc)
 	if (!intel_huc_is_supported(huc))
 		return -ENODEV;
 
-	with_intel_runtime_pm(&gt->i915->runtime_pm, wakeref)
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref)
 		status = intel_uncore_read(gt->uncore, huc->status.reg);
 
 	return (status & huc->status.mask) == huc->status.value;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 29a9eec60d2e..3fdbc935d155 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -587,7 +587,7 @@ void intel_uc_suspend(struct intel_uc *uc)
 	if (!intel_guc_is_running(guc))
 		return;
 
-	with_intel_runtime_pm(&uc_to_gt(uc)->i915->runtime_pm, wakeref)
+	with_intel_runtime_pm(uc_to_gt(uc)->uncore->rpm, wakeref)
 		intel_uc_runtime_suspend(uc);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index f2371b6083c6..3af7f7914c40 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -412,7 +412,7 @@ void gen9_reset_guc_interrupts(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 
-	assert_rpm_wakelock_held(&gt->i915->runtime_pm);
+	assert_rpm_wakelock_held(gt->uncore->rpm);
 
 	spin_lock_irq(&gt->irq_lock);
 	gen6_gt_pm_reset_iir(gt, gt->pm_guc_events);
@@ -423,7 +423,7 @@ void gen9_enable_guc_interrupts(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 
-	assert_rpm_wakelock_held(&gt->i915->runtime_pm);
+	assert_rpm_wakelock_held(gt->uncore->rpm);
 
 	spin_lock_irq(&gt->irq_lock);
 	if (!guc->interrupts.enabled) {
@@ -440,7 +440,7 @@ void gen9_disable_guc_interrupts(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
 
-	assert_rpm_wakelock_held(&gt->i915->runtime_pm);
+	assert_rpm_wakelock_held(gt->uncore->rpm);
 
 	spin_lock_irq(&gt->irq_lock);
 	guc->interrupts.enabled = false;
-- 
cgit v1.2.3


From 08ad9a3846fc72b047b110b36d162ffbcf298fa2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 20:47:58 +0100
Subject: drm/i915/execlists: Fix annotation for decoupling virtual request

As we may signal a request and take the engine->active.lock within the
signaler, the engine submission paths have to use a nested annotation on
their requests -- but we guarantee that we can never submit on the same
engine as the signaling fence.

<4>[  723.763281] WARNING: possible circular locking dependency detected
<4>[  723.763285] 5.3.0-g80fa0e042cdb-drmtip_379+ #1 Tainted: G     U
<4>[  723.763288] ------------------------------------------------------
<4>[  723.763291] gem_exec_await/1388 is trying to acquire lock:
<4>[  723.763294] ffff93a7b53221d8 (&engine->active.lock){..-.}, at: execlists_submit_request+0x2b/0x1e0 [i915]
<4>[  723.763378]
                  but task is already holding lock:
<4>[  723.763381] ffff93a7c25f6d20 (&i915_request_get(rq)->submit/1){-.-.}, at: __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  723.763420]
                  which lock already depends on the new lock.

<4>[  723.763423]
                  the existing dependency chain (in reverse order) is:
<4>[  723.763427]
                  -> #2 (&i915_request_get(rq)->submit/1){-.-.}:
<4>[  723.763434]        _raw_spin_lock_irqsave_nested+0x39/0x50
<4>[  723.763478]        __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  723.763513]        intel_engine_breadcrumbs_irq+0x3aa/0x5e0 [i915]
<4>[  723.763600]        cs_irq_handler+0x49/0x50 [i915]
<4>[  723.763659]        gen11_gt_irq_handler+0x17b/0x280 [i915]
<4>[  723.763690]        gen11_irq_handler+0x54/0xf0 [i915]
<4>[  723.763695]        __handle_irq_event_percpu+0x41/0x2d0
<4>[  723.763699]        handle_irq_event_percpu+0x2b/0x70
<4>[  723.763702]        handle_irq_event+0x2f/0x50
<4>[  723.763706]        handle_edge_irq+0xee/0x1a0
<4>[  723.763709]        do_IRQ+0x7e/0x160
<4>[  723.763712]        ret_from_intr+0x0/0x1d
<4>[  723.763717]        __slab_alloc.isra.28.constprop.33+0x4f/0x70
<4>[  723.763720]        kmem_cache_alloc+0x28d/0x2f0
<4>[  723.763724]        vm_area_dup+0x15/0x40
<4>[  723.763727]        dup_mm+0x2dd/0x550
<4>[  723.763730]        copy_process+0xf21/0x1ef0
<4>[  723.763734]        _do_fork+0x71/0x670
<4>[  723.763737]        __se_sys_clone+0x6e/0xa0
<4>[  723.763741]        do_syscall_64+0x4f/0x210
<4>[  723.763744]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  723.763747]
                  -> #1 (&(&rq->lock)->rlock#2){-.-.}:
<4>[  723.763752]        _raw_spin_lock+0x2a/0x40
<4>[  723.763789]        __unwind_incomplete_requests+0x3eb/0x450 [i915]
<4>[  723.763825]        __execlists_submission_tasklet+0x9ec/0x1d60 [i915]
<4>[  723.763864]        execlists_submission_tasklet+0x34/0x50 [i915]
<4>[  723.763874]        tasklet_action_common.isra.5+0x47/0xb0
<4>[  723.763878]        __do_softirq+0xd8/0x4ae
<4>[  723.763881]        irq_exit+0xa9/0xc0
<4>[  723.763883]        smp_apic_timer_interrupt+0xb7/0x280
<4>[  723.763887]        apic_timer_interrupt+0xf/0x20
<4>[  723.763892]        cpuidle_enter_state+0xae/0x450
<4>[  723.763895]        cpuidle_enter+0x24/0x40
<4>[  723.763899]        do_idle+0x1e7/0x250
<4>[  723.763902]        cpu_startup_entry+0x14/0x20
<4>[  723.763905]        start_secondary+0x15f/0x1b0
<4>[  723.763908]        secondary_startup_64+0xa4/0xb0
<4>[  723.763911]
                  -> #0 (&engine->active.lock){..-.}:
<4>[  723.763916]        __lock_acquire+0x15d8/0x1ea0
<4>[  723.763919]        lock_acquire+0xa6/0x1c0
<4>[  723.763922]        _raw_spin_lock_irqsave+0x33/0x50
<4>[  723.763956]        execlists_submit_request+0x2b/0x1e0 [i915]
<4>[  723.764002]        submit_notify+0xa8/0x13c [i915]
<4>[  723.764035]        __i915_sw_fence_complete+0x81/0x250 [i915]
<4>[  723.764054]        i915_sw_fence_wake+0x51/0x64 [i915]
<4>[  723.764054]        __i915_sw_fence_complete+0x1ee/0x250 [i915]
<4>[  723.764054]        dma_i915_sw_fence_wake_timer+0x14/0x20 [i915]
<4>[  723.764054]        dma_fence_signal_locked+0x9e/0x1c0
<4>[  723.764054]        dma_fence_signal+0x1f/0x40
<4>[  723.764054]        vgem_fence_signal_ioctl+0x67/0xc0 [vgem]
<4>[  723.764054]        drm_ioctl_kernel+0x83/0xf0
<4>[  723.764054]        drm_ioctl+0x2f3/0x3b0
<4>[  723.764054]        do_vfs_ioctl+0xa0/0x6f0
<4>[  723.764054]        ksys_ioctl+0x35/0x60
<4>[  723.764054]        __x64_sys_ioctl+0x11/0x20
<4>[  723.764054]        do_syscall_64+0x4f/0x210
<4>[  723.764054]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  723.764054]
                  other info that might help us debug this:

<4>[  723.764054] Chain exists of:
                    &engine->active.lock --> &(&rq->lock)->rlock#2 --> &i915_request_get(rq)->submit/1

<4>[  723.764054]  Possible unsafe locking scenario:

<4>[  723.764054]        CPU0                    CPU1
<4>[  723.764054]        ----                    ----
<4>[  723.764054]   lock(&i915_request_get(rq)->submit/1);
<4>[  723.764054]                                lock(&(&rq->lock)->rlock#2);
<4>[  723.764054]                                lock(&i915_request_get(rq)->submit/1);
<4>[  723.764054]   lock(&engine->active.lock);
<4>[  723.764054]
                   *** DEADLOCK ***

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111862
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004194758.19679-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 468438fb47af..432b8b60c4c0 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -928,7 +928,8 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 			 */
 			if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
 				     &rq->fence.flags)) {
-				spin_lock(&rq->lock);
+				spin_lock_nested(&rq->lock,
+						 SINGLE_DEPTH_NESTING);
 				i915_request_cancel_breadcrumb(rq);
 				spin_unlock(&rq->lock);
 			}
-- 
cgit v1.2.3


From 1664f35aa718815527368e57b0d4ed5bc80e889c Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 4 Oct 2019 21:31:21 +0100
Subject: drm/i915/selftests: Appease lockdep

Disable irqs around updating the context image to keep lockdep happy:

<4>[  673.483340] WARNING: possible irq lock inversion dependency detected
<4>[  673.483342] 5.4.0-rc1-CI-Trybot_5118+ #1 Tainted: G     U
<4>[  673.483342] --------------------------------------------------------
<4>[  673.483343] swapper/2/0 just changed the state of lock:
<4>[  673.483344] ffff88845db885a0 (&i915_request_get(rq)->submit/1){-...}, at: __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.483387] but this lock took another, HARDIRQ-unsafe lock in the past:
<4>[  673.483388]  (&ce->pin_mutex/2){+...}
<4>[  673.483389]

                  and interrupts could create inverse lock ordering between them.

<4>[  673.483390]
                  other info that might help us debug this:
<4>[  673.483390] Chain exists of:
                    &i915_request_get(rq)->submit/1 --> &engine->active.lock --> &ce->pin_mutex/2

<4>[  673.483392]  Possible interrupt unsafe locking scenario:

<4>[  673.483392]        CPU0                    CPU1
<4>[  673.483393]        ----                    ----
<4>[  673.483393]   lock(&ce->pin_mutex/2);
<4>[  673.483394]                                local_irq_disable();
<4>[  673.483395]                                lock(&i915_request_get(rq)->submit/1);
<4>[  673.483396]                                lock(&engine->active.lock);
<4>[  673.483396]   <Interrupt>
<4>[  673.483397]     lock(&i915_request_get(rq)->submit/1);
<4>[  673.483398]
                   *** DEADLOCK ***

<4>[  673.483398] 2 locks held by swapper/2/0:
<4>[  673.483399]  #0: ffff8883f61ac9b0 (&(&gt->irq_lock)->rlock){-.-.}, at: gen11_gt_irq_handler+0x42/0x280 [i915]
<4>[  673.483433]  #1: ffff88845db8c418 (&(&rq->lock)->rlock){-.-.}, at: intel_engine_breadcrumbs_irq+0x34a/0x5a0 [i915]
<4>[  673.483463]
                  the shortest dependencies between 2nd lock and 1st lock:
<4>[  673.483466]   -> (&ce->pin_mutex/2){+...} ops: 614520 {
<4>[  673.483468]      HARDIRQ-ON-W at:
<4>[  673.483471]                         lock_acquire+0xa7/0x1c0
<4>[  673.483501]                         live_unlite_restore+0x1d8/0x6c0 [i915]
<4>[  673.483543]                         __i915_subtests+0xb8/0x210 [i915]
<4>[  673.483581]                         __run_selftests+0x112/0x170 [i915]
<4>[  673.483615]                         i915_live_selftests+0x2c/0x60 [i915]
<4>[  673.483644]                         i915_pci_probe+0x93/0x1b0 [i915]
<4>[  673.483646]                         pci_device_probe+0x9e/0x120
<4>[  673.483648]                         really_probe+0xea/0x420
<4>[  673.483649]                         driver_probe_device+0x10b/0x120
<4>[  673.483651]                         device_driver_attach+0x4a/0x50
<4>[  673.483652]                         __driver_attach+0x97/0x130
<4>[  673.483653]                         bus_for_each_dev+0x74/0xc0
<4>[  673.483654]                         bus_add_driver+0x142/0x220
<4>[  673.483655]                         driver_register+0x56/0xf0
<4>[  673.483657]                         do_one_initcall+0x58/0x2ff
<4>[  673.483659]                         do_init_module+0x56/0x1f8
<4>[  673.483660]                         load_module+0x243e/0x29f0
<4>[  673.483661]                         __do_sys_finit_module+0xe9/0x110
<4>[  673.483662]                         do_syscall_64+0x4f/0x210
<4>[  673.483665]                         entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  673.483665]      INITIAL USE at:
<4>[  673.483667]                        lock_acquire+0xa7/0x1c0
<4>[  673.483698]                        live_unlite_restore+0x1d8/0x6c0 [i915]
<4>[  673.483733]                        __i915_subtests+0xb8/0x210 [i915]
<4>[  673.483764]                        __run_selftests+0x112/0x170 [i915]
<4>[  673.483793]                        i915_live_selftests+0x2c/0x60 [i915]
<4>[  673.483821]                        i915_pci_probe+0x93/0x1b0 [i915]
<4>[  673.483822]                        pci_device_probe+0x9e/0x120
<4>[  673.483824]                        really_probe+0xea/0x420
<4>[  673.483825]                        driver_probe_device+0x10b/0x120
<4>[  673.483826]                        device_driver_attach+0x4a/0x50
<4>[  673.483827]                        __driver_attach+0x97/0x130
<4>[  673.483828]                        bus_for_each_dev+0x74/0xc0
<4>[  673.483829]                        bus_add_driver+0x142/0x220
<4>[  673.483830]                        driver_register+0x56/0xf0
<4>[  673.483831]                        do_one_initcall+0x58/0x2ff
<4>[  673.483833]                        do_init_module+0x56/0x1f8
<4>[  673.483834]                        load_module+0x243e/0x29f0
<4>[  673.483835]                        __do_sys_finit_module+0xe9/0x110
<4>[  673.483836]                        do_syscall_64+0x4f/0x210
<4>[  673.483837]                        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  673.483838]    }
<4>[  673.483868]    ... key      at: [<ffffffffa0a8f132>] __key.70113+0x2/0xffffffffffef2ed0 [i915]
<4>[  673.483869]    ... acquired at:
<4>[  673.483935]    __execlists_reset+0xfb/0xc20 [i915]
<4>[  673.483965]    execlists_reset+0x3d/0x50 [i915]
<4>[  673.483995]    intel_engine_reset+0xdf/0x230 [i915]
<4>[  673.484022]    live_preempt_hang+0x1d7/0x2e0 [i915]
<4>[  673.484064]    __i915_subtests+0xb8/0x210 [i915]
<4>[  673.484130]    __run_selftests+0x112/0x170 [i915]
<4>[  673.484163]    i915_live_selftests+0x2c/0x60 [i915]
<4>[  673.484193]    i915_pci_probe+0x93/0x1b0 [i915]
<4>[  673.484194]    pci_device_probe+0x9e/0x120
<4>[  673.484195]    really_probe+0xea/0x420
<4>[  673.484196]    driver_probe_device+0x10b/0x120
<4>[  673.484197]    device_driver_attach+0x4a/0x50
<4>[  673.484198]    __driver_attach+0x97/0x130
<4>[  673.484199]    bus_for_each_dev+0x74/0xc0
<4>[  673.484200]    bus_add_driver+0x142/0x220
<4>[  673.484202]    driver_register+0x56/0xf0
<4>[  673.484203]    do_one_initcall+0x58/0x2ff
<4>[  673.484204]    do_init_module+0x56/0x1f8
<4>[  673.484205]    load_module+0x243e/0x29f0
<4>[  673.484206]    __do_sys_finit_module+0xe9/0x110
<4>[  673.484207]    do_syscall_64+0x4f/0x210
<4>[  673.484208]    entry_SYSCALL_64_after_hwframe+0x49/0xbe

<4>[  673.484209]  -> (&engine->active.lock){..-.} ops: 972791 {
<4>[  673.484211]     IN-SOFTIRQ-W at:
<4>[  673.484213]                       lock_acquire+0xa7/0x1c0
<4>[  673.484214]                       _raw_spin_lock_irqsave+0x33/0x50
<4>[  673.484244]                       execlists_submission_tasklet+0xaf/0x100 [i915]
<4>[  673.484246]                       tasklet_action_common.isra.18+0x6c/0x1c0
<4>[  673.484247]                       __do_softirq+0xdf/0x47f
<4>[  673.484248]                       irq_exit+0xba/0xc0
<4>[  673.484249]                       do_IRQ+0x83/0x160
<4>[  673.484250]                       ret_from_intr+0x0/0x1d
<4>[  673.484252]                       cpuidle_enter_state+0xb2/0x450
<4>[  673.484253]                       cpuidle_enter+0x24/0x40
<4>[  673.484254]                       do_idle+0x1e7/0x250
<4>[  673.484256]                       cpu_startup_entry+0x14/0x20
<4>[  673.484257]                       start_secondary+0x15f/0x1b0
<4>[  673.484258]                       secondary_startup_64+0xa4/0xb0
<4>[  673.484259]     INITIAL USE at:
<4>[  673.484261]                      lock_acquire+0xa7/0x1c0
<4>[  673.484290]                      intel_engine_init_active+0x7e/0xb0 [i915]
<4>[  673.484305]                      intel_engines_setup+0x1cd/0x3b0 [i915]
<4>[  673.484305]                      i915_gem_init+0x12d/0x900 [i915]
<4>[  673.484305]                      i915_driver_probe+0xb70/0x15d0 [i915]
<4>[  673.484305]                      i915_pci_probe+0x43/0x1b0 [i915]
<4>[  673.484305]                      pci_device_probe+0x9e/0x120
<4>[  673.484305]                      really_probe+0xea/0x420
<4>[  673.484305]                      driver_probe_device+0x10b/0x120
<4>[  673.484305]                      device_driver_attach+0x4a/0x50
<4>[  673.484305]                      __driver_attach+0x97/0x130
<4>[  673.484305]                      bus_for_each_dev+0x74/0xc0
<4>[  673.484305]                      bus_add_driver+0x142/0x220
<4>[  673.484305]                      driver_register+0x56/0xf0
<4>[  673.484305]                      do_one_initcall+0x58/0x2ff
<4>[  673.484305]                      do_init_module+0x56/0x1f8
<4>[  673.484305]                      load_module+0x243e/0x29f0
<4>[  673.484305]                      __do_sys_finit_module+0xe9/0x110
<4>[  673.484305]                      do_syscall_64+0x4f/0x210
<4>[  673.484305]                      entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  673.484305]   }
<4>[  673.484305]   ... key      at: [<ffffffffa0a8f160>] __key.70307+0x0/0xffffffffffef2ea0 [i915]
<4>[  673.484305]   ... acquired at:
<4>[  673.484305]    _raw_spin_lock_irqsave+0x33/0x50
<4>[  673.484305]    execlists_submit_request+0x2b/0x1e0 [i915]
<4>[  673.484305]    submit_notify+0xa8/0x13c [i915]
<4>[  673.484305]    __i915_sw_fence_complete+0x81/0x250 [i915]
<4>[  673.484305]    i915_sw_fence_wake+0x51/0x70 [i915]
<4>[  673.484305]    __i915_sw_fence_complete+0x1ee/0x250 [i915]
<4>[  673.484305]    dma_i915_sw_fence_wake+0x1b/0x30 [i915]
<4>[  673.484305]    dma_fence_signal_locked+0x9e/0x1b0
<4>[  673.484305]    dma_fence_signal+0x1f/0x40
<4>[  673.484305]    fence_work+0x28/0x80 [i915]
<4>[  673.484305]    process_one_work+0x26a/0x620
<4>[  673.484305]    worker_thread+0x37/0x380
<4>[  673.484305]    kthread+0x119/0x130
<4>[  673.484305]    ret_from_fork+0x24/0x50

<4>[  673.484305] -> (&i915_request_get(rq)->submit/1){-...} ops: 857694 {
<4>[  673.484305]    IN-HARDIRQ-W at:
<4>[  673.484305]                     lock_acquire+0xa7/0x1c0
<4>[  673.484305]                     _raw_spin_lock_irqsave_nested+0x39/0x50
<4>[  673.484305]                     __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.484305]                     intel_engine_breadcrumbs_irq+0x3d0/0x5a0 [i915]
<4>[  673.484305]                     cs_irq_handler+0x39/0x50 [i915]
<4>[  673.484305]                     gen11_gt_irq_handler+0x17b/0x280 [i915]
<4>[  673.484305]                     gen11_irq_handler+0x54/0xf0 [i915]
<4>[  673.484305]                     __handle_irq_event_percpu+0x41/0x2c0
<4>[  673.484305]                     handle_irq_event_percpu+0x2b/0x70
<4>[  673.484305]                     handle_irq_event+0x2f/0x50
<4>[  673.484305]                     handle_edge_irq+0x99/0x1b0
<4>[  673.484305]                     do_IRQ+0x7e/0x160
<4>[  673.484305]                     ret_from_intr+0x0/0x1d
<4>[  673.484305]                     cpuidle_enter_state+0xb2/0x450
<4>[  673.484305]                     cpuidle_enter+0x24/0x40
<4>[  673.484305]                     do_idle+0x1e7/0x250
<4>[  673.484305]                     cpu_startup_entry+0x14/0x20
<4>[  673.484305]                     start_secondary+0x15f/0x1b0
<4>[  673.484305]                     secondary_startup_64+0xa4/0xb0
<4>[  673.484305]    INITIAL USE at:
<4>[  673.484305]                    lock_acquire+0xa7/0x1c0
<4>[  673.484305]                    _raw_spin_lock_irqsave_nested+0x39/0x50
<4>[  673.484305]                    __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.484305]                    __engine_park+0x233/0x420 [i915]
<4>[  673.484305]                    ____intel_wakeref_put_last+0x1c/0x70 [i915]
<4>[  673.484305]                    intel_gt_resume+0x202/0x2c0 [i915]
<4>[  673.484305]                    i915_gem_init+0x36e/0x900 [i915]
<4>[  673.484305]                    i915_driver_probe+0xb70/0x15d0 [i915]
<4>[  673.484305]                    i915_pci_probe+0x43/0x1b0 [i915]
<4>[  673.484305]                    pci_device_probe+0x9e/0x120
<4>[  673.484305]                    really_probe+0xea/0x420
<4>[  673.484305]                    driver_probe_device+0x10b/0x120
<4>[  673.484305]                    device_driver_attach+0x4a/0x50
<4>[  673.484305]                    __driver_attach+0x97/0x130
<4>[  673.484305]                    bus_for_each_dev+0x74/0xc0
<4>[  673.484305]                    bus_add_driver+0x142/0x220
<4>[  673.484305]                    driver_register+0x56/0xf0
<4>[  673.484305]                    do_one_initcall+0x58/0x2ff
<4>[  673.484305]                    do_init_module+0x56/0x1f8
<4>[  673.484305]                    load_module+0x243e/0x29f0
<4>[  673.484305]                    __do_sys_finit_module+0xe9/0x110
<4>[  673.484305]                    do_syscall_64+0x4f/0x210
<4>[  673.484305]                    entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  673.484305]  }
<4>[  673.484305]  ... key      at: [<ffffffffa0a8f6a1>] __key.80173+0x1/0xffffffffffef2960 [i915]
<4>[  673.484305]  ... acquired at:
<4>[  673.484305]    mark_lock+0x382/0x500
<4>[  673.484305]    __lock_acquire+0x7e1/0x15d0
<4>[  673.484305]    lock_acquire+0xa7/0x1c0
<4>[  673.484305]    _raw_spin_lock_irqsave_nested+0x39/0x50
<4>[  673.484305]    __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.484305]    intel_engine_breadcrumbs_irq+0x3d0/0x5a0 [i915]
<4>[  673.484305]    cs_irq_handler+0x39/0x50 [i915]
<4>[  673.484305]    gen11_gt_irq_handler+0x17b/0x280 [i915]
<4>[  673.484305]    gen11_irq_handler+0x54/0xf0 [i915]
<4>[  673.484305]    __handle_irq_event_percpu+0x41/0x2c0
<4>[  673.484305]    handle_irq_event_percpu+0x2b/0x70
<4>[  673.484305]    handle_irq_event+0x2f/0x50
<4>[  673.484305]    handle_edge_irq+0x99/0x1b0
<4>[  673.484305]    do_IRQ+0x7e/0x160
<4>[  673.484305]    ret_from_intr+0x0/0x1d
<4>[  673.484305]    cpuidle_enter_state+0xb2/0x450
<4>[  673.484305]    cpuidle_enter+0x24/0x40
<4>[  673.484305]    do_idle+0x1e7/0x250
<4>[  673.484305]    cpu_startup_entry+0x14/0x20
<4>[  673.484305]    start_secondary+0x15f/0x1b0
<4>[  673.484305]    secondary_startup_64+0xa4/0xb0

<4>[  673.484305]
                  stack backtrace:
<4>[  673.484305] CPU: 2 PID: 0 Comm: swapper/2 Tainted: G     U            5.4.0-rc1-CI-Trybot_5118+ #1
<4>[  673.484305] Hardware name: Intel Corporation Ice Lake Client Platform/IceLake U DDR4 SODIMM PD RVP TLC, BIOS ICLSFWR1.R00.3183.A00.1905020411 05/02/2019
<4>[  673.484305] Call Trace:
<4>[  673.484305]  <IRQ>
<4>[  673.484305]  dump_stack+0x67/0x9b
<4>[  673.484305]  check_usage_forwards+0x13c/0x150
<4>[  673.484305]  ? mark_lock+0x382/0x500
<4>[  673.484305]  mark_lock+0x382/0x500
<4>[  673.484305]  ? check_usage_backwards+0x140/0x140
<4>[  673.484305]  __lock_acquire+0x7e1/0x15d0
<4>[  673.484305]  ? debug_object_deactivate+0x17e/0x190
<4>[  673.484305]  lock_acquire+0xa7/0x1c0
<4>[  673.484305]  ? __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.484305]  _raw_spin_lock_irqsave_nested+0x39/0x50
<4>[  673.484305]  ? __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.484305]  __i915_sw_fence_complete+0x1b2/0x250 [i915]
<4>[  673.484305]  intel_engine_breadcrumbs_irq+0x3d0/0x5a0 [i915]
<4>[  673.484305]  cs_irq_handler+0x39/0x50 [i915]
<4>[  673.484305]  gen11_gt_irq_handler+0x17b/0x280 [i915]
<4>[  673.484305]  gen11_irq_handler+0x54/0xf0 [i915]
<4>[  673.484305]  __handle_irq_event_percpu+0x41/0x2c0
<4>[  673.484305]  handle_irq_event_percpu+0x2b/0x70
<4>[  673.484305]  handle_irq_event+0x2f/0x50
<4>[  673.484305]  handle_edge_irq+0x99/0x1b0
<4>[  673.484305]  do_IRQ+0x7e/0x160
<4>[  673.484305]  common_interrupt+0xf/0xf
<4>[  673.484305]  </IRQ>

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004203121.31138-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/selftest_lrc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 393ae5321e1d..198cf2f754f4 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -143,11 +143,11 @@ static int live_unlite_restore(struct drm_i915_private *i915, int prio)
 		GEM_BUG_ON(!ce[1]->ring->size);
 		intel_ring_reset(ce[1]->ring, ce[1]->ring->size / 2);
 
-		local_bh_disable(); /* appease lockdep */
+		local_irq_disable(); /* appease lockdep */
 		__context_pin_acquire(ce[1]);
 		__execlists_update_reg_state(ce[1], engine);
 		__context_pin_release(ce[1]);
-		local_bh_enable();
+		local_irq_enable();
 
 		rq[0] = igt_spinner_create_request(&spin, ce[0], MI_ARB_CHECK);
 		if (IS_ERR(rq[0])) {
-- 
cgit v1.2.3


From a1b58ee3cb34c433167b7b7d3465ab3ca0e3daf1 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sun, 6 Oct 2019 17:49:54 +0100
Subject: drm/i915/gt: Treat a busy timeline as 'active' while waiting

If we cannot claim the timeline->mutex while preparing for a wait on it,
we have to skip the timeline. In doing so, treat it as active so that
under a intel_gt_wait_for_idle() loop, we repeat the wait after
scheduling away.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191006165002.30312-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_gt_requests.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index d69e78478eea..ca606b79fd5e 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -34,8 +34,10 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 
 	spin_lock_irqsave(&timelines->lock, flags);
 	list_for_each_entry_safe(tl, tn, &timelines->active_list, link) {
-		if (!mutex_trylock(&tl->mutex))
+		if (!mutex_trylock(&tl->mutex)) {
+			active_count++; /* report busy to caller, try again? */
 			continue;
+		}
 
 		intel_timeline_get(tl);
 		GEM_BUG_ON(!tl->active_count);
-- 
cgit v1.2.3


From c6875f3aacf2a5a913205accddabf0bfb75cac76 Mon Sep 17 00:00:00 2001
From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Date: Mon, 30 Sep 2019 16:44:41 -0400
Subject: x86/xen: Return from panic notifier

Currently execution of panic() continues until Xen's panic notifier
(xen_panic_event()) is called at which point we make a hypercall that
never returns.

This means that any notifier that is supposed to be called later as
well as significant part of panic() code (such as pstore writes from
kmsg_dump()) is never executed.

There is no reason for xen_panic_event() to be this last point in
execution since panic()'s emergency_restart() will call into
xen_emergency_restart() from where we can perform our hypercall.

Nevertheless, we will provide xen_legacy_crash boot option that will
preserve original behavior during crash. This option could be used,
for example, if running kernel dumper (which happens after panic
notifiers) is undesirable.

Reported-by: James Dingwall <james@dingwall.me.uk>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
---
 Documentation/admin-guide/kernel-parameters.txt |  4 ++++
 arch/x86/xen/enlighten.c                        | 28 ++++++++++++++++++++++---
 2 files changed, 29 insertions(+), 3 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 4c1971960afa..5ea005c9e2d6 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5267,6 +5267,10 @@
 				the unplug protocol
 			never -- do not unplug even if version check succeeds
 
+	xen_legacy_crash	[X86,XEN]
+			Crash from Xen panic notifier, without executing late
+			panic() code such as dumping handler.
+
 	xen_nopvspin	[X86,XEN]
 			Disables the ticketlock slowpath using Xen PV
 			optimizations.
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 750f46ad018a..205b1176084f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -269,19 +269,41 @@ void xen_reboot(int reason)
 		BUG();
 }
 
+static int reboot_reason = SHUTDOWN_reboot;
+static bool xen_legacy_crash;
 void xen_emergency_restart(void)
 {
-	xen_reboot(SHUTDOWN_reboot);
+	xen_reboot(reboot_reason);
 }
 
 static int
 xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr)
 {
-	if (!kexec_crash_loaded())
-		xen_reboot(SHUTDOWN_crash);
+	if (!kexec_crash_loaded()) {
+		if (xen_legacy_crash)
+			xen_reboot(SHUTDOWN_crash);
+
+		reboot_reason = SHUTDOWN_crash;
+
+		/*
+		 * If panic_timeout==0 then we are supposed to wait forever.
+		 * However, to preserve original dom0 behavior we have to drop
+		 * into hypervisor. (domU behavior is controlled by its
+		 * config file)
+		 */
+		if (panic_timeout == 0)
+			panic_timeout = -1;
+	}
 	return NOTIFY_DONE;
 }
 
+static int __init parse_xen_legacy_crash(char *arg)
+{
+	xen_legacy_crash = true;
+	return 0;
+}
+early_param("xen_legacy_crash", parse_xen_legacy_crash);
+
 static struct notifier_block xen_panic_block = {
 	.notifier_call = xen_panic_event,
 	.priority = INT_MIN
-- 
cgit v1.2.3


From 7a243c82ea527cd1da47381ad9cd646844f3b693 Mon Sep 17 00:00:00 2001
From: Jia Guo <guojia12@huawei.com>
Date: Sun, 6 Oct 2019 17:57:47 -0700
Subject: ocfs2: clear zero in unaligned direct IO

Unused portion of a part-written fs-block-sized block is not set to zero
in unaligned append direct write.This can lead to serious data
inconsistencies.

Ocfs2 manage disk with cluster size(for example, 1M), part-written in
one cluster will change the cluster state from UN-WRITTEN to WRITTEN,
VFS(function dio_zero_block) doesn't do the cleaning because bh's state
is not set to NEW in function ocfs2_dio_wr_get_block when we write a
WRITTEN cluster.  For example, the cluster size is 1M, file size is 8k
and we direct write from 14k to 15k, then 12k~14k and 15k~16k will
contain dirty data.

We have to deal with two cases:
 1.The starting position of direct write is outside the file.
 2.The starting position of direct write is located in the file.

We need set bh's state to NEW in the first case.  In the second case, we
need mapped twice because bh's state of area out file should be set to
NEW while area in file not.

[akpm@linux-foundation.org: coding style fixes]
Link: http://lkml.kernel.org/r/5292e287-8f1a-fd4a-1a14-661e555e0bed@huawei.com
Signed-off-by: Jia Guo <guojia12@huawei.com>
Reviewed-by: Yiwen Jiang <jiangyiwen@huawei.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <joseph.qi@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ocfs2/aops.c | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 8de1c9d644f6..50d56d9a0475 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2146,13 +2146,30 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
 	struct ocfs2_dio_write_ctxt *dwc = NULL;
 	struct buffer_head *di_bh = NULL;
 	u64 p_blkno;
-	loff_t pos = iblock << inode->i_sb->s_blocksize_bits;
+	unsigned int i_blkbits = inode->i_sb->s_blocksize_bits;
+	loff_t pos = iblock << i_blkbits;
+	sector_t endblk = (i_size_read(inode) - 1) >> i_blkbits;
 	unsigned len, total_len = bh_result->b_size;
 	int ret = 0, first_get_block = 0;
 
 	len = osb->s_clustersize - (pos & (osb->s_clustersize - 1));
 	len = min(total_len, len);
 
+	/*
+	 * bh_result->b_size is count in get_more_blocks according to write
+	 * "pos" and "end", we need map twice to return different buffer state:
+	 * 1. area in file size, not set NEW;
+	 * 2. area out file size, set  NEW.
+	 *
+	 *		   iblock    endblk
+	 * |--------|---------|---------|---------
+	 * |<-------area in file------->|
+	 */
+
+	if ((iblock <= endblk) &&
+	    ((iblock + ((len - 1) >> i_blkbits)) > endblk))
+		len = (endblk - iblock + 1) << i_blkbits;
+
 	mlog(0, "get block of %lu at %llu:%u req %u\n",
 			inode->i_ino, pos, len, total_len);
 
@@ -2236,6 +2253,9 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
 	if (desc->c_needs_zero)
 		set_buffer_new(bh_result);
 
+	if (iblock > endblk)
+		set_buffer_new(bh_result);
+
 	/* May sleep in end_io. It should not happen in a irq context. So defer
 	 * it to dio work queue. */
 	set_buffer_defer_completion(bh_result);
-- 
cgit v1.2.3


From 56e94ea132bb5c2c1d0b60a6aeb34dcb7d71a53d Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Sun, 6 Oct 2019 17:57:50 -0700
Subject: fs: ocfs2: fix possible null-pointer dereferences in
 ocfs2_xa_prepare_entry()

In ocfs2_xa_prepare_entry(), there is an if statement on line 2136 to
check whether loc->xl_entry is NULL:

    if (loc->xl_entry)

When loc->xl_entry is NULL, it is used on line 2158:

    ocfs2_xa_add_entry(loc, name_hash);
        loc->xl_entry->xe_name_hash = cpu_to_le32(name_hash);
        loc->xl_entry->xe_name_offset = cpu_to_le16(loc->xl_size);

and line 2164:

    ocfs2_xa_add_namevalue(loc, xi);
        loc->xl_entry->xe_value_size = cpu_to_le64(xi->xi_value_len);
        loc->xl_entry->xe_name_len = xi->xi_name_len;

Thus, possible null-pointer dereferences may occur.

To fix these bugs, if loc-xl_entry is NULL, ocfs2_xa_prepare_entry()
abnormally returns with -EINVAL.

These bugs are found by a static analysis tool STCheck written by us.

[akpm@linux-foundation.org: remove now-unused ocfs2_xa_add_entry()]
Link: http://lkml.kernel.org/r/20190726101447.9153-1-baijiaju1990@gmail.com
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Gang He <ghe@suse.com>
Cc: Jun Piao <piaojun@huawei.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ocfs2/xattr.c | 56 +++++++++++++++++++++++---------------------------------
 1 file changed, 23 insertions(+), 33 deletions(-)

diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 90c830e3758e..d8507972ee13 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -1490,18 +1490,6 @@ static int ocfs2_xa_check_space(struct ocfs2_xa_loc *loc,
 	return loc->xl_ops->xlo_check_space(loc, xi);
 }
 
-static void ocfs2_xa_add_entry(struct ocfs2_xa_loc *loc, u32 name_hash)
-{
-	loc->xl_ops->xlo_add_entry(loc, name_hash);
-	loc->xl_entry->xe_name_hash = cpu_to_le32(name_hash);
-	/*
-	 * We can't leave the new entry's xe_name_offset at zero or
-	 * add_namevalue() will go nuts.  We set it to the size of our
-	 * storage so that it can never be less than any other entry.
-	 */
-	loc->xl_entry->xe_name_offset = cpu_to_le16(loc->xl_size);
-}
-
 static void ocfs2_xa_add_namevalue(struct ocfs2_xa_loc *loc,
 				   struct ocfs2_xattr_info *xi)
 {
@@ -2133,29 +2121,31 @@ static int ocfs2_xa_prepare_entry(struct ocfs2_xa_loc *loc,
 	if (rc)
 		goto out;
 
-	if (loc->xl_entry) {
-		if (ocfs2_xa_can_reuse_entry(loc, xi)) {
-			orig_value_size = loc->xl_entry->xe_value_size;
-			rc = ocfs2_xa_reuse_entry(loc, xi, ctxt);
-			if (rc)
-				goto out;
-			goto alloc_value;
-		}
+	if (!loc->xl_entry) {
+		rc = -EINVAL;
+		goto out;
+	}
 
-		if (!ocfs2_xattr_is_local(loc->xl_entry)) {
-			orig_clusters = ocfs2_xa_value_clusters(loc);
-			rc = ocfs2_xa_value_truncate(loc, 0, ctxt);
-			if (rc) {
-				mlog_errno(rc);
-				ocfs2_xa_cleanup_value_truncate(loc,
-								"overwriting",
-								orig_clusters);
-				goto out;
-			}
+	if (ocfs2_xa_can_reuse_entry(loc, xi)) {
+		orig_value_size = loc->xl_entry->xe_value_size;
+		rc = ocfs2_xa_reuse_entry(loc, xi, ctxt);
+		if (rc)
+			goto out;
+		goto alloc_value;
+	}
+
+	if (!ocfs2_xattr_is_local(loc->xl_entry)) {
+		orig_clusters = ocfs2_xa_value_clusters(loc);
+		rc = ocfs2_xa_value_truncate(loc, 0, ctxt);
+		if (rc) {
+			mlog_errno(rc);
+			ocfs2_xa_cleanup_value_truncate(loc,
+							"overwriting",
+							orig_clusters);
+			goto out;
 		}
-		ocfs2_xa_wipe_namevalue(loc);
-	} else
-		ocfs2_xa_add_entry(loc, name_hash);
+	}
+	ocfs2_xa_wipe_namevalue(loc);
 
 	/*
 	 * If we get here, we have a blank entry.  Fill it.  We grow our
-- 
cgit v1.2.3


From 583fee3e12df0e6f1f66f063b989d8e7fed0e65a Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Sun, 6 Oct 2019 17:57:54 -0700
Subject: fs: ocfs2: fix a possible null-pointer dereference in
 ocfs2_write_end_nolock()

In ocfs2_write_end_nolock(), there are an if statement on lines 1976,
2047 and 2058, to check whether handle is NULL:

    if (handle)

When handle is NULL, it is used on line 2045:

	ocfs2_update_inode_fsync_trans(handle, inode, 1);
        oi->i_sync_tid = handle->h_transaction->t_tid;

Thus, a possible null-pointer dereference may occur.

To fix this bug, handle is checked before calling
ocfs2_update_inode_fsync_trans().

This bug is found by a static analysis tool STCheck written by us.

Link: http://lkml.kernel.org/r/20190726033705.32307-1-baijiaju1990@gmail.com
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Gang He <ghe@suse.com>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ocfs2/aops.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 50d56d9a0475..9cd0a6815933 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2049,7 +2049,8 @@ out_write_size:
 		inode->i_mtime = inode->i_ctime = current_time(inode);
 		di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
 		di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
-		ocfs2_update_inode_fsync_trans(handle, inode, 1);
+		if (handle)
+			ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	}
 	if (handle)
 		ocfs2_journal_dirty(handle, wc->w_di_bh);
-- 
cgit v1.2.3


From 2abb7d3b12d007c30193f48bebed781009bebdd2 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Sun, 6 Oct 2019 17:57:57 -0700
Subject: fs: ocfs2: fix a possible null-pointer dereference in
 ocfs2_info_scan_inode_alloc()

In ocfs2_info_scan_inode_alloc(), there is an if statement on line 283
to check whether inode_alloc is NULL:

    if (inode_alloc)

When inode_alloc is NULL, it is used on line 287:

    ocfs2_inode_lock(inode_alloc, &bh, 0);
        ocfs2_inode_lock_full_nested(inode, ...)
            struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);

Thus, a possible null-pointer dereference may occur.

To fix this bug, inode_alloc is checked on line 286.

This bug is found by a static analysis tool STCheck written by us.

Link: http://lkml.kernel.org/r/20190726033717.32359-1-baijiaju1990@gmail.com
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Gang He <ghe@suse.com>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ocfs2/ioctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index d6f7b299eb23..efeea208fdeb 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -283,7 +283,7 @@ static int ocfs2_info_scan_inode_alloc(struct ocfs2_super *osb,
 	if (inode_alloc)
 		inode_lock(inode_alloc);
 
-	if (o2info_coherent(&fi->ifi_req)) {
+	if (inode_alloc && o2info_coherent(&fi->ifi_req)) {
 		status = ocfs2_inode_lock(inode_alloc, &bh, 0);
 		if (status < 0) {
 			mlog_errno(status);
-- 
cgit v1.2.3


From 20bb759a66be52cf4a9ddd17fddaf509e11490cd Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Sun, 6 Oct 2019 17:58:00 -0700
Subject: panic: ensure preemption is disabled during panic()

Calling 'panic()' on a kernel with CONFIG_PREEMPT=y can leave the
calling CPU in an infinite loop, but with interrupts and preemption
enabled.  From this state, userspace can continue to be scheduled,
despite the system being "dead" as far as the kernel is concerned.

This is easily reproducible on arm64 when booting with "nosmp" on the
command line; a couple of shell scripts print out a periodic "Ping"
message whilst another triggers a crash by writing to
/proc/sysrq-trigger:

  | sysrq: Trigger a crash
  | Kernel panic - not syncing: sysrq triggered crash
  | CPU: 0 PID: 1 Comm: init Not tainted 5.2.15 #1
  | Hardware name: linux,dummy-virt (DT)
  | Call trace:
  |  dump_backtrace+0x0/0x148
  |  show_stack+0x14/0x20
  |  dump_stack+0xa0/0xc4
  |  panic+0x140/0x32c
  |  sysrq_handle_reboot+0x0/0x20
  |  __handle_sysrq+0x124/0x190
  |  write_sysrq_trigger+0x64/0x88
  |  proc_reg_write+0x60/0xa8
  |  __vfs_write+0x18/0x40
  |  vfs_write+0xa4/0x1b8
  |  ksys_write+0x64/0xf0
  |  __arm64_sys_write+0x14/0x20
  |  el0_svc_common.constprop.0+0xb0/0x168
  |  el0_svc_handler+0x28/0x78
  |  el0_svc+0x8/0xc
  | Kernel Offset: disabled
  | CPU features: 0x0002,24002004
  | Memory Limit: none
  | ---[ end Kernel panic - not syncing: sysrq triggered crash ]---
  |  Ping 2!
  |  Ping 1!
  |  Ping 1!
  |  Ping 2!

The issue can also be triggered on x86 kernels if CONFIG_SMP=n,
otherwise local interrupts are disabled in 'smp_send_stop()'.

Disable preemption in 'panic()' before re-enabling interrupts.

Link: http://lkml.kernel.org/r/20191002123538.22609-1-will@kernel.org
Link: https://lore.kernel.org/r/BX1W47JXPMR8.58IYW53H6M5N@dragonstone
Signed-off-by: Will Deacon <will@kernel.org>
Reported-by: Xogium <contact@xogium.me>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Feng Tang <feng.tang@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/panic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/panic.c b/kernel/panic.c
index 47e8ebccc22b..f470a038b05b 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -180,6 +180,7 @@ void panic(const char *fmt, ...)
 	 * after setting panic_cpu) from invoking panic() again.
 	 */
 	local_irq_disable();
+	preempt_disable_notrace();
 
 	/*
 	 * It's possible to come here directly from a panic-assertion and
-- 
cgit v1.2.3


From 6d0e9849417bfcbe997405371e0ed712b364ba0a Mon Sep 17 00:00:00 2001
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Sun, 6 Oct 2019 17:58:05 -0700
Subject: mm/memremap: drop unused SECTION_SIZE and SECTION_MASK

SECTION_SIZE and SECTION_MASK macros are not getting used anymore.  But
they do conflict with existing definitions on arm64 platform causing
following warning during build.  Lets drop these unused macros.

  mm/memremap.c:16: warning: "SECTION_MASK" redefined
   #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
  arch/arm64/include/asm/pgtable-hwdef.h:79: note: this is the location of the previous definition
   #define SECTION_MASK  (~(SECTION_SIZE-1))

  mm/memremap.c:17: warning: "SECTION_SIZE" redefined
   #define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
  arch/arm64/include/asm/pgtable-hwdef.h:78: note: this is the location of the previous definition
   #define SECTION_SIZE  (_AC(1, UL) << SECTION_SHIFT)

Link: http://lkml.kernel.org/r/1569312010-31313-1-git-send-email-anshuman.khandual@arm.com
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reported-by: kbuild test robot <lkp@intel.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memremap.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/mm/memremap.c b/mm/memremap.c
index 32c79b51af86..68204912cc0a 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -13,8 +13,6 @@
 #include <linux/xarray.h>
 
 static DEFINE_XARRAY(pgmap_array);
-#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
-#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
 DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-- 
cgit v1.2.3


From 8e00c4e9dd852f7a9bf12234fad65a2f2f93788f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Sun, 6 Oct 2019 17:58:09 -0700
Subject: writeback: fix use-after-free in finish_writeback_work()

finish_writeback_work() reads @done->waitq after decrementing
@done->cnt.  However, once @done->cnt reaches zero, @done may be freed
(from stack) at any moment and @done->waitq can contain something
unrelated by the time finish_writeback_work() tries to read it.  This
led to the following crash.

  "BUG: kernel NULL pointer dereference, address: 0000000000000002"
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP DEBUG_PAGEALLOC
  CPU: 40 PID: 555153 Comm: kworker/u98:50 Kdump: loaded Not tainted
  ...
  Workqueue: writeback wb_workfn (flush-btrfs-1)
  RIP: 0010:_raw_spin_lock_irqsave+0x10/0x30
  Code: 48 89 d8 5b c3 e8 50 db 6b ff eb f4 0f 1f 40 00 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 53 9c 5b fa 31 c0 ba 01 00 00 00 <f0> 0f b1 17 75 05 48 89 d8 5b c3 89 c6 e8 fe ca 6b ff eb f2 66 90
  RSP: 0018:ffffc90049b27d98 EFLAGS: 00010046
  RAX: 0000000000000000 RBX: 0000000000000246 RCX: 0000000000000000
  RDX: 0000000000000001 RSI: 0000000000000003 RDI: 0000000000000002
  RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000001
  R10: ffff889fff407600 R11: ffff88ba9395d740 R12: 000000000000e300
  R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000000
  FS:  0000000000000000(0000) GS:ffff88bfdfa00000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000000000002 CR3: 0000000002409005 CR4: 00000000001606e0
  Call Trace:
   __wake_up_common_lock+0x63/0xc0
   wb_workfn+0xd2/0x3e0
   process_one_work+0x1f5/0x3f0
   worker_thread+0x2d/0x3d0
   kthread+0x111/0x130
   ret_from_fork+0x1f/0x30

Fix it by reading and caching @done->waitq before decrementing
@done->cnt.

Link: http://lkml.kernel.org/r/20190924010631.GH2233839@devbig004.ftw2.facebook.com
Fixes: 5b9cce4c7eb069 ("writeback: Generalize and expose wb_completion")
Signed-off-by: Tejun Heo <tj@kernel.org>
Debugged-by: Chris Mason <clm@fb.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Cc: Jan Kara <jack@suse.cz>
Cc: <stable@vger.kernel.org>	[5.2+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fs-writeback.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 8aaa7eec7b74..e88421d9a48d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -164,8 +164,13 @@ static void finish_writeback_work(struct bdi_writeback *wb,
 
 	if (work->auto_free)
 		kfree(work);
-	if (done && atomic_dec_and_test(&done->cnt))
-		wake_up_all(done->waitq);
+	if (done) {
+		wait_queue_head_t *waitq = done->waitq;
+
+		/* @done can't be accessed after the following dec */
+		if (atomic_dec_and_test(&done->cnt))
+			wake_up_all(waitq);
+	}
 }
 
 static void wb_queue_work(struct bdi_writeback *wb,
-- 
cgit v1.2.3


From 758b8db4a56ab03eca4ecbfa7fa641ed30fb2a90 Mon Sep 17 00:00:00 2001
From: Yi Wang <wang.yi59@zte.com.cn>
Date: Sun, 6 Oct 2019 17:58:12 -0700
Subject: mm: fix -Wmissing-prototypes warnings

We get two warnings when build kernel W=1:

  mm/shuffle.c:36:12: warning: no previous prototype for `shuffle_show' [-Wmissing-prototypes]
  mm/sparse.c:220:6: warning: no previous prototype for `subsection_mask_set' [-Wmissing-prototypes]

Make the functions static to fix this.

Link: http://lkml.kernel.org/r/1566978161-7293-1-git-send-email-wang.yi59@zte.com.cn
Signed-off-by: Yi Wang <wang.yi59@zte.com.cn>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/shuffle.c | 2 +-
 mm/sparse.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/mm/shuffle.c b/mm/shuffle.c
index 3ce12481b1dc..b3fe97fd6654 100644
--- a/mm/shuffle.c
+++ b/mm/shuffle.c
@@ -33,7 +33,7 @@ __meminit void page_alloc_shuffle(enum mm_shuffle_ctl ctl)
 }
 
 static bool shuffle_param;
-extern int shuffle_show(char *buffer, const struct kernel_param *kp)
+static int shuffle_show(char *buffer, const struct kernel_param *kp)
 {
 	return sprintf(buffer, "%c\n", test_bit(SHUFFLE_ENABLE, &shuffle_state)
 			? 'Y' : 'N');
diff --git a/mm/sparse.c b/mm/sparse.c
index bf32de9e666b..f6891c1992b1 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -219,7 +219,7 @@ static inline unsigned long first_present_section_nr(void)
 	return next_present_section_nr(-1);
 }
 
-void subsection_mask_set(unsigned long *map, unsigned long pfn,
+static void subsection_mask_set(unsigned long *map, unsigned long pfn,
 		unsigned long nr_pages)
 {
 	int idx = subsection_map_index(pfn);
-- 
cgit v1.2.3


From 08d1d0e6d0a00c6e687201774f3bf61177741e80 Mon Sep 17 00:00:00 2001
From: Baoquan He <bhe@redhat.com>
Date: Sun, 6 Oct 2019 17:58:15 -0700
Subject: memcg: only record foreign writebacks with dirty pages when memcg is
 not disabled

In kdump kernel, memcg usually is disabled with 'cgroup_disable=memory'
for saving memory.  Now kdump kernel will always panic when dump vmcore
to local disk:

  BUG: kernel NULL pointer dereference, address: 0000000000000ab8
  Oops: 0000 [#1] SMP NOPTI
  CPU: 0 PID: 598 Comm: makedumpfile Not tainted 5.3.0+ #26
  Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 10/02/2018
  RIP: 0010:mem_cgroup_track_foreign_dirty_slowpath+0x38/0x140
  Call Trace:
   __set_page_dirty+0x52/0xc0
   iomap_set_page_dirty+0x50/0x90
   iomap_write_end+0x6e/0x270
   iomap_write_actor+0xce/0x170
   iomap_apply+0xba/0x11e
   iomap_file_buffered_write+0x62/0x90
   xfs_file_buffered_aio_write+0xca/0x320 [xfs]
   new_sync_write+0x12d/0x1d0
   vfs_write+0xa5/0x1a0
   ksys_write+0x59/0xd0
   do_syscall_64+0x59/0x1e0
   entry_SYSCALL_64_after_hwframe+0x44/0xa9

And this will corrupt the 1st kernel too with 'cgroup_disable=memory'.

Via the trace and with debugging, it is pointing to commit 97b27821b485
("writeback, memcg: Implement foreign dirty flushing") which introduced
this regression.  Disabling memcg causes the null pointer dereference at
uninitialized data in function mem_cgroup_track_foreign_dirty_slowpath().

Fix it by returning directly if memcg is disabled, but not trying to
record the foreign writebacks with dirty pages.

Link: http://lkml.kernel.org/r/20190924141928.GD31919@MiWiFi-R3L-srv
Fixes: 97b27821b485 ("writeback, memcg: Implement foreign dirty flushing")
Signed-off-by: Baoquan He <bhe@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 9b60863429cc..98380779f6d5 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1264,6 +1264,9 @@ void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
 static inline void mem_cgroup_track_foreign_dirty(struct page *page,
 						  struct bdi_writeback *wb)
 {
+	if (mem_cgroup_disabled())
+		return;
+
 	if (unlikely(&page->mem_cgroup->css != wb->memcg_css))
 		mem_cgroup_track_foreign_dirty_slowpath(page, wb);
 }
-- 
cgit v1.2.3


From b0f53dbc4bc4c371f38b14c391095a3bb8a0bb40 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Sun, 6 Oct 2019 17:58:19 -0700
Subject: kernel/sysctl.c: do not override max_threads provided by userspace

Partially revert 16db3d3f1170 ("kernel/sysctl.c: threads-max observe
limits") because the patch is causing a regression to any workload which
needs to override the auto-tuning of the limit provided by kernel.

set_max_threads is implementing a boot time guesstimate to provide a
sensible limit of the concurrently running threads so that runaways will
not deplete all the memory.  This is a good thing in general but there
are workloads which might need to increase this limit for an application
to run (reportedly WebSpher MQ is affected) and that is simply not
possible after the mentioned change.  It is also very dubious to
override an admin decision by an estimation that doesn't have any direct
relation to correctness of the kernel operation.

Fix this by dropping set_max_threads from sysctl_max_threads so any
value is accepted as long as it fits into MAX_THREADS which is important
to check because allowing more threads could break internal robust futex
restriction.  While at it, do not use MIN_THREADS as the lower boundary
because it is also only a heuristic for automatic estimation and admin
might have a good reason to stop new threads to be created even when
below this limit.

This became more severe when we switched x86 from 4k to 8k kernel
stacks.  Starting since 6538b8ea886e ("x86_64: expand kernel stack to
16K") (3.16) we use THREAD_SIZE_ORDER = 2 and that halved the auto-tuned
value.

In the particular case

  3.12
  kernel.threads-max = 515561

  4.4
  kernel.threads-max = 200000

Neither of the two values is really insane on 32GB machine.

I am not sure we want/need to tune the max_thread value further.  If
anything the tuning should be removed altogether if proven not useful in
general.  But we definitely need a way to override this auto-tuning.

Link: http://lkml.kernel.org/r/20190922065801.GB18814@dhcp22.suse.cz
Fixes: 16db3d3f1170 ("kernel/sysctl.c: threads-max observe limits")
Signed-off-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Heinrich Schuchardt <xypron.glpk@gmx.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/fork.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index 1f6c45f6a734..bcdf53125210 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2925,7 +2925,7 @@ int sysctl_max_threads(struct ctl_table *table, int write,
 	struct ctl_table t;
 	int ret;
 	int threads = max_threads;
-	int min = MIN_THREADS;
+	int min = 1;
 	int max = MAX_THREADS;
 
 	t = *table;
@@ -2937,7 +2937,7 @@ int sysctl_max_threads(struct ctl_table *table, int write,
 	if (ret || !write)
 		return ret;
 
-	set_max_threads(threads);
+	max_threads = threads;
 
 	return 0;
 }
-- 
cgit v1.2.3


From 5b6807de11445c05b537df8324f5d7ab1c2782f9 Mon Sep 17 00:00:00 2001
From: Vitaly Wool <vitalywool@gmail.com>
Date: Sun, 6 Oct 2019 17:58:22 -0700
Subject: mm/z3fold.c: claim page in the beginning of free

There's a really hard to reproduce race in z3fold between z3fold_free()
and z3fold_reclaim_page().  z3fold_reclaim_page() can claim the page
after z3fold_free() has checked if the page was claimed and
z3fold_free() will then schedule this page for compaction which may in
turn lead to random page faults (since that page would have been
reclaimed by then).

Fix that by claiming page in the beginning of z3fold_free() and not
forgetting to clear the claim in the end.

[vitalywool@gmail.com: v2]
  Link: http://lkml.kernel.org/r/20190928113456.152742cf@bigdell
Link: http://lkml.kernel.org/r/20190926104844.4f0c6efa1366b8f5741eaba9@gmail.com
Signed-off-by: Vitaly Wool <vitalywool@gmail.com>
Reported-by: Markus Linnala <markus.linnala@gmail.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Henry Burns <henrywolfeburns@gmail.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Markus Linnala <markus.linnala@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/z3fold.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/mm/z3fold.c b/mm/z3fold.c
index 05bdf90646e7..6d3d3f698ebb 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -998,9 +998,11 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 	struct z3fold_header *zhdr;
 	struct page *page;
 	enum buddy bud;
+	bool page_claimed;
 
 	zhdr = handle_to_z3fold_header(handle);
 	page = virt_to_page(zhdr);
+	page_claimed = test_and_set_bit(PAGE_CLAIMED, &page->private);
 
 	if (test_bit(PAGE_HEADLESS, &page->private)) {
 		/* if a headless page is under reclaim, just leave.
@@ -1008,7 +1010,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 		 * has not been set before, we release this page
 		 * immediately so we don't care about its value any more.
 		 */
-		if (!test_and_set_bit(PAGE_CLAIMED, &page->private)) {
+		if (!page_claimed) {
 			spin_lock(&pool->lock);
 			list_del(&page->lru);
 			spin_unlock(&pool->lock);
@@ -1044,13 +1046,15 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 		atomic64_dec(&pool->pages_nr);
 		return;
 	}
-	if (test_bit(PAGE_CLAIMED, &page->private)) {
+	if (page_claimed) {
+		/* the page has not been claimed by us */
 		z3fold_page_unlock(zhdr);
 		return;
 	}
 	if (unlikely(PageIsolated(page)) ||
 	    test_and_set_bit(NEEDS_COMPACTING, &page->private)) {
 		z3fold_page_unlock(zhdr);
+		clear_bit(PAGE_CLAIMED, &page->private);
 		return;
 	}
 	if (zhdr->cpu < 0 || !cpu_online(zhdr->cpu)) {
@@ -1060,10 +1064,12 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle)
 		zhdr->cpu = -1;
 		kref_get(&zhdr->refcount);
 		do_compact_page(zhdr, true);
+		clear_bit(PAGE_CLAIMED, &page->private);
 		return;
 	}
 	kref_get(&zhdr->refcount);
 	queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work);
+	clear_bit(PAGE_CLAIMED, &page->private);
 	z3fold_page_unlock(zhdr);
 }
 
-- 
cgit v1.2.3


From 234fdce892f905cbc2674349a9eb4873e288e5b3 Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Sun, 6 Oct 2019 17:58:25 -0700
Subject: mm/page_alloc.c: fix a crash in free_pages_prepare()

On architectures like s390, arch_free_page() could mark the page unused
(set_page_unused()) and any access later would trigger a kernel panic.
Fix it by moving arch_free_page() after all possible accessing calls.

 Hardware name: IBM 2964 N96 400 (z/VM 6.4.0)
 Krnl PSW : 0404e00180000000 0000000026c2b96e (__free_pages_ok+0x34e/0x5d8)
            R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:3 CC:2 PM:0 RI:0 EA:3
 Krnl GPRS: 0000000088d43af7 0000000000484000 000000000000007c 000000000000000f
            000003d080012100 000003d080013fc0 0000000000000000 0000000000100000
            00000000275cca48 0000000000000100 0000000000000008 000003d080010000
            00000000000001d0 000003d000000000 0000000026c2b78a 000000002717fdb0
 Krnl Code: 0000000026c2b95c: ec1100b30659 risbgn %r1,%r1,0,179,6
            0000000026c2b962: e32014000036 pfd 2,1024(%r1)
           #0000000026c2b968: d7ff10001000 xc 0(256,%r1),0(%r1)
           >0000000026c2b96e: 41101100  la %r1,256(%r1)
            0000000026c2b972: a737fff8  brctg %r3,26c2b962
            0000000026c2b976: d7ff10001000 xc 0(256,%r1),0(%r1)
            0000000026c2b97c: e31003400004 lg %r1,832
            0000000026c2b982: ebff1430016a asi 5168(%r1),-1
 Call Trace:
 __free_pages_ok+0x16a/0x5d8)
 memblock_free_all+0x206/0x290
 mem_init+0x58/0x120
 start_kernel+0x2b0/0x570
 startup_continue+0x6a/0xc0
 INFO: lockdep is turned off.
 Last Breaking-Event-Address:
 __free_pages_ok+0x372/0x5d8
 Kernel panic - not syncing: Fatal exception: panic_on_oops
 00: HCPGIR450W CP entered; disabled wait PSW 00020001 80000000 00000000 26A2379C

In the past, only kernel_poison_pages() would trigger this but it needs
"page_poison=on" kernel cmdline, and I suspect nobody tested that on
s390.  Recently, kernel_init_free_pages() (commit 6471384af2a6 ("mm:
security: introduce init_on_alloc=1 and init_on_free=1 boot options"))
was added and could trigger this as well.

[akpm@linux-foundation.org: add comment]
Link: http://lkml.kernel.org/r/1569613623-16820-1-git-send-email-cai@lca.pw
Fixes: 8823b1dbc05f ("mm/page_poison.c: enable PAGE_POISONING as a separate option")
Fixes: 6471384af2a6 ("mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options")
Signed-off-by: Qian Cai <cai@lca.pw>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Duyck <alexander.duyck@gmail.com>
Cc: <stable@vger.kernel.org>	[5.3+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 15c2050c629b..c0b2e0306720 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1175,11 +1175,17 @@ static __always_inline bool free_pages_prepare(struct page *page,
 		debug_check_no_obj_freed(page_address(page),
 					   PAGE_SIZE << order);
 	}
-	arch_free_page(page, order);
 	if (want_init_on_free())
 		kernel_init_free_pages(page, 1 << order);
 
 	kernel_poison_pages(page, 1 << order, 0);
+	/*
+	 * arch_free_page() can make the page's contents inaccessible.  s390
+	 * does this.  So nothing which can access the page's contents should
+	 * happen after this.
+	 */
+	arch_free_page(page, order);
+
 	if (debug_pagealloc_enabled())
 		kernel_map_pages(page, 1 << order, 0);
 
-- 
cgit v1.2.3


From 518a86713078168acd67cf50bc0b45d54b4cce6c Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Sun, 6 Oct 2019 17:58:28 -0700
Subject: mm/vmpressure.c: fix a signedness bug in vmpressure_register_event()

The "mode" and "level" variables are enums and in this context GCC will
treat them as unsigned ints so the error handling is never triggered.

I also removed the bogus initializer because it isn't required any more
and it's sort of confusing.

[akpm@linux-foundation.org: reduce implicit and explicit typecasting]
[akpm@linux-foundation.org: fix return value, add comment, per Matthew]
Link: http://lkml.kernel.org/r/20190925110449.GO3264@mwanda
Fixes: 3cadfa2b9497 ("mm/vmpressure.c: convert to use match_string() helper")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: David Rientjes <rientjes@google.com>
Reviewed-by: Matthew Wilcox <willy@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Enrico Weigelt <info@metux.net>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/vmpressure.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index f3b50811497a..4bac22fe1aa2 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -355,6 +355,9 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio)
  * "hierarchy" or "local").
  *
  * To be used as memcg event method.
+ *
+ * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could
+ * not be parsed.
  */
 int vmpressure_register_event(struct mem_cgroup *memcg,
 			      struct eventfd_ctx *eventfd, const char *args)
@@ -362,7 +365,7 @@ int vmpressure_register_event(struct mem_cgroup *memcg,
 	struct vmpressure *vmpr = memcg_to_vmpressure(memcg);
 	struct vmpressure_event *ev;
 	enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH;
-	enum vmpressure_levels level = -1;
+	enum vmpressure_levels level;
 	char *spec, *spec_orig;
 	char *token;
 	int ret = 0;
@@ -375,20 +378,18 @@ int vmpressure_register_event(struct mem_cgroup *memcg,
 
 	/* Find required level */
 	token = strsep(&spec, ",");
-	level = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token);
-	if (level < 0) {
-		ret = level;
+	ret = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token);
+	if (ret < 0)
 		goto out;
-	}
+	level = ret;
 
 	/* Find optional mode */
 	token = strsep(&spec, ",");
 	if (token) {
-		mode = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token);
-		if (mode < 0) {
-			ret = mode;
+		ret = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token);
+		if (ret < 0)
 			goto out;
-		}
+		mode = ret;
 	}
 
 	ev = kzalloc(sizeof(*ev), GFP_KERNEL);
@@ -404,6 +405,7 @@ int vmpressure_register_event(struct mem_cgroup *memcg,
 	mutex_lock(&vmpr->events_lock);
 	list_add(&ev->node, &vmpr->events);
 	mutex_unlock(&vmpr->events_lock);
+	ret = 0;
 out:
 	kfree(spec_orig);
 	return ret;
-- 
cgit v1.2.3


From 9783aa9917f8ae24759e67bf882f1aba32fe4ea1 Mon Sep 17 00:00:00 2001
From: Chris Down <chris@chrisdown.name>
Date: Sun, 6 Oct 2019 17:58:32 -0700
Subject: mm, memcg: proportional memory.{low,min} reclaim

cgroup v2 introduces two memory protection thresholds: memory.low
(best-effort) and memory.min (hard protection).  While they generally do
what they say on the tin, there is a limitation in their implementation
that makes them difficult to use effectively: that cliff behaviour often
manifests when they become eligible for reclaim.  This patch implements
more intuitive and usable behaviour, where we gradually mount more
reclaim pressure as cgroups further and further exceed their protection
thresholds.

This cliff edge behaviour happens because we only choose whether or not
to reclaim based on whether the memcg is within its protection limits
(see the use of mem_cgroup_protected in shrink_node), but we don't vary
our reclaim behaviour based on this information.  Imagine the following
timeline, with the numbers the lruvec size in this zone:

1. memory.low=1000000, memory.current=999999. 0 pages may be scanned.
2. memory.low=1000000, memory.current=1000000. 0 pages may be scanned.
3. memory.low=1000000, memory.current=1000001. 1000001* pages may be
   scanned. (?!)

* Of course, we won't usually scan all available pages in the zone even
  without this patch because of scan control priority, over-reclaim
  protection, etc.  However, as shown by the tests at the end, these
  techniques don't sufficiently throttle such an extreme change in input,
  so cliff-like behaviour isn't really averted by their existence alone.

Here's an example of how this plays out in practice.  At Facebook, we are
trying to protect various workloads from "system" software, like
configuration management tools, metric collectors, etc (see this[0] case
study).  In order to find a suitable memory.low value, we start by
determining the expected memory range within which the workload will be
comfortable operating.  This isn't an exact science -- memory usage deemed
"comfortable" will vary over time due to user behaviour, differences in
composition of work, etc, etc.  As such we need to ballpark memory.low,
but doing this is currently problematic:

1. If we end up setting it too low for the workload, it won't have
   *any* effect (see discussion above).  The group will receive the full
   weight of reclaim and won't have any priority while competing with the
   less important system software, as if we had no memory.low configured
   at all.

2. Because of this behaviour, we end up erring on the side of setting
   it too high, such that the comfort range is reliably covered.  However,
   protected memory is completely unavailable to the rest of the system,
   so we might cause undue memory and IO pressure there when we *know* we
   have some elasticity in the workload.

3. Even if we get the value totally right, smack in the middle of the
   comfort zone, we get extreme jumps between no pressure and full
   pressure that cause unpredictable pressure spikes in the workload due
   to the current binary reclaim behaviour.

With this patch, we can set it to our ballpark estimation without too much
worry.  Any undesirable behaviour, such as too much or too little reclaim
pressure on the workload or system will be proportional to how far our
estimation is off.  This means we can set memory.low much more
conservatively and thus waste less resources *without* the risk of the
workload falling off a cliff if we overshoot.

As a more abstract technical description, this unintuitive behaviour
results in having to give high-priority workloads a large protection
buffer on top of their expected usage to function reliably, as otherwise
we have abrupt periods of dramatically increased memory pressure which
hamper performance.  Having to set these thresholds so high wastes
resources and generally works against the principle of work conservation.
In addition, having proportional memory reclaim behaviour has other
benefits.  Most notably, before this patch it's basically mandatory to set
memory.low to a higher than desirable value because otherwise as soon as
you exceed memory.low, all protection is lost, and all pages are eligible
to scan again.  By contrast, having a gradual ramp in reclaim pressure
means that you now still get some protection when thresholds are exceeded,
which means that one can now be more comfortable setting memory.low to
lower values without worrying that all protection will be lost.  This is
important because workingset size is really hard to know exactly,
especially with variable workloads, so at least getting *some* protection
if your workingset size grows larger than you expect increases user
confidence in setting memory.low without a huge buffer on top being
needed.

Thanks a lot to Johannes Weiner and Tejun Heo for their advice and
assistance in thinking about how to make this work better.

In testing these changes, I intended to verify that:

1. Changes in page scanning become gradual and proportional instead of
   binary.

   To test this, I experimented stepping further and further down
   memory.low protection on a workload that floats around 19G workingset
   when under memory.low protection, watching page scan rates for the
   workload cgroup:

   +------------+-----------------+--------------------+--------------+
   | memory.low | test (pgscan/s) | control (pgscan/s) | % of control |
   +------------+-----------------+--------------------+--------------+
   |        21G |               0 |                  0 | N/A          |
   |        17G |             867 |               3799 | 23%          |
   |        12G |            1203 |               3543 | 34%          |
   |         8G |            2534 |               3979 | 64%          |
   |         4G |            3980 |               4147 | 96%          |
   |          0 |            3799 |               3980 | 95%          |
   +------------+-----------------+--------------------+--------------+

   As you can see, the test kernel (with a kernel containing this
   patch) ramps up page scanning significantly more gradually than the
   control kernel (without this patch).

2. More gradual ramp up in reclaim aggression doesn't result in
   premature OOMs.

   To test this, I wrote a script that slowly increments the number of
   pages held by stress(1)'s --vm-keep mode until a production system
   entered severe overall memory contention.  This script runs in a highly
   protected slice taking up the majority of available system memory.
   Watching vmstat revealed that page scanning continued essentially
   nominally between test and control, without causing forward reclaim
   progress to become arrested.

[0]: https://facebookmicrosites.github.io/cgroup2/docs/overview.html#case-study-the-fbtax2-project

[akpm@linux-foundation.org: reflow block comments to fit in 80 cols]
[chris@chrisdown.name: handle cgroup_disable=memory when getting memcg protection]
  Link: http://lkml.kernel.org/r/20190201045711.GA18302@chrisdown.name
Link: http://lkml.kernel.org/r/20190124014455.GA6396@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/admin-guide/cgroup-v2.rst | 20 +++++---
 include/linux/memcontrol.h              | 20 ++++++++
 mm/memcontrol.c                         |  5 ++
 mm/vmscan.c                             | 82 ++++++++++++++++++++++++++++++---
 4 files changed, 115 insertions(+), 12 deletions(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 0fa8c0e615c2..5361ebec3361 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -615,8 +615,8 @@ on an IO device and is an example of this type.
 Protections
 -----------
 
-A cgroup is protected to be allocated upto the configured amount of
-the resource if the usages of all its ancestors are under their
+A cgroup is protected upto the configured amount of the resource
+as long as the usages of all its ancestors are under their
 protected levels.  Protections can be hard guarantees or best effort
 soft boundaries.  Protections can also be over-committed in which case
 only upto the amount available to the parent is protected among
@@ -1096,7 +1096,10 @@ PAGE_SIZE multiple when read back.
 	is within its effective min boundary, the cgroup's memory
 	won't be reclaimed under any conditions. If there is no
 	unprotected reclaimable memory available, OOM killer
-	is invoked.
+	is invoked. Above the effective min boundary (or
+	effective low boundary if it is higher), pages are reclaimed
+	proportionally to the overage, reducing reclaim pressure for
+	smaller overages.
 
        Effective min boundary is limited by memory.min values of
 	all ancestor cgroups. If there is memory.min overcommitment
@@ -1118,7 +1121,10 @@ PAGE_SIZE multiple when read back.
 	Best-effort memory protection.  If the memory usage of a
 	cgroup is within its effective low boundary, the cgroup's
 	memory won't be reclaimed unless memory can be reclaimed
-	from unprotected cgroups.
+	from unprotected cgroups.  Above the effective low boundary (or
+	effective min boundary if it is higher), pages are reclaimed
+	proportionally to the overage, reducing reclaim pressure for
+	smaller overages.
 
 	Effective low boundary is limited by memory.low values of
 	all ancestor cgroups. If there is memory.low overcommitment
@@ -2482,8 +2488,10 @@ system performance due to overreclaim, to the point where the feature
 becomes self-defeating.
 
 The memory.low boundary on the other hand is a top-down allocated
-reserve.  A cgroup enjoys reclaim protection when it's within its low,
-which makes delegation of subtrees possible.
+reserve.  A cgroup enjoys reclaim protection when it's within its
+effective low, which makes delegation of subtrees possible. It also
+enjoys having reclaim pressure proportional to its overage when
+above its effective low.
 
 The original high boundary, the hard limit, is defined as a strict
 limit that can not budge, even if the OOM killer has to be called.
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 98380779f6d5..fa9ba2edf7e0 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -356,6 +356,14 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
+static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg)
+{
+	if (mem_cgroup_disabled())
+		return 0;
+
+	return max(READ_ONCE(memcg->memory.emin), READ_ONCE(memcg->memory.elow));
+}
+
 enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 						struct mem_cgroup *memcg);
 
@@ -537,6 +545,8 @@ void mem_cgroup_handle_over_high(void);
 
 unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);
 
+unsigned long mem_cgroup_size(struct mem_cgroup *memcg);
+
 void mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
 				struct task_struct *p);
 
@@ -829,6 +839,11 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 {
 }
 
+static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg)
+{
+	return 0;
+}
+
 static inline enum mem_cgroup_protection mem_cgroup_protected(
 	struct mem_cgroup *root, struct mem_cgroup *memcg)
 {
@@ -968,6 +983,11 @@ static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
 	return 0;
 }
 
+static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
+{
+	return 0;
+}
+
 static inline void
 mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c313c49074ca..bdac56009a38 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1567,6 +1567,11 @@ unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg)
 	return max;
 }
 
+unsigned long mem_cgroup_size(struct mem_cgroup *memcg)
+{
+	return page_counter_read(&memcg->memory);
+}
+
 static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				     int order)
 {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e5d52d6a24af..dfefa1d99d1b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2459,17 +2459,80 @@ out:
 	*lru_pages = 0;
 	for_each_evictable_lru(lru) {
 		int file = is_file_lru(lru);
-		unsigned long size;
+		unsigned long lruvec_size;
 		unsigned long scan;
+		unsigned long protection;
+
+		lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
+		protection = mem_cgroup_protection(memcg);
+
+		if (protection > 0) {
+			/*
+			 * Scale a cgroup's reclaim pressure by proportioning
+			 * its current usage to its memory.low or memory.min
+			 * setting.
+			 *
+			 * This is important, as otherwise scanning aggression
+			 * becomes extremely binary -- from nothing as we
+			 * approach the memory protection threshold, to totally
+			 * nominal as we exceed it.  This results in requiring
+			 * setting extremely liberal protection thresholds. It
+			 * also means we simply get no protection at all if we
+			 * set it too low, which is not ideal.
+			 */
+			unsigned long cgroup_size = mem_cgroup_size(memcg);
+			unsigned long baseline = 0;
+
+			/*
+			 * During the reclaim first pass, we only consider
+			 * cgroups in excess of their protection setting, but if
+			 * that doesn't produce free pages, we come back for a
+			 * second pass where we reclaim from all groups.
+			 *
+			 * To maintain fairness in both cases, the first pass
+			 * targets groups in proportion to their overage, and
+			 * the second pass targets groups in proportion to their
+			 * protection utilization.
+			 *
+			 * So on the first pass, a group whose size is 130% of
+			 * its protection will be targeted at 30% of its size.
+			 * On the second pass, a group whose size is at 40% of
+			 * its protection will be
+			 * targeted at 40% of its size.
+			 */
+			if (!sc->memcg_low_reclaim)
+				baseline = lruvec_size;
+			scan = lruvec_size * cgroup_size / protection - baseline;
+
+			/*
+			 * Don't allow the scan target to exceed the lruvec
+			 * size, which otherwise could happen if we have >200%
+			 * overage in the normal case, or >100% overage when
+			 * sc->memcg_low_reclaim is set.
+			 *
+			 * This is important because other cgroups without
+			 * memory.low have their scan target initially set to
+			 * their lruvec size, so allowing values >100% of the
+			 * lruvec size here could result in penalising cgroups
+			 * with memory.low set even *more* than their peers in
+			 * some cases in the case of large overages.
+			 *
+			 * Also, minimally target SWAP_CLUSTER_MAX pages to keep
+			 * reclaim moving forwards.
+			 */
+			scan = clamp(scan, SWAP_CLUSTER_MAX, lruvec_size);
+		} else {
+			scan = lruvec_size;
+		}
+
+		scan >>= sc->priority;
 
-		size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
-		scan = size >> sc->priority;
 		/*
 		 * If the cgroup's already been deleted, make sure to
 		 * scrape out the remaining cache.
 		 */
 		if (!scan && !mem_cgroup_online(memcg))
-			scan = min(size, SWAP_CLUSTER_MAX);
+			scan = min(lruvec_size, SWAP_CLUSTER_MAX);
 
 		switch (scan_balance) {
 		case SCAN_EQUAL:
@@ -2489,7 +2552,7 @@ out:
 		case SCAN_ANON:
 			/* Scan one type exclusively */
 			if ((scan_balance == SCAN_FILE) != file) {
-				size = 0;
+				lruvec_size = 0;
 				scan = 0;
 			}
 			break;
@@ -2498,7 +2561,7 @@ out:
 			BUG();
 		}
 
-		*lru_pages += size;
+		*lru_pages += lruvec_size;
 		nr[lru] = scan;
 	}
 }
@@ -2742,6 +2805,13 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 				memcg_memory_event(memcg, MEMCG_LOW);
 				break;
 			case MEMCG_PROT_NONE:
+				/*
+				 * All protection thresholds breached. We may
+				 * still choose to vary the scan pressure
+				 * applied based on by how much the cgroup in
+				 * question has exceeded its protection
+				 * thresholds (see get_scan_count).
+				 */
 				break;
 			}
 
-- 
cgit v1.2.3


From 9de7ca46ad2688bd51e80f7119fefa301ad7f3fa Mon Sep 17 00:00:00 2001
From: Chris Down <chris@chrisdown.name>
Date: Sun, 6 Oct 2019 17:58:35 -0700
Subject: mm, memcg: make memory.emin the baseline for utilisation
 determination

Roman points out that when when we do the low reclaim pass, we scale the
reclaim pressure relative to position between 0 and the maximum
protection threshold.

However, if the maximum protection is based on memory.elow, and
memory.emin is above zero, this means we still may get binary behaviour
on second-pass low reclaim.  This is because we scale starting at 0, not
starting at memory.emin, and since we don't scan at all below emin, we
end up with cliff behaviour.

This should be a fairly uncommon case since usually we don't go into the
second pass, but it makes sense to scale our low reclaim pressure
starting at emin.

You can test this by catting two large sparse files, one in a cgroup
with emin set to some moderate size compared to physical RAM, and
another cgroup without any emin.  In both cgroups, set an elow larger
than 50% of physical RAM.  The one with emin will have less page
scanning, as reclaim pressure is lower.

Rebase on top of and apply the same idea as what was applied to handle
cgroup_memory=disable properly for the original proportional patch
http://lkml.kernel.org/r/20190201045711.GA18302@chrisdown.name ("mm,
memcg: Handle cgroup_disable=memory when getting memcg protection").

Link: http://lkml.kernel.org/r/20190201051810.GA18895@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Suggested-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 19 +++++++++++-----
 mm/vmscan.c                | 55 +++++++++++++++++++++++++++-------------------
 2 files changed, 46 insertions(+), 28 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index fa9ba2edf7e0..1cbad1248e5a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -356,12 +356,17 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
-static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg)
+static inline void mem_cgroup_protection(struct mem_cgroup *memcg,
+					 unsigned long *min, unsigned long *low)
 {
-	if (mem_cgroup_disabled())
-		return 0;
+	if (mem_cgroup_disabled()) {
+		*min = 0;
+		*low = 0;
+		return;
+	}
 
-	return max(READ_ONCE(memcg->memory.emin), READ_ONCE(memcg->memory.elow));
+	*min = READ_ONCE(memcg->memory.emin);
+	*low = READ_ONCE(memcg->memory.elow);
 }
 
 enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
@@ -839,9 +844,11 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 {
 }
 
-static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg)
+static inline void mem_cgroup_protection(struct mem_cgroup *memcg,
+					 unsigned long *min, unsigned long *low)
 {
-	return 0;
+	*min = 0;
+	*low = 0;
 }
 
 static inline enum mem_cgroup_protection mem_cgroup_protected(
diff --git a/mm/vmscan.c b/mm/vmscan.c
index dfefa1d99d1b..70347d626fb3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2461,12 +2461,12 @@ out:
 		int file = is_file_lru(lru);
 		unsigned long lruvec_size;
 		unsigned long scan;
-		unsigned long protection;
+		unsigned long min, low;
 
 		lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
-		protection = mem_cgroup_protection(memcg);
+		mem_cgroup_protection(memcg, &min, &low);
 
-		if (protection > 0) {
+		if (min || low) {
 			/*
 			 * Scale a cgroup's reclaim pressure by proportioning
 			 * its current usage to its memory.low or memory.min
@@ -2481,28 +2481,38 @@ out:
 			 * set it too low, which is not ideal.
 			 */
 			unsigned long cgroup_size = mem_cgroup_size(memcg);
-			unsigned long baseline = 0;
 
 			/*
-			 * During the reclaim first pass, we only consider
-			 * cgroups in excess of their protection setting, but if
-			 * that doesn't produce free pages, we come back for a
-			 * second pass where we reclaim from all groups.
+			 * If there is any protection in place, we adjust scan
+			 * pressure in proportion to how much a group's current
+			 * usage exceeds that, in percent.
 			 *
-			 * To maintain fairness in both cases, the first pass
-			 * targets groups in proportion to their overage, and
-			 * the second pass targets groups in proportion to their
-			 * protection utilization.
-			 *
-			 * So on the first pass, a group whose size is 130% of
-			 * its protection will be targeted at 30% of its size.
-			 * On the second pass, a group whose size is at 40% of
-			 * its protection will be
-			 * targeted at 40% of its size.
+			 * There is one special case: in the first reclaim pass,
+			 * we skip over all groups that are within their low
+			 * protection. If that fails to reclaim enough pages to
+			 * satisfy the reclaim goal, we come back and override
+			 * the best-effort low protection. However, we still
+			 * ideally want to honor how well-behaved groups are in
+			 * that case instead of simply punishing them all
+			 * equally. As such, we reclaim them based on how much
+			 * of their best-effort protection they are using. Usage
+			 * below memory.min is excluded from consideration when
+			 * calculating utilisation, as it isn't ever
+			 * reclaimable, so it might as well not exist for our
+			 * purposes.
 			 */
-			if (!sc->memcg_low_reclaim)
-				baseline = lruvec_size;
-			scan = lruvec_size * cgroup_size / protection - baseline;
+			if (sc->memcg_low_reclaim && low > min) {
+				/*
+				 * Reclaim according to utilisation between min
+				 * and low
+				 */
+				scan = lruvec_size * (cgroup_size - min) /
+					(low - min);
+			} else {
+				/* Reclaim according to protection overage */
+				scan = lruvec_size * cgroup_size /
+					max(min, low) - lruvec_size;
+			}
 
 			/*
 			 * Don't allow the scan target to exceed the lruvec
@@ -2518,7 +2528,8 @@ out:
 			 * some cases in the case of large overages.
 			 *
 			 * Also, minimally target SWAP_CLUSTER_MAX pages to keep
-			 * reclaim moving forwards.
+			 * reclaim moving forwards, avoiding decremeting
+			 * sc->priority further than desirable.
 			 */
 			scan = clamp(scan, SWAP_CLUSTER_MAX, lruvec_size);
 		} else {
-- 
cgit v1.2.3


From 1bc63fb1272be0773e925f78c0fbd06c89701d55 Mon Sep 17 00:00:00 2001
From: Chris Down <chris@chrisdown.name>
Date: Sun, 6 Oct 2019 17:58:38 -0700
Subject: mm, memcg: make scan aggression always exclude protection

This patch is an incremental improvement on the existing
memory.{low,min} relative reclaim work to base its scan pressure
calculations on how much protection is available compared to the current
usage, rather than how much the current usage is over some protection
threshold.

This change doesn't change the experience for the user in the normal
case too much.  One benefit is that it replaces the (somewhat arbitrary)
100% cutoff with an indefinite slope, which makes it easier to ballpark
a memory.low value.

As well as this, the old methodology doesn't quite apply generically to
machines with varying amounts of physical memory.  Let's say we have a
top level cgroup, workload.slice, and another top level cgroup,
system-management.slice.  We want to roughly give 12G to
system-management.slice, so on a 32GB machine we set memory.low to 20GB
in workload.slice, and on a 64GB machine we set memory.low to 52GB.
However, because these are relative amounts to the total machine size,
while the amount of memory we want to generally be willing to yield to
system.slice is absolute (12G), we end up putting more pressure on
system.slice just because we have a larger machine and a larger workload
to fill it, which seems fairly unintuitive.  With this new behaviour, we
don't end up with this unintended side effect.

Previously the way that memory.low protection works is that if you are
50% over a certain baseline, you get 50% of your normal scan pressure.
This is certainly better than the previous cliff-edge behaviour, but it
can be improved even further by always considering memory under the
currently enforced protection threshold to be out of bounds.  This means
that we can set relatively low memory.low thresholds for variable or
bursty workloads while still getting a reasonable level of protection,
whereas with the previous version we may still trivially hit the 100%
clamp.  The previous 100% clamp is also somewhat arbitrary, whereas this
one is more concretely based on the currently enforced protection
threshold, which is likely easier to reason about.

There is also a subtle issue with the way that proportional reclaim
worked previously -- it promotes having no memory.low, since it makes
pressure higher during low reclaim.  This happens because we base our
scan pressure modulation on how far memory.current is between memory.min
and memory.low, but if memory.low is unset, we only use the overage
method.  In most cromulent configurations, this then means that we end
up with *more* pressure than with no memory.low at all when we're in low
reclaim, which is not really very usable or expected.

With this patch, memory.low and memory.min affect reclaim pressure in a
more understandable and composable way.  For example, from a user
standpoint, "protected" memory now remains untouchable from a reclaim
aggression standpoint, and users can also have more confidence that
bursty workloads will still receive some amount of guaranteed
protection.

Link: http://lkml.kernel.org/r/20190322160307.GA3316@chrisdown.name
Signed-off-by: Chris Down <chris@chrisdown.name>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h | 25 +++++++++----------
 mm/vmscan.c                | 61 +++++++++++++++-------------------------------
 2 files changed, 32 insertions(+), 54 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1cbad1248e5a..ae703ea3ef48 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -356,17 +356,17 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
-static inline void mem_cgroup_protection(struct mem_cgroup *memcg,
-					 unsigned long *min, unsigned long *low)
+static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
+						  bool in_low_reclaim)
 {
-	if (mem_cgroup_disabled()) {
-		*min = 0;
-		*low = 0;
-		return;
-	}
+	if (mem_cgroup_disabled())
+		return 0;
+
+	if (in_low_reclaim)
+		return READ_ONCE(memcg->memory.emin);
 
-	*min = READ_ONCE(memcg->memory.emin);
-	*low = READ_ONCE(memcg->memory.elow);
+	return max(READ_ONCE(memcg->memory.emin),
+		   READ_ONCE(memcg->memory.elow));
 }
 
 enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
@@ -844,11 +844,10 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 {
 }
 
-static inline void mem_cgroup_protection(struct mem_cgroup *memcg,
-					 unsigned long *min, unsigned long *low)
+static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
+						  bool in_low_reclaim)
 {
-	*min = 0;
-	*low = 0;
+	return 0;
 }
 
 static inline enum mem_cgroup_protection mem_cgroup_protected(
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 70347d626fb3..c6659bb758a4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2461,12 +2461,13 @@ out:
 		int file = is_file_lru(lru);
 		unsigned long lruvec_size;
 		unsigned long scan;
-		unsigned long min, low;
+		unsigned long protection;
 
 		lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
-		mem_cgroup_protection(memcg, &min, &low);
+		protection = mem_cgroup_protection(memcg,
+						   sc->memcg_low_reclaim);
 
-		if (min || low) {
+		if (protection) {
 			/*
 			 * Scale a cgroup's reclaim pressure by proportioning
 			 * its current usage to its memory.low or memory.min
@@ -2479,13 +2480,10 @@ out:
 			 * setting extremely liberal protection thresholds. It
 			 * also means we simply get no protection at all if we
 			 * set it too low, which is not ideal.
-			 */
-			unsigned long cgroup_size = mem_cgroup_size(memcg);
-
-			/*
-			 * If there is any protection in place, we adjust scan
-			 * pressure in proportion to how much a group's current
-			 * usage exceeds that, in percent.
+			 *
+			 * If there is any protection in place, we reduce scan
+			 * pressure by how much of the total memory used is
+			 * within protection thresholds.
 			 *
 			 * There is one special case: in the first reclaim pass,
 			 * we skip over all groups that are within their low
@@ -2495,43 +2493,24 @@ out:
 			 * ideally want to honor how well-behaved groups are in
 			 * that case instead of simply punishing them all
 			 * equally. As such, we reclaim them based on how much
-			 * of their best-effort protection they are using. Usage
-			 * below memory.min is excluded from consideration when
-			 * calculating utilisation, as it isn't ever
-			 * reclaimable, so it might as well not exist for our
-			 * purposes.
+			 * memory they are using, reducing the scan pressure
+			 * again by how much of the total memory used is under
+			 * hard protection.
 			 */
-			if (sc->memcg_low_reclaim && low > min) {
-				/*
-				 * Reclaim according to utilisation between min
-				 * and low
-				 */
-				scan = lruvec_size * (cgroup_size - min) /
-					(low - min);
-			} else {
-				/* Reclaim according to protection overage */
-				scan = lruvec_size * cgroup_size /
-					max(min, low) - lruvec_size;
-			}
+			unsigned long cgroup_size = mem_cgroup_size(memcg);
+
+			/* Avoid TOCTOU with earlier protection check */
+			cgroup_size = max(cgroup_size, protection);
+
+			scan = lruvec_size - lruvec_size * protection /
+				cgroup_size;
 
 			/*
-			 * Don't allow the scan target to exceed the lruvec
-			 * size, which otherwise could happen if we have >200%
-			 * overage in the normal case, or >100% overage when
-			 * sc->memcg_low_reclaim is set.
-			 *
-			 * This is important because other cgroups without
-			 * memory.low have their scan target initially set to
-			 * their lruvec size, so allowing values >100% of the
-			 * lruvec size here could result in penalising cgroups
-			 * with memory.low set even *more* than their peers in
-			 * some cases in the case of large overages.
-			 *
-			 * Also, minimally target SWAP_CLUSTER_MAX pages to keep
+			 * Minimally target SWAP_CLUSTER_MAX pages to keep
 			 * reclaim moving forwards, avoiding decremeting
 			 * sc->priority further than desirable.
 			 */
-			scan = clamp(scan, SWAP_CLUSTER_MAX, lruvec_size);
+			scan = max(scan, SWAP_CLUSTER_MAX);
 		} else {
 			scan = lruvec_size;
 		}
-- 
cgit v1.2.3


From 6a486c0ad4dcdee3946842c64884d2978bfe2602 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Sun, 6 Oct 2019 17:58:42 -0700
Subject: mm, sl[ou]b: improve memory accounting

Patch series "guarantee natural alignment for kmalloc()", v2.

This patch (of 2):

SLOB currently doesn't account its pages at all, so in /proc/meminfo the
Slab field shows zero.  Modifying a counter on page allocation and
freeing should be acceptable even for the small system scenarios SLOB is
intended for.  Since reclaimable caches are not separated in SLOB,
account everything as unreclaimable.

SLUB currently doesn't account kmalloc() and kmalloc_node() allocations
larger than order-1 page, that are passed directly to the page
allocator.  As they also don't appear in /proc/slabinfo, it might look
like a memory leak.  For consistency, account them as well.  (SLAB
doesn't actually use page allocator directly, so no change there).

Ideally SLOB and SLUB would be handled in separate patches, but due to
the shared kmalloc_order() function and different kfree()
implementations, it's easier to patch both at once to prevent
inconsistencies.

Link: http://lkml.kernel.org/r/20190826111627.7505-2-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: "Darrick J . Wong" <darrick.wong@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/slab_common.c |  8 ++++++--
 mm/slob.c        | 20 ++++++++++++++++----
 mm/slub.c        | 14 +++++++++++---
 3 files changed, 33 insertions(+), 9 deletions(-)

diff --git a/mm/slab_common.c b/mm/slab_common.c
index 6491c3a41805..0a94cf858aa4 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1287,12 +1287,16 @@ void __init create_kmalloc_caches(slab_flags_t flags)
  */
 void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
 {
-	void *ret;
+	void *ret = NULL;
 	struct page *page;
 
 	flags |= __GFP_COMP;
 	page = alloc_pages(flags, order);
-	ret = page ? page_address(page) : NULL;
+	if (likely(page)) {
+		ret = page_address(page);
+		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
+				    1 << order);
+	}
 	ret = kasan_kmalloc_large(ret, size, flags);
 	/* As ret might get tagged, call kmemleak hook after KASAN. */
 	kmemleak_alloc(ret, size, 1, flags);
diff --git a/mm/slob.c b/mm/slob.c
index cf377beab962..835088d55645 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -190,7 +190,7 @@ static int slob_last(slob_t *s)
 
 static void *slob_new_pages(gfp_t gfp, int order, int node)
 {
-	void *page;
+	struct page *page;
 
 #ifdef CONFIG_NUMA
 	if (node != NUMA_NO_NODE)
@@ -202,14 +202,21 @@ static void *slob_new_pages(gfp_t gfp, int order, int node)
 	if (!page)
 		return NULL;
 
+	mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
+			    1 << order);
 	return page_address(page);
 }
 
 static void slob_free_pages(void *b, int order)
 {
+	struct page *sp = virt_to_page(b);
+
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += 1 << order;
-	free_pages((unsigned long)b, order);
+
+	mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE,
+			    -(1 << order));
+	__free_pages(sp, order);
 }
 
 /*
@@ -521,8 +528,13 @@ void kfree(const void *block)
 		int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 		unsigned int *m = (unsigned int *)(block - align);
 		slob_free(m, *m + align);
-	} else
-		__free_pages(sp, compound_order(sp));
+	} else {
+		unsigned int order = compound_order(sp);
+		mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE,
+				    -(1 << order));
+		__free_pages(sp, order);
+
+	}
 }
 EXPORT_SYMBOL(kfree);
 
diff --git a/mm/slub.c b/mm/slub.c
index 42c1b3af3c98..3d63ae320d31 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3821,11 +3821,15 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 {
 	struct page *page;
 	void *ptr = NULL;
+	unsigned int order = get_order(size);
 
 	flags |= __GFP_COMP;
-	page = alloc_pages_node(node, flags, get_order(size));
-	if (page)
+	page = alloc_pages_node(node, flags, order);
+	if (page) {
 		ptr = page_address(page);
+		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
+				    1 << order);
+	}
 
 	return kmalloc_large_node_hook(ptr, size, flags);
 }
@@ -3951,9 +3955,13 @@ void kfree(const void *x)
 
 	page = virt_to_head_page(x);
 	if (unlikely(!PageSlab(page))) {
+		unsigned int order = compound_order(page);
+
 		BUG_ON(!PageCompound(page));
 		kfree_hook(object);
-		__free_pages(page, compound_order(page));
+		mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE,
+				    -(1 << order));
+		__free_pages(page, order);
 		return;
 	}
 	slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_);
-- 
cgit v1.2.3


From 59bb47985c1db229ccff8c5deebecd54fc77d2a9 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Sun, 6 Oct 2019 17:58:45 -0700
Subject: mm, sl[aou]b: guarantee natural alignment for kmalloc(power-of-two)

In most configurations, kmalloc() happens to return naturally aligned
(i.e.  aligned to the block size itself) blocks for power of two sizes.

That means some kmalloc() users might unknowingly rely on that
alignment, until stuff breaks when the kernel is built with e.g.
CONFIG_SLUB_DEBUG or CONFIG_SLOB, and blocks stop being aligned.  Then
developers have to devise workaround such as own kmem caches with
specified alignment [1], which is not always practical, as recently
evidenced in [2].

The topic has been discussed at LSF/MM 2019 [3].  Adding a
'kmalloc_aligned()' variant would not help with code unknowingly relying
on the implicit alignment.  For slab implementations it would either
require creating more kmalloc caches, or allocate a larger size and only
give back part of it.  That would be wasteful, especially with a generic
alignment parameter (in contrast with a fixed alignment to size).

Ideally we should provide to mm users what they need without difficult
workarounds or own reimplementations, so let's make the kmalloc()
alignment to size explicitly guaranteed for power-of-two sizes under all
configurations.  What this means for the three available allocators?

* SLAB object layout happens to be mostly unchanged by the patch.  The
  implicitly provided alignment could be compromised with
  CONFIG_DEBUG_SLAB due to redzoning, however SLAB disables redzoning for
  caches with alignment larger than unsigned long long.  Practically on at
  least x86 this includes kmalloc caches as they use cache line alignment,
  which is larger than that.  Still, this patch ensures alignment on all
  arches and cache sizes.

* SLUB layout is also unchanged unless redzoning is enabled through
  CONFIG_SLUB_DEBUG and boot parameter for the particular kmalloc cache.
  With this patch, explicit alignment is guaranteed with redzoning as
  well.  This will result in more memory being wasted, but that should be
  acceptable in a debugging scenario.

* SLOB has no implicit alignment so this patch adds it explicitly for
  kmalloc().  The potential downside is increased fragmentation.  While
  pathological allocation scenarios are certainly possible, in my testing,
  after booting a x86_64 kernel+userspace with virtme, around 16MB memory
  was consumed by slab pages both before and after the patch, with
  difference in the noise.

[1] https://lore.kernel.org/linux-btrfs/c3157c8e8e0e7588312b40c853f65c02fe6c957a.1566399731.git.christophe.leroy@c-s.fr/
[2] https://lore.kernel.org/linux-fsdevel/20190225040904.5557-1-ming.lei@redhat.com/
[3] https://lwn.net/Articles/787740/

[akpm@linux-foundation.org: documentation fixlet, per Matthew]
Link: http://lkml.kernel.org/r/20190826111627.7505-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Cc: David Sterba <dsterba@suse.cz>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: "Darrick J . Wong" <darrick.wong@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: James Bottomley <James.Bottomley@HansenPartnership.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/core-api/memory-allocation.rst |  4 +++
 include/linux/slab.h                         |  4 +++
 mm/slab_common.c                             | 11 +++++++-
 mm/slob.c                                    | 42 ++++++++++++++++++++--------
 4 files changed, 49 insertions(+), 12 deletions(-)

diff --git a/Documentation/core-api/memory-allocation.rst b/Documentation/core-api/memory-allocation.rst
index 7744aa3bf2e0..939e3dfc86e9 100644
--- a/Documentation/core-api/memory-allocation.rst
+++ b/Documentation/core-api/memory-allocation.rst
@@ -98,6 +98,10 @@ limited. The actual limit depends on the hardware and the kernel
 configuration, but it is a good practice to use `kmalloc` for objects
 smaller than page size.
 
+The address of a chunk allocated with `kmalloc` is aligned to at least
+ARCH_KMALLOC_MINALIGN bytes.  For sizes which are a power of two, the
+alignment is also guaranteed to be at least the respective size.
+
 For large allocations you can use :c:func:`vmalloc` and
 :c:func:`vzalloc`, or directly request pages from the page
 allocator. The memory allocated by `vmalloc` and related functions is
diff --git a/include/linux/slab.h b/include/linux/slab.h
index ab2b98ad76e1..4d2a2fa55ed5 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -493,6 +493,10 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
  * kmalloc is the normal method of allocating memory
  * for objects smaller than page size in the kernel.
  *
+ * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN
+ * bytes. For @size of power of two bytes, the alignment is also guaranteed
+ * to be at least to the size.
+ *
  * The @flags argument may be one of the GFP flags defined at
  * include/linux/gfp.h and described at
  * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>`
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 0a94cf858aa4..c29f03adca91 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1030,10 +1030,19 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name,
 		unsigned int useroffset, unsigned int usersize)
 {
 	int err;
+	unsigned int align = ARCH_KMALLOC_MINALIGN;
 
 	s->name = name;
 	s->size = s->object_size = size;
-	s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
+
+	/*
+	 * For power of two sizes, guarantee natural alignment for kmalloc
+	 * caches, regardless of SL*B debugging options.
+	 */
+	if (is_power_of_2(size))
+		align = max(align, size);
+	s->align = calculate_alignment(flags, align, size);
+
 	s->useroffset = useroffset;
 	s->usersize = usersize;
 
diff --git a/mm/slob.c b/mm/slob.c
index 835088d55645..fa53e9f73893 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -224,6 +224,7 @@ static void slob_free_pages(void *b, int order)
  * @sp: Page to look in.
  * @size: Size of the allocation.
  * @align: Allocation alignment.
+ * @align_offset: Offset in the allocated block that will be aligned.
  * @page_removed_from_list: Return parameter.
  *
  * Tries to find a chunk of memory at least @size bytes big within @page.
@@ -234,7 +235,7 @@ static void slob_free_pages(void *b, int order)
  *         true (set to false otherwise).
  */
 static void *slob_page_alloc(struct page *sp, size_t size, int align,
-			     bool *page_removed_from_list)
+			      int align_offset, bool *page_removed_from_list)
 {
 	slob_t *prev, *cur, *aligned = NULL;
 	int delta = 0, units = SLOB_UNITS(size);
@@ -243,8 +244,17 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align,
 	for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) {
 		slobidx_t avail = slob_units(cur);
 
+		/*
+		 * 'aligned' will hold the address of the slob block so that the
+		 * address 'aligned'+'align_offset' is aligned according to the
+		 * 'align' parameter. This is for kmalloc() which prepends the
+		 * allocated block with its size, so that the block itself is
+		 * aligned when needed.
+		 */
 		if (align) {
-			aligned = (slob_t *)ALIGN((unsigned long)cur, align);
+			aligned = (slob_t *)
+				(ALIGN((unsigned long)cur + align_offset, align)
+				 - align_offset);
 			delta = aligned - cur;
 		}
 		if (avail >= units + delta) { /* room enough? */
@@ -288,7 +298,8 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align,
 /*
  * slob_alloc: entry point into the slob allocator.
  */
-static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
+static void *slob_alloc(size_t size, gfp_t gfp, int align, int node,
+							int align_offset)
 {
 	struct page *sp;
 	struct list_head *slob_list;
@@ -319,7 +330,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 		if (sp->units < SLOB_UNITS(size))
 			continue;
 
-		b = slob_page_alloc(sp, size, align, &page_removed_from_list);
+		b = slob_page_alloc(sp, size, align, align_offset, &page_removed_from_list);
 		if (!b)
 			continue;
 
@@ -356,7 +367,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 		INIT_LIST_HEAD(&sp->slab_list);
 		set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE));
 		set_slob_page_free(sp, slob_list);
-		b = slob_page_alloc(sp, size, align, &_unused);
+		b = slob_page_alloc(sp, size, align, align_offset, &_unused);
 		BUG_ON(!b);
 		spin_unlock_irqrestore(&slob_lock, flags);
 	}
@@ -458,7 +469,7 @@ static __always_inline void *
 __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 {
 	unsigned int *m;
-	int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+	int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 	void *ret;
 
 	gfp &= gfp_allowed_mask;
@@ -466,19 +477,28 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 	fs_reclaim_acquire(gfp);
 	fs_reclaim_release(gfp);
 
-	if (size < PAGE_SIZE - align) {
+	if (size < PAGE_SIZE - minalign) {
+		int align = minalign;
+
+		/*
+		 * For power of two sizes, guarantee natural alignment for
+		 * kmalloc()'d objects.
+		 */
+		if (is_power_of_2(size))
+			align = max(minalign, (int) size);
+
 		if (!size)
 			return ZERO_SIZE_PTR;
 
-		m = slob_alloc(size + align, gfp, align, node);
+		m = slob_alloc(size + minalign, gfp, align, node, minalign);
 
 		if (!m)
 			return NULL;
 		*m = size;
-		ret = (void *)m + align;
+		ret = (void *)m + minalign;
 
 		trace_kmalloc_node(caller, ret,
-				   size, size + align, gfp, node);
+				   size, size + minalign, gfp, node);
 	} else {
 		unsigned int order = get_order(size);
 
@@ -579,7 +599,7 @@ static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 	fs_reclaim_release(flags);
 
 	if (c->size < PAGE_SIZE) {
-		b = slob_alloc(c->size, flags, c->align, node);
+		b = slob_alloc(c->size, flags, c->align, node, 0);
 		trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size,
 					    SLOB_UNITS(c->size) * SLOB_UNIT,
 					    flags, node);
-- 
cgit v1.2.3


From 6805b32ec2b0897eb180295385efe306e5ac3b3d Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 8 Oct 2019 02:18:42 +0300
Subject: io_uring: remove wait loop spurious wakeups

Any changes interesting to tasks waiting in io_cqring_wait() are
commited with io_cqring_ev_posted(). However, io_ring_drop_ctx_refs()
also tries to do that but with no reason, that means spurious wakeups
every io_free_req() and io_uring_enter().

Just use percpu_ref_put() instead.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index ab8c4e5e442c..ceb3497bdd2a 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -591,14 +591,6 @@ static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data,
 	io_cqring_ev_posted(ctx);
 }
 
-static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs)
-{
-	percpu_ref_put_many(&ctx->refs, refs);
-
-	if (waitqueue_active(&ctx->wait))
-		wake_up(&ctx->wait);
-}
-
 static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
 				   struct io_submit_state *state)
 {
@@ -646,7 +638,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
 	req->result = 0;
 	return req;
 out:
-	io_ring_drop_ctx_refs(ctx, 1);
+	percpu_ref_put(&ctx->refs);
 	return NULL;
 }
 
@@ -654,7 +646,7 @@ static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
 {
 	if (*nr) {
 		kmem_cache_free_bulk(req_cachep, *nr, reqs);
-		io_ring_drop_ctx_refs(ctx, *nr);
+		percpu_ref_put_many(&ctx->refs, *nr);
 		*nr = 0;
 	}
 }
@@ -663,7 +655,7 @@ static void __io_free_req(struct io_kiocb *req)
 {
 	if (req->file && !(req->flags & REQ_F_FIXED_FILE))
 		fput(req->file);
-	io_ring_drop_ctx_refs(req->ctx, 1);
+	percpu_ref_put(&req->ctx->refs);
 	kmem_cache_free(req_cachep, req);
 }
 
@@ -3584,7 +3576,7 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		}
 	}
 
-	io_ring_drop_ctx_refs(ctx, 1);
+	percpu_ref_put(&ctx->refs);
 out_fput:
 	fdput(f);
 	return submitted ? submitted : ret;
-- 
cgit v1.2.3


From 19305134ade08d6e1e549b7200bc60f0021f1916 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Mon, 7 Oct 2019 20:07:57 +0300
Subject: drm/panel: lg-lb035q02: Fix SPI alias

The panel-lg-lb035q02 driver incorrectly includes the OF vendor prefix
in its SPI alias. Fix it, and move the manual alias to an SPI module
device table.

Fixes: f5b0c6542476 ("drm/panel: Add driver for the LG Philips LB035Q02 panel")
Reported-by: H. Nikolaus Schaller <hns@goldelico.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191007170801.27647-2-laurent.pinchart@ideasonboard.com
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/gpu/drm/panel/panel-lg-lb035q02.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panel/panel-lg-lb035q02.c b/drivers/gpu/drm/panel/panel-lg-lb035q02.c
index fc82a525b071..ee4379729a5b 100644
--- a/drivers/gpu/drm/panel/panel-lg-lb035q02.c
+++ b/drivers/gpu/drm/panel/panel-lg-lb035q02.c
@@ -220,9 +220,17 @@ static const struct of_device_id lb035q02_of_match[] = {
 
 MODULE_DEVICE_TABLE(of, lb035q02_of_match);
 
+static const struct spi_device_id lb035q02_ids[] = {
+	{ "lb035q02", 0 },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, lb035q02_ids);
+
 static struct spi_driver lb035q02_driver = {
 	.probe		= lb035q02_probe,
 	.remove		= lb035q02_remove,
+	.id_table	= lb035q02_ids,
 	.driver		= {
 		.name	= "panel-lg-lb035q02",
 		.of_match_table = lb035q02_of_match,
@@ -231,7 +239,6 @@ static struct spi_driver lb035q02_driver = {
 
 module_spi_driver(lb035q02_driver);
 
-MODULE_ALIAS("spi:lgphilips,lb035q02");
 MODULE_AUTHOR("Tomi Valkeinen <tomi.valkeinen@ti.com>");
 MODULE_DESCRIPTION("LG.Philips LB035Q02 LCD Panel driver");
 MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From cf0c4eb15e9dfef7abc9d089740c2560856cf127 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Mon, 7 Oct 2019 20:07:58 +0300
Subject: drm/panel: nec-nl8048hl11: Fix SPI alias

The panel-nec-nl8048hl11 driver incorrectly includes the OF vendor
prefix in its SPI alias. Fix it, and move the manual alias to an SPI
module device table.

Fixes: df439abe6501 ("drm/panel: Add driver for the NEC NL8048HL11 panel")
Reported-by: H. Nikolaus Schaller <hns@goldelico.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191007170801.27647-3-laurent.pinchart@ideasonboard.com
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/gpu/drm/panel/panel-nec-nl8048hl11.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
index 299b217c83e1..20f17e46e65d 100644
--- a/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
+++ b/drivers/gpu/drm/panel/panel-nec-nl8048hl11.c
@@ -230,9 +230,17 @@ static const struct of_device_id nl8048_of_match[] = {
 
 MODULE_DEVICE_TABLE(of, nl8048_of_match);
 
+static const struct spi_device_id nl8048_ids[] = {
+	{ "nl8048hl11", 0 },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, nl8048_ids);
+
 static struct spi_driver nl8048_driver = {
 	.probe		= nl8048_probe,
 	.remove		= nl8048_remove,
+	.id_table	= nl8048_ids,
 	.driver		= {
 		.name	= "panel-nec-nl8048hl11",
 		.pm	= &nl8048_pm_ops,
@@ -242,7 +250,6 @@ static struct spi_driver nl8048_driver = {
 
 module_spi_driver(nl8048_driver);
 
-MODULE_ALIAS("spi:nec,nl8048hl11");
 MODULE_AUTHOR("Erik Gilling <konkers@android.com>");
 MODULE_DESCRIPTION("NEC-NL8048HL11 Driver");
 MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From d82a6ac3002f1701de3199da944910a353f29611 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Mon, 7 Oct 2019 20:07:59 +0300
Subject: drm/panel: sony-acx565akm: Fix SPI alias

The panel-sony-acx565akm driver incorrectly includes the OF vendor
prefix in its SPI alias. Fix it, and move the manual alias to an SPI
module device table.

Fixes: 1c8fc3f0c5d2 ("drm/panel: Add driver for the Sony ACX565AKM panel")
Reported-by: H. Nikolaus Schaller <hns@goldelico.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191007170801.27647-4-laurent.pinchart@ideasonboard.com
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/gpu/drm/panel/panel-sony-acx565akm.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panel/panel-sony-acx565akm.c b/drivers/gpu/drm/panel/panel-sony-acx565akm.c
index 305259b58767..3d5b9c4f68d9 100644
--- a/drivers/gpu/drm/panel/panel-sony-acx565akm.c
+++ b/drivers/gpu/drm/panel/panel-sony-acx565akm.c
@@ -684,9 +684,17 @@ static const struct of_device_id acx565akm_of_match[] = {
 
 MODULE_DEVICE_TABLE(of, acx565akm_of_match);
 
+static const struct spi_device_id acx565akm_ids[] = {
+	{ "acx565akm", 0 },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, acx565akm_ids);
+
 static struct spi_driver acx565akm_driver = {
 	.probe		= acx565akm_probe,
 	.remove		= acx565akm_remove,
+	.id_table	= acx565akm_ids,
 	.driver		= {
 		.name	= "panel-sony-acx565akm",
 		.of_match_table = acx565akm_of_match,
@@ -695,7 +703,6 @@ static struct spi_driver acx565akm_driver = {
 
 module_spi_driver(acx565akm_driver);
 
-MODULE_ALIAS("spi:sony,acx565akm");
 MODULE_AUTHOR("Nokia Corporation");
 MODULE_DESCRIPTION("Sony ACX565AKM LCD Panel Driver");
 MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 692a5424b5b2a574d5050c0a5f93ae0429c4cb08 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Mon, 7 Oct 2019 20:08:00 +0300
Subject: drm/panel: tpo-td028ttec1: Fix SPI alias

The panel-tpo-td028ttec1 driver incorrectly includes the OF vendor
prefix in its SPI alias. Fix it.

Fixes: 415b8dd08711 ("drm/panel: Add driver for the Toppoly TD028TTEC1 panel")
Reported-by: H. Nikolaus Schaller <hns@goldelico.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191007170801.27647-5-laurent.pinchart@ideasonboard.com
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Tested-by: H. Nikolaus Schaller <hns@goldelico.com>
Tested-by: Andreas Kemnade <andreas@kemnade.info>
---
 drivers/gpu/drm/panel/panel-tpo-td028ttec1.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
index d7b2e34626ef..f2baff827f50 100644
--- a/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
+++ b/drivers/gpu/drm/panel/panel-tpo-td028ttec1.c
@@ -375,8 +375,7 @@ static const struct of_device_id td028ttec1_of_match[] = {
 MODULE_DEVICE_TABLE(of, td028ttec1_of_match);
 
 static const struct spi_device_id td028ttec1_ids[] = {
-	{ "tpo,td028ttec1", 0},
-	{ "toppoly,td028ttec1", 0 },
+	{ "td028ttec1", 0 },
 	{ /* sentinel */ }
 };
 
-- 
cgit v1.2.3


From cc635be34eb672a30a4936db30987b7c2e91fb61 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Mon, 7 Oct 2019 20:08:01 +0300
Subject: drm/panel: tpo-td043mtea1: Fix SPI alias

The panel-tpo-td043mtea1 driver incorrectly includes the OF vendor
prefix in its SPI alias. Fix it, and move the manual alias to an SPI
module device table.

Fixes: dc2e1e5b2799 ("drm/panel: Add driver for the Toppoly TD043MTEA1 panel")
Reported-by: H. Nikolaus Schaller <hns@goldelico.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191007170801.27647-6-laurent.pinchart@ideasonboard.com
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Tested-by: H. Nikolaus Schaller <hns@goldelico.com>
---
 drivers/gpu/drm/panel/panel-tpo-td043mtea1.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
index 84370562910f..ba163c779084 100644
--- a/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
+++ b/drivers/gpu/drm/panel/panel-tpo-td043mtea1.c
@@ -491,9 +491,17 @@ static const struct of_device_id td043mtea1_of_match[] = {
 
 MODULE_DEVICE_TABLE(of, td043mtea1_of_match);
 
+static const struct spi_device_id td043mtea1_ids[] = {
+	{ "td043mtea1", 0 },
+	{ /* sentinel */ }
+};
+
+MODULE_DEVICE_TABLE(spi, td043mtea1_ids);
+
 static struct spi_driver td043mtea1_driver = {
 	.probe		= td043mtea1_probe,
 	.remove		= td043mtea1_remove,
+	.id_table	= td043mtea1_ids,
 	.driver		= {
 		.name	= "panel-tpo-td043mtea1",
 		.pm	= &td043mtea1_pm_ops,
@@ -503,7 +511,6 @@ static struct spi_driver td043mtea1_driver = {
 
 module_spi_driver(td043mtea1_driver);
 
-MODULE_ALIAS("spi:tpo,td043mtea1");
 MODULE_AUTHOR("Gražvydas Ignotas <notasas@gmail.com>");
 MODULE_DESCRIPTION("TPO TD043MTEA1 Panel Driver");
 MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From d30213e533fa73929b6af48a5b0e5761879d7db2 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 7 Oct 2019 19:33:46 +0200
Subject: drm/i915: Fix Kconfig indentation

Adjust indentation from spaces to tab (+optional two spaces) as in
coding style with command like:
    $ sed -e 's/^        /\t/' -i */Kconfig

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191007173346.9379-1-krzk@kernel.org
---
 drivers/gpu/drm/i915/Kconfig       |  12 ++--
 drivers/gpu/drm/i915/Kconfig.debug | 144 ++++++++++++++++++-------------------
 2 files changed, 78 insertions(+), 78 deletions(-)

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 0d21402945ab..3c6d57df262d 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -76,7 +76,7 @@ config DRM_I915_CAPTURE_ERROR
 	  This option enables capturing the GPU state when a hang is detected.
 	  This information is vital for triaging hangs and assists in debugging.
 	  Please report any hang to
-            https://bugs.freedesktop.org/enter_bug.cgi?product=DRI
+	    https://bugs.freedesktop.org/enter_bug.cgi?product=DRI
 	  for triaging.
 
 	  If in doubt, say "Y".
@@ -105,11 +105,11 @@ config DRM_I915_USERPTR
 	  If in doubt, say "Y".
 
 config DRM_I915_GVT
-        bool "Enable Intel GVT-g graphics virtualization host support"
-        depends on DRM_I915
-        depends on 64BIT
-        default n
-        help
+	bool "Enable Intel GVT-g graphics virtualization host support"
+	depends on DRM_I915
+	depends on 64BIT
+	default n
+	help
 	  Choose this option if you want to enable Intel GVT-g graphics
 	  virtualization technology host support with integrated graphics.
 	  With GVT-g, it's possible to have one integrated graphics
diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 87a38c6aaa41..95d5fb8058fc 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -1,48 +1,48 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config DRM_I915_WERROR
-        bool "Force GCC to throw an error instead of a warning when compiling"
-        # As this may inadvertently break the build, only allow the user
-        # to shoot oneself in the foot iff they aim really hard
-        depends on EXPERT
-        # We use the dependency on !COMPILE_TEST to not be enabled in
-        # allmodconfig or allyesconfig configurations
-        depends on !COMPILE_TEST
+	bool "Force GCC to throw an error instead of a warning when compiling"
+	# As this may inadvertently break the build, only allow the user
+	# to shoot oneself in the foot iff they aim really hard
+	depends on EXPERT
+	# We use the dependency on !COMPILE_TEST to not be enabled in
+	# allmodconfig or allyesconfig configurations
+	depends on !COMPILE_TEST
 	select HEADER_TEST
-        default n
-        help
-          Add -Werror to the build flags for (and only for) i915.ko.
-          Do not enable this unless you are writing code for the i915.ko module.
+	default n
+	help
+	  Add -Werror to the build flags for (and only for) i915.ko.
+	  Do not enable this unless you are writing code for the i915.ko module.
 
-          Recommended for driver developers only.
+	  Recommended for driver developers only.
 
-          If in doubt, say "N".
+	  If in doubt, say "N".
 
 config DRM_I915_DEBUG
-        bool "Enable additional driver debugging"
-        depends on DRM_I915
-        select DEBUG_FS
-        select PREEMPT_COUNT
-        select REFCOUNT_FULL
-        select I2C_CHARDEV
-        select STACKDEPOT
-        select DRM_DP_AUX_CHARDEV
-        select X86_MSR # used by igt/pm_rpm
-        select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
-        select DRM_DEBUG_MM if DRM=y
+	bool "Enable additional driver debugging"
+	depends on DRM_I915
+	select DEBUG_FS
+	select PREEMPT_COUNT
+	select REFCOUNT_FULL
+	select I2C_CHARDEV
+	select STACKDEPOT
+	select DRM_DP_AUX_CHARDEV
+	select X86_MSR # used by igt/pm_rpm
+	select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
+	select DRM_DEBUG_MM if DRM=y
 	select DRM_DEBUG_SELFTEST
 	select SW_SYNC # signaling validation framework (igt/syncobj*)
 	select DRM_I915_SW_FENCE_DEBUG_OBJECTS
 	select DRM_I915_SELFTEST
 	select DRM_I915_DEBUG_RUNTIME_PM
 	select DRM_I915_DEBUG_MMIO
-        default n
-        help
-          Choose this option to turn on extra driver debugging that may affect
-          performance but will catch some internal issues.
+	default n
+	help
+	  Choose this option to turn on extra driver debugging that may affect
+	  performance but will catch some internal issues.
 
-          Recommended for driver developers only.
+	  Recommended for driver developers only.
 
-          If in doubt, say "N".
+	  If in doubt, say "N".
 
 config DRM_I915_DEBUG_MMIO
 	bool "Always insert extra checks around mmio access by default"
@@ -58,16 +58,16 @@ config DRM_I915_DEBUG_MMIO
 	  If in doubt, say "N".
 
 config DRM_I915_DEBUG_GEM
-        bool "Insert extra checks into the GEM internals"
-        default n
-        depends on DRM_I915_WERROR
-        help
-          Enable extra sanity checks (including BUGs) along the GEM driver
-          paths that may slow the system down and if hit hang the machine.
+	bool "Insert extra checks into the GEM internals"
+	default n
+	depends on DRM_I915_WERROR
+	help
+	  Enable extra sanity checks (including BUGs) along the GEM driver
+	  paths that may slow the system down and if hit hang the machine.
 
-          Recommended for driver developers only.
+	  Recommended for driver developers only.
 
-          If in doubt, say "N".
+	  If in doubt, say "N".
 
 config DRM_I915_ERRLOG_GEM
 	bool "Insert extra logging (very verbose) for common GEM errors"
@@ -110,41 +110,41 @@ config DRM_I915_TRACE_GTT
 	  If in doubt, say "N".
 
 config DRM_I915_SW_FENCE_DEBUG_OBJECTS
-        bool "Enable additional driver debugging for fence objects"
-        depends on DRM_I915
-        select DEBUG_OBJECTS
-        default n
-        help
-          Choose this option to turn on extra driver debugging that may affect
-          performance but will catch some internal issues.
+	bool "Enable additional driver debugging for fence objects"
+	depends on DRM_I915
+	select DEBUG_OBJECTS
+	default n
+	help
+	  Choose this option to turn on extra driver debugging that may affect
+	  performance but will catch some internal issues.
 
-          Recommended for driver developers only.
+	  Recommended for driver developers only.
 
-          If in doubt, say "N".
+	  If in doubt, say "N".
 
 config DRM_I915_SW_FENCE_CHECK_DAG
-        bool "Enable additional driver debugging for detecting dependency cycles"
-        depends on DRM_I915
-        default n
-        help
-          Choose this option to turn on extra driver debugging that may affect
-          performance but will catch some internal issues.
+	bool "Enable additional driver debugging for detecting dependency cycles"
+	depends on DRM_I915
+	default n
+	help
+	  Choose this option to turn on extra driver debugging that may affect
+	  performance but will catch some internal issues.
 
-          Recommended for driver developers only.
+	  Recommended for driver developers only.
 
-          If in doubt, say "N".
+	  If in doubt, say "N".
 
 config DRM_I915_DEBUG_GUC
-        bool "Enable additional driver debugging for GuC"
-        depends on DRM_I915
-        default n
-        help
-          Choose this option to turn on extra driver debugging that may affect
-          performance but will help resolve GuC related issues.
+	bool "Enable additional driver debugging for GuC"
+	depends on DRM_I915
+	default n
+	help
+	  Choose this option to turn on extra driver debugging that may affect
+	  performance but will help resolve GuC related issues.
 
-          Recommended for driver developers only.
+	  Recommended for driver developers only.
 
-          If in doubt, say "N".
+	  If in doubt, say "N".
 
 config DRM_I915_SELFTEST
 	bool "Enable selftests upon driver load"
@@ -177,15 +177,15 @@ config DRM_I915_SELFTEST_BROKEN
 	  If in doubt, say "N".
 
 config DRM_I915_LOW_LEVEL_TRACEPOINTS
-        bool "Enable low level request tracing events"
-        depends on DRM_I915
-        default n
-        help
-          Choose this option to turn on low level request tracing events.
-          This provides the ability to precisely monitor engine utilisation
-          and also analyze the request dependency resolving timeline.
-
-          If in doubt, say "N".
+	bool "Enable low level request tracing events"
+	depends on DRM_I915
+	default n
+	help
+	  Choose this option to turn on low level request tracing events.
+	  This provides the ability to precisely monitor engine utilisation
+	  and also analyze the request dependency resolving timeline.
+
+	  If in doubt, say "N".
 
 config DRM_I915_DEBUG_VBLANK_EVADE
 	bool "Enable extra debug warnings for vblank evasion"
-- 
cgit v1.2.3


From 8f8b1171e1a514c2fdfd388b662a7e5b34e839a8 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 7 Oct 2019 22:09:41 +0100
Subject: drm/i915/perf: Wean ourselves off dev_priv

Use the local uncore accessors for the GT rather than using the [not-so]
magic global dev_priv mmio routines. In the process, we also teach the
perf stream to use backpointers to the i915_perf rather than digging it
out of dev_priv.

v2: Rebase onto i915_perf_types.h

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> #v1
Link: https://patchwork.freedesktop.org/patch/msgid/20191007140812.10963-1-chris@chris-wilson.co.uk
Link: https://patchwork.freedesktop.org/patch/msgid/20191007210942.18145-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.h        |  56 +--
 drivers/gpu/drm/i915/i915_perf.c       | 721 ++++++++++++++++-----------------
 drivers/gpu/drm/i915/i915_perf_types.h |  73 +++-
 3 files changed, 422 insertions(+), 428 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 1b8fd3a38c66..dd0eb8dc4491 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1332,61 +1332,7 @@ struct drm_i915_private {
 
 	struct intel_runtime_pm runtime_pm;
 
-	struct {
-		bool initialized;
-
-		struct kobject *metrics_kobj;
-		struct ctl_table_header *sysctl_header;
-
-		/*
-		 * Lock associated with adding/modifying/removing OA configs
-		 * in dev_priv->perf.metrics_idr.
-		 */
-		struct mutex metrics_lock;
-
-		/*
-		 * List of dynamic configurations, you need to hold
-		 * dev_priv->perf.metrics_lock to access it.
-		 */
-		struct idr metrics_idr;
-
-		/*
-		 * Lock associated with anything below within this structure
-		 * except exclusive_stream.
-		 */
-		struct mutex lock;
-		struct list_head streams;
-
-		/*
-		 * The stream currently using the OA unit. If accessed
-		 * outside a syscall associated to its file
-		 * descriptor, you need to hold
-		 * dev_priv->drm.struct_mutex.
-		 */
-		struct i915_perf_stream *exclusive_stream;
-
-		/**
-		 * For rate limiting any notifications of spurious
-		 * invalid OA reports
-		 */
-		struct ratelimit_state spurious_report_rs;
-
-		struct i915_oa_config test_config;
-
-		u32 gen7_latched_oastatus1;
-		u32 ctx_oactxctrl_offset;
-		u32 ctx_flexeu0_offset;
-
-		/**
-		 * The RPT_ID/reason field for Gen8+ includes a bit
-		 * to determine if the CTX ID in the report is valid
-		 * but the specific bit differs between Gen 8 and 9
-		 */
-		u32 gen8_valid_ctx_bit;
-
-		struct i915_oa_ops ops;
-		const struct i915_oa_format *oa_formats;
-	} perf;
+	struct i915_perf perf;
 
 	/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
 	struct intel_gt gt;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 231388d06c82..5a25bbeb6c7a 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -367,8 +367,7 @@ struct perf_open_properties {
 
 static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer);
 
-static void free_oa_config(struct drm_i915_private *dev_priv,
-			   struct i915_oa_config *oa_config)
+static void free_oa_config(struct i915_oa_config *oa_config)
 {
 	if (!PTR_ERR(oa_config->flex_regs))
 		kfree(oa_config->flex_regs);
@@ -379,53 +378,52 @@ static void free_oa_config(struct drm_i915_private *dev_priv,
 	kfree(oa_config);
 }
 
-static void put_oa_config(struct drm_i915_private *dev_priv,
-			  struct i915_oa_config *oa_config)
+static void put_oa_config(struct i915_oa_config *oa_config)
 {
 	if (!atomic_dec_and_test(&oa_config->ref_count))
 		return;
 
-	free_oa_config(dev_priv, oa_config);
+	free_oa_config(oa_config);
 }
 
-static int get_oa_config(struct drm_i915_private *dev_priv,
+static int get_oa_config(struct i915_perf *perf,
 			 int metrics_set,
 			 struct i915_oa_config **out_config)
 {
 	int ret;
 
 	if (metrics_set == 1) {
-		*out_config = &dev_priv->perf.test_config;
-		atomic_inc(&dev_priv->perf.test_config.ref_count);
+		*out_config = &perf->test_config;
+		atomic_inc(&perf->test_config.ref_count);
 		return 0;
 	}
 
-	ret = mutex_lock_interruptible(&dev_priv->perf.metrics_lock);
+	ret = mutex_lock_interruptible(&perf->metrics_lock);
 	if (ret)
 		return ret;
 
-	*out_config = idr_find(&dev_priv->perf.metrics_idr, metrics_set);
+	*out_config = idr_find(&perf->metrics_idr, metrics_set);
 	if (!*out_config)
 		ret = -EINVAL;
 	else
 		atomic_inc(&(*out_config)->ref_count);
 
-	mutex_unlock(&dev_priv->perf.metrics_lock);
+	mutex_unlock(&perf->metrics_lock);
 
 	return ret;
 }
 
 static u32 gen8_oa_hw_tail_read(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 
-	return I915_READ(GEN8_OATAILPTR) & GEN8_OATAILPTR_MASK;
+	return intel_uncore_read(uncore, GEN8_OATAILPTR) & GEN8_OATAILPTR_MASK;
 }
 
 static u32 gen7_oa_hw_tail_read(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
-	u32 oastatus1 = I915_READ(GEN7_OASTATUS1);
+	struct intel_uncore *uncore = stream->gt->uncore;
+	u32 oastatus1 = intel_uncore_read(uncore, GEN7_OASTATUS1);
 
 	return oastatus1 & GEN7_OASTATUS1_TAIL_MASK;
 }
@@ -456,7 +454,6 @@ static u32 gen7_oa_hw_tail_read(struct i915_perf_stream *stream)
  */
 static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
 	int report_size = stream->oa_buffer.format_size;
 	unsigned long flags;
 	unsigned int aged_idx;
@@ -479,7 +476,7 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 	aged_tail = stream->oa_buffer.tails[aged_idx].offset;
 	aging_tail = stream->oa_buffer.tails[!aged_idx].offset;
 
-	hw_tail = dev_priv->perf.ops.oa_hw_tail_read(stream);
+	hw_tail = stream->perf->ops.oa_hw_tail_read(stream);
 
 	/* The tail pointer increases in 64 byte increments,
 	 * not in report_size steps...
@@ -655,7 +652,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 				  size_t count,
 				  size_t *offset)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 	int report_size = stream->oa_buffer.format_size;
 	u8 *oa_buf_base = stream->oa_buffer.vaddr;
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
@@ -740,7 +737,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		reason = ((report32[0] >> OAREPORT_REASON_SHIFT) &
 			  OAREPORT_REASON_MASK);
 		if (reason == 0) {
-			if (__ratelimit(&dev_priv->perf.spurious_report_rs))
+			if (__ratelimit(&stream->perf->spurious_report_rs))
 				DRM_NOTE("Skipping spurious, invalid OA report\n");
 			continue;
 		}
@@ -755,7 +752,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * Note: that we don't clear the valid_ctx_bit so userspace can
 		 * understand that the ID has been squashed by the kernel.
 		 */
-		if (!(report32[0] & dev_priv->perf.gen8_valid_ctx_bit))
+		if (!(report32[0] & stream->perf->gen8_valid_ctx_bit))
 			ctx_id = report32[2] = INVALID_CTX_ID;
 
 		/*
@@ -789,7 +786,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * switches since it's not-uncommon for periodic samples to
 		 * identify a switch before any 'context switch' report.
 		 */
-		if (!dev_priv->perf.exclusive_stream->ctx ||
+		if (!stream->perf->exclusive_stream->ctx ||
 		    stream->specific_ctx_id == ctx_id ||
 		    stream->oa_buffer.last_ctx_id == stream->specific_ctx_id ||
 		    reason & OAREPORT_REASON_CTX_SWITCH) {
@@ -798,7 +795,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 			 * While filtering for a single context we avoid
 			 * leaking the IDs of other contexts.
 			 */
-			if (dev_priv->perf.exclusive_stream->ctx &&
+			if (stream->perf->exclusive_stream->ctx &&
 			    stream->specific_ctx_id != ctx_id) {
 				report32[2] = INVALID_CTX_ID;
 			}
@@ -830,7 +827,8 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 */
 		head += gtt_offset;
 
-		I915_WRITE(GEN8_OAHEADPTR, head & GEN8_OAHEADPTR_MASK);
+		intel_uncore_write(uncore, GEN8_OAHEADPTR,
+				   head & GEN8_OAHEADPTR_MASK);
 		stream->oa_buffer.head = head;
 
 		spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
@@ -864,14 +862,14 @@ static int gen8_oa_read(struct i915_perf_stream *stream,
 			size_t count,
 			size_t *offset)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 	u32 oastatus;
 	int ret;
 
 	if (WARN_ON(!stream->oa_buffer.vaddr))
 		return -EIO;
 
-	oastatus = I915_READ(GEN8_OASTATUS);
+	oastatus = intel_uncore_read(uncore, GEN8_OASTATUS);
 
 	/*
 	 * We treat OABUFFER_OVERFLOW as a significant error:
@@ -896,14 +894,14 @@ static int gen8_oa_read(struct i915_perf_stream *stream,
 		DRM_DEBUG("OA buffer overflow (exponent = %d): force restart\n",
 			  stream->period_exponent);
 
-		dev_priv->perf.ops.oa_disable(stream);
-		dev_priv->perf.ops.oa_enable(stream);
+		stream->perf->ops.oa_disable(stream);
+		stream->perf->ops.oa_enable(stream);
 
 		/*
 		 * Note: .oa_enable() is expected to re-init the oabuffer and
 		 * reset GEN8_OASTATUS for us
 		 */
-		oastatus = I915_READ(GEN8_OASTATUS);
+		oastatus = intel_uncore_read(uncore, GEN8_OASTATUS);
 	}
 
 	if (oastatus & GEN8_OASTATUS_REPORT_LOST) {
@@ -911,8 +909,8 @@ static int gen8_oa_read(struct i915_perf_stream *stream,
 				       DRM_I915_PERF_RECORD_OA_REPORT_LOST);
 		if (ret)
 			return ret;
-		I915_WRITE(GEN8_OASTATUS,
-			   oastatus & ~GEN8_OASTATUS_REPORT_LOST);
+		intel_uncore_write(uncore, GEN8_OASTATUS,
+				   oastatus & ~GEN8_OASTATUS_REPORT_LOST);
 	}
 
 	return gen8_append_oa_reports(stream, buf, count, offset);
@@ -943,7 +941,7 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 				  size_t count,
 				  size_t *offset)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 	int report_size = stream->oa_buffer.format_size;
 	u8 *oa_buf_base = stream->oa_buffer.vaddr;
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
@@ -1017,7 +1015,7 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 		 * copying it to userspace...
 		 */
 		if (report32[0] == 0) {
-			if (__ratelimit(&dev_priv->perf.spurious_report_rs))
+			if (__ratelimit(&stream->perf->spurious_report_rs))
 				DRM_NOTE("Skipping spurious, invalid OA report\n");
 			continue;
 		}
@@ -1043,9 +1041,9 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 		 */
 		head += gtt_offset;
 
-		I915_WRITE(GEN7_OASTATUS2,
-			   ((head & GEN7_OASTATUS2_HEAD_MASK) |
-			    GEN7_OASTATUS2_MEM_SELECT_GGTT));
+		intel_uncore_write(uncore, GEN7_OASTATUS2,
+				   (head & GEN7_OASTATUS2_HEAD_MASK) |
+				   GEN7_OASTATUS2_MEM_SELECT_GGTT);
 		stream->oa_buffer.head = head;
 
 		spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
@@ -1075,21 +1073,21 @@ static int gen7_oa_read(struct i915_perf_stream *stream,
 			size_t count,
 			size_t *offset)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 	u32 oastatus1;
 	int ret;
 
 	if (WARN_ON(!stream->oa_buffer.vaddr))
 		return -EIO;
 
-	oastatus1 = I915_READ(GEN7_OASTATUS1);
+	oastatus1 = intel_uncore_read(uncore, GEN7_OASTATUS1);
 
 	/* XXX: On Haswell we don't have a safe way to clear oastatus1
 	 * bits while the OA unit is enabled (while the tail pointer
 	 * may be updated asynchronously) so we ignore status bits
 	 * that have already been reported to userspace.
 	 */
-	oastatus1 &= ~dev_priv->perf.gen7_latched_oastatus1;
+	oastatus1 &= ~stream->perf->gen7_latched_oastatus1;
 
 	/* We treat OABUFFER_OVERFLOW as a significant error:
 	 *
@@ -1120,10 +1118,10 @@ static int gen7_oa_read(struct i915_perf_stream *stream,
 		DRM_DEBUG("OA buffer overflow (exponent = %d): force restart\n",
 			  stream->period_exponent);
 
-		dev_priv->perf.ops.oa_disable(stream);
-		dev_priv->perf.ops.oa_enable(stream);
+		stream->perf->ops.oa_disable(stream);
+		stream->perf->ops.oa_enable(stream);
 
-		oastatus1 = I915_READ(GEN7_OASTATUS1);
+		oastatus1 = intel_uncore_read(uncore, GEN7_OASTATUS1);
 	}
 
 	if (unlikely(oastatus1 & GEN7_OASTATUS1_REPORT_LOST)) {
@@ -1131,7 +1129,7 @@ static int gen7_oa_read(struct i915_perf_stream *stream,
 				       DRM_I915_PERF_RECORD_OA_REPORT_LOST);
 		if (ret)
 			return ret;
-		dev_priv->perf.gen7_latched_oastatus1 |=
+		stream->perf->gen7_latched_oastatus1 |=
 			GEN7_OASTATUS1_REPORT_LOST;
 	}
 
@@ -1196,9 +1194,7 @@ static int i915_oa_read(struct i915_perf_stream *stream,
 			size_t count,
 			size_t *offset)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
-
-	return dev_priv->perf.ops.read(stream, buf, count, offset);
+	return stream->perf->ops.read(stream, buf, count, offset);
 }
 
 static struct intel_context *oa_pin_context(struct i915_perf_stream *stream)
@@ -1239,14 +1235,13 @@ static struct intel_context *oa_pin_context(struct i915_perf_stream *stream)
  */
 static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *i915 = stream->dev_priv;
 	struct intel_context *ce;
 
 	ce = oa_pin_context(stream);
 	if (IS_ERR(ce))
 		return PTR_ERR(ce);
 
-	switch (INTEL_GEN(i915)) {
+	switch (INTEL_GEN(ce->engine->i915)) {
 	case 7: {
 		/*
 		 * On Haswell we don't do any post processing of the reports
@@ -1260,7 +1255,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 	case 8:
 	case 9:
 	case 10:
-		if (USES_GUC_SUBMISSION(i915)) {
+		if (USES_GUC_SUBMISSION(ce->engine->i915)) {
 			/*
 			 * When using GuC, the context descriptor we write in
 			 * i915 is read by GuC and rewritten before it's
@@ -1296,7 +1291,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 	}
 
 	default:
-		MISSING_CASE(INTEL_GEN(i915));
+		MISSING_CASE(INTEL_GEN(ce->engine->i915));
 	}
 
 	ce->tag = stream->specific_ctx_id_mask;
@@ -1340,38 +1335,38 @@ free_oa_buffer(struct i915_perf_stream *stream)
 
 static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct i915_perf *perf = stream->perf;
 
-	BUG_ON(stream != dev_priv->perf.exclusive_stream);
+	BUG_ON(stream != perf->exclusive_stream);
 
 	/*
 	 * Unset exclusive_stream first, it will be checked while disabling
 	 * the metric set on gen8+.
 	 */
-	mutex_lock(&dev_priv->drm.struct_mutex);
-	dev_priv->perf.exclusive_stream = NULL;
-	dev_priv->perf.ops.disable_metric_set(stream);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
+	mutex_lock(&perf->i915->drm.struct_mutex);
+	perf->exclusive_stream = NULL;
+	perf->ops.disable_metric_set(stream);
+	mutex_unlock(&perf->i915->drm.struct_mutex);
 
 	free_oa_buffer(stream);
 
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-	intel_runtime_pm_put(&dev_priv->runtime_pm, stream->wakeref);
+	intel_uncore_forcewake_put(stream->gt->uncore, FORCEWAKE_ALL);
+	intel_runtime_pm_put(stream->gt->uncore->rpm, stream->wakeref);
 
 	if (stream->ctx)
 		oa_put_render_ctx_id(stream);
 
-	put_oa_config(dev_priv, stream->oa_config);
+	put_oa_config(stream->oa_config);
 
-	if (dev_priv->perf.spurious_report_rs.missed) {
+	if (perf->spurious_report_rs.missed) {
 		DRM_NOTE("%d spurious OA report notices suppressed due to ratelimiting\n",
-			 dev_priv->perf.spurious_report_rs.missed);
+			 perf->spurious_report_rs.missed);
 	}
 }
 
 static void gen7_init_oa_buffer(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
 	unsigned long flags;
 
@@ -1380,13 +1375,14 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream)
 	/* Pre-DevBDW: OABUFFER must be set with counters off,
 	 * before OASTATUS1, but after OASTATUS2
 	 */
-	I915_WRITE(GEN7_OASTATUS2,
-		   gtt_offset | GEN7_OASTATUS2_MEM_SELECT_GGTT); /* head */
+	intel_uncore_write(uncore, GEN7_OASTATUS2, /* head */
+			   gtt_offset | GEN7_OASTATUS2_MEM_SELECT_GGTT);
 	stream->oa_buffer.head = gtt_offset;
 
-	I915_WRITE(GEN7_OABUFFER, gtt_offset);
+	intel_uncore_write(uncore, GEN7_OABUFFER, gtt_offset);
 
-	I915_WRITE(GEN7_OASTATUS1, gtt_offset | OABUFFER_SIZE_16M); /* tail */
+	intel_uncore_write(uncore, GEN7_OASTATUS1, /* tail */
+			   gtt_offset | OABUFFER_SIZE_16M);
 
 	/* Mark that we need updated tail pointers to read from... */
 	stream->oa_buffer.tails[0].offset = INVALID_TAIL_PTR;
@@ -1398,7 +1394,7 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream)
 	 * already seen since they can't be cleared while periodic
 	 * sampling is enabled.
 	 */
-	dev_priv->perf.gen7_latched_oastatus1 = 0;
+	stream->perf->gen7_latched_oastatus1 = 0;
 
 	/* NB: although the OA buffer will initially be allocated
 	 * zeroed via shmfs (and so this memset is redundant when
@@ -1421,17 +1417,17 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream)
 
 static void gen8_init_oa_buffer(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
 	unsigned long flags;
 
 	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
 
-	I915_WRITE(GEN8_OASTATUS, 0);
-	I915_WRITE(GEN8_OAHEADPTR, gtt_offset);
+	intel_uncore_write(uncore, GEN8_OASTATUS, 0);
+	intel_uncore_write(uncore, GEN8_OAHEADPTR, gtt_offset);
 	stream->oa_buffer.head = gtt_offset;
 
-	I915_WRITE(GEN8_OABUFFER_UDW, 0);
+	intel_uncore_write(uncore, GEN8_OABUFFER_UDW, 0);
 
 	/*
 	 * PRM says:
@@ -1441,9 +1437,9 @@ static void gen8_init_oa_buffer(struct i915_perf_stream *stream)
 	 *  to enable proper functionality of the overflow
 	 *  bit."
 	 */
-	I915_WRITE(GEN8_OABUFFER, gtt_offset |
+	intel_uncore_write(uncore, GEN8_OABUFFER, gtt_offset |
 		   OABUFFER_SIZE_16M | GEN8_OABUFFER_MEM_SELECT_GGTT);
-	I915_WRITE(GEN8_OATAILPTR, gtt_offset & GEN8_OATAILPTR_MASK);
+	intel_uncore_write(uncore, GEN8_OATAILPTR, gtt_offset & GEN8_OATAILPTR_MASK);
 
 	/* Mark that we need updated tail pointers to read from... */
 	stream->oa_buffer.tails[0].offset = INVALID_TAIL_PTR;
@@ -1482,7 +1478,6 @@ static void gen8_init_oa_buffer(struct i915_perf_stream *stream)
 static int alloc_oa_buffer(struct i915_perf_stream *stream)
 {
 	struct drm_i915_gem_object *bo;
-	struct drm_i915_private *dev_priv = stream->dev_priv;
 	struct i915_vma *vma;
 	int ret;
 
@@ -1492,7 +1487,7 @@ static int alloc_oa_buffer(struct i915_perf_stream *stream)
 	BUILD_BUG_ON_NOT_POWER_OF_2(OA_BUFFER_SIZE);
 	BUILD_BUG_ON(OA_BUFFER_SIZE < SZ_128K || OA_BUFFER_SIZE > SZ_16M);
 
-	bo = i915_gem_object_create_shmem(dev_priv, OA_BUFFER_SIZE);
+	bo = i915_gem_object_create_shmem(stream->perf->i915, OA_BUFFER_SIZE);
 	if (IS_ERR(bo)) {
 		DRM_ERROR("Failed to allocate OA buffer\n");
 		return PTR_ERR(bo);
@@ -1533,7 +1528,7 @@ err_unref:
 	return ret;
 }
 
-static void config_oa_regs(struct drm_i915_private *dev_priv,
+static void config_oa_regs(struct intel_uncore *uncore,
 			   const struct i915_oa_reg *regs,
 			   u32 n_regs)
 {
@@ -1542,7 +1537,7 @@ static void config_oa_regs(struct drm_i915_private *dev_priv,
 	for (i = 0; i < n_regs; i++) {
 		const struct i915_oa_reg *reg = regs + i;
 
-		I915_WRITE(reg->addr, reg->value);
+		intel_uncore_write(uncore, reg->addr, reg->value);
 	}
 }
 
@@ -1575,7 +1570,7 @@ static void delay_after_mux(void)
 
 static int hsw_enable_metric_set(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 	const struct i915_oa_config *oa_config = stream->oa_config;
 
 	/*
@@ -1588,15 +1583,15 @@ static int hsw_enable_metric_set(struct i915_perf_stream *stream)
 	 * count the events from non-render domain. Unit level clock
 	 * gating for RCS should also be disabled.
 	 */
-	I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) &
-				    ~GEN7_DOP_CLOCK_GATE_ENABLE));
-	I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) |
-				  GEN6_CSUNIT_CLOCK_GATE_DISABLE));
+	intel_uncore_rmw(uncore, GEN7_MISCCPCTL,
+			 GEN7_DOP_CLOCK_GATE_ENABLE, 0);
+	intel_uncore_rmw(uncore, GEN6_UCGCTL1,
+			 0, GEN6_CSUNIT_CLOCK_GATE_DISABLE);
 
-	config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len);
+	config_oa_regs(uncore, oa_config->mux_regs, oa_config->mux_regs_len);
 	delay_after_mux();
 
-	config_oa_regs(dev_priv, oa_config->b_counter_regs,
+	config_oa_regs(uncore, oa_config->b_counter_regs,
 		       oa_config->b_counter_regs_len);
 
 	return 0;
@@ -1604,15 +1599,14 @@ static int hsw_enable_metric_set(struct i915_perf_stream *stream)
 
 static void hsw_disable_metric_set(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 
-	I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) &
-				  ~GEN6_CSUNIT_CLOCK_GATE_DISABLE));
-	I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) |
-				    GEN7_DOP_CLOCK_GATE_ENABLE));
+	intel_uncore_rmw(uncore, GEN6_UCGCTL1,
+			 GEN6_CSUNIT_CLOCK_GATE_DISABLE, 0);
+	intel_uncore_rmw(uncore, GEN7_MISCCPCTL,
+			 0, GEN7_DOP_CLOCK_GATE_ENABLE);
 
-	I915_WRITE(GDT_CHICKEN_BITS, (I915_READ(GDT_CHICKEN_BITS) &
-				      ~GT_NOA_ENABLE));
+	intel_uncore_rmw(uncore, GDT_CHICKEN_BITS, GT_NOA_ENABLE, 0);
 }
 
 static u32 oa_config_flex_reg(const struct i915_oa_config *oa_config,
@@ -1647,9 +1641,8 @@ static void
 gen8_update_reg_state_unlocked(const struct intel_context *ce,
 			       const struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *i915 = ce->engine->i915;
-	u32 ctx_oactxctrl = i915->perf.ctx_oactxctrl_offset;
-	u32 ctx_flexeu0 = i915->perf.ctx_flexeu0_offset;
+	u32 ctx_oactxctrl = stream->perf->ctx_oactxctrl_offset;
+	u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset;
 	/* The MMIO offsets for Flex EU registers aren't contiguous */
 	i915_reg_t flex_regs[] = {
 		EU_PERF_CNTL0,
@@ -1672,7 +1665,8 @@ gen8_update_reg_state_unlocked(const struct intel_context *ce,
 		reg_state[ctx_flexeu0 + i * 2 + 1] =
 			oa_config_flex_reg(stream->oa_config, flex_regs[i]);
 
-	reg_state[CTX_R_PWR_CLK_STATE] = intel_sseu_make_rpcs(i915, &ce->sseu);
+	reg_state[CTX_R_PWR_CLK_STATE] =
+		intel_sseu_make_rpcs(ce->engine->i915, &ce->sseu);
 }
 
 struct flex {
@@ -1827,9 +1821,9 @@ static int gen8_configure_context(struct i915_gem_context *ctx,
 static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 				       const struct i915_oa_config *oa_config)
 {
-	struct drm_i915_private *i915 = stream->dev_priv;
+	struct drm_i915_private *i915 = stream->perf->i915;
 	/* The MMIO offsets for Flex EU registers aren't contiguous */
-	const u32 ctx_flexeu0 = i915->perf.ctx_flexeu0_offset;
+	const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset;
 #define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1)
 	struct flex regs[] = {
 		{
@@ -1838,7 +1832,7 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 		},
 		{
 			GEN8_OACTXCONTROL,
-			i915->perf.ctx_oactxctrl_offset + 1,
+			stream->perf->ctx_oactxctrl_offset + 1,
 			((stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
 			 (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
 			 GEN8_OA_COUNTER_RESUME)
@@ -1922,7 +1916,7 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 
 static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 	const struct i915_oa_config *oa_config = stream->oa_config;
 	int ret;
 
@@ -1949,10 +1943,10 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	 * be read back from automatically triggered reports, as part of the
 	 * RPT_ID field.
 	 */
-	if (IS_GEN_RANGE(dev_priv, 9, 11)) {
-		I915_WRITE(GEN8_OA_DEBUG,
-			   _MASKED_BIT_ENABLE(GEN9_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS |
-					      GEN9_OA_DEBUG_INCLUDE_CLK_RATIO));
+	if (IS_GEN_RANGE(stream->perf->i915, 9, 11)) {
+		intel_uncore_write(uncore, GEN8_OA_DEBUG,
+				   _MASKED_BIT_ENABLE(GEN9_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS |
+						      GEN9_OA_DEBUG_INCLUDE_CLK_RATIO));
 	}
 
 	/*
@@ -1964,10 +1958,10 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	if (ret)
 		return ret;
 
-	config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len);
+	config_oa_regs(uncore, oa_config->mux_regs, oa_config->mux_regs_len);
 	delay_after_mux();
 
-	config_oa_regs(dev_priv, oa_config->b_counter_regs,
+	config_oa_regs(uncore, oa_config->b_counter_regs,
 		       oa_config->b_counter_regs_len);
 
 	return 0;
@@ -1975,30 +1969,28 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 
 static void gen8_disable_metric_set(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 
 	/* Reset all contexts' slices/subslices configurations. */
 	gen8_configure_all_contexts(stream, NULL);
 
-	I915_WRITE(GDT_CHICKEN_BITS, (I915_READ(GDT_CHICKEN_BITS) &
-				      ~GT_NOA_ENABLE));
+	intel_uncore_rmw(uncore, GDT_CHICKEN_BITS, GT_NOA_ENABLE, 0);
 }
 
 static void gen10_disable_metric_set(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 
 	/* Reset all contexts' slices/subslices configurations. */
 	gen8_configure_all_contexts(stream, NULL);
 
 	/* Make sure we disable noa to save power. */
-	I915_WRITE(RPM_CONFIG1,
-		   I915_READ(RPM_CONFIG1) & ~GEN10_GT_NOA_ENABLE);
+	intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0);
 }
 
 static void gen7_oa_enable(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 	struct i915_gem_context *ctx = stream->ctx;
 	u32 ctx_id = stream->specific_ctx_id;
 	bool periodic = stream->periodic;
@@ -2016,19 +2008,19 @@ static void gen7_oa_enable(struct i915_perf_stream *stream)
 	 */
 	gen7_init_oa_buffer(stream);
 
-	I915_WRITE(GEN7_OACONTROL,
-		   (ctx_id & GEN7_OACONTROL_CTX_MASK) |
-		   (period_exponent <<
-		    GEN7_OACONTROL_TIMER_PERIOD_SHIFT) |
-		   (periodic ? GEN7_OACONTROL_TIMER_ENABLE : 0) |
-		   (report_format << GEN7_OACONTROL_FORMAT_SHIFT) |
-		   (ctx ? GEN7_OACONTROL_PER_CTX_ENABLE : 0) |
-		   GEN7_OACONTROL_ENABLE);
+	intel_uncore_write(uncore, GEN7_OACONTROL,
+			   (ctx_id & GEN7_OACONTROL_CTX_MASK) |
+			   (period_exponent <<
+			    GEN7_OACONTROL_TIMER_PERIOD_SHIFT) |
+			   (periodic ? GEN7_OACONTROL_TIMER_ENABLE : 0) |
+			   (report_format << GEN7_OACONTROL_FORMAT_SHIFT) |
+			   (ctx ? GEN7_OACONTROL_PER_CTX_ENABLE : 0) |
+			   GEN7_OACONTROL_ENABLE);
 }
 
 static void gen8_oa_enable(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_uncore *uncore = stream->gt->uncore;
 	u32 report_format = stream->oa_buffer.format;
 
 	/*
@@ -2047,9 +2039,9 @@ static void gen8_oa_enable(struct i915_perf_stream *stream)
 	 * filtering and instead filter on the cpu based on the context-id
 	 * field of reports
 	 */
-	I915_WRITE(GEN8_OACONTROL, (report_format <<
-				    GEN8_OA_REPORT_FORMAT_SHIFT) |
-				   GEN8_OA_COUNTER_ENABLE);
+	intel_uncore_write(uncore, GEN8_OACONTROL,
+			   (report_format << GEN8_OA_REPORT_FORMAT_SHIFT) |
+			   GEN8_OA_COUNTER_ENABLE);
 }
 
 /**
@@ -2063,9 +2055,7 @@ static void gen8_oa_enable(struct i915_perf_stream *stream)
  */
 static void i915_oa_stream_enable(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
-
-	dev_priv->perf.ops.oa_enable(stream);
+	stream->perf->ops.oa_enable(stream);
 
 	if (stream->periodic)
 		hrtimer_start(&stream->poll_check_timer,
@@ -2075,7 +2065,7 @@ static void i915_oa_stream_enable(struct i915_perf_stream *stream)
 
 static void gen7_oa_disable(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = &stream->dev_priv->uncore;
+	struct intel_uncore *uncore = stream->gt->uncore;
 
 	intel_uncore_write(uncore, GEN7_OACONTROL, 0);
 	if (intel_wait_for_register(uncore,
@@ -2086,7 +2076,7 @@ static void gen7_oa_disable(struct i915_perf_stream *stream)
 
 static void gen8_oa_disable(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = &stream->dev_priv->uncore;
+	struct intel_uncore *uncore = stream->gt->uncore;
 
 	intel_uncore_write(uncore, GEN8_OACONTROL, 0);
 	if (intel_wait_for_register(uncore,
@@ -2105,9 +2095,7 @@ static void gen8_oa_disable(struct i915_perf_stream *stream)
  */
 static void i915_oa_stream_disable(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
-
-	dev_priv->perf.ops.oa_disable(stream);
+	stream->perf->ops.oa_disable(stream);
 
 	if (stream->periodic)
 		hrtimer_cancel(&stream->poll_check_timer);
@@ -2144,7 +2132,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 			       struct drm_i915_perf_open_param *param,
 			       struct perf_open_properties *props)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct i915_perf *perf = stream->perf;
 	int format_size;
 	int ret;
 
@@ -2152,7 +2140,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	 * reason then don't let userspace try their luck with config
 	 * IDs
 	 */
-	if (!dev_priv->perf.metrics_kobj) {
+	if (!perf->metrics_kobj) {
 		DRM_DEBUG("OA metrics weren't advertised via sysfs\n");
 		return -EINVAL;
 	}
@@ -2162,7 +2150,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		return -EINVAL;
 	}
 
-	if (!dev_priv->perf.ops.enable_metric_set) {
+	if (!perf->ops.enable_metric_set) {
 		DRM_DEBUG("OA unit not supported\n");
 		return -ENODEV;
 	}
@@ -2171,7 +2159,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	 * counter reports and marshal to the appropriate client
 	 * we currently only allow exclusive access
 	 */
-	if (dev_priv->perf.exclusive_stream) {
+	if (perf->exclusive_stream) {
 		DRM_DEBUG("OA unit already in use\n");
 		return -EBUSY;
 	}
@@ -2183,7 +2171,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 
 	stream->sample_size = sizeof(struct drm_i915_perf_record_header);
 
-	format_size = dev_priv->perf.oa_formats[props->oa_format].size;
+	format_size = perf->oa_formats[props->oa_format].size;
 
 	stream->sample_flags |= SAMPLE_OA_REPORT;
 	stream->sample_size += format_size;
@@ -2193,7 +2181,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		return -EINVAL;
 
 	stream->oa_buffer.format =
-		dev_priv->perf.oa_formats[props->oa_format].format;
+		perf->oa_formats[props->oa_format].format;
 
 	stream->periodic = props->oa_periodic;
 	if (stream->periodic)
@@ -2207,7 +2195,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		}
 	}
 
-	ret = get_oa_config(dev_priv, props->metrics_set, &stream->oa_config);
+	ret = get_oa_config(perf, props->metrics_set, &stream->oa_config);
 	if (ret) {
 		DRM_DEBUG("Invalid OA config id=%i\n", props->metrics_set);
 		goto err_config;
@@ -2225,27 +2213,27 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	 *   In our case we are expecting that taking pm + FORCEWAKE
 	 *   references will effectively disable RC6.
 	 */
-	stream->wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
+	stream->wakeref = intel_runtime_pm_get(stream->gt->uncore->rpm);
+	intel_uncore_forcewake_get(stream->gt->uncore, FORCEWAKE_ALL);
 
 	ret = alloc_oa_buffer(stream);
 	if (ret)
 		goto err_oa_buf_alloc;
 
-	ret = i915_mutex_lock_interruptible(&dev_priv->drm);
+	ret = i915_mutex_lock_interruptible(&stream->perf->i915->drm);
 	if (ret)
 		goto err_lock;
 
 	stream->ops = &i915_oa_stream_ops;
-	dev_priv->perf.exclusive_stream = stream;
+	perf->exclusive_stream = stream;
 
-	ret = dev_priv->perf.ops.enable_metric_set(stream);
+	ret = perf->ops.enable_metric_set(stream);
 	if (ret) {
 		DRM_DEBUG("Unable to enable metric set\n");
 		goto err_enable;
 	}
 
-	mutex_unlock(&dev_priv->drm.struct_mutex);
+	mutex_unlock(&stream->perf->i915->drm.struct_mutex);
 
 	hrtimer_init(&stream->poll_check_timer,
 		     CLOCK_MONOTONIC, HRTIMER_MODE_REL);
@@ -2256,18 +2244,18 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	return 0;
 
 err_enable:
-	dev_priv->perf.exclusive_stream = NULL;
-	dev_priv->perf.ops.disable_metric_set(stream);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
+	perf->exclusive_stream = NULL;
+	perf->ops.disable_metric_set(stream);
+	mutex_unlock(&stream->perf->i915->drm.struct_mutex);
 
 err_lock:
 	free_oa_buffer(stream);
 
 err_oa_buf_alloc:
-	put_oa_config(dev_priv, stream->oa_config);
+	put_oa_config(stream->oa_config);
 
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-	intel_runtime_pm_put(&dev_priv->runtime_pm, stream->wakeref);
+	intel_uncore_forcewake_put(stream->gt->uncore, FORCEWAKE_ALL);
+	intel_runtime_pm_put(stream->gt->uncore->rpm, stream->wakeref);
 
 err_config:
 	if (stream->ctx)
@@ -2359,7 +2347,7 @@ static ssize_t i915_perf_read(struct file *file,
 			      loff_t *ppos)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct i915_perf *perf = stream->perf;
 	ssize_t ret;
 
 	/* To ensure it's handled consistently we simply treat all reads of a
@@ -2382,15 +2370,15 @@ static ssize_t i915_perf_read(struct file *file,
 			if (ret)
 				return ret;
 
-			mutex_lock(&dev_priv->perf.lock);
+			mutex_lock(&perf->lock);
 			ret = i915_perf_read_locked(stream, file,
 						    buf, count, ppos);
-			mutex_unlock(&dev_priv->perf.lock);
+			mutex_unlock(&perf->lock);
 		} while (ret == -EAGAIN);
 	} else {
-		mutex_lock(&dev_priv->perf.lock);
+		mutex_lock(&perf->lock);
 		ret = i915_perf_read_locked(stream, file, buf, count, ppos);
-		mutex_unlock(&dev_priv->perf.lock);
+		mutex_unlock(&perf->lock);
 	}
 
 	/* We allow the poll checking to sometimes report false positive EPOLLIN
@@ -2428,7 +2416,6 @@ static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer)
 
 /**
  * i915_perf_poll_locked - poll_wait() with a suitable wait queue for stream
- * @dev_priv: i915 device instance
  * @stream: An i915 perf stream
  * @file: An i915 perf stream file
  * @wait: poll() state table
@@ -2437,15 +2424,14 @@ static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer)
  * &i915_perf_stream_ops->poll_wait to call poll_wait() with a wait queue that
  * will be woken for new stream data.
  *
- * Note: The &drm_i915_private->perf.lock mutex has been taken to serialize
+ * Note: The &perf->lock mutex has been taken to serialize
  * with any non-file-operation driver hooks.
  *
  * Returns: any poll events that are ready without sleeping
  */
-static __poll_t i915_perf_poll_locked(struct drm_i915_private *dev_priv,
-					  struct i915_perf_stream *stream,
-					  struct file *file,
-					  poll_table *wait)
+static __poll_t i915_perf_poll_locked(struct i915_perf_stream *stream,
+				      struct file *file,
+				      poll_table *wait)
 {
 	__poll_t events = 0;
 
@@ -2479,12 +2465,12 @@ static __poll_t i915_perf_poll_locked(struct drm_i915_private *dev_priv,
 static __poll_t i915_perf_poll(struct file *file, poll_table *wait)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct i915_perf *perf = stream->perf;
 	__poll_t ret;
 
-	mutex_lock(&dev_priv->perf.lock);
-	ret = i915_perf_poll_locked(dev_priv, stream, file, wait);
-	mutex_unlock(&dev_priv->perf.lock);
+	mutex_lock(&perf->lock);
+	ret = i915_perf_poll_locked(stream, file, wait);
+	mutex_unlock(&perf->lock);
 
 	return ret;
 }
@@ -2543,7 +2529,7 @@ static void i915_perf_disable_locked(struct i915_perf_stream *stream)
  * @cmd: the ioctl request
  * @arg: the ioctl data
  *
- * Note: The &drm_i915_private->perf.lock mutex has been taken to serialize
+ * Note: The &perf->lock mutex has been taken to serialize
  * with any non-file-operation driver hooks.
  *
  * Returns: zero on success or a negative error code. Returns -EINVAL for
@@ -2581,12 +2567,12 @@ static long i915_perf_ioctl(struct file *file,
 			    unsigned long arg)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct i915_perf *perf = stream->perf;
 	long ret;
 
-	mutex_lock(&dev_priv->perf.lock);
+	mutex_lock(&perf->lock);
 	ret = i915_perf_ioctl_locked(stream, cmd, arg);
-	mutex_unlock(&dev_priv->perf.lock);
+	mutex_unlock(&perf->lock);
 
 	return ret;
 }
@@ -2598,7 +2584,7 @@ static long i915_perf_ioctl(struct file *file,
  * Frees all resources associated with the given i915 perf @stream, disabling
  * any associated data capture in the process.
  *
- * Note: The &drm_i915_private->perf.lock mutex has been taken to serialize
+ * Note: The &perf->lock mutex has been taken to serialize
  * with any non-file-operation driver hooks.
  */
 static void i915_perf_destroy_locked(struct i915_perf_stream *stream)
@@ -2631,14 +2617,14 @@ static void i915_perf_destroy_locked(struct i915_perf_stream *stream)
 static int i915_perf_release(struct inode *inode, struct file *file)
 {
 	struct i915_perf_stream *stream = file->private_data;
-	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct i915_perf *perf = stream->perf;
 
-	mutex_lock(&dev_priv->perf.lock);
+	mutex_lock(&perf->lock);
 	i915_perf_destroy_locked(stream);
-	mutex_unlock(&dev_priv->perf.lock);
+	mutex_unlock(&perf->lock);
 
 	/* Release the reference the perf stream kept on the driver. */
-	drm_dev_put(&dev_priv->drm);
+	drm_dev_put(&perf->i915->drm);
 
 	return 0;
 }
@@ -2660,7 +2646,7 @@ static const struct file_operations fops = {
 
 /**
  * i915_perf_open_ioctl_locked - DRM ioctl() for userspace to open a stream FD
- * @dev_priv: i915 device instance
+ * @perf: i915 perf instance
  * @param: The open parameters passed to 'DRM_I915_PERF_OPEN`
  * @props: individually validated u64 property value pairs
  * @file: drm file
@@ -2668,7 +2654,7 @@ static const struct file_operations fops = {
  * See i915_perf_ioctl_open() for interface details.
  *
  * Implements further stream config validation and stream initialization on
- * behalf of i915_perf_open_ioctl() with the &drm_i915_private->perf.lock mutex
+ * behalf of i915_perf_open_ioctl() with the &perf->lock mutex
  * taken to serialize with any non-file-operation driver hooks.
  *
  * Note: at this point the @props have only been validated in isolation and
@@ -2683,7 +2669,7 @@ static const struct file_operations fops = {
  * Returns: zero on success or a negative error code.
  */
 static int
-i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv,
+i915_perf_open_ioctl_locked(struct i915_perf *perf,
 			    struct drm_i915_perf_open_param *param,
 			    struct perf_open_properties *props,
 			    struct drm_file *file)
@@ -2722,7 +2708,7 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv,
 	 * MI_REPORT_PERF_COUNT commands and so consider it a privileged op to
 	 * enable the OA unit by default.
 	 */
-	if (IS_HASWELL(dev_priv) && specific_ctx)
+	if (IS_HASWELL(perf->i915) && specific_ctx)
 		privileged_op = false;
 
 	/* Similar to perf's kernel.perf_paranoid_cpu sysctl option
@@ -2743,7 +2729,8 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv,
 		goto err_ctx;
 	}
 
-	stream->dev_priv = dev_priv;
+	stream->perf = perf;
+	stream->gt = &perf->i915->gt;
 	stream->ctx = specific_ctx;
 
 	ret = i915_oa_stream_init(stream, param, props);
@@ -2759,7 +2746,7 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv,
 		goto err_flags;
 	}
 
-	list_add(&stream->link, &dev_priv->perf.streams);
+	list_add(&stream->link, &perf->streams);
 
 	if (param->flags & I915_PERF_FLAG_FD_CLOEXEC)
 		f_flags |= O_CLOEXEC;
@@ -2778,7 +2765,7 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv,
 	/* Take a reference on the driver that will be kept with stream_fd
 	 * until its release.
 	 */
-	drm_dev_get(&dev_priv->drm);
+	drm_dev_get(&perf->i915->drm);
 
 	return stream_fd;
 
@@ -2796,15 +2783,15 @@ err:
 	return ret;
 }
 
-static u64 oa_exponent_to_ns(struct drm_i915_private *dev_priv, int exponent)
+static u64 oa_exponent_to_ns(struct i915_perf *perf, int exponent)
 {
 	return div64_u64(1000000000ULL * (2ULL << exponent),
-			 1000ULL * RUNTIME_INFO(dev_priv)->cs_timestamp_frequency_khz);
+			 1000ULL * RUNTIME_INFO(perf->i915)->cs_timestamp_frequency_khz);
 }
 
 /**
  * read_properties_unlocked - validate + copy userspace stream open properties
- * @dev_priv: i915 device instance
+ * @perf: i915 perf instance
  * @uprops: The array of u64 key value pairs given by userspace
  * @n_props: The number of key value pairs expected in @uprops
  * @props: The stream configuration built up while validating properties
@@ -2817,7 +2804,7 @@ static u64 oa_exponent_to_ns(struct drm_i915_private *dev_priv, int exponent)
  * we shouldn't validate or assume anything about ordering here. This doesn't
  * rule out defining new properties with ordering requirements in the future.
  */
-static int read_properties_unlocked(struct drm_i915_private *dev_priv,
+static int read_properties_unlocked(struct i915_perf *perf,
 				    u64 __user *uprops,
 				    u32 n_props,
 				    struct perf_open_properties *props)
@@ -2883,7 +2870,7 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv,
 					  value);
 				return -EINVAL;
 			}
-			if (!dev_priv->perf.oa_formats[value].size) {
+			if (!perf->oa_formats[value].size) {
 				DRM_DEBUG("Unsupported OA report format %llu\n",
 					  value);
 				return -EINVAL;
@@ -2904,7 +2891,7 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv,
 			 */
 
 			BUILD_BUG_ON(sizeof(oa_period) != 8);
-			oa_period = oa_exponent_to_ns(dev_priv, value);
+			oa_period = oa_exponent_to_ns(perf, value);
 
 			/* This check is primarily to ensure that oa_period <=
 			 * UINT32_MAX (before passing to do_div which only
@@ -2958,7 +2945,7 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv,
  * mutex to avoid an awkward lockdep with mmap_sem.
  *
  * Most of the implementation details are handled by
- * i915_perf_open_ioctl_locked() after taking the &drm_i915_private->perf.lock
+ * i915_perf_open_ioctl_locked() after taking the &perf->lock
  * mutex for serializing with any non-file-operation driver hooks.
  *
  * Return: A newly opened i915 Perf stream file descriptor or negative
@@ -2967,13 +2954,13 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv,
 int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_perf *perf = &to_i915(dev)->perf;
 	struct drm_i915_perf_open_param *param = data;
 	struct perf_open_properties props;
 	u32 known_open_flags;
 	int ret;
 
-	if (!dev_priv->perf.initialized) {
+	if (!perf->i915) {
 		DRM_DEBUG("i915 perf interface not available for this system\n");
 		return -ENOTSUPP;
 	}
@@ -2986,124 +2973,127 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	ret = read_properties_unlocked(dev_priv,
+	ret = read_properties_unlocked(perf,
 				       u64_to_user_ptr(param->properties_ptr),
 				       param->num_properties,
 				       &props);
 	if (ret)
 		return ret;
 
-	mutex_lock(&dev_priv->perf.lock);
-	ret = i915_perf_open_ioctl_locked(dev_priv, param, &props, file);
-	mutex_unlock(&dev_priv->perf.lock);
+	mutex_lock(&perf->lock);
+	ret = i915_perf_open_ioctl_locked(perf, param, &props, file);
+	mutex_unlock(&perf->lock);
 
 	return ret;
 }
 
 /**
  * i915_perf_register - exposes i915-perf to userspace
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * In particular OA metric sets are advertised under a sysfs metrics/
  * directory allowing userspace to enumerate valid IDs that can be
  * used to open an i915-perf stream.
  */
-void i915_perf_register(struct drm_i915_private *dev_priv)
+void i915_perf_register(struct drm_i915_private *i915)
 {
+	struct i915_perf *perf = &i915->perf;
 	int ret;
 
-	if (!dev_priv->perf.initialized)
+	if (!perf->i915)
 		return;
 
 	/* To be sure we're synchronized with an attempted
 	 * i915_perf_open_ioctl(); considering that we register after
 	 * being exposed to userspace.
 	 */
-	mutex_lock(&dev_priv->perf.lock);
+	mutex_lock(&perf->lock);
 
-	dev_priv->perf.metrics_kobj =
+	perf->metrics_kobj =
 		kobject_create_and_add("metrics",
-				       &dev_priv->drm.primary->kdev->kobj);
-	if (!dev_priv->perf.metrics_kobj)
+				       &i915->drm.primary->kdev->kobj);
+	if (!perf->metrics_kobj)
 		goto exit;
 
-	sysfs_attr_init(&dev_priv->perf.test_config.sysfs_metric_id.attr);
-
-	if (INTEL_GEN(dev_priv) >= 11) {
-		i915_perf_load_test_config_icl(dev_priv);
-	} else if (IS_CANNONLAKE(dev_priv)) {
-		i915_perf_load_test_config_cnl(dev_priv);
-	} else if (IS_COFFEELAKE(dev_priv)) {
-		if (IS_CFL_GT2(dev_priv))
-			i915_perf_load_test_config_cflgt2(dev_priv);
-		if (IS_CFL_GT3(dev_priv))
-			i915_perf_load_test_config_cflgt3(dev_priv);
-	} else if (IS_GEMINILAKE(dev_priv)) {
-		i915_perf_load_test_config_glk(dev_priv);
-	} else if (IS_KABYLAKE(dev_priv)) {
-		if (IS_KBL_GT2(dev_priv))
-			i915_perf_load_test_config_kblgt2(dev_priv);
-		else if (IS_KBL_GT3(dev_priv))
-			i915_perf_load_test_config_kblgt3(dev_priv);
-	} else if (IS_BROXTON(dev_priv)) {
-		i915_perf_load_test_config_bxt(dev_priv);
-	} else if (IS_SKYLAKE(dev_priv)) {
-		if (IS_SKL_GT2(dev_priv))
-			i915_perf_load_test_config_sklgt2(dev_priv);
-		else if (IS_SKL_GT3(dev_priv))
-			i915_perf_load_test_config_sklgt3(dev_priv);
-		else if (IS_SKL_GT4(dev_priv))
-			i915_perf_load_test_config_sklgt4(dev_priv);
-	} else if (IS_CHERRYVIEW(dev_priv)) {
-		i915_perf_load_test_config_chv(dev_priv);
-	} else if (IS_BROADWELL(dev_priv)) {
-		i915_perf_load_test_config_bdw(dev_priv);
-	} else if (IS_HASWELL(dev_priv)) {
-		i915_perf_load_test_config_hsw(dev_priv);
-}
-
-	if (dev_priv->perf.test_config.id == 0)
+	sysfs_attr_init(&perf->test_config.sysfs_metric_id.attr);
+
+	if (INTEL_GEN(i915) >= 11) {
+		i915_perf_load_test_config_icl(i915);
+	} else if (IS_CANNONLAKE(i915)) {
+		i915_perf_load_test_config_cnl(i915);
+	} else if (IS_COFFEELAKE(i915)) {
+		if (IS_CFL_GT2(i915))
+			i915_perf_load_test_config_cflgt2(i915);
+		if (IS_CFL_GT3(i915))
+			i915_perf_load_test_config_cflgt3(i915);
+	} else if (IS_GEMINILAKE(i915)) {
+		i915_perf_load_test_config_glk(i915);
+	} else if (IS_KABYLAKE(i915)) {
+		if (IS_KBL_GT2(i915))
+			i915_perf_load_test_config_kblgt2(i915);
+		else if (IS_KBL_GT3(i915))
+			i915_perf_load_test_config_kblgt3(i915);
+	} else if (IS_BROXTON(i915)) {
+		i915_perf_load_test_config_bxt(i915);
+	} else if (IS_SKYLAKE(i915)) {
+		if (IS_SKL_GT2(i915))
+			i915_perf_load_test_config_sklgt2(i915);
+		else if (IS_SKL_GT3(i915))
+			i915_perf_load_test_config_sklgt3(i915);
+		else if (IS_SKL_GT4(i915))
+			i915_perf_load_test_config_sklgt4(i915);
+	} else if (IS_CHERRYVIEW(i915)) {
+		i915_perf_load_test_config_chv(i915);
+	} else if (IS_BROADWELL(i915)) {
+		i915_perf_load_test_config_bdw(i915);
+	} else if (IS_HASWELL(i915)) {
+		i915_perf_load_test_config_hsw(i915);
+	}
+
+	if (perf->test_config.id == 0)
 		goto sysfs_error;
 
-	ret = sysfs_create_group(dev_priv->perf.metrics_kobj,
-				 &dev_priv->perf.test_config.sysfs_metric);
+	ret = sysfs_create_group(perf->metrics_kobj,
+				 &perf->test_config.sysfs_metric);
 	if (ret)
 		goto sysfs_error;
 
-	atomic_set(&dev_priv->perf.test_config.ref_count, 1);
+	atomic_set(&perf->test_config.ref_count, 1);
 
 	goto exit;
 
 sysfs_error:
-	kobject_put(dev_priv->perf.metrics_kobj);
-	dev_priv->perf.metrics_kobj = NULL;
+	kobject_put(perf->metrics_kobj);
+	perf->metrics_kobj = NULL;
 
 exit:
-	mutex_unlock(&dev_priv->perf.lock);
+	mutex_unlock(&perf->lock);
 }
 
 /**
  * i915_perf_unregister - hide i915-perf from userspace
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * i915-perf state cleanup is split up into an 'unregister' and
  * 'deinit' phase where the interface is first hidden from
  * userspace by i915_perf_unregister() before cleaning up
  * remaining state in i915_perf_fini().
  */
-void i915_perf_unregister(struct drm_i915_private *dev_priv)
+void i915_perf_unregister(struct drm_i915_private *i915)
 {
-	if (!dev_priv->perf.metrics_kobj)
+	struct i915_perf *perf = &i915->perf;
+
+	if (!perf->metrics_kobj)
 		return;
 
-	sysfs_remove_group(dev_priv->perf.metrics_kobj,
-			   &dev_priv->perf.test_config.sysfs_metric);
+	sysfs_remove_group(perf->metrics_kobj,
+			   &perf->test_config.sysfs_metric);
 
-	kobject_put(dev_priv->perf.metrics_kobj);
-	dev_priv->perf.metrics_kobj = NULL;
+	kobject_put(perf->metrics_kobj);
+	perf->metrics_kobj = NULL;
 }
 
-static bool gen8_is_valid_flex_addr(struct drm_i915_private *dev_priv, u32 addr)
+static bool gen8_is_valid_flex_addr(struct i915_perf *perf, u32 addr)
 {
 	static const i915_reg_t flex_eu_regs[] = {
 		EU_PERF_CNTL0,
@@ -3123,7 +3113,7 @@ static bool gen8_is_valid_flex_addr(struct drm_i915_private *dev_priv, u32 addr)
 	return false;
 }
 
-static bool gen7_is_valid_b_counter_addr(struct drm_i915_private *dev_priv, u32 addr)
+static bool gen7_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr)
 {
 	return (addr >= i915_mmio_reg_offset(OASTARTTRIG1) &&
 		addr <= i915_mmio_reg_offset(OASTARTTRIG8)) ||
@@ -3133,7 +3123,7 @@ static bool gen7_is_valid_b_counter_addr(struct drm_i915_private *dev_priv, u32
 		 addr <= i915_mmio_reg_offset(OACEC7_1));
 }
 
-static bool gen7_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
+static bool gen7_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
 	return addr == i915_mmio_reg_offset(HALF_SLICE_CHICKEN2) ||
 		(addr >= i915_mmio_reg_offset(MICRO_BP0_0) &&
@@ -3144,34 +3134,34 @@ static bool gen7_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
 		 addr <= i915_mmio_reg_offset(OA_PERFMATRIX_HI));
 }
 
-static bool gen8_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
+static bool gen8_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
-	return gen7_is_valid_mux_addr(dev_priv, addr) ||
+	return gen7_is_valid_mux_addr(perf, addr) ||
 		addr == i915_mmio_reg_offset(WAIT_FOR_RC6_EXIT) ||
 		(addr >= i915_mmio_reg_offset(RPM_CONFIG0) &&
 		 addr <= i915_mmio_reg_offset(NOA_CONFIG(8)));
 }
 
-static bool gen10_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
+static bool gen10_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
-	return gen8_is_valid_mux_addr(dev_priv, addr) ||
+	return gen8_is_valid_mux_addr(perf, addr) ||
 		addr == i915_mmio_reg_offset(GEN10_NOA_WRITE_HIGH) ||
 		(addr >= i915_mmio_reg_offset(OA_PERFCNT3_LO) &&
 		 addr <= i915_mmio_reg_offset(OA_PERFCNT4_HI));
 }
 
-static bool hsw_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
+static bool hsw_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
-	return gen7_is_valid_mux_addr(dev_priv, addr) ||
+	return gen7_is_valid_mux_addr(perf, addr) ||
 		(addr >= 0x25100 && addr <= 0x2FF90) ||
 		(addr >= i915_mmio_reg_offset(HSW_MBVID2_NOA0) &&
 		 addr <= i915_mmio_reg_offset(HSW_MBVID2_NOA9)) ||
 		addr == i915_mmio_reg_offset(HSW_MBVID2_MISR0);
 }
 
-static bool chv_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
+static bool chv_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
-	return gen7_is_valid_mux_addr(dev_priv, addr) ||
+	return gen7_is_valid_mux_addr(perf, addr) ||
 		(addr >= 0x182300 && addr <= 0x1823A4);
 }
 
@@ -3194,8 +3184,8 @@ static u32 mask_reg_value(u32 reg, u32 val)
 	return val;
 }
 
-static struct i915_oa_reg *alloc_oa_regs(struct drm_i915_private *dev_priv,
-					 bool (*is_valid)(struct drm_i915_private *dev_priv, u32 addr),
+static struct i915_oa_reg *alloc_oa_regs(struct i915_perf *perf,
+					 bool (*is_valid)(struct i915_perf *perf, u32 addr),
 					 u32 __user *regs,
 					 u32 n_regs)
 {
@@ -3225,7 +3215,7 @@ static struct i915_oa_reg *alloc_oa_regs(struct drm_i915_private *dev_priv,
 		if (err)
 			goto addr_err;
 
-		if (!is_valid(dev_priv, addr)) {
+		if (!is_valid(perf, addr)) {
 			DRM_DEBUG("Invalid oa_reg address: %X\n", addr);
 			err = -EINVAL;
 			goto addr_err;
@@ -3258,7 +3248,7 @@ static ssize_t show_dynamic_id(struct device *dev,
 	return sprintf(buf, "%d\n", oa_config->id);
 }
 
-static int create_dynamic_oa_sysfs_entry(struct drm_i915_private *dev_priv,
+static int create_dynamic_oa_sysfs_entry(struct i915_perf *perf,
 					 struct i915_oa_config *oa_config)
 {
 	sysfs_attr_init(&oa_config->sysfs_metric_id.attr);
@@ -3273,7 +3263,7 @@ static int create_dynamic_oa_sysfs_entry(struct drm_i915_private *dev_priv,
 	oa_config->sysfs_metric.name = oa_config->uuid;
 	oa_config->sysfs_metric.attrs = oa_config->attrs;
 
-	return sysfs_create_group(dev_priv->perf.metrics_kobj,
+	return sysfs_create_group(perf->metrics_kobj,
 				  &oa_config->sysfs_metric);
 }
 
@@ -3293,17 +3283,17 @@ static int create_dynamic_oa_sysfs_entry(struct drm_i915_private *dev_priv,
 int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_perf *perf = &to_i915(dev)->perf;
 	struct drm_i915_perf_oa_config *args = data;
 	struct i915_oa_config *oa_config, *tmp;
 	int err, id;
 
-	if (!dev_priv->perf.initialized) {
+	if (!perf->i915) {
 		DRM_DEBUG("i915 perf interface not available for this system\n");
 		return -ENOTSUPP;
 	}
 
-	if (!dev_priv->perf.metrics_kobj) {
+	if (!perf->metrics_kobj) {
 		DRM_DEBUG("OA metrics weren't advertised via sysfs\n");
 		return -EINVAL;
 	}
@@ -3341,8 +3331,8 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 
 	oa_config->mux_regs_len = args->n_mux_regs;
 	oa_config->mux_regs =
-		alloc_oa_regs(dev_priv,
-			      dev_priv->perf.ops.is_valid_mux_reg,
+		alloc_oa_regs(perf,
+			      perf->ops.is_valid_mux_reg,
 			      u64_to_user_ptr(args->mux_regs_ptr),
 			      args->n_mux_regs);
 
@@ -3354,8 +3344,8 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 
 	oa_config->b_counter_regs_len = args->n_boolean_regs;
 	oa_config->b_counter_regs =
-		alloc_oa_regs(dev_priv,
-			      dev_priv->perf.ops.is_valid_b_counter_reg,
+		alloc_oa_regs(perf,
+			      perf->ops.is_valid_b_counter_reg,
 			      u64_to_user_ptr(args->boolean_regs_ptr),
 			      args->n_boolean_regs);
 
@@ -3365,7 +3355,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 		goto reg_err;
 	}
 
-	if (INTEL_GEN(dev_priv) < 8) {
+	if (INTEL_GEN(perf->i915) < 8) {
 		if (args->n_flex_regs != 0) {
 			err = -EINVAL;
 			goto reg_err;
@@ -3373,8 +3363,8 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 	} else {
 		oa_config->flex_regs_len = args->n_flex_regs;
 		oa_config->flex_regs =
-			alloc_oa_regs(dev_priv,
-				      dev_priv->perf.ops.is_valid_flex_reg,
+			alloc_oa_regs(perf,
+				      perf->ops.is_valid_flex_reg,
 				      u64_to_user_ptr(args->flex_regs_ptr),
 				      args->n_flex_regs);
 
@@ -3385,14 +3375,14 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 		}
 	}
 
-	err = mutex_lock_interruptible(&dev_priv->perf.metrics_lock);
+	err = mutex_lock_interruptible(&perf->metrics_lock);
 	if (err)
 		goto reg_err;
 
 	/* We shouldn't have too many configs, so this iteration shouldn't be
 	 * too costly.
 	 */
-	idr_for_each_entry(&dev_priv->perf.metrics_idr, tmp, id) {
+	idr_for_each_entry(&perf->metrics_idr, tmp, id) {
 		if (!strcmp(tmp->uuid, oa_config->uuid)) {
 			DRM_DEBUG("OA config already exists with this uuid\n");
 			err = -EADDRINUSE;
@@ -3400,14 +3390,14 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 		}
 	}
 
-	err = create_dynamic_oa_sysfs_entry(dev_priv, oa_config);
+	err = create_dynamic_oa_sysfs_entry(perf, oa_config);
 	if (err) {
 		DRM_DEBUG("Failed to create sysfs entry for OA config\n");
 		goto sysfs_err;
 	}
 
 	/* Config id 0 is invalid, id 1 for kernel stored test config. */
-	oa_config->id = idr_alloc(&dev_priv->perf.metrics_idr,
+	oa_config->id = idr_alloc(&perf->metrics_idr,
 				  oa_config, 2,
 				  0, GFP_KERNEL);
 	if (oa_config->id < 0) {
@@ -3416,16 +3406,16 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 		goto sysfs_err;
 	}
 
-	mutex_unlock(&dev_priv->perf.metrics_lock);
+	mutex_unlock(&perf->metrics_lock);
 
 	DRM_DEBUG("Added config %s id=%i\n", oa_config->uuid, oa_config->id);
 
 	return oa_config->id;
 
 sysfs_err:
-	mutex_unlock(&dev_priv->perf.metrics_lock);
+	mutex_unlock(&perf->metrics_lock);
 reg_err:
-	put_oa_config(dev_priv, oa_config);
+	put_oa_config(oa_config);
 	DRM_DEBUG("Failed to add new OA config\n");
 	return err;
 }
@@ -3444,12 +3434,12 @@ reg_err:
 int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct i915_perf *perf = &to_i915(dev)->perf;
 	u64 *arg = data;
 	struct i915_oa_config *oa_config;
 	int ret;
 
-	if (!dev_priv->perf.initialized) {
+	if (!perf->i915) {
 		DRM_DEBUG("i915 perf interface not available for this system\n");
 		return -ENOTSUPP;
 	}
@@ -3459,11 +3449,11 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 		return -EACCES;
 	}
 
-	ret = mutex_lock_interruptible(&dev_priv->perf.metrics_lock);
+	ret = mutex_lock_interruptible(&perf->metrics_lock);
 	if (ret)
 		goto lock_err;
 
-	oa_config = idr_find(&dev_priv->perf.metrics_idr, *arg);
+	oa_config = idr_find(&perf->metrics_idr, *arg);
 	if (!oa_config) {
 		DRM_DEBUG("Failed to remove unknown OA config\n");
 		ret = -ENOENT;
@@ -3472,17 +3462,17 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 
 	GEM_BUG_ON(*arg != oa_config->id);
 
-	sysfs_remove_group(dev_priv->perf.metrics_kobj,
+	sysfs_remove_group(perf->metrics_kobj,
 			   &oa_config->sysfs_metric);
 
-	idr_remove(&dev_priv->perf.metrics_idr, *arg);
+	idr_remove(&perf->metrics_idr, *arg);
 
 	DRM_DEBUG("Removed config %s id=%i\n", oa_config->uuid, oa_config->id);
 
-	put_oa_config(dev_priv, oa_config);
+	put_oa_config(oa_config);
 
 config_err:
-	mutex_unlock(&dev_priv->perf.metrics_lock);
+	mutex_unlock(&perf->metrics_lock);
 lock_err:
 	return ret;
 }
@@ -3531,103 +3521,104 @@ static struct ctl_table dev_root[] = {
 
 /**
  * i915_perf_init - initialize i915-perf state on module load
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * Initializes i915-perf state without exposing anything to userspace.
  *
  * Note: i915-perf initialization is split into an 'init' and 'register'
  * phase with the i915_perf_register() exposing state to userspace.
  */
-void i915_perf_init(struct drm_i915_private *dev_priv)
-{
-	if (IS_HASWELL(dev_priv)) {
-		dev_priv->perf.ops.is_valid_b_counter_reg =
-			gen7_is_valid_b_counter_addr;
-		dev_priv->perf.ops.is_valid_mux_reg =
-			hsw_is_valid_mux_addr;
-		dev_priv->perf.ops.is_valid_flex_reg = NULL;
-		dev_priv->perf.ops.enable_metric_set = hsw_enable_metric_set;
-		dev_priv->perf.ops.disable_metric_set = hsw_disable_metric_set;
-		dev_priv->perf.ops.oa_enable = gen7_oa_enable;
-		dev_priv->perf.ops.oa_disable = gen7_oa_disable;
-		dev_priv->perf.ops.read = gen7_oa_read;
-		dev_priv->perf.ops.oa_hw_tail_read =
-			gen7_oa_hw_tail_read;
-
-		dev_priv->perf.oa_formats = hsw_oa_formats;
-	} else if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
+void i915_perf_init(struct drm_i915_private *i915)
+{
+	struct i915_perf *perf = &i915->perf;
+
+	/* XXX const struct i915_perf_ops! */
+
+	if (IS_HASWELL(i915)) {
+		perf->ops.is_valid_b_counter_reg = gen7_is_valid_b_counter_addr;
+		perf->ops.is_valid_mux_reg = hsw_is_valid_mux_addr;
+		perf->ops.is_valid_flex_reg = NULL;
+		perf->ops.enable_metric_set = hsw_enable_metric_set;
+		perf->ops.disable_metric_set = hsw_disable_metric_set;
+		perf->ops.oa_enable = gen7_oa_enable;
+		perf->ops.oa_disable = gen7_oa_disable;
+		perf->ops.read = gen7_oa_read;
+		perf->ops.oa_hw_tail_read = gen7_oa_hw_tail_read;
+
+		perf->oa_formats = hsw_oa_formats;
+	} else if (HAS_LOGICAL_RING_CONTEXTS(i915)) {
 		/* Note: that although we could theoretically also support the
 		 * legacy ringbuffer mode on BDW (and earlier iterations of
 		 * this driver, before upstreaming did this) it didn't seem
 		 * worth the complexity to maintain now that BDW+ enable
 		 * execlist mode by default.
 		 */
-		dev_priv->perf.oa_formats = gen8_plus_oa_formats;
+		perf->oa_formats = gen8_plus_oa_formats;
 
-		dev_priv->perf.ops.oa_enable = gen8_oa_enable;
-		dev_priv->perf.ops.oa_disable = gen8_oa_disable;
-		dev_priv->perf.ops.read = gen8_oa_read;
-		dev_priv->perf.ops.oa_hw_tail_read = gen8_oa_hw_tail_read;
+		perf->ops.oa_enable = gen8_oa_enable;
+		perf->ops.oa_disable = gen8_oa_disable;
+		perf->ops.read = gen8_oa_read;
+		perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read;
 
-		if (IS_GEN_RANGE(dev_priv, 8, 9)) {
-			dev_priv->perf.ops.is_valid_b_counter_reg =
+		if (IS_GEN_RANGE(i915, 8, 9)) {
+			perf->ops.is_valid_b_counter_reg =
 				gen7_is_valid_b_counter_addr;
-			dev_priv->perf.ops.is_valid_mux_reg =
+			perf->ops.is_valid_mux_reg =
 				gen8_is_valid_mux_addr;
-			dev_priv->perf.ops.is_valid_flex_reg =
+			perf->ops.is_valid_flex_reg =
 				gen8_is_valid_flex_addr;
 
-			if (IS_CHERRYVIEW(dev_priv)) {
-				dev_priv->perf.ops.is_valid_mux_reg =
+			if (IS_CHERRYVIEW(i915)) {
+				perf->ops.is_valid_mux_reg =
 					chv_is_valid_mux_addr;
 			}
 
-			dev_priv->perf.ops.enable_metric_set = gen8_enable_metric_set;
-			dev_priv->perf.ops.disable_metric_set = gen8_disable_metric_set;
+			perf->ops.enable_metric_set = gen8_enable_metric_set;
+			perf->ops.disable_metric_set = gen8_disable_metric_set;
 
-			if (IS_GEN(dev_priv, 8)) {
-				dev_priv->perf.ctx_oactxctrl_offset = 0x120;
-				dev_priv->perf.ctx_flexeu0_offset = 0x2ce;
+			if (IS_GEN(i915, 8)) {
+				perf->ctx_oactxctrl_offset = 0x120;
+				perf->ctx_flexeu0_offset = 0x2ce;
 
-				dev_priv->perf.gen8_valid_ctx_bit = BIT(25);
+				perf->gen8_valid_ctx_bit = BIT(25);
 			} else {
-				dev_priv->perf.ctx_oactxctrl_offset = 0x128;
-				dev_priv->perf.ctx_flexeu0_offset = 0x3de;
+				perf->ctx_oactxctrl_offset = 0x128;
+				perf->ctx_flexeu0_offset = 0x3de;
 
-				dev_priv->perf.gen8_valid_ctx_bit = BIT(16);
+				perf->gen8_valid_ctx_bit = BIT(16);
 			}
-		} else if (IS_GEN_RANGE(dev_priv, 10, 11)) {
-			dev_priv->perf.ops.is_valid_b_counter_reg =
+		} else if (IS_GEN_RANGE(i915, 10, 11)) {
+			perf->ops.is_valid_b_counter_reg =
 				gen7_is_valid_b_counter_addr;
-			dev_priv->perf.ops.is_valid_mux_reg =
+			perf->ops.is_valid_mux_reg =
 				gen10_is_valid_mux_addr;
-			dev_priv->perf.ops.is_valid_flex_reg =
+			perf->ops.is_valid_flex_reg =
 				gen8_is_valid_flex_addr;
 
-			dev_priv->perf.ops.enable_metric_set = gen8_enable_metric_set;
-			dev_priv->perf.ops.disable_metric_set = gen10_disable_metric_set;
+			perf->ops.enable_metric_set = gen8_enable_metric_set;
+			perf->ops.disable_metric_set = gen10_disable_metric_set;
 
-			if (IS_GEN(dev_priv, 10)) {
-				dev_priv->perf.ctx_oactxctrl_offset = 0x128;
-				dev_priv->perf.ctx_flexeu0_offset = 0x3de;
+			if (IS_GEN(i915, 10)) {
+				perf->ctx_oactxctrl_offset = 0x128;
+				perf->ctx_flexeu0_offset = 0x3de;
 			} else {
-				dev_priv->perf.ctx_oactxctrl_offset = 0x124;
-				dev_priv->perf.ctx_flexeu0_offset = 0x78e;
+				perf->ctx_oactxctrl_offset = 0x124;
+				perf->ctx_flexeu0_offset = 0x78e;
 			}
-			dev_priv->perf.gen8_valid_ctx_bit = BIT(16);
+			perf->gen8_valid_ctx_bit = BIT(16);
 		}
 	}
 
-	if (dev_priv->perf.ops.enable_metric_set) {
-		INIT_LIST_HEAD(&dev_priv->perf.streams);
-		mutex_init(&dev_priv->perf.lock);
+	if (perf->ops.enable_metric_set) {
+		INIT_LIST_HEAD(&perf->streams);
+		mutex_init(&perf->lock);
 
 		oa_sample_rate_hard_limit = 1000 *
-			(RUNTIME_INFO(dev_priv)->cs_timestamp_frequency_khz / 2);
-		dev_priv->perf.sysctl_header = register_sysctl_table(dev_root);
+			(RUNTIME_INFO(i915)->cs_timestamp_frequency_khz / 2);
+		perf->sysctl_header = register_sysctl_table(dev_root);
 
-		mutex_init(&dev_priv->perf.metrics_lock);
-		idr_init(&dev_priv->perf.metrics_idr);
+		mutex_init(&perf->metrics_lock);
+		idr_init(&perf->metrics_idr);
 
 		/* We set up some ratelimit state to potentially throttle any
 		 * _NOTES about spurious, invalid OA reports which we don't
@@ -3639,44 +3630,40 @@ void i915_perf_init(struct drm_i915_private *dev_priv)
 		 *
 		 * Using the same limiting factors as printk_ratelimit()
 		 */
-		ratelimit_state_init(&dev_priv->perf.spurious_report_rs,
-				     5 * HZ, 10);
+		ratelimit_state_init(&perf->spurious_report_rs, 5 * HZ, 10);
 		/* Since we use a DRM_NOTE for spurious reports it would be
 		 * inconsistent to let __ratelimit() automatically print a
 		 * warning for throttling.
 		 */
-		ratelimit_set_flags(&dev_priv->perf.spurious_report_rs,
+		ratelimit_set_flags(&perf->spurious_report_rs,
 				    RATELIMIT_MSG_ON_RELEASE);
 
-		dev_priv->perf.initialized = true;
+		perf->i915 = i915;
 	}
 }
 
 static int destroy_config(int id, void *p, void *data)
 {
-	struct drm_i915_private *dev_priv = data;
-	struct i915_oa_config *oa_config = p;
-
-	put_oa_config(dev_priv, oa_config);
-
+	put_oa_config(p);
 	return 0;
 }
 
 /**
  * i915_perf_fini - Counter part to i915_perf_init()
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  */
-void i915_perf_fini(struct drm_i915_private *dev_priv)
+void i915_perf_fini(struct drm_i915_private *i915)
 {
-	if (!dev_priv->perf.initialized)
-		return;
+	struct i915_perf *perf = &i915->perf;
 
-	idr_for_each(&dev_priv->perf.metrics_idr, destroy_config, dev_priv);
-	idr_destroy(&dev_priv->perf.metrics_idr);
+	if (!perf->i915)
+		return;
 
-	unregister_sysctl_table(dev_priv->perf.sysctl_header);
+	idr_for_each(&perf->metrics_idr, destroy_config, perf);
+	idr_destroy(&perf->metrics_idr);
 
-	memset(&dev_priv->perf.ops, 0, sizeof(dev_priv->perf.ops));
+	unregister_sysctl_table(perf->sysctl_header);
 
-	dev_priv->perf.initialized = false;
+	memset(&perf->ops, 0, sizeof(perf->ops));
+	perf->i915 = NULL;
 }
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index edcab2df74fb..3c6246064a0b 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -12,6 +12,7 @@
 #include <linux/list.h>
 #include <linux/poll.h>
 #include <linux/sysfs.h>
+#include <linux/types.h>
 #include <linux/uuid.h>
 #include <linux/wait.h>
 
@@ -124,9 +125,14 @@ struct i915_perf_stream_ops {
  */
 struct i915_perf_stream {
 	/**
-	 * @dev_priv: i915 drm device
+	 * @perf: i915_perf backpointer
 	 */
-	struct drm_i915_private *dev_priv;
+	struct i915_perf *perf;
+
+	/**
+	 * @gt: intel_gt container
+	 */
+	struct intel_gt *gt;
 
 	/**
 	 * @link: Links the stream into ``&drm_i915_private->streams``
@@ -266,20 +272,19 @@ struct i915_oa_ops {
 	 * @is_valid_b_counter_reg: Validates register's address for
 	 * programming boolean counters for a particular platform.
 	 */
-	bool (*is_valid_b_counter_reg)(struct drm_i915_private *dev_priv,
-				       u32 addr);
+	bool (*is_valid_b_counter_reg)(struct i915_perf *perf, u32 addr);
 
 	/**
 	 * @is_valid_mux_reg: Validates register's address for programming mux
 	 * for a particular platform.
 	 */
-	bool (*is_valid_mux_reg)(struct drm_i915_private *dev_priv, u32 addr);
+	bool (*is_valid_mux_reg)(struct i915_perf *perf, u32 addr);
 
 	/**
 	 * @is_valid_flex_reg: Validates register's address for programming
 	 * flex EU filtering for a particular platform.
 	 */
-	bool (*is_valid_flex_reg)(struct drm_i915_private *dev_priv, u32 addr);
+	bool (*is_valid_flex_reg)(struct i915_perf *perf, u32 addr);
 
 	/**
 	 * @enable_metric_set: Selects and applies any MUX configuration to set
@@ -324,4 +329,60 @@ struct i915_oa_ops {
 	u32 (*oa_hw_tail_read)(struct i915_perf_stream *stream);
 };
 
+struct i915_perf {
+	struct drm_i915_private *i915;
+
+	struct kobject *metrics_kobj;
+	struct ctl_table_header *sysctl_header;
+
+	/*
+	 * Lock associated with adding/modifying/removing OA configs
+	 * in dev_priv->perf.metrics_idr.
+	 */
+	struct mutex metrics_lock;
+
+	/*
+	 * List of dynamic configurations, you need to hold
+	 * dev_priv->perf.metrics_lock to access it.
+	 */
+	struct idr metrics_idr;
+
+	/*
+	 * Lock associated with anything below within this structure
+	 * except exclusive_stream.
+	 */
+	struct mutex lock;
+	struct list_head streams;
+
+	/*
+	 * The stream currently using the OA unit. If accessed
+	 * outside a syscall associated to its file
+	 * descriptor, you need to hold
+	 * dev_priv->drm.struct_mutex.
+	 */
+	struct i915_perf_stream *exclusive_stream;
+
+	/**
+	 * For rate limiting any notifications of spurious
+	 * invalid OA reports
+	 */
+	struct ratelimit_state spurious_report_rs;
+
+	struct i915_oa_config test_config;
+
+	u32 gen7_latched_oastatus1;
+	u32 ctx_oactxctrl_offset;
+	u32 ctx_flexeu0_offset;
+
+	/**
+	 * The RPT_ID/reason field for Gen8+ includes a bit
+	 * to determine if the CTX ID in the report is valid
+	 * but the specific bit differs between Gen 8 and 9
+	 */
+	u32 gen8_valid_ctx_bit;
+
+	struct i915_oa_ops ops;
+	const struct i915_oa_format *oa_formats;
+};
+
 #endif /* _I915_PERF_TYPES_H_ */
-- 
cgit v1.2.3


From a4c969d107a66369e6b8bf6b2fa28ca01723133b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 7 Oct 2019 22:09:42 +0100
Subject: drm/i915/perf: Set the exclusive stream under perf->lock

The BKL struct_mutex is no more, the only serialisation we required for
setting the exclusive stream is already managed by ce->pin_mutex in
gen8_configure_all_contexts(). As such, we can manipulate
i915_perf.exclusive_stream underneath our own (already held) perf->lock.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191007140812.10963-2-chris@chris-wilson.co.uk
Link: https://patchwork.freedesktop.org/patch/msgid/20191007210942.18145-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_perf.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 5a25bbeb6c7a..e5973809b69a 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1343,10 +1343,8 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 	 * Unset exclusive_stream first, it will be checked while disabling
 	 * the metric set on gen8+.
 	 */
-	mutex_lock(&perf->i915->drm.struct_mutex);
 	perf->exclusive_stream = NULL;
 	perf->ops.disable_metric_set(stream);
-	mutex_unlock(&perf->i915->drm.struct_mutex);
 
 	free_oa_buffer(stream);
 
@@ -1853,7 +1851,7 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 	for (i = 2; i < ARRAY_SIZE(regs); i++)
 		regs[i].value = oa_config_flex_reg(oa_config, regs[i].reg);
 
-	lockdep_assert_held(&i915->drm.struct_mutex);
+	lockdep_assert_held(&stream->perf->lock);
 
 	/*
 	 * The OA register config is setup through the context image. This image
@@ -2220,10 +2218,6 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	if (ret)
 		goto err_oa_buf_alloc;
 
-	ret = i915_mutex_lock_interruptible(&stream->perf->i915->drm);
-	if (ret)
-		goto err_lock;
-
 	stream->ops = &i915_oa_stream_ops;
 	perf->exclusive_stream = stream;
 
@@ -2233,8 +2227,6 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		goto err_enable;
 	}
 
-	mutex_unlock(&stream->perf->i915->drm.struct_mutex);
-
 	hrtimer_init(&stream->poll_check_timer,
 		     CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	stream->poll_check_timer.function = oa_poll_check_timer_cb;
@@ -2246,9 +2238,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 err_enable:
 	perf->exclusive_stream = NULL;
 	perf->ops.disable_metric_set(stream);
-	mutex_unlock(&stream->perf->i915->drm.struct_mutex);
 
-err_lock:
 	free_oa_buffer(stream);
 
 err_oa_buf_alloc:
-- 
cgit v1.2.3


From e45e0003f60d3e9d62d9bb42d72efbbada7132bc Mon Sep 17 00:00:00 2001
From: Anshuman Gupta <anshuman.gupta@intel.com>
Date: Mon, 7 Oct 2019 15:16:07 +0530
Subject: drm/i915/tgl: Add DC3CO required register and bits

Adding following definition to i915_reg.h
1. DC_STATE_EN register DC3CO bit fields and masks.
   DC3CO enable bit will be used by driver to make DC3CO
   ready for DMC f/w and status bit will be used as DC3CO
   entry status.
2. Transcoder EXITLINE register and its bit fields and mask.
   Transcoder EXITLINE enable bit represents PSR2 idle frame
   reset should be applied at exit line and exitlines mask
   represent required number of scanlines at which DC3CO
   exit happens.

   B.Specs:49196

v1: Use of REG_BIT and using extra space for EXITLINE_ macro
    definition. [Animesh]
v2: Grouping EXITLINE reg bits with EXITLINE(trans) define,
    no functional change. [Ville]

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Animesh Manna <animesh.manna@intel.com>
Reviewed-by: Animesh Manna <animesh.manna@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191007094607.2111-1-anshuman.gupta@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6d67bd238cfe..d252ee7803cc 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4145,6 +4145,7 @@ enum {
 #define _VTOTAL_A	0x6000c
 #define _VBLANK_A	0x60010
 #define _VSYNC_A	0x60014
+#define _EXITLINE_A	0x60018
 #define _PIPEASRC	0x6001c
 #define _BCLRPAT_A	0x60020
 #define _VSYNCSHIFT_A	0x60028
@@ -4196,6 +4197,11 @@ enum {
 #define PIPESRC(trans)		_MMIO_TRANS2(trans, _PIPEASRC)
 #define PIPE_MULT(trans)	_MMIO_TRANS2(trans, _PIPE_MULT_A)
 
+#define EXITLINE(trans)		_MMIO_TRANS2(trans, _EXITLINE_A)
+#define   EXITLINE_ENABLE	REG_BIT(31)
+#define   EXITLINE_MASK		REG_GENMASK(12, 0)
+#define   EXITLINE_SHIFT	0
+
 /*
  * HSW+ eDP PSR registers
  *
@@ -10291,6 +10297,8 @@ enum skl_power_gate {
 /* GEN9 DC */
 #define DC_STATE_EN			_MMIO(0x45504)
 #define  DC_STATE_DISABLE		0
+#define  DC_STATE_EN_DC3CO		REG_BIT(30)
+#define  DC_STATE_DC3CO_STATUS		REG_BIT(29)
 #define  DC_STATE_EN_UPTO_DC5		(1 << 0)
 #define  DC_STATE_EN_DC9		(1 << 3)
 #define  DC_STATE_EN_UPTO_DC6		(2 << 0)
-- 
cgit v1.2.3


From 19c79ff82b4ad95c6ce1a101dc238a643cea3835 Mon Sep 17 00:00:00 2001
From: Anshuman Gupta <anshuman.gupta@intel.com>
Date: Thu, 3 Oct 2019 13:47:34 +0530
Subject: drm/i915/tgl: Add DC3CO mask to allowed_dc_mask and gen9_dc_mask

Enable dc3co state in enable_dc module param and add dc3co
enable mask to allowed_dc_mask and gen9_dc_mask.

v1: Adding enable_dc=3,4 options to enable DC3CO with DC5 and DC6
    independently. [Animesh]
v2: Using a switch statement for cleaner code. [Animesh]

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Animesh Manna <animesh.manna@intel.com>
Reviewed-by: Animesh Manna <animesh.manna@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191003081738.22101-3-anshuman.gupta@intel.com
---
 drivers/gpu/drm/i915/display/intel_display_power.c | 29 +++++++++++++++++-----
 drivers/gpu/drm/i915/i915_params.c                 |  3 ++-
 2 files changed, 25 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 0616284c6da6..c00cf061fab4 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -695,7 +695,11 @@ static u32 gen9_dc_mask(struct drm_i915_private *dev_priv)
 	u32 mask;
 
 	mask = DC_STATE_EN_UPTO_DC5;
-	if (INTEL_GEN(dev_priv) >= 11)
+
+	if (INTEL_GEN(dev_priv) >= 12)
+		mask |= DC_STATE_EN_DC3CO | DC_STATE_EN_UPTO_DC6
+					  | DC_STATE_EN_DC9;
+	else if (IS_GEN(dev_priv, 11))
 		mask |= DC_STATE_EN_UPTO_DC6 | DC_STATE_EN_DC9;
 	else if (IS_GEN9_LP(dev_priv))
 		mask |= DC_STATE_EN_DC9;
@@ -3924,14 +3928,17 @@ static u32 get_allowed_dc_mask(const struct drm_i915_private *dev_priv,
 	int requested_dc;
 	int max_dc;
 
-	if (INTEL_GEN(dev_priv) >= 11) {
-		max_dc = 2;
+	if (INTEL_GEN(dev_priv) >= 12) {
+		max_dc = 4;
 		/*
 		 * DC9 has a separate HW flow from the rest of the DC states,
 		 * not depending on the DMC firmware. It's needed by system
 		 * suspend/resume, so allow it unconditionally.
 		 */
 		mask = DC_STATE_EN_DC9;
+	} else if (IS_GEN(dev_priv, 11)) {
+		max_dc = 2;
+		mask = DC_STATE_EN_DC9;
 	} else if (IS_GEN(dev_priv, 10) || IS_GEN9_BC(dev_priv)) {
 		max_dc = 2;
 		mask = 0;
@@ -3950,7 +3957,7 @@ static u32 get_allowed_dc_mask(const struct drm_i915_private *dev_priv,
 		requested_dc = enable_dc;
 	} else if (enable_dc == -1) {
 		requested_dc = max_dc;
-	} else if (enable_dc > max_dc && enable_dc <= 2) {
+	} else if (enable_dc > max_dc && enable_dc <= 4) {
 		DRM_DEBUG_KMS("Adjusting requested max DC state (%d->%d)\n",
 			      enable_dc, max_dc);
 		requested_dc = max_dc;
@@ -3959,10 +3966,20 @@ static u32 get_allowed_dc_mask(const struct drm_i915_private *dev_priv,
 		requested_dc = max_dc;
 	}
 
-	if (requested_dc > 1)
+	switch (requested_dc) {
+	case 4:
+		mask |= DC_STATE_EN_DC3CO | DC_STATE_EN_UPTO_DC6;
+		break;
+	case 3:
+		mask |= DC_STATE_EN_DC3CO | DC_STATE_EN_UPTO_DC5;
+		break;
+	case 2:
 		mask |= DC_STATE_EN_UPTO_DC6;
-	if (requested_dc > 0)
+		break;
+	case 1:
 		mask |= DC_STATE_EN_UPTO_DC5;
+		break;
+	}
 
 	DRM_DEBUG_KMS("Allowed DC state mask %02x\n", mask);
 
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 296452f9efe4..4f1806f65040 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -46,7 +46,8 @@ i915_param_named(modeset, int, 0400,
 
 i915_param_named_unsafe(enable_dc, int, 0400,
 	"Enable power-saving display C-states. "
-	"(-1=auto [default]; 0=disable; 1=up to DC5; 2=up to DC6)");
+	"(-1=auto [default]; 0=disable; 1=up to DC5; 2=up to DC6; "
+	"3=up to DC5 with DC3CO; 4=up to DC6 with DC3CO)");
 
 i915_param_named_unsafe(enable_fbc, int, 0600,
 	"Enable frame buffer compression for power savings "
-- 
cgit v1.2.3


From 4645e906f2d40ff4000c78373bb932f713259611 Mon Sep 17 00:00:00 2001
From: Anshuman Gupta <anshuman.gupta@intel.com>
Date: Thu, 3 Oct 2019 13:47:35 +0530
Subject: drm/i915/tgl: Enable DC3CO state in "DC Off" power well

Add target_dc_state and used by set_target_dc_state API
in order to enable DC3CO state with existing DC states.
target_dc_state will enable/disable the desired DC state in
DC_STATE_EN reg when "DC Off" power well gets disable/enable.

v2: commit log improvement.
v3: Used intel_wait_for_register to wait for DC3CO exit. [Imre]
    Used gen9_set_dc_state() to allow/disallow DC3CO. [Imre]
    Moved transcoder psr2 exit line enablement from tgl_allow_dc3co()
    to a appropriate place haswell_crtc_enable(). [Imre]
    Changed the DC3CO power well enabled call back logic as
    recommended in review comments. [Imre]
v4: Used wait_for_us() instead of intel_wait_for_reg(). [Imre (IRC)]
v5: using udelay() instead of waiting for DC3CO exit status.
v6: Fixed minor unwanted change.
v7: Removed DC3CO powerwell and POWER_DOMAIN_VIDEO.
v8: Uniform checks by using only target_dc_state instead of allowed_dc_mask
    in "DC off" power well callback. [Imre]
    Adding "DC off" power well id to older platforms. [Imre]
    Removed psr2_deep_sleep flag from tgl_set_target_dc_state. [Imre]
v9: Used switch case for target DC state in
    gen9_dc_off_power_well_disable(), checking DC3CO state against
    allowed DC mask, using WARN_ON() in
    tgl_set_target_dc_state(). [Imre]
v10: Code refactoring and using sanitize_target_dc_state(). [Imre]

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Animesh Manna <animesh.manna@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191003081738.22101-4-anshuman.gupta@intel.com
---
 drivers/gpu/drm/i915/display/intel_display_power.c | 80 +++++++++++++++++++---
 drivers/gpu/drm/i915/display/intel_display_power.h |  1 +
 drivers/gpu/drm/i915/i915_drv.h                    |  1 +
 3 files changed, 73 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index c00cf061fab4..812081f5232f 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -769,6 +769,52 @@ static void gen9_set_dc_state(struct drm_i915_private *dev_priv, u32 state)
 	dev_priv->csr.dc_state = val & mask;
 }
 
+static u32
+sanitize_target_dc_state(struct drm_i915_private *dev_priv,
+			 u32 target_dc_state)
+{
+	u32 states[] = {
+		DC_STATE_EN_UPTO_DC6,
+		DC_STATE_EN_UPTO_DC5,
+		DC_STATE_EN_DC3CO,
+		DC_STATE_DISABLE,
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(states) - 1; i++) {
+		if (target_dc_state != states[i])
+			continue;
+
+		if (dev_priv->csr.allowed_dc_mask & target_dc_state)
+			break;
+
+		target_dc_state = states[i + 1];
+	}
+
+	return target_dc_state;
+}
+
+static void tgl_enable_dc3co(struct drm_i915_private *dev_priv)
+{
+	DRM_DEBUG_KMS("Enabling DC3CO\n");
+	gen9_set_dc_state(dev_priv, DC_STATE_EN_DC3CO);
+}
+
+static void tgl_disable_dc3co(struct drm_i915_private *dev_priv)
+{
+	u32 val;
+
+	DRM_DEBUG_KMS("Disabling DC3CO\n");
+	val = I915_READ(DC_STATE_EN);
+	val &= ~DC_STATE_DC3CO_STATUS;
+	I915_WRITE(DC_STATE_EN, val);
+	gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
+	/*
+	 * Delay of 200us DC3CO Exit time B.Spec 49196
+	 */
+	usleep_range(200, 210);
+}
+
 static void bxt_enable_dc9(struct drm_i915_private *dev_priv)
 {
 	assert_can_enable_dc9(dev_priv);
@@ -936,7 +982,8 @@ static void bxt_verify_ddi_phy_power_wells(struct drm_i915_private *dev_priv)
 static bool gen9_dc_off_power_well_enabled(struct drm_i915_private *dev_priv,
 					   struct i915_power_well *power_well)
 {
-	return (I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC5_DC6_MASK) == 0;
+	return ((I915_READ(DC_STATE_EN) & DC_STATE_EN_DC3CO) == 0 &&
+		(I915_READ(DC_STATE_EN) & DC_STATE_EN_UPTO_DC5_DC6_MASK) == 0);
 }
 
 static void gen9_assert_dbuf_enabled(struct drm_i915_private *dev_priv)
@@ -952,6 +999,11 @@ static void gen9_disable_dc_states(struct drm_i915_private *dev_priv)
 {
 	struct intel_cdclk_state cdclk_state = {};
 
+	if (dev_priv->csr.target_dc_state == DC_STATE_EN_DC3CO) {
+		tgl_disable_dc3co(dev_priv);
+		return;
+	}
+
 	gen9_set_dc_state(dev_priv, DC_STATE_DISABLE);
 
 	dev_priv->display.get_cdclk(dev_priv, &cdclk_state);
@@ -984,10 +1036,17 @@ static void gen9_dc_off_power_well_disable(struct drm_i915_private *dev_priv,
 	if (!dev_priv->csr.dmc_payload)
 		return;
 
-	if (dev_priv->csr.allowed_dc_mask & DC_STATE_EN_UPTO_DC6)
+	switch (dev_priv->csr.target_dc_state) {
+	case DC_STATE_EN_DC3CO:
+		tgl_enable_dc3co(dev_priv);
+		break;
+	case DC_STATE_EN_UPTO_DC6:
 		skl_enable_dc6(dev_priv);
-	else if (dev_priv->csr.allowed_dc_mask & DC_STATE_EN_UPTO_DC5)
+		break;
+	case DC_STATE_EN_UPTO_DC5:
 		gen9_enable_dc5(dev_priv);
+		break;
+	}
 }
 
 static void i9xx_power_well_sync_hw_noop(struct drm_i915_private *dev_priv,
@@ -2935,7 +2994,7 @@ static const struct i915_power_well_desc skl_power_wells[] = {
 		.name = "DC off",
 		.domains = SKL_DISPLAY_DC_OFF_POWER_DOMAINS,
 		.ops = &gen9_dc_off_power_well_ops,
-		.id = DISP_PW_ID_NONE,
+		.id = SKL_DISP_DC_OFF,
 	},
 	{
 		.name = "power well 2",
@@ -3017,7 +3076,7 @@ static const struct i915_power_well_desc bxt_power_wells[] = {
 		.name = "DC off",
 		.domains = BXT_DISPLAY_DC_OFF_POWER_DOMAINS,
 		.ops = &gen9_dc_off_power_well_ops,
-		.id = DISP_PW_ID_NONE,
+		.id = SKL_DISP_DC_OFF,
 	},
 	{
 		.name = "power well 2",
@@ -3077,7 +3136,7 @@ static const struct i915_power_well_desc glk_power_wells[] = {
 		.name = "DC off",
 		.domains = GLK_DISPLAY_DC_OFF_POWER_DOMAINS,
 		.ops = &gen9_dc_off_power_well_ops,
-		.id = DISP_PW_ID_NONE,
+		.id = SKL_DISP_DC_OFF,
 	},
 	{
 		.name = "power well 2",
@@ -3246,7 +3305,7 @@ static const struct i915_power_well_desc cnl_power_wells[] = {
 		.name = "DC off",
 		.domains = CNL_DISPLAY_DC_OFF_POWER_DOMAINS,
 		.ops = &gen9_dc_off_power_well_ops,
-		.id = DISP_PW_ID_NONE,
+		.id = SKL_DISP_DC_OFF,
 	},
 	{
 		.name = "power well 2",
@@ -3374,7 +3433,7 @@ static const struct i915_power_well_desc icl_power_wells[] = {
 		.name = "DC off",
 		.domains = ICL_DISPLAY_DC_OFF_POWER_DOMAINS,
 		.ops = &gen9_dc_off_power_well_ops,
-		.id = DISP_PW_ID_NONE,
+		.id = SKL_DISP_DC_OFF,
 	},
 	{
 		.name = "power well 2",
@@ -3607,7 +3666,7 @@ static const struct i915_power_well_desc tgl_power_wells[] = {
 		.name = "DC off",
 		.domains = TGL_DISPLAY_DC_OFF_POWER_DOMAINS,
 		.ops = &gen9_dc_off_power_well_ops,
-		.id = DISP_PW_ID_NONE,
+		.id = SKL_DISP_DC_OFF,
 	},
 	{
 		.name = "power well 2",
@@ -4040,6 +4099,9 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 	dev_priv->csr.allowed_dc_mask =
 		get_allowed_dc_mask(dev_priv, i915_modparams.enable_dc);
 
+	dev_priv->csr.target_dc_state =
+		sanitize_target_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6);
+
 	BUILD_BUG_ON(POWER_DOMAIN_NUM > 64);
 
 	mutex_init(&power_domains->lock);
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.h b/drivers/gpu/drm/i915/display/intel_display_power.h
index 737b5def7fc6..7d72faf474b2 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.h
+++ b/drivers/gpu/drm/i915/display/intel_display_power.h
@@ -100,6 +100,7 @@ enum i915_power_well_id {
 	SKL_DISP_PW_MISC_IO,
 	SKL_DISP_PW_1,
 	SKL_DISP_PW_2,
+	SKL_DISP_DC_OFF,
 };
 
 #define POWER_DOMAIN_PIPE(pipe) ((pipe) + POWER_DOMAIN_PIPE_A)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index dd0eb8dc4491..887ea4a4d687 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -339,6 +339,7 @@ struct intel_csr {
 	i915_reg_t mmioaddr[20];
 	u32 mmiodata[20];
 	u32 dc_state;
+	u32 target_dc_state;
 	u32 allowed_dc_mask;
 	intel_wakeref_t wakeref;
 };
-- 
cgit v1.2.3


From bdacf0871f8771c2763b53efb9f9aa9bdea7b570 Mon Sep 17 00:00:00 2001
From: Anshuman Gupta <anshuman.gupta@intel.com>
Date: Thu, 3 Oct 2019 13:47:36 +0530
Subject: drm/i915/tgl: Do modeset to enable and configure DC3CO exitline

DC3CO enabling B.Specs sequence requires to enable end configure
exit scanlines to TRANS_EXITLINE register, programming this register
has to be part of modeset sequence as this can't be change when
transcoder or port is enabled.
When system boots with only eDP panel there may not be real
modeset as BIOS has already programmed the necessary registers,
therefore it needs to force a modeset to enable and configure
DC3CO exitline.

v1: Computing dc3co_exitline crtc state from a DP encoder
    compute config. [Imre]
    Enabling and disabling DC3CO PSR2 transcoder exitline from
    encoder pre_enable and post_disable hooks. [Imre]
    Computing dc3co_exitline instead of has_dc3co_exitline bool. [Imre]
v2: Code refactoring for symmetry and to avoid exported function. [Imre]
    Removing IS_TIGERLAKE check from compute_config, adding PIPE_A
    restriction and clearing dc3co_exitline state if crtc is not active
    or it is not PSR2 capable in dc3co exitline compute_config. [Imre]
    Using GEN >= 12 check in dc3co exitline get_config. [Imre]

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Animesh Manna <animesh.manna@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191003081738.22101-5-anshuman.gupta@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c           | 93 +++++++++++++++++++++-
 drivers/gpu/drm/i915/display/intel_display.c       |  1 +
 drivers/gpu/drm/i915/display/intel_display_types.h |  1 +
 3 files changed, 93 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 3c1e885e0187..6c1315c7bcde 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -45,6 +45,7 @@
 #include "intel_lspcon.h"
 #include "intel_panel.h"
 #include "intel_psr.h"
+#include "intel_sprite.h"
 #include "intel_tc.h"
 #include "intel_vdsc.h"
 
@@ -3330,6 +3331,86 @@ static void intel_ddi_disable_fec_state(struct intel_encoder *encoder,
 	POSTING_READ(intel_dp->regs.dp_tp_ctl);
 }
 
+static void
+tgl_clear_psr2_transcoder_exitline(const struct intel_crtc_state *cstate)
+{
+	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
+	u32 val;
+
+	if (!cstate->dc3co_exitline)
+		return;
+
+	val = I915_READ(EXITLINE(cstate->cpu_transcoder));
+	val &= ~(EXITLINE_MASK | EXITLINE_ENABLE);
+	I915_WRITE(EXITLINE(cstate->cpu_transcoder), val);
+}
+
+static void
+tgl_set_psr2_transcoder_exitline(const struct intel_crtc_state *cstate)
+{
+	u32 val, exit_scanlines;
+	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
+
+	if (!cstate->dc3co_exitline)
+		return;
+
+	exit_scanlines = cstate->dc3co_exitline;
+	exit_scanlines <<= EXITLINE_SHIFT;
+	val = I915_READ(EXITLINE(cstate->cpu_transcoder));
+	val &= ~(EXITLINE_MASK | EXITLINE_ENABLE);
+	val |= exit_scanlines;
+	val |= EXITLINE_ENABLE;
+	I915_WRITE(EXITLINE(cstate->cpu_transcoder), val);
+}
+
+static void tgl_dc3co_exitline_compute_config(struct intel_encoder *encoder,
+					      struct intel_crtc_state *cstate)
+{
+	u32 exit_scanlines;
+	struct drm_i915_private *dev_priv = to_i915(cstate->base.crtc->dev);
+	u32 crtc_vdisplay = cstate->base.adjusted_mode.crtc_vdisplay;
+
+	cstate->dc3co_exitline = 0;
+
+	if (!(dev_priv->csr.allowed_dc_mask & DC_STATE_EN_DC3CO))
+		return;
+
+	/* B.Specs:49196 DC3CO only works with pipeA and DDIA.*/
+	if (to_intel_crtc(cstate->base.crtc)->pipe != PIPE_A ||
+	    encoder->port != PORT_A)
+		return;
+
+	if (!cstate->has_psr2 || !cstate->base.active)
+		return;
+
+	/*
+	 * DC3CO Exit time 200us B.Spec 49196
+	 * PSR2 transcoder Early Exit scanlines = ROUNDUP(200 / line time) + 1
+	 */
+	exit_scanlines =
+		intel_usecs_to_scanlines(&cstate->base.adjusted_mode, 200) + 1;
+
+	if (WARN_ON(exit_scanlines > crtc_vdisplay))
+		return;
+
+	cstate->dc3co_exitline = crtc_vdisplay - exit_scanlines;
+	DRM_DEBUG_KMS("DC3CO exit scanlines %d\n", cstate->dc3co_exitline);
+}
+
+static void tgl_dc3co_exitline_get_config(struct intel_crtc_state *crtc_state)
+{
+	u32 val;
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+
+	if (INTEL_GEN(dev_priv) < 12)
+		return;
+
+	val = I915_READ(EXITLINE(crtc_state->cpu_transcoder));
+
+	if (val & EXITLINE_ENABLE)
+		crtc_state->dc3co_exitline = val & EXITLINE_MASK;
+}
+
 static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 				  const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state)
@@ -3342,6 +3423,7 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	int level = intel_ddi_dp_level(intel_dp);
 	enum transcoder transcoder = crtc_state->cpu_transcoder;
 
+	tgl_set_psr2_transcoder_exitline(crtc_state);
 	intel_dp_set_link_params(intel_dp, crtc_state->port_clock,
 				 crtc_state->lane_count, is_mst);
 
@@ -3666,6 +3748,7 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
 						  dig_port->ddi_io_power_domain);
 
 	intel_ddi_clk_disable(encoder);
+	tgl_clear_psr2_transcoder_exitline(old_crtc_state);
 }
 
 static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
@@ -4212,6 +4295,9 @@ void intel_ddi_get_config(struct intel_encoder *encoder,
 		break;
 	}
 
+	if (encoder->type == INTEL_OUTPUT_EDP)
+		tgl_dc3co_exitline_get_config(pipe_config);
+
 	pipe_config->has_audio =
 		intel_ddi_is_audio_enabled(dev_priv, cpu_transcoder);
 
@@ -4289,10 +4375,13 @@ static int intel_ddi_compute_config(struct intel_encoder *encoder,
 	if (HAS_TRANSCODER_EDP(dev_priv) && port == PORT_A)
 		pipe_config->cpu_transcoder = TRANSCODER_EDP;
 
-	if (intel_crtc_has_type(pipe_config, INTEL_OUTPUT_HDMI))
+	if (intel_crtc_has_type(pipe_config, INTEL_OUTPUT_HDMI)) {
 		ret = intel_hdmi_compute_config(encoder, pipe_config, conn_state);
-	else
+	} else {
 		ret = intel_dp_compute_config(encoder, pipe_config, conn_state);
+		tgl_dc3co_exitline_compute_config(encoder, pipe_config);
+	}
+
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 05fb672a00b9..1a533ccdb54f 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -12808,6 +12808,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 	PIPE_CONF_CHECK_I(pixel_multiplier);
 	PIPE_CONF_CHECK_I(output_format);
+	PIPE_CONF_CHECK_I(dc3co_exitline);
 	PIPE_CONF_CHECK_BOOL(has_hdmi_sink);
 	if ((INTEL_GEN(dev_priv) < 8 && !IS_HASWELL(dev_priv)) ||
 	    IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 1602aac7ca0f..40390d855815 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -870,6 +870,7 @@ struct intel_crtc_state {
 
 	bool has_psr;
 	bool has_psr2;
+	u32 dc3co_exitline;
 
 	/*
 	 * Frequence the dpll for the port should run at. Differs from the
-- 
cgit v1.2.3


From 1c4d821db919366034dc9ff4c01b4b0da0b8e30f Mon Sep 17 00:00:00 2001
From: Anshuman Gupta <anshuman.gupta@intel.com>
Date: Thu, 3 Oct 2019 13:47:37 +0530
Subject: drm/i915/tgl: Switch between dc3co and dc5 based on display idleness

DC3CO is useful power state, when DMC detects PSR2 idle frame
while an active video playback, playing 30fps video on 60hz panel
is the classic example of this use case.

B.Specs:49196 has a restriction to enable DC3CO only for Video Playback.
It will be worthy to enable DC3CO after completion of each pageflip
and switch back to DC5 when display is idle because driver doesn't
differentiate between video playback and a normal pageflip.
We will use Frontbuffer flush call tgl_dc3co_flush() to enable DC3CO
state only for ORIGIN_FLIP flush call, because DC3CO state has primarily
targeted for VPB use case. We are not interested here for frontbuffer
invalidates calls because that triggers PSR2 exit, which will
explicitly disable DC3CO.

DC5 and DC6 saves more power, but can't be entered during video
playback because there are not enough idle frames in a row to meet
most PSR2 panel deep sleep entry requirement typically 4 frames.
As PSR2 existing implementation is using minimum 6 idle frames for
deep sleep, it is safer to enable DC5/6 after 6 idle frames
(By scheduling a delayed work of 6 idle frames, once DC3CO has been
enabled after a pageflip).

After manually waiting for 6 idle frames DC5/6 will be enabled and
PSR2 deep sleep idle frames will be restored to 6 idle frames, at this
point DMC will triggers DC5/6 once PSR2 enters to deep sleep after
6 idle frames.
In future when we will enable S/W PSR2 tracking, we can change the
PSR2 required deep sleep idle frames to 1 so DMC can trigger the
DC5/6 immediately after S/W manual waiting of 6 idle frames get
complete.

v2: calculated s/w state to switch over dc3co when there is an
    update. [Imre]
    Used cancel_delayed_work_sync() in order to avoid any race
    with already scheduled delayed work. [Imre]
v3: Cancel_delayed_work_sync() may blocked the commit work.
    hence dropping it, dc5_idle_thread() checks the valid wakeref before
    putting the reference count, which avoids any chances of dropping
    a zero wakeref. [Imre (IRC)]
v4: Used frontbuffer flush mechanism. [Imre]
v5: Used psr.pipe to extract frontbuffer busy bits. [Imre]
    Used cancel_delayed_work_sync() in encoder disable path. [Imre]
    Used mod_delayed_work() instead of cancelling and scheduling a
    delayed work. [Imre]
    Used psr.lock in tgl_dc5_idle_thread() to enable psr2 deep
    sleep. [Imre]
    Removed DC5_REQ_IDLE_FRAMES macro. [Imre]
v6: Used dc3co_exitline check instead of TGL and dc3co allowed_dc_mask
    checks, used delayed_work_pending with the psr lock and removed the
    psr2_deep_slp_disabled flag. [Imre]
v7: Code refactoring, moved most of functional code to inte_psr.c [Imre]
    Using frontbuffer_bits on psr.pipe check instead of
    busy_frontbuffer_bits. [Imre]
    Calculating dc3co_exit_delay in intel_psr_enable_locked. [Imre]

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Animesh Manna <animesh.manna@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191003081738.22101-6-anshuman.gupta@intel.com
---
 drivers/gpu/drm/i915/display/intel_display_power.c |  45 ++++++++
 drivers/gpu/drm/i915/display/intel_display_power.h |   2 +
 drivers/gpu/drm/i915/display/intel_psr.c           | 114 ++++++++++++++++++++-
 drivers/gpu/drm/i915/i915_drv.h                    |   3 +
 4 files changed, 163 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 812081f5232f..6f9e7927e248 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -870,6 +870,51 @@ lookup_power_well(struct drm_i915_private *dev_priv,
 	return &dev_priv->power_domains.power_wells[0];
 }
 
+/**
+ * intel_display_power_set_target_dc_state - Set target dc state.
+ * @dev_priv: i915 device
+ * @state: state which needs to be set as target_dc_state.
+ *
+ * This function set the "DC off" power well target_dc_state,
+ * based upon this target_dc_stste, "DC off" power well will
+ * enable desired DC state.
+ */
+void intel_display_power_set_target_dc_state(struct drm_i915_private *dev_priv,
+					     u32 state)
+{
+	struct i915_power_well *power_well;
+	bool dc_off_enabled;
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+
+	mutex_lock(&power_domains->lock);
+	power_well = lookup_power_well(dev_priv, SKL_DISP_DC_OFF);
+
+	if (WARN_ON(!power_well))
+		goto unlock;
+
+	state = sanitize_target_dc_state(dev_priv, state);
+
+	if (state == dev_priv->csr.target_dc_state)
+		goto unlock;
+
+	dc_off_enabled = power_well->desc->ops->is_enabled(dev_priv,
+							   power_well);
+	/*
+	 * If DC off power well is disabled, need to enable and disable the
+	 * DC off power well to effect target DC state.
+	 */
+	if (!dc_off_enabled)
+		power_well->desc->ops->enable(dev_priv, power_well);
+
+	dev_priv->csr.target_dc_state = state;
+
+	if (!dc_off_enabled)
+		power_well->desc->ops->disable(dev_priv, power_well);
+
+unlock:
+	mutex_unlock(&power_domains->lock);
+}
+
 static void assert_can_enable_dc5(struct drm_i915_private *dev_priv)
 {
 	bool pg2_enabled = intel_display_power_well_is_enabled(dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.h b/drivers/gpu/drm/i915/display/intel_display_power.h
index 7d72faf474b2..1da04f3e0fb3 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.h
+++ b/drivers/gpu/drm/i915/display/intel_display_power.h
@@ -257,6 +257,8 @@ void intel_display_power_suspend_late(struct drm_i915_private *i915);
 void intel_display_power_resume_early(struct drm_i915_private *i915);
 void intel_display_power_suspend(struct drm_i915_private *i915);
 void intel_display_power_resume(struct drm_i915_private *i915);
+void intel_display_power_set_target_dc_state(struct drm_i915_private *dev_priv,
+					     u32 state);
 
 const char *
 intel_display_power_domain_str(enum intel_display_power_domain domain);
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index b3c7eef53bf3..50f22abcd30e 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -534,6 +534,73 @@ transcoder_has_psr2(struct drm_i915_private *dev_priv, enum transcoder trans)
 		return trans == TRANSCODER_EDP;
 }
 
+static u32 intel_get_frame_time_us(const struct intel_crtc_state *cstate)
+{
+	if (!cstate || !cstate->base.active)
+		return 0;
+
+	return DIV_ROUND_UP(1000 * 1000,
+			    drm_mode_vrefresh(&cstate->base.adjusted_mode));
+}
+
+static void psr2_program_idle_frames(struct drm_i915_private *dev_priv,
+				     u32 idle_frames)
+{
+	u32 val;
+
+	idle_frames <<=  EDP_PSR2_IDLE_FRAME_SHIFT;
+	val = I915_READ(EDP_PSR2_CTL(dev_priv->psr.transcoder));
+	val &= ~EDP_PSR2_IDLE_FRAME_MASK;
+	val |= idle_frames;
+	I915_WRITE(EDP_PSR2_CTL(dev_priv->psr.transcoder), val);
+}
+
+static void tgl_psr2_enable_dc3co(struct drm_i915_private *dev_priv)
+{
+	psr2_program_idle_frames(dev_priv, 0);
+	intel_display_power_set_target_dc_state(dev_priv, DC_STATE_EN_DC3CO);
+}
+
+static void tgl_psr2_disable_dc3co(struct drm_i915_private *dev_priv)
+{
+	int idle_frames;
+
+	intel_display_power_set_target_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6);
+	/*
+	 * Restore PSR2 idle frame let's use 6 as the minimum to cover all known
+	 * cases including the off-by-one issue that HW has in some cases.
+	 */
+	idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
+	idle_frames = max(idle_frames, dev_priv->psr.sink_sync_latency + 1);
+	psr2_program_idle_frames(dev_priv, idle_frames);
+}
+
+static void tgl_dc5_idle_thread(struct work_struct *work)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(work, typeof(*dev_priv), psr.idle_work.work);
+
+	mutex_lock(&dev_priv->psr.lock);
+	/* If delayed work is pending, it is not idle */
+	if (delayed_work_pending(&dev_priv->psr.idle_work))
+		goto unlock;
+
+	DRM_DEBUG_KMS("DC5/6 idle thread\n");
+	tgl_psr2_disable_dc3co(dev_priv);
+unlock:
+	mutex_unlock(&dev_priv->psr.lock);
+}
+
+static void tgl_disallow_dc3co_on_psr2_exit(struct drm_i915_private *dev_priv)
+{
+	if (!dev_priv->psr.dc3co_enabled)
+		return;
+
+	cancel_delayed_work(&dev_priv->psr.idle_work);
+	/* Before PSR2 exit disallow dc3co*/
+	tgl_psr2_disable_dc3co(dev_priv);
+}
+
 static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 				    struct intel_crtc_state *crtc_state)
 {
@@ -746,6 +813,8 @@ static void intel_psr_enable_locked(struct drm_i915_private *dev_priv,
 	dev_priv->psr.psr2_enabled = intel_psr2_enabled(dev_priv, crtc_state);
 	dev_priv->psr.busy_frontbuffer_bits = 0;
 	dev_priv->psr.pipe = to_intel_crtc(crtc_state->base.crtc)->pipe;
+	dev_priv->psr.dc3co_enabled = !!crtc_state->dc3co_exitline;
+	dev_priv->psr.dc3co_exit_delay = intel_get_frame_time_us(crtc_state);
 	dev_priv->psr.transcoder = crtc_state->cpu_transcoder;
 
 	/*
@@ -829,6 +898,7 @@ static void intel_psr_exit(struct drm_i915_private *dev_priv)
 	}
 
 	if (dev_priv->psr.psr2_enabled) {
+		tgl_disallow_dc3co_on_psr2_exit(dev_priv);
 		val = I915_READ(EDP_PSR2_CTL(dev_priv->psr.transcoder));
 		WARN_ON(!(val & EDP_PSR2_ENABLE));
 		val &= ~EDP_PSR2_ENABLE;
@@ -901,6 +971,7 @@ void intel_psr_disable(struct intel_dp *intel_dp,
 
 	mutex_unlock(&dev_priv->psr.lock);
 	cancel_work_sync(&dev_priv->psr.work);
+	cancel_delayed_work_sync(&dev_priv->psr.idle_work);
 }
 
 static void psr_force_hw_tracking_exit(struct drm_i915_private *dev_priv)
@@ -1208,6 +1279,44 @@ void intel_psr_invalidate(struct drm_i915_private *dev_priv,
 	mutex_unlock(&dev_priv->psr.lock);
 }
 
+/*
+ * When we will be completely rely on PSR2 S/W tracking in future,
+ * intel_psr_flush() will invalidate and flush the PSR for ORIGIN_FLIP
+ * event also therefore tgl_dc3co_flush() require to be changed
+ * accrodingly in future.
+ */
+static void
+tgl_dc3co_flush(struct drm_i915_private *dev_priv,
+		unsigned int frontbuffer_bits, enum fb_op_origin origin)
+{
+	u32 delay;
+
+	mutex_lock(&dev_priv->psr.lock);
+
+	if (!dev_priv->psr.dc3co_enabled)
+		goto unlock;
+
+	if (!dev_priv->psr.psr2_enabled || !dev_priv->psr.active)
+		goto unlock;
+
+	/*
+	 * At every frontbuffer flush flip event modified delay of delayed work,
+	 * when delayed work schedules that means display has been idle.
+	 */
+	if (!(frontbuffer_bits &
+	    INTEL_FRONTBUFFER_ALL_MASK(dev_priv->psr.pipe)))
+		goto unlock;
+
+	tgl_psr2_enable_dc3co(dev_priv);
+	/* DC5/DC6 required idle frames = 6 */
+	delay = 6 * dev_priv->psr.dc3co_exit_delay;
+	mod_delayed_work(system_wq, &dev_priv->psr.idle_work,
+			 usecs_to_jiffies(delay));
+
+unlock:
+	mutex_unlock(&dev_priv->psr.lock);
+}
+
 /**
  * intel_psr_flush - Flush PSR
  * @dev_priv: i915 device
@@ -1227,8 +1336,10 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 	if (!CAN_PSR(dev_priv))
 		return;
 
-	if (origin == ORIGIN_FLIP)
+	if (origin == ORIGIN_FLIP) {
+		tgl_dc3co_flush(dev_priv, frontbuffer_bits, origin);
 		return;
+	}
 
 	mutex_lock(&dev_priv->psr.lock);
 	if (!dev_priv->psr.enabled) {
@@ -1284,6 +1395,7 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 		dev_priv->psr.link_standby = dev_priv->vbt.psr.full_link;
 
 	INIT_WORK(&dev_priv->psr.work, intel_psr_work);
+	INIT_DELAYED_WORK(&dev_priv->psr.idle_work, tgl_dc5_idle_thread);
 	mutex_init(&dev_priv->psr.lock);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 887ea4a4d687..bcfb355aab4d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -502,6 +502,9 @@ struct i915_psr {
 	bool sink_not_reliable;
 	bool irq_aux_error;
 	u16 su_x_granularity;
+	bool dc3co_enabled;
+	u32 dc3co_exit_delay;
+	struct delayed_work idle_work;
 };
 
 #define QUIRK_LVDS_SSC_DISABLE (1<<1)
-- 
cgit v1.2.3


From 41286861b4c9abdb4e0b32c6caa0967780e6f803 Mon Sep 17 00:00:00 2001
From: Anshuman Gupta <anshuman.gupta@intel.com>
Date: Thu, 3 Oct 2019 13:47:38 +0530
Subject: drm/i915/tgl: Add DC3CO counter in i915_dmc_info

Adding DC3CO counter in i915_dmc_info debugfs will be
useful for DC3CO validation.
DMC firmware uses DMC_DEBUG3 register as DC3CO counter
register on TGL, as per B.Specs DMC_DEBUG3 is general
purpose register.

v1: comment modification for DMC_DBUG3.
    using GEN >= 12 check instead of IS_TIGERLAKE()
    to print DMC_DEBUG3 counter value.

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Animesh Manna <animesh.manna@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Anshuman Gupta <anshuman.gupta@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191003081738.22101-7-anshuman.gupta@intel.com
---
 drivers/gpu/drm/i915/i915_debugfs.c | 7 +++++++
 drivers/gpu/drm/i915/i915_reg.h     | 2 ++
 2 files changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 298a3e879e65..277f31297f29 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2405,6 +2405,13 @@ static int i915_dmc_info(struct seq_file *m, void *unused)
 	if (INTEL_GEN(dev_priv) >= 12) {
 		dc5_reg = TGL_DMC_DEBUG_DC5_COUNT;
 		dc6_reg = TGL_DMC_DEBUG_DC6_COUNT;
+		/*
+		 * NOTE: DMC_DEBUG3 is a general purpose reg.
+		 * According to B.Specs:49196 DMC f/w reuses DC5/6 counter
+		 * reg for DC3CO debugging and validation,
+		 * but TGL DMC f/w is using DMC_DEBUG3 reg for DC3CO counter.
+		 */
+		seq_printf(m, "DC3CO count: %d\n", I915_READ(DMC_DEBUG3));
 	} else {
 		dc5_reg = IS_BROXTON(dev_priv) ? BXT_CSR_DC3_DC5_COUNT :
 						 SKL_CSR_DC3_DC5_COUNT;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index d252ee7803cc..1dc067fc57ab 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7268,6 +7268,8 @@ enum {
 #define TGL_DMC_DEBUG_DC5_COUNT	_MMIO(0x101084)
 #define TGL_DMC_DEBUG_DC6_COUNT	_MMIO(0x101088)
 
+#define DMC_DEBUG3		_MMIO(0x101090)
+
 /* interrupts */
 #define DE_MASTER_IRQ_CONTROL   (1 << 31)
 #define DE_SPRITEB_FLIP_DONE    (1 << 29)
-- 
cgit v1.2.3


From 20af04f3dd567970508d5ad756e1777ba1286815 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 8 Oct 2019 08:03:42 +0100
Subject: drm/i915/execlists: Assign virtual_engine->uncore from first sibling

Copy across the engine->uncore shortcut to the virtual_engine from its
first physical engine, similar to the handling of the engine->gt
backpointer.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191008070342.4045-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 432b8b60c4c0..6db762c509b8 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -4170,6 +4170,7 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 
 	ve->base.i915 = ctx->i915;
 	ve->base.gt = siblings[0]->gt;
+	ve->base.uncore = siblings[0]->uncore;
 	ve->base.id = -1;
 	ve->base.class = OTHER_CLASS;
 	ve->base.uabi_class = I915_ENGINE_CLASS_INVALID;
-- 
cgit v1.2.3


From 3de1627851321fc5589b2a49bf52755a60c8276f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 8 Oct 2019 08:11:21 +0100
Subject: drm/i915/selftests: Assign the mock_engine->uncore shortcut

Set up the engine->uncore shortcut on mock_engine creation.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191008071121.25088-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/mock_engine.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index 5d43cbc3f345..3d88397c0dbb 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -248,6 +248,7 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	/* minimal engine setup for requests */
 	engine->base.i915 = i915;
 	engine->base.gt = &i915->gt;
+	engine->base.uncore = i915->gt.uncore;
 	snprintf(engine->base.name, sizeof(engine->base.name), "%s", name);
 	engine->base.id = id;
 	engine->base.mask = BIT(id);
-- 
cgit v1.2.3


From be59d57f98065af0b8472f66a0a969207b168680 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 8 Oct 2019 11:01:53 +0100
Subject: efi/tpm: Fix sanity check of unsigned tbl_size being less than zero

Currently the check for tbl_size being less than zero is always false
because tbl_size is unsigned. Fix this by making it a signed int.

Addresses-Coverity: ("Unsigned compared against 0")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Jerry Snitselaar <jsnitsel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: kernel-janitors@vger.kernel.org
Cc: linux-efi@vger.kernel.org
Fixes: e658c82be556 ("efi/tpm: Only set 'efi_tpm_final_log_size' after successful event log parsing")
Link: https://lkml.kernel.org/r/20191008100153.8499-1-colin.king@canonical.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/firmware/efi/tpm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c
index 703469c1ab8e..ebd7977653a8 100644
--- a/drivers/firmware/efi/tpm.c
+++ b/drivers/firmware/efi/tpm.c
@@ -40,7 +40,7 @@ int __init efi_tpm_eventlog_init(void)
 {
 	struct linux_efi_tpm_eventlog *log_tbl;
 	struct efi_tcg2_final_events_table *final_tbl;
-	unsigned int tbl_size;
+	int tbl_size;
 	int ret = 0;
 
 	if (efi.tpm_log == EFI_INVALID_TABLE_ADDR) {
-- 
cgit v1.2.3


From 431d39887d6273d6d84edf3c2eab09f4200e788a Mon Sep 17 00:00:00 2001
From: Austin Kim <austindh.kim@gmail.com>
Date: Tue, 3 Sep 2019 12:30:19 +0900
Subject: btrfs: silence maybe-uninitialized warning in clone_range
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GCC throws warning message as below:

‘clone_src_i_size’ may be used uninitialized in this function
[-Wmaybe-uninitialized]
 #define IS_ALIGNED(x, a)  (((x) & ((typeof(x))(a) - 1)) == 0)
                       ^
fs/btrfs/send.c:5088:6: note: ‘clone_src_i_size’ was declared here
 u64 clone_src_i_size;
   ^
The clone_src_i_size is only used as call-by-reference
in a call to get_inode_info().

Silence the warning by initializing clone_src_i_size to 0.

Note that the warning is a false positive and reported by older versions
of GCC (eg. 7.x) but not eg 9.x. As there have been numerous people, the
patch is applied. Setting clone_src_i_size to 0 does not otherwise make
sense and would not do any action in case the code changes in the future.

Signed-off-by: Austin Kim <austindh.kim@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ add note ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/send.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index f3215028235c..123ac54af071 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -5085,7 +5085,7 @@ static int clone_range(struct send_ctx *sctx,
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	int ret;
-	u64 clone_src_i_size;
+	u64 clone_src_i_size = 0;
 
 	/*
 	 * Prevent cloning from a zero offset with a length matching the sector
-- 
cgit v1.2.3


From d3ec3a08fa700c8b46abb137dce4e2514a6f9668 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Thu, 7 Feb 2019 16:01:21 +0000
Subject: arm64: KVM: Trap VM ops when ARM64_WORKAROUND_CAVIUM_TX2_219_TVM is
 set

In order to workaround the TX2-219 erratum, it is necessary to trap
TTBRx_EL1 accesses to EL2. This is done by setting HCR_EL2.TVM on
guest entry, which has the side effect of trapping all the other
VM-related sysregs as well.

To minimize the overhead, a fast path is used so that we don't
have to go all the way back to the main sysreg handling code,
unless the rest of the hypervisor expects to see these accesses.

Cc: <stable@vger.kernel.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/cpucaps.h |  3 +-
 arch/arm64/kvm/hyp/switch.c      | 69 ++++++++++++++++++++++++++++++++++++++--
 2 files changed, 69 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index f19fe4b9acc4..e81e0cbd728f 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -52,7 +52,8 @@
 #define ARM64_HAS_IRQ_PRIO_MASKING		42
 #define ARM64_HAS_DCPODP			43
 #define ARM64_WORKAROUND_1463225		44
+#define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM	45
 
-#define ARM64_NCAPS				45
+#define ARM64_NCAPS				46
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 3d3815020e36..799e84a40335 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -124,6 +124,9 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 {
 	u64 hcr = vcpu->arch.hcr_el2;
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
+		hcr |= HCR_TVM;
+
 	write_sysreg(hcr, hcr_el2);
 
 	if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
@@ -174,8 +177,10 @@ static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu)
 	 * the crucial bit is "On taking a vSError interrupt,
 	 * HCR_EL2.VSE is cleared to 0."
 	 */
-	if (vcpu->arch.hcr_el2 & HCR_VSE)
-		vcpu->arch.hcr_el2 = read_sysreg(hcr_el2);
+	if (vcpu->arch.hcr_el2 & HCR_VSE) {
+		vcpu->arch.hcr_el2 &= ~HCR_VSE;
+		vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE;
+	}
 
 	if (has_vhe())
 		deactivate_traps_vhe();
@@ -380,6 +385,61 @@ static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
 	return true;
 }
 
+static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu)
+{
+	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu));
+	int rt = kvm_vcpu_sys_get_rt(vcpu);
+	u64 val = vcpu_get_reg(vcpu, rt);
+
+	/*
+	 * The normal sysreg handling code expects to see the traps,
+	 * let's not do anything here.
+	 */
+	if (vcpu->arch.hcr_el2 & HCR_TVM)
+		return false;
+
+	switch (sysreg) {
+	case SYS_SCTLR_EL1:
+		write_sysreg_el1(val, SYS_SCTLR);
+		break;
+	case SYS_TTBR0_EL1:
+		write_sysreg_el1(val, SYS_TTBR0);
+		break;
+	case SYS_TTBR1_EL1:
+		write_sysreg_el1(val, SYS_TTBR1);
+		break;
+	case SYS_TCR_EL1:
+		write_sysreg_el1(val, SYS_TCR);
+		break;
+	case SYS_ESR_EL1:
+		write_sysreg_el1(val, SYS_ESR);
+		break;
+	case SYS_FAR_EL1:
+		write_sysreg_el1(val, SYS_FAR);
+		break;
+	case SYS_AFSR0_EL1:
+		write_sysreg_el1(val, SYS_AFSR0);
+		break;
+	case SYS_AFSR1_EL1:
+		write_sysreg_el1(val, SYS_AFSR1);
+		break;
+	case SYS_MAIR_EL1:
+		write_sysreg_el1(val, SYS_MAIR);
+		break;
+	case SYS_AMAIR_EL1:
+		write_sysreg_el1(val, SYS_AMAIR);
+		break;
+	case SYS_CONTEXTIDR_EL1:
+		write_sysreg_el1(val, SYS_CONTEXTIDR);
+		break;
+	default:
+		return false;
+	}
+
+	__kvm_skip_instr(vcpu);
+	return true;
+}
+
 /*
  * Return true when we were able to fixup the guest exit and should return to
  * the guest, false when we should restore the host state and return to the
@@ -399,6 +459,11 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 	if (*exit_code != ARM_EXCEPTION_TRAP)
 		goto exit;
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+	    kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
+	    handle_tx2_tvm(vcpu))
+		return true;
+
 	/*
 	 * We trap the first access to the FP/SIMD to save the host context
 	 * and restore the guest context lazily.
-- 
cgit v1.2.3


From 454de1e7d970d6bc567686052329e4814842867c Mon Sep 17 00:00:00 2001
From: Janakarajan Natarajan <Janakarajan.Natarajan@amd.com>
Date: Mon, 7 Oct 2019 19:00:22 +0000
Subject: x86/asm: Fix MWAITX C-state hint value

As per "AMD64 Architecture Programmer's Manual Volume 3: General-Purpose
and System Instructions", MWAITX EAX[7:4]+1 specifies the optional hint
of the optimized C-state. For C0 state, EAX[7:4] should be set to 0xf.

Currently, a value of 0xf is set for EAX[3:0] instead of EAX[7:4]. Fix
this by changing MWAITX_DISABLE_CSTATES from 0xf to 0xf0.

This hasn't had any implications so far because setting reserved bits in
EAX is simply ignored by the CPU.

 [ bp: Fixup comment in delay_mwaitx() and massage. ]

Signed-off-by: Janakarajan Natarajan <Janakarajan.Natarajan@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "x86@kernel.org" <x86@kernel.org>
Cc: Zhenzhong Duan <zhenzhong.duan@oracle.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20191007190011.4859-1-Janakarajan.Natarajan@amd.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/mwait.h | 2 +-
 arch/x86/lib/delay.c         | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index e28f8b723b5c..9d5252c9685c 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -21,7 +21,7 @@
 #define MWAIT_ECX_INTERRUPT_BREAK	0x1
 #define MWAITX_ECX_TIMER_ENABLE		BIT(1)
 #define MWAITX_MAX_LOOPS		((u32)-1)
-#define MWAITX_DISABLE_CSTATES		0xf
+#define MWAITX_DISABLE_CSTATES		0xf0
 
 static inline void __monitor(const void *eax, unsigned long ecx,
 			     unsigned long edx)
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index b7375dc6898f..c126571e5e2e 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -113,8 +113,8 @@ static void delay_mwaitx(unsigned long __loops)
 		__monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
 
 		/*
-		 * AMD, like Intel, supports the EAX hint and EAX=0xf
-		 * means, do not enter any deep C-state and we use it
+		 * AMD, like Intel's MWAIT version, supports the EAX hint and
+		 * EAX=0xf0 means, do not enter any deep C-state and we use it
 		 * here in delay() to minimize wakeup latency.
 		 */
 		__mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE);
-- 
cgit v1.2.3


From 93916beb70143c46bf1d2bacf814be3a124b253b Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 9 Apr 2019 16:26:21 +0100
Subject: arm64: Enable workaround for Cavium TX2 erratum 219 when running SMT

It appears that the only case where we need to apply the TX2_219_TVM
mitigation is when the core is in SMT mode. So let's condition the
enabling on detecting a CPU whose MPIDR_EL1.Aff0 is non-zero.

Cc: <stable@vger.kernel.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/cpu_errata.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 1e43ba5c79b7..d999ca2dd760 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -12,6 +12,7 @@
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/smp_plat.h>
 
 static bool __maybe_unused
 is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
@@ -623,6 +624,30 @@ check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope)
 	return (need_wa > 0);
 }
 
+static const __maybe_unused struct midr_range tx2_family_cpus[] = {
+	MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
+	MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
+	{},
+};
+
+static bool __maybe_unused
+needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry,
+			 int scope)
+{
+	int i;
+
+	if (!is_affected_midr_range_list(entry, scope) ||
+	    !is_hyp_mode_available())
+		return false;
+
+	for_each_possible_cpu(i) {
+		if (MPIDR_AFFINITY_LEVEL(cpu_logical_map(i), 0) != 0)
+			return true;
+	}
+
+	return false;
+}
+
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 
 static const struct midr_range arm64_harden_el2_vectors[] = {
@@ -851,6 +876,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = has_cortex_a76_erratum_1463225,
 	},
+#endif
+#ifdef CONFIG_CAVIUM_TX2_ERRATUM_219
+	{
+		.desc = "Cavium ThunderX2 erratum 219 (KVM guest sysreg trapping)",
+		.capability = ARM64_WORKAROUND_CAVIUM_TX2_219_TVM,
+		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
+		.matches = needs_tx2_tvm_workaround,
+	},
 #endif
 	{
 	}
-- 
cgit v1.2.3


From 9405447ef79bc93101373e130f72e9e6cbf17dbb Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 9 Apr 2019 16:22:24 +0100
Subject: arm64: Avoid Cavium TX2 erratum 219 when switching TTBR

As a PRFM instruction racing against a TTBR update can have undesirable
effects on TX2, NOP-out such PRFM on cores that are affected by
the TX2-219 erratum.

Cc: <stable@vger.kernel.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/cpucaps.h | 3 ++-
 arch/arm64/kernel/cpu_errata.c   | 5 +++++
 arch/arm64/kernel/entry.S        | 2 ++
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index e81e0cbd728f..ac1dbca3d0cd 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -53,7 +53,8 @@
 #define ARM64_HAS_DCPODP			43
 #define ARM64_WORKAROUND_1463225		44
 #define ARM64_WORKAROUND_CAVIUM_TX2_219_TVM	45
+#define ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM	46
 
-#define ARM64_NCAPS				46
+#define ARM64_NCAPS				47
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index d999ca2dd760..a19bb3e4bcfb 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -884,6 +884,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
 		.matches = needs_tx2_tvm_workaround,
 	},
+	{
+		.desc = "Cavium ThunderX2 erratum 219 (PRFM removal)",
+		.capability = ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM,
+		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
+	},
 #endif
 	{
 	}
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 84a822748c84..109894bd3194 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -1070,7 +1070,9 @@ alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003
 #else
 	ldr	x30, =vectors
 #endif
+alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM
 	prfm	plil1strm, [x30, #(1b - tramp_vectors)]
+alternative_else_nop_endif
 	msr	vbar_el1, x30
 	add	x30, x30, #(1b - tramp_vectors)
 	isb
-- 
cgit v1.2.3


From 603afdc9438ac546181e843f807253d75d3dbc45 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Fri, 13 Sep 2019 10:57:50 +0100
Subject: arm64: Allow CAVIUM_TX2_ERRATUM_219 to be selected

Allow the user to select the workaround for TX2-219, and update
the silicon-errata.rst file to reflect this.

Cc: <stable@vger.kernel.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 Documentation/arm64/silicon-errata.rst |  2 ++
 arch/arm64/Kconfig                     | 17 +++++++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index 17ea3fecddaa..ab7ed2fd072f 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -107,6 +107,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | Cavium         | ThunderX2 SMMUv3| #126            | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
+| Cavium         | ThunderX2 Core  | #219            | CAVIUM_TX2_ERRATUM_219      |
++----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
 | Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
 +----------------+-----------------+-----------------+-----------------------------+
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 41a9b4257b72..7d36fd95ae5a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -617,6 +617,23 @@ config CAVIUM_ERRATUM_30115
 
 	  If unsure, say Y.
 
+config CAVIUM_TX2_ERRATUM_219
+	bool "Cavium ThunderX2 erratum 219: PRFM between TTBR change and ISB fails"
+	default y
+	help
+	  On Cavium ThunderX2, a load, store or prefetch instruction between a
+	  TTBR update and the corresponding context synchronizing operation can
+	  cause a spurious Data Abort to be delivered to any hardware thread in
+	  the CPU core.
+
+	  Work around the issue by avoiding the problematic code sequence and
+	  trapping KVM guest TTBRx_EL1 writes to EL2 when SMT is enabled. The
+	  trap handler performs the corresponding register access, skips the
+	  instruction and ensures context synchronization by virtue of the
+	  exception return.
+
+	  If unsure, say Y.
+
 config QCOM_FALKOR_ERRATUM_1003
 	bool "Falkor E1003: Incorrect translation due to ASID change"
 	default y
-- 
cgit v1.2.3


From fbcfb8f0270bf24fe348393540b17a7f2ba577d7 Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Mon, 7 Oct 2019 12:21:29 -0700
Subject: x86/cpu/vmware: Use the full form of INL in VMWARE_PORT

LLVM's assembler doesn't accept the short form INL instruction:

  inl (%%dx)

but instead insists on the output register to be explicitly specified:

  <inline asm>:1:7: error: invalid operand for instruction
          inl (%dx)
             ^
  LLVM ERROR: Error parsing inline asm

Use the full form of the instruction to fix the build.

Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Thomas Hellstrom <thellstrom@vmware.com>
Cc: clang-built-linux@googlegroups.com
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: virtualization@lists.linux-foundation.org
Cc: "VMware, Inc." <pv-drivers@vmware.com>
Cc: x86-ml <x86@kernel.org>
Link: https://github.com/ClangBuiltLinux/linux/issues/734
Link: https://lkml.kernel.org/r/20191007192129.104336-1-samitolvanen@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/vmware.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 9735139cfdf8..46d732696c1c 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -49,7 +49,7 @@
 #define VMWARE_CMD_VCPU_RESERVED 31
 
 #define VMWARE_PORT(cmd, eax, ebx, ecx, edx)				\
-	__asm__("inl (%%dx)" :						\
+	__asm__("inl (%%dx), %%eax" :					\
 		"=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :		\
 		"a"(VMWARE_HYPERVISOR_MAGIC),				\
 		"c"(VMWARE_CMD_##cmd),					\
-- 
cgit v1.2.3


From bec500777089b3c96c53681fc0aa6fee59711d4a Mon Sep 17 00:00:00 2001
From: Arvind Sankar <nivedita@alum.mit.edu>
Date: Mon, 7 Oct 2019 18:00:02 -0400
Subject: lib/string: Make memzero_explicit() inline instead of external

With the use of the barrier implied by barrier_data(), there is no need
for memzero_explicit() to be extern. Making it inline saves the overhead
of a function call, and allows the code to be reused in arch/*/purgatory
without having to duplicate the implementation.

Tested-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H . Peter Anvin <hpa@zytor.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephan Mueller <smueller@chronox.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-crypto@vger.kernel.org
Cc: linux-s390@vger.kernel.org
Fixes: 906a4bb97f5d ("crypto: sha256 - Use get/put_unaligned_be32 to get input, memzero_explicit")
Link: https://lkml.kernel.org/r/20191007220000.GA408752@rani.riverdale.lan
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/string.h | 21 ++++++++++++++++++++-
 lib/string.c           | 21 ---------------------
 2 files changed, 20 insertions(+), 22 deletions(-)

diff --git a/include/linux/string.h b/include/linux/string.h
index b2f9df7f0761..b6ccdc2c7f02 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -227,7 +227,26 @@ static inline bool strstarts(const char *str, const char *prefix)
 }
 
 size_t memweight(const void *ptr, size_t bytes);
-void memzero_explicit(void *s, size_t count);
+
+/**
+ * memzero_explicit - Fill a region of memory (e.g. sensitive
+ *		      keying data) with 0s.
+ * @s: Pointer to the start of the area.
+ * @count: The size of the area.
+ *
+ * Note: usually using memset() is just fine (!), but in cases
+ * where clearing out _local_ data at the end of a scope is
+ * necessary, memzero_explicit() should be used instead in
+ * order to prevent the compiler from optimising away zeroing.
+ *
+ * memzero_explicit() doesn't need an arch-specific version as
+ * it just invokes the one of memset() implicitly.
+ */
+static inline void memzero_explicit(void *s, size_t count)
+{
+	memset(s, 0, count);
+	barrier_data(s);
+}
 
 /**
  * kbasename - return the last part of a pathname.
diff --git a/lib/string.c b/lib/string.c
index cd7a10c19210..08ec58cc673b 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -748,27 +748,6 @@ void *memset(void *s, int c, size_t count)
 EXPORT_SYMBOL(memset);
 #endif
 
-/**
- * memzero_explicit - Fill a region of memory (e.g. sensitive
- *		      keying data) with 0s.
- * @s: Pointer to the start of the area.
- * @count: The size of the area.
- *
- * Note: usually using memset() is just fine (!), but in cases
- * where clearing out _local_ data at the end of a scope is
- * necessary, memzero_explicit() should be used instead in
- * order to prevent the compiler from optimising away zeroing.
- *
- * memzero_explicit() doesn't need an arch-specific version as
- * it just invokes the one of memset() implicitly.
- */
-void memzero_explicit(void *s, size_t count)
-{
-	memset(s, 0, count);
-	barrier_data(s);
-}
-EXPORT_SYMBOL(memzero_explicit);
-
 #ifndef __HAVE_ARCH_MEMSET16
 /**
  * memset16() - Fill a memory area with a uint16_t
-- 
cgit v1.2.3


From 3e7c93bd04edfb0cae7dad1215544c9350254b8f Mon Sep 17 00:00:00 2001
From: Yunfeng Ye <yeyunfeng@huawei.com>
Date: Sun, 29 Sep 2019 12:44:17 +0800
Subject: arm64: armv8_deprecated: Checking return value for memory allocation

There are no return value checking when using kzalloc() and kcalloc() for
memory allocation. so add it.

Signed-off-by: Yunfeng Ye <yeyunfeng@huawei.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/armv8_deprecated.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 2ec09debc2bb..ca158be21f83 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -174,6 +174,9 @@ static void __init register_insn_emulation(struct insn_emulation_ops *ops)
 	struct insn_emulation *insn;
 
 	insn = kzalloc(sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return;
+
 	insn->ops = ops;
 	insn->min = INSN_UNDEF;
 
@@ -233,6 +236,8 @@ static void __init register_insn_emulation_sysctl(void)
 
 	insns_sysctl = kcalloc(nr_insn_emulated + 1, sizeof(*sysctl),
 			       GFP_KERNEL);
+	if (!insns_sysctl)
+		return;
 
 	raw_spin_lock_irqsave(&insn_emulation_lock, flags);
 	list_for_each_entry(insn, &insn_emulation, node) {
-- 
cgit v1.2.3


From d14a701b00706395de33c61866daa3d424d758fc Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 8 Oct 2019 15:50:45 +0100
Subject: drm/i915/selftests: Assign the intel_runtime_pm pointer for
 mock_uncore

Couple up our mock_uncore to know about the fake global device and its
runtime powermanagement.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191008145045.23157-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/mock_engine.c            | 1 +
 drivers/gpu/drm/i915/selftests/mock_gem_device.c | 2 +-
 drivers/gpu/drm/i915/selftests/mock_uncore.c     | 5 ++++-
 drivers/gpu/drm/i915/selftests/mock_uncore.h     | 3 ++-
 4 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index 3d88397c0dbb..747f7c7790eb 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -240,6 +240,7 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	struct mock_engine *engine;
 
 	GEM_BUG_ON(id >= I915_NUM_ENGINES);
+	GEM_BUG_ON(!i915->gt.uncore);
 
 	engine = kzalloc(sizeof(*engine) + PAGE_SIZE, GFP_KERNEL);
 	if (!engine)
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 70a7026db08d..d14c6d8735fe 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -162,7 +162,7 @@ struct drm_i915_private *mock_gem_device(void)
 		I915_GTT_PAGE_SIZE_64K |
 		I915_GTT_PAGE_SIZE_2M;
 
-	mock_uncore_init(&i915->uncore);
+	mock_uncore_init(&i915->uncore, i915);
 	i915_gem_init__mm(i915);
 	intel_gt_init_early(&i915->gt, i915);
 	atomic_inc(&i915->gt.wakeref.count); /* disable; no hw support */
diff --git a/drivers/gpu/drm/i915/selftests/mock_uncore.c b/drivers/gpu/drm/i915/selftests/mock_uncore.c
index 49585f16d4a2..ca57e4008701 100644
--- a/drivers/gpu/drm/i915/selftests/mock_uncore.c
+++ b/drivers/gpu/drm/i915/selftests/mock_uncore.c
@@ -39,8 +39,11 @@ __nop_read(16)
 __nop_read(32)
 __nop_read(64)
 
-void mock_uncore_init(struct intel_uncore *uncore)
+void mock_uncore_init(struct intel_uncore *uncore,
+		      struct drm_i915_private *i915)
 {
+	intel_uncore_init_early(uncore, i915);
+
 	ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, nop);
 	ASSIGN_RAW_READ_MMIO_VFUNCS(uncore, nop);
 }
diff --git a/drivers/gpu/drm/i915/selftests/mock_uncore.h b/drivers/gpu/drm/i915/selftests/mock_uncore.h
index dacb36b5ffcd..8a2cc553f466 100644
--- a/drivers/gpu/drm/i915/selftests/mock_uncore.h
+++ b/drivers/gpu/drm/i915/selftests/mock_uncore.h
@@ -25,6 +25,7 @@
 #ifndef __MOCK_UNCORE_H
 #define __MOCK_UNCORE_H
 
-void mock_uncore_init(struct intel_uncore *uncore);
+void mock_uncore_init(struct intel_uncore *uncore,
+		      struct drm_i915_private *i915);
 
 #endif /* !__MOCK_UNCORE_H */
-- 
cgit v1.2.3


From 23b9e41a3dbdad16266b16d0c16ac629f0b6d732 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Tue, 8 Oct 2019 15:01:11 +0100
Subject: drm/i915/perf: drop list of streams

At some point in time there was the idea that we could have multiple
stream from the same piece of HW but that never materialized and given
the hard time we already have making everything work with the
submission side, there is no real point having this list of 1 element
around.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191008140111.5437-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_perf.c       | 16 +---------------
 drivers/gpu/drm/i915/i915_perf_types.h |  6 ------
 2 files changed, 1 insertion(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index e5973809b69a..5a34cad7d824 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1407,9 +1407,6 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream)
 	 */
 	memset(stream->oa_buffer.vaddr, 0, OA_BUFFER_SIZE);
 
-	/* Maybe make ->pollin per-stream state if we support multiple
-	 * concurrent streams in the future.
-	 */
 	stream->pollin = false;
 }
 
@@ -1466,10 +1463,6 @@ static void gen8_init_oa_buffer(struct i915_perf_stream *stream)
 	 */
 	memset(stream->oa_buffer.vaddr, 0, OA_BUFFER_SIZE);
 
-	/*
-	 * Maybe make ->pollin per-stream state if we support multiple
-	 * concurrent streams in the future.
-	 */
 	stream->pollin = false;
 }
 
@@ -2585,8 +2578,6 @@ static void i915_perf_destroy_locked(struct i915_perf_stream *stream)
 	if (stream->ops->destroy)
 		stream->ops->destroy(stream);
 
-	list_del(&stream->link);
-
 	if (stream->ctx)
 		i915_gem_context_put(stream->ctx);
 
@@ -2736,8 +2727,6 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 		goto err_flags;
 	}
 
-	list_add(&stream->link, &perf->streams);
-
 	if (param->flags & I915_PERF_FLAG_FD_CLOEXEC)
 		f_flags |= O_CLOEXEC;
 	if (param->flags & I915_PERF_FLAG_FD_NONBLOCK)
@@ -2746,7 +2735,7 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 	stream_fd = anon_inode_getfd("[i915_perf]", &fops, stream, f_flags);
 	if (stream_fd < 0) {
 		ret = stream_fd;
-		goto err_open;
+		goto err_flags;
 	}
 
 	if (!(param->flags & I915_PERF_FLAG_DISABLED))
@@ -2759,8 +2748,6 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 
 	return stream_fd;
 
-err_open:
-	list_del(&stream->link);
 err_flags:
 	if (stream->ops->destroy)
 		stream->ops->destroy(stream);
@@ -3600,7 +3587,6 @@ void i915_perf_init(struct drm_i915_private *i915)
 	}
 
 	if (perf->ops.enable_metric_set) {
-		INIT_LIST_HEAD(&perf->streams);
 		mutex_init(&perf->lock);
 
 		oa_sample_rate_hard_limit = 1000 *
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 3c6246064a0b..2d17059d32ee 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -134,11 +134,6 @@ struct i915_perf_stream {
 	 */
 	struct intel_gt *gt;
 
-	/**
-	 * @link: Links the stream into ``&drm_i915_private->streams``
-	 */
-	struct list_head link;
-
 	/**
 	 * @wakeref: As we keep the device awake while the perf stream is
 	 * active, we track our runtime pm reference for later release.
@@ -352,7 +347,6 @@ struct i915_perf {
 	 * except exclusive_stream.
 	 */
 	struct mutex lock;
-	struct list_head streams;
 
 	/*
 	 * The stream currently using the OA unit. If accessed
-- 
cgit v1.2.3


From d99f7b079c2a49b2278fe80192fbca083db87d18 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 8 Oct 2019 11:56:55 +0100
Subject: drm/i915/gt: Flush submission tasklet before waiting/retiring

A common bane of ours is arbitrary delays in ksoftirqd processing our
submission tasklet. Give the submission tasklet a kick before we wait to
avoid those delays eating into a tight timeout.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191008105655.13256-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_engine.h      |  3 ++-
 drivers/gpu/drm/i915/gt/intel_engine_cs.c   | 33 +++++++++++++++++------------
 drivers/gpu/drm/i915/gt/intel_gt_requests.c | 12 +++++++++++
 3 files changed, 34 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index c9e8c8ccbd47..d624752f2a92 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -407,8 +407,9 @@ static inline void __intel_engine_reset(struct intel_engine_cs *engine,
 	engine->serial++; /* contexts lost */
 }
 
-bool intel_engine_is_idle(struct intel_engine_cs *engine);
 bool intel_engines_are_idle(struct intel_gt *gt);
+bool intel_engine_is_idle(struct intel_engine_cs *engine);
+void intel_engine_flush_submission(struct intel_engine_cs *engine);
 
 void intel_engines_reset_default_submission(struct intel_gt *gt);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 6220b7151bb9..7e2aa7a6bef0 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1040,6 +1040,25 @@ static bool ring_is_idle(struct intel_engine_cs *engine)
 	return idle;
 }
 
+void intel_engine_flush_submission(struct intel_engine_cs *engine)
+{
+	struct tasklet_struct *t = &engine->execlists.tasklet;
+
+	if (__tasklet_is_scheduled(t)) {
+		local_bh_disable();
+		if (tasklet_trylock(t)) {
+			/* Must wait for any GPU reset in progress. */
+			if (__tasklet_is_enabled(t))
+				t->func(t->data);
+			tasklet_unlock(t);
+		}
+		local_bh_enable();
+	}
+
+	/* Otherwise flush the tasklet if it was running on another cpu */
+	tasklet_unlock_wait(t);
+}
+
 /**
  * intel_engine_is_idle() - Report if the engine has finished process all work
  * @engine: the intel_engine_cs
@@ -1058,21 +1077,9 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 
 	/* Waiting to drain ELSP? */
 	if (execlists_active(&engine->execlists)) {
-		struct tasklet_struct *t = &engine->execlists.tasklet;
-
 		synchronize_hardirq(engine->i915->drm.pdev->irq);
 
-		local_bh_disable();
-		if (tasklet_trylock(t)) {
-			/* Must wait for any GPU reset in progress. */
-			if (__tasklet_is_enabled(t))
-				t->func(t->data);
-			tasklet_unlock(t);
-		}
-		local_bh_enable();
-
-		/* Otherwise flush the tasklet if it was on another cpu */
-		tasklet_unlock_wait(t);
+		intel_engine_flush_submission(engine);
 
 		if (execlists_active(&engine->execlists))
 			return false;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index ca606b79fd5e..cbb4069b11e1 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -4,6 +4,7 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include "i915_drv.h" /* for_each_engine() */
 #include "i915_request.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
@@ -19,6 +20,15 @@ static void retire_requests(struct intel_timeline *tl)
 			break;
 }
 
+static void flush_submission(struct intel_gt *gt)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	for_each_engine(engine, gt->i915, id)
+		intel_engine_flush_submission(engine);
+}
+
 long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
@@ -32,6 +42,8 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 	if (unlikely(timeout < 0))
 		timeout = -timeout, interruptible = false;
 
+	flush_submission(gt); /* kick the ksoftirqd tasklets */
+
 	spin_lock_irqsave(&timelines->lock, flags);
 	list_for_each_entry_safe(tl, tn, &timelines->active_list, link) {
 		if (!mutex_trylock(&tl->mutex)) {
-- 
cgit v1.2.3


From fcfacb9f83745d9fa97937b8bc94a73bb0607912 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Tue, 8 Oct 2019 12:10:09 +0900
Subject: doc: move namespaces.rst from kbuild/ to core-api/

We discussed a better location for this file, and agreed that
core-api/ is a good fit. Rename it to symbol-namespaces.rst
for disambiguation, and also add it to index.rst and MAINTAINERS.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Acked-by: Matthias Maennich <maennich@google.com>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
---
 Documentation/core-api/index.rst             |   1 +
 Documentation/core-api/symbol-namespaces.rst | 154 +++++++++++++++++++++++++++
 Documentation/kbuild/namespaces.rst          | 154 ---------------------------
 MAINTAINERS                                  |   1 +
 4 files changed, 156 insertions(+), 154 deletions(-)
 create mode 100644 Documentation/core-api/symbol-namespaces.rst
 delete mode 100644 Documentation/kbuild/namespaces.rst

diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index fa16a0538dcb..ab0eae1c153a 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -38,6 +38,7 @@ Core utilities
    protection-keys
    ../RCU/index
    gcc-plugins
+   symbol-namespaces
 
 
 Interfaces for kernel debugging
diff --git a/Documentation/core-api/symbol-namespaces.rst b/Documentation/core-api/symbol-namespaces.rst
new file mode 100644
index 000000000000..982ed7b568ac
--- /dev/null
+++ b/Documentation/core-api/symbol-namespaces.rst
@@ -0,0 +1,154 @@
+=================
+Symbol Namespaces
+=================
+
+The following document describes how to use Symbol Namespaces to structure the
+export surface of in-kernel symbols exported through the family of
+EXPORT_SYMBOL() macros.
+
+.. Table of Contents
+
+	=== 1 Introduction
+	=== 2 How to define Symbol Namespaces
+	   --- 2.1 Using the EXPORT_SYMBOL macros
+	   --- 2.2 Using the DEFAULT_SYMBOL_NAMESPACE define
+	=== 3 How to use Symbols exported in Namespaces
+	=== 4 Loading Modules that use namespaced Symbols
+	=== 5 Automatically creating MODULE_IMPORT_NS statements
+
+1. Introduction
+===============
+
+Symbol Namespaces have been introduced as a means to structure the export
+surface of the in-kernel API. It allows subsystem maintainers to partition
+their exported symbols into separate namespaces. That is useful for
+documentation purposes (think of the SUBSYSTEM_DEBUG namespace) as well as for
+limiting the availability of a set of symbols for use in other parts of the
+kernel. As of today, modules that make use of symbols exported into namespaces,
+are required to import the namespace. Otherwise the kernel will, depending on
+its configuration, reject loading the module or warn about a missing import.
+
+2. How to define Symbol Namespaces
+==================================
+
+Symbols can be exported into namespace using different methods. All of them are
+changing the way EXPORT_SYMBOL and friends are instrumented to create ksymtab
+entries.
+
+2.1 Using the EXPORT_SYMBOL macros
+==================================
+
+In addition to the macros EXPORT_SYMBOL() and EXPORT_SYMBOL_GPL(), that allow
+exporting of kernel symbols to the kernel symbol table, variants of these are
+available to export symbols into a certain namespace: EXPORT_SYMBOL_NS() and
+EXPORT_SYMBOL_NS_GPL(). They take one additional argument: the namespace.
+Please note that due to macro expansion that argument needs to be a
+preprocessor symbol. E.g. to export the symbol `usb_stor_suspend` into the
+namespace `USB_STORAGE`, use::
+
+	EXPORT_SYMBOL_NS(usb_stor_suspend, USB_STORAGE);
+
+The corresponding ksymtab entry struct `kernel_symbol` will have the member
+`namespace` set accordingly. A symbol that is exported without a namespace will
+refer to `NULL`. There is no default namespace if none is defined. `modpost`
+and kernel/module.c make use the namespace at build time or module load time,
+respectively.
+
+2.2 Using the DEFAULT_SYMBOL_NAMESPACE define
+=============================================
+
+Defining namespaces for all symbols of a subsystem can be very verbose and may
+become hard to maintain. Therefore a default define (DEFAULT_SYMBOL_NAMESPACE)
+is been provided, that, if set, will become the default for all EXPORT_SYMBOL()
+and EXPORT_SYMBOL_GPL() macro expansions that do not specify a namespace.
+
+There are multiple ways of specifying this define and it depends on the
+subsystem and the maintainer's preference, which one to use. The first option
+is to define the default namespace in the `Makefile` of the subsystem. E.g. to
+export all symbols defined in usb-common into the namespace USB_COMMON, add a
+line like this to drivers/usb/common/Makefile::
+
+	ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=USB_COMMON
+
+That will affect all EXPORT_SYMBOL() and EXPORT_SYMBOL_GPL() statements. A
+symbol exported with EXPORT_SYMBOL_NS() while this definition is present, will
+still be exported into the namespace that is passed as the namespace argument
+as this argument has preference over a default symbol namespace.
+
+A second option to define the default namespace is directly in the compilation
+unit as preprocessor statement. The above example would then read::
+
+	#undef  DEFAULT_SYMBOL_NAMESPACE
+	#define DEFAULT_SYMBOL_NAMESPACE USB_COMMON
+
+within the corresponding compilation unit before any EXPORT_SYMBOL macro is
+used.
+
+3. How to use Symbols exported in Namespaces
+============================================
+
+In order to use symbols that are exported into namespaces, kernel modules need
+to explicitly import these namespaces. Otherwise the kernel might reject to
+load the module. The module code is required to use the macro MODULE_IMPORT_NS
+for the namespaces it uses symbols from. E.g. a module using the
+usb_stor_suspend symbol from above, needs to import the namespace USB_STORAGE
+using a statement like::
+
+	MODULE_IMPORT_NS(USB_STORAGE);
+
+This will create a `modinfo` tag in the module for each imported namespace.
+This has the side effect, that the imported namespaces of a module can be
+inspected with modinfo::
+
+	$ modinfo drivers/usb/storage/ums-karma.ko
+	[...]
+	import_ns:      USB_STORAGE
+	[...]
+
+
+It is advisable to add the MODULE_IMPORT_NS() statement close to other module
+metadata definitions like MODULE_AUTHOR() or MODULE_LICENSE(). Refer to section
+5. for a way to create missing import statements automatically.
+
+4. Loading Modules that use namespaced Symbols
+==============================================
+
+At module loading time (e.g. `insmod`), the kernel will check each symbol
+referenced from the module for its availability and whether the namespace it
+might be exported to has been imported by the module. The default behaviour of
+the kernel is to reject loading modules that don't specify sufficient imports.
+An error will be logged and loading will be failed with EINVAL. In order to
+allow loading of modules that don't satisfy this precondition, a configuration
+option is available: Setting MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS=y will
+enable loading regardless, but will emit a warning.
+
+5. Automatically creating MODULE_IMPORT_NS statements
+=====================================================
+
+Missing namespaces imports can easily be detected at build time. In fact,
+modpost will emit a warning if a module uses a symbol from a namespace
+without importing it.
+MODULE_IMPORT_NS() statements will usually be added at a definite location
+(along with other module meta data). To make the life of module authors (and
+subsystem maintainers) easier, a script and make target is available to fixup
+missing imports. Fixing missing imports can be done with::
+
+	$ make nsdeps
+
+A typical scenario for module authors would be::
+
+	- write code that depends on a symbol from a not imported namespace
+	- `make`
+	- notice the warning of modpost telling about a missing import
+	- run `make nsdeps` to add the import to the correct code location
+
+For subsystem maintainers introducing a namespace, the steps are very similar.
+Again, `make nsdeps` will eventually add the missing namespace imports for
+in-tree modules::
+
+	- move or add symbols to a namespace (e.g. with EXPORT_SYMBOL_NS())
+	- `make` (preferably with an allmodconfig to cover all in-kernel
+	  modules)
+	- notice the warning of modpost telling about a missing import
+	- run `make nsdeps` to add the import to the correct code location
+
diff --git a/Documentation/kbuild/namespaces.rst b/Documentation/kbuild/namespaces.rst
deleted file mode 100644
index 982ed7b568ac..000000000000
--- a/Documentation/kbuild/namespaces.rst
+++ /dev/null
@@ -1,154 +0,0 @@
-=================
-Symbol Namespaces
-=================
-
-The following document describes how to use Symbol Namespaces to structure the
-export surface of in-kernel symbols exported through the family of
-EXPORT_SYMBOL() macros.
-
-.. Table of Contents
-
-	=== 1 Introduction
-	=== 2 How to define Symbol Namespaces
-	   --- 2.1 Using the EXPORT_SYMBOL macros
-	   --- 2.2 Using the DEFAULT_SYMBOL_NAMESPACE define
-	=== 3 How to use Symbols exported in Namespaces
-	=== 4 Loading Modules that use namespaced Symbols
-	=== 5 Automatically creating MODULE_IMPORT_NS statements
-
-1. Introduction
-===============
-
-Symbol Namespaces have been introduced as a means to structure the export
-surface of the in-kernel API. It allows subsystem maintainers to partition
-their exported symbols into separate namespaces. That is useful for
-documentation purposes (think of the SUBSYSTEM_DEBUG namespace) as well as for
-limiting the availability of a set of symbols for use in other parts of the
-kernel. As of today, modules that make use of symbols exported into namespaces,
-are required to import the namespace. Otherwise the kernel will, depending on
-its configuration, reject loading the module or warn about a missing import.
-
-2. How to define Symbol Namespaces
-==================================
-
-Symbols can be exported into namespace using different methods. All of them are
-changing the way EXPORT_SYMBOL and friends are instrumented to create ksymtab
-entries.
-
-2.1 Using the EXPORT_SYMBOL macros
-==================================
-
-In addition to the macros EXPORT_SYMBOL() and EXPORT_SYMBOL_GPL(), that allow
-exporting of kernel symbols to the kernel symbol table, variants of these are
-available to export symbols into a certain namespace: EXPORT_SYMBOL_NS() and
-EXPORT_SYMBOL_NS_GPL(). They take one additional argument: the namespace.
-Please note that due to macro expansion that argument needs to be a
-preprocessor symbol. E.g. to export the symbol `usb_stor_suspend` into the
-namespace `USB_STORAGE`, use::
-
-	EXPORT_SYMBOL_NS(usb_stor_suspend, USB_STORAGE);
-
-The corresponding ksymtab entry struct `kernel_symbol` will have the member
-`namespace` set accordingly. A symbol that is exported without a namespace will
-refer to `NULL`. There is no default namespace if none is defined. `modpost`
-and kernel/module.c make use the namespace at build time or module load time,
-respectively.
-
-2.2 Using the DEFAULT_SYMBOL_NAMESPACE define
-=============================================
-
-Defining namespaces for all symbols of a subsystem can be very verbose and may
-become hard to maintain. Therefore a default define (DEFAULT_SYMBOL_NAMESPACE)
-is been provided, that, if set, will become the default for all EXPORT_SYMBOL()
-and EXPORT_SYMBOL_GPL() macro expansions that do not specify a namespace.
-
-There are multiple ways of specifying this define and it depends on the
-subsystem and the maintainer's preference, which one to use. The first option
-is to define the default namespace in the `Makefile` of the subsystem. E.g. to
-export all symbols defined in usb-common into the namespace USB_COMMON, add a
-line like this to drivers/usb/common/Makefile::
-
-	ccflags-y += -DDEFAULT_SYMBOL_NAMESPACE=USB_COMMON
-
-That will affect all EXPORT_SYMBOL() and EXPORT_SYMBOL_GPL() statements. A
-symbol exported with EXPORT_SYMBOL_NS() while this definition is present, will
-still be exported into the namespace that is passed as the namespace argument
-as this argument has preference over a default symbol namespace.
-
-A second option to define the default namespace is directly in the compilation
-unit as preprocessor statement. The above example would then read::
-
-	#undef  DEFAULT_SYMBOL_NAMESPACE
-	#define DEFAULT_SYMBOL_NAMESPACE USB_COMMON
-
-within the corresponding compilation unit before any EXPORT_SYMBOL macro is
-used.
-
-3. How to use Symbols exported in Namespaces
-============================================
-
-In order to use symbols that are exported into namespaces, kernel modules need
-to explicitly import these namespaces. Otherwise the kernel might reject to
-load the module. The module code is required to use the macro MODULE_IMPORT_NS
-for the namespaces it uses symbols from. E.g. a module using the
-usb_stor_suspend symbol from above, needs to import the namespace USB_STORAGE
-using a statement like::
-
-	MODULE_IMPORT_NS(USB_STORAGE);
-
-This will create a `modinfo` tag in the module for each imported namespace.
-This has the side effect, that the imported namespaces of a module can be
-inspected with modinfo::
-
-	$ modinfo drivers/usb/storage/ums-karma.ko
-	[...]
-	import_ns:      USB_STORAGE
-	[...]
-
-
-It is advisable to add the MODULE_IMPORT_NS() statement close to other module
-metadata definitions like MODULE_AUTHOR() or MODULE_LICENSE(). Refer to section
-5. for a way to create missing import statements automatically.
-
-4. Loading Modules that use namespaced Symbols
-==============================================
-
-At module loading time (e.g. `insmod`), the kernel will check each symbol
-referenced from the module for its availability and whether the namespace it
-might be exported to has been imported by the module. The default behaviour of
-the kernel is to reject loading modules that don't specify sufficient imports.
-An error will be logged and loading will be failed with EINVAL. In order to
-allow loading of modules that don't satisfy this precondition, a configuration
-option is available: Setting MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS=y will
-enable loading regardless, but will emit a warning.
-
-5. Automatically creating MODULE_IMPORT_NS statements
-=====================================================
-
-Missing namespaces imports can easily be detected at build time. In fact,
-modpost will emit a warning if a module uses a symbol from a namespace
-without importing it.
-MODULE_IMPORT_NS() statements will usually be added at a definite location
-(along with other module meta data). To make the life of module authors (and
-subsystem maintainers) easier, a script and make target is available to fixup
-missing imports. Fixing missing imports can be done with::
-
-	$ make nsdeps
-
-A typical scenario for module authors would be::
-
-	- write code that depends on a symbol from a not imported namespace
-	- `make`
-	- notice the warning of modpost telling about a missing import
-	- run `make nsdeps` to add the import to the correct code location
-
-For subsystem maintainers introducing a namespace, the steps are very similar.
-Again, `make nsdeps` will eventually add the missing namespace imports for
-in-tree modules::
-
-	- move or add symbols to a namespace (e.g. with EXPORT_SYMBOL_NS())
-	- `make` (preferably with an allmodconfig to cover all in-kernel
-	  modules)
-	- notice the warning of modpost telling about a missing import
-	- run `make nsdeps` to add the import to the correct code location
-
diff --git a/MAINTAINERS b/MAINTAINERS
index 296de2b51c83..3dec8d53c34b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11543,6 +11543,7 @@ NSDEPS
 M:	Matthias Maennich <maennich@google.com>
 S:	Maintained
 F:	scripts/nsdeps
+F:	Documentation/core-api/symbol-namespaces.rst
 
 NTB AMD DRIVER
 M:	Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
-- 
cgit v1.2.3


From 98d22b01f9f6f85eb8870290006241b316829fd3 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Wed, 2 Oct 2019 14:50:52 -0700
Subject: rt2x00: remove input-polldev.h header

The driver does not use input subsystem so we do not need this header,
and it is being removed, so stop pulling it in.

Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ralink/rt2x00/rt2x00.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
index 2b216edd0c7d..a90a518b40d3 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
@@ -23,7 +23,6 @@
 #include <linux/leds.h>
 #include <linux/mutex.h>
 #include <linux/etherdevice.h>
-#include <linux/input-polldev.h>
 #include <linux/kfifo.h>
 #include <linux/hrtimer.h>
 #include <linux/average.h>
-- 
cgit v1.2.3


From 8d7c6ac3b2371eb1cbc9925a88f4d10efff374de Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 8 Oct 2019 08:50:02 -0700
Subject: x86/cpu: Add Comet Lake to the Intel CPU models header

Comet Lake is the new 10th Gen Intel processor. Add two new CPU model
numbers to the Intel family list.

The CPU model numbers are not published in the SDM yet but they come
from an authoritative internal source.

 [ bp: Touch up commit message. ]

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Cc: ak@linux.intel.com
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86-ml <x86@kernel.org>
Link: https://lkml.kernel.org/r/1570549810-25049-2-git-send-email-kan.liang@linux.intel.com
---
 arch/x86/include/asm/intel-family.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index f04622500da3..c606c0b70738 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -83,6 +83,9 @@
 #define INTEL_FAM6_TIGERLAKE_L		0x8C
 #define INTEL_FAM6_TIGERLAKE		0x8D
 
+#define INTEL_FAM6_COMETLAKE		0xA5
+#define INTEL_FAM6_COMETLAKE_L		0xA6
+
 /* "Small Core" Processors (Atom) */
 
 #define INTEL_FAM6_ATOM_BONNELL		0x1C /* Diamondville, Pineview */
-- 
cgit v1.2.3


From 0a005856d35936e351cc20ff3de04499bd7ffbfd Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 23 Sep 2019 14:11:11 +0800
Subject: dm clone: Make __hash_find static

drivers/md/dm-clone-target.c:594:34: warning:
 symbol '__hash_find' was not declared. Should it be static?

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-clone-target.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index cd6f9e9fc98e..4ca8f1977222 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -591,8 +591,8 @@ static struct hash_table_bucket *get_hash_table_bucket(struct clone *clone,
  *
  * NOTE: Must be called with the bucket lock held
  */
-struct dm_clone_region_hydration *__hash_find(struct hash_table_bucket *bucket,
-					      unsigned long region_nr)
+static struct dm_clone_region_hydration *__hash_find(struct hash_table_bucket *bucket,
+						     unsigned long region_nr)
 {
 	struct dm_clone_region_hydration *hd;
 
-- 
cgit v1.2.3


From 232a6ebae419193f5b8da4fa869ae5089ab105c2 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Tue, 8 Oct 2019 17:01:14 +0100
Subject: drm/i915: introduce intel_memory_region

Support memory regions, as defined by a given (start, end), and allow
creating GEM objects which are backed by said region. The immediate goal
here is to have something to represent our device memory, but later on
we also want to represent every memory domain with a region, so stolen,
shmem, and of course device. At some point we are probably going to want
use a common struct here, such that we are better aligned with say TTM.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
Signed-off-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191008160116.18379-2-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/Makefile                      |   2 +
 drivers/gpu/drm/i915/gem/i915_gem_object_types.h   |   9 +
 drivers/gpu/drm/i915/gem/i915_gem_region.c         | 145 ++++++++++++++++
 drivers/gpu/drm/i915/gem/i915_gem_region.h         |  28 +++
 drivers/gpu/drm/i915/gem/selftests/huge_pages.c    |  78 +++++++++
 drivers/gpu/drm/i915/i915_drv.h                    |   1 +
 drivers/gpu/drm/i915/intel_memory_region.c         | 191 +++++++++++++++++++++
 drivers/gpu/drm/i915/intel_memory_region.h         |  83 +++++++++
 .../gpu/drm/i915/selftests/i915_mock_selftests.h   |   1 +
 .../gpu/drm/i915/selftests/intel_memory_region.c   | 115 +++++++++++++
 drivers/gpu/drm/i915/selftests/mock_gem_device.c   |   1 +
 drivers/gpu/drm/i915/selftests/mock_region.c       |  59 +++++++
 drivers/gpu/drm/i915/selftests/mock_region.h       |  16 ++
 13 files changed, 729 insertions(+)
 create mode 100644 drivers/gpu/drm/i915/gem/i915_gem_region.c
 create mode 100644 drivers/gpu/drm/i915/gem/i915_gem_region.h
 create mode 100644 drivers/gpu/drm/i915/intel_memory_region.c
 create mode 100644 drivers/gpu/drm/i915/intel_memory_region.h
 create mode 100644 drivers/gpu/drm/i915/selftests/intel_memory_region.c
 create mode 100644 drivers/gpu/drm/i915/selftests/mock_region.c
 create mode 100644 drivers/gpu/drm/i915/selftests/mock_region.h

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 45d3be12359d..b6a1fcb810c2 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -51,6 +51,7 @@ i915-y += i915_drv.o \
 	  i915_utils.o \
 	  intel_csr.o \
 	  intel_device_info.o \
+	  intel_memory_region.o \
 	  intel_pch.o \
 	  intel_pm.o \
 	  intel_runtime_pm.o \
@@ -121,6 +122,7 @@ gem-y += \
 	gem/i915_gem_pages.o \
 	gem/i915_gem_phys.o \
 	gem/i915_gem_pm.o \
+	gem/i915_gem_region.o \
 	gem/i915_gem_shmem.o \
 	gem/i915_gem_shrinker.o \
 	gem/i915_gem_stolen.o \
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index c00b4f077f9e..11390586cfe1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -160,6 +160,15 @@ struct drm_i915_gem_object {
 		atomic_t pages_pin_count;
 		atomic_t shrink_pin;
 
+		/**
+		 * Memory region for this object.
+		 */
+		struct intel_memory_region *region;
+		/**
+		 * List of memory region blocks allocated for this object.
+		 */
+		struct list_head blocks;
+
 		struct sg_table *pages;
 		void *mapping;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c
new file mode 100644
index 000000000000..6588e3c99e5d
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "intel_memory_region.h"
+#include "i915_gem_region.h"
+#include "i915_drv.h"
+
+void
+i915_gem_object_put_pages_buddy(struct drm_i915_gem_object *obj,
+				struct sg_table *pages)
+{
+	__intel_memory_region_put_pages_buddy(obj->mm.region, &obj->mm.blocks);
+
+	obj->mm.dirty = false;
+	sg_free_table(pages);
+	kfree(pages);
+}
+
+int
+i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj)
+{
+	struct intel_memory_region *mem = obj->mm.region;
+	struct list_head *blocks = &obj->mm.blocks;
+	unsigned int flags = I915_ALLOC_MIN_PAGE_SIZE;
+	resource_size_t size = obj->base.size;
+	resource_size_t prev_end;
+	struct i915_buddy_block *block;
+	struct sg_table *st;
+	struct scatterlist *sg;
+	unsigned int sg_page_sizes;
+	int ret;
+
+	st = kmalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		return -ENOMEM;
+
+	if (sg_alloc_table(st, size >> ilog2(mem->mm.chunk_size), GFP_KERNEL)) {
+		kfree(st);
+		return -ENOMEM;
+	}
+
+	ret = __intel_memory_region_get_pages_buddy(mem, size, flags, blocks);
+	if (ret)
+		goto err_free_sg;
+
+	GEM_BUG_ON(list_empty(blocks));
+
+	sg = st->sgl;
+	st->nents = 0;
+	sg_page_sizes = 0;
+	prev_end = (resource_size_t)-1;
+
+	list_for_each_entry(block, blocks, link) {
+		u64 block_size, offset;
+
+		block_size = i915_buddy_block_size(&mem->mm, block);
+		offset = i915_buddy_block_offset(block);
+
+		GEM_BUG_ON(overflows_type(block_size, sg->length));
+
+		if (offset != prev_end ||
+		    add_overflows_t(typeof(sg->length), sg->length, block_size)) {
+			if (st->nents) {
+				sg_page_sizes |= sg->length;
+				sg = __sg_next(sg);
+			}
+
+			sg_dma_address(sg) = mem->region.start + offset;
+			sg_dma_len(sg) = block_size;
+
+			sg->length = block_size;
+
+			st->nents++;
+		} else {
+			sg->length += block_size;
+			sg_dma_len(sg) += block_size;
+		}
+
+		prev_end = offset + block_size;
+	};
+
+	sg_page_sizes |= sg->length;
+	sg_mark_end(sg);
+	i915_sg_trim(st);
+
+	__i915_gem_object_set_pages(obj, st, sg_page_sizes);
+
+	return 0;
+
+err_free_sg:
+	sg_free_table(st);
+	kfree(st);
+	return ret;
+}
+
+void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj,
+					struct intel_memory_region *mem)
+{
+	INIT_LIST_HEAD(&obj->mm.blocks);
+	obj->mm.region = intel_memory_region_get(mem);
+}
+
+void i915_gem_object_release_memory_region(struct drm_i915_gem_object *obj)
+{
+	intel_memory_region_put(obj->mm.region);
+}
+
+struct drm_i915_gem_object *
+i915_gem_object_create_region(struct intel_memory_region *mem,
+			      resource_size_t size,
+			      unsigned int flags)
+{
+	struct drm_i915_gem_object *obj;
+
+	/*
+	 * NB: Our use of resource_size_t for the size stems from using struct
+	 * resource for the mem->region. We might need to revisit this in the
+	 * future.
+	 */
+
+	if (!mem)
+		return ERR_PTR(-ENODEV);
+
+	size = round_up(size, mem->min_page_size);
+
+	GEM_BUG_ON(!size);
+	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_MIN_ALIGNMENT));
+
+	/*
+	 * XXX: There is a prevalence of the assumption that we fit the
+	 * object's page count inside a 32bit _signed_ variable. Let's document
+	 * this and catch if we ever need to fix it. In the meantime, if you do
+	 * spot such a local variable, please consider fixing!
+	 */
+
+	if (size >> PAGE_SHIFT > INT_MAX)
+		return ERR_PTR(-E2BIG);
+
+	if (overflows_type(size, obj->base.size))
+		return ERR_PTR(-E2BIG);
+
+	return mem->ops->create_object(mem, size, flags);
+}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.h b/drivers/gpu/drm/i915/gem/i915_gem_region.h
new file mode 100644
index 000000000000..ebddc86d78f7
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __I915_GEM_REGION_H__
+#define __I915_GEM_REGION_H__
+
+#include <linux/types.h>
+
+struct intel_memory_region;
+struct drm_i915_gem_object;
+struct sg_table;
+
+int i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj);
+void i915_gem_object_put_pages_buddy(struct drm_i915_gem_object *obj,
+				     struct sg_table *pages);
+
+void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj,
+					struct intel_memory_region *mem);
+void i915_gem_object_release_memory_region(struct drm_i915_gem_object *obj);
+
+struct drm_i915_gem_object *
+i915_gem_object_create_region(struct intel_memory_region *mem,
+			      resource_size_t size,
+			      unsigned int flags);
+
+#endif
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index e42abddd4a36..b4c390e9fa50 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -8,6 +8,7 @@
 
 #include "i915_selftest.h"
 
+#include "gem/i915_gem_region.h"
 #include "gem/i915_gem_pm.h"
 
 #include "gt/intel_gt.h"
@@ -17,6 +18,7 @@
 
 #include "selftests/mock_drm.h"
 #include "selftests/mock_gem_device.h"
+#include "selftests/mock_region.h"
 #include "selftests/i915_random.h"
 
 static const unsigned int page_sizes[] = {
@@ -452,6 +454,81 @@ out_device:
 	return err;
 }
 
+static int igt_mock_memory_region_huge_pages(void *arg)
+{
+	struct i915_ppgtt *ppgtt = arg;
+	struct drm_i915_private *i915 = ppgtt->vm.i915;
+	unsigned long supported = INTEL_INFO(i915)->page_sizes;
+	struct intel_memory_region *mem;
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int bit;
+	int err = 0;
+
+	mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0);
+	if (IS_ERR(mem)) {
+		pr_err("%s failed to create memory region\n", __func__);
+		return PTR_ERR(mem);
+	}
+
+	for_each_set_bit(bit, &supported, ilog2(I915_GTT_MAX_PAGE_SIZE) + 1) {
+		unsigned int page_size = BIT(bit);
+		resource_size_t phys;
+
+		obj = i915_gem_object_create_region(mem, page_size, 0);
+		if (IS_ERR(obj)) {
+			err = PTR_ERR(obj);
+			goto out_region;
+		}
+
+		vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
+		if (IS_ERR(vma)) {
+			err = PTR_ERR(vma);
+			goto out_put;
+		}
+
+		err = i915_vma_pin(vma, 0, 0, PIN_USER);
+		if (err)
+			goto out_close;
+
+		err = igt_check_page_sizes(vma);
+		if (err)
+			goto out_unpin;
+
+		phys = i915_gem_object_get_dma_address(obj, 0);
+		if (!IS_ALIGNED(phys, page_size)) {
+			pr_err("%s addr misaligned(%pa) page_size=%u\n",
+			       __func__, &phys, page_size);
+			err = -EINVAL;
+			goto out_unpin;
+		}
+
+		if (vma->page_sizes.gtt != page_size) {
+			pr_err("%s page_sizes.gtt=%u, expected=%u\n",
+			       __func__, vma->page_sizes.gtt, page_size);
+			err = -EINVAL;
+			goto out_unpin;
+		}
+
+		i915_vma_unpin(vma);
+		i915_vma_close(vma);
+
+		i915_gem_object_put(obj);
+	}
+
+	goto out_region;
+
+out_unpin:
+	i915_vma_unpin(vma);
+out_close:
+	i915_vma_close(vma);
+out_put:
+	i915_gem_object_put(obj);
+out_region:
+	intel_memory_region_put(mem);
+	return err;
+}
+
 static int igt_mock_ppgtt_misaligned_dma(void *arg)
 {
 	struct i915_ppgtt *ppgtt = arg;
@@ -1623,6 +1700,7 @@ int i915_gem_huge_page_mock_selftests(void)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_mock_exhaust_device_supported_pages),
+		SUBTEST(igt_mock_memory_region_huge_pages),
 		SUBTEST(igt_mock_ppgtt_misaligned_dma),
 		SUBTEST(igt_mock_ppgtt_huge_fill),
 		SUBTEST(igt_mock_ppgtt_64K),
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index bcfb355aab4d..d284b04c492b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -85,6 +85,7 @@
 #include "intel_device_info.h"
 #include "intel_pch.h"
 #include "intel_runtime_pm.h"
+#include "intel_memory_region.h"
 #include "intel_uncore.h"
 #include "intel_wakeref.h"
 #include "intel_wopcm.h"
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
new file mode 100644
index 000000000000..2ef67c397fca
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "intel_memory_region.h"
+#include "i915_drv.h"
+
+static u64
+intel_memory_region_free_pages(struct intel_memory_region *mem,
+			       struct list_head *blocks)
+{
+	struct i915_buddy_block *block, *on;
+	u64 size = 0;
+
+	list_for_each_entry_safe(block, on, blocks, link) {
+		size += i915_buddy_block_size(&mem->mm, block);
+		i915_buddy_free(&mem->mm, block);
+	}
+	INIT_LIST_HEAD(blocks);
+
+	return size;
+}
+
+void
+__intel_memory_region_put_pages_buddy(struct intel_memory_region *mem,
+				      struct list_head *blocks)
+{
+	mutex_lock(&mem->mm_lock);
+	intel_memory_region_free_pages(mem, blocks);
+	mutex_unlock(&mem->mm_lock);
+}
+
+void
+__intel_memory_region_put_block_buddy(struct i915_buddy_block *block)
+{
+	struct list_head blocks;
+
+	INIT_LIST_HEAD(&blocks);
+	list_add(&block->link, &blocks);
+	__intel_memory_region_put_pages_buddy(block->private, &blocks);
+}
+
+int
+__intel_memory_region_get_pages_buddy(struct intel_memory_region *mem,
+				      resource_size_t size,
+				      unsigned int flags,
+				      struct list_head *blocks)
+{
+	unsigned long n_pages = size >> ilog2(mem->mm.chunk_size);
+	unsigned int min_order = 0;
+
+	GEM_BUG_ON(!IS_ALIGNED(size, mem->mm.chunk_size));
+	GEM_BUG_ON(!list_empty(blocks));
+
+	if (flags & I915_ALLOC_MIN_PAGE_SIZE) {
+		min_order = ilog2(mem->min_page_size) -
+			    ilog2(mem->mm.chunk_size);
+	}
+
+	mutex_lock(&mem->mm_lock);
+
+	do {
+		struct i915_buddy_block *block;
+		unsigned int order;
+
+		order = fls(n_pages) - 1;
+		GEM_BUG_ON(order > mem->mm.max_order);
+		GEM_BUG_ON(order < min_order);
+
+		do {
+			block = i915_buddy_alloc(&mem->mm, order);
+			if (!IS_ERR(block))
+				break;
+
+			if (order-- == min_order)
+				goto err_free_blocks;
+		} while (1);
+
+		n_pages -= BIT(order);
+
+		block->private = mem;
+		list_add(&block->link, blocks);
+
+		if (!n_pages)
+			break;
+	} while (1);
+
+	mutex_unlock(&mem->mm_lock);
+	return 0;
+
+err_free_blocks:
+	intel_memory_region_free_pages(mem, blocks);
+	mutex_unlock(&mem->mm_lock);
+	return -ENXIO;
+}
+
+struct i915_buddy_block *
+__intel_memory_region_get_block_buddy(struct intel_memory_region *mem,
+				      resource_size_t size,
+				      unsigned int flags)
+{
+	struct i915_buddy_block *block;
+	LIST_HEAD(blocks);
+	int ret;
+
+	ret = __intel_memory_region_get_pages_buddy(mem, size, flags, &blocks);
+	if (ret)
+		return ERR_PTR(ret);
+
+	block = list_first_entry(&blocks, typeof(*block), link);
+	list_del_init(&block->link);
+	return block;
+}
+
+int intel_memory_region_init_buddy(struct intel_memory_region *mem)
+{
+	return i915_buddy_init(&mem->mm, resource_size(&mem->region),
+			       PAGE_SIZE);
+}
+
+void intel_memory_region_release_buddy(struct intel_memory_region *mem)
+{
+	i915_buddy_fini(&mem->mm);
+}
+
+struct intel_memory_region *
+intel_memory_region_create(struct drm_i915_private *i915,
+			   resource_size_t start,
+			   resource_size_t size,
+			   resource_size_t min_page_size,
+			   resource_size_t io_start,
+			   const struct intel_memory_region_ops *ops)
+{
+	struct intel_memory_region *mem;
+	int err;
+
+	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
+	if (!mem)
+		return ERR_PTR(-ENOMEM);
+
+	mem->i915 = i915;
+	mem->region = (struct resource)DEFINE_RES_MEM(start, size);
+	mem->io_start = io_start;
+	mem->min_page_size = min_page_size;
+	mem->ops = ops;
+
+	mutex_init(&mem->mm_lock);
+
+	if (ops->init) {
+		err = ops->init(mem);
+		if (err)
+			goto err_free;
+	}
+
+	kref_init(&mem->kref);
+	return mem;
+
+err_free:
+	kfree(mem);
+	return ERR_PTR(err);
+}
+
+static void __intel_memory_region_destroy(struct kref *kref)
+{
+	struct intel_memory_region *mem =
+		container_of(kref, typeof(*mem), kref);
+
+	if (mem->ops->release)
+		mem->ops->release(mem);
+
+	mutex_destroy(&mem->mm_lock);
+	kfree(mem);
+}
+
+struct intel_memory_region *
+intel_memory_region_get(struct intel_memory_region *mem)
+{
+	kref_get(&mem->kref);
+	return mem;
+}
+
+void intel_memory_region_put(struct intel_memory_region *mem)
+{
+	kref_put(&mem->kref, __intel_memory_region_destroy);
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/intel_memory_region.c"
+#include "selftests/mock_region.c"
+#endif
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
new file mode 100644
index 000000000000..2ea17d6c31ed
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __INTEL_MEMORY_REGION_H__
+#define __INTEL_MEMORY_REGION_H__
+
+#include <linux/kref.h>
+#include <linux/ioport.h>
+#include <linux/mutex.h>
+#include <linux/io-mapping.h>
+
+#include "i915_buddy.h"
+
+struct drm_i915_private;
+struct drm_i915_gem_object;
+struct intel_memory_region;
+struct sg_table;
+
+#define I915_ALLOC_MIN_PAGE_SIZE   BIT(0)
+
+struct intel_memory_region_ops {
+	unsigned int flags;
+
+	int (*init)(struct intel_memory_region *mem);
+	void (*release)(struct intel_memory_region *mem);
+
+	struct drm_i915_gem_object *
+	(*create_object)(struct intel_memory_region *mem,
+			 resource_size_t size,
+			 unsigned int flags);
+};
+
+struct intel_memory_region {
+	struct drm_i915_private *i915;
+
+	const struct intel_memory_region_ops *ops;
+
+	struct io_mapping iomap;
+	struct resource region;
+
+	struct i915_buddy_mm mm;
+	struct mutex mm_lock;
+
+	struct kref kref;
+
+	resource_size_t io_start;
+	resource_size_t min_page_size;
+
+	unsigned int type;
+	unsigned int instance;
+	unsigned int id;
+};
+
+int intel_memory_region_init_buddy(struct intel_memory_region *mem);
+void intel_memory_region_release_buddy(struct intel_memory_region *mem);
+
+int __intel_memory_region_get_pages_buddy(struct intel_memory_region *mem,
+					  resource_size_t size,
+					  unsigned int flags,
+					  struct list_head *blocks);
+struct i915_buddy_block *
+__intel_memory_region_get_block_buddy(struct intel_memory_region *mem,
+				      resource_size_t size,
+				      unsigned int flags);
+void __intel_memory_region_put_pages_buddy(struct intel_memory_region *mem,
+					   struct list_head *blocks);
+void __intel_memory_region_put_block_buddy(struct i915_buddy_block *block);
+
+struct intel_memory_region *
+intel_memory_region_create(struct drm_i915_private *i915,
+			   resource_size_t start,
+			   resource_size_t size,
+			   resource_size_t min_page_size,
+			   resource_size_t io_start,
+			   const struct intel_memory_region_ops *ops);
+
+struct intel_memory_region *
+intel_memory_region_get(struct intel_memory_region *mem);
+void intel_memory_region_put(struct intel_memory_region *mem);
+
+#endif
diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
index b88084fe3269..aa5a0e7f5d9e 100644
--- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
@@ -26,3 +26,4 @@ selftest(gtt, i915_gem_gtt_mock_selftests)
 selftest(hugepages, i915_gem_huge_page_mock_selftests)
 selftest(contexts, i915_gem_context_mock_selftests)
 selftest(buddy, i915_buddy_mock_selftests)
+selftest(memory_region, intel_memory_region_mock_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
new file mode 100644
index 000000000000..89eaa419eaf2
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/prime_numbers.h>
+
+#include "../i915_selftest.h"
+
+#include "mock_drm.h"
+#include "mock_gem_device.h"
+#include "mock_region.h"
+
+#include "gem/i915_gem_region.h"
+#include "gem/selftests/mock_context.h"
+
+static void close_objects(struct intel_memory_region *mem,
+			  struct list_head *objects)
+{
+	struct drm_i915_private *i915 = mem->i915;
+	struct drm_i915_gem_object *obj, *on;
+
+	list_for_each_entry_safe(obj, on, objects, st_link) {
+		if (i915_gem_object_has_pinned_pages(obj))
+			i915_gem_object_unpin_pages(obj);
+		/* No polluting the memory region between tests */
+		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+		list_del(&obj->st_link);
+		i915_gem_object_put(obj);
+	}
+
+	cond_resched();
+
+	i915_gem_drain_freed_objects(i915);
+}
+
+static int igt_mock_fill(void *arg)
+{
+	struct intel_memory_region *mem = arg;
+	resource_size_t total = resource_size(&mem->region);
+	resource_size_t page_size;
+	resource_size_t rem;
+	unsigned long max_pages;
+	unsigned long page_num;
+	LIST_HEAD(objects);
+	int err = 0;
+
+	page_size = mem->mm.chunk_size;
+	max_pages = div64_u64(total, page_size);
+	rem = total;
+
+	for_each_prime_number_from(page_num, 1, max_pages) {
+		resource_size_t size = page_num * page_size;
+		struct drm_i915_gem_object *obj;
+
+		obj = i915_gem_object_create_region(mem, size, 0);
+		if (IS_ERR(obj)) {
+			err = PTR_ERR(obj);
+			break;
+		}
+
+		err = i915_gem_object_pin_pages(obj);
+		if (err) {
+			i915_gem_object_put(obj);
+			break;
+		}
+
+		list_add(&obj->st_link, &objects);
+		rem -= size;
+	}
+
+	if (err == -ENOMEM)
+		err = 0;
+	if (err == -ENXIO) {
+		if (page_num * page_size <= rem) {
+			pr_err("%s failed, space still left in region\n",
+			       __func__);
+			err = -EINVAL;
+		} else {
+			err = 0;
+		}
+	}
+
+	close_objects(mem, &objects);
+
+	return err;
+}
+
+int intel_memory_region_mock_selftests(void)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_mock_fill),
+	};
+	struct intel_memory_region *mem;
+	struct drm_i915_private *i915;
+	int err;
+
+	i915 = mock_gem_device();
+	if (!i915)
+		return -ENOMEM;
+
+	mem = mock_region_create(i915, 0, SZ_2G, I915_GTT_PAGE_SIZE_4K, 0);
+	if (IS_ERR(mem)) {
+		pr_err("failed to create memory region\n");
+		err = PTR_ERR(mem);
+		goto out_unref;
+	}
+
+	err = i915_subtests(tests, mem);
+
+	intel_memory_region_put(mem);
+out_unref:
+	drm_dev_put(&i915->drm);
+	return err;
+}
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index d14c6d8735fe..9c22d41b30cd 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -33,6 +33,7 @@
 #include "mock_gem_device.h"
 #include "mock_gtt.h"
 #include "mock_uncore.h"
+#include "mock_region.h"
 
 #include "gem/selftests/mock_context.h"
 #include "gem/selftests/mock_gem_object.h"
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c
new file mode 100644
index 000000000000..0e9a575ede3b
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/mock_region.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "gem/i915_gem_region.h"
+#include "intel_memory_region.h"
+
+#include "mock_region.h"
+
+static const struct drm_i915_gem_object_ops mock_region_obj_ops = {
+	.get_pages = i915_gem_object_get_pages_buddy,
+	.put_pages = i915_gem_object_put_pages_buddy,
+	.release = i915_gem_object_release_memory_region,
+};
+
+static struct drm_i915_gem_object *
+mock_object_create(struct intel_memory_region *mem,
+		   resource_size_t size,
+		   unsigned int flags)
+{
+	struct drm_i915_private *i915 = mem->i915;
+	struct drm_i915_gem_object *obj;
+
+	if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size)
+		return ERR_PTR(-E2BIG);
+
+	obj = i915_gem_object_alloc();
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+
+	drm_gem_private_object_init(&i915->drm, &obj->base, size);
+	i915_gem_object_init(obj, &mock_region_obj_ops);
+
+	obj->read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT;
+
+	i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
+
+	i915_gem_object_init_memory_region(obj, mem);
+
+	return obj;
+}
+
+static const struct intel_memory_region_ops mock_region_ops = {
+	.init = intel_memory_region_init_buddy,
+	.release = intel_memory_region_release_buddy,
+	.create_object = mock_object_create,
+};
+
+struct intel_memory_region *
+mock_region_create(struct drm_i915_private *i915,
+		   resource_size_t start,
+		   resource_size_t size,
+		   resource_size_t min_page_size,
+		   resource_size_t io_start)
+{
+	return intel_memory_region_create(i915, start, size, min_page_size,
+					  io_start, &mock_region_ops);
+}
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.h b/drivers/gpu/drm/i915/selftests/mock_region.h
new file mode 100644
index 000000000000..24608089d833
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/mock_region.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __MOCK_REGION_H
+#define __MOCK_REGION_H
+
+struct intel_memory_region *
+mock_region_create(struct drm_i915_private *i915,
+		   resource_size_t start,
+		   resource_size_t size,
+		   resource_size_t min_page_size,
+		   resource_size_t io_start);
+
+#endif /* !__MOCK_REGION_H */
-- 
cgit v1.2.3


From 2f0b97ca02118630132dddf258fbdb5d5f5ec32a Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Tue, 8 Oct 2019 17:01:15 +0100
Subject: drm/i915/region: support contiguous allocations

Some kernel internal objects may need to be allocated as a contiguous
block, also thinking ahead the various kernel io_mapping interfaces seem
to expect it, although this is purely a limitation in the kernel
API...so perhaps something to be improved.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
Cc: Michael J Ruhl <michael.j.ruhl@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191008160116.18379-3-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/gem/i915_gem_object.h         |   6 +
 drivers/gpu/drm/i915/gem/i915_gem_object_types.h   |   4 +
 drivers/gpu/drm/i915/gem/i915_gem_region.c         |  15 +-
 drivers/gpu/drm/i915/gem/i915_gem_region.h         |   3 +-
 drivers/gpu/drm/i915/gem/selftests/huge_pages.c    |  71 +++++----
 drivers/gpu/drm/i915/intel_memory_region.c         |   9 +-
 drivers/gpu/drm/i915/intel_memory_region.h         |   3 +-
 .../gpu/drm/i915/selftests/intel_memory_region.c   | 165 +++++++++++++++++++++
 drivers/gpu/drm/i915/selftests/mock_region.c       |   2 +-
 9 files changed, 239 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 086a9bf5adcc..dfd16d65630f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -139,6 +139,12 @@ i915_gem_object_is_readonly(const struct drm_i915_gem_object *obj)
 	return obj->base.vma_node.readonly;
 }
 
+static inline bool
+i915_gem_object_is_contiguous(const struct drm_i915_gem_object *obj)
+{
+	return obj->flags & I915_BO_ALLOC_CONTIGUOUS;
+}
+
 static inline bool
 i915_gem_object_type_has(const struct drm_i915_gem_object *obj,
 			 unsigned long flags)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index 11390586cfe1..c6a712cf7d7a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -119,6 +119,10 @@ struct drm_i915_gem_object {
 
 	I915_SELFTEST_DECLARE(struct list_head st_link);
 
+	unsigned long flags;
+#define I915_BO_ALLOC_CONTIGUOUS BIT(0)
+#define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS)
+
 	/*
 	 * Is the object to be mapped as read-only to the GPU
 	 * Only honoured if hardware has relevant pte bit
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c
index 6588e3c99e5d..d94914a86737 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_region.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c
@@ -23,10 +23,10 @@ i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj)
 {
 	struct intel_memory_region *mem = obj->mm.region;
 	struct list_head *blocks = &obj->mm.blocks;
-	unsigned int flags = I915_ALLOC_MIN_PAGE_SIZE;
 	resource_size_t size = obj->base.size;
 	resource_size_t prev_end;
 	struct i915_buddy_block *block;
+	unsigned int flags;
 	struct sg_table *st;
 	struct scatterlist *sg;
 	unsigned int sg_page_sizes;
@@ -41,6 +41,10 @@ i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj)
 		return -ENOMEM;
 	}
 
+	flags = I915_ALLOC_MIN_PAGE_SIZE;
+	if (obj->flags & I915_BO_ALLOC_CONTIGUOUS)
+		flags |= I915_ALLOC_CONTIGUOUS;
+
 	ret = __intel_memory_region_get_pages_buddy(mem, size, flags, blocks);
 	if (ret)
 		goto err_free_sg;
@@ -55,7 +59,8 @@ i915_gem_object_get_pages_buddy(struct drm_i915_gem_object *obj)
 	list_for_each_entry(block, blocks, link) {
 		u64 block_size, offset;
 
-		block_size = i915_buddy_block_size(&mem->mm, block);
+		block_size = min_t(u64, size,
+				   i915_buddy_block_size(&mem->mm, block));
 		offset = i915_buddy_block_offset(block);
 
 		GEM_BUG_ON(overflows_type(block_size, sg->length));
@@ -96,10 +101,12 @@ err_free_sg:
 }
 
 void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj,
-					struct intel_memory_region *mem)
+					struct intel_memory_region *mem,
+					unsigned long flags)
 {
 	INIT_LIST_HEAD(&obj->mm.blocks);
 	obj->mm.region = intel_memory_region_get(mem);
+	obj->flags |= flags;
 }
 
 void i915_gem_object_release_memory_region(struct drm_i915_gem_object *obj)
@@ -120,6 +127,8 @@ i915_gem_object_create_region(struct intel_memory_region *mem,
 	 * future.
 	 */
 
+	GEM_BUG_ON(flags & ~I915_BO_ALLOC_FLAGS);
+
 	if (!mem)
 		return ERR_PTR(-ENODEV);
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.h b/drivers/gpu/drm/i915/gem/i915_gem_region.h
index ebddc86d78f7..f2ff6f8bff74 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_region.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.h
@@ -17,7 +17,8 @@ void i915_gem_object_put_pages_buddy(struct drm_i915_gem_object *obj,
 				     struct sg_table *pages);
 
 void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj,
-					struct intel_memory_region *mem);
+					struct intel_memory_region *mem,
+					unsigned long flags);
 void i915_gem_object_release_memory_region(struct drm_i915_gem_object *obj);
 
 struct drm_i915_gem_object *
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index b4c390e9fa50..63a4743e5f54 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -456,6 +456,7 @@ out_device:
 
 static int igt_mock_memory_region_huge_pages(void *arg)
 {
+	const unsigned int flags[] = { 0, I915_BO_ALLOC_CONTIGUOUS };
 	struct i915_ppgtt *ppgtt = arg;
 	struct drm_i915_private *i915 = ppgtt->vm.i915;
 	unsigned long supported = INTEL_INFO(i915)->page_sizes;
@@ -474,46 +475,52 @@ static int igt_mock_memory_region_huge_pages(void *arg)
 	for_each_set_bit(bit, &supported, ilog2(I915_GTT_MAX_PAGE_SIZE) + 1) {
 		unsigned int page_size = BIT(bit);
 		resource_size_t phys;
+		int i;
 
-		obj = i915_gem_object_create_region(mem, page_size, 0);
-		if (IS_ERR(obj)) {
-			err = PTR_ERR(obj);
-			goto out_region;
-		}
+		for (i = 0; i < ARRAY_SIZE(flags); ++i) {
+			obj = i915_gem_object_create_region(mem, page_size,
+							    flags[i]);
+			if (IS_ERR(obj)) {
+				err = PTR_ERR(obj);
+				goto out_region;
+			}
 
-		vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
-		if (IS_ERR(vma)) {
-			err = PTR_ERR(vma);
-			goto out_put;
-		}
+			vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
+			if (IS_ERR(vma)) {
+				err = PTR_ERR(vma);
+				goto out_put;
+			}
 
-		err = i915_vma_pin(vma, 0, 0, PIN_USER);
-		if (err)
-			goto out_close;
+			err = i915_vma_pin(vma, 0, 0, PIN_USER);
+			if (err)
+				goto out_close;
 
-		err = igt_check_page_sizes(vma);
-		if (err)
-			goto out_unpin;
+			err = igt_check_page_sizes(vma);
+			if (err)
+				goto out_unpin;
 
-		phys = i915_gem_object_get_dma_address(obj, 0);
-		if (!IS_ALIGNED(phys, page_size)) {
-			pr_err("%s addr misaligned(%pa) page_size=%u\n",
-			       __func__, &phys, page_size);
-			err = -EINVAL;
-			goto out_unpin;
-		}
+			phys = i915_gem_object_get_dma_address(obj, 0);
+			if (!IS_ALIGNED(phys, page_size)) {
+				pr_err("%s addr misaligned(%pa) page_size=%u\n",
+				       __func__, &phys, page_size);
+				err = -EINVAL;
+				goto out_unpin;
+			}
 
-		if (vma->page_sizes.gtt != page_size) {
-			pr_err("%s page_sizes.gtt=%u, expected=%u\n",
-			       __func__, vma->page_sizes.gtt, page_size);
-			err = -EINVAL;
-			goto out_unpin;
-		}
+			if (vma->page_sizes.gtt != page_size) {
+				pr_err("%s page_sizes.gtt=%u, expected=%u\n",
+				       __func__, vma->page_sizes.gtt,
+				       page_size);
+				err = -EINVAL;
+				goto out_unpin;
+			}
 
-		i915_vma_unpin(vma);
-		i915_vma_close(vma);
+			i915_vma_unpin(vma);
+			i915_vma_close(vma);
 
-		i915_gem_object_put(obj);
+			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+			i915_gem_object_put(obj);
+		}
 	}
 
 	goto out_region;
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index 2ef67c397fca..98006618e871 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -47,8 +47,8 @@ __intel_memory_region_get_pages_buddy(struct intel_memory_region *mem,
 				      unsigned int flags,
 				      struct list_head *blocks)
 {
-	unsigned long n_pages = size >> ilog2(mem->mm.chunk_size);
 	unsigned int min_order = 0;
+	unsigned long n_pages;
 
 	GEM_BUG_ON(!IS_ALIGNED(size, mem->mm.chunk_size));
 	GEM_BUG_ON(!list_empty(blocks));
@@ -58,6 +58,13 @@ __intel_memory_region_get_pages_buddy(struct intel_memory_region *mem,
 			    ilog2(mem->mm.chunk_size);
 	}
 
+	if (flags & I915_ALLOC_CONTIGUOUS) {
+		size = roundup_pow_of_two(size);
+		min_order = ilog2(size) - ilog2(mem->mm.chunk_size);
+	}
+
+	n_pages = size >> ilog2(mem->mm.chunk_size);
+
 	mutex_lock(&mem->mm_lock);
 
 	do {
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index 2ea17d6c31ed..29b86ca17dd9 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -18,7 +18,8 @@ struct drm_i915_gem_object;
 struct intel_memory_region;
 struct sg_table;
 
-#define I915_ALLOC_MIN_PAGE_SIZE   BIT(0)
+#define I915_ALLOC_MIN_PAGE_SIZE  BIT(0)
+#define I915_ALLOC_CONTIGUOUS     BIT(1)
 
 struct intel_memory_region_ops {
 	unsigned int flags;
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 89eaa419eaf2..4e44c81e8e5b 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -13,6 +13,7 @@
 
 #include "gem/i915_gem_region.h"
 #include "gem/selftests/mock_context.h"
+#include "selftests/i915_random.h"
 
 static void close_objects(struct intel_memory_region *mem,
 			  struct list_head *objects)
@@ -86,10 +87,174 @@ static int igt_mock_fill(void *arg)
 	return err;
 }
 
+static struct drm_i915_gem_object *
+igt_object_create(struct intel_memory_region *mem,
+		  struct list_head *objects,
+		  u64 size,
+		  unsigned int flags)
+{
+	struct drm_i915_gem_object *obj;
+	int err;
+
+	obj = i915_gem_object_create_region(mem, size, flags);
+	if (IS_ERR(obj))
+		return obj;
+
+	err = i915_gem_object_pin_pages(obj);
+	if (err)
+		goto put;
+
+	list_add(&obj->st_link, objects);
+	return obj;
+
+put:
+	i915_gem_object_put(obj);
+	return ERR_PTR(err);
+}
+
+static void igt_object_release(struct drm_i915_gem_object *obj)
+{
+	i915_gem_object_unpin_pages(obj);
+	__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+	list_del(&obj->st_link);
+	i915_gem_object_put(obj);
+}
+
+static int igt_mock_contiguous(void *arg)
+{
+	struct intel_memory_region *mem = arg;
+	struct drm_i915_gem_object *obj;
+	unsigned long n_objects;
+	LIST_HEAD(objects);
+	LIST_HEAD(holes);
+	I915_RND_STATE(prng);
+	resource_size_t target;
+	resource_size_t total;
+	resource_size_t min;
+	int err = 0;
+
+	total = resource_size(&mem->region);
+
+	/* Min size */
+	obj = igt_object_create(mem, &objects, mem->mm.chunk_size,
+				I915_BO_ALLOC_CONTIGUOUS);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	if (obj->mm.pages->nents != 1) {
+		pr_err("%s min object spans multiple sg entries\n", __func__);
+		err = -EINVAL;
+		goto err_close_objects;
+	}
+
+	igt_object_release(obj);
+
+	/* Max size */
+	obj = igt_object_create(mem, &objects, total, I915_BO_ALLOC_CONTIGUOUS);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	if (obj->mm.pages->nents != 1) {
+		pr_err("%s max object spans multiple sg entries\n", __func__);
+		err = -EINVAL;
+		goto err_close_objects;
+	}
+
+	igt_object_release(obj);
+
+	/* Internal fragmentation should not bleed into the object size */
+	target = round_up(prandom_u32_state(&prng) % total, PAGE_SIZE);
+	target = max_t(u64, PAGE_SIZE, target);
+
+	obj = igt_object_create(mem, &objects, target,
+				I915_BO_ALLOC_CONTIGUOUS);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	if (obj->base.size != target) {
+		pr_err("%s obj->base.size(%llx) != target(%llx)\n", __func__,
+		       (u64)obj->base.size, (u64)target);
+		err = -EINVAL;
+		goto err_close_objects;
+	}
+
+	if (obj->mm.pages->nents != 1) {
+		pr_err("%s object spans multiple sg entries\n", __func__);
+		err = -EINVAL;
+		goto err_close_objects;
+	}
+
+	igt_object_release(obj);
+
+	/*
+	 * Try to fragment the address space, such that half of it is free, but
+	 * the max contiguous block size is SZ_64K.
+	 */
+
+	target = SZ_64K;
+	n_objects = div64_u64(total, target);
+
+	while (n_objects--) {
+		struct list_head *list;
+
+		if (n_objects % 2)
+			list = &holes;
+		else
+			list = &objects;
+
+		obj = igt_object_create(mem, list, target,
+					I915_BO_ALLOC_CONTIGUOUS);
+		if (IS_ERR(obj)) {
+			err = PTR_ERR(obj);
+			goto err_close_objects;
+		}
+	}
+
+	close_objects(mem, &holes);
+
+	min = target;
+	target = total >> 1;
+
+	/* Make sure we can still allocate all the fragmented space */
+	obj = igt_object_create(mem, &objects, target, 0);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto err_close_objects;
+	}
+
+	igt_object_release(obj);
+
+	/*
+	 * Even though we have enough free space, we don't have a big enough
+	 * contiguous block. Make sure that holds true.
+	 */
+
+	do {
+		bool should_fail = target > min;
+
+		obj = igt_object_create(mem, &objects, target,
+					I915_BO_ALLOC_CONTIGUOUS);
+		if (should_fail != IS_ERR(obj)) {
+			pr_err("%s target allocation(%llx) mismatch\n",
+			       __func__, (u64)target);
+			err = -EINVAL;
+			goto err_close_objects;
+		}
+
+		target >>= 1;
+	} while (target >= mem->mm.chunk_size);
+
+err_close_objects:
+	list_splice_tail(&holes, &objects);
+	close_objects(mem, &objects);
+	return err;
+}
+
 int intel_memory_region_mock_selftests(void)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_mock_fill),
+		SUBTEST(igt_mock_contiguous),
 	};
 	struct intel_memory_region *mem;
 	struct drm_i915_private *i915;
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c
index 0e9a575ede3b..7b0c99ddc2d5 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.c
+++ b/drivers/gpu/drm/i915/selftests/mock_region.c
@@ -36,7 +36,7 @@ mock_object_create(struct intel_memory_region *mem,
 
 	i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
 
-	i915_gem_object_init_memory_region(obj, mem);
+	i915_gem_object_init_memory_region(obj, mem, flags);
 
 	return obj;
 }
-- 
cgit v1.2.3


From 7c98501acb94318819f5ea764fc3aae09f69aff6 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Tue, 8 Oct 2019 17:01:16 +0100
Subject: drm/i915/region: support volatile objects

Volatile objects are marked as DONTNEED while pinned, therefore once
unpinned the backing store can be discarded. This is limited to kernel
internal objects.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: CQ Tang <cq.tang@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191008160116.18379-4-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/gem/i915_gem_internal.c     | 17 +++++++++--------
 drivers/gpu/drm/i915/gem/i915_gem_object.h       | 12 ++++++++++++
 drivers/gpu/drm/i915/gem/i915_gem_object_types.h |  9 ++++++++-
 drivers/gpu/drm/i915/gem/i915_gem_pages.c        |  6 ++++++
 drivers/gpu/drm/i915/gem/i915_gem_region.c       | 17 ++++++++++++++++-
 drivers/gpu/drm/i915/gem/selftests/huge_pages.c  | 12 ++++--------
 drivers/gpu/drm/i915/intel_memory_region.c       |  5 +++++
 drivers/gpu/drm/i915/intel_memory_region.h       |  6 ++++++
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c    |  5 ++---
 9 files changed, 68 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
index 0c41e04ab8fa..5ae694c24df4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
@@ -117,13 +117,6 @@ create_st:
 		goto err;
 	}
 
-	/* Mark the pages as dontneed whilst they are still pinned. As soon
-	 * as they are unpinned they are allowed to be reaped by the shrinker,
-	 * and the caller is expected to repopulate - the contents of this
-	 * object are only valid whilst active and pinned.
-	 */
-	obj->mm.madv = I915_MADV_DONTNEED;
-
 	__i915_gem_object_set_pages(obj, st, sg_page_sizes);
 
 	return 0;
@@ -143,7 +136,6 @@ static void i915_gem_object_put_pages_internal(struct drm_i915_gem_object *obj,
 	internal_free_pages(pages);
 
 	obj->mm.dirty = false;
-	obj->mm.madv = I915_MADV_WILLNEED;
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_object_internal_ops = {
@@ -188,6 +180,15 @@ i915_gem_object_create_internal(struct drm_i915_private *i915,
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
 	i915_gem_object_init(obj, &i915_gem_object_internal_ops);
 
+	/*
+	 * Mark the object as volatile, such that the pages are marked as
+	 * dontneed whilst they are still pinned. As soon as they are unpinned
+	 * they are allowed to be reaped by the shrinker, and the caller is
+	 * expected to repopulate - the contents of this object are only valid
+	 * whilst active and pinned.
+	 */
+	i915_gem_object_set_volatile(obj);
+
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index dfd16d65630f..c5e14c9c805c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -145,6 +145,18 @@ i915_gem_object_is_contiguous(const struct drm_i915_gem_object *obj)
 	return obj->flags & I915_BO_ALLOC_CONTIGUOUS;
 }
 
+static inline bool
+i915_gem_object_is_volatile(const struct drm_i915_gem_object *obj)
+{
+	return obj->flags & I915_BO_ALLOC_VOLATILE;
+}
+
+static inline void
+i915_gem_object_set_volatile(struct drm_i915_gem_object *obj)
+{
+	obj->flags |= I915_BO_ALLOC_VOLATILE;
+}
+
 static inline bool
 i915_gem_object_type_has(const struct drm_i915_gem_object *obj,
 			 unsigned long flags)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index c6a712cf7d7a..a387e3ee728b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -121,7 +121,8 @@ struct drm_i915_gem_object {
 
 	unsigned long flags;
 #define I915_BO_ALLOC_CONTIGUOUS BIT(0)
-#define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS)
+#define I915_BO_ALLOC_VOLATILE   BIT(1)
+#define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | I915_BO_ALLOC_VOLATILE)
 
 	/*
 	 * Is the object to be mapped as read-only to the GPU
@@ -172,6 +173,12 @@ struct drm_i915_gem_object {
 		 * List of memory region blocks allocated for this object.
 		 */
 		struct list_head blocks;
+		/**
+		 * Element within memory_region->objects or region->purgeable
+		 * if the object is marked as DONTNEED. Access is protected by
+		 * region->obj_lock.
+		 */
+		struct list_head region_link;
 
 		struct sg_table *pages;
 		void *mapping;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 2e941f093a20..b0ec0959c13f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -18,6 +18,9 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
 
 	lockdep_assert_held(&obj->mm.lock);
 
+	if (i915_gem_object_is_volatile(obj))
+		obj->mm.madv = I915_MADV_DONTNEED;
+
 	/* Make the pages coherent with the GPU (flushing any swapin). */
 	if (obj->cache_dirty) {
 		obj->write_domain = 0;
@@ -160,6 +163,9 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 	if (IS_ERR_OR_NULL(pages))
 		return pages;
 
+	if (i915_gem_object_is_volatile(obj))
+		obj->mm.madv = I915_MADV_WILLNEED;
+
 	i915_gem_object_make_unshrinkable(obj);
 
 	if (obj->mm.mapping) {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c
index d94914a86737..d3f7733bc7ed 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_region.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c
@@ -107,11 +107,26 @@ void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj,
 	INIT_LIST_HEAD(&obj->mm.blocks);
 	obj->mm.region = intel_memory_region_get(mem);
 	obj->flags |= flags;
+
+	mutex_lock(&mem->objects.lock);
+
+	if (obj->flags & I915_BO_ALLOC_VOLATILE)
+		list_add(&obj->mm.region_link, &mem->objects.purgeable);
+	else
+		list_add(&obj->mm.region_link, &mem->objects.list);
+
+	mutex_unlock(&mem->objects.lock);
 }
 
 void i915_gem_object_release_memory_region(struct drm_i915_gem_object *obj)
 {
-	intel_memory_region_put(obj->mm.region);
+	struct intel_memory_region *mem = obj->mm.region;
+
+	mutex_lock(&mem->objects.lock);
+	list_del(&obj->mm.region_link);
+	mutex_unlock(&mem->objects.lock);
+
+	intel_memory_region_put(mem);
 }
 
 struct drm_i915_gem_object *
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index 63a4743e5f54..f27772f6779a 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -115,8 +115,6 @@ static int get_huge_pages(struct drm_i915_gem_object *obj)
 	if (i915_gem_gtt_prepare_pages(obj, st))
 		goto err;
 
-	obj->mm.madv = I915_MADV_DONTNEED;
-
 	GEM_BUG_ON(sg_page_sizes != obj->mm.page_mask);
 	__i915_gem_object_set_pages(obj, st, sg_page_sizes);
 
@@ -137,7 +135,6 @@ static void put_huge_pages(struct drm_i915_gem_object *obj,
 	huge_pages_free_pages(pages);
 
 	obj->mm.dirty = false;
-	obj->mm.madv = I915_MADV_WILLNEED;
 }
 
 static const struct drm_i915_gem_object_ops huge_page_ops = {
@@ -170,6 +167,8 @@ huge_pages_object(struct drm_i915_private *i915,
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
 	i915_gem_object_init(obj, &huge_page_ops);
 
+	i915_gem_object_set_volatile(obj);
+
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 	obj->cache_level = I915_CACHE_NONE;
@@ -229,8 +228,6 @@ static int fake_get_huge_pages(struct drm_i915_gem_object *obj)
 
 	i915_sg_trim(st);
 
-	obj->mm.madv = I915_MADV_DONTNEED;
-
 	__i915_gem_object_set_pages(obj, st, sg_page_sizes);
 
 	return 0;
@@ -263,8 +260,6 @@ static int fake_get_huge_pages_single(struct drm_i915_gem_object *obj)
 	sg_dma_len(sg) = obj->base.size;
 	sg_dma_address(sg) = page_size;
 
-	obj->mm.madv = I915_MADV_DONTNEED;
-
 	__i915_gem_object_set_pages(obj, st, sg->length);
 
 	return 0;
@@ -283,7 +278,6 @@ static void fake_put_huge_pages(struct drm_i915_gem_object *obj,
 {
 	fake_free_huge_pages(obj, pages);
 	obj->mm.dirty = false;
-	obj->mm.madv = I915_MADV_WILLNEED;
 }
 
 static const struct drm_i915_gem_object_ops fake_ops = {
@@ -323,6 +317,8 @@ fake_huge_pages_object(struct drm_i915_private *i915, u64 size, bool single)
 	else
 		i915_gem_object_init(obj, &fake_ops);
 
+	i915_gem_object_set_volatile(obj);
+
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 	obj->cache_level = I915_CACHE_NONE;
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index 98006618e871..c0299435d75e 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -152,6 +152,10 @@ intel_memory_region_create(struct drm_i915_private *i915,
 	mem->min_page_size = min_page_size;
 	mem->ops = ops;
 
+	mutex_init(&mem->objects.lock);
+	INIT_LIST_HEAD(&mem->objects.list);
+	INIT_LIST_HEAD(&mem->objects.purgeable);
+
 	mutex_init(&mem->mm_lock);
 
 	if (ops->init) {
@@ -177,6 +181,7 @@ static void __intel_memory_region_destroy(struct kref *kref)
 		mem->ops->release(mem);
 
 	mutex_destroy(&mem->mm_lock);
+	mutex_destroy(&mem->objects.lock);
 	kfree(mem);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index 29b86ca17dd9..52c141b6108c 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -52,6 +52,12 @@ struct intel_memory_region {
 	unsigned int type;
 	unsigned int instance;
 	unsigned int id;
+
+	struct {
+		struct mutex lock; /* Protects access to objects */
+		struct list_head list;
+		struct list_head purgeable;
+	} objects;
 };
 
 int intel_memory_region_init_buddy(struct intel_memory_region *mem);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 165b3a7f9744..ebe735df6504 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -82,8 +82,6 @@ static int fake_get_pages(struct drm_i915_gem_object *obj)
 	}
 	GEM_BUG_ON(rem);
 
-	obj->mm.madv = I915_MADV_DONTNEED;
-
 	__i915_gem_object_set_pages(obj, pages, sg_page_sizes);
 
 	return 0;
@@ -95,7 +93,6 @@ static void fake_put_pages(struct drm_i915_gem_object *obj,
 {
 	fake_free_pages(obj, pages);
 	obj->mm.dirty = false;
-	obj->mm.madv = I915_MADV_WILLNEED;
 }
 
 static const struct drm_i915_gem_object_ops fake_ops = {
@@ -122,6 +119,8 @@ fake_dma_object(struct drm_i915_private *i915, u64 size)
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
 	i915_gem_object_init(obj, &fake_ops);
 
+	i915_gem_object_set_volatile(obj);
+
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 	obj->cache_level = I915_CACHE_NONE;
-- 
cgit v1.2.3


From e3f1271474182682638654021123b94e6ec1626b Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Wed, 2 Oct 2019 07:40:42 -0500
Subject: leds: core: Fix leds.h structure documentation

Update the leds.h structure documentation to define the
correct arguments.

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 include/linux/leds.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/linux/leds.h b/include/linux/leds.h
index b8df71193329..efb309dba914 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -247,7 +247,7 @@ extern void led_set_brightness(struct led_classdev *led_cdev,
 /**
  * led_set_brightness_sync - set LED brightness synchronously
  * @led_cdev: the LED to set
- * @brightness: the brightness to set it to
+ * @value: the brightness to set it to
  *
  * Set an LED's brightness immediately. This function will block
  * the caller for the time required for accessing device registers,
@@ -301,8 +301,7 @@ extern void led_sysfs_enable(struct led_classdev *led_cdev);
 /**
  * led_compose_name - compose LED class device name
  * @dev: LED controller device object
- * @child: child fwnode_handle describing a LED or a group of synchronized LEDs;
- *	   it must be provided only for fwnode based LEDs
+ * @init_data: the LED class device initialization data
  * @led_classdev_name: composed LED class device name
  *
  * Create LED class device name basing on the provided init_data argument.
-- 
cgit v1.2.3


From 4050d21d2009faccae5cab74eeb9f460f25d5108 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@ucw.cz>
Date: Tue, 8 Oct 2019 20:58:35 +0200
Subject: Add my linux-leds branch to MAINTAINERS

Add pointer to my git tree to MAINTAINERS. I'd like to maintain
linux-leds for-next branch for 5.5.

Signed-off-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 296de2b51c83..ed49fb760f33 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9183,6 +9183,7 @@ M:	Pavel Machek <pavel@ucw.cz>
 R:	Dan Murphy <dmurphy@ti.com>
 L:	linux-leds@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pavel/linux-leds.git
 S:	Maintained
 F:	Documentation/devicetree/bindings/leds/
 F:	drivers/leds/
-- 
cgit v1.2.3


From c6ee11c39fcc1fb55130748990a8f199e76263b4 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sun, 6 Oct 2019 14:24:24 -0700
Subject: llc: fix sk_buff leak in llc_sap_state_process()

syzbot reported:

    BUG: memory leak
    unreferenced object 0xffff888116270800 (size 224):
       comm "syz-executor641", pid 7047, jiffies 4294947360 (age 13.860s)
       hex dump (first 32 bytes):
         00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
         00 20 e1 2a 81 88 ff ff 00 40 3d 2a 81 88 ff ff  . .*.....@=*....
       backtrace:
         [<000000004d41b4cc>] kmemleak_alloc_recursive  include/linux/kmemleak.h:55 [inline]
         [<000000004d41b4cc>] slab_post_alloc_hook mm/slab.h:439 [inline]
         [<000000004d41b4cc>] slab_alloc_node mm/slab.c:3269 [inline]
         [<000000004d41b4cc>] kmem_cache_alloc_node+0x153/0x2a0 mm/slab.c:3579
         [<00000000506a5965>] __alloc_skb+0x6e/0x210 net/core/skbuff.c:198
         [<000000001ba5a161>] alloc_skb include/linux/skbuff.h:1058 [inline]
         [<000000001ba5a161>] alloc_skb_with_frags+0x5f/0x250  net/core/skbuff.c:5327
         [<0000000047d9c78b>] sock_alloc_send_pskb+0x269/0x2a0  net/core/sock.c:2225
         [<000000003828fe54>] sock_alloc_send_skb+0x32/0x40 net/core/sock.c:2242
         [<00000000e34d94f9>] llc_ui_sendmsg+0x10a/0x540 net/llc/af_llc.c:933
         [<00000000de2de3fb>] sock_sendmsg_nosec net/socket.c:652 [inline]
         [<00000000de2de3fb>] sock_sendmsg+0x54/0x70 net/socket.c:671
         [<000000008fe16e7a>] __sys_sendto+0x148/0x1f0 net/socket.c:1964
	 [...]

The bug is that llc_sap_state_process() always takes an extra reference
to the skb, but sometimes neither llc_sap_next_state() nor
llc_sap_state_process() itself drops this reference.

Fix it by changing llc_sap_next_state() to never consume a reference to
the skb, rather than sometimes do so and sometimes not.  Then remove the
extra skb_get() and kfree_skb() from llc_sap_state_process().

Reported-by: syzbot+6bf095f9becf5efef645@syzkaller.appspotmail.com
Reported-by: syzbot+31c16aa4202dace3812e@syzkaller.appspotmail.com
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/llc/llc_s_ac.c | 12 +++++++++---
 net/llc/llc_sap.c  | 23 ++++++++---------------
 2 files changed, 17 insertions(+), 18 deletions(-)

diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c
index a94bd56bcac6..7ae4cc684d3a 100644
--- a/net/llc/llc_s_ac.c
+++ b/net/llc/llc_s_ac.c
@@ -58,8 +58,10 @@ int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb)
 			    ev->daddr.lsap, LLC_PDU_CMD);
 	llc_pdu_init_as_ui_cmd(skb);
 	rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
-	if (likely(!rc))
+	if (likely(!rc)) {
+		skb_get(skb);
 		rc = dev_queue_xmit(skb);
+	}
 	return rc;
 }
 
@@ -81,8 +83,10 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb)
 			    ev->daddr.lsap, LLC_PDU_CMD);
 	llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0);
 	rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
-	if (likely(!rc))
+	if (likely(!rc)) {
+		skb_get(skb);
 		rc = dev_queue_xmit(skb);
+	}
 	return rc;
 }
 
@@ -135,8 +139,10 @@ int llc_sap_action_send_test_c(struct llc_sap *sap, struct sk_buff *skb)
 			    ev->daddr.lsap, LLC_PDU_CMD);
 	llc_pdu_init_as_test_cmd(skb);
 	rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
-	if (likely(!rc))
+	if (likely(!rc)) {
+		skb_get(skb);
 		rc = dev_queue_xmit(skb);
+	}
 	return rc;
 }
 
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index a7f7b8ff4729..be419062e19a 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -197,29 +197,22 @@ out:
  *	After executing actions of the event, upper layer will be indicated
  *	if needed(on receiving an UI frame). sk can be null for the
  *	datalink_proto case.
+ *
+ *	This function always consumes a reference to the skb.
  */
 static void llc_sap_state_process(struct llc_sap *sap, struct sk_buff *skb)
 {
 	struct llc_sap_state_ev *ev = llc_sap_ev(skb);
 
-	/*
-	 * We have to hold the skb, because llc_sap_next_state
-	 * will kfree it in the sending path and we need to
-	 * look at the skb->cb, where we encode llc_sap_state_ev.
-	 */
-	skb_get(skb);
 	ev->ind_cfm_flag = 0;
 	llc_sap_next_state(sap, skb);
-	if (ev->ind_cfm_flag == LLC_IND) {
-		if (skb->sk->sk_state == TCP_LISTEN)
-			kfree_skb(skb);
-		else {
-			llc_save_primitive(skb->sk, skb, ev->prim);
 
-			/* queue skb to the user. */
-			if (sock_queue_rcv_skb(skb->sk, skb))
-				kfree_skb(skb);
-		}
+	if (ev->ind_cfm_flag == LLC_IND && skb->sk->sk_state != TCP_LISTEN) {
+		llc_save_primitive(skb->sk, skb, ev->prim);
+
+		/* queue skb to the user. */
+		if (sock_queue_rcv_skb(skb->sk, skb) == 0)
+			return;
 	}
 	kfree_skb(skb);
 }
-- 
cgit v1.2.3


From b74555de21acd791f12c4a1aeaf653dd7ac21133 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sun, 6 Oct 2019 14:24:25 -0700
Subject: llc: fix sk_buff leak in llc_conn_service()

syzbot reported:

    BUG: memory leak
    unreferenced object 0xffff88811eb3de00 (size 224):
       comm "syz-executor559", pid 7315, jiffies 4294943019 (age 10.300s)
       hex dump (first 32 bytes):
         00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
         00 a0 38 24 81 88 ff ff 00 c0 f2 15 81 88 ff ff  ..8$............
       backtrace:
         [<000000008d1c66a1>] kmemleak_alloc_recursive  include/linux/kmemleak.h:55 [inline]
         [<000000008d1c66a1>] slab_post_alloc_hook mm/slab.h:439 [inline]
         [<000000008d1c66a1>] slab_alloc_node mm/slab.c:3269 [inline]
         [<000000008d1c66a1>] kmem_cache_alloc_node+0x153/0x2a0 mm/slab.c:3579
         [<00000000447d9496>] __alloc_skb+0x6e/0x210 net/core/skbuff.c:198
         [<000000000cdbf82f>] alloc_skb include/linux/skbuff.h:1058 [inline]
         [<000000000cdbf82f>] llc_alloc_frame+0x66/0x110 net/llc/llc_sap.c:54
         [<000000002418b52e>] llc_conn_ac_send_sabme_cmd_p_set_x+0x2f/0x140  net/llc/llc_c_ac.c:777
         [<000000001372ae17>] llc_exec_conn_trans_actions net/llc/llc_conn.c:475  [inline]
         [<000000001372ae17>] llc_conn_service net/llc/llc_conn.c:400 [inline]
         [<000000001372ae17>] llc_conn_state_process+0x1ac/0x640  net/llc/llc_conn.c:75
         [<00000000f27e53c1>] llc_establish_connection+0x110/0x170  net/llc/llc_if.c:109
         [<00000000291b2ca0>] llc_ui_connect+0x10e/0x370 net/llc/af_llc.c:477
         [<000000000f9c740b>] __sys_connect+0x11d/0x170 net/socket.c:1840
         [...]

The bug is that most callers of llc_conn_send_pdu() assume it consumes a
reference to the skb, when actually due to commit b85ab56c3f81 ("llc:
properly handle dev_queue_xmit() return value") it doesn't.

Revert most of that commit, and instead make the few places that need
llc_conn_send_pdu() to *not* consume a reference call skb_get() before.

Fixes: b85ab56c3f81 ("llc: properly handle dev_queue_xmit() return value")
Reported-by: syzbot+6b825a6494a04cc0e3f7@syzkaller.appspotmail.com
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 include/net/llc_conn.h |  2 +-
 net/llc/llc_c_ac.c     |  8 ++++++--
 net/llc/llc_conn.c     | 32 +++++++++-----------------------
 3 files changed, 16 insertions(+), 26 deletions(-)

diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h
index df528a623548..ea985aa7a6c5 100644
--- a/include/net/llc_conn.h
+++ b/include/net/llc_conn.h
@@ -104,7 +104,7 @@ void llc_sk_reset(struct sock *sk);
 
 /* Access to a connection */
 int llc_conn_state_process(struct sock *sk, struct sk_buff *skb);
-int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb);
+void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb);
 void llc_conn_rtn_pdu(struct sock *sk, struct sk_buff *skb);
 void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit);
 void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit);
diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c
index 4d78375f9872..647c0554d04c 100644
--- a/net/llc/llc_c_ac.c
+++ b/net/llc/llc_c_ac.c
@@ -372,6 +372,7 @@ int llc_conn_ac_send_i_cmd_p_set_1(struct sock *sk, struct sk_buff *skb)
 	llc_pdu_init_as_i_cmd(skb, 1, llc->vS, llc->vR);
 	rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac);
 	if (likely(!rc)) {
+		skb_get(skb);
 		llc_conn_send_pdu(sk, skb);
 		llc_conn_ac_inc_vs_by_1(sk, skb);
 	}
@@ -389,7 +390,8 @@ static int llc_conn_ac_send_i_cmd_p_set_0(struct sock *sk, struct sk_buff *skb)
 	llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR);
 	rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac);
 	if (likely(!rc)) {
-		rc = llc_conn_send_pdu(sk, skb);
+		skb_get(skb);
+		llc_conn_send_pdu(sk, skb);
 		llc_conn_ac_inc_vs_by_1(sk, skb);
 	}
 	return rc;
@@ -406,6 +408,7 @@ int llc_conn_ac_send_i_xxx_x_set_0(struct sock *sk, struct sk_buff *skb)
 	llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR);
 	rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac);
 	if (likely(!rc)) {
+		skb_get(skb);
 		llc_conn_send_pdu(sk, skb);
 		llc_conn_ac_inc_vs_by_1(sk, skb);
 	}
@@ -916,7 +919,8 @@ static int llc_conn_ac_send_i_rsp_f_set_ackpf(struct sock *sk,
 	llc_pdu_init_as_i_cmd(skb, llc->ack_pf, llc->vS, llc->vR);
 	rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac);
 	if (likely(!rc)) {
-		rc = llc_conn_send_pdu(sk, skb);
+		skb_get(skb);
+		llc_conn_send_pdu(sk, skb);
 		llc_conn_ac_inc_vs_by_1(sk, skb);
 	}
 	return rc;
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 4ff89cb7c86f..ed2aca12460c 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -30,7 +30,7 @@
 #endif
 
 static int llc_find_offset(int state, int ev_type);
-static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *skb);
+static void llc_conn_send_pdus(struct sock *sk);
 static int llc_conn_service(struct sock *sk, struct sk_buff *skb);
 static int llc_exec_conn_trans_actions(struct sock *sk,
 				       struct llc_conn_state_trans *trans,
@@ -193,11 +193,11 @@ out_skb_put:
 	return rc;
 }
 
-int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb)
+void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb)
 {
 	/* queue PDU to send to MAC layer */
 	skb_queue_tail(&sk->sk_write_queue, skb);
-	return llc_conn_send_pdus(sk, skb);
+	llc_conn_send_pdus(sk);
 }
 
 /**
@@ -255,7 +255,7 @@ void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit)
 	if (howmany_resend > 0)
 		llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO;
 	/* any PDUs to re-send are queued up; start sending to MAC */
-	llc_conn_send_pdus(sk, NULL);
+	llc_conn_send_pdus(sk);
 out:;
 }
 
@@ -296,7 +296,7 @@ void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit)
 	if (howmany_resend > 0)
 		llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO;
 	/* any PDUs to re-send are queued up; start sending to MAC */
-	llc_conn_send_pdus(sk, NULL);
+	llc_conn_send_pdus(sk);
 out:;
 }
 
@@ -340,16 +340,12 @@ out:
 /**
  *	llc_conn_send_pdus - Sends queued PDUs
  *	@sk: active connection
- *	@hold_skb: the skb held by caller, or NULL if does not care
  *
- *	Sends queued pdus to MAC layer for transmission. When @hold_skb is
- *	NULL, always return 0. Otherwise, return 0 if @hold_skb is sent
- *	successfully, or 1 for failure.
+ *	Sends queued pdus to MAC layer for transmission.
  */
-static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb)
+static void llc_conn_send_pdus(struct sock *sk)
 {
 	struct sk_buff *skb;
-	int ret = 0;
 
 	while ((skb = skb_dequeue(&sk->sk_write_queue)) != NULL) {
 		struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb);
@@ -361,20 +357,10 @@ static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb)
 			skb_queue_tail(&llc_sk(sk)->pdu_unack_q, skb);
 			if (!skb2)
 				break;
-			dev_queue_xmit(skb2);
-		} else {
-			bool is_target = skb == hold_skb;
-			int rc;
-
-			if (is_target)
-				skb_get(skb);
-			rc = dev_queue_xmit(skb);
-			if (is_target)
-				ret = rc;
+			skb = skb2;
 		}
+		dev_queue_xmit(skb);
 	}
-
-	return ret;
 }
 
 /**
-- 
cgit v1.2.3


From fc8d5db10cbe1338a52ebc74e7feab9276721774 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sun, 6 Oct 2019 14:24:26 -0700
Subject: llc: fix another potential sk_buff leak in llc_ui_sendmsg()

All callers of llc_conn_state_process() except llc_build_and_send_pkt()
(via llc_ui_sendmsg() -> llc_ui_send_data()) assume that it always
consumes a reference to the skb.  Fix this caller to do the same.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/llc/af_llc.c   | 34 ++++++++++++++++++++--------------
 net/llc/llc_conn.c |  2 ++
 net/llc/llc_if.c   | 12 ++++++++----
 3 files changed, 30 insertions(+), 18 deletions(-)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 2017b7d780f5..c74f44dfaa22 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -113,22 +113,26 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr)
  *
  *	Send data via reliable llc2 connection.
  *	Returns 0 upon success, non-zero if action did not succeed.
+ *
+ *	This function always consumes a reference to the skb.
  */
 static int llc_ui_send_data(struct sock* sk, struct sk_buff *skb, int noblock)
 {
 	struct llc_sock* llc = llc_sk(sk);
-	int rc = 0;
 
 	if (unlikely(llc_data_accept_state(llc->state) ||
 		     llc->remote_busy_flag ||
 		     llc->p_flag)) {
 		long timeout = sock_sndtimeo(sk, noblock);
+		int rc;
 
 		rc = llc_ui_wait_for_busy_core(sk, timeout);
+		if (rc) {
+			kfree_skb(skb);
+			return rc;
+		}
 	}
-	if (unlikely(!rc))
-		rc = llc_build_and_send_pkt(sk, skb);
-	return rc;
+	return llc_build_and_send_pkt(sk, skb);
 }
 
 static void llc_ui_sk_init(struct socket *sock, struct sock *sk)
@@ -899,7 +903,7 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name);
 	int flags = msg->msg_flags;
 	int noblock = flags & MSG_DONTWAIT;
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	size_t size = 0;
 	int rc = -EINVAL, copied = 0, hdrlen;
 
@@ -908,10 +912,10 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	lock_sock(sk);
 	if (addr) {
 		if (msg->msg_namelen < sizeof(*addr))
-			goto release;
+			goto out;
 	} else {
 		if (llc_ui_addr_null(&llc->addr))
-			goto release;
+			goto out;
 		addr = &llc->addr;
 	}
 	/* must bind connection to sap if user hasn't done it. */
@@ -919,7 +923,7 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		/* bind to sap with null dev, exclusive. */
 		rc = llc_ui_autobind(sock, addr);
 		if (rc)
-			goto release;
+			goto out;
 	}
 	hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr);
 	size = hdrlen + len;
@@ -928,12 +932,12 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	copied = size - hdrlen;
 	rc = -EINVAL;
 	if (copied < 0)
-		goto release;
+		goto out;
 	release_sock(sk);
 	skb = sock_alloc_send_skb(sk, size, noblock, &rc);
 	lock_sock(sk);
 	if (!skb)
-		goto release;
+		goto out;
 	skb->dev      = llc->dev;
 	skb->protocol = llc_proto_type(addr->sllc_arphrd);
 	skb_reserve(skb, hdrlen);
@@ -943,29 +947,31 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	if (sk->sk_type == SOCK_DGRAM || addr->sllc_ua) {
 		llc_build_and_send_ui_pkt(llc->sap, skb, addr->sllc_mac,
 					  addr->sllc_sap);
+		skb = NULL;
 		goto out;
 	}
 	if (addr->sllc_test) {
 		llc_build_and_send_test_pkt(llc->sap, skb, addr->sllc_mac,
 					    addr->sllc_sap);
+		skb = NULL;
 		goto out;
 	}
 	if (addr->sllc_xid) {
 		llc_build_and_send_xid_pkt(llc->sap, skb, addr->sllc_mac,
 					   addr->sllc_sap);
+		skb = NULL;
 		goto out;
 	}
 	rc = -ENOPROTOOPT;
 	if (!(sk->sk_type == SOCK_STREAM && !addr->sllc_ua))
 		goto out;
 	rc = llc_ui_send_data(sk, skb, noblock);
+	skb = NULL;
 out:
-	if (rc) {
-		kfree_skb(skb);
-release:
+	kfree_skb(skb);
+	if (rc)
 		dprintk("%s: failed sending from %02X to %02X: %d\n",
 			__func__, llc->laddr.lsap, llc->daddr.lsap, rc);
-	}
 	release_sock(sk);
 	return rc ? : copied;
 }
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index ed2aca12460c..0b0c6f12153b 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -55,6 +55,8 @@ int sysctl_llc2_busy_timeout = LLC2_BUSY_TIME * HZ;
  *	(executing it's actions and changing state), upper layer will be
  *	indicated or confirmed, if needed. Returns 0 for success, 1 for
  *	failure. The socket lock has to be held before calling this function.
+ *
+ *	This function always consumes a reference to the skb.
  */
 int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
 {
diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c
index 8db03c2d5440..ad6547736c21 100644
--- a/net/llc/llc_if.c
+++ b/net/llc/llc_if.c
@@ -38,6 +38,8 @@
  *	closed and -EBUSY when sending data is not permitted in this state or
  *	LLC has send an I pdu with p bit set to 1 and is waiting for it's
  *	response.
+ *
+ *	This function always consumes a reference to the skb.
  */
 int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb)
 {
@@ -46,20 +48,22 @@ int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb)
 	struct llc_sock *llc = llc_sk(sk);
 
 	if (unlikely(llc->state == LLC_CONN_STATE_ADM))
-		goto out;
+		goto out_free;
 	rc = -EBUSY;
 	if (unlikely(llc_data_accept_state(llc->state) || /* data_conn_refuse */
 		     llc->p_flag)) {
 		llc->failed_data_req = 1;
-		goto out;
+		goto out_free;
 	}
 	ev = llc_conn_ev(skb);
 	ev->type      = LLC_CONN_EV_TYPE_PRIM;
 	ev->prim      = LLC_DATA_PRIM;
 	ev->prim_type = LLC_PRIM_TYPE_REQ;
 	skb->dev      = llc->dev;
-	rc = llc_conn_state_process(sk, skb);
-out:
+	return llc_conn_state_process(sk, skb);
+
+out_free:
+	kfree_skb(skb);
 	return rc;
 }
 
-- 
cgit v1.2.3


From 36453c852816f19947ca482a595dffdd2efa4965 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sun, 6 Oct 2019 14:24:27 -0700
Subject: llc: fix sk_buff refcounting in llc_conn_state_process()

If llc_conn_state_process() sees that llc_conn_service() put the skb on
a list, it will drop one fewer references to it.  This is wrong because
the current behavior is that llc_conn_service() never consumes a
reference to the skb.

The code also makes the number of skb references being dropped
conditional on which of ind_prim and cfm_prim are nonzero, yet neither
of these affects how many references are *acquired*.  So there is extra
code that tries to fix this up by sometimes taking another reference.

Remove the unnecessary/broken refcounting logic and instead just add an
skb_get() before the only two places where an extra reference is
actually consumed.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/llc/llc_conn.c | 33 ++++++---------------------------
 1 file changed, 6 insertions(+), 27 deletions(-)

diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 0b0c6f12153b..a79b739eb223 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -64,12 +64,6 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
 	struct llc_sock *llc = llc_sk(skb->sk);
 	struct llc_conn_state_ev *ev = llc_conn_ev(skb);
 
-	/*
-	 * We have to hold the skb, because llc_conn_service will kfree it in
-	 * the sending path and we need to look at the skb->cb, where we encode
-	 * llc_conn_state_ev.
-	 */
-	skb_get(skb);
 	ev->ind_prim = ev->cfm_prim = 0;
 	/*
 	 * Send event to state machine
@@ -77,21 +71,12 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
 	rc = llc_conn_service(skb->sk, skb);
 	if (unlikely(rc != 0)) {
 		printk(KERN_ERR "%s: llc_conn_service failed\n", __func__);
-		goto out_kfree_skb;
-	}
-
-	if (unlikely(!ev->ind_prim && !ev->cfm_prim)) {
-		/* indicate or confirm not required */
-		if (!skb->next)
-			goto out_kfree_skb;
 		goto out_skb_put;
 	}
 
-	if (unlikely(ev->ind_prim && ev->cfm_prim)) /* Paranoia */
-		skb_get(skb);
-
 	switch (ev->ind_prim) {
 	case LLC_DATA_PRIM:
+		skb_get(skb);
 		llc_save_primitive(sk, skb, LLC_DATA_PRIM);
 		if (unlikely(sock_queue_rcv_skb(sk, skb))) {
 			/*
@@ -108,6 +93,7 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
 		 * skb->sk pointing to the newly created struct sock in
 		 * llc_conn_handler. -acme
 		 */
+		skb_get(skb);
 		skb_queue_tail(&sk->sk_receive_queue, skb);
 		sk->sk_state_change(sk);
 		break;
@@ -123,7 +109,6 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
 				sk->sk_state_change(sk);
 			}
 		}
-		kfree_skb(skb);
 		sock_put(sk);
 		break;
 	case LLC_RESET_PRIM:
@@ -132,14 +117,11 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
 		 * RESET is not being notified to upper layers for now
 		 */
 		printk(KERN_INFO "%s: received a reset ind!\n", __func__);
-		kfree_skb(skb);
 		break;
 	default:
-		if (ev->ind_prim) {
+		if (ev->ind_prim)
 			printk(KERN_INFO "%s: received unknown %d prim!\n",
 				__func__, ev->ind_prim);
-			kfree_skb(skb);
-		}
 		/* No indication */
 		break;
 	}
@@ -181,15 +163,12 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
 		printk(KERN_INFO "%s: received a reset conf!\n", __func__);
 		break;
 	default:
-		if (ev->cfm_prim) {
+		if (ev->cfm_prim)
 			printk(KERN_INFO "%s: received unknown %d prim!\n",
 					__func__, ev->cfm_prim);
-			break;
-		}
-		goto out_skb_put; /* No confirmation */
+		/* No confirmation */
+		break;
 	}
-out_kfree_skb:
-	kfree_skb(skb);
 out_skb_put:
 	kfree_skb(skb);
 	return rc;
-- 
cgit v1.2.3


From 6ad145fe0246abe31a312ce19321bb5b11635802 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 8 Oct 2019 19:59:41 +0100
Subject: drm/i915/gt: Give engine->kernel_context distinct timeline lock
 classes

Assign a separate lockclass to the perma-pinned timelines of the
kernel_context, such that we can use them from within the user timelines
should we ever need to inject GPU operations to fixup faults during
request construction.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191008185941.15228-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 7e2aa7a6bef0..5aa1371f6a0f 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -736,6 +736,7 @@ intel_engine_init_active(struct intel_engine_cs *engine, unsigned int subclass)
 static struct intel_context *
 create_kernel_context(struct intel_engine_cs *engine)
 {
+	static struct lock_class_key kernel;
 	struct intel_context *ce;
 	int err;
 
@@ -751,6 +752,14 @@ create_kernel_context(struct intel_engine_cs *engine)
 		return ERR_PTR(err);
 	}
 
+	/*
+	 * Give our perma-pinned kernel timelines a separate lockdep class,
+	 * so that we can use them from within the normal user timelines
+	 * should we need to inject GPU operations during their request
+	 * construction.
+	 */
+	lockdep_set_class(&ce->timeline->mutex, &kernel);
+
 	return ce;
 }
 
-- 
cgit v1.2.3


From fd418b01fe26c2430b1091675cceb3ab2b52e1e0 Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Tue, 8 Oct 2019 15:10:44 +0200
Subject: selftests/bpf: Set rp_filter in test_flow_dissector

Many distributions enable rp_filter. However, the flow dissector test
generates packets that have 1.1.1.1 set as (inner) source address without
this address being reachable. This causes the selftest to fail.

The selftests should not assume a particular initial configuration. Switch
off rp_filter.

Fixes: 50b3ed57dee9 ("selftests/bpf: test bpf flow dissection")
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Petar Penkov <ppenkov@google.com>
Link: https://lore.kernel.org/bpf/513a298f53e99561d2f70b2e60e2858ea6cda754.1570539863.git.jbenc@redhat.com
---
 tools/testing/selftests/bpf/test_flow_dissector.sh | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh
index d23d4da66b83..e2d06191bd35 100755
--- a/tools/testing/selftests/bpf/test_flow_dissector.sh
+++ b/tools/testing/selftests/bpf/test_flow_dissector.sh
@@ -63,6 +63,9 @@ fi
 
 # Setup
 tc qdisc add dev lo ingress
+echo 0 > /proc/sys/net/ipv4/conf/default/rp_filter
+echo 0 > /proc/sys/net/ipv4/conf/all/rp_filter
+echo 0 > /proc/sys/net/ipv4/conf/lo/rp_filter
 
 echo "Testing IPv4..."
 # Drops all IP/UDP packets coming from port 9
-- 
cgit v1.2.3


From 106c35dda32f8b63f88cad7433f1b8bb0056958a Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Tue, 8 Oct 2019 15:10:45 +0200
Subject: selftests/bpf: More compatible nc options in test_lwt_ip_encap

Out of the three nc implementations widely in use, at least two (BSD netcat
and nmap-ncat) do not support -l combined with -s. Modify the nc invocation
to be accepted by all of them.

Fixes: 17a90a788473 ("selftests/bpf: test that GSO works in lwt_ip_encap")
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/9f177682c387f3f943bb64d849e6c6774df3c5b4.1570539863.git.jbenc@redhat.com
---
 tools/testing/selftests/bpf/test_lwt_ip_encap.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
index acf7a74f97cd..59ea56945e6c 100755
--- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
+++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
@@ -314,15 +314,15 @@ test_gso()
 	command -v nc >/dev/null 2>&1 || \
 		{ echo >&2 "nc is not available: skipping TSO tests"; return; }
 
-	# listen on IPv*_DST, capture TCP into $TMPFILE
+	# listen on port 9000, capture TCP into $TMPFILE
 	if [ "${PROTO}" == "IPv4" ] ; then
 		IP_DST=${IPv4_DST}
 		ip netns exec ${NS3} bash -c \
-			"nc -4 -l -s ${IPv4_DST} -p 9000 > ${TMPFILE} &"
+			"nc -4 -l -p 9000 > ${TMPFILE} &"
 	elif [ "${PROTO}" == "IPv6" ] ; then
 		IP_DST=${IPv6_DST}
 		ip netns exec ${NS3} bash -c \
-			"nc -6 -l -s ${IPv6_DST} -p 9000 > ${TMPFILE} &"
+			"nc -6 -l -p 9000 > ${TMPFILE} &"
 		RET=$?
 	else
 		echo "    test_gso: unknown PROTO: ${PROTO}"
-- 
cgit v1.2.3


From 0041412694eca70387aee4076254fbed8222700a Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Mon, 7 Oct 2019 16:13:25 +0300
Subject: net/mlx5: DR, Allow insertion of duplicate rules

Duplicate rules were not allowed to be configured with SW steering.
This restriction caused failures with the replace rule logic done by
upper layers.

This fix allows for multiple rules with the same match values, in
such case the first inserted rules will match.

Fixes: 41d07074154c ("net/mlx5: DR, Expose steering rule functionality")
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index 4187f2b112b8..e8b656075c6f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -788,12 +788,10 @@ again:
 			 * it means that all the previous stes are the same,
 			 * if so, this rule is duplicated.
 			 */
-			if (mlx5dr_ste_is_last_in_rule(nic_matcher,
-						       matched_ste->ste_chain_location)) {
-				mlx5dr_info(dmn, "Duplicate rule inserted, aborting!!\n");
-				return NULL;
-			}
-			return matched_ste;
+			if (!mlx5dr_ste_is_last_in_rule(nic_matcher, ste_location))
+				return matched_ste;
+
+			mlx5dr_dbg(dmn, "Duplicate rule inserted\n");
 		}
 
 		if (!skip_rehash && dr_rule_need_enlarge_hash(cur_htbl, dmn, nic_dmn)) {
-- 
cgit v1.2.3


From 6f96c3c6904c26cea9ca2726d5d8a9b0b8205b3c Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 7 Oct 2019 13:26:28 -0700
Subject: net_sched: fix backward compatibility for TCA_KIND

Marcelo noticed a backward compatibility issue of TCA_KIND
after we move from NLA_STRING to NLA_NUL_STRING, so it is probably
too late to change it.

Instead, to make everyone happy, we can just insert a NUL to
terminate the string with nla_strlcpy() like we do for TC actions.

Fixes: 62794fc4fbf5 ("net_sched: add max len check for TCA_KIND")
Reported-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sched/cls_api.c | 36 +++++++++++++++++++++++++++++++++---
 net/sched/sch_api.c |  3 +--
 2 files changed, 34 insertions(+), 5 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 64584a1df425..8717c0b26c90 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -162,11 +162,22 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp)
 	return TC_H_MAJ(first);
 }
 
+static bool tcf_proto_check_kind(struct nlattr *kind, char *name)
+{
+	if (kind)
+		return nla_strlcpy(name, kind, IFNAMSIZ) >= IFNAMSIZ;
+	memset(name, 0, IFNAMSIZ);
+	return false;
+}
+
 static bool tcf_proto_is_unlocked(const char *kind)
 {
 	const struct tcf_proto_ops *ops;
 	bool ret;
 
+	if (strlen(kind) == 0)
+		return false;
+
 	ops = tcf_proto_lookup_ops(kind, false, NULL);
 	/* On error return false to take rtnl lock. Proto lookup/create
 	 * functions will perform lookup again and properly handle errors.
@@ -1843,6 +1854,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tca[TCA_MAX + 1];
+	char name[IFNAMSIZ];
 	struct tcmsg *t;
 	u32 protocol;
 	u32 prio;
@@ -1899,13 +1911,19 @@ replay:
 	if (err)
 		return err;
 
+	if (tcf_proto_check_kind(tca[TCA_KIND], name)) {
+		NL_SET_ERR_MSG(extack, "Specified TC filter name too long");
+		err = -EINVAL;
+		goto errout;
+	}
+
 	/* Take rtnl mutex if rtnl_held was set to true on previous iteration,
 	 * block is shared (no qdisc found), qdisc is not unlocked, classifier
 	 * type is not specified, classifier is not unlocked.
 	 */
 	if (rtnl_held ||
 	    (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) ||
-	    !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) {
+	    !tcf_proto_is_unlocked(name)) {
 		rtnl_held = true;
 		rtnl_lock();
 	}
@@ -2063,6 +2081,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tca[TCA_MAX + 1];
+	char name[IFNAMSIZ];
 	struct tcmsg *t;
 	u32 protocol;
 	u32 prio;
@@ -2102,13 +2121,18 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	if (err)
 		return err;
 
+	if (tcf_proto_check_kind(tca[TCA_KIND], name)) {
+		NL_SET_ERR_MSG(extack, "Specified TC filter name too long");
+		err = -EINVAL;
+		goto errout;
+	}
 	/* Take rtnl mutex if flushing whole chain, block is shared (no qdisc
 	 * found), qdisc is not unlocked, classifier type is not specified,
 	 * classifier is not unlocked.
 	 */
 	if (!prio ||
 	    (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) ||
-	    !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) {
+	    !tcf_proto_is_unlocked(name)) {
 		rtnl_held = true;
 		rtnl_lock();
 	}
@@ -2216,6 +2240,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 {
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *tca[TCA_MAX + 1];
+	char name[IFNAMSIZ];
 	struct tcmsg *t;
 	u32 protocol;
 	u32 prio;
@@ -2252,12 +2277,17 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	if (err)
 		return err;
 
+	if (tcf_proto_check_kind(tca[TCA_KIND], name)) {
+		NL_SET_ERR_MSG(extack, "Specified TC filter name too long");
+		err = -EINVAL;
+		goto errout;
+	}
 	/* Take rtnl mutex if block is shared (no qdisc found), qdisc is not
 	 * unlocked, classifier type is not specified, classifier is not
 	 * unlocked.
 	 */
 	if ((q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) ||
-	    !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) {
+	    !tcf_proto_is_unlocked(name)) {
 		rtnl_held = true;
 		rtnl_lock();
 	}
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 81d58b280612..1047825d9f48 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1390,8 +1390,7 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w)
 }
 
 const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = {
-	[TCA_KIND]		= { .type = NLA_NUL_STRING,
-				    .len = IFNAMSIZ - 1 },
+	[TCA_KIND]		= { .type = NLA_STRING },
 	[TCA_RATE]		= { .type = NLA_BINARY,
 				    .len = sizeof(struct tc_estimator) },
 	[TCA_STAB]		= { .type = NLA_NESTED },
-- 
cgit v1.2.3


From 4b793feccae3b06764268377a4030eb774ed924e Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Mon, 7 Oct 2019 13:26:29 -0700
Subject: net_sched: fix backward compatibility for TCA_ACT_KIND

For TCA_ACT_KIND, we have to keep the backward compatibility too,
and rely on nla_strlcpy() to check and terminate the string with
a NUL.

Note for TC actions, nla_strcmp() is already used to compare kind
strings, so we don't need to fix other places.

Fixes: 199ce850ce11 ("net_sched: add policy validation for action attributes")
Reported-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sched/act_api.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 2558f00f6b3e..4e7429c6f864 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -832,8 +832,7 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 }
 
 static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
-	[TCA_ACT_KIND]		= { .type = NLA_NUL_STRING,
-				    .len = IFNAMSIZ - 1 },
+	[TCA_ACT_KIND]		= { .type = NLA_STRING },
 	[TCA_ACT_INDEX]		= { .type = NLA_U32 },
 	[TCA_ACT_COOKIE]	= { .type = NLA_BINARY,
 				    .len = TC_COOKIE_MAX_SIZE },
@@ -865,8 +864,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 			NL_SET_ERR_MSG(extack, "TC action kind must be specified");
 			goto err_out;
 		}
-		nla_strlcpy(act_name, kind, IFNAMSIZ);
-
+		if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) {
+			NL_SET_ERR_MSG(extack, "TC action name too long");
+			goto err_out;
+		}
 		if (tb[TCA_ACT_COOKIE]) {
 			cookie = nla_memdup_cookie(tb);
 			if (!cookie) {
-- 
cgit v1.2.3


From bcf059578980526d6067a2b1b0cd8344b58bf2d5 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 8 Oct 2019 16:40:33 -0700
Subject: Input: soc_button_array - partial revert of support for newer surface
 devices

Commit c394159310d0 ("Input: soc_button_array - add support for newer
surface devices") not only added support for the MSHW0040 ACPI HID,
but for some reason it also makes changes to the error handling of the
soc_button_lookup_gpio() call in soc_button_device_create(). Note ideally
this seamingly unrelated change would have been made in a separate commit,
with a message explaining the what and why of this change.

I guess this change may have been added to deal with -EPROBE_DEFER errors,
but in case of the existing support for PNP0C40 devices, treating
-EPROBE_DEFER as any other error is deliberate, see the comment this
commit adds for why.

The actual returning of -EPROBE_DEFER to the caller of soc_button_probe()
introduced by the new error checking causes a serious regression:

On devices with so called virtual GPIOs soc_button_lookup_gpio() will
always return -EPROBE_DEFER for these fake GPIOs, when this happens
during the second call of soc_button_device_create() we already have
successfully registered our first child. This causes the kernel to think
we are making progress with probing things even though we unregister the
child before again before we return the -EPROBE_DEFER. Since we are making
progress the kernel will retry deferred-probes again immediately ending
up stuck in a loop with the following showing in dmesg:

[  124.022697] input: gpio-keys as /devices/platform/INTCFD9:00/gpio-keys.0.auto/input/input6537
[  124.040764] input: gpio-keys as /devices/platform/INTCFD9:00/gpio-keys.0.auto/input/input6538
[  124.056967] input: gpio-keys as /devices/platform/INTCFD9:00/gpio-keys.0.auto/input/input6539
[  124.072143] input: gpio-keys as /devices/platform/INTCFD9:00/gpio-keys.0.auto/input/input6540
[  124.092373] input: gpio-keys as /devices/platform/INTCFD9:00/gpio-keys.0.auto/input/input6541
[  124.108065] input: gpio-keys as /devices/platform/INTCFD9:00/gpio-keys.0.auto/input/input6542
[  124.128483] input: gpio-keys as /devices/platform/INTCFD9:00/gpio-keys.0.auto/input/input6543
[  124.147141] input: gpio-keys as /devices/platform/INTCFD9:00/gpio-keys.0.auto/input/input6544
[  124.165070] input: gpio-keys as /devices/platform/INTCFD9:00/gpio-keys.0.auto/input/input6545
[  124.179775] input: gpio-keys as /devices/platform/INTCFD9:00/gpio-keys.0.auto/input/input6546
[  124.202726] input: gpio-keys as /devices/platform/INTCFD9:00/gpio-keys.0.auto/input/input6547
<continues on and on and on>

And 1 CPU core being stuck at 100% and udev hanging since it is waiting
for the modprobe of soc_button_array to return.

This patch reverts the soc_button_lookup_gpio() error handling changes,
fixing this regression.

Fixes: c394159310d0 ("Input: soc_button_array - add support for newer surface devices")
BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=205031
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Tested-by: Maximilian Luz <luzmaximilian@gmail.com>
Acked-by: Maximilian Luz <luzmaximilian@gmail.com>
Link: https://lore.kernel.org/r/20191005105551.353273-1-hdegoede@redhat.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/soc_button_array.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c
index 97e3639e99d0..08520b3a18b8 100644
--- a/drivers/input/misc/soc_button_array.c
+++ b/drivers/input/misc/soc_button_array.c
@@ -92,11 +92,18 @@ soc_button_device_create(struct platform_device *pdev,
 			continue;
 
 		gpio = soc_button_lookup_gpio(&pdev->dev, info->acpi_index);
-		if (gpio < 0 && gpio != -ENOENT) {
-			error = gpio;
-			goto err_free_mem;
-		} else if (!gpio_is_valid(gpio)) {
-			/* Skip GPIO if not present */
+		if (!gpio_is_valid(gpio)) {
+			/*
+			 * Skip GPIO if not present. Note we deliberately
+			 * ignore -EPROBE_DEFER errors here. On some devices
+			 * Intel is using so called virtual GPIOs which are not
+			 * GPIOs at all but some way for AML code to check some
+			 * random status bits without need a custom opregion.
+			 * In some cases the resources table we parse points to
+			 * such a virtual GPIO, since these are not real GPIOs
+			 * we do not have a driver for these so they will never
+			 * show up, therefore we ignore -EPROBE_DEFER.
+			 */
 			continue;
 		}
 
-- 
cgit v1.2.3


From 6af3aa57a0984e061f61308fe181a9a12359fecc Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Mon, 7 Oct 2019 18:40:59 +0200
Subject: NFC: pn533: fix use-after-free and memleaks

The driver would fail to deregister and its class device and free
related resources on late probe errors.

Reported-by: syzbot+cb035c75c03dbe34b796@syzkaller.appspotmail.com
Fixes: 32ecc75ded72 ("NFC: pn533: change order operations in dev registation")
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/nfc/pn533/usb.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c
index c5289eaf17ee..e897e4d768ef 100644
--- a/drivers/nfc/pn533/usb.c
+++ b/drivers/nfc/pn533/usb.c
@@ -547,18 +547,25 @@ static int pn533_usb_probe(struct usb_interface *interface,
 
 	rc = pn533_finalize_setup(priv);
 	if (rc)
-		goto error;
+		goto err_deregister;
 
 	usb_set_intfdata(interface, phy);
 
 	return 0;
 
+err_deregister:
+	pn533_unregister_device(phy->priv);
 error:
+	usb_kill_urb(phy->in_urb);
+	usb_kill_urb(phy->out_urb);
+	usb_kill_urb(phy->ack_urb);
+
 	usb_free_urb(phy->in_urb);
 	usb_free_urb(phy->out_urb);
 	usb_free_urb(phy->ack_urb);
 	usb_put_dev(phy->udev);
 	kfree(in_buf);
+	kfree(phy->ack_buffer);
 
 	return rc;
 }
-- 
cgit v1.2.3


From d0959b080b1faa9741857ef607c90531b66e2fb8 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Sat, 5 Oct 2019 10:53:58 -0500
Subject: smb3: remove noisy debug message and minor cleanup

Message was intended only for developer temporary build
In addition cleanup two minor warnings noticed by Coverity
and a trivial change to workaround a sparse warning

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/cifsglob.h |  2 +-
 fs/cifs/connect.c  |  2 +-
 fs/cifs/smb2pdu.c  | 11 ++++-------
 3 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 2e960e1049db..50dfd9049370 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1210,7 +1210,7 @@ struct cifs_search_info {
 	bool smallBuf:1; /* so we know which buf_release function to call */
 };
 
-#define ACL_NO_MODE	-1
+#define ACL_NO_MODE	((umode_t)(-1))
 struct cifs_open_parms {
 	struct cifs_tcon *tcon;
 	struct cifs_sb_info *cifs_sb;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index b724227b853c..a64dfa95a925 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -4445,7 +4445,7 @@ static int setup_dfs_tgt_conn(const char *path,
 	int rc;
 	struct dfs_info3_param ref = {0};
 	char *mdata = NULL, *fake_devname = NULL;
-	struct smb_vol fake_vol = {0};
+	struct smb_vol fake_vol = {NULL};
 
 	cifs_dbg(FYI, "%s: dfs path: %s\n", __func__, path);
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index fd5f2b4b7582..05149862aea4 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -751,8 +751,8 @@ add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode)
 	unsigned int num = *num_iovec;
 
 	iov[num].iov_base = create_posix_buf(mode);
-	if (mode == -1)
-		cifs_dbg(VFS, "illegal mode\n"); /* BB REMOVEME */
+	if (mode == ACL_NO_MODE)
+		cifs_dbg(FYI, "illegal mode\n");
 	if (iov[num].iov_base == NULL)
 		return -ENOMEM;
 	iov[num].iov_len = sizeof(struct create_posix);
@@ -2521,11 +2521,8 @@ SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, __u8 *oplock,
 			return rc;
 	}
 
-	/* TODO: add handling for the mode on create */
-	if (oparms->disposition == FILE_CREATE)
-		cifs_dbg(VFS, "mode is 0x%x\n", oparms->mode); /* BB REMOVEME */
-
-	if ((oparms->disposition == FILE_CREATE) && (oparms->mode != -1)) {
+	if ((oparms->disposition == FILE_CREATE) &&
+	    (oparms->mode != ACL_NO_MODE)) {
 		if (n_iov > 2) {
 			struct create_context *ccontext =
 			    (struct create_context *)iov[n_iov-1].iov_base;
-- 
cgit v1.2.3


From b82316d25522e8ee748b8cc9d8aadeb3c135c6fe Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 8 Oct 2019 08:35:51 -0700
Subject: Doc: networking/device_drivers/pensando: fix ionic.rst warnings

Fix documentation build warnings for Pensando ionic:

Documentation/networking/device_drivers/pensando/ionic.rst:39: WARNING: Unexpected indentation.
Documentation/networking/device_drivers/pensando/ionic.rst:43: WARNING: Unexpected indentation.

Fixes: df69ba43217d ("ionic: Add basic framework for IONIC Network device driver")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 Documentation/networking/device_drivers/pensando/ionic.rst | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/device_drivers/pensando/ionic.rst b/Documentation/networking/device_drivers/pensando/ionic.rst
index 67b6839d516b..13935896bee6 100644
--- a/Documentation/networking/device_drivers/pensando/ionic.rst
+++ b/Documentation/networking/device_drivers/pensando/ionic.rst
@@ -36,8 +36,10 @@ Support
 =======
 For general Linux networking support, please use the netdev mailing
 list, which is monitored by Pensando personnel::
+
   netdev@vger.kernel.org
 
 For more specific support needs, please use the Pensando driver support
 email::
-	drivers@pensando.io
+
+  drivers@pensando.io
-- 
cgit v1.2.3


From 4123f637a5129470ff9d3cb00a5a4e213f2e15cc Mon Sep 17 00:00:00 2001
From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Tue, 8 Oct 2019 17:56:03 +0800
Subject: ip6erspan: remove the incorrect mtu limit for ip6erspan

ip6erspan driver calls ether_setup(), after commit 61e84623ace3
("net: centralize net_device min/max MTU checking"), the range
of mtu is [min_mtu, max_mtu], which is [68, 1500] by default.

It causes the dev mtu of the erspan device to not be greater
than 1500, this limit value is not correct for ip6erspan tap
device.

Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking")
Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Acked-by: William Tu <u9012063@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/ipv6/ip6_gre.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index d5779d6a6065..787d9f2a6e99 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -2192,6 +2192,7 @@ static void ip6erspan_tap_setup(struct net_device *dev)
 {
 	ether_setup(dev);
 
+	dev->max_mtu = 0;
 	dev->netdev_ops = &ip6erspan_netdev_ops;
 	dev->needs_free_netdev = true;
 	dev->priv_destructor = ip6gre_dev_free;
-- 
cgit v1.2.3


From d4cfbf04b2aafcb657eb8ea0835e5cf51d371448 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Tue, 8 Oct 2019 00:27:14 -0500
Subject: smb3: Fix regression in time handling

Fixes: cb7a69e60590 ("cifs: Initialize filesystem timestamp ranges")

Only very old servers (e.g. OS/2 and DOS) did not support
DCE TIME (100 nanosecond granularity).  Fix the checks used
to set minimum and maximum times.

Fixes xfstest generic/258 (on 5.4-rc1 and later)

CC: Deepa Dinamani <deepa.kernel@gmail.com>
Acked-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/cifsfs.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 2e9c7f493f99..c049c7b3aa87 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -169,18 +169,26 @@ cifs_read_super(struct super_block *sb)
 	else
 		sb->s_maxbytes = MAX_NON_LFS;
 
-	/* BB FIXME fix time_gran to be larger for LANMAN sessions */
-	sb->s_time_gran = 100;
-
-	if (tcon->unix_ext) {
-		ts = cifs_NTtimeToUnix(0);
+	/* Some very old servers like DOS and OS/2 used 2 second granularity */
+	if ((tcon->ses->server->vals->protocol_id == SMB10_PROT_ID) &&
+	    ((tcon->ses->capabilities &
+	      tcon->ses->server->vals->cap_nt_find) == 0) &&
+	    !tcon->unix_ext) {
+		sb->s_time_gran = 1000000000; /* 1 second is max allowed gran */
+		ts = cnvrtDosUnixTm(cpu_to_le16(SMB_DATE_MIN), 0, 0);
 		sb->s_time_min = ts.tv_sec;
-		ts = cifs_NTtimeToUnix(cpu_to_le64(S64_MAX));
+		ts = cnvrtDosUnixTm(cpu_to_le16(SMB_DATE_MAX),
+				    cpu_to_le16(SMB_TIME_MAX), 0);
 		sb->s_time_max = ts.tv_sec;
 	} else {
-		ts = cnvrtDosUnixTm(cpu_to_le16(SMB_DATE_MIN), 0, 0);
+		/*
+		 * Almost every server, including all SMB2+, uses DCE TIME
+		 * ie 100 nanosecond units, since 1601.  See MS-DTYP and MS-FSCC
+		 */
+		sb->s_time_gran = 100;
+		ts = cifs_NTtimeToUnix(0);
 		sb->s_time_min = ts.tv_sec;
-		ts = cnvrtDosUnixTm(cpu_to_le16(SMB_DATE_MAX), cpu_to_le16(SMB_TIME_MAX), 0);
+		ts = cifs_NTtimeToUnix(cpu_to_le64(S64_MAX));
 		sb->s_time_max = ts.tv_sec;
 	}
 
-- 
cgit v1.2.3


From c82e5ac7fe3570a269c0929bf7899f62048e7dbc Mon Sep 17 00:00:00 2001
From: Pavel Shilovsky <piastryyy@gmail.com>
Date: Mon, 30 Sep 2019 10:06:19 -0700
Subject: CIFS: Force revalidate inode when dentry is stale

Currently the client indicates that a dentry is stale when inode
numbers or type types between a local inode and a remote file
don't match. If this is the case attributes is not being copied
from remote to local, so, it is already known that the local copy
has stale metadata. That's why the inode needs to be marked for
revalidation in order to tell the VFS to lookup the dentry again
before openning a file. This prevents unexpected stale errors
to be returned to the user space when openning a file.

Cc: <stable@vger.kernel.org>
Signed-off-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/inode.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 3bae2e53f0b8..5dcc95b38310 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -414,6 +414,7 @@ int cifs_get_inode_info_unix(struct inode **pinode,
 		/* if uniqueid is different, return error */
 		if (unlikely(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM &&
 		    CIFS_I(*pinode)->uniqueid != fattr.cf_uniqueid)) {
+			CIFS_I(*pinode)->time = 0; /* force reval */
 			rc = -ESTALE;
 			goto cgiiu_exit;
 		}
@@ -421,6 +422,7 @@ int cifs_get_inode_info_unix(struct inode **pinode,
 		/* if filetype is different, return error */
 		if (unlikely(((*pinode)->i_mode & S_IFMT) !=
 		    (fattr.cf_mode & S_IFMT))) {
+			CIFS_I(*pinode)->time = 0; /* force reval */
 			rc = -ESTALE;
 			goto cgiiu_exit;
 		}
@@ -933,6 +935,7 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
 		/* if uniqueid is different, return error */
 		if (unlikely(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM &&
 		    CIFS_I(*inode)->uniqueid != fattr.cf_uniqueid)) {
+			CIFS_I(*inode)->time = 0; /* force reval */
 			rc = -ESTALE;
 			goto cgii_exit;
 		}
@@ -940,6 +943,7 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
 		/* if filetype is different, return error */
 		if (unlikely(((*inode)->i_mode & S_IFMT) !=
 		    (fattr.cf_mode & S_IFMT))) {
+			CIFS_I(*inode)->time = 0; /* force reval */
 			rc = -ESTALE;
 			goto cgii_exit;
 		}
-- 
cgit v1.2.3


From 0b3d0ef9840f7be202393ca9116b857f6f793715 Mon Sep 17 00:00:00 2001
From: Pavel Shilovsky <piastryyy@gmail.com>
Date: Mon, 30 Sep 2019 10:06:20 -0700
Subject: CIFS: Force reval dentry if LOOKUP_REVAL flag is set

Mark inode for force revalidation if LOOKUP_REVAL flag is set.
This tells the client to actually send a QueryInfo request to
the server to obtain the latest metadata in case a directory
or a file were changed remotely. Only do that if the client
doesn't have a lease for the file to avoid unneeded round
trips to the server.

Cc: <stable@vger.kernel.org>
Signed-off-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/dir.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index dd5ac841aefa..7ce689d31aa2 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -738,10 +738,16 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 static int
 cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
 {
+	struct inode *inode;
+
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	if (d_really_is_positive(direntry)) {
+		inode = d_inode(direntry);
+		if ((flags & LOOKUP_REVAL) && !CIFS_CACHE_READ(CIFS_I(inode)))
+			CIFS_I(inode)->time = 0; /* force reval */
+
 		if (cifs_revalidate_dentry(direntry))
 			return 0;
 		else {
@@ -752,7 +758,7 @@ cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
 			 * attributes will have been updated by
 			 * cifs_revalidate_dentry().
 			 */
-			if (IS_AUTOMOUNT(d_inode(direntry)) &&
+			if (IS_AUTOMOUNT(inode) &&
 			   !(direntry->d_flags & DCACHE_NEED_AUTOMOUNT)) {
 				spin_lock(&direntry->d_lock);
 				direntry->d_flags |= DCACHE_NEED_AUTOMOUNT;
-- 
cgit v1.2.3


From 18217da36103c25d87870624dfa569e6b9906a90 Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Mon, 30 Sep 2019 10:13:42 +1000
Subject: powerpc/64s/radix: Fix build failure with RADIX_MMU=n

After merging the powerpc tree, today's linux-next build (powerpc64
allnoconfig) failed like this:

 arch/powerpc/mm/book3s64/pgtable.c:216:3:
 error: implicit declaration of function 'radix__flush_all_lpid_guest'

radix__flush_all_lpid_guest() is only declared for
CONFIG_PPC_RADIX_MMU which is not set for this build.

Fix it by adding an empty version for the RADIX_MMU=n case, which
should never be called.

Fixes: 99161de3a283 ("powerpc/64s/radix: tidy up TLB flushing code")
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
[mpe: Munge change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190930101342.36c1afa0@canb.auug.org.au
---
 arch/powerpc/include/asm/book3s/64/tlbflush-radix.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 4ce795d30377..ca8db193ae38 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -35,6 +35,10 @@ static inline void radix__flush_all_lpid(unsigned int lpid)
 {
 	WARN_ON(1);
 }
+static inline void radix__flush_all_lpid_guest(unsigned int lpid)
+{
+	WARN_ON(1);
+}
 #endif
 
 extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma,
-- 
cgit v1.2.3


From 4ab8a485f7bc69e04e3e8d75f62bdcac5f4ed02e Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour@linux.ibm.com>
Date: Tue, 1 Oct 2019 15:29:28 +0200
Subject: powerpc/pseries: Remove confusing warning message.

Since commit 1211ee61b4a8 ("powerpc/pseries: Read TLB Block Invalidate
Characteristics"), a warning message is displayed when booting a guest
on top of KVM:

  lpar: arch/powerpc/platforms/pseries/lpar.c pseries_lpar_read_hblkrm_characteristics Error calling get-system-parameter (0xfffffffd)

This message is displayed because this hypervisor is not supporting
the H_BLOCK_REMOVE hcall and thus is not exposing the corresponding
feature.

Reading the TLB Block Invalidate Characteristics should not be done if
the feature is not exposed.

Fixes: 1211ee61b4a8 ("powerpc/pseries: Read TLB Block Invalidate Characteristics")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191001132928.72555-1-ldufour@linux.ibm.com
---
 arch/powerpc/platforms/pseries/lpar.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index b53359258d99..f87a5c64e24d 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -1419,6 +1419,9 @@ void __init pseries_lpar_read_hblkrm_characteristics(void)
 	unsigned char local_buffer[SPLPAR_TLB_BIC_MAXLENGTH];
 	int call_status, len, idx, bpsize;
 
+	if (!firmware_has_feature(FW_FEATURE_BLOCK_REMOVE))
+		return;
+
 	spin_lock(&rtas_data_buf_lock);
 	memset(rtas_data_buf, 0, RTAS_DATA_BUF_SIZE);
 	call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
-- 
cgit v1.2.3


From 5b216ea1c40cf06eead15054c70e238c9bd4729e Mon Sep 17 00:00:00 2001
From: "Desnes A. Nunes do Rosario" <desnesn@linux.ibm.com>
Date: Thu, 3 Oct 2019 18:10:10 -0300
Subject: selftests/powerpc: Fix compile error on tlbie_test due to newer gcc

Newer versions of GCC (>= 9) demand that the size of the string to be
copied must be explicitly smaller than the size of the destination.
Thus, the NULL char has to be taken into account on strncpy.

This will avoid the following compiling error:

  tlbie_test.c: In function 'main':
  tlbie_test.c:639:4: error: 'strncpy' specified bound 100 equals destination size
      strncpy(logdir, optarg, LOGDIR_NAME_SIZE);
      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  cc1: all warnings being treated as errors

Signed-off-by: Desnes A. Nunes do Rosario <desnesn@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191003211010.9711-1-desnesn@linux.ibm.com
---
 tools/testing/selftests/powerpc/mm/tlbie_test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/powerpc/mm/tlbie_test.c b/tools/testing/selftests/powerpc/mm/tlbie_test.c
index 9868a5ddd847..f85a0938ab25 100644
--- a/tools/testing/selftests/powerpc/mm/tlbie_test.c
+++ b/tools/testing/selftests/powerpc/mm/tlbie_test.c
@@ -636,7 +636,7 @@ int main(int argc, char *argv[])
 			nrthreads = strtoul(optarg, NULL, 10);
 			break;
 		case 'l':
-			strncpy(logdir, optarg, LOGDIR_NAME_SIZE);
+			strncpy(logdir, optarg, LOGDIR_NAME_SIZE - 1);
 			break;
 		case 't':
 			run_time = strtoul(optarg, NULL, 10);
-- 
cgit v1.2.3


From 7fe4e1176dfe47a243d8edd98d26abd11f91b042 Mon Sep 17 00:00:00 2001
From: Jordan Niethe <jniethe5@gmail.com>
Date: Fri, 4 Oct 2019 12:53:17 +1000
Subject: powerpc/kvm: Fix kvmppc_vcore->in_guest value in kvmhv_switch_to_host

kvmhv_switch_to_host() in arch/powerpc/kvm/book3s_hv_rmhandlers.S
needs to set kvmppc_vcore->in_guest to 0 to signal secondary CPUs to
continue. This happens after resetting the PCR. Before commit
13c7bb3c57dc ("powerpc/64s: Set reserved PCR bits"), r0 would always
be 0 before it was stored to kvmppc_vcore->in_guest. However because
of this change in the commit:

          /* Reset PCR */
          ld      r0, VCORE_PCR(r5)
  -       cmpdi   r0, 0
  +       LOAD_REG_IMMEDIATE(r6, PCR_MASK)
  +       cmpld   r0, r6
          beq     18f
  -       li      r0, 0
  -       mtspr   SPRN_PCR, r0
  +       mtspr   SPRN_PCR, r6
   18:
          /* Signal secondary CPUs to continue */
          stb     r0,VCORE_IN_GUEST(r5)

We are no longer comparing r0 against 0 and loading it with 0 if it
contains something else. Hence when we store r0 to
kvmppc_vcore->in_guest, it might not be 0. This means that secondary
CPUs will not be signalled to continue. Those CPUs get stuck and
errors like the following are logged:

    KVM: CPU 1 seems to be stuck
    KVM: CPU 2 seems to be stuck
    KVM: CPU 3 seems to be stuck
    KVM: CPU 4 seems to be stuck
    KVM: CPU 5 seems to be stuck
    KVM: CPU 6 seems to be stuck
    KVM: CPU 7 seems to be stuck

This can be reproduced with:
    $ for i in `seq 1 7` ; do chcpu -d $i ; done ;
    $ taskset -c 0 qemu-system-ppc64 -smp 8,threads=8 \
       -M pseries,accel=kvm,kvm-type=HV -m 1G -nographic -vga none \
       -kernel vmlinux -initrd initrd.cpio.xz

Fix by making sure r0 is 0 before storing it to
kvmppc_vcore->in_guest.

Fixes: 13c7bb3c57dc ("powerpc/64s: Set reserved PCR bits")
Reported-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
Reviewed-by: Alistair Popple <alistair@popple.id.au>
Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191004025317.19340-1-jniethe5@gmail.com
---
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 74a9cfe84aee..faebcbb8c4db 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1921,6 +1921,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_PCR, r6
 18:
 	/* Signal secondary CPUs to continue */
+	li	r0, 0
 	stb	r0,VCORE_IN_GUEST(r5)
 19:	lis	r8,0x7fff		/* MAX_INT@h */
 	mtspr	SPRN_HDEC,r8
-- 
cgit v1.2.3


From 41f0bc49f7f2014feab8b278fea2adaea6ccaf4e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 9 Oct 2019 07:17:59 +0100
Subject: drm/i915/selftests: Hold request reference over waits

Take a reference on the request before submitting it to the HW and then
waiting on it for selftest_workarounds. Once submitted, the request may
be freed by a background worker, unless we take an extra reference for
ourselves.

References: https://bugs.freedesktop.org/show_bug.cgi?id=111926
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191009061759.3189-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/selftest_workarounds.c | 73 ++++++++++++--------------
 1 file changed, 34 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 74952bda9256..1048be646c35 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -33,6 +33,30 @@ struct wa_lists {
 	} engine[I915_NUM_ENGINES];
 };
 
+static int request_add_sync(struct i915_request *rq, int err)
+{
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (i915_request_wait(rq, 0, HZ / 5) < 0)
+		err = -EIO;
+	i915_request_put(rq);
+
+	return err;
+}
+
+static int request_add_spin(struct i915_request *rq, struct igt_spinner *spin)
+{
+	int err = 0;
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (spin && !igt_wait_for_spinner(spin, rq))
+		err = -ETIMEDOUT;
+	i915_request_put(rq);
+
+	return err;
+}
+
 static void
 reference_lists_init(struct drm_i915_private *i915, struct wa_lists *lists)
 {
@@ -243,7 +267,6 @@ switch_to_scratch_context(struct intel_engine_cs *engine,
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
 	struct i915_request *rq;
-	intel_wakeref_t wakeref;
 	int err = 0;
 
 	ctx = kernel_context(engine->i915);
@@ -255,9 +278,7 @@ switch_to_scratch_context(struct intel_engine_cs *engine,
 	ce = i915_gem_context_get_engine(ctx, engine->legacy_idx);
 	GEM_BUG_ON(IS_ERR(ce));
 
-	rq = ERR_PTR(-ENODEV);
-	with_intel_runtime_pm(engine->uncore->rpm, wakeref)
-		rq = igt_spinner_create_request(spin, ce, MI_NOOP);
+	rq = igt_spinner_create_request(spin, ce, MI_NOOP);
 
 	intel_context_put(ce);
 
@@ -267,13 +288,7 @@ switch_to_scratch_context(struct intel_engine_cs *engine,
 		goto err;
 	}
 
-	i915_request_add(rq);
-
-	if (spin && !igt_wait_for_spinner(spin, rq)) {
-		pr_err("Spinner failed to start\n");
-		err = -ETIMEDOUT;
-	}
-
+	err = request_add_spin(rq, spin);
 err:
 	if (err && spin)
 		igt_spinner_end(spin);
@@ -586,15 +601,11 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 			goto err_request;
 
 err_request:
-		i915_request_add(rq);
-		if (err)
-			goto out_batch;
-
-		if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+		err = request_add_sync(rq, err);
+		if (err) {
 			pr_err("%s: Futzing %x timedout; cancelling test\n",
 			       engine->name, reg);
 			intel_gt_set_wedged(&ctx->i915->gt);
-			err = -EIO;
 			goto out_batch;
 		}
 
@@ -697,7 +708,6 @@ static int live_dirty_whitelist(void *arg)
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	struct drm_file *file;
 	int err = 0;
 
@@ -706,13 +716,9 @@ static int live_dirty_whitelist(void *arg)
 	if (INTEL_GEN(i915) < 7) /* minimum requirement for LRI, SRM, LRM */
 		return 0;
 
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	file = mock_file(i915);
-	if (IS_ERR(file)) {
-		err = PTR_ERR(file);
-		goto out_rpm;
-	}
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
 	ctx = live_context(i915, file);
 	if (IS_ERR(ctx)) {
@@ -731,8 +737,6 @@ static int live_dirty_whitelist(void *arg)
 
 out_file:
 	mock_file_free(i915, file);
-out_rpm:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 	return err;
 }
 
@@ -807,12 +811,7 @@ static int read_whitelisted_registers(struct i915_gem_context *ctx,
 	intel_ring_advance(rq, cs);
 
 err_req:
-	i915_request_add(rq);
-
-	if (i915_request_wait(rq, 0, HZ / 5) < 0)
-		err = -EIO;
-
-	return err;
+	return request_add_sync(rq, err);
 }
 
 static int scrub_whitelisted_registers(struct i915_gem_context *ctx,
@@ -872,9 +871,7 @@ static int scrub_whitelisted_registers(struct i915_gem_context *ctx,
 	err = engine->emit_bb_start(rq, batch->node.start, 0, 0);
 
 err_request:
-	i915_request_add(rq);
-	if (i915_request_wait(rq, 0, HZ / 5) < 0)
-		err = -EIO;
+	err = request_add_sync(rq, err);
 
 err_unpin:
 	i915_gem_object_unpin_map(batch->obj);
@@ -1229,12 +1226,10 @@ live_engine_reset_workarounds(void *arg)
 			goto err;
 		}
 
-		i915_request_add(rq);
-
-		if (!igt_wait_for_spinner(&spin, rq)) {
+		ret = request_add_spin(rq, &spin);
+		if (ret) {
 			pr_err("Spinner failed to start\n");
 			igt_spinner_fini(&spin);
-			ret = -ETIMEDOUT;
 			goto err;
 		}
 
-- 
cgit v1.2.3


From cefb6abfcc1cb49e21966117c5d881887a5cd4b8 Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:36 +0800
Subject: drm/mediatek: add ddp component CCORR

This patch add ddp component CCORR

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 32 +++++++++++++++++++++++++++++
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h |  2 ++
 2 files changed, 34 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index efa85973e46b..1f6df17b244e 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -33,6 +33,12 @@
 #define DISP_AAL_EN				0x0000
 #define DISP_AAL_SIZE				0x0030
 
+#define DISP_CCORR_EN				0x0000
+#define CCORR_EN				BIT(0)
+#define DISP_CCORR_CFG				0x0020
+#define CCORR_RELAY_MODE			BIT(0)
+#define DISP_CCORR_SIZE				0x0030
+
 #define DISP_GAMMA_EN				0x0000
 #define DISP_GAMMA_CFG				0x0020
 #define DISP_GAMMA_SIZE				0x0030
@@ -123,6 +129,24 @@ static void mtk_aal_stop(struct mtk_ddp_comp *comp)
 	writel_relaxed(0x0, comp->regs + DISP_AAL_EN);
 }
 
+static void mtk_ccorr_config(struct mtk_ddp_comp *comp, unsigned int w,
+			     unsigned int h, unsigned int vrefresh,
+			     unsigned int bpc)
+{
+	writel(h << 16 | w, comp->regs + DISP_CCORR_SIZE);
+	writel(CCORR_RELAY_MODE, comp->regs + DISP_CCORR_CFG);
+}
+
+static void mtk_ccorr_start(struct mtk_ddp_comp *comp)
+{
+	writel(CCORR_EN, comp->regs + DISP_CCORR_EN);
+}
+
+static void mtk_ccorr_stop(struct mtk_ddp_comp *comp)
+{
+	writel_relaxed(0x0, comp->regs + DISP_CCORR_EN);
+}
+
 static void mtk_gamma_config(struct mtk_ddp_comp *comp, unsigned int w,
 			     unsigned int h, unsigned int vrefresh,
 			     unsigned int bpc)
@@ -171,6 +195,12 @@ static const struct mtk_ddp_comp_funcs ddp_aal = {
 	.stop = mtk_aal_stop,
 };
 
+static const struct mtk_ddp_comp_funcs ddp_ccorr = {
+	.config = mtk_ccorr_config,
+	.start = mtk_ccorr_start,
+	.stop = mtk_ccorr_stop,
+};
+
 static const struct mtk_ddp_comp_funcs ddp_gamma = {
 	.gamma_set = mtk_gamma_set,
 	.config = mtk_gamma_config,
@@ -192,6 +222,7 @@ static const char * const mtk_ddp_comp_stem[MTK_DDP_COMP_TYPE_MAX] = {
 	[MTK_DISP_RDMA] = "rdma",
 	[MTK_DISP_WDMA] = "wdma",
 	[MTK_DISP_COLOR] = "color",
+	[MTK_DISP_CCORR] = "ccorr",
 	[MTK_DISP_AAL] = "aal",
 	[MTK_DISP_GAMMA] = "gamma",
 	[MTK_DISP_UFOE] = "ufoe",
@@ -213,6 +244,7 @@ static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_AAL0]	= { MTK_DISP_AAL,	0, &ddp_aal },
 	[DDP_COMPONENT_AAL1]	= { MTK_DISP_AAL,	1, &ddp_aal },
 	[DDP_COMPONENT_BLS]	= { MTK_DISP_BLS,	0, NULL },
+	[DDP_COMPONENT_CCORR]	= { MTK_DISP_CCORR,	0, &ddp_ccorr },
 	[DDP_COMPONENT_COLOR0]	= { MTK_DISP_COLOR,	0, NULL },
 	[DDP_COMPONENT_COLOR1]	= { MTK_DISP_COLOR,	1, NULL },
 	[DDP_COMPONENT_DPI0]	= { MTK_DPI,		0, NULL },
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 0ad287f427cc..b5869a1d3345 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -20,6 +20,7 @@ enum mtk_ddp_comp_type {
 	MTK_DISP_RDMA,
 	MTK_DISP_WDMA,
 	MTK_DISP_COLOR,
+	MTK_DISP_CCORR,
 	MTK_DISP_AAL,
 	MTK_DISP_GAMMA,
 	MTK_DISP_UFOE,
@@ -36,6 +37,7 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_AAL0,
 	DDP_COMPONENT_AAL1,
 	DDP_COMPONENT_BLS,
+	DDP_COMPONENT_CCORR,
 	DDP_COMPONENT_COLOR0,
 	DDP_COMPONENT_COLOR1,
 	DDP_COMPONENT_DPI0,
-- 
cgit v1.2.3


From 450aa87c7353d1e4c84fef77f57ca173c84cc172 Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:39 +0800
Subject: drm/mediatek: add component DITHER

This patch add component DITHER

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 32 +++++++++++++++++++++++++++++
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h |  2 ++
 2 files changed, 34 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 1f6df17b244e..74056a18dc34 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -39,6 +39,12 @@
 #define CCORR_RELAY_MODE			BIT(0)
 #define DISP_CCORR_SIZE				0x0030
 
+#define DISP_DITHER_EN				0x0000
+#define DITHER_EN				BIT(0)
+#define DISP_DITHER_CFG				0x0020
+#define DITHER_RELAY_MODE			BIT(0)
+#define DISP_DITHER_SIZE			0x0030
+
 #define DISP_GAMMA_EN				0x0000
 #define DISP_GAMMA_CFG				0x0020
 #define DISP_GAMMA_SIZE				0x0030
@@ -147,6 +153,24 @@ static void mtk_ccorr_stop(struct mtk_ddp_comp *comp)
 	writel_relaxed(0x0, comp->regs + DISP_CCORR_EN);
 }
 
+static void mtk_dither_config(struct mtk_ddp_comp *comp, unsigned int w,
+			      unsigned int h, unsigned int vrefresh,
+			      unsigned int bpc)
+{
+	writel(h << 16 | w, comp->regs + DISP_DITHER_SIZE);
+	writel(DITHER_RELAY_MODE, comp->regs + DISP_DITHER_CFG);
+}
+
+static void mtk_dither_start(struct mtk_ddp_comp *comp)
+{
+	writel(DITHER_EN, comp->regs + DISP_DITHER_EN);
+}
+
+static void mtk_dither_stop(struct mtk_ddp_comp *comp)
+{
+	writel_relaxed(0x0, comp->regs + DISP_DITHER_EN);
+}
+
 static void mtk_gamma_config(struct mtk_ddp_comp *comp, unsigned int w,
 			     unsigned int h, unsigned int vrefresh,
 			     unsigned int bpc)
@@ -201,6 +225,12 @@ static const struct mtk_ddp_comp_funcs ddp_ccorr = {
 	.stop = mtk_ccorr_stop,
 };
 
+static const struct mtk_ddp_comp_funcs ddp_dither = {
+	.config = mtk_dither_config,
+	.start = mtk_dither_start,
+	.stop = mtk_dither_stop,
+};
+
 static const struct mtk_ddp_comp_funcs ddp_gamma = {
 	.gamma_set = mtk_gamma_set,
 	.config = mtk_gamma_config,
@@ -225,6 +255,7 @@ static const char * const mtk_ddp_comp_stem[MTK_DDP_COMP_TYPE_MAX] = {
 	[MTK_DISP_CCORR] = "ccorr",
 	[MTK_DISP_AAL] = "aal",
 	[MTK_DISP_GAMMA] = "gamma",
+	[MTK_DISP_DITHER] = "dither",
 	[MTK_DISP_UFOE] = "ufoe",
 	[MTK_DSI] = "dsi",
 	[MTK_DPI] = "dpi",
@@ -247,6 +278,7 @@ static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_CCORR]	= { MTK_DISP_CCORR,	0, &ddp_ccorr },
 	[DDP_COMPONENT_COLOR0]	= { MTK_DISP_COLOR,	0, NULL },
 	[DDP_COMPONENT_COLOR1]	= { MTK_DISP_COLOR,	1, NULL },
+	[DDP_COMPONENT_DITHER]	= { MTK_DISP_DITHER,	0, &ddp_dither },
 	[DDP_COMPONENT_DPI0]	= { MTK_DPI,		0, NULL },
 	[DDP_COMPONENT_DPI1]	= { MTK_DPI,		1, NULL },
 	[DDP_COMPONENT_DSI0]	= { MTK_DSI,		0, NULL },
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index b5869a1d3345..c085e78a98bf 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -21,6 +21,7 @@ enum mtk_ddp_comp_type {
 	MTK_DISP_WDMA,
 	MTK_DISP_COLOR,
 	MTK_DISP_CCORR,
+	MTK_DISP_DITHER,
 	MTK_DISP_AAL,
 	MTK_DISP_GAMMA,
 	MTK_DISP_UFOE,
@@ -40,6 +41,7 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_CCORR,
 	DDP_COMPONENT_COLOR0,
 	DDP_COMPONENT_COLOR1,
+	DDP_COMPONENT_DITHER,
 	DDP_COMPONENT_DPI0,
 	DDP_COMPONENT_DPI1,
 	DDP_COMPONENT_DSI0,
-- 
cgit v1.2.3


From b17bdd0d7a733caf0b794af7db9fd07a57d450fd Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:37 +0800
Subject: drm/mediatek: add component OVL_2L0

This patch add component OVL_2L0

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 2 ++
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h | 2 ++
 drivers/gpu/drm/mediatek/mtk_drm_drv.c      | 1 +
 3 files changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 74056a18dc34..10b6574de59b 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -249,6 +249,7 @@ static const struct mtk_ddp_comp_funcs ddp_ufoe = {
 
 static const char * const mtk_ddp_comp_stem[MTK_DDP_COMP_TYPE_MAX] = {
 	[MTK_DISP_OVL] = "ovl",
+	[MTK_DISP_OVL_2L] = "ovl_2l",
 	[MTK_DISP_RDMA] = "rdma",
 	[MTK_DISP_WDMA] = "wdma",
 	[MTK_DISP_COLOR] = "color",
@@ -290,6 +291,7 @@ static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_OD1]	= { MTK_DISP_OD,	1, &ddp_od },
 	[DDP_COMPONENT_OVL0]	= { MTK_DISP_OVL,	0, NULL },
 	[DDP_COMPONENT_OVL1]	= { MTK_DISP_OVL,	1, NULL },
+	[DDP_COMPONENT_OVL_2L0]	= { MTK_DISP_OVL_2L,	0, NULL },
 	[DDP_COMPONENT_PWM0]	= { MTK_DISP_PWM,	0, NULL },
 	[DDP_COMPONENT_PWM1]	= { MTK_DISP_PWM,	1, NULL },
 	[DDP_COMPONENT_PWM2]	= { MTK_DISP_PWM,	2, NULL },
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index c085e78a98bf..a04622e5f4cb 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -17,6 +17,7 @@ struct drm_crtc_state;
 
 enum mtk_ddp_comp_type {
 	MTK_DISP_OVL,
+	MTK_DISP_OVL_2L,
 	MTK_DISP_RDMA,
 	MTK_DISP_WDMA,
 	MTK_DISP_COLOR,
@@ -52,6 +53,7 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_OD0,
 	DDP_COMPONENT_OD1,
 	DDP_COMPONENT_OVL0,
+	DDP_COMPONENT_OVL_2L0,
 	DDP_COMPONENT_OVL1,
 	DDP_COMPONENT_PWM0,
 	DDP_COMPONENT_PWM1,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 62845ad4f542..84d14213d992 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -547,6 +547,7 @@ static int mtk_drm_probe(struct platform_device *pdev)
 		 */
 		if (comp_type == MTK_DISP_COLOR ||
 		    comp_type == MTK_DISP_OVL ||
+		    comp_type == MTK_DISP_OVL_2L ||
 		    comp_type == MTK_DISP_RDMA ||
 		    comp_type == MTK_DSI ||
 		    comp_type == MTK_DPI) {
-- 
cgit v1.2.3


From dd8feb2262d988ee870224c27264ef2163579f9c Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:38 +0800
Subject: drm/mediatek: add component OVL_2L1

This patch add component OVL_2L1

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 1 +
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 10b6574de59b..7f21307cda75 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -292,6 +292,7 @@ static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_OVL0]	= { MTK_DISP_OVL,	0, NULL },
 	[DDP_COMPONENT_OVL1]	= { MTK_DISP_OVL,	1, NULL },
 	[DDP_COMPONENT_OVL_2L0]	= { MTK_DISP_OVL_2L,	0, NULL },
+	[DDP_COMPONENT_OVL_2L1]	= { MTK_DISP_OVL_2L,	1, NULL },
 	[DDP_COMPONENT_PWM0]	= { MTK_DISP_PWM,	0, NULL },
 	[DDP_COMPONENT_PWM1]	= { MTK_DISP_PWM,	1, NULL },
 	[DDP_COMPONENT_PWM2]	= { MTK_DISP_PWM,	2, NULL },
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index a04622e5f4cb..61d53be9c33b 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -54,6 +54,7 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_OD1,
 	DDP_COMPONENT_OVL0,
 	DDP_COMPONENT_OVL_2L0,
+	DDP_COMPONENT_OVL_2L1,
 	DDP_COMPONENT_OVL1,
 	DDP_COMPONENT_PWM0,
 	DDP_COMPONENT_PWM1,
-- 
cgit v1.2.3


From d5abb5f2144a8f54e599eaf57dfac7864e130dcc Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:40 +0800
Subject: drm/mediatek: add gmc_bits for ovl private data

This patch add gmc_bits for ovl private data
GMC register was set RDMA ultra and pre-ultra threshold.
10bit GMC register define is different with other SOC, gmc_thrshd_l not
used.

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 21851756c579..6491c2582530 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -31,7 +31,9 @@
 #define DISP_REG_OVL_ADDR_MT8173		0x0f40
 #define DISP_REG_OVL_ADDR(ovl, n)		((ovl)->data->addr + 0x20 * (n))
 
-#define	OVL_RDMA_MEM_GMC	0x40402020
+#define GMC_THRESHOLD_BITS	16
+#define GMC_THRESHOLD_HIGH	((1 << GMC_THRESHOLD_BITS) / 4)
+#define GMC_THRESHOLD_LOW	((1 << GMC_THRESHOLD_BITS) / 8)
 
 #define OVL_CON_BYTE_SWAP	BIT(24)
 #define OVL_CON_MTX_YUV_TO_RGB	(6 << 16)
@@ -49,6 +51,7 @@
 
 struct mtk_disp_ovl_data {
 	unsigned int addr;
+	unsigned int gmc_bits;
 	bool fmt_rgb565_is_0;
 };
 
@@ -132,9 +135,23 @@ static unsigned int mtk_ovl_layer_nr(struct mtk_ddp_comp *comp)
 static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx)
 {
 	unsigned int reg;
+	unsigned int gmc_thrshd_l;
+	unsigned int gmc_thrshd_h;
+	unsigned int gmc_value;
+	struct mtk_disp_ovl *ovl = comp_to_ovl(comp);
 
 	writel(0x1, comp->regs + DISP_REG_OVL_RDMA_CTRL(idx));
-	writel(OVL_RDMA_MEM_GMC, comp->regs + DISP_REG_OVL_RDMA_GMC(idx));
+
+	gmc_thrshd_l = GMC_THRESHOLD_LOW >>
+		      (GMC_THRESHOLD_BITS - ovl->data->gmc_bits);
+	gmc_thrshd_h = GMC_THRESHOLD_HIGH >>
+		      (GMC_THRESHOLD_BITS - ovl->data->gmc_bits);
+	if (ovl->data->gmc_bits == 10)
+		gmc_value = gmc_thrshd_h | gmc_thrshd_h << 16;
+	else
+		gmc_value = gmc_thrshd_l | gmc_thrshd_l << 8 |
+			    gmc_thrshd_h << 16 | gmc_thrshd_h << 24;
+	writel(gmc_value, comp->regs + DISP_REG_OVL_RDMA_GMC(idx));
 
 	reg = readl(comp->regs + DISP_REG_OVL_SRC_CON);
 	reg = reg | BIT(idx);
@@ -316,11 +333,13 @@ static int mtk_disp_ovl_remove(struct platform_device *pdev)
 
 static const struct mtk_disp_ovl_data mt2701_ovl_driver_data = {
 	.addr = DISP_REG_OVL_ADDR_MT2701,
+	.gmc_bits = 8,
 	.fmt_rgb565_is_0 = false,
 };
 
 static const struct mtk_disp_ovl_data mt8173_ovl_driver_data = {
 	.addr = DISP_REG_OVL_ADDR_MT8173,
+	.gmc_bits = 8,
 	.fmt_rgb565_is_0 = true,
 };
 
-- 
cgit v1.2.3


From 0a5ccda42033517c463749737bc9b81c52239e16 Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:41 +0800
Subject: drm/medaitek: add layer_nr for ovl private data

This patch add layer_nr for ovl private data
ovl_2l almost same with with ovl hardware, except the
layer number for ovl_2l is 2 and ovl is 4.
this patch is a preparation for ovl-2l and
ovl share the same driver.

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 6491c2582530..11b20490087a 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -52,6 +52,7 @@
 struct mtk_disp_ovl_data {
 	unsigned int addr;
 	unsigned int gmc_bits;
+	unsigned int layer_nr;
 	bool fmt_rgb565_is_0;
 };
 
@@ -129,7 +130,9 @@ static void mtk_ovl_config(struct mtk_ddp_comp *comp, unsigned int w,
 
 static unsigned int mtk_ovl_layer_nr(struct mtk_ddp_comp *comp)
 {
-	return 4;
+	struct mtk_disp_ovl *ovl = comp_to_ovl(comp);
+
+	return ovl->data->layer_nr;
 }
 
 static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx)
@@ -334,12 +337,14 @@ static int mtk_disp_ovl_remove(struct platform_device *pdev)
 static const struct mtk_disp_ovl_data mt2701_ovl_driver_data = {
 	.addr = DISP_REG_OVL_ADDR_MT2701,
 	.gmc_bits = 8,
+	.layer_nr = 4,
 	.fmt_rgb565_is_0 = false,
 };
 
 static const struct mtk_disp_ovl_data mt8173_ovl_driver_data = {
 	.addr = DISP_REG_OVL_ADDR_MT8173,
 	.gmc_bits = 8,
+	.layer_nr = 4,
 	.fmt_rgb565_is_0 = true,
 };
 
-- 
cgit v1.2.3


From 132c6e250ed745443973cada8db17cdbaebdf551 Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:42 +0800
Subject: drm/mediatek: add function to background color input select for
 ovl/ovl_2l direct link

This patch add function to background color input select for ovl/ovl_2l
direct link for ovl/ovl_2l direct link usecase, we need set background
color input select for these hardware. This is preparation patch for
ovl/ovl_2l usecase.

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 61d53be9c33b..26441f4d1ad3 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -84,6 +84,8 @@ struct mtk_ddp_comp_funcs {
 			     struct mtk_plane_state *state);
 	void (*gamma_set)(struct mtk_ddp_comp *comp,
 			  struct drm_crtc_state *state);
+	void (*bgclr_in_on)(struct mtk_ddp_comp *comp);
+	void (*bgclr_in_off)(struct mtk_ddp_comp *comp);
 };
 
 struct mtk_ddp_comp {
@@ -165,6 +167,18 @@ static inline void mtk_ddp_gamma_set(struct mtk_ddp_comp *comp,
 		comp->funcs->gamma_set(comp, state);
 }
 
+static inline void mtk_ddp_comp_bgclr_in_on(struct mtk_ddp_comp *comp)
+{
+	if (comp->funcs && comp->funcs->bgclr_in_on)
+		comp->funcs->bgclr_in_on(comp);
+}
+
+static inline void mtk_ddp_comp_bgclr_in_off(struct mtk_ddp_comp *comp)
+{
+	if (comp->funcs && comp->funcs->bgclr_in_off)
+		comp->funcs->bgclr_in_off(comp);
+}
+
 int mtk_ddp_comp_get_id(struct device_node *node,
 			enum mtk_ddp_comp_type comp_type);
 int mtk_ddp_comp_init(struct device *dev, struct device_node *comp_node,
-- 
cgit v1.2.3


From 318462d1a568634ba09263cc730cb0fb1d56c2b3 Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:43 +0800
Subject: drm/mediatek: add background color input select function for
 ovl/ovl_2l

This patch add background color input select function for ovl/ovl_2l

ovl include 4 DRAM layer and 1 background color layer
ovl_2l include 4 DRAM layer and 1 background color layer
DRAM layer frame buffer data from render hardware, GPU for example.
backgournd color layer is embed in ovl/ovl_2l, we can only set
it color, but not support DRAM frame buffer.

for ovl0->ovl0_2l direct link usecase,
we need set ovl0_2l background color intput select from ovl0
if render send DRAM buffer layer number <=4, all these layer read
by ovl.
layer0 is at the bottom of all layers.
layer3 is at the top of all layers.
if render send DRAM buffer layer numbfer >=4 && <=6
ovl0 read layer0~3
ovl0_2l read layer4~5
layer5 is at the top ot all these layers.

the decision of how to setting ovl0/ovl0_2l read these layer data
is controlled in mtk crtc, which will be another patch

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 11b20490087a..7a87196cb570 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -19,6 +19,8 @@
 #define DISP_REG_OVL_EN				0x000c
 #define DISP_REG_OVL_RST			0x0014
 #define DISP_REG_OVL_ROI_SIZE			0x0020
+#define DISP_REG_OVL_DATAPATH_CON		0x0024
+#define OVL_BGCLR_SEL_IN				BIT(2)
 #define DISP_REG_OVL_ROI_BGCLR			0x0028
 #define DISP_REG_OVL_SRC_CON			0x002c
 #define DISP_REG_OVL_CON(n)			(0x0030 + 0x20 * (n))
@@ -237,6 +239,24 @@ static void mtk_ovl_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
 		mtk_ovl_layer_on(comp, idx);
 }
 
+static void mtk_ovl_bgclr_in_on(struct mtk_ddp_comp *comp)
+{
+	unsigned int reg;
+
+	reg = readl(comp->regs + DISP_REG_OVL_DATAPATH_CON);
+	reg = reg | OVL_BGCLR_SEL_IN;
+	writel(reg, comp->regs + DISP_REG_OVL_DATAPATH_CON);
+}
+
+static void mtk_ovl_bgclr_in_off(struct mtk_ddp_comp *comp)
+{
+	unsigned int reg;
+
+	reg = readl(comp->regs + DISP_REG_OVL_DATAPATH_CON);
+	reg = reg & ~OVL_BGCLR_SEL_IN;
+	writel(reg, comp->regs + DISP_REG_OVL_DATAPATH_CON);
+}
+
 static const struct mtk_ddp_comp_funcs mtk_disp_ovl_funcs = {
 	.config = mtk_ovl_config,
 	.start = mtk_ovl_start,
@@ -247,6 +267,8 @@ static const struct mtk_ddp_comp_funcs mtk_disp_ovl_funcs = {
 	.layer_on = mtk_ovl_layer_on,
 	.layer_off = mtk_ovl_layer_off,
 	.layer_config = mtk_ovl_layer_config,
+	.bgclr_in_on = mtk_ovl_bgclr_in_on,
+	.bgclr_in_off = mtk_ovl_bgclr_in_off,
 };
 
 static int mtk_disp_ovl_bind(struct device *dev, struct device *master,
-- 
cgit v1.2.3


From 57148baac8b78461e394953cfd5317bde8f795ab Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:45 +0800
Subject: drm/mediatek: distinguish ovl and ovl_2l by layer_nr

distinguish ovl and ovl_2l by layer_nr when get comp
id

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 7a87196cb570..14878ebf59d7 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -318,7 +318,12 @@ static int mtk_disp_ovl_probe(struct platform_device *pdev)
 	if (irq < 0)
 		return irq;
 
-	comp_id = mtk_ddp_comp_get_id(dev->of_node, MTK_DISP_OVL);
+	priv->data = of_device_get_match_data(dev);
+
+	comp_id = mtk_ddp_comp_get_id(dev->of_node,
+				      priv->data->layer_nr == 4 ?
+				      MTK_DISP_OVL :
+				      MTK_DISP_OVL_2L);
 	if (comp_id < 0) {
 		dev_err(dev, "Failed to identify by alias: %d\n", comp_id);
 		return comp_id;
@@ -331,8 +336,6 @@ static int mtk_disp_ovl_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	priv->data = of_device_get_match_data(dev);
-
 	platform_set_drvdata(pdev, priv);
 
 	ret = devm_request_irq(dev, irq, mtk_disp_ovl_irq_handler,
-- 
cgit v1.2.3


From 412b1e463ec3200970218d7c23bd4310da55b894 Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:44 +0800
Subject: drm/mediatek: add ovl0/ovl_2l0 usecase

This patch add ovl0/ovl_2l0 usecase
in ovl->ovl_2l0 direct link usecase:
1. the crtc support layer number will 4+2
2. ovl_2l0 background color input select ovl0 when crtc init
and disable it when crtc finish
3. config ovl_2l0 layer, if crtc config layer number is
bigger than ovl0 support layers(max is 4)

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_crtc.c | 37 ++++++++++++++++++++++++++++++---
 1 file changed, 34 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 34a731755791..b841d3706d8b 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -272,6 +272,9 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
 		struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[i];
 
+		if (i == 1)
+			mtk_ddp_comp_bgclr_in_on(comp);
+
 		mtk_ddp_comp_config(comp, width, height, vrefresh, bpc);
 		mtk_ddp_comp_start(comp);
 	}
@@ -280,9 +283,18 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 	for (i = 0; i < mtk_crtc->layer_nr; i++) {
 		struct drm_plane *plane = &mtk_crtc->planes[i];
 		struct mtk_plane_state *plane_state;
+		struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[0];
+		unsigned int comp_layer_nr = mtk_ddp_comp_layer_nr(comp);
+		unsigned int local_layer;
 
 		plane_state = to_mtk_plane_state(plane->state);
-		mtk_ddp_comp_layer_config(mtk_crtc->ddp_comp[0], i,
+
+		if (i >= comp_layer_nr) {
+			comp = mtk_crtc->ddp_comp[1];
+			local_layer = i - comp_layer_nr;
+		} else
+			local_layer = i;
+		mtk_ddp_comp_layer_config(comp, local_layer,
 					  plane_state);
 	}
 
@@ -301,8 +313,12 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc)
 	int i;
 
 	DRM_DEBUG_DRIVER("%s\n", __func__);
-	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++)
+	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
 		mtk_ddp_comp_stop(mtk_crtc->ddp_comp[i]);
+		if (i == 1)
+			mtk_ddp_comp_bgclr_in_off(mtk_crtc->ddp_comp[i]);
+	}
+
 	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++)
 		mtk_disp_mutex_remove_comp(mtk_crtc->mutex,
 					   mtk_crtc->ddp_comp[i]->id);
@@ -327,6 +343,8 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
 	struct mtk_crtc_state *state = to_mtk_crtc_state(mtk_crtc->base.state);
 	struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[0];
 	unsigned int i;
+	unsigned int comp_layer_nr = mtk_ddp_comp_layer_nr(comp);
+	unsigned int local_layer;
 
 	/*
 	 * TODO: instead of updating the registers here, we should prepare
@@ -349,7 +367,14 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
 			plane_state = to_mtk_plane_state(plane->state);
 
 			if (plane_state->pending.config) {
-				mtk_ddp_comp_layer_config(comp, i, plane_state);
+				if (i >= comp_layer_nr) {
+					comp = mtk_crtc->ddp_comp[1];
+					local_layer = i - comp_layer_nr;
+				} else
+					local_layer = i;
+
+				mtk_ddp_comp_layer_config(comp, local_layer,
+							  plane_state);
 				plane_state->pending.config = false;
 			}
 		}
@@ -582,6 +607,12 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	}
 
 	mtk_crtc->layer_nr = mtk_ddp_comp_layer_nr(mtk_crtc->ddp_comp[0]);
+	if (mtk_crtc->ddp_comp_nr > 1) {
+		struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[1];
+
+		if (comp->funcs->bgclr_in_on)
+			mtk_crtc->layer_nr += mtk_ddp_comp_layer_nr(comp);
+	}
 	mtk_crtc->planes = devm_kcalloc(dev, mtk_crtc->layer_nr,
 					sizeof(struct drm_plane),
 					GFP_KERNEL);
-- 
cgit v1.2.3


From 0d3a120286f48662d73533cc246199a40395823b Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:29 +0800
Subject: drm/mediatek: add mutex mod into ddp private data

except mutex mod, mutex mod reg,mutex sof reg,
and mutex sof id will be ddp private data

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 41 +++++++++++++++++++++++++---------
 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 8106a71a7404..b6cc3d852d53 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -139,12 +139,16 @@ struct mtk_disp_mutex {
 	bool claimed;
 };
 
+struct mtk_ddp_data {
+	const unsigned int *mutex_mod;
+};
+
 struct mtk_ddp {
 	struct device			*dev;
 	struct clk			*clk;
 	void __iomem			*regs;
 	struct mtk_disp_mutex		mutex[10];
-	const unsigned int		*mutex_mod;
+	const struct mtk_ddp_data	*data;
 };
 
 static const unsigned int mt2701_mutex_mod[DDP_COMPONENT_ID_MAX] = {
@@ -194,6 +198,18 @@ static const unsigned int mt8173_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_WDMA1] = MT8173_MUTEX_MOD_DISP_WDMA1,
 };
 
+static const struct mtk_ddp_data mt2701_ddp_driver_data = {
+	.mutex_mod = mt2701_mutex_mod,
+};
+
+static const struct mtk_ddp_data mt2712_ddp_driver_data = {
+	.mutex_mod = mt2712_mutex_mod,
+};
+
+static const struct mtk_ddp_data mt8173_ddp_driver_data = {
+	.mutex_mod = mt8173_mutex_mod,
+};
+
 static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 				    enum mtk_ddp_comp_id next,
 				    unsigned int *addr)
@@ -456,15 +472,15 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 		reg = MUTEX_SOF_DPI1;
 		break;
 	default:
-		if (ddp->mutex_mod[id] < 32) {
+		if (ddp->data->mutex_mod[id] < 32) {
 			offset = DISP_REG_MUTEX_MOD(mutex->id);
 			reg = readl_relaxed(ddp->regs + offset);
-			reg |= 1 << ddp->mutex_mod[id];
+			reg |= 1 << ddp->data->mutex_mod[id];
 			writel_relaxed(reg, ddp->regs + offset);
 		} else {
 			offset = DISP_REG_MUTEX_MOD2(mutex->id);
 			reg = readl_relaxed(ddp->regs + offset);
-			reg |= 1 << (ddp->mutex_mod[id] - 32);
+			reg |= 1 << (ddp->data->mutex_mod[id] - 32);
 			writel_relaxed(reg, ddp->regs + offset);
 		}
 		return;
@@ -494,15 +510,15 @@ void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
 			       ddp->regs + DISP_REG_MUTEX_SOF(mutex->id));
 		break;
 	default:
-		if (ddp->mutex_mod[id] < 32) {
+		if (ddp->data->mutex_mod[id] < 32) {
 			offset = DISP_REG_MUTEX_MOD(mutex->id);
 			reg = readl_relaxed(ddp->regs + offset);
-			reg &= ~(1 << ddp->mutex_mod[id]);
+			reg &= ~(1 << ddp->data->mutex_mod[id]);
 			writel_relaxed(reg, ddp->regs + offset);
 		} else {
 			offset = DISP_REG_MUTEX_MOD2(mutex->id);
 			reg = readl_relaxed(ddp->regs + offset);
-			reg &= ~(1 << (ddp->mutex_mod[id] - 32));
+			reg &= ~(1 << (ddp->data->mutex_mod[id] - 32));
 			writel_relaxed(reg, ddp->regs + offset);
 		}
 		break;
@@ -577,7 +593,7 @@ static int mtk_ddp_probe(struct platform_device *pdev)
 		return PTR_ERR(ddp->regs);
 	}
 
-	ddp->mutex_mod = of_device_get_match_data(dev);
+	ddp->data = of_device_get_match_data(dev);
 
 	platform_set_drvdata(pdev, ddp);
 
@@ -590,9 +606,12 @@ static int mtk_ddp_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id ddp_driver_dt_match[] = {
-	{ .compatible = "mediatek,mt2701-disp-mutex", .data = mt2701_mutex_mod},
-	{ .compatible = "mediatek,mt2712-disp-mutex", .data = mt2712_mutex_mod},
-	{ .compatible = "mediatek,mt8173-disp-mutex", .data = mt8173_mutex_mod},
+	{ .compatible = "mediatek,mt2701-disp-mutex",
+	  .data = &mt2701_ddp_driver_data},
+	{ .compatible = "mediatek,mt2712-disp-mutex",
+	  .data = &mt2712_ddp_driver_data},
+	{ .compatible = "mediatek,mt8173-disp-mutex",
+	  .data = &mt8173_ddp_driver_data},
 	{},
 };
 MODULE_DEVICE_TABLE(of, ddp_driver_dt_match);
-- 
cgit v1.2.3


From d730af989e99610b1d79b9dae21758343ab7233d Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:30 +0800
Subject: drm/mediatek: add mutex mod register offset into ddp private data

mutex mod register offset will be private data of ddp.

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index b6cc3d852d53..ae22e21e988c 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -33,12 +33,14 @@
 #define DISP_REG_CONFIG_DSI_SEL			0x050
 #define DISP_REG_CONFIG_DPI_SEL			0x064
 
-#define DISP_REG_MUTEX_EN(n)	(0x20 + 0x20 * (n))
-#define DISP_REG_MUTEX(n)	(0x24 + 0x20 * (n))
-#define DISP_REG_MUTEX_RST(n)	(0x28 + 0x20 * (n))
-#define DISP_REG_MUTEX_MOD(n)	(0x2c + 0x20 * (n))
-#define DISP_REG_MUTEX_SOF(n)	(0x30 + 0x20 * (n))
-#define DISP_REG_MUTEX_MOD2(n)	(0x34 + 0x20 * (n))
+#define MT2701_DISP_MUTEX0_MOD0			0x2c
+
+#define DISP_REG_MUTEX_EN(n)			(0x20 + 0x20 * (n))
+#define DISP_REG_MUTEX(n)			(0x24 + 0x20 * (n))
+#define DISP_REG_MUTEX_RST(n)			(0x28 + 0x20 * (n))
+#define DISP_REG_MUTEX_MOD(mutex_mod_reg, n)	(mutex_mod_reg + 0x20 * (n))
+#define DISP_REG_MUTEX_SOF(n)			(0x30 + 0x20 * (n))
+#define DISP_REG_MUTEX_MOD2(n)			(0x34 + 0x20 * (n))
 
 #define INT_MUTEX				BIT(1)
 
@@ -141,6 +143,7 @@ struct mtk_disp_mutex {
 
 struct mtk_ddp_data {
 	const unsigned int *mutex_mod;
+	const unsigned int mutex_mod_reg;
 };
 
 struct mtk_ddp {
@@ -200,14 +203,17 @@ static const unsigned int mt8173_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 
 static const struct mtk_ddp_data mt2701_ddp_driver_data = {
 	.mutex_mod = mt2701_mutex_mod,
+	.mutex_mod_reg = MT2701_DISP_MUTEX0_MOD0,
 };
 
 static const struct mtk_ddp_data mt2712_ddp_driver_data = {
 	.mutex_mod = mt2712_mutex_mod,
+	.mutex_mod_reg = MT2701_DISP_MUTEX0_MOD0,
 };
 
 static const struct mtk_ddp_data mt8173_ddp_driver_data = {
 	.mutex_mod = mt8173_mutex_mod,
+	.mutex_mod_reg = MT2701_DISP_MUTEX0_MOD0,
 };
 
 static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
@@ -473,7 +479,8 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 		break;
 	default:
 		if (ddp->data->mutex_mod[id] < 32) {
-			offset = DISP_REG_MUTEX_MOD(mutex->id);
+			offset = DISP_REG_MUTEX_MOD(ddp->data->mutex_mod_reg,
+						    mutex->id);
 			reg = readl_relaxed(ddp->regs + offset);
 			reg |= 1 << ddp->data->mutex_mod[id];
 			writel_relaxed(reg, ddp->regs + offset);
@@ -511,7 +518,8 @@ void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
 		break;
 	default:
 		if (ddp->data->mutex_mod[id] < 32) {
-			offset = DISP_REG_MUTEX_MOD(mutex->id);
+			offset = DISP_REG_MUTEX_MOD(ddp->data->mutex_mod_reg,
+						    mutex->id);
 			reg = readl_relaxed(ddp->regs + offset);
 			reg &= ~(1 << ddp->data->mutex_mod[id]);
 			writel_relaxed(reg, ddp->regs + offset);
-- 
cgit v1.2.3


From 1c7da0c76238b23739fca3a751f131de71e7213f Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:31 +0800
Subject: drm/mediatek: add mutex sof into ddp private data

mutex sof will be ddp private data

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 43 +++++++++++++++++++++++++++-------
 1 file changed, 35 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index ae22e21e988c..9bdbd8d5dcd5 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -141,8 +141,19 @@ struct mtk_disp_mutex {
 	bool claimed;
 };
 
+enum mtk_ddp_mutex_sof_id {
+	DDP_MUTEX_SOF_SINGLE_MODE,
+	DDP_MUTEX_SOF_DSI0,
+	DDP_MUTEX_SOF_DSI1,
+	DDP_MUTEX_SOF_DPI0,
+	DDP_MUTEX_SOF_DPI1,
+	DDP_MUTEX_SOF_DSI2,
+	DDP_MUTEX_SOF_DSI3,
+};
+
 struct mtk_ddp_data {
 	const unsigned int *mutex_mod;
+	const unsigned int *mutex_sof;
 	const unsigned int mutex_mod_reg;
 };
 
@@ -201,18 +212,31 @@ static const unsigned int mt8173_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_WDMA1] = MT8173_MUTEX_MOD_DISP_WDMA1,
 };
 
+static const unsigned int mt2712_mutex_sof[DDP_MUTEX_SOF_DSI3 + 1] = {
+	[DDP_MUTEX_SOF_SINGLE_MODE] = MUTEX_SOF_SINGLE_MODE,
+	[DDP_MUTEX_SOF_DSI0] = MUTEX_SOF_DSI0,
+	[DDP_MUTEX_SOF_DSI1] = MUTEX_SOF_DSI1,
+	[DDP_MUTEX_SOF_DPI0] = MUTEX_SOF_DPI0,
+	[DDP_MUTEX_SOF_DPI1] = MUTEX_SOF_DPI1,
+	[DDP_MUTEX_SOF_DSI2] = MUTEX_SOF_DSI2,
+	[DDP_MUTEX_SOF_DSI3] = MUTEX_SOF_DSI3,
+};
+
 static const struct mtk_ddp_data mt2701_ddp_driver_data = {
 	.mutex_mod = mt2701_mutex_mod,
+	.mutex_sof = mt2712_mutex_sof,
 	.mutex_mod_reg = MT2701_DISP_MUTEX0_MOD0,
 };
 
 static const struct mtk_ddp_data mt2712_ddp_driver_data = {
 	.mutex_mod = mt2712_mutex_mod,
+	.mutex_sof = mt2712_mutex_sof,
 	.mutex_mod_reg = MT2701_DISP_MUTEX0_MOD0,
 };
 
 static const struct mtk_ddp_data mt8173_ddp_driver_data = {
 	.mutex_mod = mt8173_mutex_mod,
+	.mutex_sof = mt2712_mutex_sof,
 	.mutex_mod_reg = MT2701_DISP_MUTEX0_MOD0,
 };
 
@@ -454,28 +478,29 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 	struct mtk_ddp *ddp = container_of(mutex, struct mtk_ddp,
 					   mutex[mutex->id]);
 	unsigned int reg;
+	unsigned int sof_id;
 	unsigned int offset;
 
 	WARN_ON(&ddp->mutex[mutex->id] != mutex);
 
 	switch (id) {
 	case DDP_COMPONENT_DSI0:
-		reg = MUTEX_SOF_DSI0;
+		sof_id = DDP_MUTEX_SOF_DSI0;
 		break;
 	case DDP_COMPONENT_DSI1:
-		reg = MUTEX_SOF_DSI0;
+		sof_id = DDP_MUTEX_SOF_DSI0;
 		break;
 	case DDP_COMPONENT_DSI2:
-		reg = MUTEX_SOF_DSI2;
+		sof_id = DDP_MUTEX_SOF_DSI2;
 		break;
 	case DDP_COMPONENT_DSI3:
-		reg = MUTEX_SOF_DSI3;
+		sof_id = DDP_MUTEX_SOF_DSI3;
 		break;
 	case DDP_COMPONENT_DPI0:
-		reg = MUTEX_SOF_DPI0;
+		sof_id = DDP_MUTEX_SOF_DPI0;
 		break;
 	case DDP_COMPONENT_DPI1:
-		reg = MUTEX_SOF_DPI1;
+		sof_id = DDP_MUTEX_SOF_DPI1;
 		break;
 	default:
 		if (ddp->data->mutex_mod[id] < 32) {
@@ -493,7 +518,8 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 		return;
 	}
 
-	writel_relaxed(reg, ddp->regs + DISP_REG_MUTEX_SOF(mutex->id));
+	writel_relaxed(ddp->data->mutex_sof[sof_id],
+		       ddp->regs + DISP_REG_MUTEX_SOF(mutex->id));
 }
 
 void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
@@ -514,7 +540,8 @@ void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
 	case DDP_COMPONENT_DPI0:
 	case DDP_COMPONENT_DPI1:
 		writel_relaxed(MUTEX_SOF_SINGLE_MODE,
-			       ddp->regs + DISP_REG_MUTEX_SOF(mutex->id));
+			       ddp->regs +
+			       DISP_REG_MUTEX_SOF(mutex->id));
 		break;
 	default:
 		if (ddp->data->mutex_mod[id] < 32) {
-- 
cgit v1.2.3


From 1037edf20cb6c75b3d283866048632467f6790e5 Mon Sep 17 00:00:00 2001
From: Yongqiang Niu <yongqiang.niu@mediatek.com>
Date: Thu, 29 Aug 2019 22:50:32 +0800
Subject: drm/mediatek: add mutex sof register offset into ddp private data

mutex sof register offset will be private data of ddp

Signed-off-by: Yongqiang Niu <yongqiang.niu@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 9bdbd8d5dcd5..4866a9b43330 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -34,12 +34,13 @@
 #define DISP_REG_CONFIG_DPI_SEL			0x064
 
 #define MT2701_DISP_MUTEX0_MOD0			0x2c
+#define MT2701_DISP_MUTEX0_SOF0			0x30
 
 #define DISP_REG_MUTEX_EN(n)			(0x20 + 0x20 * (n))
 #define DISP_REG_MUTEX(n)			(0x24 + 0x20 * (n))
 #define DISP_REG_MUTEX_RST(n)			(0x28 + 0x20 * (n))
 #define DISP_REG_MUTEX_MOD(mutex_mod_reg, n)	(mutex_mod_reg + 0x20 * (n))
-#define DISP_REG_MUTEX_SOF(n)			(0x30 + 0x20 * (n))
+#define DISP_REG_MUTEX_SOF(mutex_sof_reg, n)	(mutex_sof_reg + 0x20 * (n))
 #define DISP_REG_MUTEX_MOD2(n)			(0x34 + 0x20 * (n))
 
 #define INT_MUTEX				BIT(1)
@@ -155,6 +156,7 @@ struct mtk_ddp_data {
 	const unsigned int *mutex_mod;
 	const unsigned int *mutex_sof;
 	const unsigned int mutex_mod_reg;
+	const unsigned int mutex_sof_reg;
 };
 
 struct mtk_ddp {
@@ -226,18 +228,21 @@ static const struct mtk_ddp_data mt2701_ddp_driver_data = {
 	.mutex_mod = mt2701_mutex_mod,
 	.mutex_sof = mt2712_mutex_sof,
 	.mutex_mod_reg = MT2701_DISP_MUTEX0_MOD0,
+	.mutex_sof_reg = MT2701_DISP_MUTEX0_SOF0,
 };
 
 static const struct mtk_ddp_data mt2712_ddp_driver_data = {
 	.mutex_mod = mt2712_mutex_mod,
 	.mutex_sof = mt2712_mutex_sof,
 	.mutex_mod_reg = MT2701_DISP_MUTEX0_MOD0,
+	.mutex_sof_reg = MT2701_DISP_MUTEX0_SOF0,
 };
 
 static const struct mtk_ddp_data mt8173_ddp_driver_data = {
 	.mutex_mod = mt8173_mutex_mod,
 	.mutex_sof = mt2712_mutex_sof,
 	.mutex_mod_reg = MT2701_DISP_MUTEX0_MOD0,
+	.mutex_sof_reg = MT2701_DISP_MUTEX0_SOF0,
 };
 
 static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
@@ -519,7 +524,8 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 	}
 
 	writel_relaxed(ddp->data->mutex_sof[sof_id],
-		       ddp->regs + DISP_REG_MUTEX_SOF(mutex->id));
+		       ddp->regs +
+		       DISP_REG_MUTEX_SOF(ddp->data->mutex_sof_reg, mutex->id));
 }
 
 void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
@@ -541,7 +547,8 @@ void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
 	case DDP_COMPONENT_DPI1:
 		writel_relaxed(MUTEX_SOF_SINGLE_MODE,
 			       ddp->regs +
-			       DISP_REG_MUTEX_SOF(mutex->id));
+			       DISP_REG_MUTEX_SOF(ddp->data->mutex_sof_reg,
+						  mutex->id));
 		break;
 	default:
 		if (ddp->data->mutex_mod[id] < 32) {
-- 
cgit v1.2.3


From 631005b255aab5f846f7ca03606613f898d70207 Mon Sep 17 00:00:00 2001
From: CK Hu <ck.hu@mediatek.com>
Date: Wed, 9 Oct 2019 16:37:47 +0800
Subject: drm/mediatek: add no_clk into ddp private data

Mutex has no clock in some SoC, so add no_clk in private data and get
clock according to no_clk.

Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 4866a9b43330..13035c906035 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -157,6 +157,7 @@ struct mtk_ddp_data {
 	const unsigned int *mutex_sof;
 	const unsigned int mutex_mod_reg;
 	const unsigned int mutex_sof_reg;
+	const bool no_clk;
 };
 
 struct mtk_ddp {
@@ -622,10 +623,14 @@ static int mtk_ddp_probe(struct platform_device *pdev)
 	for (i = 0; i < 10; i++)
 		ddp->mutex[i].id = i;
 
-	ddp->clk = devm_clk_get(dev, NULL);
-	if (IS_ERR(ddp->clk)) {
-		dev_err(dev, "Failed to get clock\n");
-		return PTR_ERR(ddp->clk);
+	ddp->data = of_device_get_match_data(dev);
+
+	if (!ddp->data->no_clk) {
+		ddp->clk = devm_clk_get(dev, NULL);
+		if (IS_ERR(ddp->clk)) {
+			dev_err(dev, "Failed to get clock\n");
+			return PTR_ERR(ddp->clk);
+		}
 	}
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -635,8 +640,6 @@ static int mtk_ddp_probe(struct platform_device *pdev)
 		return PTR_ERR(ddp->regs);
 	}
 
-	ddp->data = of_device_get_match_data(dev);
-
 	platform_set_drvdata(pdev, ddp);
 
 	return 0;
-- 
cgit v1.2.3


From 19ec6bb80290e496021488084944b77f03a87dd7 Mon Sep 17 00:00:00 2001
From: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Date: Fri, 4 Oct 2019 15:44:52 +0200
Subject: mmc: sdhci-iproc: fix spurious interrupts on Multiblock reads with
 bcm2711

The Raspberry Pi 4 SDHCI hardware seems to automatically issue CMD12
after multiblock reads even when ACMD12 is disabled. This triggers
spurious interrupts after the data transfer is done with the following
message:

  mmc1: Got data interrupt 0x00000002 even though no data operation was in progress.
  mmc1: sdhci: ============ SDHCI REGISTER DUMP ===========
  mmc1: sdhci: Sys addr:  0x00000000 | Version:  0x00001002
  mmc1: sdhci: Blk size:  0x00007200 | Blk cnt:  0x00000000
  mmc1: sdhci: Argument:  0x00000000 | Trn mode: 0x00000033
  mmc1: sdhci: Present:   0x1fff0000 | Host ctl: 0x00000017
  mmc1: sdhci: Power:     0x0000000f | Blk gap:  0x00000080
  mmc1: sdhci: Wake-up:   0x00000000 | Clock:    0x00000107
  mmc1: sdhci: Timeout:   0x00000000 | Int stat: 0x00000000
  mmc1: sdhci: Int enab:  0x03ff100b | Sig enab: 0x03ff100b
  mmc1: sdhci: ACmd stat: 0x00000000 | Slot int: 0x00000000
  mmc1: sdhci: Caps:      0x45ee6432 | Caps_1:   0x0000a525
  mmc1: sdhci: Cmd:       0x00000c1a | Max curr: 0x00080008
  mmc1: sdhci: Resp[0]:   0x00000b00 | Resp[1]:  0x00edc87f
  mmc1: sdhci: Resp[2]:   0x325b5900 | Resp[3]:  0x00400e00
  mmc1: sdhci: Host ctl2: 0x00000001
  mmc1: sdhci: ADMA Err:  0x00000000 | ADMA Ptr: 0xf3025208
  mmc1: sdhci: ============================================

Enable SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12 to enable ACMD12 on multiblock
reads and suppress the spurious interrupts.

Fixes: f84e411c85be ("mmc: sdhci-iproc: Add support for emmc2 of the BCM2711")
Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Tested-by: Matthias Brugger <mbrugger@suse.com>
Acked-by: Stefan Wahren <wahrenst@gmx.net>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-iproc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/mmc/host/sdhci-iproc.c b/drivers/mmc/host/sdhci-iproc.c
index 2b9cdcd1dd9d..f4f5f0a70cda 100644
--- a/drivers/mmc/host/sdhci-iproc.c
+++ b/drivers/mmc/host/sdhci-iproc.c
@@ -262,6 +262,7 @@ static const struct sdhci_iproc_data bcm2835_data = {
 };
 
 static const struct sdhci_pltfm_data sdhci_bcm2711_pltfm_data = {
+	.quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12,
 	.ops = &sdhci_iproc_32only_ops,
 };
 
-- 
cgit v1.2.3


From 28c9fac09ab0147158db0baeec630407a5e9b892 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 5 Oct 2019 13:21:01 +0200
Subject: memstick: jmb38x_ms: Fix an error handling path in
 'jmb38x_ms_probe()'

If 'jmb38x_ms_count_slots()' returns 0, we must undo the previous
'pci_request_regions()' call.

Goto 'err_out_int' to fix it.

Fixes: 60fdd931d577 ("memstick: add support for JMicron jmb38x MemoryStick host controller")
Cc: stable@vger.kernel.org
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/memstick/host/jmb38x_ms.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c
index 32747425297d..64fff6abe60e 100644
--- a/drivers/memstick/host/jmb38x_ms.c
+++ b/drivers/memstick/host/jmb38x_ms.c
@@ -941,7 +941,7 @@ static int jmb38x_ms_probe(struct pci_dev *pdev,
 	if (!cnt) {
 		rc = -ENODEV;
 		pci_dev_busy = 1;
-		goto err_out;
+		goto err_out_int;
 	}
 
 	jm = kzalloc(sizeof(struct jmb38x_ms)
-- 
cgit v1.2.3


From 1fee35d04a42290a3c44b8a4e3c66dbdd6180c42 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Thu, 8 Aug 2019 13:52:50 +0300
Subject: iwlwifi: don't access trans_cfg via cfg

We copy cfg->trans to trans->trans_cfg at the very beginning, so don't
try to access it via cfg->trans anymore, because the cfg may be unset
in later cases.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-io.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-io.h b/drivers/net/wireless/intel/iwlwifi/iwl-io.h
index f8e4f0f5de0c..f09e368c7040 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-io.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-io.h
@@ -112,38 +112,38 @@ int iwl_dump_fh(struct iwl_trans *trans, char **buf);
  */
 static inline u32 iwl_umac_prph(struct iwl_trans *trans, u32 ofs)
 {
-	return ofs + trans->cfg->trans.umac_prph_offset;
+	return ofs + trans->trans_cfg->umac_prph_offset;
 }
 
 static inline u32 iwl_read_umac_prph_no_grab(struct iwl_trans *trans, u32 ofs)
 {
 	return iwl_read_prph_no_grab(trans, ofs +
-				     trans->cfg->trans.umac_prph_offset);
+				     trans->trans_cfg->umac_prph_offset);
 }
 
 static inline u32 iwl_read_umac_prph(struct iwl_trans *trans, u32 ofs)
 {
-	return iwl_read_prph(trans, ofs + trans->cfg->trans.umac_prph_offset);
+	return iwl_read_prph(trans, ofs + trans->trans_cfg->umac_prph_offset);
 }
 
 static inline void iwl_write_umac_prph_no_grab(struct iwl_trans *trans, u32 ofs,
 					       u32 val)
 {
-	iwl_write_prph_no_grab(trans,  ofs + trans->cfg->trans.umac_prph_offset,
+	iwl_write_prph_no_grab(trans,  ofs + trans->trans_cfg->umac_prph_offset,
 			       val);
 }
 
 static inline void iwl_write_umac_prph(struct iwl_trans *trans, u32 ofs,
 				       u32 val)
 {
-	iwl_write_prph(trans,  ofs + trans->cfg->trans.umac_prph_offset, val);
+	iwl_write_prph(trans,  ofs + trans->trans_cfg->umac_prph_offset, val);
 }
 
 static inline int iwl_poll_umac_prph_bit(struct iwl_trans *trans, u32 addr,
 					 u32 bits, u32 mask, int timeout)
 {
 	return iwl_poll_prph_bit(trans, addr +
-				 trans->cfg->trans.umac_prph_offset,
+				 trans->trans_cfg->umac_prph_offset,
 				 bits, mask, timeout);
 }
 
-- 
cgit v1.2.3


From 3ed83da39aed275a5b74c74f77e85c839ad2efe9 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Fri, 23 Aug 2019 11:59:09 +0300
Subject: iwlwifi: fix ACPI table revision checks

We can't check for the ACPI table revision validity in the same if
where we check if the package was read correctly, because we return
PTR_ERR(pkg) and if the table is not valid but the pointer is, we
would return a valid pointer as an error.  Fix that by moving the
table checks to a separate if and return -EINVAL if it's not valid.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/acpi.c | 10 ++++++----
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c  | 24 ++++++++++++++++++------
 2 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
index 7573af2d88ce..c2db758b9d54 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@@ -162,12 +162,13 @@ int iwl_acpi_get_mcc(struct device *dev, char *mcc)
 
 	wifi_pkg = iwl_acpi_get_wifi_pkg(dev, data, ACPI_WRDD_WIFI_DATA_SIZE,
 					 &tbl_rev);
-	if (IS_ERR(wifi_pkg) || tbl_rev != 0) {
+	if (IS_ERR(wifi_pkg)) {
 		ret = PTR_ERR(wifi_pkg);
 		goto out_free;
 	}
 
-	if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) {
+	if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER ||
+	    tbl_rev != 0) {
 		ret = -EINVAL;
 		goto out_free;
 	}
@@ -224,12 +225,13 @@ int iwl_acpi_get_eckv(struct device *dev, u32 *extl_clk)
 
 	wifi_pkg = iwl_acpi_get_wifi_pkg(dev, data, ACPI_ECKV_WIFI_DATA_SIZE,
 					 &tbl_rev);
-	if (IS_ERR(wifi_pkg) || tbl_rev != 0) {
+	if (IS_ERR(wifi_pkg)) {
 		ret = PTR_ERR(wifi_pkg);
 		goto out_free;
 	}
 
-	if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) {
+	if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER ||
+	    tbl_rev != 0) {
 		ret = -EINVAL;
 		goto out_free;
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 32a5e4e5461f..b2eb18eedf02 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -694,12 +694,13 @@ static int iwl_mvm_sar_get_wrds_table(struct iwl_mvm *mvm)
 
 	wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data,
 					 ACPI_WRDS_WIFI_DATA_SIZE, &tbl_rev);
-	if (IS_ERR(wifi_pkg) || tbl_rev != 0) {
+	if (IS_ERR(wifi_pkg)) {
 		ret = PTR_ERR(wifi_pkg);
 		goto out_free;
 	}
 
-	if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) {
+	if (wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER ||
+	    tbl_rev != 0) {
 		ret = -EINVAL;
 		goto out_free;
 	}
@@ -731,13 +732,14 @@ static int iwl_mvm_sar_get_ewrd_table(struct iwl_mvm *mvm)
 
 	wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data,
 					 ACPI_EWRD_WIFI_DATA_SIZE, &tbl_rev);
-	if (IS_ERR(wifi_pkg) || tbl_rev != 0) {
+	if (IS_ERR(wifi_pkg)) {
 		ret = PTR_ERR(wifi_pkg);
 		goto out_free;
 	}
 
 	if ((wifi_pkg->package.elements[1].type != ACPI_TYPE_INTEGER) ||
-	    (wifi_pkg->package.elements[2].type != ACPI_TYPE_INTEGER)) {
+	    (wifi_pkg->package.elements[2].type != ACPI_TYPE_INTEGER) ||
+	    tbl_rev != 0) {
 		ret = -EINVAL;
 		goto out_free;
 	}
@@ -791,11 +793,16 @@ static int iwl_mvm_sar_get_wgds_table(struct iwl_mvm *mvm)
 
 	wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data,
 					 ACPI_WGDS_WIFI_DATA_SIZE, &tbl_rev);
-	if (IS_ERR(wifi_pkg) || tbl_rev > 1) {
+	if (IS_ERR(wifi_pkg)) {
 		ret = PTR_ERR(wifi_pkg);
 		goto out_free;
 	}
 
+	if (tbl_rev != 0) {
+		ret = -EINVAL;
+		goto out_free;
+	}
+
 	mvm->geo_rev = tbl_rev;
 	for (i = 0; i < ACPI_NUM_GEO_PROFILES; i++) {
 		for (j = 0; j < ACPI_GEO_TABLE_SIZE; j++) {
@@ -1020,11 +1027,16 @@ static int iwl_mvm_get_ppag_table(struct iwl_mvm *mvm)
 	wifi_pkg = iwl_acpi_get_wifi_pkg(mvm->dev, data,
 					 ACPI_PPAG_WIFI_DATA_SIZE, &tbl_rev);
 
-	if (IS_ERR(wifi_pkg) || tbl_rev != 0) {
+	if (IS_ERR(wifi_pkg)) {
 		ret = PTR_ERR(wifi_pkg);
 		goto out_free;
 	}
 
+	if (tbl_rev != 0) {
+		ret = -EINVAL;
+		goto out_free;
+	}
+
 	enabled = &wifi_pkg->package.elements[1];
 	if (enabled->type != ACPI_TYPE_INTEGER ||
 	    (enabled->integer.value != 0 && enabled->integer.value != 1)) {
-- 
cgit v1.2.3


From a4584729291c71c5c14718ff00ea6c5f971c45b2 Mon Sep 17 00:00:00 2001
From: Haim Dreyfuss <haim.dreyfuss@intel.com>
Date: Mon, 12 Aug 2019 13:25:42 +0300
Subject: iwlwifi: mvm: force single phy init

The PHY is initialized during device initialization, but devices with
the tx_siso_diversity flag set need to send PHY_CONFIGURATION_CMD first,
otherwise the PHY would be reinitialized, causing a SYSASSERT.

To fix this, use a bit that tells the FW not to complete the PHY
initialization before a PHY_CONFIGURATION_CMD is received.

Signed-off-by: Haim Dreyfuss <haim.dreyfuss@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index b2eb18eedf02..0d2229319261 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -420,6 +420,9 @@ static int iwl_run_unified_mvm_ucode(struct iwl_mvm *mvm, bool read_nvm)
 	};
 	int ret;
 
+	if (mvm->trans->cfg->tx_with_siso_diversity)
+		init_cfg.init_flags |= cpu_to_le32(BIT(IWL_INIT_PHY));
+
 	lockdep_assert_held(&mvm->mutex);
 
 	mvm->rfkill_safe_init_done = false;
-- 
cgit v1.2.3


From a2113cc44d4387a7c3ef3a9082d273524f9230ac Mon Sep 17 00:00:00 2001
From: Naftali Goldstein <naftali.goldstein@intel.com>
Date: Mon, 9 Sep 2019 13:11:04 +0300
Subject: iwlwifi: mvm: fix race in sync rx queue notification

Consider the following flow:
 1. Driver starts to sync the rx queues due to a delba.
    mvm->queue_sync_cookie=1.
    This rx-queues-sync is synchronous, so it doesn't increment the
    cookie until all rx queues handle the notification from FW.
 2. During this time, driver starts to sync rx queues due to nssn sync
    required.
    The cookie's value is still 1, but it doesn't matter since this
    rx-queue-sync is non-synchronous so in the notification handler the
    cookie is ignored.
    What _does_ matter is that this flow increments the cookie to 2
    immediately.
    Remember though that the FW won't start servicing this command until
    it's done with the previous one.
 3. FW is still handling the first command, so it sends a notification
    with internal_notif->sync=1, and internal_notif->cookie=0, which
    triggers a WARN_ONCE.

The solution for this race is to only use the mvm->queue_sync_cookie in
case of a synchronous sync-rx-queues. This way in step 2 the cookie's
value won't change so we avoid the WARN.

The commit in the "fixes" field is the first commit to introduce
non-synchronous sending of this command to FW.

Fixes: 3c514bf831ac ("iwlwifi: mvm: add a loose synchronization of the NSSN across Rx queues")
Signed-off-by: Naftali Goldstein <naftali.goldstein@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index cd1b10042fbf..d31f96c3f925 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -4881,11 +4881,11 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
 	if (!iwl_mvm_has_new_rx_api(mvm))
 		return;
 
-	notif->cookie = mvm->queue_sync_cookie;
-
-	if (notif->sync)
+	if (notif->sync) {
+		notif->cookie = mvm->queue_sync_cookie;
 		atomic_set(&mvm->queue_sync_counter,
 			   mvm->trans->num_rx_queues);
+	}
 
 	ret = iwl_mvm_notify_rx_queue(mvm, qmask, (u8 *)notif,
 				      size, !notif->sync);
@@ -4905,7 +4905,8 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
 
 out:
 	atomic_set(&mvm->queue_sync_counter, 0);
-	mvm->queue_sync_cookie++;
+	if (notif->sync)
+		mvm->queue_sync_cookie++;
 }
 
 static void iwl_mvm_sync_rx_queues(struct ieee80211_hw *hw)
-- 
cgit v1.2.3


From 08326a97afbe808e50e1610c2835fa2747bdb908 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 4 Sep 2019 16:23:27 +0200
Subject: iwlwifi: pcie: fix indexing in command dump for new HW

We got a crash in iwl_trans_pcie_get_cmdlen(), while the TFD was
being accessed to sum up the lengths.

We want to access the TFD here, which is the information for the
hardware. We always only allocate 32 buffers for the cmd queue,
but on newer hardware (using TFH) we can also allocate only a
shorter hardware array, also only 32 TFDs. Prior to the TFH, we
had to allocate a bigger TFD array but would make those point to
a smaller set of buffers.

Additionally, now max_tfd_queue_size is up to 65536, so we can
access *way* out of bounds of a really only 32-entry array, so
it crashes.

Fix this by making the TFD index depend on which hardware we are
using right now.

While changing the calculation, also fix it to not use void ptr
arithmetic, but cast to u8 * before.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index f8a1f985a1d8..ab7480a85015 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -3272,11 +3272,17 @@ static struct iwl_trans_dump_data
 		ptr = cmdq->write_ptr;
 		for (i = 0; i < cmdq->n_window; i++) {
 			u8 idx = iwl_pcie_get_cmd_index(cmdq, ptr);
+			u8 tfdidx;
 			u32 caplen, cmdlen;
 
+			if (trans->trans_cfg->use_tfh)
+				tfdidx = idx;
+			else
+				tfdidx = ptr;
+
 			cmdlen = iwl_trans_pcie_get_cmdlen(trans,
-							   cmdq->tfds +
-							   tfd_size * ptr);
+							   (u8 *)cmdq->tfds +
+							   tfd_size * tfdidx);
 			caplen = min_t(u32, TFD_MAX_PAYLOAD_SIZE, cmdlen);
 
 			if (cmdlen) {
-- 
cgit v1.2.3


From 8188a18ee2e48c9a7461139838048363bfce3fef Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 19 Sep 2019 09:04:09 +0200
Subject: iwlwifi: pcie: fix rb_allocator workqueue allocation

We don't handle failures in the rb_allocator workqueue allocation
correctly. To fix that, move the code earlier so the cleanup is
easier and we don't have to undo all the interrupt allocations in
this case.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index ab7480a85015..6961f00ff812 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -3456,6 +3456,15 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 	spin_lock_init(&trans_pcie->reg_lock);
 	mutex_init(&trans_pcie->mutex);
 	init_waitqueue_head(&trans_pcie->ucode_write_waitq);
+
+	trans_pcie->rba.alloc_wq = alloc_workqueue("rb_allocator",
+						   WQ_HIGHPRI | WQ_UNBOUND, 1);
+	if (!trans_pcie->rba.alloc_wq) {
+		ret = -ENOMEM;
+		goto out_free_trans;
+	}
+	INIT_WORK(&trans_pcie->rba.rx_alloc, iwl_pcie_rx_allocator_work);
+
 	trans_pcie->tso_hdr_page = alloc_percpu(struct iwl_tso_hdr_page);
 	if (!trans_pcie->tso_hdr_page) {
 		ret = -ENOMEM;
@@ -3590,10 +3599,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		trans_pcie->inta_mask = CSR_INI_SET_MASK;
 	 }
 
-	trans_pcie->rba.alloc_wq = alloc_workqueue("rb_allocator",
-						   WQ_HIGHPRI | WQ_UNBOUND, 1);
-	INIT_WORK(&trans_pcie->rba.rx_alloc, iwl_pcie_rx_allocator_work);
-
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 	trans_pcie->fw_mon_data.state = IWL_FW_MON_DBGFS_STATE_CLOSED;
 	mutex_init(&trans_pcie->fw_mon_data.mutex);
@@ -3605,6 +3610,8 @@ out_free_ict:
 	iwl_pcie_free_ict(trans);
 out_no_pci:
 	free_percpu(trans_pcie->tso_hdr_page);
+	destroy_workqueue(trans_pcie->rba.alloc_wq);
+out_free_trans:
 	iwl_trans_free(trans);
 	return ERR_PTR(ret);
 }
-- 
cgit v1.2.3


From b4b814fec1a5a849383f7b3886b654a13abbda7d Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Thu, 12 Sep 2019 23:23:27 -0500
Subject: iwlwifi: dbg_ini: fix memory leak in alloc_sgtable

In alloc_sgtable if alloc_page fails, the alocated table should be
released.

Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 5c8602de9168..87421807e040 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -646,6 +646,7 @@ static struct scatterlist *alloc_sgtable(int size)
 				if (new_page)
 					__free_page(new_page);
 			}
+			kfree(table);
 			return NULL;
 		}
 		alloc_size = min_t(int, size, PAGE_SIZE);
-- 
cgit v1.2.3


From 0f4f199443faca715523b0659aa536251d8b978f Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Fri, 27 Sep 2019 15:56:04 -0500
Subject: iwlwifi: pcie: fix memory leaks in iwl_pcie_ctxt_info_gen3_init

In iwl_pcie_ctxt_info_gen3_init there are cases that the allocated dma
memory is leaked in case of error.

DMA memories prph_scratch, prph_info, and ctxt_info_gen3 are allocated
and initialized to be later assigned to trans_pcie. But in any error case
before such assignment the allocated memories should be released.

First of such error cases happens when iwl_pcie_init_fw_sec fails.
Current implementation correctly releases prph_scratch. But in two
sunsequent error cases where dma_alloc_coherent may fail, such
releases are missing.

This commit adds release for prph_scratch when allocation for
prph_info fails, and adds releases for prph_scratch and prph_info when
allocation for ctxt_info_gen3 fails.

Fixes: 2ee824026288 ("iwlwifi: pcie: support context information for 22560 devices")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 .../wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c   | 36 +++++++++++++++-------
 1 file changed, 25 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
index 75fa8a6aafee..74980382e64c 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
@@ -107,13 +107,9 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 
 	/* allocate ucode sections in dram and set addresses */
 	ret = iwl_pcie_init_fw_sec(trans, fw, &prph_scratch->dram);
-	if (ret) {
-		dma_free_coherent(trans->dev,
-				  sizeof(*prph_scratch),
-				  prph_scratch,
-				  trans_pcie->prph_scratch_dma_addr);
-		return ret;
-	}
+	if (ret)
+		goto err_free_prph_scratch;
+
 
 	/* Allocate prph information
 	 * currently we don't assign to the prph info anything, but it would get
@@ -121,16 +117,20 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 	prph_info = dma_alloc_coherent(trans->dev, sizeof(*prph_info),
 				       &trans_pcie->prph_info_dma_addr,
 				       GFP_KERNEL);
-	if (!prph_info)
-		return -ENOMEM;
+	if (!prph_info) {
+		ret = -ENOMEM;
+		goto err_free_prph_scratch;
+	}
 
 	/* Allocate context info */
 	ctxt_info_gen3 = dma_alloc_coherent(trans->dev,
 					    sizeof(*ctxt_info_gen3),
 					    &trans_pcie->ctxt_info_dma_addr,
 					    GFP_KERNEL);
-	if (!ctxt_info_gen3)
-		return -ENOMEM;
+	if (!ctxt_info_gen3) {
+		ret = -ENOMEM;
+		goto err_free_prph_info;
+	}
 
 	ctxt_info_gen3->prph_info_base_addr =
 		cpu_to_le64(trans_pcie->prph_info_dma_addr);
@@ -186,6 +186,20 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 		iwl_set_bit(trans, CSR_GP_CNTRL, CSR_AUTO_FUNC_INIT);
 
 	return 0;
+
+err_free_prph_info:
+	dma_free_coherent(trans->dev,
+			  sizeof(*prph_info),
+			prph_info,
+			trans_pcie->prph_info_dma_addr);
+
+err_free_prph_scratch:
+	dma_free_coherent(trans->dev,
+			  sizeof(*prph_scratch),
+			prph_scratch,
+			trans_pcie->prph_scratch_dma_addr);
+	return ret;
+
 }
 
 void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans)
-- 
cgit v1.2.3


From 12e36d98d3e5acf5fc57774e0a15906d55f30cb9 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Tue, 8 Oct 2019 13:10:53 +0300
Subject: iwlwifi: exclude GEO SAR support for 3168

We currently support two NICs in FW version 29, namely 7265D and 3168.
Out of these, only 7265D supports GEO SAR, so adjust the function that
checks for it accordingly.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Fixes: f5a47fae6aa3 ("iwlwifi: mvm: fix version check for GEO_TX_POWER_LIMIT support")
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 0d2229319261..d9eb2b286438 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -899,15 +899,17 @@ static bool iwl_mvm_sar_geo_support(struct iwl_mvm *mvm)
 	 * firmware versions.  Unfortunately, we don't have a TLV API
 	 * flag to rely on, so rely on the major version which is in
 	 * the first byte of ucode_ver.  This was implemented
-	 * initially on version 38 and then backported to29 and 17.
-	 * The intention was to have it in 36 as well, but not all
-	 * 8000 family got this feature enabled.  The 8000 family is
-	 * the only one using version 36, so skip this version
-	 * entirely.
+	 * initially on version 38 and then backported to 17.  It was
+	 * also backported to 29, but only for 7265D devices.  The
+	 * intention was to have it in 36 as well, but not all 8000
+	 * family got this feature enabled.  The 8000 family is the
+	 * only one using version 36, so skip this version entirely.
 	 */
 	return IWL_UCODE_SERIAL(mvm->fw->ucode_ver) >= 38 ||
-	       IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 29 ||
-	       IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 17;
+	       IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 17 ||
+	       (IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 29 &&
+		((mvm->trans->hw_rev & CSR_HW_REV_TYPE_MSK) ==
+		 CSR_HW_REV_TYPE_7265D));
 }
 
 int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm)
-- 
cgit v1.2.3


From aa0cc7dde17bb6b8cc533bbcfe3f53d70e0dd269 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Tue, 8 Oct 2019 13:21:02 +0300
Subject: iwlwifi: pcie: change qu with jf devices to use qu configuration

There were a bunch of devices with qu and jf that were loading the
configuration with pu and jf, which is wrong.  Fix them all
accordingly.  Additionally, remove 0x1010 and 0x1210 subsytem IDs from
the list, since they are obviously wrong, and 0x0044 and 0x0244, which
were duplicate.

Cc: stable@vger.kernel.org # 5.1+
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 274 +++++++++++++-------------
 1 file changed, 137 insertions(+), 137 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index e29c47744ef5..6f4bb7ce71a5 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -513,31 +513,33 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x24FD, 0x9074, iwl8265_2ac_cfg)},
 
 /* 9000 Series */
-	{IWL_PCI_DEVICE(0x02F0, 0x0030, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x0034, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x0038, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x003C, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x0060, iwl9461_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x0064, iwl9461_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x00A0, iwl9462_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x00A4, iwl9462_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x0230, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x0234, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x0238, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x023C, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x0260, iwl9461_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x0264, iwl9461_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x02A0, iwl9462_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x02A4, iwl9462_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x1551, iwl9560_killer_s_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x1552, iwl9560_killer_i_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x2030, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x2034, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x4030, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x4034, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x40A4, iwl9462_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x4234, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)},
-	{IWL_PCI_DEVICE(0x02F0, 0x42A4, iwl9462_2ac_cfg_quz_a0_jf_b0_soc)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x02F0, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+
 	{IWL_PCI_DEVICE(0x06F0, 0x0030, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)},
 	{IWL_PCI_DEVICE(0x06F0, 0x0034, iwl9560_2ac_cfg_quz_a0_jf_b0_soc)},
 	{IWL_PCI_DEVICE(0x06F0, 0x0038, iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc)},
@@ -643,34 +645,34 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x2720, 0x40A4, iwl9462_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2720, 0x4234, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2720, 0x42A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0034, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0038, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x003C, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0060, iwl9460_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0064, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x00A0, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x00A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0230, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0234, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0238, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x023C, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0260, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0264, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x02A0, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x02A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x1010, iwl9260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x1210, iwl9260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x30DC, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x1552, iwl9560_killer_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x4034, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x40A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x4234, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x30DC, 0x42A4, iwl9462_2ac_cfg_soc)},
+
+	{IWL_PCI_DEVICE(0x30DC, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x30DC, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+
 	{IWL_PCI_DEVICE(0x31DC, 0x0030, iwl9560_2ac_160_cfg_shared_clk)},
 	{IWL_PCI_DEVICE(0x31DC, 0x0034, iwl9560_2ac_cfg_shared_clk)},
 	{IWL_PCI_DEVICE(0x31DC, 0x0038, iwl9560_2ac_160_cfg_shared_clk)},
@@ -726,62 +728,60 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x34F0, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
 	{IWL_PCI_DEVICE(0x34F0, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
 
-	{IWL_PCI_DEVICE(0x3DF0, 0x0030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x0034, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x0038, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x003C, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x0060, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x0064, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x00A0, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x00A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x0230, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x0234, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x0238, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x023C, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x0260, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x0264, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x02A0, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x02A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x1010, iwl9260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x1030, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x1210, iwl9260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x2030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x2034, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x4030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x4034, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x40A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x4234, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x3DF0, 0x42A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x0030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x0034, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x0038, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x003C, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x0060, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x0064, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x00A0, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x00A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x0230, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x0234, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x0238, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x023C, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x0260, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x0264, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x02A0, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x02A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x1010, iwl9260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x43F0, 0x1030, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x1210, iwl9260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x43F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x2030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x2034, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x4030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x4034, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x40A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x4234, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x43F0, 0x42A4, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x3DF0, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+
+	{IWL_PCI_DEVICE(0x43F0, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x43F0, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+
 	{IWL_PCI_DEVICE(0x9DF0, 0x0000, iwl9460_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x9DF0, 0x0010, iwl9460_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x9DF0, 0x0030, iwl9560_2ac_160_cfg_soc)},
@@ -821,34 +821,34 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x9DF0, 0x40A4, iwl9462_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x9DF0, 0x4234, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x9DF0, 0x42A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x0030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x0034, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x0038, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x003C, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x0060, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x0064, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x00A0, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x00A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x0230, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x0234, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x0238, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x023C, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x0260, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x0264, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x02A0, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x02A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x1010, iwl9260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x1030, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x1210, iwl9260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x1552, iwl9560_killer_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x2030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x2034, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x4030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x4034, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x40A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x4234, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0xA0F0, 0x42A4, iwl9462_2ac_cfg_soc)},
+
+	{IWL_PCI_DEVICE(0xA0F0, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+
 	{IWL_PCI_DEVICE(0xA370, 0x0030, iwl9560_2ac_160_cfg_soc)},
 	{IWL_PCI_DEVICE(0xA370, 0x0034, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0xA370, 0x0038, iwl9560_2ac_160_cfg_soc)},
-- 
cgit v1.2.3


From d46e137c44974938bc08700000a4b1231491ca8a Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 9 Oct 2019 11:00:24 +0100
Subject: drm/i915/selftests: fix null pointer dereference on pointer data

In the case where data fails to be allocated the error exit path is
via label 'out' where data is dereferenced in a for-loop.  Fix this
by exiting via the label 'out_file' instead to avoid the null pointer
dereference.

Addresses-Coverity: ("Dereference after null check")
Fixes: 50d16d44cce4 ("drm/i915/selftests: Exercise context switching in parallel")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191009100024.23077-1-colin.king@canonical.com
---
 drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index fb58c0919ea1..e5c235051ae5 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -263,7 +263,7 @@ static int live_parallel_switch(void *arg)
 	if (!data) {
 		i915_gem_context_unlock_engines(ctx);
 		err = -ENOMEM;
-		goto out;
+		goto out_file;
 	}
 
 	m = 0; /* Use the first context as our template for the engines */
-- 
cgit v1.2.3


From 4929a4e6faa0f13289a67cae98139e727f0d4a97 Mon Sep 17 00:00:00 2001
From: Xuewei Zhang <xueweiz@google.com>
Date: Thu, 3 Oct 2019 17:12:43 -0700
Subject: sched/fair: Scale bandwidth quota and period without losing
 quota/period ratio precision

The quota/period ratio is used to ensure a child task group won't get
more bandwidth than the parent task group, and is calculated as:

  normalized_cfs_quota() = [(quota_us << 20) / period_us]

If the quota/period ratio was changed during this scaling due to
precision loss, it will cause inconsistency between parent and child
task groups.

See below example:

A userspace container manager (kubelet) does three operations:

 1) Create a parent cgroup, set quota to 1,000us and period to 10,000us.
 2) Create a few children cgroups.
 3) Set quota to 1,000us and period to 10,000us on a child cgroup.

These operations are expected to succeed. However, if the scaling of
147/128 happens before step 3, quota and period of the parent cgroup
will be changed:

  new_quota: 1148437ns,   1148us
 new_period: 11484375ns, 11484us

And when step 3 comes in, the ratio of the child cgroup will be
104857, which will be larger than the parent cgroup ratio (104821),
and will fail.

Scaling them by a factor of 2 will fix the problem.

Tested-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Xuewei Zhang <xueweiz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Phil Auld <pauld@redhat.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Fixes: 2e8e19226398 ("sched/fair: Limit sched_cfs_period_timer() loop to avoid hard lockup")
Link: https://lkml.kernel.org/r/20191004001243.140897-1-xueweiz@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 36 ++++++++++++++++++++++--------------
 1 file changed, 22 insertions(+), 14 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 83ab35e2374f..682a754ea3e1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4926,20 +4926,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 		if (++count > 3) {
 			u64 new, old = ktime_to_ns(cfs_b->period);
 
-			new = (old * 147) / 128; /* ~115% */
-			new = min(new, max_cfs_quota_period);
-
-			cfs_b->period = ns_to_ktime(new);
-
-			/* since max is 1s, this is limited to 1e9^2, which fits in u64 */
-			cfs_b->quota *= new;
-			cfs_b->quota = div64_u64(cfs_b->quota, old);
-
-			pr_warn_ratelimited(
-	"cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
-				smp_processor_id(),
-				div_u64(new, NSEC_PER_USEC),
-				div_u64(cfs_b->quota, NSEC_PER_USEC));
+			/*
+			 * Grow period by a factor of 2 to avoid losing precision.
+			 * Precision loss in the quota/period ratio can cause __cfs_schedulable
+			 * to fail.
+			 */
+			new = old * 2;
+			if (new < max_cfs_quota_period) {
+				cfs_b->period = ns_to_ktime(new);
+				cfs_b->quota *= 2;
+
+				pr_warn_ratelimited(
+	"cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+					smp_processor_id(),
+					div_u64(new, NSEC_PER_USEC),
+					div_u64(cfs_b->quota, NSEC_PER_USEC));
+			} else {
+				pr_warn_ratelimited(
+	"cfs_period_timer[cpu%d]: period too short, but cannot scale up without losing precision (cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+					smp_processor_id(),
+					div_u64(old, NSEC_PER_USEC),
+					div_u64(cfs_b->quota, NSEC_PER_USEC));
+			}
 
 			/* reset count so we don't come right back in here */
 			count = 0;
-- 
cgit v1.2.3


From 68e7a4d66b0ce04bf18ff2ffded5596ab3618585 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Wed, 25 Sep 2019 23:42:42 +0200
Subject: sched/vtime: Fix guest/system mis-accounting on task switch

vtime_account_system() assumes that the target task to account cputime
to is always the current task. This is most often true indeed except on
task switch where we call:

	vtime_common_task_switch(prev)
		vtime_account_system(prev)

Here prev is the scheduling-out task where we account the cputime to. It
doesn't match current that is already the scheduling-in task at this
stage of the context switch.

So we end up checking the wrong task flags to determine if we are
accounting guest or system time to the previous task.

As a result the wrong task is used to check if the target is running in
guest mode. We may then spuriously account or leak either system or
guest time on task switch.

Fix this assumption and also turn vtime_guest_enter/exit() to use the
task passed in parameter as well to avoid future similar issues.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <wanpengli@tencent.com>
Fixes: 2a42eb9594a1 ("sched/cputime: Accumulate vtime on top of nsec clocksource")
Link: https://lkml.kernel.org/r/20190925214242.21873-1-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/cputime.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 2305ce89a26c..46ed4e1383e2 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -740,7 +740,7 @@ void vtime_account_system(struct task_struct *tsk)
 
 	write_seqcount_begin(&vtime->seqcount);
 	/* We might have scheduled out from guest path */
-	if (current->flags & PF_VCPU)
+	if (tsk->flags & PF_VCPU)
 		vtime_account_guest(tsk, vtime);
 	else
 		__vtime_account_system(tsk, vtime);
@@ -783,7 +783,7 @@ void vtime_guest_enter(struct task_struct *tsk)
 	 */
 	write_seqcount_begin(&vtime->seqcount);
 	__vtime_account_system(tsk, vtime);
-	current->flags |= PF_VCPU;
+	tsk->flags |= PF_VCPU;
 	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_enter);
@@ -794,7 +794,7 @@ void vtime_guest_exit(struct task_struct *tsk)
 
 	write_seqcount_begin(&vtime->seqcount);
 	vtime_account_guest(tsk, vtime);
-	current->flags &= ~PF_VCPU;
+	tsk->flags &= ~PF_VCPU;
 	write_seqcount_end(&vtime->seqcount);
 }
 EXPORT_SYMBOL_GPL(vtime_guest_exit);
-- 
cgit v1.2.3


From d44248a41337731a111374822d7d4451b64e73e4 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Wed, 4 Sep 2019 14:46:18 -0700
Subject: perf/core: Rework memory accounting in perf_mmap()

perf_mmap() always increases user->locked_vm. As a result, "extra" could
grow bigger than "user_extra", which doesn't make sense. Here is an
example case:

(Note: Assume "user_lock_limit" is very small.)

  | # of perf_mmap calls |vma->vm_mm->pinned_vm|user->locked_vm|
  | 0                    | 0                   | 0             |
  | 1                    | user_extra          | user_extra    |
  | 2                    | 3 * user_extra      | 2 * user_extra|
  | 3                    | 6 * user_extra      | 3 * user_extra|
  | 4                    | 10 * user_extra     | 4 * user_extra|

Fix this by maintaining proper user_extra and extra.

Reviewed-By: Hechao Li <hechaol@fb.com>
Reported-by: Hechao Li <hechaol@fb.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <kernel-team@fb.com>
Cc: Jie Meng <jmeng@fb.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20190904214618.3795672-1-songliubraving@fb.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/events/core.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index f953dd16a5e2..2b8265ad7bf5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5668,7 +5668,8 @@ again:
 	 * undo the VM accounting.
 	 */
 
-	atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm);
+	atomic_long_sub((size >> PAGE_SHIFT) + 1 - mmap_locked,
+			&mmap_user->locked_vm);
 	atomic64_sub(mmap_locked, &vma->vm_mm->pinned_vm);
 	free_uid(mmap_user);
 
@@ -5812,8 +5813,20 @@ accounting:
 
 	user_locked = atomic_long_read(&user->locked_vm) + user_extra;
 
-	if (user_locked > user_lock_limit)
+	if (user_locked <= user_lock_limit) {
+		/* charge all to locked_vm */
+	} else if (atomic_long_read(&user->locked_vm) >= user_lock_limit) {
+		/* charge all to pinned_vm */
+		extra = user_extra;
+		user_extra = 0;
+	} else {
+		/*
+		 * charge locked_vm until it hits user_lock_limit;
+		 * charge the rest from pinned_vm
+		 */
 		extra = user_locked - user_lock_limit;
+		user_extra -= extra;
+	}
 
 	lock_limit = rlimit(RLIMIT_MEMLOCK);
 	lock_limit >>= PAGE_SHIFT;
-- 
cgit v1.2.3


From 7fa343b7fdc4f351de4e3f28d5c285937dd1f42f Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Tue, 8 Oct 2019 09:59:49 -0700
Subject: perf/core: Fix corner case in perf_rotate_context()

In perf_rotate_context(), when the first cpu flexible event fail to
schedule, cpu_rotate is 1, while cpu_event is NULL. Since cpu_event is
NULL, perf_rotate_context will _NOT_ call cpu_ctx_sched_out(), thus
cpuctx->ctx.is_active will have EVENT_FLEXIBLE set. Then, the next
perf_event_sched_in() will skip all cpu flexible events because of the
EVENT_FLEXIBLE bit.

In the next call of perf_rotate_context(), cpu_rotate stays 1, and
cpu_event stays NULL, so this process repeats. The end result is, flexible
events on this cpu will not be scheduled (until another event being added
to the cpuctx).

Here is an easy repro of this issue. On Intel CPUs, where ref-cycles
could only use one counter, run one pinned event for ref-cycles, one
flexible event for ref-cycles, and one flexible event for cycles. The
flexible ref-cycles is never scheduled, which is expected. However,
because of this issue, the cycles event is never scheduled either.

 $ perf stat -e ref-cycles:D,ref-cycles,cycles -C 5 -I 1000

           time             counts unit events
    1.000152973         15,412,480      ref-cycles:D
    1.000152973      <not counted>      ref-cycles     (0.00%)
    1.000152973      <not counted>      cycles         (0.00%)
    2.000486957         18,263,120      ref-cycles:D
    2.000486957      <not counted>      ref-cycles     (0.00%)
    2.000486957      <not counted>      cycles         (0.00%)

To fix this, when the flexible_active list is empty, try rotate the
first event in the flexible_groups. Also, rename ctx_first_active() to
ctx_event_to_rotate(), which is more accurate.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <kernel-team@fb.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sasha Levin <sashal@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 8d5bce0c37fa ("perf/core: Optimize perf_rotate_context() event scheduling")
Link: https://lkml.kernel.org/r/20191008165949.920548-1-songliubraving@fb.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/events/core.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2b8265ad7bf5..9ec0b0bfddbd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3779,11 +3779,23 @@ static void rotate_ctx(struct perf_event_context *ctx, struct perf_event *event)
 	perf_event_groups_insert(&ctx->flexible_groups, event);
 }
 
+/* pick an event from the flexible_groups to rotate */
 static inline struct perf_event *
-ctx_first_active(struct perf_event_context *ctx)
+ctx_event_to_rotate(struct perf_event_context *ctx)
 {
-	return list_first_entry_or_null(&ctx->flexible_active,
-					struct perf_event, active_list);
+	struct perf_event *event;
+
+	/* pick the first active flexible event */
+	event = list_first_entry_or_null(&ctx->flexible_active,
+					 struct perf_event, active_list);
+
+	/* if no active flexible event, pick the first event */
+	if (!event) {
+		event = rb_entry_safe(rb_first(&ctx->flexible_groups.tree),
+				      typeof(*event), group_node);
+	}
+
+	return event;
 }
 
 static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
@@ -3808,9 +3820,9 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
 	perf_pmu_disable(cpuctx->ctx.pmu);
 
 	if (task_rotate)
-		task_event = ctx_first_active(task_ctx);
+		task_event = ctx_event_to_rotate(task_ctx);
 	if (cpu_rotate)
-		cpu_event = ctx_first_active(&cpuctx->ctx);
+		cpu_event = ctx_event_to_rotate(&cpuctx->ctx);
 
 	/*
 	 * As per the order given at ctx_resched() first 'pop' task flexible
-- 
cgit v1.2.3


From df4d29732fdad43a51284f826bec3e6ded177540 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Thu, 1 Aug 2019 18:57:41 +0000
Subject: perf/x86/amd: Change/fix NMI latency mitigation to use a timestamp

It turns out that the NMI latency workaround from commit:

  6d3edaae16c6 ("x86/perf/amd: Resolve NMI latency issues for active PMCs")

ends up being too conservative and results in the perf NMI handler claiming
NMIs too easily on AMD hardware when the NMI watchdog is active.

This has an impact, for example, on the hpwdt (HPE watchdog timer) module.
This module can produce an NMI that is used to reset the system. It
registers an NMI handler for the NMI_UNKNOWN type and relies on the fact
that nothing has claimed an NMI so that its handler will be invoked when
the watchdog device produces an NMI. After the referenced commit, the
hpwdt module is unable to process its generated NMI if the NMI watchdog is
active, because the current NMI latency mitigation results in the NMI
being claimed by the perf NMI handler.

Update the AMD perf NMI latency mitigation workaround to, instead, use a
window of time. Whenever a PMC is handled in the perf NMI handler, set a
timestamp which will act as a perf NMI window. Any NMIs arriving within
that window will be claimed by perf. Anything outside that window will
not be claimed by perf. The value for the NMI window is set to 100 msecs.
This is a conservative value that easily covers any NMI latency in the
hardware. While this still results in a window in which the hpwdt module
will not receive its NMI, the window is now much, much smaller.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jerry Hoemann <jerry.hoemann@hpe.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 6d3edaae16c6 ("x86/perf/amd: Resolve NMI latency issues for active PMCs")
Link: https://lkml.kernel.org/r/Message-ID:
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/amd/core.c | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 deletions(-)

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index e7d35f60d53f..64c3e70b0556 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -5,12 +5,14 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
+#include <linux/jiffies.h>
 #include <asm/apicdef.h>
 #include <asm/nmi.h>
 
 #include "../perf_event.h"
 
-static DEFINE_PER_CPU(unsigned int, perf_nmi_counter);
+static DEFINE_PER_CPU(unsigned long, perf_nmi_tstamp);
+static unsigned long perf_nmi_window;
 
 static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
@@ -641,11 +643,12 @@ static void amd_pmu_disable_event(struct perf_event *event)
  * handler when multiple PMCs are active or PMC overflow while handling some
  * other source of an NMI.
  *
- * Attempt to mitigate this by using the number of active PMCs to determine
- * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset
- * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the
- * number of active PMCs or 2. The value of 2 is used in case an NMI does not
- * arrive at the LAPIC in time to be collapsed into an already pending NMI.
+ * Attempt to mitigate this by creating an NMI window in which un-handled NMIs
+ * received during this window will be claimed. This prevents extending the
+ * window past when it is possible that latent NMIs should be received. The
+ * per-CPU perf_nmi_tstamp will be set to the window end time whenever perf has
+ * handled a counter. When an un-handled NMI is received, it will be claimed
+ * only if arriving within that window.
  */
 static int amd_pmu_handle_irq(struct pt_regs *regs)
 {
@@ -663,21 +666,19 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
 	handled = x86_pmu_handle_irq(regs);
 
 	/*
-	 * If a counter was handled, record the number of possible remaining
-	 * NMIs that can occur.
+	 * If a counter was handled, record a timestamp such that un-handled
+	 * NMIs will be claimed if arriving within that window.
 	 */
 	if (handled) {
-		this_cpu_write(perf_nmi_counter,
-			       min_t(unsigned int, 2, active));
+		this_cpu_write(perf_nmi_tstamp,
+			       jiffies + perf_nmi_window);
 
 		return handled;
 	}
 
-	if (!this_cpu_read(perf_nmi_counter))
+	if (time_after(jiffies, this_cpu_read(perf_nmi_tstamp)))
 		return NMI_DONE;
 
-	this_cpu_dec(perf_nmi_counter);
-
 	return NMI_HANDLED;
 }
 
@@ -909,6 +910,9 @@ static int __init amd_core_pmu_init(void)
 	if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE))
 		return 0;
 
+	/* Avoid calulating the value each time in the NMI handler */
+	perf_nmi_window = msecs_to_jiffies(100);
+
 	switch (boot_cpu_data.x86) {
 	case 0x15:
 		pr_cont("Fam15h ");
-- 
cgit v1.2.3


From 9b000b47cc18fa3b078ce080cbcf84f1a8a497ad Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Wed, 9 Oct 2019 12:25:39 +0530
Subject: drm/i915/color: fix broken gamma state-checker during boot
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Premature gamma lut prepration and loading which was getting
reflected in first modeset causing different colors on
screen during boot.

Issue: In BIOS, gamma is disabled by default. However, legacy read_luts()
was setting crtc_state->base.gamma_lut and gamma_lut was programmed
with junk values which led to visual artifacts (different
colored screens instead of usual black during boot).

Fix: Calling read_luts() only when gamma is enabled which will happen
after first modeset.

This fix is independent from the revert 1b8588741fdc ("Revert
"drm/i915/color: Extract icl_read_luts()"") and should fix different colors
on screen in legacy platforms too.

v2:
-Added gamma_enable checks inside read_luts() [Ville/Jani N]
-Corrected gamma enable check for CHV [Ville]

v3:
-Added check in ilk_read_luts() [Ville]
-Simplified gamma enable check for CHV [Ville]

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111809
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111885
Tested-by: Jani Saarinen <jani.saarinen@intel.com>
Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191009065542.27415-2-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 9ab34902663e..08d020d4da35 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1613,6 +1613,9 @@ i9xx_read_lut_8(const struct intel_crtc_state *crtc_state)
 
 static void i9xx_read_luts(struct intel_crtc_state *crtc_state)
 {
+	if (!crtc_state->gamma_enable)
+		return;
+
 	crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
 }
 
@@ -1659,6 +1662,9 @@ i965_read_lut_10p6(const struct intel_crtc_state *crtc_state)
 
 static void i965_read_luts(struct intel_crtc_state *crtc_state)
 {
+	if (!crtc_state->gamma_enable)
+		return;
+
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
 		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
 	else
@@ -1701,10 +1707,10 @@ chv_read_cgm_lut(const struct intel_crtc_state *crtc_state)
 
 static void chv_read_luts(struct intel_crtc_state *crtc_state)
 {
-	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
-		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
-	else
+	if (crtc_state->cgm_mode & CGM_PIPE_MODE_GAMMA)
 		crtc_state->base.gamma_lut = chv_read_cgm_lut(crtc_state);
+	else
+		i965_read_luts(crtc_state);
 }
 
 static struct drm_property_blob *
@@ -1742,6 +1748,12 @@ ilk_read_lut_10(const struct intel_crtc_state *crtc_state)
 
 static void ilk_read_luts(struct intel_crtc_state *crtc_state)
 {
+	if (!crtc_state->gamma_enable)
+		return;
+
+	if ((crtc_state->csc_mode & CSC_POSITION_BEFORE_GAMMA) == 0)
+		return;
+
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
 		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
 	else
@@ -1788,6 +1800,9 @@ glk_read_lut_10(const struct intel_crtc_state *crtc_state, u32 prec_index)
 
 static void glk_read_luts(struct intel_crtc_state *crtc_state)
 {
+	if (!crtc_state->gamma_enable)
+		return;
+
 	if (crtc_state->gamma_mode == GAMMA_MODE_MODE_8BIT)
 		crtc_state->base.gamma_lut = i9xx_read_lut_8(crtc_state);
 	else
-- 
cgit v1.2.3


From d50341274d013e80d80d33e03f4573a34f4d7277 Mon Sep 17 00:00:00 2001
From: Swati Sharma <swati2.sharma@intel.com>
Date: Wed, 9 Oct 2019 12:25:40 +0530
Subject: drm/i915/color: move check of gamma_enable to specific func/platform
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Moved common code to check gamma_enable to specific funcs per platform
in bit_precision func. icl doesn't support that and chv has separate
enable knob for CGM LUT.

v2:
-Simplified chv_gamma_precision() [Ville]

Signed-off-by: Swati Sharma <swati2.sharma@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191009065542.27415-3-swati2.sharma@intel.com
---
 drivers/gpu/drm/i915/display/intel_color.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index 08d020d4da35..fa44eb73d088 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1420,6 +1420,9 @@ static int icl_color_check(struct intel_crtc_state *crtc_state)
 
 static int i9xx_gamma_precision(const struct intel_crtc_state *crtc_state)
 {
+	if (!crtc_state->gamma_enable)
+		return 0;
+
 	switch (crtc_state->gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
 		return 8;
@@ -1433,6 +1436,9 @@ static int i9xx_gamma_precision(const struct intel_crtc_state *crtc_state)
 
 static int ilk_gamma_precision(const struct intel_crtc_state *crtc_state)
 {
+	if (!crtc_state->gamma_enable)
+		return 0;
+
 	if ((crtc_state->csc_mode & CSC_POSITION_BEFORE_GAMMA) == 0)
 		return 0;
 
@@ -1457,6 +1463,9 @@ static int chv_gamma_precision(const struct intel_crtc_state *crtc_state)
 
 static int glk_gamma_precision(const struct intel_crtc_state *crtc_state)
 {
+	if (!crtc_state->gamma_enable)
+		return 0;
+
 	switch (crtc_state->gamma_mode) {
 	case GAMMA_MODE_MODE_8BIT:
 		return 8;
@@ -1473,9 +1482,6 @@ int intel_color_get_gamma_bit_precision(const struct intel_crtc_state *crtc_stat
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 
-	if (!crtc_state->gamma_enable)
-		return 0;
-
 	if (HAS_GMCH(dev_priv)) {
 		if (IS_CHERRYVIEW(dev_priv))
 			return chv_gamma_precision(crtc_state);
-- 
cgit v1.2.3


From 2a86972f60fcfaa0daa02b9fe461935ea2063791 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Tue, 8 Oct 2019 10:29:20 -0700
Subject: drm/i915: Select DPLL's via mask
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This slightly simplifies the EHL DPLL4 handling and also gives us more
flexibility in the future in case we need to skip the use of specific
PLL's (e.g., due to hardware workarounds and such).

v2:
 - Replace GENMASK() with or'd BIT()'s to make the specific DPLLs more
   explicit.  (Ville)
 - s/unsigned/unsigned long/.  (Lucas)

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191008172920.11362-1-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/display/intel_dpll_mgr.c | 48 +++++++++++++++------------
 1 file changed, 26 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index 5e9e84c94a15..ec10fa7d3c69 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -247,8 +247,7 @@ static struct intel_shared_dpll *
 intel_find_shared_dpll(struct intel_atomic_state *state,
 		       const struct intel_crtc *crtc,
 		       const struct intel_dpll_hw_state *pll_state,
-		       enum intel_dpll_id range_min,
-		       enum intel_dpll_id range_max)
+		       unsigned long dpll_mask)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_shared_dpll *pll, *unused_pll = NULL;
@@ -257,7 +256,9 @@ intel_find_shared_dpll(struct intel_atomic_state *state,
 
 	shared_dpll = intel_atomic_get_shared_dpll_state(&state->base);
 
-	for (i = range_min; i <= range_max; i++) {
+	WARN_ON(dpll_mask & ~(BIT(I915_NUM_PLLS) - 1));
+
+	for_each_set_bit(i, &dpll_mask, I915_NUM_PLLS) {
 		pll = &dev_priv->shared_dplls[i];
 
 		/* Only want to check enabled timings first */
@@ -464,8 +465,8 @@ static bool ibx_get_dpll(struct intel_atomic_state *state,
 	} else {
 		pll = intel_find_shared_dpll(state, crtc,
 					     &crtc_state->dpll_hw_state,
-					     DPLL_ID_PCH_PLL_A,
-					     DPLL_ID_PCH_PLL_B);
+					     BIT(DPLL_ID_PCH_PLL_B) |
+					     BIT(DPLL_ID_PCH_PLL_A));
 	}
 
 	if (!pll)
@@ -814,7 +815,8 @@ hsw_ddi_hdmi_get_dpll(struct intel_atomic_state *state,
 
 	pll = intel_find_shared_dpll(state, crtc,
 				     &crtc_state->dpll_hw_state,
-				     DPLL_ID_WRPLL1, DPLL_ID_WRPLL2);
+				     BIT(DPLL_ID_WRPLL2) |
+				     BIT(DPLL_ID_WRPLL1));
 
 	if (!pll)
 		return NULL;
@@ -877,7 +879,7 @@ static bool hsw_get_dpll(struct intel_atomic_state *state,
 
 		pll = intel_find_shared_dpll(state, crtc,
 					     &crtc_state->dpll_hw_state,
-					     DPLL_ID_SPLL, DPLL_ID_SPLL);
+					     BIT(DPLL_ID_SPLL));
 	} else {
 		return false;
 	}
@@ -1447,13 +1449,13 @@ static bool skl_get_dpll(struct intel_atomic_state *state,
 	if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP))
 		pll = intel_find_shared_dpll(state, crtc,
 					     &crtc_state->dpll_hw_state,
-					     DPLL_ID_SKL_DPLL0,
-					     DPLL_ID_SKL_DPLL0);
+					     BIT(DPLL_ID_SKL_DPLL0));
 	else
 		pll = intel_find_shared_dpll(state, crtc,
 					     &crtc_state->dpll_hw_state,
-					     DPLL_ID_SKL_DPLL1,
-					     DPLL_ID_SKL_DPLL3);
+					     BIT(DPLL_ID_SKL_DPLL3) |
+					     BIT(DPLL_ID_SKL_DPLL2) |
+					     BIT(DPLL_ID_SKL_DPLL1));
 	if (!pll)
 		return false;
 
@@ -2401,8 +2403,9 @@ static bool cnl_get_dpll(struct intel_atomic_state *state,
 
 	pll = intel_find_shared_dpll(state, crtc,
 				     &crtc_state->dpll_hw_state,
-				     DPLL_ID_SKL_DPLL0,
-				     DPLL_ID_SKL_DPLL2);
+				     BIT(DPLL_ID_SKL_DPLL2) |
+				     BIT(DPLL_ID_SKL_DPLL1) |
+				     BIT(DPLL_ID_SKL_DPLL0));
 	if (!pll) {
 		DRM_DEBUG_KMS("No PLL selected\n");
 		return false;
@@ -2975,7 +2978,7 @@ static bool icl_get_combo_phy_dpll(struct intel_atomic_state *state,
 		&crtc_state->icl_port_dplls[ICL_PORT_DPLL_DEFAULT];
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum port port = encoder->port;
-	bool has_dpll4 = false;
+	unsigned long dpll_mask;
 
 	if (!icl_calc_dpll_state(crtc_state, encoder, &port_dpll->hw_state)) {
 		DRM_DEBUG_KMS("Could not calculate combo PHY PLL state.\n");
@@ -2984,13 +2987,16 @@ static bool icl_get_combo_phy_dpll(struct intel_atomic_state *state,
 	}
 
 	if (IS_ELKHARTLAKE(dev_priv) && port != PORT_A)
-		has_dpll4 = true;
+		dpll_mask =
+			BIT(DPLL_ID_EHL_DPLL4) |
+			BIT(DPLL_ID_ICL_DPLL1) |
+			BIT(DPLL_ID_ICL_DPLL0);
+	else
+		dpll_mask = BIT(DPLL_ID_ICL_DPLL1) | BIT(DPLL_ID_ICL_DPLL0);
 
 	port_dpll->pll = intel_find_shared_dpll(state, crtc,
 						&port_dpll->hw_state,
-						DPLL_ID_ICL_DPLL0,
-						has_dpll4 ? DPLL_ID_EHL_DPLL4
-							  : DPLL_ID_ICL_DPLL1);
+						dpll_mask);
 	if (!port_dpll->pll) {
 		DRM_DEBUG_KMS("No combo PHY PLL found for [ENCODER:%d:%s]\n",
 			      encoder->base.base.id, encoder->base.name);
@@ -3023,8 +3029,7 @@ static bool icl_get_tc_phy_dplls(struct intel_atomic_state *state,
 
 	port_dpll->pll = intel_find_shared_dpll(state, crtc,
 						&port_dpll->hw_state,
-						DPLL_ID_ICL_TBTPLL,
-						DPLL_ID_ICL_TBTPLL);
+						BIT(DPLL_ID_ICL_TBTPLL));
 	if (!port_dpll->pll) {
 		DRM_DEBUG_KMS("No TBT-ALT PLL found\n");
 		return false;
@@ -3043,8 +3048,7 @@ static bool icl_get_tc_phy_dplls(struct intel_atomic_state *state,
 							 encoder->port));
 	port_dpll->pll = intel_find_shared_dpll(state, crtc,
 						&port_dpll->hw_state,
-						dpll_id,
-						dpll_id);
+						BIT(dpll_id));
 	if (!port_dpll->pll) {
 		DRM_DEBUG_KMS("No MG PHY PLL found\n");
 		goto err_unreference_tbt_pll;
-- 
cgit v1.2.3


From 031d73ed768a40684f3ca21992265ffdb6a270bf Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trondmy@gmail.com>
Date: Mon, 30 Sep 2019 14:02:56 -0400
Subject: NFS: Fix O_DIRECT accounting of number of bytes read/written

When a series of O_DIRECT reads or writes are truncated, either due to
eof or due to an error, then we should return the number of contiguous
bytes that were received/sent starting at the offset specified by the
application.

Currently, we are failing to correctly check contiguity, and so we're
failing the generic/465 in xfstests when the race between the read
and write RPCs causes the file to get extended while the 2 reads are
outstanding. If the first read RPC call wins the race and returns with
eof set, we should treat the second read RPC as being truncated.

Reported-by: Su Yanjun <suyj.fnst@cn.fujitsu.com>
Fixes: 1ccbad9f9f9bd ("nfs: fix DIO good bytes calculation")
Cc: stable@vger.kernel.org # 4.1+
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/direct.c | 78 +++++++++++++++++++++++++++++++--------------------------
 1 file changed, 43 insertions(+), 35 deletions(-)

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 222d7115db71..98a9a0bcdf38 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -123,32 +123,49 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
 }
 
 static void
-nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr)
+nfs_direct_handle_truncated(struct nfs_direct_req *dreq,
+			    const struct nfs_pgio_header *hdr,
+			    ssize_t dreq_len)
 {
-	int i;
-	ssize_t count;
+	struct nfs_direct_mirror *mirror = &dreq->mirrors[hdr->pgio_mirror_idx];
+
+	if (!(test_bit(NFS_IOHDR_ERROR, &hdr->flags) ||
+	      test_bit(NFS_IOHDR_EOF, &hdr->flags)))
+		return;
+	if (dreq->max_count >= dreq_len) {
+		dreq->max_count = dreq_len;
+		if (dreq->count > dreq_len)
+			dreq->count = dreq_len;
+
+		if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
+			dreq->error = hdr->error;
+		else /* Clear outstanding error if this is EOF */
+			dreq->error = 0;
+	}
+	if (mirror->count > dreq_len)
+		mirror->count = dreq_len;
+}
 
-	WARN_ON_ONCE(dreq->count >= dreq->max_count);
+static void
+nfs_direct_count_bytes(struct nfs_direct_req *dreq,
+		       const struct nfs_pgio_header *hdr)
+{
+	struct nfs_direct_mirror *mirror = &dreq->mirrors[hdr->pgio_mirror_idx];
+	loff_t hdr_end = hdr->io_start + hdr->good_bytes;
+	ssize_t dreq_len = 0;
 
-	if (dreq->mirror_count == 1) {
-		dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes;
-		dreq->count += hdr->good_bytes;
-	} else {
-		/* mirrored writes */
-		count = dreq->mirrors[hdr->pgio_mirror_idx].count;
-		if (count + dreq->io_start < hdr->io_start + hdr->good_bytes) {
-			count = hdr->io_start + hdr->good_bytes - dreq->io_start;
-			dreq->mirrors[hdr->pgio_mirror_idx].count = count;
-		}
-		/* update the dreq->count by finding the minimum agreed count from all
-		 * mirrors */
-		count = dreq->mirrors[0].count;
+	if (hdr_end > dreq->io_start)
+		dreq_len = hdr_end - dreq->io_start;
 
-		for (i = 1; i < dreq->mirror_count; i++)
-			count = min(count, dreq->mirrors[i].count);
+	nfs_direct_handle_truncated(dreq, hdr, dreq_len);
 
-		dreq->count = count;
-	}
+	if (dreq_len > dreq->max_count)
+		dreq_len = dreq->max_count;
+
+	if (mirror->count < dreq_len)
+		mirror->count = dreq_len;
+	if (dreq->count < dreq_len)
+		dreq->count = dreq_len;
 }
 
 /*
@@ -402,20 +419,12 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 	struct nfs_direct_req *dreq = hdr->dreq;
 
 	spin_lock(&dreq->lock);
-	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
-		dreq->error = hdr->error;
-
 	if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) {
 		spin_unlock(&dreq->lock);
 		goto out_put;
 	}
 
-	if (hdr->good_bytes != 0)
-		nfs_direct_good_bytes(dreq, hdr);
-
-	if (test_bit(NFS_IOHDR_EOF, &hdr->flags))
-		dreq->error = 0;
-
+	nfs_direct_count_bytes(dreq, hdr);
 	spin_unlock(&dreq->lock);
 
 	while (!list_empty(&hdr->pages)) {
@@ -652,6 +661,9 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo);
 
 	dreq->count = 0;
+	dreq->max_count = 0;
+	list_for_each_entry(req, &reqs, wb_list)
+		dreq->max_count += req->wb_bytes;
 	dreq->verf.committed = NFS_INVALID_STABLE_HOW;
 	nfs_clear_pnfs_ds_commit_verifiers(&dreq->ds_cinfo);
 	for (i = 0; i < dreq->mirror_count; i++)
@@ -791,17 +803,13 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 	nfs_init_cinfo_from_dreq(&cinfo, dreq);
 
 	spin_lock(&dreq->lock);
-
-	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
-		dreq->error = hdr->error;
-
 	if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) {
 		spin_unlock(&dreq->lock);
 		goto out_put;
 	}
 
+	nfs_direct_count_bytes(dreq, hdr);
 	if (hdr->good_bytes != 0) {
-		nfs_direct_good_bytes(dreq, hdr);
 		if (nfs_write_need_commit(hdr)) {
 			if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
 				request_commit = true;
-- 
cgit v1.2.3


From 0b5748477924d2fb37f6b77d1a7eef600a96d722 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trondmy@gmail.com>
Date: Mon, 30 Sep 2019 14:02:57 -0400
Subject: NFS: Remove redundant mirror tracking in O_DIRECT

We no longer need the extra mirror length tracking in the O_DIRECT code,
as we are able to track the maximum contiguous length in dreq->max_count.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/direct.c | 42 ------------------------------------------
 1 file changed, 42 deletions(-)

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 98a9a0bcdf38..040a50fd9bf3 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -64,13 +64,6 @@
 
 static struct kmem_cache *nfs_direct_cachep;
 
-/*
- * This represents a set of asynchronous requests that we're waiting on
- */
-struct nfs_direct_mirror {
-	ssize_t count;
-};
-
 struct nfs_direct_req {
 	struct kref		kref;		/* release manager */
 
@@ -84,9 +77,6 @@ struct nfs_direct_req {
 	atomic_t		io_count;	/* i/os we're waiting for */
 	spinlock_t		lock;		/* protect completion state */
 
-	struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX];
-	int			mirror_count;
-
 	loff_t			io_start;	/* Start offset for I/O */
 	ssize_t			count,		/* bytes actually processed */
 				max_count,	/* max expected count */
@@ -127,8 +117,6 @@ nfs_direct_handle_truncated(struct nfs_direct_req *dreq,
 			    const struct nfs_pgio_header *hdr,
 			    ssize_t dreq_len)
 {
-	struct nfs_direct_mirror *mirror = &dreq->mirrors[hdr->pgio_mirror_idx];
-
 	if (!(test_bit(NFS_IOHDR_ERROR, &hdr->flags) ||
 	      test_bit(NFS_IOHDR_EOF, &hdr->flags)))
 		return;
@@ -142,15 +130,12 @@ nfs_direct_handle_truncated(struct nfs_direct_req *dreq,
 		else /* Clear outstanding error if this is EOF */
 			dreq->error = 0;
 	}
-	if (mirror->count > dreq_len)
-		mirror->count = dreq_len;
 }
 
 static void
 nfs_direct_count_bytes(struct nfs_direct_req *dreq,
 		       const struct nfs_pgio_header *hdr)
 {
-	struct nfs_direct_mirror *mirror = &dreq->mirrors[hdr->pgio_mirror_idx];
 	loff_t hdr_end = hdr->io_start + hdr->good_bytes;
 	ssize_t dreq_len = 0;
 
@@ -162,8 +147,6 @@ nfs_direct_count_bytes(struct nfs_direct_req *dreq,
 	if (dreq_len > dreq->max_count)
 		dreq_len = dreq->max_count;
 
-	if (mirror->count < dreq_len)
-		mirror->count = dreq_len;
 	if (dreq->count < dreq_len)
 		dreq->count = dreq_len;
 }
@@ -310,18 +293,6 @@ void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
 	cinfo->completion_ops = &nfs_direct_commit_completion_ops;
 }
 
-static inline void nfs_direct_setup_mirroring(struct nfs_direct_req *dreq,
-					     struct nfs_pageio_descriptor *pgio,
-					     struct nfs_page *req)
-{
-	int mirror_count = 1;
-
-	if (pgio->pg_ops->pg_get_mirror_count)
-		mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req);
-
-	dreq->mirror_count = mirror_count;
-}
-
 static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
 {
 	struct nfs_direct_req *dreq;
@@ -336,7 +307,6 @@ static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
 	INIT_LIST_HEAD(&dreq->mds_cinfo.list);
 	dreq->verf.committed = NFS_INVALID_STABLE_HOW;	/* not set yet */
 	INIT_WORK(&dreq->work, nfs_direct_write_schedule_work);
-	dreq->mirror_count = 1;
 	spin_lock_init(&dreq->lock);
 
 	return dreq;
@@ -655,7 +625,6 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	LIST_HEAD(reqs);
 	struct nfs_commit_info cinfo;
 	LIST_HEAD(failed);
-	int i;
 
 	nfs_init_cinfo_from_dreq(&cinfo, dreq);
 	nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo);
@@ -666,21 +635,12 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 		dreq->max_count += req->wb_bytes;
 	dreq->verf.committed = NFS_INVALID_STABLE_HOW;
 	nfs_clear_pnfs_ds_commit_verifiers(&dreq->ds_cinfo);
-	for (i = 0; i < dreq->mirror_count; i++)
-		dreq->mirrors[i].count = 0;
 	get_dreq(dreq);
 
 	nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, false,
 			      &nfs_direct_write_completion_ops);
 	desc.pg_dreq = dreq;
 
-	req = nfs_list_entry(reqs.next);
-	nfs_direct_setup_mirroring(dreq, &desc, req);
-	if (desc.pg_error < 0) {
-		list_splice_init(&reqs, &failed);
-		goto out_failed;
-	}
-
 	list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
 		/* Bump the transmission count */
 		req->wb_nio++;
@@ -698,7 +658,6 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	}
 	nfs_pageio_complete(&desc);
 
-out_failed:
 	while (!list_empty(&failed)) {
 		req = nfs_list_entry(failed.next);
 		nfs_list_remove_request(req);
@@ -931,7 +890,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 				break;
 			}
 
-			nfs_direct_setup_mirroring(dreq, &desc, req);
 			if (desc.pg_error < 0) {
 				nfs_free_request(req);
 				result = desc.pg_error;
-- 
cgit v1.2.3


From 0b10d8a89f55c416f6a1f6a616669543fa8bdb69 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Mon, 7 Oct 2019 12:54:15 -0700
Subject: xfs: log the inode on directory sf to block format change

When a directory changes from shortform (sf) to block format, the sf
format is copied to a temporary buffer, the inode format is modified
and the updated format filled with the dentries from the temporary
buffer. If the inode format is modified and attempt to grow the
inode fails (due to I/O error, for example), it is possible to
return an error while leaving the directory in an inconsistent state
and with an otherwise clean transaction. This results in corruption
of the associated directory and leads to xfs_dabuf_map() errors as
subsequent lookups cannot accurately determine the format of the
directory. This problem is reproduced occasionally by generic/475.

The fundamental problem is that xfs_dir2_sf_to_block() changes the
on-disk inode format without logging the inode. The inode is
eventually logged by the bmapi layer in the common case, but error
checking introduces the possibility of failing the high level
request before this happens.

Update both of the dir2 and attr callers of
xfs_bmap_local_to_extents_empty() to log the inode core as
consistent with the bmap local to extent format change codepath.
This ensures that any subsequent errors after the format has changed
cause the transaction to abort.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr_leaf.c  | 1 +
 fs/xfs/libxfs/xfs_dir2_block.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index b9f019603d0b..36c0a32cefcf 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -827,6 +827,7 @@ xfs_attr_shortform_to_leaf(
 
 	xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
 	xfs_bmap_local_to_extents_empty(dp, XFS_ATTR_FORK);
+	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE);
 
 	bp = NULL;
 	error = xfs_da_grow_inode(args, &blkno);
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 9595ced393dc..3d1e5f6d64fd 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -1098,6 +1098,7 @@ xfs_dir2_sf_to_block(
 	xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK);
 	xfs_bmap_local_to_extents_empty(dp, XFS_DATA_FORK);
 	dp->i_d.di_size = 0;
+	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 
 	/*
 	 * Add block 0 to the inode.
-- 
cgit v1.2.3


From 603efebd6768356fb7cea02e4a822587c2dc5d7c Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Mon, 7 Oct 2019 12:54:15 -0700
Subject: xfs: remove broken error handling on failed attr sf to leaf change

xfs_attr_shortform_to_leaf() attempts to put the shortform fork back
together after a failed attempt to convert from shortform to leaf
format. While this code reallocates and copies back the shortform
attr fork data, it never resets the inode format field back to local
format. Further, now that the inode is properly logged after the
initial switch from local format, any error that triggers the
recovery code will eventually abort the transaction and shutdown the
fs. Therefore, remove the broken and unnecessary error handling
code.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr_leaf.c | 19 ++-----------------
 1 file changed, 2 insertions(+), 17 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 36c0a32cefcf..1b956c313b6b 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -831,28 +831,13 @@ xfs_attr_shortform_to_leaf(
 
 	bp = NULL;
 	error = xfs_da_grow_inode(args, &blkno);
-	if (error) {
-		/*
-		 * If we hit an IO error middle of the transaction inside
-		 * grow_inode(), we may have inconsistent data. Bail out.
-		 */
-		if (error == -EIO)
-			goto out;
-		xfs_idata_realloc(dp, size, XFS_ATTR_FORK);	/* try to put */
-		memcpy(ifp->if_u1.if_data, tmpbuffer, size);	/* it back */
+	if (error)
 		goto out;
-	}
 
 	ASSERT(blkno == 0);
 	error = xfs_attr3_leaf_create(args, blkno, &bp);
-	if (error) {
-		/* xfs_attr3_leaf_create may not have instantiated a block */
-		if (bp && (xfs_da_shrink_inode(args, 0, bp) != 0))
-			goto out;
-		xfs_idata_realloc(dp, size, XFS_ATTR_FORK);	/* try to put */
-		memcpy(ifp->if_u1.if_data, tmpbuffer, size);	/* it back */
+	if (error)
 		goto out;
-	}
 
 	memset((char *)&nargs, 0, sizeof(nargs));
 	nargs.dp = dp;
-- 
cgit v1.2.3


From aeea4b75f045294e1c026acc380466daa43afc65 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Mon, 7 Oct 2019 12:54:16 -0700
Subject: xfs: move local to extent inode logging into bmap helper

The callers of xfs_bmap_local_to_extents_empty() log the inode
external to the function, yet this function is where the on-disk
format value is updated. Push the inode logging down into the
function itself to help prevent future mistakes.

Note that internal bmap callers track the inode logging flags
independently and thus may log the inode core twice due to this
change. This is harmless, so leave this code around for consistency
with the other attr fork conversion functions.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr_leaf.c  | 3 +--
 fs/xfs/libxfs/xfs_bmap.c       | 6 ++++--
 fs/xfs/libxfs/xfs_bmap.h       | 3 ++-
 fs/xfs/libxfs/xfs_dir2_block.c | 3 +--
 4 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 1b956c313b6b..f0089e862216 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -826,8 +826,7 @@ xfs_attr_shortform_to_leaf(
 	sf = (xfs_attr_shortform_t *)tmpbuffer;
 
 	xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
-	xfs_bmap_local_to_extents_empty(dp, XFS_ATTR_FORK);
-	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE);
+	xfs_bmap_local_to_extents_empty(args->trans, dp, XFS_ATTR_FORK);
 
 	bp = NULL;
 	error = xfs_da_grow_inode(args, &blkno);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 4edc25a2ba80..02469d59c787 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -792,6 +792,7 @@ out_root_realloc:
  */
 void
 xfs_bmap_local_to_extents_empty(
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork)
 {
@@ -808,6 +809,7 @@ xfs_bmap_local_to_extents_empty(
 	ifp->if_u1.if_root = NULL;
 	ifp->if_height = 0;
 	XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 }
 
 
@@ -840,7 +842,7 @@ xfs_bmap_local_to_extents(
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
 
 	if (!ifp->if_bytes) {
-		xfs_bmap_local_to_extents_empty(ip, whichfork);
+		xfs_bmap_local_to_extents_empty(tp, ip, whichfork);
 		flags = XFS_ILOG_CORE;
 		goto done;
 	}
@@ -887,7 +889,7 @@ xfs_bmap_local_to_extents(
 
 	/* account for the change in fork size */
 	xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
-	xfs_bmap_local_to_extents_empty(ip, whichfork);
+	xfs_bmap_local_to_extents_empty(tp, ip, whichfork);
 	flags |= XFS_ILOG_CORE;
 
 	ifp->if_u1.if_root = NULL;
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 5bb446d80542..e2798c6f3a5f 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -182,7 +182,8 @@ void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
 		xfs_filblks_t len);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 int	xfs_bmap_set_attrforkoff(struct xfs_inode *ip, int size, int *version);
-void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
+void	xfs_bmap_local_to_extents_empty(struct xfs_trans *tp,
+		struct xfs_inode *ip, int whichfork);
 void	__xfs_bmap_add_free(struct xfs_trans *tp, xfs_fsblock_t bno,
 		xfs_filblks_t len, const struct xfs_owner_info *oinfo,
 		bool skip_discard);
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 3d1e5f6d64fd..49e4bc39e7bb 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -1096,9 +1096,8 @@ xfs_dir2_sf_to_block(
 	memcpy(sfp, oldsfp, ifp->if_bytes);
 
 	xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK);
-	xfs_bmap_local_to_extents_empty(dp, XFS_DATA_FORK);
+	xfs_bmap_local_to_extents_empty(tp, dp, XFS_DATA_FORK);
 	dp->i_d.di_size = 0;
-	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 
 	/*
 	 * Add block 0 to the inode.
-- 
cgit v1.2.3


From 083164dbdb17c5ea4ad92c1782b59c9d75567790 Mon Sep 17 00:00:00 2001
From: Nirmoy Das <nirmoy.das@amd.com>
Date: Fri, 4 Oct 2019 11:53:37 +0200
Subject: drm/amdgpu: fix memory leak
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

cleanup error handling code and make sure temporary info array
with the handles are freed by amdgpu_bo_list_put() on
idr_replace()'s failure.

Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 7bcf86c61999..61e38e43ad1d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -270,7 +270,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 
 	r = amdgpu_bo_create_list_entry_array(&args->in, &info);
 	if (r)
-		goto error_free;
+		return r;
 
 	switch (args->in.operation) {
 	case AMDGPU_BO_LIST_OP_CREATE:
@@ -283,8 +283,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 		r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL);
 		mutex_unlock(&fpriv->bo_list_lock);
 		if (r < 0) {
-			amdgpu_bo_list_put(list);
-			return r;
+			goto error_put_list;
 		}
 
 		handle = r;
@@ -306,9 +305,8 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 		mutex_unlock(&fpriv->bo_list_lock);
 
 		if (IS_ERR(old)) {
-			amdgpu_bo_list_put(list);
 			r = PTR_ERR(old);
-			goto error_free;
+			goto error_put_list;
 		}
 
 		amdgpu_bo_list_put(old);
@@ -325,8 +323,10 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 
 	return 0;
 
+error_put_list:
+	amdgpu_bo_list_put(list);
+
 error_free:
-	if (info)
-		kvfree(info);
+	kvfree(info);
 	return r;
 }
-- 
cgit v1.2.3


From 598c30dbcc9434706f29a085a8eba4730573bcc2 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 2 Oct 2019 16:10:24 -0500
Subject: drm/amdgpu/powerplay: fix typo in mvdd table setup

Polaris and vegam use count for the value rather than
level.  This looks like a copy paste typo from when
the code was adapted from previous asics.

I'm not sure that the SMU actually uses this value, so
I don't know that it actually is a bug per se.

Bug: https://bugs.freedesktop.org/show_bug.cgi?id=108609
Reported-by: Robert Strube <rstrube@gmail.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c | 2 +-
 drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index dc754447f0dd..23c12018dbc1 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -655,7 +655,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
 			count = SMU_MAX_SMIO_LEVELS;
 		for (level = 0; level < count; level++) {
 			table->SmioTable2.Pattern[level].Voltage =
-				PP_HOST_TO_SMC_US(data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE);
+				PP_HOST_TO_SMC_US(data->mvdd_voltage_table.entries[level].value * VOLTAGE_SCALE);
 			/* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/
 			table->SmioTable2.Pattern[level].Smio =
 				(uint8_t) level;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index 7c960b07746f..ae18fbcb26fb 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -456,7 +456,7 @@ static int vegam_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr,
 			count = SMU_MAX_SMIO_LEVELS;
 		for (level = 0; level < count; level++) {
 			table->SmioTable2.Pattern[level].Voltage = PP_HOST_TO_SMC_US(
-					data->mvdd_voltage_table.entries[count].value * VOLTAGE_SCALE);
+					data->mvdd_voltage_table.entries[level].value * VOLTAGE_SCALE);
 			/* Index into DpmTable.Smio. Drive bits from Smio entry to get this voltage level.*/
 			table->SmioTable2.Pattern[level].Smio =
 				(uint8_t) level;
-- 
cgit v1.2.3


From 4043ecfb5fc4355a090111e14faf7945ff0fdbd5 Mon Sep 17 00:00:00 2001
From: Andreas Klinger <ak@it-klinger.de>
Date: Mon, 9 Sep 2019 14:37:21 +0200
Subject: iio: adc: hx711: fix bug in sampling of data

Fix bug in sampling function hx711_cycle() when interrupt occures while
PD_SCK is high. If PD_SCK is high for at least 60 us power down mode of
the sensor is entered which in turn leads to a wrong measurement.

Switch off interrupts during a PD_SCK high period and move query of DOUT
to the latest point of time which is at the end of PD_SCK low period.

This bug exists in the driver since it's initial addition. The more
interrupts on the system the higher is the probability that it happens.

Fixes: c3b2fdd0ea7e ("iio: adc: hx711: Add IIO driver for AVIA HX711")
Signed-off-by: Andreas Klinger <ak@it-klinger.de>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/hx711.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/iio/adc/hx711.c b/drivers/iio/adc/hx711.c
index 88c7fe15003b..62e6c8badd22 100644
--- a/drivers/iio/adc/hx711.c
+++ b/drivers/iio/adc/hx711.c
@@ -100,14 +100,14 @@ struct hx711_data {
 
 static int hx711_cycle(struct hx711_data *hx711_data)
 {
-	int val;
+	unsigned long flags;
 
 	/*
 	 * if preempted for more then 60us while PD_SCK is high:
 	 * hx711 is going in reset
 	 * ==> measuring is false
 	 */
-	preempt_disable();
+	local_irq_save(flags);
 	gpiod_set_value(hx711_data->gpiod_pd_sck, 1);
 
 	/*
@@ -117,7 +117,6 @@ static int hx711_cycle(struct hx711_data *hx711_data)
 	 */
 	ndelay(hx711_data->data_ready_delay_ns);
 
-	val = gpiod_get_value(hx711_data->gpiod_dout);
 	/*
 	 * here we are not waiting for 0.2 us as suggested by the datasheet,
 	 * because the oscilloscope showed in a test scenario
@@ -125,7 +124,7 @@ static int hx711_cycle(struct hx711_data *hx711_data)
 	 * and 0.56 us for PD_SCK low on TI Sitara with 800 MHz
 	 */
 	gpiod_set_value(hx711_data->gpiod_pd_sck, 0);
-	preempt_enable();
+	local_irq_restore(flags);
 
 	/*
 	 * make it a square wave for addressing cases with capacitance on
@@ -133,7 +132,8 @@ static int hx711_cycle(struct hx711_data *hx711_data)
 	 */
 	ndelay(hx711_data->data_ready_delay_ns);
 
-	return val;
+	/* sample as late as possible */
+	return gpiod_get_value(hx711_data->gpiod_dout);
 }
 
 static int hx711_read(struct hx711_data *hx711_data)
-- 
cgit v1.2.3


From d202ce4787e446556c6b9d01f84734c3f8174ba3 Mon Sep 17 00:00:00 2001
From: Stefan Popa <stefan.popa@analog.com>
Date: Tue, 10 Sep 2019 17:43:32 +0300
Subject: iio: accel: adxl372: Fix/remove limitation for FIFO samples

Currently, the driver sets the FIFO_SAMPLES register with the number of
sample sets (maximum of 170 for 3 axis data, 256 for 2-axis and 512 for
single axis). However, the FIFO_SAMPLES register should store the number
of samples, regardless of how the FIFO format is configured.

Signed-off-by: Stefan Popa <stefan.popa@analog.com>
Fixes: f4f55ce38e5f ("iio:adxl372: Add FIFO and interrupts support")
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/adxl372.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/iio/accel/adxl372.c b/drivers/iio/accel/adxl372.c
index 055227cb3d43..863fe61a371f 100644
--- a/drivers/iio/accel/adxl372.c
+++ b/drivers/iio/accel/adxl372.c
@@ -474,12 +474,17 @@ static int adxl372_configure_fifo(struct adxl372_state *st)
 	if (ret < 0)
 		return ret;
 
-	fifo_samples = st->watermark & 0xFF;
+	/*
+	 * watermark stores the number of sets; we need to write the FIFO
+	 * registers with the number of samples
+	 */
+	fifo_samples = (st->watermark * st->fifo_set_size);
 	fifo_ctl = ADXL372_FIFO_CTL_FORMAT_MODE(st->fifo_format) |
 		   ADXL372_FIFO_CTL_MODE_MODE(st->fifo_mode) |
-		   ADXL372_FIFO_CTL_SAMPLES_MODE(st->watermark);
+		   ADXL372_FIFO_CTL_SAMPLES_MODE(fifo_samples);
 
-	ret = regmap_write(st->regmap, ADXL372_FIFO_SAMPLES, fifo_samples);
+	ret = regmap_write(st->regmap,
+			   ADXL372_FIFO_SAMPLES, fifo_samples & 0xFF);
 	if (ret < 0)
 		return ret;
 
-- 
cgit v1.2.3


From 62df81b74393079debf04961c48cb22268fc5fab Mon Sep 17 00:00:00 2001
From: Stefan Popa <stefan.popa@analog.com>
Date: Tue, 10 Sep 2019 17:44:21 +0300
Subject: iio: accel: adxl372: Fix push to buffers lost samples

One in two sample sets was lost by multiplying fifo_set_size with
sizeof(u16). Also, the double number of available samples were pushed to
the iio buffers.

Signed-off-by: Stefan Popa <stefan.popa@analog.com>
Fixes: f4f55ce38e5f ("iio:adxl372: Add FIFO and interrupts support")
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/adxl372.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/iio/accel/adxl372.c b/drivers/iio/accel/adxl372.c
index 863fe61a371f..fbad4b45fe42 100644
--- a/drivers/iio/accel/adxl372.c
+++ b/drivers/iio/accel/adxl372.c
@@ -553,8 +553,7 @@ static irqreturn_t adxl372_trigger_handler(int irq, void  *p)
 			goto err;
 
 		/* Each sample is 2 bytes */
-		for (i = 0; i < fifo_entries * sizeof(u16);
-		     i += st->fifo_set_size * sizeof(u16))
+		for (i = 0; i < fifo_entries; i += st->fifo_set_size)
 			iio_push_to_buffers(indio_dev, &st->fifo_buf[i]);
 	}
 err:
-- 
cgit v1.2.3


From d9a997bd4d762d5bd8cc548d762902f58b5e0a74 Mon Sep 17 00:00:00 2001
From: Stefan Popa <stefan.popa@analog.com>
Date: Tue, 10 Sep 2019 17:44:46 +0300
Subject: iio: accel: adxl372: Perform a reset at start up

We need to perform a reset a start up to make sure that the chip is in a
consistent state. This reset also disables all the interrupts which
should only be enabled together with the iio buffer. Not doing this, was
sometimes causing unwanted interrupts to trigger.

Signed-off-by: Stefan Popa <stefan.popa@analog.com>
Fixes: f4f55ce38e5f ("iio:adxl372: Add FIFO and interrupts support")
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/accel/adxl372.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/iio/accel/adxl372.c b/drivers/iio/accel/adxl372.c
index fbad4b45fe42..67b8817995c0 100644
--- a/drivers/iio/accel/adxl372.c
+++ b/drivers/iio/accel/adxl372.c
@@ -575,6 +575,14 @@ static int adxl372_setup(struct adxl372_state *st)
 		return -ENODEV;
 	}
 
+	/*
+	 * Perform a software reset to make sure the device is in a consistent
+	 * state after start up.
+	 */
+	ret = regmap_write(st->regmap, ADXL372_RESET, ADXL372_RESET_CODE);
+	if (ret < 0)
+		return ret;
+
 	ret = adxl372_set_op_mode(st, ADXL372_STANDBY);
 	if (ret < 0)
 		return ret;
-- 
cgit v1.2.3


From 31922f62bb527d749b99dbc776e514bcba29b7fe Mon Sep 17 00:00:00 2001
From: Fabrice Gasnier <fabrice.gasnier@st.com>
Date: Tue, 17 Sep 2019 14:38:15 +0200
Subject: iio: adc: stm32-adc: move registers definitions

Move STM32 ADC registers definitions to common header.
This is precursor patch to:
- iio: adc: stm32-adc: fix a race when using several adcs with dma and irq

It keeps registers definitions as a whole block, to ease readability and
allow simple access path to EOC bits (readl) in stm32-adc-core driver.

Fixes: 2763ea0585c9 ("iio: adc: stm32: add optional dma support")

Signed-off-by: Fabrice Gasnier <fabrice.gasnier@st.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/stm32-adc-core.c |  27 --------
 drivers/iio/adc/stm32-adc-core.h | 136 +++++++++++++++++++++++++++++++++++++++
 drivers/iio/adc/stm32-adc.c      | 109 -------------------------------
 3 files changed, 136 insertions(+), 136 deletions(-)

diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c
index 9b85fefc0a96..84ac326bb714 100644
--- a/drivers/iio/adc/stm32-adc-core.c
+++ b/drivers/iio/adc/stm32-adc-core.c
@@ -24,33 +24,6 @@
 
 #include "stm32-adc-core.h"
 
-/* STM32F4 - common registers for all ADC instances: 1, 2 & 3 */
-#define STM32F4_ADC_CSR			(STM32_ADCX_COMN_OFFSET + 0x00)
-#define STM32F4_ADC_CCR			(STM32_ADCX_COMN_OFFSET + 0x04)
-
-/* STM32F4_ADC_CSR - bit fields */
-#define STM32F4_EOC3			BIT(17)
-#define STM32F4_EOC2			BIT(9)
-#define STM32F4_EOC1			BIT(1)
-
-/* STM32F4_ADC_CCR - bit fields */
-#define STM32F4_ADC_ADCPRE_SHIFT	16
-#define STM32F4_ADC_ADCPRE_MASK		GENMASK(17, 16)
-
-/* STM32H7 - common registers for all ADC instances */
-#define STM32H7_ADC_CSR			(STM32_ADCX_COMN_OFFSET + 0x00)
-#define STM32H7_ADC_CCR			(STM32_ADCX_COMN_OFFSET + 0x08)
-
-/* STM32H7_ADC_CSR - bit fields */
-#define STM32H7_EOC_SLV			BIT(18)
-#define STM32H7_EOC_MST			BIT(2)
-
-/* STM32H7_ADC_CCR - bit fields */
-#define STM32H7_PRESC_SHIFT		18
-#define STM32H7_PRESC_MASK		GENMASK(21, 18)
-#define STM32H7_CKMODE_SHIFT		16
-#define STM32H7_CKMODE_MASK		GENMASK(17, 16)
-
 #define STM32_ADC_CORE_SLEEP_DELAY_MS	2000
 
 /* SYSCFG registers */
diff --git a/drivers/iio/adc/stm32-adc-core.h b/drivers/iio/adc/stm32-adc-core.h
index 8af507b3f32d..94aa2d2577dc 100644
--- a/drivers/iio/adc/stm32-adc-core.h
+++ b/drivers/iio/adc/stm32-adc-core.h
@@ -27,6 +27,142 @@
 #define STM32_ADC_MAX_ADCS		3
 #define STM32_ADCX_COMN_OFFSET		0x300
 
+/* STM32F4 - Registers for each ADC instance */
+#define STM32F4_ADC_SR			0x00
+#define STM32F4_ADC_CR1			0x04
+#define STM32F4_ADC_CR2			0x08
+#define STM32F4_ADC_SMPR1		0x0C
+#define STM32F4_ADC_SMPR2		0x10
+#define STM32F4_ADC_HTR			0x24
+#define STM32F4_ADC_LTR			0x28
+#define STM32F4_ADC_SQR1		0x2C
+#define STM32F4_ADC_SQR2		0x30
+#define STM32F4_ADC_SQR3		0x34
+#define STM32F4_ADC_JSQR		0x38
+#define STM32F4_ADC_JDR1		0x3C
+#define STM32F4_ADC_JDR2		0x40
+#define STM32F4_ADC_JDR3		0x44
+#define STM32F4_ADC_JDR4		0x48
+#define STM32F4_ADC_DR			0x4C
+
+/* STM32F4 - common registers for all ADC instances: 1, 2 & 3 */
+#define STM32F4_ADC_CSR			(STM32_ADCX_COMN_OFFSET + 0x00)
+#define STM32F4_ADC_CCR			(STM32_ADCX_COMN_OFFSET + 0x04)
+
+/* STM32F4_ADC_SR - bit fields */
+#define STM32F4_STRT			BIT(4)
+#define STM32F4_EOC			BIT(1)
+
+/* STM32F4_ADC_CR1 - bit fields */
+#define STM32F4_RES_SHIFT		24
+#define STM32F4_RES_MASK		GENMASK(25, 24)
+#define STM32F4_SCAN			BIT(8)
+#define STM32F4_EOCIE			BIT(5)
+
+/* STM32F4_ADC_CR2 - bit fields */
+#define STM32F4_SWSTART			BIT(30)
+#define STM32F4_EXTEN_SHIFT		28
+#define STM32F4_EXTEN_MASK		GENMASK(29, 28)
+#define STM32F4_EXTSEL_SHIFT		24
+#define STM32F4_EXTSEL_MASK		GENMASK(27, 24)
+#define STM32F4_EOCS			BIT(10)
+#define STM32F4_DDS			BIT(9)
+#define STM32F4_DMA			BIT(8)
+#define STM32F4_ADON			BIT(0)
+
+/* STM32F4_ADC_CSR - bit fields */
+#define STM32F4_EOC3			BIT(17)
+#define STM32F4_EOC2			BIT(9)
+#define STM32F4_EOC1			BIT(1)
+
+/* STM32F4_ADC_CCR - bit fields */
+#define STM32F4_ADC_ADCPRE_SHIFT	16
+#define STM32F4_ADC_ADCPRE_MASK		GENMASK(17, 16)
+
+/* STM32H7 - Registers for each ADC instance */
+#define STM32H7_ADC_ISR			0x00
+#define STM32H7_ADC_IER			0x04
+#define STM32H7_ADC_CR			0x08
+#define STM32H7_ADC_CFGR		0x0C
+#define STM32H7_ADC_SMPR1		0x14
+#define STM32H7_ADC_SMPR2		0x18
+#define STM32H7_ADC_PCSEL		0x1C
+#define STM32H7_ADC_SQR1		0x30
+#define STM32H7_ADC_SQR2		0x34
+#define STM32H7_ADC_SQR3		0x38
+#define STM32H7_ADC_SQR4		0x3C
+#define STM32H7_ADC_DR			0x40
+#define STM32H7_ADC_DIFSEL		0xC0
+#define STM32H7_ADC_CALFACT		0xC4
+#define STM32H7_ADC_CALFACT2		0xC8
+
+/* STM32H7 - common registers for all ADC instances */
+#define STM32H7_ADC_CSR			(STM32_ADCX_COMN_OFFSET + 0x00)
+#define STM32H7_ADC_CCR			(STM32_ADCX_COMN_OFFSET + 0x08)
+
+/* STM32H7_ADC_ISR - bit fields */
+#define STM32MP1_VREGREADY		BIT(12)
+#define STM32H7_EOC			BIT(2)
+#define STM32H7_ADRDY			BIT(0)
+
+/* STM32H7_ADC_IER - bit fields */
+#define STM32H7_EOCIE			STM32H7_EOC
+
+/* STM32H7_ADC_CR - bit fields */
+#define STM32H7_ADCAL			BIT(31)
+#define STM32H7_ADCALDIF		BIT(30)
+#define STM32H7_DEEPPWD			BIT(29)
+#define STM32H7_ADVREGEN		BIT(28)
+#define STM32H7_LINCALRDYW6		BIT(27)
+#define STM32H7_LINCALRDYW5		BIT(26)
+#define STM32H7_LINCALRDYW4		BIT(25)
+#define STM32H7_LINCALRDYW3		BIT(24)
+#define STM32H7_LINCALRDYW2		BIT(23)
+#define STM32H7_LINCALRDYW1		BIT(22)
+#define STM32H7_ADCALLIN		BIT(16)
+#define STM32H7_BOOST			BIT(8)
+#define STM32H7_ADSTP			BIT(4)
+#define STM32H7_ADSTART			BIT(2)
+#define STM32H7_ADDIS			BIT(1)
+#define STM32H7_ADEN			BIT(0)
+
+/* STM32H7_ADC_CFGR bit fields */
+#define STM32H7_EXTEN_SHIFT		10
+#define STM32H7_EXTEN_MASK		GENMASK(11, 10)
+#define STM32H7_EXTSEL_SHIFT		5
+#define STM32H7_EXTSEL_MASK		GENMASK(9, 5)
+#define STM32H7_RES_SHIFT		2
+#define STM32H7_RES_MASK		GENMASK(4, 2)
+#define STM32H7_DMNGT_SHIFT		0
+#define STM32H7_DMNGT_MASK		GENMASK(1, 0)
+
+enum stm32h7_adc_dmngt {
+	STM32H7_DMNGT_DR_ONLY,		/* Regular data in DR only */
+	STM32H7_DMNGT_DMA_ONESHOT,	/* DMA one shot mode */
+	STM32H7_DMNGT_DFSDM,		/* DFSDM mode */
+	STM32H7_DMNGT_DMA_CIRC,		/* DMA circular mode */
+};
+
+/* STM32H7_ADC_CALFACT - bit fields */
+#define STM32H7_CALFACT_D_SHIFT		16
+#define STM32H7_CALFACT_D_MASK		GENMASK(26, 16)
+#define STM32H7_CALFACT_S_SHIFT		0
+#define STM32H7_CALFACT_S_MASK		GENMASK(10, 0)
+
+/* STM32H7_ADC_CALFACT2 - bit fields */
+#define STM32H7_LINCALFACT_SHIFT	0
+#define STM32H7_LINCALFACT_MASK		GENMASK(29, 0)
+
+/* STM32H7_ADC_CSR - bit fields */
+#define STM32H7_EOC_SLV			BIT(18)
+#define STM32H7_EOC_MST			BIT(2)
+
+/* STM32H7_ADC_CCR - bit fields */
+#define STM32H7_PRESC_SHIFT		18
+#define STM32H7_PRESC_MASK		GENMASK(21, 18)
+#define STM32H7_CKMODE_SHIFT		16
+#define STM32H7_CKMODE_MASK		GENMASK(17, 16)
+
 /**
  * struct stm32_adc_common - stm32 ADC driver common data (for all instances)
  * @base:		control registers base cpu addr
diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c
index 6a7dd08b1e0b..663f8a5012d6 100644
--- a/drivers/iio/adc/stm32-adc.c
+++ b/drivers/iio/adc/stm32-adc.c
@@ -28,115 +28,6 @@
 
 #include "stm32-adc-core.h"
 
-/* STM32F4 - Registers for each ADC instance */
-#define STM32F4_ADC_SR			0x00
-#define STM32F4_ADC_CR1			0x04
-#define STM32F4_ADC_CR2			0x08
-#define STM32F4_ADC_SMPR1		0x0C
-#define STM32F4_ADC_SMPR2		0x10
-#define STM32F4_ADC_HTR			0x24
-#define STM32F4_ADC_LTR			0x28
-#define STM32F4_ADC_SQR1		0x2C
-#define STM32F4_ADC_SQR2		0x30
-#define STM32F4_ADC_SQR3		0x34
-#define STM32F4_ADC_JSQR		0x38
-#define STM32F4_ADC_JDR1		0x3C
-#define STM32F4_ADC_JDR2		0x40
-#define STM32F4_ADC_JDR3		0x44
-#define STM32F4_ADC_JDR4		0x48
-#define STM32F4_ADC_DR			0x4C
-
-/* STM32F4_ADC_SR - bit fields */
-#define STM32F4_STRT			BIT(4)
-#define STM32F4_EOC			BIT(1)
-
-/* STM32F4_ADC_CR1 - bit fields */
-#define STM32F4_RES_SHIFT		24
-#define STM32F4_RES_MASK		GENMASK(25, 24)
-#define STM32F4_SCAN			BIT(8)
-#define STM32F4_EOCIE			BIT(5)
-
-/* STM32F4_ADC_CR2 - bit fields */
-#define STM32F4_SWSTART			BIT(30)
-#define STM32F4_EXTEN_SHIFT		28
-#define STM32F4_EXTEN_MASK		GENMASK(29, 28)
-#define STM32F4_EXTSEL_SHIFT		24
-#define STM32F4_EXTSEL_MASK		GENMASK(27, 24)
-#define STM32F4_EOCS			BIT(10)
-#define STM32F4_DDS			BIT(9)
-#define STM32F4_DMA			BIT(8)
-#define STM32F4_ADON			BIT(0)
-
-/* STM32H7 - Registers for each ADC instance */
-#define STM32H7_ADC_ISR			0x00
-#define STM32H7_ADC_IER			0x04
-#define STM32H7_ADC_CR			0x08
-#define STM32H7_ADC_CFGR		0x0C
-#define STM32H7_ADC_SMPR1		0x14
-#define STM32H7_ADC_SMPR2		0x18
-#define STM32H7_ADC_PCSEL		0x1C
-#define STM32H7_ADC_SQR1		0x30
-#define STM32H7_ADC_SQR2		0x34
-#define STM32H7_ADC_SQR3		0x38
-#define STM32H7_ADC_SQR4		0x3C
-#define STM32H7_ADC_DR			0x40
-#define STM32H7_ADC_DIFSEL		0xC0
-#define STM32H7_ADC_CALFACT		0xC4
-#define STM32H7_ADC_CALFACT2		0xC8
-
-/* STM32H7_ADC_ISR - bit fields */
-#define STM32MP1_VREGREADY		BIT(12)
-#define STM32H7_EOC			BIT(2)
-#define STM32H7_ADRDY			BIT(0)
-
-/* STM32H7_ADC_IER - bit fields */
-#define STM32H7_EOCIE			STM32H7_EOC
-
-/* STM32H7_ADC_CR - bit fields */
-#define STM32H7_ADCAL			BIT(31)
-#define STM32H7_ADCALDIF		BIT(30)
-#define STM32H7_DEEPPWD			BIT(29)
-#define STM32H7_ADVREGEN		BIT(28)
-#define STM32H7_LINCALRDYW6		BIT(27)
-#define STM32H7_LINCALRDYW5		BIT(26)
-#define STM32H7_LINCALRDYW4		BIT(25)
-#define STM32H7_LINCALRDYW3		BIT(24)
-#define STM32H7_LINCALRDYW2		BIT(23)
-#define STM32H7_LINCALRDYW1		BIT(22)
-#define STM32H7_ADCALLIN		BIT(16)
-#define STM32H7_BOOST			BIT(8)
-#define STM32H7_ADSTP			BIT(4)
-#define STM32H7_ADSTART			BIT(2)
-#define STM32H7_ADDIS			BIT(1)
-#define STM32H7_ADEN			BIT(0)
-
-/* STM32H7_ADC_CFGR bit fields */
-#define STM32H7_EXTEN_SHIFT		10
-#define STM32H7_EXTEN_MASK		GENMASK(11, 10)
-#define STM32H7_EXTSEL_SHIFT		5
-#define STM32H7_EXTSEL_MASK		GENMASK(9, 5)
-#define STM32H7_RES_SHIFT		2
-#define STM32H7_RES_MASK		GENMASK(4, 2)
-#define STM32H7_DMNGT_SHIFT		0
-#define STM32H7_DMNGT_MASK		GENMASK(1, 0)
-
-enum stm32h7_adc_dmngt {
-	STM32H7_DMNGT_DR_ONLY,		/* Regular data in DR only */
-	STM32H7_DMNGT_DMA_ONESHOT,	/* DMA one shot mode */
-	STM32H7_DMNGT_DFSDM,		/* DFSDM mode */
-	STM32H7_DMNGT_DMA_CIRC,		/* DMA circular mode */
-};
-
-/* STM32H7_ADC_CALFACT - bit fields */
-#define STM32H7_CALFACT_D_SHIFT		16
-#define STM32H7_CALFACT_D_MASK		GENMASK(26, 16)
-#define STM32H7_CALFACT_S_SHIFT		0
-#define STM32H7_CALFACT_S_MASK		GENMASK(10, 0)
-
-/* STM32H7_ADC_CALFACT2 - bit fields */
-#define STM32H7_LINCALFACT_SHIFT	0
-#define STM32H7_LINCALFACT_MASK		GENMASK(29, 0)
-
 /* Number of linear calibration shadow registers / LINCALRDYW control bits */
 #define STM32H7_LINCALFACT_NUM		6
 
-- 
cgit v1.2.3


From dcb10920179ab74caf88a6f2afadecfc2743b910 Mon Sep 17 00:00:00 2001
From: Fabrice Gasnier <fabrice.gasnier@st.com>
Date: Tue, 17 Sep 2019 14:38:16 +0200
Subject: iio: adc: stm32-adc: fix a race when using several adcs with dma and
 irq

End of conversion may be handled by using IRQ or DMA. There may be a
race when two conversions complete at the same time on several ADCs.
EOC can be read as 'set' for several ADCs, with:
- an ADC configured to use IRQs. EOCIE bit is set. The handler is normally
  called in this case.
- an ADC configured to use DMA. EOCIE bit isn't set. EOC triggers the DMA
  request instead. It's then automatically cleared by DMA read. But the
  handler gets called due to status bit is temporarily set (IRQ triggered
  by the other ADC).
So both EOC status bit in CSR and EOCIE control bit must be checked
before invoking the interrupt handler (e.g. call ISR only for
IRQ-enabled ADCs).

Fixes: 2763ea0585c9 ("iio: adc: stm32: add optional dma support")

Signed-off-by: Fabrice Gasnier <fabrice.gasnier@st.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/stm32-adc-core.c | 43 +++++++++++++++++++++++++++++++++++++---
 drivers/iio/adc/stm32-adc-core.h |  1 +
 2 files changed, 41 insertions(+), 3 deletions(-)

diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c
index 84ac326bb714..93a096a91f8c 100644
--- a/drivers/iio/adc/stm32-adc-core.c
+++ b/drivers/iio/adc/stm32-adc-core.c
@@ -44,6 +44,8 @@
  * @eoc1:	adc1 end of conversion flag in @csr
  * @eoc2:	adc2 end of conversion flag in @csr
  * @eoc3:	adc3 end of conversion flag in @csr
+ * @ier:	interrupt enable register offset for each adc
+ * @eocie_msk:	end of conversion interrupt enable mask in @ier
  */
 struct stm32_adc_common_regs {
 	u32 csr;
@@ -51,6 +53,8 @@ struct stm32_adc_common_regs {
 	u32 eoc1_msk;
 	u32 eoc2_msk;
 	u32 eoc3_msk;
+	u32 ier;
+	u32 eocie_msk;
 };
 
 struct stm32_adc_priv;
@@ -276,6 +280,8 @@ static const struct stm32_adc_common_regs stm32f4_adc_common_regs = {
 	.eoc1_msk = STM32F4_EOC1,
 	.eoc2_msk = STM32F4_EOC2,
 	.eoc3_msk = STM32F4_EOC3,
+	.ier = STM32F4_ADC_CR1,
+	.eocie_msk = STM32F4_EOCIE,
 };
 
 /* STM32H7 common registers definitions */
@@ -284,8 +290,24 @@ static const struct stm32_adc_common_regs stm32h7_adc_common_regs = {
 	.ccr = STM32H7_ADC_CCR,
 	.eoc1_msk = STM32H7_EOC_MST,
 	.eoc2_msk = STM32H7_EOC_SLV,
+	.ier = STM32H7_ADC_IER,
+	.eocie_msk = STM32H7_EOCIE,
 };
 
+static const unsigned int stm32_adc_offset[STM32_ADC_MAX_ADCS] = {
+	0, STM32_ADC_OFFSET, STM32_ADC_OFFSET * 2,
+};
+
+static unsigned int stm32_adc_eoc_enabled(struct stm32_adc_priv *priv,
+					  unsigned int adc)
+{
+	u32 ier, offset = stm32_adc_offset[adc];
+
+	ier = readl_relaxed(priv->common.base + offset + priv->cfg->regs->ier);
+
+	return ier & priv->cfg->regs->eocie_msk;
+}
+
 /* ADC common interrupt for all instances */
 static void stm32_adc_irq_handler(struct irq_desc *desc)
 {
@@ -296,13 +318,28 @@ static void stm32_adc_irq_handler(struct irq_desc *desc)
 	chained_irq_enter(chip, desc);
 	status = readl_relaxed(priv->common.base + priv->cfg->regs->csr);
 
-	if (status & priv->cfg->regs->eoc1_msk)
+	/*
+	 * End of conversion may be handled by using IRQ or DMA. There may be a
+	 * race here when two conversions complete at the same time on several
+	 * ADCs. EOC may be read 'set' for several ADCs, with:
+	 * - an ADC configured to use DMA (EOC triggers the DMA request, and
+	 *   is then automatically cleared by DR read in hardware)
+	 * - an ADC configured to use IRQs (EOCIE bit is set. The handler must
+	 *   be called in this case)
+	 * So both EOC status bit in CSR and EOCIE control bit must be checked
+	 * before invoking the interrupt handler (e.g. call ISR only for
+	 * IRQ-enabled ADCs).
+	 */
+	if (status & priv->cfg->regs->eoc1_msk &&
+	    stm32_adc_eoc_enabled(priv, 0))
 		generic_handle_irq(irq_find_mapping(priv->domain, 0));
 
-	if (status & priv->cfg->regs->eoc2_msk)
+	if (status & priv->cfg->regs->eoc2_msk &&
+	    stm32_adc_eoc_enabled(priv, 1))
 		generic_handle_irq(irq_find_mapping(priv->domain, 1));
 
-	if (status & priv->cfg->regs->eoc3_msk)
+	if (status & priv->cfg->regs->eoc3_msk &&
+	    stm32_adc_eoc_enabled(priv, 2))
 		generic_handle_irq(irq_find_mapping(priv->domain, 2));
 
 	chained_irq_exit(chip, desc);
diff --git a/drivers/iio/adc/stm32-adc-core.h b/drivers/iio/adc/stm32-adc-core.h
index 94aa2d2577dc..2579d514c2a3 100644
--- a/drivers/iio/adc/stm32-adc-core.h
+++ b/drivers/iio/adc/stm32-adc-core.h
@@ -25,6 +25,7 @@
  * --------------------------------------------------------
  */
 #define STM32_ADC_MAX_ADCS		3
+#define STM32_ADC_OFFSET		0x100
 #define STM32_ADCX_COMN_OFFSET		0x300
 
 /* STM32F4 - Registers for each ADC instance */
-- 
cgit v1.2.3


From ab612b1daf415b62c58e130cb3d0f30b255a14d0 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Thu, 19 Sep 2019 10:50:02 -0500
Subject: iio: imu: adis16400: release allocated memory on failure

In adis_update_scan_mode, if allocation for adis->buffer fails,
previously allocated adis->xfer needs to be released.

Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Reviewed-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/adis_buffer.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c
index 9ac8356d9a95..f446ff497809 100644
--- a/drivers/iio/imu/adis_buffer.c
+++ b/drivers/iio/imu/adis_buffer.c
@@ -78,8 +78,11 @@ int adis_update_scan_mode(struct iio_dev *indio_dev,
 		return -ENOMEM;
 
 	adis->buffer = kcalloc(indio_dev->scan_bytes, 2, GFP_KERNEL);
-	if (!adis->buffer)
+	if (!adis->buffer) {
+		kfree(adis->xfer);
+		adis->xfer = NULL;
 		return -ENOMEM;
+	}
 
 	rx = adis->buffer;
 	tx = rx + scan_count;
-- 
cgit v1.2.3


From 9c0530e898f384c5d279bfcebd8bb17af1105873 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Thu, 19 Sep 2019 10:56:35 -0500
Subject: iio: imu: adis16400: fix memory leak

In adis_update_scan_mode_burst, if adis->buffer allocation fails release
the adis->xfer.

Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Reviewed-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/adis_buffer.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/imu/adis_buffer.c b/drivers/iio/imu/adis_buffer.c
index f446ff497809..4998a89d083d 100644
--- a/drivers/iio/imu/adis_buffer.c
+++ b/drivers/iio/imu/adis_buffer.c
@@ -35,8 +35,11 @@ static int adis_update_scan_mode_burst(struct iio_dev *indio_dev,
 		return -ENOMEM;
 
 	adis->buffer = kzalloc(burst_length + sizeof(u16), GFP_KERNEL);
-	if (!adis->buffer)
+	if (!adis->buffer) {
+		kfree(adis->xfer);
+		adis->xfer = NULL;
 		return -ENOMEM;
+	}
 
 	tx = adis->buffer + burst_length;
 	tx[0] = ADIS_READ_REG(adis->burst->reg_cmd);
-- 
cgit v1.2.3


From 972917419a0ba25afbf69d5d8c9fa644d676f887 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 15 Sep 2019 20:53:42 +0200
Subject: iio: adc: axp288: Override TS pin bias current for some models
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since commit 9bcf15f75cac ("iio: adc: axp288: Fix TS-pin handling") we
preserve the bias current set by the firmware at boot.  This fixes issues
we were seeing on various models, but it seems our old hardcoded 80ųA bias
current was working around a firmware bug on at least one model laptop.

In order to both have our cake and eat it, this commit adds a dmi based
list of models where we need to override the firmware set bias current and
adds the one model we now know needs this to it: The Lenovo Ideapad 100S
(11 inch version).

Fixes: 9bcf15f75cac ("iio: adc: axp288: Fix TS-pin handling")
BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=203829
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/axp288_adc.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/drivers/iio/adc/axp288_adc.c b/drivers/iio/adc/axp288_adc.c
index adc9cf7a075d..8ea2aed6d6f5 100644
--- a/drivers/iio/adc/axp288_adc.c
+++ b/drivers/iio/adc/axp288_adc.c
@@ -7,6 +7,7 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
+#include <linux/dmi.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/device.h>
@@ -25,6 +26,11 @@
 #define AXP288_ADC_EN_MASK				0xF0
 #define AXP288_ADC_TS_ENABLE				0x01
 
+#define AXP288_ADC_TS_BIAS_MASK				GENMASK(5, 4)
+#define AXP288_ADC_TS_BIAS_20UA				(0 << 4)
+#define AXP288_ADC_TS_BIAS_40UA				(1 << 4)
+#define AXP288_ADC_TS_BIAS_60UA				(2 << 4)
+#define AXP288_ADC_TS_BIAS_80UA				(3 << 4)
 #define AXP288_ADC_TS_CURRENT_ON_OFF_MASK		GENMASK(1, 0)
 #define AXP288_ADC_TS_CURRENT_OFF			(0 << 0)
 #define AXP288_ADC_TS_CURRENT_ON_WHEN_CHARGING		(1 << 0)
@@ -177,10 +183,36 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev,
 	return ret;
 }
 
+/*
+ * We rely on the machine's firmware to correctly setup the TS pin bias current
+ * at boot. This lists systems with broken fw where we need to set it ourselves.
+ */
+static const struct dmi_system_id axp288_adc_ts_bias_override[] = {
+	{
+		/* Lenovo Ideapad 100S (11 inch) */
+		.matches = {
+		  DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		  DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad 100S-11IBY"),
+		},
+		.driver_data = (void *)(uintptr_t)AXP288_ADC_TS_BIAS_80UA,
+	},
+	{}
+};
+
 static int axp288_adc_initialize(struct axp288_adc_info *info)
 {
+	const struct dmi_system_id *bias_override;
 	int ret, adc_enable_val;
 
+	bias_override = dmi_first_match(axp288_adc_ts_bias_override);
+	if (bias_override) {
+		ret = regmap_update_bits(info->regmap, AXP288_ADC_TS_PIN_CTRL,
+					 AXP288_ADC_TS_BIAS_MASK,
+					 (uintptr_t)bias_override->driver_data);
+		if (ret)
+			return ret;
+	}
+
 	/*
 	 * Determine if the TS pin is enabled and set the TS current-source
 	 * accordingly.
-- 
cgit v1.2.3


From fdb828e2c71a09bb9e865f41b015597c5f671705 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 17 Sep 2019 00:01:29 +0200
Subject: iio: imu: st_lsm6dsx: fix waitime for st_lsm6dsx i2c controller

i2c controller available in st_lsm6dsx series performs i2c slave
configuration using accel clock as trigger.
st_lsm6dsx_shub_wait_complete routine is used to wait the controller has
carried out the requested configuration. However if the accel sensor is not
enabled we should not use its configured odr to estimate a proper timeout

Fixes: c91c1c844ebd ("iio: imu: st_lsm6dsx: add i2c embedded controller support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c
index f5fca2171954..ea472cf6db7b 100644
--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c
+++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_shub.c
@@ -93,9 +93,11 @@ static const struct st_lsm6dsx_ext_dev_settings st_lsm6dsx_ext_dev_table[] = {
 static void st_lsm6dsx_shub_wait_complete(struct st_lsm6dsx_hw *hw)
 {
 	struct st_lsm6dsx_sensor *sensor;
+	u16 odr;
 
 	sensor = iio_priv(hw->iio_devs[ST_LSM6DSX_ID_ACC]);
-	msleep((2000U / sensor->odr) + 1);
+	odr = (hw->enable_mask & BIT(ST_LSM6DSX_ID_ACC)) ? sensor->odr : 13;
+	msleep((2000U / odr) + 1);
 }
 
 /**
-- 
cgit v1.2.3


From 1436a78c63495dd94c8d4f84a76d78d5317d481b Mon Sep 17 00:00:00 2001
From: Marco Felsch <m.felsch@pengutronix.de>
Date: Tue, 17 Sep 2019 16:56:36 +0200
Subject: iio: light: fix vcnl4000 devicetree hooks

Since commit ebd457d55911 ("iio: light: vcnl4000 add devicetree hooks")
the of_match_table is supported but the data shouldn't be a string.
Instead it shall be one of 'enum vcnl4000_device_ids'. Also the matching
logic for the vcnl4020 was wrong. Since the data retrieve mechanism is
still based on the i2c_device_id no failures did appeared till now.

Fixes: ebd457d55911 ("iio: light: vcnl4000 add devicetree hooks")
Signed-off-by: Marco Felsch <m.felsch@pengutronix.de>
Reviewed-by: Angus Ainslie (Purism) angus@akkea.ca
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/vcnl4000.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/iio/light/vcnl4000.c b/drivers/iio/light/vcnl4000.c
index 51421ac32517..f522cb863e8c 100644
--- a/drivers/iio/light/vcnl4000.c
+++ b/drivers/iio/light/vcnl4000.c
@@ -398,19 +398,19 @@ static int vcnl4000_probe(struct i2c_client *client,
 static const struct of_device_id vcnl_4000_of_match[] = {
 	{
 		.compatible = "vishay,vcnl4000",
-		.data = "VCNL4000",
+		.data = (void *)VCNL4000,
 	},
 	{
 		.compatible = "vishay,vcnl4010",
-		.data = "VCNL4010",
+		.data = (void *)VCNL4010,
 	},
 	{
-		.compatible = "vishay,vcnl4010",
-		.data = "VCNL4020",
+		.compatible = "vishay,vcnl4020",
+		.data = (void *)VCNL4010,
 	},
 	{
 		.compatible = "vishay,vcnl4200",
-		.data = "VCNL4200",
+		.data = (void *)VCNL4200,
 	},
 	{},
 };
-- 
cgit v1.2.3


From 7fd1c2606508eb384992251e87d50591393a48d0 Mon Sep 17 00:00:00 2001
From: Marco Felsch <m.felsch@pengutronix.de>
Date: Tue, 17 Sep 2019 16:56:37 +0200
Subject: iio: light: add missing vcnl4040 of_compatible

Commit 5a441aade5b3 ("iio: light: vcnl4000 add support for the VCNL4040
proximity and light sensor") added the support for the vcnl4040 but
forgot to add the of_compatible. Fix this by adding it now.

Signed-off-by: Marco Felsch <m.felsch@pengutronix.de>
Fixes: 5a441aade5b3 ("iio: light: vcnl4000 add support for the VCNL4040 proximity and light sensor")
Reviewed-by: Angus Ainslie (Purism) angus@akkea.ca
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/vcnl4000.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/iio/light/vcnl4000.c b/drivers/iio/light/vcnl4000.c
index f522cb863e8c..16dacea9eadf 100644
--- a/drivers/iio/light/vcnl4000.c
+++ b/drivers/iio/light/vcnl4000.c
@@ -408,6 +408,10 @@ static const struct of_device_id vcnl_4000_of_match[] = {
 		.compatible = "vishay,vcnl4020",
 		.data = (void *)VCNL4010,
 	},
+	{
+		.compatible = "vishay,vcnl4040",
+		.data = (void *)VCNL4040,
+	},
 	{
 		.compatible = "vishay,vcnl4200",
 		.data = (void *)VCNL4200,
-- 
cgit v1.2.3


From c62dd44901cfff12acc5792bf3d2dec20bcaf392 Mon Sep 17 00:00:00 2001
From: Marco Felsch <m.felsch@pengutronix.de>
Date: Tue, 17 Sep 2019 18:09:23 +0200
Subject: iio: adc: ad799x: fix probe error handling

Since commit 0f7ddcc1bff1 ("iio:adc:ad799x: Write default config on probe
and reset alert status on probe") the error path is wrong since it
leaves the vref regulator on. Fix this by disabling both regulators.

Fixes: 0f7ddcc1bff1 ("iio:adc:ad799x: Write default config on probe and reset alert status on probe")
Signed-off-by: Marco Felsch <m.felsch@pengutronix.de>
Reviewed-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad799x.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/adc/ad799x.c b/drivers/iio/adc/ad799x.c
index 5a3ca5904ded..f658012baad8 100644
--- a/drivers/iio/adc/ad799x.c
+++ b/drivers/iio/adc/ad799x.c
@@ -810,10 +810,10 @@ static int ad799x_probe(struct i2c_client *client,
 
 	ret = ad799x_write_config(st, st->chip_config->default_config);
 	if (ret < 0)
-		goto error_disable_reg;
+		goto error_disable_vref;
 	ret = ad799x_read_config(st);
 	if (ret < 0)
-		goto error_disable_reg;
+		goto error_disable_vref;
 	st->config = ret;
 
 	ret = iio_triggered_buffer_setup(indio_dev, NULL,
-- 
cgit v1.2.3


From 82f3015635249a8c8c45bac303fd84905066f04f Mon Sep 17 00:00:00 2001
From: David Frey <dpfrey@gmail.com>
Date: Thu, 19 Sep 2019 15:54:18 -0700
Subject: iio: light: opt3001: fix mutex unlock race

When an end-of-conversion interrupt is received after performing a
single-shot reading of the light sensor, the driver was waking up the
result ready queue before checking opt->ok_to_ignore_lock to determine
if it should unlock the mutex. The problem occurred in the case where
the other thread woke up and changed the value of opt->ok_to_ignore_lock
to false prior to the interrupt thread performing its read of the
variable. In this case, the mutex would be unlocked twice.

Signed-off-by: David Frey <dpfrey@gmail.com>
Reviewed-by: Andreas Dannenberg <dannenberg@ti.com>
Fixes: 94a9b7b1809f ("iio: light: add support for TI's opt3001 light sensor")
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/opt3001.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/light/opt3001.c b/drivers/iio/light/opt3001.c
index e666879007d2..92004a2563ea 100644
--- a/drivers/iio/light/opt3001.c
+++ b/drivers/iio/light/opt3001.c
@@ -686,6 +686,7 @@ static irqreturn_t opt3001_irq(int irq, void *_iio)
 	struct iio_dev *iio = _iio;
 	struct opt3001 *opt = iio_priv(iio);
 	int ret;
+	bool wake_result_ready_queue = false;
 
 	if (!opt->ok_to_ignore_lock)
 		mutex_lock(&opt->lock);
@@ -720,13 +721,16 @@ static irqreturn_t opt3001_irq(int irq, void *_iio)
 		}
 		opt->result = ret;
 		opt->result_ready = true;
-		wake_up(&opt->result_ready_queue);
+		wake_result_ready_queue = true;
 	}
 
 out:
 	if (!opt->ok_to_ignore_lock)
 		mutex_unlock(&opt->lock);
 
+	if (wake_result_ready_queue)
+		wake_up(&opt->result_ready_queue);
+
 	return IRQ_HANDLED;
 }
 
-- 
cgit v1.2.3


From a26e0fbe06e20077afdaa40d1a90092f16b0bc67 Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Mon, 23 Sep 2019 10:04:32 +0800
Subject: iio: Fix an undefied reference error in noa1305_probe

I hit the following error when compile the kernel.

drivers/iio/light/noa1305.o: In function `noa1305_probe':
noa1305.c:(.text+0x65): undefined reference to `__devm_regmap_init_i2c'
make: *** [vmlinux] Error 1

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig
index 08d7e1ef2186..4a1a883dc061 100644
--- a/drivers/iio/light/Kconfig
+++ b/drivers/iio/light/Kconfig
@@ -314,6 +314,7 @@ config MAX44009
 config NOA1305
 	tristate "ON Semiconductor NOA1305 ambient light sensor"
 	depends on I2C
+	select REGMAP_I2C
 	help
 	 Say Y here if you want to build support for the ON Semiconductor
 	 NOA1305 ambient light sensor.
-- 
cgit v1.2.3


From c949ae431467764277cdd88d7c26ff963a9db40a Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 9 Oct 2019 11:09:54 +0100
Subject: drm/i915/execlists: Protect peeking at execlists->active

Now that we dropped the engine->active.lock serialisation from around
process_csb(), direct submission can run concurrently to the interrupt
handler. As such execlists->active may be advanced as we dequeue,
dropping the reference to the request. We need to employ our RCU request
protection to ensure that the request is not freed too early.

Fixes: df403069029d ("drm/i915/execlists: Lift process_csb() out of the irq-off spinlock")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191009100955.21477-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 6db762c509b8..7ea58335f04c 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1289,7 +1289,7 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve,
 static struct i915_request *
 last_active(const struct intel_engine_execlists *execlists)
 {
-	struct i915_request * const *last = execlists->active;
+	struct i915_request * const *last = READ_ONCE(execlists->active);
 
 	while (*last && i915_request_completed(*last))
 		last++;
@@ -1981,8 +1981,11 @@ static void process_csb(struct intel_engine_cs *engine)
 static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
 {
 	lockdep_assert_held(&engine->active.lock);
-	if (!engine->execlists.pending[0])
+	if (!engine->execlists.pending[0]) {
+		rcu_read_lock(); /* protect peeking at execlists->active */
 		execlists_dequeue(engine);
+		rcu_read_unlock();
+	}
 }
 
 /*
-- 
cgit v1.2.3


From c36eebd9ba5d70b84e1e7408ccc7632566f285c4 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 9 Oct 2019 17:09:06 +0100
Subject: drm/i915/gt: execlists->active is serialised by the tasklet

The active/pending execlists is no longer protected by the
engine->active.lock, but is serialised by the tasklet instead. Update
the locking around the debug and stats to follow suit.

v2: local_bh_disable() to prevent recursing into the tasklet in case we
trigger a softirq (Tvrtko)

Fixes: df403069029d ("drm/i915/execlists: Lift process_csb() out of the irq-off spinlock")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191009160906.16195-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_engine.h    | 14 ++++++++++++++
 drivers/gpu/drm/i915/gt/intel_engine_cs.c | 16 +++++++---------
 drivers/gpu/drm/i915/i915_gem.h           |  6 ++++++
 3 files changed, 27 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index d624752f2a92..93ea367fe624 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -136,6 +136,20 @@ execlists_active(const struct intel_engine_execlists *execlists)
 	return READ_ONCE(*execlists->active);
 }
 
+static inline void
+execlists_active_lock_bh(struct intel_engine_execlists *execlists)
+{
+	local_bh_disable(); /* prevent local softirq and lock recursion */
+	tasklet_lock(&execlists->tasklet);
+}
+
+static inline void
+execlists_active_unlock_bh(struct intel_engine_execlists *execlists)
+{
+	tasklet_unlock(&execlists->tasklet);
+	local_bh_enable(); /* restore softirq, and kick ksoftirqd! */
+}
+
 struct i915_request *
 execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 5aa1371f6a0f..c9d639c6becb 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1245,9 +1245,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 					 struct drm_printer *m)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
-	const struct intel_engine_execlists * const execlists =
-		&engine->execlists;
-	unsigned long flags;
+	struct intel_engine_execlists * const execlists = &engine->execlists;
 	u64 addr;
 
 	if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7))
@@ -1329,7 +1327,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 				   idx, hws[idx * 2], hws[idx * 2 + 1]);
 		}
 
-		spin_lock_irqsave(&engine->active.lock, flags);
+		execlists_active_lock_bh(execlists);
 		for (port = execlists->active; (rq = *port); port++) {
 			char hdr[80];
 			int len;
@@ -1367,7 +1365,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 			if (tl)
 				intel_timeline_put(tl);
 		}
-		spin_unlock_irqrestore(&engine->active.lock, flags);
+		execlists_active_unlock_bh(execlists);
 	} else if (INTEL_GEN(dev_priv) > 6) {
 		drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n",
 			   ENGINE_READ(engine, RING_PP_DIR_BASE));
@@ -1509,8 +1507,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	if (!intel_engine_supports_stats(engine))
 		return -ENODEV;
 
-	spin_lock_irqsave(&engine->active.lock, flags);
-	write_seqlock(&engine->stats.lock);
+	execlists_active_lock_bh(execlists);
+	write_seqlock_irqsave(&engine->stats.lock, flags);
 
 	if (unlikely(engine->stats.enabled == ~0)) {
 		err = -EBUSY;
@@ -1538,8 +1536,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	}
 
 unlock:
-	write_sequnlock(&engine->stats.lock);
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	write_sequnlock_irqrestore(&engine->stats.lock, flags);
+	execlists_active_unlock_bh(execlists);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 167a7b56ed5b..6795f1daa3d5 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -77,6 +77,12 @@ struct drm_i915_private;
 
 #define I915_GEM_IDLE_TIMEOUT (HZ / 5)
 
+static inline void tasklet_lock(struct tasklet_struct *t)
+{
+	while (!tasklet_trylock(t))
+		cpu_relax();
+}
+
 static inline void __tasklet_disable_sync_once(struct tasklet_struct *t)
 {
 	if (!atomic_fetch_inc(&t->count))
-- 
cgit v1.2.3


From 46f1619500d022501a4f0389f9f4c349ab46bb86 Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Wed, 9 Oct 2019 12:06:00 +0200
Subject: MIPS: include: Mark __xchg as __always_inline
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit ac7c3e4ff401 ("compiler: enable CONFIG_OPTIMIZE_INLINING
forcibly") allows compiler to uninline functions marked as 'inline'.
In cace of __xchg this would cause to reference function
__xchg_called_with_bad_pointer, which is an error case
for catching bugs and will not happen for correct code, if
__xchg is inlined.

Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/include/asm/cmpxchg.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index 012dcf7046ad..f6136871561d 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -77,8 +77,8 @@ extern unsigned long __xchg_called_with_bad_pointer(void)
 extern unsigned long __xchg_small(volatile void *ptr, unsigned long val,
 				  unsigned int size);
 
-static inline unsigned long __xchg(volatile void *ptr, unsigned long x,
-				   int size)
+static __always_inline
+unsigned long __xchg(volatile void *ptr, unsigned long x, int size)
 {
 	switch (size) {
 	case 1:
-- 
cgit v1.2.3


From efcb529694c3b707dc0471b312944337ba16e4dd Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Wed, 9 Oct 2019 17:10:56 +0200
Subject: MIPS: fw: sni: Fix out of bounds init of o32 stack

Use ARRAY_SIZE to caluculate the top of the o32 stack.

Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/fw/sni/sniprom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/fw/sni/sniprom.c b/arch/mips/fw/sni/sniprom.c
index 8772617b64ce..80112f2298b6 100644
--- a/arch/mips/fw/sni/sniprom.c
+++ b/arch/mips/fw/sni/sniprom.c
@@ -43,7 +43,7 @@
 
 /* O32 stack has to be 8-byte aligned. */
 static u64 o32_stk[4096];
-#define O32_STK	  &o32_stk[sizeof(o32_stk)]
+#define O32_STK	  (&o32_stk[ARRAY_SIZE(o32_stk)])
 
 #define __PROM_O32(fun, arg) fun arg __asm__(#fun); \
 				     __asm__(#fun " = call_o32")
-- 
cgit v1.2.3


From a8064d577dab1a81222a50c2de66a2de495f14f4 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Mon, 16 Sep 2019 16:32:51 -0700
Subject: drm/i915/cml: Add second PCH ID for CMP

The CMP PCH ID we have in the driver is correct for the CML-U machines we have
in our CI system, but the CML-S and CML-H CI machines appear to use a
different PCH ID, leading our driver to detect no PCH for them.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
References: 729ae330a0f2e2 ("drm/i915/cml: Introduce Comet Lake PCH")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111461
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190916233251.387-1-matthew.d.roper@intel.com
Fixes: 729ae330a0f2e2 ("drm/i915/cml: Introduce Comet Lake PCH")
(cherry picked from commit 8698ba53cd7173c32320ebbef4d389d41ebb5780)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/intel_pch.c | 1 +
 drivers/gpu/drm/i915/intel_pch.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c
index fa864d8f2b73..15f8bff141f9 100644
--- a/drivers/gpu/drm/i915/intel_pch.c
+++ b/drivers/gpu/drm/i915/intel_pch.c
@@ -69,6 +69,7 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 		WARN_ON(!IS_CANNONLAKE(dev_priv) && !IS_COFFEELAKE(dev_priv));
 		return PCH_CNP;
 	case INTEL_PCH_CMP_DEVICE_ID_TYPE:
+	case INTEL_PCH_CMP2_DEVICE_ID_TYPE:
 		DRM_DEBUG_KMS("Found Comet Lake PCH (CMP)\n");
 		WARN_ON(!IS_COFFEELAKE(dev_priv));
 		/* CometPoint is CNP Compatible */
diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h
index e6a2d65f19c6..c29c81ec7971 100644
--- a/drivers/gpu/drm/i915/intel_pch.h
+++ b/drivers/gpu/drm/i915/intel_pch.h
@@ -41,6 +41,7 @@ enum intel_pch {
 #define INTEL_PCH_CNP_DEVICE_ID_TYPE		0xA300
 #define INTEL_PCH_CNP_LP_DEVICE_ID_TYPE		0x9D80
 #define INTEL_PCH_CMP_DEVICE_ID_TYPE		0x0280
+#define INTEL_PCH_CMP2_DEVICE_ID_TYPE		0x0680
 #define INTEL_PCH_ICP_DEVICE_ID_TYPE		0x3480
 #define INTEL_PCH_MCC_DEVICE_ID_TYPE		0x4B00
 #define INTEL_PCH_MCC2_DEVICE_ID_TYPE		0x3880
-- 
cgit v1.2.3


From 6535a4b34ed9e566eca4008a26dae94699f3afce Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 12:00:54 +0100
Subject: drm/i915/execlists: Drop redundant list_del_init(&rq->sched.link)

Since amalgamating the queued and active lists in commit 422d7df4f090
("drm/i915: Replace engine->timeline with a plain list"), performing a
i915_request_submit() will remove the request from the execlists
priority queue.

References: 422d7df4f090 ("drm/i915: Replace engine->timeline with a plain list")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923110056.15176-2-chris@chris-wilson.co.uk
(cherry picked from commit 3231f8c01121ee1febfd82398ee22f7ff9dc5d76)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 97d4f5c90287..21f06d5db9dd 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2564,7 +2564,6 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
-			list_del_init(&rq->sched.link);
 			__i915_request_submit(rq);
 			dma_fence_set_error(&rq->fence, -EIO);
 			i915_request_mark_complete(rq);
-- 
cgit v1.2.3


From a8385f0c3fd3f31ab53726e26229b428d18a51bf Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 12:00:55 +0100
Subject: drm/i915: Only enqueue already completed requests

If we are asked to submit a completed request, just move it onto the
active-list without modifying it's payload. If we try to emit the
modified payload of a completed request, we risk racing with the
ring->head update during retirement which may advance the head past our
breadcrumb and so we generate a warning for the emission being behind
the RING_HEAD.

v2: Commentary for the sneaky, shared responsibility between functions.
v3: Spelling mistakes and bonus assertion

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923110056.15176-3-chris@chris-wilson.co.uk
(cherry picked from commit c0bb487dc19fc45dbeede7dcf8f513df51a3cd33)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 66 +++++++++++++++++++++++--------------
 drivers/gpu/drm/i915/i915_request.c | 44 ++++++++++++++++++-------
 drivers/gpu/drm/i915/i915_request.h |  2 +-
 3 files changed, 74 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 21f06d5db9dd..b9520319684a 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -796,6 +796,17 @@ static bool can_merge_rq(const struct i915_request *prev,
 	GEM_BUG_ON(prev == next);
 	GEM_BUG_ON(!assert_priority_queue(prev, next));
 
+	/*
+	 * We do not submit known completed requests. Therefore if the next
+	 * request is already completed, we can pretend to merge it in
+	 * with the previous context (and we will skip updating the ELSP
+	 * and tracking). Thus hopefully keeping the ELSP full with active
+	 * contexts, despite the best efforts of preempt-to-busy to confuse
+	 * us.
+	 */
+	if (i915_request_completed(next))
+		return true;
+
 	if (!can_merge_ctx(prev->hw_context, next->hw_context))
 		return false;
 
@@ -1171,21 +1182,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				continue;
 			}
 
-			if (i915_request_completed(rq)) {
-				ve->request = NULL;
-				ve->base.execlists.queue_priority_hint = INT_MIN;
-				rb_erase_cached(rb, &execlists->virtual);
-				RB_CLEAR_NODE(rb);
-
-				rq->engine = engine;
-				__i915_request_submit(rq);
-
-				spin_unlock(&ve->base.active.lock);
-
-				rb = rb_first_cached(&execlists->virtual);
-				continue;
-			}
-
 			if (last && !can_merge_rq(last, rq)) {
 				spin_unlock(&ve->base.active.lock);
 				return; /* leave this for another */
@@ -1236,11 +1232,23 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				GEM_BUG_ON(ve->siblings[0] != engine);
 			}
 
-			__i915_request_submit(rq);
-			if (!i915_request_completed(rq)) {
+			if (__i915_request_submit(rq)) {
 				submit = true;
 				last = rq;
 			}
+
+			/*
+			 * Hmm, we have a bunch of virtual engine requests,
+			 * but the first one was already completed (thanks
+			 * preempt-to-busy!). Keep looking at the veng queue
+			 * until we have no more relevant requests (i.e.
+			 * the normal submit queue has higher priority).
+			 */
+			if (!submit) {
+				spin_unlock(&ve->base.active.lock);
+				rb = rb_first_cached(&execlists->virtual);
+				continue;
+			}
 		}
 
 		spin_unlock(&ve->base.active.lock);
@@ -1253,8 +1261,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
-			if (i915_request_completed(rq))
-				goto skip;
+			bool merge = true;
 
 			/*
 			 * Can we combine this request with the current port?
@@ -1295,14 +1302,23 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				    ctx_single_port_submission(rq->hw_context))
 					goto done;
 
-				*port = execlists_schedule_in(last, port - execlists->pending);
-				port++;
+				merge = false;
 			}
 
-			last = rq;
-			submit = true;
-skip:
-			__i915_request_submit(rq);
+			if (__i915_request_submit(rq)) {
+				if (!merge) {
+					*port = execlists_schedule_in(last, port - execlists->pending);
+					port++;
+					last = NULL;
+				}
+
+				GEM_BUG_ON(last &&
+					   !can_merge_ctx(last->hw_context,
+							  rq->hw_context));
+
+				submit = true;
+				last = rq;
+			}
 		}
 
 		rb_erase_cached(&p->node, &execlists->queue);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 8f88851a9306..1c5506822dc7 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -377,9 +377,10 @@ __i915_request_await_execution(struct i915_request *rq,
 	return 0;
 }
 
-void __i915_request_submit(struct i915_request *request)
+bool __i915_request_submit(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
+	bool result = false;
 
 	GEM_TRACE("%s fence %llx:%lld, current %d\n",
 		  engine->name,
@@ -389,6 +390,25 @@ void __i915_request_submit(struct i915_request *request)
 	GEM_BUG_ON(!irqs_disabled());
 	lockdep_assert_held(&engine->active.lock);
 
+	/*
+	 * With the advent of preempt-to-busy, we frequently encounter
+	 * requests that we have unsubmitted from HW, but left running
+	 * until the next ack and so have completed in the meantime. On
+	 * resubmission of that completed request, we can skip
+	 * updating the payload, and execlists can even skip submitting
+	 * the request.
+	 *
+	 * We must remove the request from the caller's priority queue,
+	 * and the caller must only call us when the request is in their
+	 * priority queue, under the active.lock. This ensures that the
+	 * request has *not* yet been retired and we can safely move
+	 * the request into the engine->active.list where it will be
+	 * dropped upon retiring. (Otherwise if resubmit a *retired*
+	 * request, this would be a horrible use-after-free.)
+	 */
+	if (i915_request_completed(request))
+		goto xfer;
+
 	if (i915_gem_context_is_banned(request->gem_context))
 		i915_request_skip(request, -EIO);
 
@@ -412,13 +432,18 @@ void __i915_request_submit(struct i915_request *request)
 	    i915_sw_fence_signaled(&request->semaphore))
 		engine->saturated |= request->sched.semaphores;
 
-	/* We may be recursing from the signal callback of another i915 fence */
-	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
+	engine->emit_fini_breadcrumb(request,
+				     request->ring->vaddr + request->postfix);
+
+	trace_i915_request_execute(request);
+	engine->serial++;
+	result = true;
 
-	list_move_tail(&request->sched.link, &engine->active.requests);
+xfer:	/* We may be recursing from the signal callback of another i915 fence */
+	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
 
-	GEM_BUG_ON(test_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags));
-	set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags);
+	if (!test_and_set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags))
+		list_move_tail(&request->sched.link, &engine->active.requests);
 
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
 	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) &&
@@ -429,12 +454,7 @@ void __i915_request_submit(struct i915_request *request)
 
 	spin_unlock(&request->lock);
 
-	engine->emit_fini_breadcrumb(request,
-				     request->ring->vaddr + request->postfix);
-
-	engine->serial++;
-
-	trace_i915_request_execute(request);
+	return result;
 }
 
 void i915_request_submit(struct i915_request *request)
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 8ac6e1226a56..e4dd013761e8 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -292,7 +292,7 @@ int i915_request_await_execution(struct i915_request *rq,
 
 void i915_request_add(struct i915_request *rq);
 
-void __i915_request_submit(struct i915_request *request);
+bool __i915_request_submit(struct i915_request *request);
 void i915_request_submit(struct i915_request *request);
 
 void i915_request_skip(struct i915_request *request, int error);
-- 
cgit v1.2.3


From 8a99734081775c012a4a6c442fdef0379fe52bdf Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 9 Oct 2019 14:40:13 -0600
Subject: io_uring: only flush workqueues on fileset removal

We should not remove the workqueue, we just need to ensure that the
workqueues are synced. The workqueues are torn down on ctx removal.

Cc: stable@vger.kernel.org
Fixes: 6b06314c47e1 ("io_uring: add file set registration")
Reported-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index ceb3497bdd2a..2c44648217bd 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -2866,8 +2866,12 @@ static void io_finish_async(struct io_ring_ctx *ctx)
 static void io_destruct_skb(struct sk_buff *skb)
 {
 	struct io_ring_ctx *ctx = skb->sk->sk_user_data;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ctx->sqo_wq); i++)
+		if (ctx->sqo_wq[i])
+			flush_workqueue(ctx->sqo_wq[i]);
 
-	io_finish_async(ctx);
 	unix_destruct_scm(skb);
 }
 
-- 
cgit v1.2.3


From 68184eb7b09640ac84aeefe31923d70d1fa07292 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 16:28:43 +0100
Subject: drm/i915: Fixup preempt-to-busy vs reset of a virtual request

Due to the nature of preempt-to-busy the execlists active tracking and
the schedule queue may become temporarily desync'ed (between resubmission
to HW and its ack from HW). This means that we may have unwound a
request and passed it back to the virtual engine, but it is still
inflight on the HW and may even result in a GPU hang. If we detect that
GPU hang and try to reset, the hanging request->engine will no longer
match the current engine, which means that the request is not on the
execlists active list and we should not try to find an older incomplete
request. Given that we have deduced this must be a request on a virtual
engine, it is the single active request in the context and so must be
guilty (as the context is still inflight, it is prevented from being
executed on another engine as we process the reset).

Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923152844.8914-2-chris@chris-wilson.co.uk
(cherry picked from commit cb2377a919bbe8107af269c5a31a8d5cfb27d867)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c   | 6 +++++-
 drivers/gpu/drm/i915/gt/intel_reset.c | 4 +---
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index b9520319684a..b09bd1729d39 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2414,10 +2414,14 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
 
 static struct i915_request *active_request(struct i915_request *rq)
 {
-	const struct list_head * const list = &rq->timeline->requests;
 	const struct intel_context * const ce = rq->hw_context;
 	struct i915_request *active = NULL;
+	struct list_head *list;
 
+	if (!i915_request_is_active(rq)) /* unwound, but incomplete! */
+		return rq;
+
+	list = &rq->timeline->requests;
 	list_for_each_entry_from_reverse(rq, list, link) {
 		if (i915_request_completed(rq))
 			break;
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index eeb3bd0c4d69..8cea42379dd7 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -42,11 +42,10 @@ static void engine_skip_context(struct i915_request *rq)
 	struct intel_engine_cs *engine = rq->engine;
 	struct i915_gem_context *hung_ctx = rq->gem_context;
 
-	lockdep_assert_held(&engine->active.lock);
-
 	if (!i915_request_is_active(rq))
 		return;
 
+	lockdep_assert_held(&engine->active.lock);
 	list_for_each_entry_continue(rq, &engine->active.requests, sched.link)
 		if (rq->gem_context == hung_ctx)
 			i915_request_skip(rq, -EIO);
@@ -123,7 +122,6 @@ void __i915_request_reset(struct i915_request *rq, bool guilty)
 		  rq->fence.seqno,
 		  yesno(guilty));
 
-	lockdep_assert_held(&rq->engine->active.lock);
 	GEM_BUG_ON(i915_request_completed(rq));
 
 	if (guilty) {
-- 
cgit v1.2.3


From 749085a2131f7e328dd33635eb3d37b519f451f9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 9 Oct 2019 11:09:54 +0100
Subject: drm/i915/execlists: Protect peeking at execlists->active

Now that we dropped the engine->active.lock serialisation from around
process_csb(), direct submission can run concurrently to the interrupt
handler. As such execlists->active may be advanced as we dequeue,
dropping the reference to the request. We need to employ our RCU request
protection to ensure that the request is not freed too early.

Fixes: df403069029d ("drm/i915/execlists: Lift process_csb() out of the irq-off spinlock")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191009100955.21477-1-chris@chris-wilson.co.uk
(cherry picked from commit c949ae431467764277cdd88d7c26ff963a9db40a)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index b09bd1729d39..bdfcc7bdadbf 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -903,7 +903,7 @@ static void virtual_xfer_breadcrumbs(struct virtual_engine *ve,
 static struct i915_request *
 last_active(const struct intel_engine_execlists *execlists)
 {
-	struct i915_request * const *last = execlists->active;
+	struct i915_request * const *last = READ_ONCE(execlists->active);
 
 	while (*last && i915_request_completed(*last))
 		last++;
@@ -1608,8 +1608,11 @@ static void process_csb(struct intel_engine_cs *engine)
 static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
 {
 	lockdep_assert_held(&engine->active.lock);
-	if (!engine->execlists.pending[0])
+	if (!engine->execlists.pending[0]) {
+		rcu_read_lock(); /* protect peeking at execlists->active */
 		execlists_dequeue(engine);
+		rcu_read_unlock();
+	}
 }
 
 /*
-- 
cgit v1.2.3


From e137d3abdfca0fb6fc270da576a9d9d6a1f8d8b3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 9 Oct 2019 17:09:06 +0100
Subject: drm/i915/gt: execlists->active is serialised by the tasklet

The active/pending execlists is no longer protected by the
engine->active.lock, but is serialised by the tasklet instead. Update
the locking around the debug and stats to follow suit.

v2: local_bh_disable() to prevent recursing into the tasklet in case we
trigger a softirq (Tvrtko)

Fixes: df403069029d ("drm/i915/execlists: Lift process_csb() out of the irq-off spinlock")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191009160906.16195-1-chris@chris-wilson.co.uk
(cherry picked from commit c36eebd9ba5d70b84e1e7408ccc7632566f285c4)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_engine.h    | 14 ++++++++++++++
 drivers/gpu/drm/i915/gt/intel_engine_cs.c | 16 +++++++---------
 drivers/gpu/drm/i915/i915_gem.h           |  6 ++++++
 3 files changed, 27 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index d3c6993f4f46..22aab8593abf 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -136,6 +136,20 @@ execlists_active(const struct intel_engine_execlists *execlists)
 	return READ_ONCE(*execlists->active);
 }
 
+static inline void
+execlists_active_lock_bh(struct intel_engine_execlists *execlists)
+{
+	local_bh_disable(); /* prevent local softirq and lock recursion */
+	tasklet_lock(&execlists->tasklet);
+}
+
+static inline void
+execlists_active_unlock_bh(struct intel_engine_execlists *execlists)
+{
+	tasklet_unlock(&execlists->tasklet);
+	local_bh_enable(); /* restore softirq, and kick ksoftirqd! */
+}
+
 struct i915_request *
 execlists_unwind_incomplete_requests(struct intel_engine_execlists *execlists);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 82630db0394b..4ce8626b140e 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1197,9 +1197,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 					 struct drm_printer *m)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
-	const struct intel_engine_execlists * const execlists =
-		&engine->execlists;
-	unsigned long flags;
+	struct intel_engine_execlists * const execlists = &engine->execlists;
 	u64 addr;
 
 	if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7))
@@ -1281,7 +1279,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 				   idx, hws[idx * 2], hws[idx * 2 + 1]);
 		}
 
-		spin_lock_irqsave(&engine->active.lock, flags);
+		execlists_active_lock_bh(execlists);
 		for (port = execlists->active; (rq = *port); port++) {
 			char hdr[80];
 			int len;
@@ -1309,7 +1307,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 				 hwsp_seqno(rq));
 			print_request(m, rq, hdr);
 		}
-		spin_unlock_irqrestore(&engine->active.lock, flags);
+		execlists_active_unlock_bh(execlists);
 	} else if (INTEL_GEN(dev_priv) > 6) {
 		drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n",
 			   ENGINE_READ(engine, RING_PP_DIR_BASE));
@@ -1440,8 +1438,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	if (!intel_engine_supports_stats(engine))
 		return -ENODEV;
 
-	spin_lock_irqsave(&engine->active.lock, flags);
-	write_seqlock(&engine->stats.lock);
+	execlists_active_lock_bh(execlists);
+	write_seqlock_irqsave(&engine->stats.lock, flags);
 
 	if (unlikely(engine->stats.enabled == ~0)) {
 		err = -EBUSY;
@@ -1469,8 +1467,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	}
 
 unlock:
-	write_sequnlock(&engine->stats.lock);
-	spin_unlock_irqrestore(&engine->active.lock, flags);
+	write_sequnlock_irqrestore(&engine->stats.lock, flags);
+	execlists_active_unlock_bh(execlists);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 167a7b56ed5b..6795f1daa3d5 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -77,6 +77,12 @@ struct drm_i915_private;
 
 #define I915_GEM_IDLE_TIMEOUT (HZ / 5)
 
+static inline void tasklet_lock(struct tasklet_struct *t)
+{
+	while (!tasklet_trylock(t))
+		cpu_relax();
+}
+
 static inline void __tasklet_disable_sync_once(struct tasklet_struct *t)
 {
 	if (!atomic_fetch_inc(&t->count))
-- 
cgit v1.2.3


From 5da202c88f8c355ad79bc2e8eb582e6d433060e7 Mon Sep 17 00:00:00 2001
From: Antonio Borneo <antonio.borneo@st.com>
Date: Mon, 7 Oct 2019 17:43:04 +0200
Subject: net: stmmac: fix length of PTP clock's name string

The field "name" in struct ptp_clock_info has a fixed size of 16
chars and is used as zero terminated string by clock_name_show()
in drivers/ptp/ptp_sysfs.c
The current initialization value requires 17 chars to fit also the
null termination, and this causes overflow to the next bytes in
the struct when the string is read as null terminated:
	hexdump -C /sys/class/ptp/ptp0/clock_name
	00000000  73 74 6d 6d 61 63 5f 70  74 70 5f 63 6c 6f 63 6b  |stmmac_ptp_clock|
	00000010  a0 ac b9 03 0a                                    |.....|
where the extra 4 bytes (excluding the newline) after the string
represent the integer 0x03b9aca0 = 62500000 assigned to the field
"max_adj" that follows "name" in the same struct.

There is no strict requirement for the "name" content and in the
comment in ptp_clock_kernel.h it's reported it should just be 'A
short "friendly name" to identify the clock'.
Replace it with "stmmac ptp".

Signed-off-by: Antonio Borneo <antonio.borneo@st.com>
Fixes: 92ba6888510c ("stmmac: add the support for PTP hw clock driver")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 173493db038c..df638b18b72c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -164,7 +164,7 @@ static int stmmac_enable(struct ptp_clock_info *ptp,
 /* structure describing a PTP hardware clock */
 static struct ptp_clock_info stmmac_ptp_clock_ops = {
 	.owner = THIS_MODULE,
-	.name = "stmmac_ptp_clock",
+	.name = "stmmac ptp",
 	.max_adj = 62500000,
 	.n_alarm = 0,
 	.n_ext_ts = 0,
-- 
cgit v1.2.3


From 520cf6002147281d1e7b522bb338416b623dcb93 Mon Sep 17 00:00:00 2001
From: Antonio Borneo <antonio.borneo@st.com>
Date: Mon, 7 Oct 2019 17:43:05 +0200
Subject: net: stmmac: fix disabling flexible PPS output

Accordingly to Synopsys documentation [1] and [2], when bit PPSEN0
in register MAC_PPS_CONTROL is set it selects the functionality
command in the same register, otherwise selects the functionality
control.
Command functionality is required to either enable (command 0x2)
and disable (command 0x5) the flexible PPS output, but the bit
PPSEN0 is currently set only for enabling.

Set the bit PPSEN0 to properly disable flexible PPS output.

Tested on STM32MP15x, based on dwmac 4.10a.

[1] DWC Ethernet QoS Databook 4.10a October 2014
[2] DWC Ethernet QoS Databook 5.00a September 2017

Signed-off-by: Antonio Borneo <antonio.borneo@st.com>
Fixes: 9a8a02c9d46d ("net: stmmac: Add Flexible PPS support")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac5.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
index 3f4f3132e16b..e436fa160c7d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c
@@ -515,6 +515,7 @@ int dwmac5_flex_pps_config(void __iomem *ioaddr, int index,
 
 	if (!enable) {
 		val |= PPSCMDx(index, 0x5);
+		val |= PPSEN0;
 		writel(val, ioaddr + MAC_PPS_CONTROL);
 		return 0;
 	}
-- 
cgit v1.2.3


From a7137534b597b7c303203e6bc3ed87e87a273bb8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 7 Oct 2019 15:43:01 -0700
Subject: bonding: fix potential NULL deref in bond_update_slave_arr

syzbot got a NULL dereference in bond_update_slave_arr() [1],
happening after a failure to allocate bond->slave_arr

A workqueue (bond_slave_arr_handler) is supposed to retry
the allocation later, but if the slave is removed before
the workqueue had a chance to complete, bond->slave_arr
can still be NULL.

[1]

Failed to build slave-array.
kasan: CONFIG_KASAN_INLINE enabled
kasan: GPF could be caused by NULL-ptr deref or user memory access
general protection fault: 0000 [#1] SMP KASAN PTI
Modules linked in:
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:bond_update_slave_arr.cold+0xc6/0x198 drivers/net/bonding/bond_main.c:4039
RSP: 0018:ffff88018fe33678 EFLAGS: 00010246
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffc9000290b000
RDX: 0000000000000000 RSI: ffffffff82b63037 RDI: ffff88019745ea20
RBP: ffff88018fe33760 R08: ffff880170754280 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: ffff88019745ea00 R14: 0000000000000000 R15: ffff88018fe338b0
FS:  00007febd837d700(0000) GS:ffff8801dad00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000004540a0 CR3: 00000001c242e005 CR4: 00000000001626f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 [<ffffffff82b5b45e>] __bond_release_one+0x43e/0x500 drivers/net/bonding/bond_main.c:1923
 [<ffffffff82b5b966>] bond_release drivers/net/bonding/bond_main.c:2039 [inline]
 [<ffffffff82b5b966>] bond_do_ioctl+0x416/0x870 drivers/net/bonding/bond_main.c:3562
 [<ffffffff83ae25f4>] dev_ifsioc+0x6f4/0x940 net/core/dev_ioctl.c:328
 [<ffffffff83ae2e58>] dev_ioctl+0x1b8/0xc70 net/core/dev_ioctl.c:495
 [<ffffffff83995ffd>] sock_do_ioctl+0x1bd/0x300 net/socket.c:1088
 [<ffffffff83996a80>] sock_ioctl+0x300/0x5d0 net/socket.c:1196
 [<ffffffff81b124db>] vfs_ioctl fs/ioctl.c:47 [inline]
 [<ffffffff81b124db>] file_ioctl fs/ioctl.c:501 [inline]
 [<ffffffff81b124db>] do_vfs_ioctl+0xacb/0x1300 fs/ioctl.c:688
 [<ffffffff81b12dc6>] SYSC_ioctl fs/ioctl.c:705 [inline]
 [<ffffffff81b12dc6>] SyS_ioctl+0xb6/0xe0 fs/ioctl.c:696
 [<ffffffff8101ccc8>] do_syscall_64+0x528/0x770 arch/x86/entry/common.c:305
 [<ffffffff84400091>] entry_SYSCALL_64_after_hwframe+0x42/0xb7

Fixes: ee6377147409 ("bonding: Simplify the xmit function for modes that use xmit_hash")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/bonding/bond_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 931d9d935686..21d8fcc83c9c 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4039,7 +4039,7 @@ out:
 		 * this to-be-skipped slave to send a packet out.
 		 */
 		old_arr = rtnl_dereference(bond->slave_arr);
-		for (idx = 0; idx < old_arr->count; idx++) {
+		for (idx = 0; old_arr != NULL && idx < old_arr->count; idx++) {
 			if (skipslave == old_arr->arr[idx]) {
 				old_arr->arr[idx] =
 				    old_arr->arr[old_arr->count-1];
-- 
cgit v1.2.3


From 819be8108fded0b9e710bbbf81193e52f7bab2f7 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 8 Oct 2019 19:09:23 +0800
Subject: sctp: add chunks to sk_backlog when the newsk sk_socket is not set

This patch is to fix a NULL-ptr deref in selinux_socket_connect_helper:

  [...] kasan: GPF could be caused by NULL-ptr deref or user memory access
  [...] RIP: 0010:selinux_socket_connect_helper+0x94/0x460
  [...] Call Trace:
  [...]  selinux_sctp_bind_connect+0x16a/0x1d0
  [...]  security_sctp_bind_connect+0x58/0x90
  [...]  sctp_process_asconf+0xa52/0xfd0 [sctp]
  [...]  sctp_sf_do_asconf+0x785/0x980 [sctp]
  [...]  sctp_do_sm+0x175/0x5a0 [sctp]
  [...]  sctp_assoc_bh_rcv+0x285/0x5b0 [sctp]
  [...]  sctp_backlog_rcv+0x482/0x910 [sctp]
  [...]  __release_sock+0x11e/0x310
  [...]  release_sock+0x4f/0x180
  [...]  sctp_accept+0x3f9/0x5a0 [sctp]
  [...]  inet_accept+0xe7/0x720

It was caused by that the 'newsk' sk_socket was not set before going to
security sctp hook when processing asconf chunk with SCTP_PARAM_ADD_IP
or SCTP_PARAM_SET_PRIMARY:

  inet_accept()->
    sctp_accept():
      lock_sock():
          lock listening 'sk'
                                          do_softirq():
                                            sctp_rcv():  <-- [1]
                                                asconf chunk arrives and
                                                enqueued in 'sk' backlog
      sctp_sock_migrate():
          set asoc's sk to 'newsk'
      release_sock():
          sctp_backlog_rcv():
            lock 'newsk'
            sctp_process_asconf()  <-- [2]
            unlock 'newsk'
    sock_graft():
        set sk_socket  <-- [3]

As it shows, at [1] the asconf chunk would be put into the listening 'sk'
backlog, as accept() was holding its sock lock. Then at [2] asconf would
get processed with 'newsk' as asoc's sk had been set to 'newsk'. However,
'newsk' sk_socket is not set until [3], while selinux_sctp_bind_connect()
would deref it, then kernel crashed.

Here to fix it by adding the chunk to sk_backlog until newsk sk_socket is
set when .accept() is done.

Note that sk->sk_socket can be NULL when the sock is closed, so SOCK_DEAD
flag is also needed to check in sctp_newsk_ready().

Thanks to Ondrej for reviewing the code.

Fixes: d452930fd3b9 ("selinux: Add SCTP support")
Reported-by: Ying Xu <yinxu@redhat.com>
Suggested-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 include/net/sctp/sctp.h |  5 +++++
 net/sctp/input.c        | 12 +++++++++---
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 5d60f13d2347..3ab5c6bbb90b 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -610,4 +610,9 @@ static inline __u32 sctp_min_frag_point(struct sctp_sock *sp, __u16 datasize)
 	return sctp_mtu_payload(sp, SCTP_DEFAULT_MINSEGMENT, datasize);
 }
 
+static inline bool sctp_newsk_ready(const struct sock *sk)
+{
+	return sock_flag(sk, SOCK_DEAD) || sk->sk_socket;
+}
+
 #endif /* __net_sctp_h__ */
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 5a070fb5b278..f2771375bfc0 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -243,7 +243,7 @@ int sctp_rcv(struct sk_buff *skb)
 		bh_lock_sock(sk);
 	}
 
-	if (sock_owned_by_user(sk)) {
+	if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) {
 		if (sctp_add_backlog(sk, skb)) {
 			bh_unlock_sock(sk);
 			sctp_chunk_free(chunk);
@@ -321,7 +321,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 		local_bh_disable();
 		bh_lock_sock(sk);
 
-		if (sock_owned_by_user(sk)) {
+		if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) {
 			if (sk_add_backlog(sk, skb, sk->sk_rcvbuf))
 				sctp_chunk_free(chunk);
 			else
@@ -336,7 +336,13 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 		if (backloged)
 			return 0;
 	} else {
-		sctp_inq_push(inqueue, chunk);
+		if (!sctp_newsk_ready(sk)) {
+			if (!sk_add_backlog(sk, skb, sk->sk_rcvbuf))
+				return 0;
+			sctp_chunk_free(chunk);
+		} else {
+			sctp_inq_push(inqueue, chunk);
+		}
 	}
 
 done:
-- 
cgit v1.2.3


From cd9e72b80090a8cd7d84a47a30a06fa92ff277d1 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Mon, 23 Sep 2019 15:36:17 +0100
Subject: RISC-V: entry: Remove unneeded need_resched() loop

Since the enabling and disabling of IRQs within preempt_schedule_irq()
is contained in a need_resched() loop, we don't need the outer arch
code loop.

Reviewed-by: Palmer Dabbelt <palmer@sifive.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: linux-riscv@lists.infradead.org
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
---
 arch/riscv/kernel/entry.S | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 2d592da1e776..8ca479831142 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -273,12 +273,11 @@ restore_all:
 resume_kernel:
 	REG_L s0, TASK_TI_PREEMPT_COUNT(tp)
 	bnez s0, restore_all
-need_resched:
 	REG_L s0, TASK_TI_FLAGS(tp)
 	andi s0, s0, _TIF_NEED_RESCHED
 	beqz s0, restore_all
 	call preempt_schedule_irq
-	j need_resched
+	j restore_all
 #endif
 
 work_pending:
-- 
cgit v1.2.3


From 9db74e51ec08d75c3e97f851299bc25e645cc5ad Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 8 Oct 2019 08:39:04 -0700
Subject: phylink: fix kernel-doc warnings

Fix kernel-doc warnings in phylink.c:

../drivers/net/phy/phylink.c:595: warning: Function parameter or member 'config' not described in 'phylink_create'
../drivers/net/phy/phylink.c:595: warning: Excess function parameter 'ndev' description in 'phylink_create'

Fixes: 8796c8923d9c ("phylink: add documentation for kernel APIs")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/phy/phylink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index a5a57ca94c1a..20e2ebe458f2 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -576,7 +576,7 @@ static int phylink_register_sfp(struct phylink *pl,
 
 /**
  * phylink_create() - create a phylink instance
- * @ndev: a pointer to the &struct net_device
+ * @config: a pointer to the target &struct phylink_config
  * @fwnode: a pointer to a &struct fwnode_handle describing the network
  *	interface
  * @iface: the desired link mode defined by &typedef phy_interface_t
-- 
cgit v1.2.3


From b528965bcc827dad32a8d21745feaacfc76c9703 Mon Sep 17 00:00:00 2001
From: Alexandra Winter <wintera@linux.ibm.com>
Date: Tue, 8 Oct 2019 18:21:06 +0200
Subject: s390/qeth: Fix error handling during VNICC initialization

Smatch discovered the use of uninitialized variable sup_cmds
in error paths.

Fixes: caa1f0b10d18 ("s390/qeth: add VNICC enable/disable support")
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/s390/net/qeth_l2_main.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index b8799cd3e7aa..de62a9ccc882 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -2021,10 +2021,10 @@ static bool qeth_l2_vnicc_recover_char(struct qeth_card *card, u32 vnicc,
 static void qeth_l2_vnicc_init(struct qeth_card *card)
 {
 	u32 *timeout = &card->options.vnicc.learning_timeout;
+	bool enable, error = false;
 	unsigned int chars_len, i;
 	unsigned long chars_tmp;
 	u32 sup_cmds, vnicc;
-	bool enable, error;
 
 	QETH_CARD_TEXT(card, 2, "vniccini");
 	/* reset rx_bcast */
@@ -2045,7 +2045,10 @@ static void qeth_l2_vnicc_init(struct qeth_card *card)
 	chars_len = sizeof(card->options.vnicc.sup_chars) * BITS_PER_BYTE;
 	for_each_set_bit(i, &chars_tmp, chars_len) {
 		vnicc = BIT(i);
-		qeth_l2_vnicc_query_cmds(card, vnicc, &sup_cmds);
+		if (qeth_l2_vnicc_query_cmds(card, vnicc, &sup_cmds)) {
+			sup_cmds = 0;
+			error = true;
+		}
 		if (!(sup_cmds & IPA_VNICC_SET_TIMEOUT) ||
 		    !(sup_cmds & IPA_VNICC_GET_TIMEOUT))
 			card->options.vnicc.getset_timeout_sup &= ~vnicc;
@@ -2054,8 +2057,8 @@ static void qeth_l2_vnicc_init(struct qeth_card *card)
 			card->options.vnicc.set_char_sup &= ~vnicc;
 	}
 	/* enforce assumed default values and recover settings, if changed  */
-	error = qeth_l2_vnicc_recover_timeout(card, QETH_VNICC_LEARNING,
-					      timeout);
+	error |= qeth_l2_vnicc_recover_timeout(card, QETH_VNICC_LEARNING,
+					       timeout);
 	chars_tmp = card->options.vnicc.wanted_chars ^ QETH_VNICC_DEFAULT;
 	chars_tmp |= QETH_VNICC_BRIDGE_INVISIBLE;
 	chars_len = sizeof(card->options.vnicc.wanted_chars) * BITS_PER_BYTE;
-- 
cgit v1.2.3


From be40a86c319706f90caca144343c64743c32b953 Mon Sep 17 00:00:00 2001
From: Alexandra Winter <wintera@linux.ibm.com>
Date: Tue, 8 Oct 2019 18:21:07 +0200
Subject: s390/qeth: Fix initialization of vnicc cmd masks during set online

Without this patch, a command bit in the supported commands mask is only
ever set to unsupported during set online. If a command is ever marked as
unsupported (e.g. because of error during qeth_l2_vnicc_query_cmds),
subsequent successful initialization (offline/online) would not bring it
back.

Fixes: caa1f0b10d18 ("s390/qeth: add VNICC enable/disable support")
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/s390/net/qeth_l2_main.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index de62a9ccc882..bd8143e51747 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -2049,11 +2049,15 @@ static void qeth_l2_vnicc_init(struct qeth_card *card)
 			sup_cmds = 0;
 			error = true;
 		}
-		if (!(sup_cmds & IPA_VNICC_SET_TIMEOUT) ||
-		    !(sup_cmds & IPA_VNICC_GET_TIMEOUT))
+		if ((sup_cmds & IPA_VNICC_SET_TIMEOUT) &&
+		    (sup_cmds & IPA_VNICC_GET_TIMEOUT))
+			card->options.vnicc.getset_timeout_sup |= vnicc;
+		else
 			card->options.vnicc.getset_timeout_sup &= ~vnicc;
-		if (!(sup_cmds & IPA_VNICC_ENABLE) ||
-		    !(sup_cmds & IPA_VNICC_DISABLE))
+		if ((sup_cmds & IPA_VNICC_ENABLE) &&
+		    (sup_cmds & IPA_VNICC_DISABLE))
+			card->options.vnicc.set_char_sup |= vnicc;
+		else
 			card->options.vnicc.set_char_sup &= ~vnicc;
 	}
 	/* enforce assumed default values and recover settings, if changed  */
-- 
cgit v1.2.3


From a954380acde6adf584de76c41e1d520097820dd5 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Tue, 8 Oct 2019 16:20:07 -0700
Subject: net: taprio: Fix returning EINVAL when configuring without flags

When configuring a taprio instance if "flags" is not specified (or
it's zero), taprio currently replies with an "Invalid argument" error.

So, set the return value to zero after we are done with all the
checks.

Fixes: 9c66d1564676 ("taprio: Add support for hardware offloading")
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Acked-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sched/sch_taprio.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 68b543f85a96..6719a65169d4 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1341,6 +1341,10 @@ static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb,
 		NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory");
 		goto out;
 	}
+
+	/* Everything went ok, return success. */
+	err = 0;
+
 out:
 	return err;
 }
-- 
cgit v1.2.3


From 11c9a7d38af524217efb7a176ad322b97ac2f163 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 9 Oct 2019 11:10:52 +0800
Subject: act_mirred: Fix mirred_init_module error handling

If tcf_register_action failed, mirred_device_notifier
should be unregistered.

Fixes: 3b87956ea645 ("net sched: fix race in mirred device removal")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/sched/act_mirred.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 9ce073a05414..08923b21e566 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -484,7 +484,11 @@ static int __init mirred_init_module(void)
 		return err;
 
 	pr_info("Mirror/redirect action on\n");
-	return tcf_register_action(&act_mirred_ops, &mirred_net_ops);
+	err = tcf_register_action(&act_mirred_ops, &mirred_net_ops);
+	if (err)
+		unregister_netdevice_notifier(&mirred_device_notifier);
+
+	return err;
 }
 
 static void __exit mirred_cleanup_module(void)
-- 
cgit v1.2.3


From 33f37c648812bdbe1bd1eea75ddab3e799d51e77 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 9 Oct 2019 22:48:01 -0400
Subject: shmem: fix LSM options parsing

->parse_monolithic() there forgets to call security_sb_eat_lsm_opts()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 mm/shmem.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/mm/shmem.c b/mm/shmem.c
index 0f7fd4a85db6..8dcc8d04cbaf 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3482,6 +3482,12 @@ static int shmem_parse_options(struct fs_context *fc, void *data)
 {
 	char *options = data;
 
+	if (options) {
+		int err = security_sb_eat_lsm_opts(options, &fc->security);
+		if (err)
+			return err;
+	}
+
 	while (options != NULL) {
 		char *this_char = options;
 		for (;;) {
-- 
cgit v1.2.3


From 6fcf0c72e4b9360768cf5ef543c4f14c34800ee8 Mon Sep 17 00:00:00 2001
From: Ian Kent <raven@themaw.net>
Date: Wed, 2 Oct 2019 17:56:33 +0800
Subject: vfs: add missing blkdev_put() in get_tree_bdev()

Is there are a couple of missing blkdev_put() in get_tree_bdev()?

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/super.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/super.c b/fs/super.c
index beaf076d9733..530dd13fa98b 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1296,6 +1296,7 @@ int get_tree_bdev(struct fs_context *fc,
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
 	if (bdev->bd_fsfreeze_count > 0) {
 		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+		blkdev_put(bdev, mode);
 		warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
 		return -EBUSY;
 	}
@@ -1304,8 +1305,10 @@ int get_tree_bdev(struct fs_context *fc,
 	fc->sget_key = bdev;
 	s = sget_fc(fc, test_bdev_super_fc, set_bdev_super_fc);
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
-	if (IS_ERR(s))
+	if (IS_ERR(s)) {
+		blkdev_put(bdev, mode);
 		return PTR_ERR(s);
+	}
 
 	if (s->s_root) {
 		/* Don't summarily change the RO/RW state. */
-- 
cgit v1.2.3


From 26b6c984338474b7032a3f1ee28e9d7590c225db Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 20 Sep 2019 16:32:42 -0400
Subject: libfs: take cursors out of list when moving past the end of directory

that eliminates the last place where we accessed the tail of ->d_subdirs

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/libfs.c | 49 +++++++++++++++++++++++++------------------------
 1 file changed, 25 insertions(+), 24 deletions(-)

diff --git a/fs/libfs.c b/fs/libfs.c
index 8e023b08a240..540611b99b9a 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -92,14 +92,13 @@ EXPORT_SYMBOL(dcache_dir_close);
 /*
  * Returns an element of siblings' list.
  * We are looking for <count>th positive after <p>; if
- * found, dentry is grabbed and passed to caller via *<res>.
- * If no such element exists, the anchor of list is returned
- * and *<res> is set to NULL.
+ * found, dentry is grabbed and returned to caller.
+ * If no such element exists, NULL is returned.
  */
-static struct list_head *scan_positives(struct dentry *cursor,
+static struct dentry *scan_positives(struct dentry *cursor,
 					struct list_head *p,
 					loff_t count,
-					struct dentry **res)
+					struct dentry *last)
 {
 	struct dentry *dentry = cursor->d_parent, *found = NULL;
 
@@ -127,9 +126,8 @@ static struct list_head *scan_positives(struct dentry *cursor,
 		}
 	}
 	spin_unlock(&dentry->d_lock);
-	dput(*res);
-	*res = found;
-	return p;
+	dput(last);
+	return found;
 }
 
 loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
@@ -149,25 +147,22 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
 	if (offset != file->f_pos) {
 		struct dentry *cursor = file->private_data;
 		struct dentry *to = NULL;
-		struct list_head *p;
 
-		file->f_pos = offset;
 		inode_lock_shared(dentry->d_inode);
 
-		if (file->f_pos > 2) {
-			p = scan_positives(cursor, &dentry->d_subdirs,
-					   file->f_pos - 2, &to);
-			spin_lock(&dentry->d_lock);
-			list_move(&cursor->d_child, p);
-			spin_unlock(&dentry->d_lock);
-		} else {
-			spin_lock(&dentry->d_lock);
+		if (offset > 2)
+			to = scan_positives(cursor, &dentry->d_subdirs,
+					    offset - 2, NULL);
+		spin_lock(&dentry->d_lock);
+		if (to)
+			list_move(&cursor->d_child, &to->d_child);
+		else
 			list_del_init(&cursor->d_child);
-			spin_unlock(&dentry->d_lock);
-		}
-
+		spin_unlock(&dentry->d_lock);
 		dput(to);
 
+		file->f_pos = offset;
+
 		inode_unlock_shared(dentry->d_inode);
 	}
 	return offset;
@@ -199,17 +194,23 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
 
 	if (ctx->pos == 2)
 		p = anchor;
-	else
+	else if (!list_empty(&cursor->d_child))
 		p = &cursor->d_child;
+	else
+		return 0;
 
-	while ((p = scan_positives(cursor, p, 1, &next)) != anchor) {
+	while ((next = scan_positives(cursor, p, 1, next)) != NULL) {
 		if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
 			      d_inode(next)->i_ino, dt_type(d_inode(next))))
 			break;
 		ctx->pos++;
+		p = &next->d_child;
 	}
 	spin_lock(&dentry->d_lock);
-	list_move_tail(&cursor->d_child, p);
+	if (next)
+		list_move_tail(&cursor->d_child, &next->d_child);
+	else
+		list_del_init(&cursor->d_child);
 	spin_unlock(&dentry->d_lock);
 	dput(next);
 
-- 
cgit v1.2.3


From e0ae2c578d3909e60e9448207f5d83f785f1129f Mon Sep 17 00:00:00 2001
From: Daniele Palmas <dnlplm@gmail.com>
Date: Wed, 9 Oct 2019 11:07:18 +0200
Subject: net: usb: qmi_wwan: add Telit 0x1050 composition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds support for Telit FN980 0x1050 composition

0x1050: tty, adb, rmnet, tty, tty, tty, tty

Signed-off-by: Daniele Palmas <dnlplm@gmail.com>
Acked-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 3d77cd402ba9..596428ec71df 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1327,6 +1327,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x2357, 0x0201, 4)},	/* TP-LINK HSUPA Modem MA180 */
 	{QMI_FIXED_INTF(0x2357, 0x9000, 4)},	/* TP-LINK MA260 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */
-- 
cgit v1.2.3


From 79a85e214d62da9a750cc63ef49483e62abbda81 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 10 Oct 2019 00:38:13 +0900
Subject: null_blk: Fix zoned command return code

The return code from null_handle_zoned() sets the cmd->error value.
Returning OK status when an error occured overwrites the intended
cmd->error. Return the appropriate error code instead of setting the
error in the cmd.

Fixes: fceb5d1b19cbe626 ("null_blk: create a helper for zoned devices")
Cc: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/null_blk_zoned.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
index eabc116832a7..3d7fdea872f8 100644
--- a/drivers/block/null_blk_zoned.c
+++ b/drivers/block/null_blk_zoned.c
@@ -142,8 +142,7 @@ static blk_status_t null_zone_reset(struct nullb_cmd *cmd, sector_t sector)
 		zone->wp = zone->start;
 		break;
 	default:
-		cmd->error = BLK_STS_NOTSUPP;
-		break;
+		return BLK_STS_NOTSUPP;
 	}
 	return BLK_STS_OK;
 }
-- 
cgit v1.2.3


From 993e4c929a073595d22c85f59082f0c387e31c21 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Wed, 9 Oct 2019 11:19:10 +0200
Subject: netns: fix NLM_F_ECHO mechanism for RTM_NEWNSID

The flag NLM_F_ECHO aims to reply to the user the message notified to all
listeners.
It was not the case with the command RTM_NEWNSID, let's fix this.

Fixes: 0c7aecd4bde4 ("netns: add rtnl cmd to add and get peer netns ids")
Reported-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Guillaume Nault <gnault@redhat.com>
Tested-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/core/net_namespace.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index a0e0d298c991..6d3e4821b02d 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -245,7 +245,8 @@ static int __peernet2id(struct net *net, struct net *peer)
 	return __peernet2id_alloc(net, peer, &no);
 }
 
-static void rtnl_net_notifyid(struct net *net, int cmd, int id);
+static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
+			      struct nlmsghdr *nlh);
 /* This function returns the id of a peer netns. If no id is assigned, one will
  * be allocated and returned.
  */
@@ -268,7 +269,7 @@ int peernet2id_alloc(struct net *net, struct net *peer)
 	id = __peernet2id_alloc(net, peer, &alloc);
 	spin_unlock_bh(&net->nsid_lock);
 	if (alloc && id >= 0)
-		rtnl_net_notifyid(net, RTM_NEWNSID, id);
+		rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL);
 	if (alive)
 		put_net(peer);
 	return id;
@@ -532,7 +533,7 @@ static void unhash_nsid(struct net *net, struct net *last)
 			idr_remove(&tmp->netns_ids, id);
 		spin_unlock_bh(&tmp->nsid_lock);
 		if (id >= 0)
-			rtnl_net_notifyid(tmp, RTM_DELNSID, id);
+			rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL);
 		if (tmp == last)
 			break;
 	}
@@ -764,7 +765,8 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
 	err = alloc_netid(net, peer, nsid);
 	spin_unlock_bh(&net->nsid_lock);
 	if (err >= 0) {
-		rtnl_net_notifyid(net, RTM_NEWNSID, err);
+		rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid,
+				  nlh);
 		err = 0;
 	} else if (err == -ENOSPC && nsid >= 0) {
 		err = -EEXIST;
@@ -1051,9 +1053,12 @@ end:
 	return err < 0 ? err : skb->len;
 }
 
-static void rtnl_net_notifyid(struct net *net, int cmd, int id)
+static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
+			      struct nlmsghdr *nlh)
 {
 	struct net_fill_args fillargs = {
+		.portid = portid,
+		.seq = nlh ? nlh->nlmsg_seq : 0,
 		.cmd = cmd,
 		.nsid = id,
 	};
@@ -1068,7 +1073,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id)
 	if (err < 0)
 		goto err_out;
 
-	rtnl_notify(msg, net, 0, RTNLGRP_NSID, NULL, 0);
+	rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, 0);
 	return;
 
 err_out:
-- 
cgit v1.2.3


From e37542ba111f3974dc622ae0a21c1787318de500 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Oct 2019 09:19:13 -0700
Subject: netfilter: conntrack: avoid possible false sharing

As hinted by KCSAN, we need at least one READ_ONCE()
to prevent a compiler optimization.

More details on :
https://github.com/google/ktsan/wiki/READ_ONCE-and-WRITE_ONCE#it-may-improve-performance

sysbot report :
BUG: KCSAN: data-race in __nf_ct_refresh_acct / __nf_ct_refresh_acct

read to 0xffff888123eb4f08 of 4 bytes by interrupt on cpu 0:
 __nf_ct_refresh_acct+0xd4/0x1b0 net/netfilter/nf_conntrack_core.c:1796
 nf_ct_refresh_acct include/net/netfilter/nf_conntrack.h:201 [inline]
 nf_conntrack_tcp_packet+0xd40/0x3390 net/netfilter/nf_conntrack_proto_tcp.c:1161
 nf_conntrack_handle_packet net/netfilter/nf_conntrack_core.c:1633 [inline]
 nf_conntrack_in+0x410/0xaa0 net/netfilter/nf_conntrack_core.c:1727
 ipv4_conntrack_in+0x27/0x40 net/netfilter/nf_conntrack_proto.c:178
 nf_hook_entry_hookfn include/linux/netfilter.h:135 [inline]
 nf_hook_slow+0x83/0x160 net/netfilter/core.c:512
 nf_hook include/linux/netfilter.h:260 [inline]
 NF_HOOK include/linux/netfilter.h:303 [inline]
 ip_rcv+0x12f/0x1a0 net/ipv4/ip_input.c:523
 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5004
 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5118
 netif_receive_skb_internal+0x59/0x190 net/core/dev.c:5208
 napi_skb_finish net/core/dev.c:5671 [inline]
 napi_gro_receive+0x28f/0x330 net/core/dev.c:5704
 receive_buf+0x284/0x30b0 drivers/net/virtio_net.c:1061
 virtnet_receive drivers/net/virtio_net.c:1323 [inline]
 virtnet_poll+0x436/0x7d0 drivers/net/virtio_net.c:1428
 napi_poll net/core/dev.c:6352 [inline]
 net_rx_action+0x3ae/0xa50 net/core/dev.c:6418
 __do_softirq+0x115/0x33f kernel/softirq.c:292

write to 0xffff888123eb4f08 of 4 bytes by task 7191 on cpu 1:
 __nf_ct_refresh_acct+0xfb/0x1b0 net/netfilter/nf_conntrack_core.c:1797
 nf_ct_refresh_acct include/net/netfilter/nf_conntrack.h:201 [inline]
 nf_conntrack_tcp_packet+0xd40/0x3390 net/netfilter/nf_conntrack_proto_tcp.c:1161
 nf_conntrack_handle_packet net/netfilter/nf_conntrack_core.c:1633 [inline]
 nf_conntrack_in+0x410/0xaa0 net/netfilter/nf_conntrack_core.c:1727
 ipv4_conntrack_local+0xbe/0x130 net/netfilter/nf_conntrack_proto.c:200
 nf_hook_entry_hookfn include/linux/netfilter.h:135 [inline]
 nf_hook_slow+0x83/0x160 net/netfilter/core.c:512
 nf_hook include/linux/netfilter.h:260 [inline]
 __ip_local_out+0x1f7/0x2b0 net/ipv4/ip_output.c:114
 ip_local_out+0x31/0x90 net/ipv4/ip_output.c:123
 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532
 ip_queue_xmit+0x45/0x60 include/net/ip.h:236
 __tcp_transmit_skb+0xdeb/0x1cd0 net/ipv4/tcp_output.c:1158
 __tcp_send_ack+0x246/0x300 net/ipv4/tcp_output.c:3685
 tcp_send_ack+0x34/0x40 net/ipv4/tcp_output.c:3691
 tcp_cleanup_rbuf+0x130/0x360 net/ipv4/tcp.c:1575

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 7191 Comm: syz-fuzzer Not tainted 5.3.0+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Fixes: cc16921351d8 ("netfilter: conntrack: avoid same-timeout update")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Jozsef Kadlecsik <kadlec@netfilter.org>
Cc: Florian Westphal <fw@strlen.de>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/netfilter/nf_conntrack_core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 0c63120b2db2..5cd610b547e0 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1792,8 +1792,8 @@ void __nf_ct_refresh_acct(struct nf_conn *ct,
 	if (nf_ct_is_confirmed(ct))
 		extra_jiffies += nfct_time_stamp;
 
-	if (ct->timeout != extra_jiffies)
-		ct->timeout = extra_jiffies;
+	if (READ_ONCE(ct->timeout) != extra_jiffies)
+		WRITE_ONCE(ct->timeout, extra_jiffies);
 acct:
 	if (do_acct)
 		nf_ct_acct_update(ct, ctinfo, skb->len);
-- 
cgit v1.2.3


From 4ffdd22e49f47db543906d75453a0048a53071ab Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Oct 2019 09:20:02 -0700
Subject: tun: remove possible false sharing in tun_flow_update()

As mentioned in https://github.com/google/ktsan/wiki/READ_ONCE-and-WRITE_ONCE#it-may-improve-performance
a C compiler can legally transform

if (e->queue_index != queue_index)
	e->queue_index = queue_index;

to :

	e->queue_index = queue_index;

Note that the code using jiffies has no issue, since jiffies
has volatile attribute.

if (e->updated != jiffies)
    e->updated = jiffies;

Fixes: 83b1bc122cab ("tun: align write-heavy flow entry members to a cache line")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Zhang Yu <zhangyu31@baidu.com>
Cc: Wang Li <wangli39@baidu.com>
Cc: Li RongQing <lirongqing@baidu.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/tun.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 812dc3a65efb..a8d3141582a5 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -526,8 +526,8 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash,
 	e = tun_flow_find(head, rxhash);
 	if (likely(e)) {
 		/* TODO: keep queueing to old queue until it's empty? */
-		if (e->queue_index != queue_index)
-			e->queue_index = queue_index;
+		if (READ_ONCE(e->queue_index) != queue_index)
+			WRITE_ONCE(e->queue_index, queue_index);
 		if (e->updated != jiffies)
 			e->updated = jiffies;
 		sock_rps_record_flow_hash(e->rps_rxhash);
-- 
cgit v1.2.3


From 503978aca46124cd714703e180b9c8292ba50ba7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Oct 2019 12:55:53 -0700
Subject: net: avoid possible false sharing in sk_leave_memory_pressure()

As mentioned in https://github.com/google/ktsan/wiki/READ_ONCE-and-WRITE_ONCE#it-may-improve-performance
a C compiler can legally transform :

if (memory_pressure && *memory_pressure)
        *memory_pressure = 0;

to :

if (memory_pressure)
        *memory_pressure = 0;

Fixes: 0604475119de ("tcp: add TCPMemoryPressuresChrono counter")
Fixes: 180d8cd942ce ("foundations of per-cgroup memory pressure controlling.")
Fixes: 3ab224be6d69 ("[NET] CORE: Introducing new memory accounting interface.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/core/sock.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index fac2b4d80de5..50647a10fdb7 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2334,8 +2334,8 @@ static void sk_leave_memory_pressure(struct sock *sk)
 	} else {
 		unsigned long *memory_pressure = sk->sk_prot->memory_pressure;
 
-		if (memory_pressure && *memory_pressure)
-			*memory_pressure = 0;
+		if (memory_pressure && READ_ONCE(*memory_pressure))
+			WRITE_ONCE(*memory_pressure, 0);
 	}
 }
 
-- 
cgit v1.2.3


From 60b173ca3d1cd1782bd0096dc17298ec242f6fb1 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Oct 2019 14:51:20 -0700
Subject: net: add {READ|WRITE}_ONCE() annotations on ->rskq_accept_head

reqsk_queue_empty() is called from inet_csk_listen_poll() while
other cpus might write ->rskq_accept_head value.

Use {READ|WRITE}_ONCE() to avoid compiler tricks
and potential KCSAN splats.

Fixes: fff1f3001cc5 ("tcp: add a spinlock to protect struct request_sock_queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/xen/pvcalls-back.c      | 2 +-
 include/net/request_sock.h      | 4 ++--
 net/ipv4/inet_connection_sock.c | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c
index 69a626b0e594..c57c71b7d53d 100644
--- a/drivers/xen/pvcalls-back.c
+++ b/drivers/xen/pvcalls-back.c
@@ -775,7 +775,7 @@ static int pvcalls_back_poll(struct xenbus_device *dev,
 	mappass->reqcopy = *req;
 	icsk = inet_csk(mappass->sock->sk);
 	queue = &icsk->icsk_accept_queue;
-	data = queue->rskq_accept_head != NULL;
+	data = READ_ONCE(queue->rskq_accept_head) != NULL;
 	if (data) {
 		mappass->reqcopy.cmd = 0;
 		ret = 0;
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index fd178d58fa84..cf8b33213bbc 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -185,7 +185,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
 
 static inline bool reqsk_queue_empty(const struct request_sock_queue *queue)
 {
-	return queue->rskq_accept_head == NULL;
+	return READ_ONCE(queue->rskq_accept_head) == NULL;
 }
 
 static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue,
@@ -197,7 +197,7 @@ static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue
 	req = queue->rskq_accept_head;
 	if (req) {
 		sk_acceptq_removed(parent);
-		queue->rskq_accept_head = req->dl_next;
+		WRITE_ONCE(queue->rskq_accept_head, req->dl_next);
 		if (queue->rskq_accept_head == NULL)
 			queue->rskq_accept_tail = NULL;
 	}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index a9183543ca30..dbcf34ec8dd2 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -934,7 +934,7 @@ struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
 		req->sk = child;
 		req->dl_next = NULL;
 		if (queue->rskq_accept_head == NULL)
-			queue->rskq_accept_head = req;
+			WRITE_ONCE(queue->rskq_accept_head, req);
 		else
 			queue->rskq_accept_tail->dl_next = req;
 		queue->rskq_accept_tail = req;
-- 
cgit v1.2.3


From 1f142c17d19a5618d5a633195a46f2c8be9bf232 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Oct 2019 15:10:15 -0700
Subject: tcp: annotate lockless access to tcp_memory_pressure

tcp_memory_pressure is read without holding any lock,
and its value could be changed on other cpus.

Use READ_ONCE() to annotate these lockless reads.

The write side is already using atomic ops.

Fixes: b8da51ebb1aa ("tcp: introduce tcp_under_memory_pressure()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 include/net/tcp.h | 2 +-
 net/ipv4/tcp.c    | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index c9a3f9688223..88e63d64c698 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -258,7 +258,7 @@ static inline bool tcp_under_memory_pressure(const struct sock *sk)
 	    mem_cgroup_under_socket_pressure(sk->sk_memcg))
 		return true;
 
-	return tcp_memory_pressure;
+	return READ_ONCE(tcp_memory_pressure);
 }
 /*
  * The next routines deal with comparing 32 bit unsigned ints
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f98a1882e537..888c92b63f5a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -326,7 +326,7 @@ void tcp_enter_memory_pressure(struct sock *sk)
 {
 	unsigned long val;
 
-	if (tcp_memory_pressure)
+	if (READ_ONCE(tcp_memory_pressure))
 		return;
 	val = jiffies;
 
@@ -341,7 +341,7 @@ void tcp_leave_memory_pressure(struct sock *sk)
 {
 	unsigned long val;
 
-	if (!tcp_memory_pressure)
+	if (!READ_ONCE(tcp_memory_pressure))
 		return;
 	val = xchg(&tcp_memory_pressure, 0);
 	if (val)
-- 
cgit v1.2.3


From 8265792bf8871acc2d00fd03883d830e2249d395 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Oct 2019 15:21:13 -0700
Subject: net: silence KCSAN warnings around sk_add_backlog() calls

sk_add_backlog() callers usually read sk->sk_rcvbuf without
owning the socket lock. This means sk_rcvbuf value can
be changed by other cpus, and KCSAN complains.

Add READ_ONCE() annotations to document the lockless nature
of these reads.

Note that writes over sk_rcvbuf should also use WRITE_ONCE(),
but this will be done in separate patches to ease stable
backports (if we decide this is relevant for stable trees).

BUG: KCSAN: data-race in tcp_add_backlog / tcp_recvmsg

write to 0xffff88812ab369f8 of 8 bytes by interrupt on cpu 1:
 __sk_add_backlog include/net/sock.h:902 [inline]
 sk_add_backlog include/net/sock.h:933 [inline]
 tcp_add_backlog+0x45a/0xcc0 net/ipv4/tcp_ipv4.c:1737
 tcp_v4_rcv+0x1aba/0x1bf0 net/ipv4/tcp_ipv4.c:1925
 ip_protocol_deliver_rcu+0x51/0x470 net/ipv4/ip_input.c:204
 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231
 NF_HOOK include/linux/netfilter.h:305 [inline]
 NF_HOOK include/linux/netfilter.h:299 [inline]
 ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252
 dst_input include/net/dst.h:442 [inline]
 ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413
 NF_HOOK include/linux/netfilter.h:305 [inline]
 NF_HOOK include/linux/netfilter.h:299 [inline]
 ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523
 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5004
 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5118
 netif_receive_skb_internal+0x59/0x190 net/core/dev.c:5208
 napi_skb_finish net/core/dev.c:5671 [inline]
 napi_gro_receive+0x28f/0x330 net/core/dev.c:5704
 receive_buf+0x284/0x30b0 drivers/net/virtio_net.c:1061
 virtnet_receive drivers/net/virtio_net.c:1323 [inline]
 virtnet_poll+0x436/0x7d0 drivers/net/virtio_net.c:1428
 napi_poll net/core/dev.c:6352 [inline]
 net_rx_action+0x3ae/0xa50 net/core/dev.c:6418

read to 0xffff88812ab369f8 of 8 bytes by task 7271 on cpu 0:
 tcp_recvmsg+0x470/0x1a30 net/ipv4/tcp.c:2047
 inet_recvmsg+0xbb/0x250 net/ipv4/af_inet.c:838
 sock_recvmsg_nosec net/socket.c:871 [inline]
 sock_recvmsg net/socket.c:889 [inline]
 sock_recvmsg+0x92/0xb0 net/socket.c:885
 sock_read_iter+0x15f/0x1e0 net/socket.c:967
 call_read_iter include/linux/fs.h:1864 [inline]
 new_sync_read+0x389/0x4f0 fs/read_write.c:414
 __vfs_read+0xb1/0xc0 fs/read_write.c:427
 vfs_read fs/read_write.c:461 [inline]
 vfs_read+0x143/0x2c0 fs/read_write.c:446
 ksys_read+0xd5/0x1b0 fs/read_write.c:587
 __do_sys_read fs/read_write.c:597 [inline]
 __se_sys_read fs/read_write.c:595 [inline]
 __x64_sys_read+0x4c/0x60 fs/read_write.c:595
 do_syscall_64+0xcf/0x2f0 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 7271 Comm: syz-fuzzer Not tainted 5.3.0+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/core/sock.c     | 2 +-
 net/ipv4/tcp_ipv4.c | 2 +-
 net/llc/llc_conn.c  | 2 +-
 net/sctp/input.c    | 6 +++---
 net/tipc/socket.c   | 6 +++---
 net/x25/x25_dev.c   | 2 +-
 6 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 50647a10fdb7..1cf06934da50 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -522,7 +522,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
 		rc = sk_backlog_rcv(sk, skb);
 
 		mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
-	} else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) {
+	} else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) {
 		bh_unlock_sock(sk);
 		atomic_inc(&sk->sk_drops);
 		goto discard_and_relse;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bf124b1742df..492bf6a6b023 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1644,7 +1644,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
 
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
-	u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf;
+	u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf);
 	struct skb_shared_info *shinfo;
 	const struct tcphdr *th;
 	struct tcphdr *thtail;
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index a79b739eb223..7b620acaca9e 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -813,7 +813,7 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb)
 	else {
 		dprintk("%s: adding to backlog...\n", __func__);
 		llc_set_backlog_type(skb, LLC_PACKET);
-		if (sk_add_backlog(sk, skb, sk->sk_rcvbuf))
+		if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))
 			goto drop_unlock;
 	}
 out:
diff --git a/net/sctp/input.c b/net/sctp/input.c
index f2771375bfc0..2277981559d0 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -322,7 +322,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 		bh_lock_sock(sk);
 
 		if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) {
-			if (sk_add_backlog(sk, skb, sk->sk_rcvbuf))
+			if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))
 				sctp_chunk_free(chunk);
 			else
 				backloged = 1;
@@ -337,7 +337,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb)
 			return 0;
 	} else {
 		if (!sctp_newsk_ready(sk)) {
-			if (!sk_add_backlog(sk, skb, sk->sk_rcvbuf))
+			if (!sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))
 				return 0;
 			sctp_chunk_free(chunk);
 		} else {
@@ -364,7 +364,7 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	struct sctp_ep_common *rcvr = chunk->rcvr;
 	int ret;
 
-	ret = sk_add_backlog(sk, skb, sk->sk_rcvbuf);
+	ret = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf));
 	if (!ret) {
 		/* Hold the assoc/ep while hanging on the backlog queue.
 		 * This way, we know structures we need will not disappear
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3b9f8cc328f5..7c736cfec57f 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2119,13 +2119,13 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
 	struct tipc_msg *hdr = buf_msg(skb);
 
 	if (unlikely(msg_in_group(hdr)))
-		return sk->sk_rcvbuf;
+		return READ_ONCE(sk->sk_rcvbuf);
 
 	if (unlikely(!msg_connected(hdr)))
-		return sk->sk_rcvbuf << msg_importance(hdr);
+		return READ_ONCE(sk->sk_rcvbuf) << msg_importance(hdr);
 
 	if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL))
-		return sk->sk_rcvbuf;
+		return READ_ONCE(sk->sk_rcvbuf);
 
 	return FLOWCTL_MSG_LIM;
 }
diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c
index 5c111bc3c8ea..00e782335cb0 100644
--- a/net/x25/x25_dev.c
+++ b/net/x25/x25_dev.c
@@ -55,7 +55,7 @@ static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb)
 		if (!sock_owned_by_user(sk)) {
 			queued = x25_process_rx_frame(sk, skb);
 		} else {
-			queued = !sk_add_backlog(sk, skb, sk->sk_rcvbuf);
+			queued = !sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf));
 		}
 		bh_unlock_sock(sk);
 		sock_put(sk);
-- 
cgit v1.2.3


From eac66402d1c342f07ff38f8d631ff95eb7ad3220 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Oct 2019 15:32:35 -0700
Subject: net: annotate sk->sk_rcvlowat lockless reads

sock_rcvlowat() or int_sk_rcvlowat() might be called without the socket
lock for example from tcp_poll().

Use READ_ONCE() to document the fact that other cpus might change
sk->sk_rcvlowat under us and avoid KCSAN splats.

Use WRITE_ONCE() on write sides too.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 include/net/sock.h  | 4 +++-
 net/core/filter.c   | 2 +-
 net/core/sock.c     | 2 +-
 net/ipv4/tcp.c      | 2 +-
 net/sched/em_meta.c | 2 +-
 5 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 2c53f1a1d905..79f54e1f8827 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2271,7 +2271,9 @@ static inline long sock_sndtimeo(const struct sock *sk, bool noblock)
 
 static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len)
 {
-	return (waitall ? len : min_t(int, sk->sk_rcvlowat, len)) ? : 1;
+	int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len);
+
+	return v ?: 1;
 }
 
 /* Alas, with timeout socket operations are not restartable.
diff --git a/net/core/filter.c b/net/core/filter.c
index ed6563622ce3..a50c0b6846f2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4274,7 +4274,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 		case SO_RCVLOWAT:
 			if (val < 0)
 				val = INT_MAX;
-			sk->sk_rcvlowat = val ? : 1;
+			WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 			break;
 		case SO_MARK:
 			if (sk->sk_mark != val) {
diff --git a/net/core/sock.c b/net/core/sock.c
index 1cf06934da50..b7c5c6ea51ba 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -974,7 +974,7 @@ set_rcvbuf:
 		if (sock->ops->set_rcvlowat)
 			ret = sock->ops->set_rcvlowat(sk, val);
 		else
-			sk->sk_rcvlowat = val ? : 1;
+			WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 		break;
 
 	case SO_RCVTIMEO_OLD:
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 888c92b63f5a..8781a92ea4b6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1699,7 +1699,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 	else
 		cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
 	val = min(val, cap);
-	sk->sk_rcvlowat = val ? : 1;
+	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 
 	/* Check if we need to signal EPOLLIN right now */
 	tcp_data_ready(sk);
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 82bd14e7ac93..4c9122fc35c9 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -554,7 +554,7 @@ META_COLLECTOR(int_sk_rcvlowat)
 		*err = -1;
 		return;
 	}
-	dst->value = sk->sk_rcvlowat;
+	dst->value = READ_ONCE(sk->sk_rcvlowat);
 }
 
 META_COLLECTOR(int_sk_rcvtimeo)
-- 
cgit v1.2.3


From 70c2655849a25431f31b505a07fe0c861e5e41fb Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Oct 2019 15:41:03 -0700
Subject: net: silence KCSAN warnings about sk->sk_backlog.len reads

sk->sk_backlog.len can be written by BH handlers, and read
from process contexts in a lockless way.

Note the write side should also use WRITE_ONCE() or a variant.
We need some agreement about the best way to do this.

syzbot reported :

BUG: KCSAN: data-race in tcp_add_backlog / tcp_grow_window.isra.0

write to 0xffff88812665f32c of 4 bytes by interrupt on cpu 1:
 sk_add_backlog include/net/sock.h:934 [inline]
 tcp_add_backlog+0x4a0/0xcc0 net/ipv4/tcp_ipv4.c:1737
 tcp_v4_rcv+0x1aba/0x1bf0 net/ipv4/tcp_ipv4.c:1925
 ip_protocol_deliver_rcu+0x51/0x470 net/ipv4/ip_input.c:204
 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231
 NF_HOOK include/linux/netfilter.h:305 [inline]
 NF_HOOK include/linux/netfilter.h:299 [inline]
 ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252
 dst_input include/net/dst.h:442 [inline]
 ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413
 NF_HOOK include/linux/netfilter.h:305 [inline]
 NF_HOOK include/linux/netfilter.h:299 [inline]
 ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523
 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5004
 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5118
 netif_receive_skb_internal+0x59/0x190 net/core/dev.c:5208
 napi_skb_finish net/core/dev.c:5671 [inline]
 napi_gro_receive+0x28f/0x330 net/core/dev.c:5704
 receive_buf+0x284/0x30b0 drivers/net/virtio_net.c:1061
 virtnet_receive drivers/net/virtio_net.c:1323 [inline]
 virtnet_poll+0x436/0x7d0 drivers/net/virtio_net.c:1428
 napi_poll net/core/dev.c:6352 [inline]
 net_rx_action+0x3ae/0xa50 net/core/dev.c:6418

read to 0xffff88812665f32c of 4 bytes by task 7292 on cpu 0:
 tcp_space include/net/tcp.h:1373 [inline]
 tcp_grow_window.isra.0+0x6b/0x480 net/ipv4/tcp_input.c:413
 tcp_event_data_recv+0x68f/0x990 net/ipv4/tcp_input.c:717
 tcp_rcv_established+0xbfe/0xf50 net/ipv4/tcp_input.c:5618
 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1542
 sk_backlog_rcv include/net/sock.h:945 [inline]
 __release_sock+0x135/0x1e0 net/core/sock.c:2427
 release_sock+0x61/0x160 net/core/sock.c:2943
 tcp_recvmsg+0x63b/0x1a30 net/ipv4/tcp.c:2181
 inet_recvmsg+0xbb/0x250 net/ipv4/af_inet.c:838
 sock_recvmsg_nosec net/socket.c:871 [inline]
 sock_recvmsg net/socket.c:889 [inline]
 sock_recvmsg+0x92/0xb0 net/socket.c:885
 sock_read_iter+0x15f/0x1e0 net/socket.c:967
 call_read_iter include/linux/fs.h:1864 [inline]
 new_sync_read+0x389/0x4f0 fs/read_write.c:414
 __vfs_read+0xb1/0xc0 fs/read_write.c:427
 vfs_read fs/read_write.c:461 [inline]
 vfs_read+0x143/0x2c0 fs/read_write.c:446

Reported by Kernel Concurrency Sanitizer on:
CPU: 0 PID: 7292 Comm: syz-fuzzer Not tainted 5.3.0+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 include/net/tcp.h | 3 ++-
 net/core/sock.c   | 2 +-
 net/sctp/diag.c   | 2 +-
 net/tipc/socket.c | 2 +-
 4 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 88e63d64c698..35f6f7e0fdc2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1380,7 +1380,8 @@ static inline int tcp_win_from_space(const struct sock *sk, int space)
 /* Note: caller must be prepared to deal with negative returns */
 static inline int tcp_space(const struct sock *sk)
 {
-	return tcp_win_from_space(sk, sk->sk_rcvbuf - sk->sk_backlog.len -
+	return tcp_win_from_space(sk, sk->sk_rcvbuf -
+				  READ_ONCE(sk->sk_backlog.len) -
 				  atomic_read(&sk->sk_rmem_alloc));
 }
 
diff --git a/net/core/sock.c b/net/core/sock.c
index b7c5c6ea51ba..2a053999df11 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3210,7 +3210,7 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem)
 	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
 	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
 	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
-	mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+	mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
 	mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
 }
 
diff --git a/net/sctp/diag.c b/net/sctp/diag.c
index fc9a4c6629ce..0851166b9175 100644
--- a/net/sctp/diag.c
+++ b/net/sctp/diag.c
@@ -175,7 +175,7 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc,
 		mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
 		mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
 		mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
-		mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+		mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
 		mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
 
 		if (nla_put(skb, INET_DIAG_SKMEMINFO, sizeof(mem), &mem) < 0)
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 7c736cfec57f..f8bbc4aab213 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -3790,7 +3790,7 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf)
 	i += scnprintf(buf + i, sz - i, " %d", sk->sk_sndbuf);
 	i += scnprintf(buf + i, sz - i, " | %d", sk_rmem_alloc_get(sk));
 	i += scnprintf(buf + i, sz - i, " %d", sk->sk_rcvbuf);
-	i += scnprintf(buf + i, sz - i, " | %d\n", sk->sk_backlog.len);
+	i += scnprintf(buf + i, sz - i, " | %d\n", READ_ONCE(sk->sk_backlog.len));
 
 	if (dqueues & TIPC_DUMP_SK_SNDQ) {
 		i += scnprintf(buf + i, sz - i, "sk_write_queue: ");
-- 
cgit v1.2.3


From 05668e1d74b84c53fbe0f28565e4c9502a6b8a67 Mon Sep 17 00:00:00 2001
From: Halil Pasic <pasic@linux.ibm.com>
Date: Mon, 30 Sep 2019 17:38:02 +0200
Subject: s390/cio: fix virtio-ccw DMA without PV

Commit 37db8985b211 ("s390/cio: add basic protected virtualization
support") breaks virtio-ccw devices with VIRTIO_F_IOMMU_PLATFORM for non
Protected Virtualization (PV) guests. The problem is that the dma_mask
of the ccw device, which is used by virtio core, gets changed from 64 to
31 bit, because some of the DMA allocations do require 31 bit
addressable memory. For PV the only drawback is that some of the virtio
structures must end up in ZONE_DMA because we have the bounce the
buffers mapped via DMA API anyway.

But for non PV guests we have a problem: because of the 31 bit mask
guests bigger than 2G are likely to try bouncing buffers. The swiotlb
however is only initialized for PV guests, because we don't want to
bounce anything for non PV guests. The first such map kills the guest.

Since the DMA API won't allow us to specify for each allocation whether
we need memory from ZONE_DMA (31 bit addressable) or any DMA capable
memory will do, let us use coherent_dma_mask (which is used for
allocations) to force allocating form ZONE_DMA while changing dma_mask
to DMA_BIT_MASK(64) so that at least the streaming API will regard
the whole memory DMA capable.

Signed-off-by: Halil Pasic <pasic@linux.ibm.com>
Reported-by: Marc Hartmayer <mhartmay@linux.ibm.com>
Suggested-by: Robin Murphy <robin.murphy@arm.com>
Fixes: 37db8985b211 ("s390/cio: add basic protected virtualization support")
Link: https://lore.kernel.org/lkml/20190930153803.7958-1-pasic@linux.ibm.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 drivers/s390/cio/cio.h    | 1 +
 drivers/s390/cio/css.c    | 7 ++++++-
 drivers/s390/cio/device.c | 2 +-
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index ba7d2480613b..dcdaba689b20 100644
--- a/drivers/s390/cio/cio.h
+++ b/drivers/s390/cio/cio.h
@@ -113,6 +113,7 @@ struct subchannel {
 	enum sch_todo todo;
 	struct work_struct todo_work;
 	struct schib_config config;
+	u64 dma_mask;
 	char *driver_override; /* Driver name to force a match */
 } __attribute__ ((aligned(8)));
 
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 1fbfb0a93f5f..831850435c23 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -232,7 +232,12 @@ struct subchannel *css_alloc_subchannel(struct subchannel_id schid,
 	 * belong to a subchannel need to fit 31 bit width (e.g. ccw).
 	 */
 	sch->dev.coherent_dma_mask = DMA_BIT_MASK(31);
-	sch->dev.dma_mask = &sch->dev.coherent_dma_mask;
+	/*
+	 * But we don't have such restrictions imposed on the stuff that
+	 * is handled by the streaming API.
+	 */
+	sch->dma_mask = DMA_BIT_MASK(64);
+	sch->dev.dma_mask = &sch->dma_mask;
 	return sch;
 
 err:
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 131430bd48d9..0c6245fc7706 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -710,7 +710,7 @@ static struct ccw_device * io_subchannel_allocate_dev(struct subchannel *sch)
 	if (!cdev->private)
 		goto err_priv;
 	cdev->dev.coherent_dma_mask = sch->dev.coherent_dma_mask;
-	cdev->dev.dma_mask = &cdev->dev.coherent_dma_mask;
+	cdev->dev.dma_mask = sch->dev.dma_mask;
 	dma_pool = cio_gp_dma_create(&cdev->dev, 1);
 	if (!dma_pool)
 		goto err_dma_pool;
-- 
cgit v1.2.3


From 2189624b3c5a6fb03416129e35c09aa5151b7392 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@dell.com>
Date: Thu, 26 Sep 2019 11:08:57 -0500
Subject: ACPI: PM: Drop Dell XPS13 9360 from LPS0 Idle _DSM blacklist

This reverts part of commit 71630b7a832f ("ACPI / PM: Blacklist Low
Power S0 Idle _DSM for Dell XPS13 9360") to remove the S0ix blacklist
for the XPS 9360.

The problems with this system occurred in one possible NVME SSD when
putting system into s0ix.  As the NVME sleep behavior has been adjusted
in commit d916b1be94b6 ("nvme-pci: use host managed power state for
suspend") this is expected to be now resolved.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=196907
Signed-off-by: Mario Limonciello <mario.limonciello@dell.com>
Tested-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/sleep.c | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 9fa77d72ef27..2af937a8b1c5 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -361,19 +361,6 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "80E3"),
 		},
 	},
-	/*
-	 * https://bugzilla.kernel.org/show_bug.cgi?id=196907
-	 * Some Dell XPS13 9360 cannot do suspend-to-idle using the Low Power
-	 * S0 Idle firmware interface.
-	 */
-	{
-	.callback = init_default_s3,
-	.ident = "Dell XPS13 9360",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-		DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9360"),
-		},
-	},
 	/*
 	 * ThinkPad X1 Tablet(2016) cannot do suspend-to-idle using
 	 * the Low Power S0 Idle firmware interface (see
-- 
cgit v1.2.3


From 65650b35133ff20f0c9ef0abd5c3c66dbce3ae57 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 9 Oct 2019 01:29:10 +0200
Subject: cpufreq: Avoid cpufreq_suspend() deadlock on system shutdown
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It is incorrect to set the cpufreq syscore shutdown callback pointer
to cpufreq_suspend(), because that function cannot be run in the
syscore stage of system shutdown for two reasons: (a) it may attempt
to carry out actions depending on devices that have already been shut
down at that point and (b) the RCU synchronization carried out by it
may not be able to make progress then.

The latter issue has been present since commit 45975c7d21a1 ("rcu:
Define RCU-sched API in terms of RCU for Tree RCU PREEMPT builds"),
but the former one has been there since commit 90de2a4aa9f3 ("cpufreq:
suspend cpufreq governors on shutdown") regardless.

Fix that by dropping cpufreq_syscore_ops altogether and making
device_shutdown() call cpufreq_suspend() directly before shutting
down devices, which is along the lines of what system-wide power
management does.

Fixes: 45975c7d21a1 ("rcu: Define RCU-sched API in terms of RCU for Tree RCU PREEMPT builds")
Fixes: 90de2a4aa9f3 ("cpufreq: suspend cpufreq governors on shutdown")
Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Tested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: 4.0+ <stable@vger.kernel.org> # 4.0+
---
 drivers/base/core.c       |  3 +++
 drivers/cpufreq/cpufreq.c | 10 ----------
 2 files changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 2db62d98e395..7bd9cd366d41 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/cpufreq.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/fwnode.h>
@@ -3179,6 +3180,8 @@ void device_shutdown(void)
 	wait_for_device_probe();
 	device_block_probing();
 
+	cpufreq_suspend();
+
 	spin_lock(&devices_kset->list_lock);
 	/*
 	 * Walk the devices list backward, shutting down each in turn.
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index c52d6fa32aac..bffc11b87247 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2737,14 +2737,6 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 }
 EXPORT_SYMBOL_GPL(cpufreq_unregister_driver);
 
-/*
- * Stop cpufreq at shutdown to make sure it isn't holding any locks
- * or mutexes when secondary CPUs are halted.
- */
-static struct syscore_ops cpufreq_syscore_ops = {
-	.shutdown = cpufreq_suspend,
-};
-
 struct kobject *cpufreq_global_kobject;
 EXPORT_SYMBOL(cpufreq_global_kobject);
 
@@ -2756,8 +2748,6 @@ static int __init cpufreq_core_init(void)
 	cpufreq_global_kobject = kobject_create_and_add("cpufreq", &cpu_subsys.dev_root->kobj);
 	BUG_ON(!cpufreq_global_kobject);
 
-	register_syscore_ops(&cpufreq_syscore_ops);
-
 	return 0;
 }
 module_param(off, int, 0444);
-- 
cgit v1.2.3


From f49249d58abdc12067d69f15d509487171148b30 Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Tue, 8 Oct 2019 11:46:46 +0100
Subject: PM: sleep: include <linux/pm_runtime.h> for pm_wq

Include the <linux/runtime_pm.h> for the definition of
pm_wq to avoid the following warning:

kernel/power/main.c:890:25: warning: symbol 'pm_wq' was not declared. Should it be static?

Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/power/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/power/main.c b/kernel/power/main.c
index e8710d179b35..e26de7af520b 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -15,6 +15,7 @@
 #include <linux/seq_file.h>
 #include <linux/suspend.h>
 #include <linux/syscalls.h>
+#include <linux/pm_runtime.h>
 
 #include "power.h"
 
-- 
cgit v1.2.3


From ba2c74da52eba388d959a1000a9dd08fa4857659 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Wed, 9 Oct 2019 16:04:23 -0700
Subject: drm/i915/tgl: the BCS engine supports relative MMIO

The specs don't mention any specific HW limitation on the blitter and
manual inspection shows that the HW does set the relative MMIO bit in
the LRI of the blitter context image, so we can remove our limitations.

Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191009230424.6507-1-daniele.ceraolospurio@intel.com
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 7ea58335f04c..eb061f345166 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -3451,7 +3451,7 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 			engine->flags |= I915_ENGINE_HAS_PREEMPTION;
 	}
 
-	if (engine->class != COPY_ENGINE_CLASS && INTEL_GEN(engine->i915) >= 12)
+	if (INTEL_GEN(engine->i915) >= 12)
 		engine->flags |= I915_ENGINE_HAS_RELATIVE_MMIO;
 }
 
-- 
cgit v1.2.3


From 9d41318c4e43da6b4c95a21cf366bf18179291fd Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Wed, 9 Oct 2019 16:04:24 -0700
Subject: drm/i915/tgl: simplify the lrc register list for !RCS

There are small differences between the blitter and the video engines in
the xcs context image (e.g. registers 0x200 and 0x204 only exist on the
blitter). Since we never explicitly set a value for those register and
given that we don't need to update the offsets in the lrc image when we
change engine within the class for virtual engine because the HW can
handle that, instead of having a separate define for the BCS we can
just restrict the programming to the part we're interested in, which is
common across the engines.

Bspec: 45584
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Stuart Summers <stuart.summers@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191009230424.6507-2-daniele.ceraolospurio@intel.com
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 67 +++++--------------------------------
 1 file changed, 9 insertions(+), 58 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index eb061f345166..bdfd602b402a 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -669,64 +669,6 @@ static const u8 gen12_xcs_offsets[] = {
 	REG16(0x274),
 	REG16(0x270),
 
-	NOP(13),
-	LRI(2, POSTED),
-	REG16(0x200),
-	REG16(0x204),
-
-	NOP(11),
-	LRI(50, POSTED),
-	REG16(0x588),
-	REG16(0x588),
-	REG16(0x588),
-	REG16(0x588),
-	REG16(0x588),
-	REG16(0x588),
-	REG(0x028),
-	REG(0x09c),
-	REG(0x0c0),
-	REG(0x178),
-	REG(0x17c),
-	REG16(0x358),
-	REG(0x170),
-	REG(0x150),
-	REG(0x154),
-	REG(0x158),
-	REG16(0x41c),
-	REG16(0x600),
-	REG16(0x604),
-	REG16(0x608),
-	REG16(0x60c),
-	REG16(0x610),
-	REG16(0x614),
-	REG16(0x618),
-	REG16(0x61c),
-	REG16(0x620),
-	REG16(0x624),
-	REG16(0x628),
-	REG16(0x62c),
-	REG16(0x630),
-	REG16(0x634),
-	REG16(0x638),
-	REG16(0x63c),
-	REG16(0x640),
-	REG16(0x644),
-	REG16(0x648),
-	REG16(0x64c),
-	REG16(0x650),
-	REG16(0x654),
-	REG16(0x658),
-	REG16(0x65c),
-	REG16(0x660),
-	REG16(0x664),
-	REG16(0x668),
-	REG16(0x66c),
-	REG16(0x670),
-	REG16(0x674),
-	REG16(0x678),
-	REG16(0x67c),
-	REG(0x068),
-
 	END(),
 };
 
@@ -857,6 +799,15 @@ static const u8 gen12_rcs_offsets[] = {
 
 static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 {
+	/*
+	 * The gen12+ lists only have the registers we program in the basic
+	 * default state. We rely on the context image using relative
+	 * addressing to automatic fixup the register state between the
+	 * physical engines for virtual engine.
+	 */
+	GEM_BUG_ON(INTEL_GEN(engine->i915) >= 12 &&
+		   !intel_engine_has_relative_mmio(engine));
+
 	if (engine->class == RENDER_CLASS) {
 		if (INTEL_GEN(engine->i915) >= 12)
 			return gen12_rcs_offsets;
-- 
cgit v1.2.3


From fd70c7755bf0172ddd33b558aef69c322de3b5cf Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ti.com>
Date: Tue, 24 Sep 2019 16:17:02 +0300
Subject: drm/bridge: tc358767: fix max_tu_symbol value

max_tu_symbol was programmed to TU_SIZE_RECOMMENDED - 1, which is not
what the spec says. The spec says:

roundup ((input active video bandwidth in bytes/output active video
bandwidth in bytes) * tu_size)

It is not quite clear what the above means, but calculating
max_tu_symbol = (input Bps / output Bps) * tu_size seems to work and
fixes the issues seen.

This fixes artifacts in some videomodes (e.g. 1024x768@60 on 2-lanes &
1.62Gbps was pretty bad for me).

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Tested-by: Jyri Sarha <jsarha@ti.com>
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190924131702.9988-1-tomi.valkeinen@ti.com
---
 drivers/gpu/drm/bridge/tc358767.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index cebc8e620820..8a8d605021f0 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -728,6 +728,8 @@ static int tc_set_video_mode(struct tc_data *tc,
 	int lower_margin = mode->vsync_start - mode->vdisplay;
 	int vsync_len = mode->vsync_end - mode->vsync_start;
 	u32 dp0_syncval;
+	u32 bits_per_pixel = 24;
+	u32 in_bw, out_bw;
 
 	/*
 	 * Recommended maximum number of symbols transferred in a transfer unit:
@@ -735,7 +737,10 @@ static int tc_set_video_mode(struct tc_data *tc,
 	 *              (output active video bandwidth in bytes))
 	 * Must be less than tu_size.
 	 */
-	max_tu_symbol = TU_SIZE_RECOMMENDED - 1;
+
+	in_bw = mode->clock * bits_per_pixel / 8;
+	out_bw = tc->link.base.num_lanes * tc->link.base.rate;
+	max_tu_symbol = DIV_ROUND_UP(in_bw * TU_SIZE_RECOMMENDED, out_bw);
 
 	dev_dbg(tc->dev, "set mode %dx%d\n",
 		mode->hdisplay, mode->vdisplay);
-- 
cgit v1.2.3


From 542a5c66e0ff6cf257600df1d7362735f8ebde35 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 2 Oct 2019 17:00:34 +0100
Subject: drm/i915/gt: Warn CI about an unrecoverable wedge

If we have a wedged GPU that we need to recover, but fail, add a taint
for CI to pickup and schedule a reboot.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Petri Latvala <petri.latvala@intel.com>
Reviewed-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191002160034.5121-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_reset.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 34791fc79dea..77445d100ca8 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -872,8 +872,14 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	ok = !HAS_EXECLISTS(gt->i915); /* XXX better agnosticism desired */
 	if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display)
 		ok = __intel_gt_reset(gt, ALL_ENGINES) == 0;
-	if (!ok)
+	if (!ok) {
+		/*
+		 * Warn CI about the unrecoverable wedged condition.
+		 * Time for a reboot.
+		 */
+		add_taint_for_CI(TAINT_WARN);
 		return false;
+	}
 
 	/*
 	 * Undo nop_submit_request. We prevent all new i915 requests from
-- 
cgit v1.2.3


From bed5ef230943863b9abf5eae226a20fad9a8ff71 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 19:09:42 +0200
Subject: USB: usb-skeleton: fix NULL-deref on disconnect

The driver was using its struct usb_interface pointer as an inverted
disconnected flag and was setting it to NULL before making sure all
completion handlers had run. This could lead to NULL-pointer
dereferences in the dev_err() statements in the completion handlers
which relies on said pointer.

Fix this by using a dedicated disconnected flag.

Note that this is also addresses a NULL-pointer dereference at release()
and a struct usb_interface reference leak introduced by a recent runtime
PM fix, which depends on and should have been submitted together with
this patch.

Fixes: 4212cd74ca6f ("USB: usb-skeleton.c: remove err() usage")
Fixes: 5c290a5e42c3 ("USB: usb-skeleton: fix runtime PM after driver unbind")
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009170944.30057-2-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usb-skeleton.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/usb/usb-skeleton.c b/drivers/usb/usb-skeleton.c
index 8001d6384c73..c2843fcfa52d 100644
--- a/drivers/usb/usb-skeleton.c
+++ b/drivers/usb/usb-skeleton.c
@@ -61,6 +61,7 @@ struct usb_skel {
 	spinlock_t		err_lock;		/* lock for errors */
 	struct kref		kref;
 	struct mutex		io_mutex;		/* synchronize I/O with disconnect */
+	unsigned long		disconnected:1;
 	wait_queue_head_t	bulk_in_wait;		/* to wait for an ongoing read */
 };
 #define to_skel_dev(d) container_of(d, struct usb_skel, kref)
@@ -238,7 +239,7 @@ static ssize_t skel_read(struct file *file, char *buffer, size_t count,
 	if (rv < 0)
 		return rv;
 
-	if (!dev->interface) {		/* disconnect() was called */
+	if (dev->disconnected) {		/* disconnect() was called */
 		rv = -ENODEV;
 		goto exit;
 	}
@@ -420,7 +421,7 @@ static ssize_t skel_write(struct file *file, const char *user_buffer,
 
 	/* this lock makes sure we don't submit URBs to gone devices */
 	mutex_lock(&dev->io_mutex);
-	if (!dev->interface) {		/* disconnect() was called */
+	if (dev->disconnected) {		/* disconnect() was called */
 		mutex_unlock(&dev->io_mutex);
 		retval = -ENODEV;
 		goto error;
@@ -571,7 +572,7 @@ static void skel_disconnect(struct usb_interface *interface)
 
 	/* prevent more I/O from starting */
 	mutex_lock(&dev->io_mutex);
-	dev->interface = NULL;
+	dev->disconnected = 1;
 	mutex_unlock(&dev->io_mutex);
 
 	usb_kill_anchored_urbs(&dev->submitted);
-- 
cgit v1.2.3


From 6353001852776e7eeaab4da78922d4c6f2b076af Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 19:09:43 +0200
Subject: USB: usb-skeleton: fix use-after-free after driver unbind

The driver failed to stop its read URB on disconnect, something which
could lead to a use-after-free in the completion handler after driver
unbind in case the character device has been closed.

Fixes: e7389cc9a7ff ("USB: skel_read really sucks royally")
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009170944.30057-3-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usb-skeleton.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/usb-skeleton.c b/drivers/usb/usb-skeleton.c
index c2843fcfa52d..be311787403e 100644
--- a/drivers/usb/usb-skeleton.c
+++ b/drivers/usb/usb-skeleton.c
@@ -575,6 +575,7 @@ static void skel_disconnect(struct usb_interface *interface)
 	dev->disconnected = 1;
 	mutex_unlock(&dev->io_mutex);
 
+	usb_kill_urb(dev->bulk_in_urb);
 	usb_kill_anchored_urbs(&dev->submitted);
 
 	/* decrement our usage count */
-- 
cgit v1.2.3


From 369dca424a3f9ef80bc4e5a5ccdd41a17ce306c1 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 19:09:44 +0200
Subject: USB: usb-skeleton: drop redundant in-urb check

The driver bails out at probe if we can't find a bulk-in endpoint or
if we fail to allocate the URB, so drop the check in read().

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009170944.30057-4-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/usb-skeleton.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/usb/usb-skeleton.c b/drivers/usb/usb-skeleton.c
index be311787403e..2dc58766273a 100644
--- a/drivers/usb/usb-skeleton.c
+++ b/drivers/usb/usb-skeleton.c
@@ -230,8 +230,7 @@ static ssize_t skel_read(struct file *file, char *buffer, size_t count,
 
 	dev = file->private_data;
 
-	/* if we cannot read at all, return EOF */
-	if (!dev->bulk_in_urb || !count)
+	if (!count)
 		return 0;
 
 	/* no concurrent readers */
-- 
cgit v1.2.3


From ac9099e10a603f02f52f583fba78dd54c52b5542 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Mon, 7 Oct 2019 15:16:01 +0300
Subject: usb: cdns3: gadget: Fix full-speed mode

We need to disable USB3 PHY for full-speed mode else
gadget mode is broken.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
Reviewed-by: Peter Chen <peter.chen@nxp.com>
Link: https://lore.kernel.org/r/20191007121601.25996-3-rogerq@ti.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/gadget.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c
index 228cdc4ab886..157536753b8c 100644
--- a/drivers/usb/cdns3/gadget.c
+++ b/drivers/usb/cdns3/gadget.c
@@ -2571,6 +2571,7 @@ static int cdns3_gadget_start(struct cdns3 *cdns)
 	switch (max_speed) {
 	case USB_SPEED_FULL:
 		writel(USB_CONF_SFORCE_FS, &priv_dev->regs->usb_conf);
+		writel(USB_CONF_USB3DIS, &priv_dev->regs->usb_conf);
 		break;
 	case USB_SPEED_HIGH:
 		writel(USB_CONF_USB3DIS, &priv_dev->regs->usb_conf);
-- 
cgit v1.2.3


From 02ffc26df96b487f476b8945eaef13c7f170e79a Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@ti.com>
Date: Mon, 7 Oct 2019 15:16:00 +0300
Subject: usb: cdns3: fix cdns3_core_init_role()

At startup we should trigger the HW state machine
only if it is OTG mode. Otherwise we should just
start the respective role.

Initialize idle role by default. If we don't do this then
cdns3_idle_role_stop() is not called when switching to
host/device role and so lane switch mechanism
doesn't work. This results to super-speed device not working
in one orientation if it was plugged before driver probe.

Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
Link: https://lore.kernel.org/r/20191007121601.25996-2-rogerq@ti.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/core.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c
index 06f1e105be4e..1109dc5a4c39 100644
--- a/drivers/usb/cdns3/core.c
+++ b/drivers/usb/cdns3/core.c
@@ -160,10 +160,28 @@ static int cdns3_core_init_role(struct cdns3 *cdns)
 	if (ret)
 		goto err;
 
-	if (cdns->dr_mode != USB_DR_MODE_OTG) {
+	/* Initialize idle role to start with */
+	ret = cdns3_role_start(cdns, USB_ROLE_NONE);
+	if (ret)
+		goto err;
+
+	switch (cdns->dr_mode) {
+	case USB_DR_MODE_UNKNOWN:
+	case USB_DR_MODE_OTG:
 		ret = cdns3_hw_role_switch(cdns);
 		if (ret)
 			goto err;
+		break;
+	case USB_DR_MODE_PERIPHERAL:
+		ret = cdns3_role_start(cdns, USB_ROLE_DEVICE);
+		if (ret)
+			goto err;
+		break;
+	case USB_DR_MODE_HOST:
+		ret = cdns3_role_start(cdns, USB_ROLE_HOST);
+		if (ret)
+			goto err;
+		break;
 	}
 
 	return ret;
-- 
cgit v1.2.3


From eb21a74adaa11846737f503dd618bd35337e2c37 Mon Sep 17 00:00:00 2001
From: Pawel Laszczak <pawell@cadence.com>
Date: Mon, 7 Oct 2019 13:03:23 +0100
Subject: usb: cdns3: Fix for incorrect DMA mask.

This patch restores the correct DMA mask after switching back to device
mode.
The issue occurred because Device part of controller use 32 bits DMA and
Host side use 64 bits DMA. During loading XHCI driver the DMA mask
used by driver is overwritten by XHCI driver so it must be restored
to 32 bits.

Reported-by: Pawel Laszczak <pawell@cadence.com>
Signed-off-by: Roger Quadros <rogerq@ti.com>
Signed-off-by: Pawel Laszczak <pawell@cadence.com>
Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver")
Reviewed-by: Peter Chen <peter.chen@nxp.com>
Tested-by: Roger Quadros <rogerq@ti.com>
Link: https://lore.kernel.org/r/1570449803-15299-1-git-send-email-pawell@cadence.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/cdns3/gadget.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c
index 157536753b8c..2ca280f4c054 100644
--- a/drivers/usb/cdns3/gadget.c
+++ b/drivers/usb/cdns3/gadget.c
@@ -2663,6 +2663,13 @@ static int __cdns3_gadget_init(struct cdns3 *cdns)
 {
 	int ret = 0;
 
+	/* Ensure 32-bit DMA Mask in case we switched back from Host mode */
+	ret = dma_set_mask_and_coherent(cdns->dev, DMA_BIT_MASK(32));
+	if (ret) {
+		dev_err(cdns->dev, "Failed to set dma mask: %d\n", ret);
+		return ret;
+	}
+
 	cdns3_drd_switch_gadget(cdns, 1);
 	pm_runtime_get_sync(cdns->dev);
 
-- 
cgit v1.2.3


From 726b55d0e22ca72c69c947af87785c830289ddbc Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 17:38:47 +0200
Subject: USB: legousbtower: fix use-after-free on release

The driver was accessing its struct usb_device in its release()
callback without holding a reference. This would lead to a
use-after-free whenever the device was disconnected while the character
device was still open.

Fixes: fef526cae700 ("USB: legousbtower: remove custom debug macro")
Cc: stable <stable@vger.kernel.org>     # 3.12
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009153848.8664-5-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/legousbtower.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c
index 44d6a3381804..9d4c52a7ebe0 100644
--- a/drivers/usb/misc/legousbtower.c
+++ b/drivers/usb/misc/legousbtower.c
@@ -296,6 +296,7 @@ static inline void tower_delete (struct lego_usb_tower *dev)
 	kfree (dev->read_buffer);
 	kfree (dev->interrupt_in_buffer);
 	kfree (dev->interrupt_out_buffer);
+	usb_put_dev(dev->udev);
 	kfree (dev);
 }
 
@@ -810,7 +811,7 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device
 
 	mutex_init(&dev->lock);
 
-	dev->udev = udev;
+	dev->udev = usb_get_dev(udev);
 	dev->open_count = 0;
 	dev->disconnected = 0;
 
-- 
cgit v1.2.3


From 58ecf131e74620305175a7aa103f81350bb37570 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 17:38:46 +0200
Subject: USB: ldusb: fix NULL-derefs on driver unbind

The driver was using its struct usb_interface pointer as an inverted
disconnected flag, but was setting it to NULL before making sure all
completion handlers had run. This could lead to a NULL-pointer
dereference in a number of dev_dbg, dev_warn and dev_err statements in
the completion handlers which relies on said pointer.

Fix this by unconditionally stopping all I/O and preventing
resubmissions by poisoning the interrupt URBs at disconnect and using a
dedicated disconnected flag.

This also makes sure that all I/O has completed by the time the
disconnect callback returns.

Fixes: 2824bd250f0b ("[PATCH] USB: add ldusb driver")
Cc: stable <stable@vger.kernel.org>     # 2.6.13
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009153848.8664-4-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/ldusb.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c
index 6581774bdfa4..f3108d85e768 100644
--- a/drivers/usb/misc/ldusb.c
+++ b/drivers/usb/misc/ldusb.c
@@ -153,6 +153,7 @@ MODULE_PARM_DESC(min_interrupt_out_interval, "Minimum interrupt out interval in
 struct ld_usb {
 	struct mutex		mutex;		/* locks this structure */
 	struct usb_interface	*intf;		/* save off the usb interface pointer */
+	unsigned long		disconnected:1;
 
 	int			open_count;	/* number of times this port has been opened */
 
@@ -192,12 +193,10 @@ static void ld_usb_abort_transfers(struct ld_usb *dev)
 	/* shutdown transfer */
 	if (dev->interrupt_in_running) {
 		dev->interrupt_in_running = 0;
-		if (dev->intf)
-			usb_kill_urb(dev->interrupt_in_urb);
+		usb_kill_urb(dev->interrupt_in_urb);
 	}
 	if (dev->interrupt_out_busy)
-		if (dev->intf)
-			usb_kill_urb(dev->interrupt_out_urb);
+		usb_kill_urb(dev->interrupt_out_urb);
 }
 
 /**
@@ -205,8 +204,6 @@ static void ld_usb_abort_transfers(struct ld_usb *dev)
  */
 static void ld_usb_delete(struct ld_usb *dev)
 {
-	ld_usb_abort_transfers(dev);
-
 	/* free data structures */
 	usb_free_urb(dev->interrupt_in_urb);
 	usb_free_urb(dev->interrupt_out_urb);
@@ -263,7 +260,7 @@ static void ld_usb_interrupt_in_callback(struct urb *urb)
 
 resubmit:
 	/* resubmit if we're still running */
-	if (dev->interrupt_in_running && !dev->buffer_overflow && dev->intf) {
+	if (dev->interrupt_in_running && !dev->buffer_overflow) {
 		retval = usb_submit_urb(dev->interrupt_in_urb, GFP_ATOMIC);
 		if (retval) {
 			dev_err(&dev->intf->dev,
@@ -392,7 +389,7 @@ static int ld_usb_release(struct inode *inode, struct file *file)
 		retval = -ENODEV;
 		goto unlock_exit;
 	}
-	if (dev->intf == NULL) {
+	if (dev->disconnected) {
 		/* the device was unplugged before the file was released */
 		mutex_unlock(&dev->mutex);
 		/* unlock here as ld_usb_delete frees dev */
@@ -423,7 +420,7 @@ static __poll_t ld_usb_poll(struct file *file, poll_table *wait)
 
 	dev = file->private_data;
 
-	if (!dev->intf)
+	if (dev->disconnected)
 		return EPOLLERR | EPOLLHUP;
 
 	poll_wait(file, &dev->read_wait, wait);
@@ -462,7 +459,7 @@ static ssize_t ld_usb_read(struct file *file, char __user *buffer, size_t count,
 	}
 
 	/* verify that the device wasn't unplugged */
-	if (dev->intf == NULL) {
+	if (dev->disconnected) {
 		retval = -ENODEV;
 		printk(KERN_ERR "ldusb: No device or device unplugged %d\n", retval);
 		goto unlock_exit;
@@ -542,7 +539,7 @@ static ssize_t ld_usb_write(struct file *file, const char __user *buffer,
 	}
 
 	/* verify that the device wasn't unplugged */
-	if (dev->intf == NULL) {
+	if (dev->disconnected) {
 		retval = -ENODEV;
 		printk(KERN_ERR "ldusb: No device or device unplugged %d\n", retval);
 		goto unlock_exit;
@@ -764,6 +761,9 @@ static void ld_usb_disconnect(struct usb_interface *intf)
 	/* give back our minor */
 	usb_deregister_dev(intf, &ld_usb_class);
 
+	usb_poison_urb(dev->interrupt_in_urb);
+	usb_poison_urb(dev->interrupt_out_urb);
+
 	mutex_lock(&dev->mutex);
 
 	/* if the device is not opened, then we clean up right now */
@@ -771,7 +771,7 @@ static void ld_usb_disconnect(struct usb_interface *intf)
 		mutex_unlock(&dev->mutex);
 		ld_usb_delete(dev);
 	} else {
-		dev->intf = NULL;
+		dev->disconnected = 1;
 		/* wake up pollers */
 		wake_up_interruptible_all(&dev->read_wait);
 		wake_up_interruptible_all(&dev->write_wait);
-- 
cgit v1.2.3


From 123a0f125fa3d2104043697baa62899d9e549272 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 17:38:44 +0200
Subject: USB: adutux: fix use-after-free on release

The driver was accessing its struct usb_device in its release()
callback without holding a reference. This would lead to a
use-after-free whenever the device was disconnected while the character
device was still open.

Fixes: 66d4bc30d128 ("USB: adutux: remove custom debug macro")
Cc: stable <stable@vger.kernel.org>     # 3.12
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009153848.8664-2-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/adutux.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/misc/adutux.c b/drivers/usb/misc/adutux.c
index f9efec719359..6f5edb9fc61e 100644
--- a/drivers/usb/misc/adutux.c
+++ b/drivers/usb/misc/adutux.c
@@ -149,6 +149,7 @@ static void adu_delete(struct adu_device *dev)
 	kfree(dev->read_buffer_secondary);
 	kfree(dev->interrupt_in_buffer);
 	kfree(dev->interrupt_out_buffer);
+	usb_put_dev(dev->udev);
 	kfree(dev);
 }
 
@@ -664,7 +665,7 @@ static int adu_probe(struct usb_interface *interface,
 
 	mutex_init(&dev->mtx);
 	spin_lock_init(&dev->buflock);
-	dev->udev = udev;
+	dev->udev = usb_get_dev(udev);
 	init_waitqueue_head(&dev->read_wait);
 	init_waitqueue_head(&dev->write_wait);
 
-- 
cgit v1.2.3


From 93ddb1f56ae102f14f9e46a9a9c8017faa970003 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 17:38:45 +0200
Subject: USB: chaoskey: fix use-after-free on release

The driver was accessing its struct usb_interface in its release()
callback without holding a reference. This would lead to a
use-after-free whenever the device was disconnected while the character
device was still open.

Fixes: 66e3e591891d ("usb: Add driver for Altus Metrum ChaosKey device (v2)")
Cc: stable <stable@vger.kernel.org>     # 4.1
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009153848.8664-3-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/chaoskey.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/misc/chaoskey.c b/drivers/usb/misc/chaoskey.c
index cf5828ce927a..34e6cd6f40d3 100644
--- a/drivers/usb/misc/chaoskey.c
+++ b/drivers/usb/misc/chaoskey.c
@@ -98,6 +98,7 @@ static void chaoskey_free(struct chaoskey *dev)
 		usb_free_urb(dev->urb);
 		kfree(dev->name);
 		kfree(dev->buf);
+		usb_put_intf(dev->interface);
 		kfree(dev);
 	}
 }
@@ -145,6 +146,8 @@ static int chaoskey_probe(struct usb_interface *interface,
 	if (dev == NULL)
 		goto out;
 
+	dev->interface = usb_get_intf(interface);
+
 	dev->buf = kmalloc(size, GFP_KERNEL);
 
 	if (dev->buf == NULL)
@@ -174,8 +177,6 @@ static int chaoskey_probe(struct usb_interface *interface,
 			goto out;
 	}
 
-	dev->interface = interface;
-
 	dev->in_ep = in_ep;
 
 	if (le16_to_cpu(udev->descriptor.idVendor) != ALEA_VENDOR_ID)
-- 
cgit v1.2.3


From edc4746f253d907d048de680a621e121517f484b Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 12:48:41 +0200
Subject: USB: iowarrior: fix use-after-free on disconnect

A recent fix addressing a deadlock on disconnect introduced a new bug
by moving the present flag out of the critical section protected by the
driver-data mutex. This could lead to a racing release() freeing the
driver data before disconnect() is done with it.

Due to insufficient locking a related use-after-free could be triggered
also before the above mentioned commit. Specifically, the driver needs
to hold the driver-data mutex also while checking the opened flag at
disconnect().

Fixes: c468a8aa790e ("usb: iowarrior: fix deadlock on disconnect")
Fixes: 946b960d13c1 ("USB: add driver for iowarrior devices.")
Cc: stable <stable@vger.kernel.org>	# 2.6.21
Reported-by: syzbot+0761012cebf7bdb38137@syzkaller.appspotmail.com
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009104846.5925-2-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/iowarrior.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index f5bed9f29e56..4fe1d3267b3c 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -866,8 +866,6 @@ static void iowarrior_disconnect(struct usb_interface *interface)
 	dev = usb_get_intfdata(interface);
 	mutex_lock(&iowarrior_open_disc_lock);
 	usb_set_intfdata(interface, NULL);
-	/* prevent device read, write and ioctl */
-	dev->present = 0;
 
 	minor = dev->minor;
 	mutex_unlock(&iowarrior_open_disc_lock);
@@ -878,8 +876,7 @@ static void iowarrior_disconnect(struct usb_interface *interface)
 	mutex_lock(&dev->mutex);
 
 	/* prevent device read, write and ioctl */
-
-	mutex_unlock(&dev->mutex);
+	dev->present = 0;
 
 	if (dev->opened) {
 		/* There is a process that holds a filedescriptor to the device ,
@@ -889,8 +886,10 @@ static void iowarrior_disconnect(struct usb_interface *interface)
 		usb_kill_urb(dev->int_in_urb);
 		wake_up_interruptible(&dev->read_wait);
 		wake_up_interruptible(&dev->write_wait);
+		mutex_unlock(&dev->mutex);
 	} else {
 		/* no process is using the device, cleanup now */
+		mutex_unlock(&dev->mutex);
 		iowarrior_delete(dev);
 	}
 
-- 
cgit v1.2.3


From 80cd5479b525093a56ef768553045741af61b250 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 12:48:42 +0200
Subject: USB: iowarrior: fix use-after-free on release

The driver was accessing its struct usb_interface from its release()
callback without holding a reference. This would lead to a
use-after-free whenever debugging was enabled and the device was
disconnected while its character device was open.

Fixes: 549e83500b80 ("USB: iowarrior: Convert local dbg macro to dev_dbg")
Cc: stable <stable@vger.kernel.org>     # 3.16
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009104846.5925-3-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/iowarrior.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index 4fe1d3267b3c..6841267820c6 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -243,6 +243,7 @@ static inline void iowarrior_delete(struct iowarrior *dev)
 	kfree(dev->int_in_buffer);
 	usb_free_urb(dev->int_in_urb);
 	kfree(dev->read_queue);
+	usb_put_intf(dev->interface);
 	kfree(dev);
 }
 
@@ -764,7 +765,7 @@ static int iowarrior_probe(struct usb_interface *interface,
 	init_waitqueue_head(&dev->write_wait);
 
 	dev->udev = udev;
-	dev->interface = interface;
+	dev->interface = usb_get_intf(interface);
 
 	iface_desc = interface->cur_altsetting;
 	dev->product_id = le16_to_cpu(udev->descriptor.idProduct);
-- 
cgit v1.2.3


From b5f8d46867ca233d773408ffbe691a8062ed718f Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 12:48:43 +0200
Subject: USB: iowarrior: fix use-after-free after driver unbind

Make sure to stop also the asynchronous write URBs on disconnect() to
avoid use-after-free in the completion handler after driver unbind.

Fixes: 946b960d13c1 ("USB: add driver for iowarrior devices.")
Cc: stable <stable@vger.kernel.org>	# 2.6.21: 51a2f077c44e ("USB: introduce usb_anchor")
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009104846.5925-4-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/iowarrior.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index 6841267820c6..f405fa734bcc 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -87,6 +87,7 @@ struct iowarrior {
 	char chip_serial[9];		/* the serial number string of the chip connected */
 	int report_size;		/* number of bytes in a report */
 	u16 product_id;
+	struct usb_anchor submitted;
 };
 
 /*--------------*/
@@ -425,11 +426,13 @@ static ssize_t iowarrior_write(struct file *file,
 			retval = -EFAULT;
 			goto error;
 		}
+		usb_anchor_urb(int_out_urb, &dev->submitted);
 		retval = usb_submit_urb(int_out_urb, GFP_KERNEL);
 		if (retval) {
 			dev_dbg(&dev->interface->dev,
 				"submit error %d for urb nr.%d\n",
 				retval, atomic_read(&dev->write_busy));
+			usb_unanchor_urb(int_out_urb);
 			goto error;
 		}
 		/* submit was ok */
@@ -770,6 +773,8 @@ static int iowarrior_probe(struct usb_interface *interface,
 	iface_desc = interface->cur_altsetting;
 	dev->product_id = le16_to_cpu(udev->descriptor.idProduct);
 
+	init_usb_anchor(&dev->submitted);
+
 	res = usb_find_last_int_in_endpoint(iface_desc, &dev->int_in_endpoint);
 	if (res) {
 		dev_err(&interface->dev, "no interrupt-in endpoint found\n");
@@ -885,6 +890,7 @@ static void iowarrior_disconnect(struct usb_interface *interface)
 		   Deleting the device is postponed until close() was called.
 		 */
 		usb_kill_urb(dev->int_in_urb);
+		usb_kill_anchored_urbs(&dev->submitted);
 		wake_up_interruptible(&dev->read_wait);
 		wake_up_interruptible(&dev->write_wait);
 		mutex_unlock(&dev->mutex);
-- 
cgit v1.2.3


From 7c5b971d623fdb40c03205e99f9ef68002b34726 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 12:48:44 +0200
Subject: USB: iowarrior: drop redundant disconnect mutex

Drop the redundant disconnect mutex which was introduced after the
open-disconnect race had been addressed generally in USB core by commit
d4ead16f50f9 ("USB: prevent char device open/deregister race").

Specifically, the rw-semaphore in core guarantees that all calls to
open() will have completed and that no new calls to open() will occur
after usb_deregister_dev() returns. Hence there is no need use the
driver data as an inverted disconnected flag.

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009104846.5925-5-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/iowarrior.c | 17 ++---------------
 1 file changed, 2 insertions(+), 15 deletions(-)

diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index f405fa734bcc..d844c2098e42 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -58,7 +58,6 @@ MODULE_LICENSE("GPL");
 static DEFINE_MUTEX(iowarrior_mutex);
 
 static struct usb_driver iowarrior_driver;
-static DEFINE_MUTEX(iowarrior_open_disc_lock);
 
 /*--------------*/
 /*     data     */
@@ -601,16 +600,13 @@ static int iowarrior_open(struct inode *inode, struct file *file)
 		return -ENODEV;
 	}
 
-	mutex_lock(&iowarrior_open_disc_lock);
 	dev = usb_get_intfdata(interface);
 	if (!dev) {
-		mutex_unlock(&iowarrior_open_disc_lock);
 		mutex_unlock(&iowarrior_mutex);
 		return -ENODEV;
 	}
 
 	mutex_lock(&dev->mutex);
-	mutex_unlock(&iowarrior_open_disc_lock);
 
 	/* Only one process can open each device, no sharing. */
 	if (dev->opened) {
@@ -842,7 +838,6 @@ static int iowarrior_probe(struct usb_interface *interface,
 	if (retval) {
 		/* something prevented us from registering this driver */
 		dev_err(&interface->dev, "Not able to get a minor for this device.\n");
-		usb_set_intfdata(interface, NULL);
 		goto error;
 	}
 
@@ -866,16 +861,8 @@ error:
  */
 static void iowarrior_disconnect(struct usb_interface *interface)
 {
-	struct iowarrior *dev;
-	int minor;
-
-	dev = usb_get_intfdata(interface);
-	mutex_lock(&iowarrior_open_disc_lock);
-	usb_set_intfdata(interface, NULL);
-
-	minor = dev->minor;
-	mutex_unlock(&iowarrior_open_disc_lock);
-	/* give back our minor - this will call close() locks need to be dropped at this point*/
+	struct iowarrior *dev = usb_get_intfdata(interface);
+	int minor = dev->minor;
 
 	usb_deregister_dev(interface, &iowarrior_class);
 
-- 
cgit v1.2.3


From 8d33e828f72c216ae264ad39088a595d9a6cc95c Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 12:48:45 +0200
Subject: USB: iowarrior: drop redundant iowarrior mutex

Drop the redundant iowarrior mutex introduced by commit 925ce689bb31
("USB: autoconvert trivial BKL users to private mutex") which replaced
an earlier BKL use.

The lock serialised calls to open() against other open() and ioctl(),
but neither is needed.

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009104846.5925-6-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/iowarrior.c | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index d844c2098e42..ad29ef51e53f 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -54,9 +54,6 @@ MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
 
-/* Module parameters */
-static DEFINE_MUTEX(iowarrior_mutex);
-
 static struct usb_driver iowarrior_driver;
 
 /*--------------*/
@@ -480,8 +477,6 @@ static long iowarrior_ioctl(struct file *file, unsigned int cmd,
 	if (!buffer)
 		return -ENOMEM;
 
-	/* lock this object */
-	mutex_lock(&iowarrior_mutex);
 	mutex_lock(&dev->mutex);
 
 	/* verify that the device wasn't unplugged */
@@ -574,7 +569,6 @@ static long iowarrior_ioctl(struct file *file, unsigned int cmd,
 error_out:
 	/* unlock the device */
 	mutex_unlock(&dev->mutex);
-	mutex_unlock(&iowarrior_mutex);
 	kfree(buffer);
 	return retval;
 }
@@ -589,22 +583,18 @@ static int iowarrior_open(struct inode *inode, struct file *file)
 	int subminor;
 	int retval = 0;
 
-	mutex_lock(&iowarrior_mutex);
 	subminor = iminor(inode);
 
 	interface = usb_find_interface(&iowarrior_driver, subminor);
 	if (!interface) {
-		mutex_unlock(&iowarrior_mutex);
 		printk(KERN_ERR "%s - error, can't find device for minor %d\n",
 		       __func__, subminor);
 		return -ENODEV;
 	}
 
 	dev = usb_get_intfdata(interface);
-	if (!dev) {
-		mutex_unlock(&iowarrior_mutex);
+	if (!dev)
 		return -ENODEV;
-	}
 
 	mutex_lock(&dev->mutex);
 
@@ -628,7 +618,6 @@ static int iowarrior_open(struct inode *inode, struct file *file)
 
 out:
 	mutex_unlock(&dev->mutex);
-	mutex_unlock(&iowarrior_mutex);
 	return retval;
 }
 
-- 
cgit v1.2.3


From ebb2fe57a51c630e0f852becbbdd295ad5d60514 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 12:48:46 +0200
Subject: USB: iowarrior: use pr_err()

Replace the one remaining printk with pr_err().

Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009104846.5925-7-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/iowarrior.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index ad29ef51e53f..dce44fbf031f 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -587,7 +587,7 @@ static int iowarrior_open(struct inode *inode, struct file *file)
 
 	interface = usb_find_interface(&iowarrior_driver, subminor);
 	if (!interface) {
-		printk(KERN_ERR "%s - error, can't find device for minor %d\n",
+		pr_err("%s - error, can't find device for minor %d\n",
 		       __func__, subminor);
 		return -ENODEV;
 	}
-- 
cgit v1.2.3


From ff30283a8de4f978dad120936c1af507d01a6a98 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 8 Oct 2019 13:46:53 -0700
Subject: serial: fix kernel-doc warning in comments

Fix Sphinx warning in serial_core.c:

../drivers/tty/serial/serial_core.c:1969: WARNING: Definition list ends without a blank line; unexpected unindent.

Fixes: 73abaf87f01b ("serial: earlycon: Refactor parse_options into serial core")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Peter Hurley <peter@hurleysoftware.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/e989641c-224a-1090-e596-e7cc800bed44@infradead.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/serial_core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 6e713be1d4e9..c4a414a46c7f 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1964,8 +1964,10 @@ uart_get_console(struct uart_port *ports, int nr, struct console *co)
  *	   console=<name>,io|mmio|mmio16|mmio32|mmio32be|mmio32native,<addr>,<options>
  *
  *	The optional form
+ *
  *	   earlycon=<name>,0x<addr>,<options>
  *	   console=<name>,0x<addr>,<options>
+ *
  *	is also accepted; the returned @iotype will be UPIO_MEM.
  *
  *	Returns 0 on success or -EINVAL on failure
-- 
cgit v1.2.3


From 31a8d8fa84c51d3ab00bf059158d5de6178cf890 Mon Sep 17 00:00:00 2001
From: Anson Huang <Anson.Huang@nxp.com>
Date: Wed, 9 Oct 2019 17:49:19 +0800
Subject: tty: serial: imx: Use platform_get_irq_optional() for optional IRQs

All i.MX SoCs except i.MX1 have ONLY one necessary IRQ, use
platform_get_irq_optional() to get second/third IRQ which are
optional to avoid below error message during probe:

[    0.726219] imx-uart 30860000.serial: IRQ index 1 not found
[    0.731329] imx-uart 30860000.serial: IRQ index 2 not found

Fixes: 7723f4c5ecdb8d83 ("driver core: platform: Add an error message to platform_get_irq*()")
Signed-off-by: Anson Huang <Anson.Huang@nxp.com>
Link: https://lore.kernel.org/r/1570614559-11900-1-git-send-email-Anson.Huang@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/imx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 87c58f9f6390..5e08f2657b90 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -2222,8 +2222,8 @@ static int imx_uart_probe(struct platform_device *pdev)
 		return PTR_ERR(base);
 
 	rxirq = platform_get_irq(pdev, 0);
-	txirq = platform_get_irq(pdev, 1);
-	rtsirq = platform_get_irq(pdev, 2);
+	txirq = platform_get_irq_optional(pdev, 1);
+	rtsirq = platform_get_irq_optional(pdev, 2);
 
 	sport->port.dev = &pdev->dev;
 	sport->port.mapbase = res->start;
-- 
cgit v1.2.3


From 18380f52dbac230032a16545e67a6d90b548cf18 Mon Sep 17 00:00:00 2001
From: yu kuai <yukuai3@huawei.com>
Date: Sun, 29 Sep 2019 21:42:49 +0800
Subject: platform/x86: classmate-laptop: remove unused variable

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/platform/x86/classmate-laptop.c: In function cmpc_accel_remove_v4:
drivers/platform/x86/classmate-laptop.c:424:21: warning: variable accel
set but not used [-Wunused-but-set-variable]
drivers/platform/x86/classmate-laptop.c: In function cmpc_accel_remove:
drivers/platform/x86/classmate-laptop.c:660:21: warning: variable accel
set but not used [-Wunused-but-set-variable]

In function cmpc_accel_remove_v4 and cmpc_accel_remove, variable accel is
set but not used, so it can be removed. In that case, variable inputdev is
set but not used and can be removed.

Fixes: 7125587df4e8 ("classmate-laptop: Add support for Classmate V4 accelerometer.")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: yu kuai <yukuai3@huawei.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/platform/x86/classmate-laptop.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/platform/x86/classmate-laptop.c b/drivers/platform/x86/classmate-laptop.c
index 86cc2cc68fb5..af063f690846 100644
--- a/drivers/platform/x86/classmate-laptop.c
+++ b/drivers/platform/x86/classmate-laptop.c
@@ -420,12 +420,6 @@ failed_sensitivity:
 
 static int cmpc_accel_remove_v4(struct acpi_device *acpi)
 {
-	struct input_dev *inputdev;
-	struct cmpc_accel *accel;
-
-	inputdev = dev_get_drvdata(&acpi->dev);
-	accel = dev_get_drvdata(&inputdev->dev);
-
 	device_remove_file(&acpi->dev, &cmpc_accel_sensitivity_attr_v4);
 	device_remove_file(&acpi->dev, &cmpc_accel_g_select_attr_v4);
 	return cmpc_remove_acpi_notify_device(acpi);
@@ -656,12 +650,6 @@ failed_file:
 
 static int cmpc_accel_remove(struct acpi_device *acpi)
 {
-	struct input_dev *inputdev;
-	struct cmpc_accel *accel;
-
-	inputdev = dev_get_drvdata(&acpi->dev);
-	accel = dev_get_drvdata(&inputdev->dev);
-
 	device_remove_file(&acpi->dev, &cmpc_accel_sensitivity_attr);
 	return cmpc_remove_acpi_notify_device(acpi);
 }
-- 
cgit v1.2.3


From 71eea7071583b04e9b796ee1d6f7a07334426495 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 10 Oct 2019 11:15:20 +0300
Subject: platform/x86: intel_punit_ipc: Avoid error message when retrieving
 IRQ

Since the commit

  7723f4c5ecdb ("driver core: platform: Add an error message to platform_get_irq*()")

the platform_get_irq() started issuing an error message which is not
what we want here.

Switch to platform_get_irq_optional() to have only warning message
provided by the driver.

Fixes: 7723f4c5ecdb ("driver core: platform: Add an error message to platform_get_irq*()")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
---
 drivers/platform/x86/intel_punit_ipc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/platform/x86/intel_punit_ipc.c b/drivers/platform/x86/intel_punit_ipc.c
index ab7ae1950867..fa97834fdb78 100644
--- a/drivers/platform/x86/intel_punit_ipc.c
+++ b/drivers/platform/x86/intel_punit_ipc.c
@@ -293,9 +293,8 @@ static int intel_punit_ipc_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, punit_ipcdev);
 
-	irq = platform_get_irq(pdev, 0);
+	irq = platform_get_irq_optional(pdev, 0);
 	if (irq < 0) {
-		punit_ipcdev->irq = 0;
 		dev_warn(&pdev->dev, "Invalid IRQ, using polling mode\n");
 	} else {
 		ret = devm_request_irq(&pdev->dev, irq, intel_punit_ioc,
-- 
cgit v1.2.3


From aafb00a977cf7d81821f7c9d12e04c558c22dc3c Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Wed, 9 Oct 2019 17:38:48 +0200
Subject: USB: yurex: fix NULL-derefs on disconnect

The driver was using its struct usb_interface pointer as an inverted
disconnected flag, but was setting it to NULL without making sure all
code paths that used it were done with it.

Before commit ef61eb43ada6 ("USB: yurex: Fix protection fault after
device removal") this included the interrupt-in completion handler, but
there are further accesses in dev_err and dev_dbg statements in
yurex_write() and the driver-data destructor (sic!).

Fix this by unconditionally stopping also the control URB at disconnect
and by using a dedicated disconnected flag.

Note that we need to take a reference to the struct usb_interface to
avoid a use-after-free in the destructor whenever the device was
disconnected while the character device was still open.

Fixes: aadd6472d904 ("USB: yurex.c: remove dbg() usage")
Fixes: 45714104b9e8 ("USB: yurex.c: remove err() usage")
Cc: stable <stable@vger.kernel.org>     # 3.5: ef61eb43ada6
Signed-off-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/r/20191009153848.8664-6-johan@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/misc/yurex.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 8d52d4336c29..be0505b8b5d4 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -60,6 +60,7 @@ struct usb_yurex {
 
 	struct kref		kref;
 	struct mutex		io_mutex;
+	unsigned long		disconnected:1;
 	struct fasync_struct	*async_queue;
 	wait_queue_head_t	waitq;
 
@@ -107,6 +108,7 @@ static void yurex_delete(struct kref *kref)
 				dev->int_buffer, dev->urb->transfer_dma);
 		usb_free_urb(dev->urb);
 	}
+	usb_put_intf(dev->interface);
 	usb_put_dev(dev->udev);
 	kfree(dev);
 }
@@ -205,7 +207,7 @@ static int yurex_probe(struct usb_interface *interface, const struct usb_device_
 	init_waitqueue_head(&dev->waitq);
 
 	dev->udev = usb_get_dev(interface_to_usbdev(interface));
-	dev->interface = interface;
+	dev->interface = usb_get_intf(interface);
 
 	/* set up the endpoint information */
 	iface_desc = interface->cur_altsetting;
@@ -316,8 +318,9 @@ static void yurex_disconnect(struct usb_interface *interface)
 
 	/* prevent more I/O from starting */
 	usb_poison_urb(dev->urb);
+	usb_poison_urb(dev->cntl_urb);
 	mutex_lock(&dev->io_mutex);
-	dev->interface = NULL;
+	dev->disconnected = 1;
 	mutex_unlock(&dev->io_mutex);
 
 	/* wakeup waiters */
@@ -405,7 +408,7 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count,
 	dev = file->private_data;
 
 	mutex_lock(&dev->io_mutex);
-	if (!dev->interface) {		/* already disconnected */
+	if (dev->disconnected) {		/* already disconnected */
 		mutex_unlock(&dev->io_mutex);
 		return -ENODEV;
 	}
@@ -440,7 +443,7 @@ static ssize_t yurex_write(struct file *file, const char __user *user_buffer,
 		goto error;
 
 	mutex_lock(&dev->io_mutex);
-	if (!dev->interface) {		/* already disconnected */
+	if (dev->disconnected) {		/* already disconnected */
 		mutex_unlock(&dev->io_mutex);
 		retval = -ENODEV;
 		goto error;
-- 
cgit v1.2.3


From 51d8a7eca67784b155a07aeab4bfb9f63ebaaf9e Mon Sep 17 00:00:00 2001
From: Christian Brauner <christian.brauner@ubuntu.com>
Date: Tue, 8 Oct 2019 15:01:59 +0200
Subject: binder: prevent UAF read in print_binder_transaction_log_entry()

When a binder transaction is initiated on a binder device coming from a
binderfs instance, a pointer to the name of the binder device is stashed
in the binder_transaction_log_entry's context_name member. Later on it
is used to print the name in print_binder_transaction_log_entry(). By
the time print_binder_transaction_log_entry() accesses context_name
binderfs_evict_inode() might have already freed the associated memory
thereby causing a UAF. Do the simple thing and prevent this by copying
the name of the binder device instead of stashing a pointer to it.

Reported-by: Jann Horn <jannh@google.com>
Fixes: 03e2e07e3814 ("binder: Make transaction_log available in binderfs")
Link: https://lore.kernel.org/r/CAG48ez14Q0-F8LqsvcNbyR2o6gPW8SHXsm4u5jmD9MpsteM2Tw@mail.gmail.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Acked-by: Todd Kjos <tkjos@google.com>
Reviewed-by: Hridya Valsaraju <hridya@google.com>
Link: https://lore.kernel.org/r/20191008130159.10161-1-christian.brauner@ubuntu.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder.c          | 4 +++-
 drivers/android/binder_internal.h | 2 +-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index c0a491277aca..5b9ac2122e89 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -57,6 +57,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/mm.h>
 #include <linux/seq_file.h>
+#include <linux/string.h>
 #include <linux/uaccess.h>
 #include <linux/pid_namespace.h>
 #include <linux/security.h>
@@ -66,6 +67,7 @@
 #include <linux/task_work.h>
 
 #include <uapi/linux/android/binder.h>
+#include <uapi/linux/android/binderfs.h>
 
 #include <asm/cacheflush.h>
 
@@ -2876,7 +2878,7 @@ static void binder_transaction(struct binder_proc *proc,
 	e->target_handle = tr->target.handle;
 	e->data_size = tr->data_size;
 	e->offsets_size = tr->offsets_size;
-	e->context_name = proc->context->name;
+	strscpy(e->context_name, proc->context->name, BINDERFS_MAX_NAME);
 
 	if (reply) {
 		binder_inner_proc_lock(proc);
diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h
index bd47f7f72075..ae991097d14d 100644
--- a/drivers/android/binder_internal.h
+++ b/drivers/android/binder_internal.h
@@ -130,7 +130,7 @@ struct binder_transaction_log_entry {
 	int return_error_line;
 	uint32_t return_error;
 	uint32_t return_error_param;
-	const char *context_name;
+	char context_name[BINDERFS_MAX_NAME + 1];
 };
 
 struct binder_transaction_log {
-- 
cgit v1.2.3


From 5dc54a06f6e575f146492661129d24f3b50d17bb Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Mon, 30 Sep 2019 16:12:50 -0400
Subject: binder: Fix comment headers on binder_alloc_prepare_to_free()

binder_alloc_buffer_lookup() doesn't exist and is named
"binder_alloc_prepare_to_free()". Correct the code comments to reflect
this.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Reviewed-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20190930201250.139554-1-joel@joelfernandes.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binder_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 6d79a1b0d446..d42a8b2f636a 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -156,7 +156,7 @@ static struct binder_buffer *binder_alloc_prepare_to_free_locked(
 }
 
 /**
- * binder_alloc_buffer_lookup() - get buffer given user ptr
+ * binder_alloc_prepare_to_free() - get buffer given user ptr
  * @alloc:	binder_alloc for this proc
  * @user_ptr:	User pointer to buffer data
  *
-- 
cgit v1.2.3


From e0b0cb9388642c104838fac100a4af32745621e2 Mon Sep 17 00:00:00 2001
From: Navid Emamdoost <navid.emamdoost@gmail.com>
Date: Mon, 30 Sep 2019 15:42:22 -0500
Subject: virt: vbox: fix memory leak in hgcm_call_preprocess_linaddr

In hgcm_call_preprocess_linaddr memory is allocated for bounce_buf but
is not released if copy_form_user fails. In order to prevent memory leak
in case of failure, the assignment to bounce_buf_ret is moved before the
error check. This way the allocated bounce_buf will be released by the
caller.

Fixes: 579db9d45cb4 ("virt: Add vboxguest VMMDEV communication code")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20190930204223.3660-1-navid.emamdoost@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/vboxguest/vboxguest_utils.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/virt/vboxguest/vboxguest_utils.c b/drivers/virt/vboxguest/vboxguest_utils.c
index 75fd140b02ff..43c391626a00 100644
--- a/drivers/virt/vboxguest/vboxguest_utils.c
+++ b/drivers/virt/vboxguest/vboxguest_utils.c
@@ -220,6 +220,8 @@ static int hgcm_call_preprocess_linaddr(
 	if (!bounce_buf)
 		return -ENOMEM;
 
+	*bounce_buf_ret = bounce_buf;
+
 	if (copy_in) {
 		ret = copy_from_user(bounce_buf, (void __user *)buf, len);
 		if (ret)
@@ -228,7 +230,6 @@ static int hgcm_call_preprocess_linaddr(
 		memset(bounce_buf, 0, len);
 	}
 
-	*bounce_buf_ret = bounce_buf;
 	hgcm_call_add_pagelist_size(bounce_buf, len, extra);
 	return 0;
 }
-- 
cgit v1.2.3


From bd9bec5b6a09a3a7656f096e3ff0ca6709f89770 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 10 Oct 2019 09:32:42 +0100
Subject: drm/i915/execlists: Mark up expected state during reset

Move the BUG_ON around slightly and add some explanations for each to
try and capture the expected state more carefully. We want to compare
the expected active state of our bookkeeping as compared to the tracked
HW state.

References: https://bugs.freedesktop.org/show_bug.cgi?id=111937
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191010083242.1387-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index bdfd602b402a..bd8ba98e35df 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2728,8 +2728,10 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	if (!rq)
 		goto unwind;
 
+	/* We still have requests in-flight; the engine should be active */
+	GEM_BUG_ON(!intel_engine_pm_is_awake(engine));
+
 	ce = rq->hw_context;
-	GEM_BUG_ON(i915_active_is_idle(&ce->active));
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
 	/* Proclaim we have exclusive access to the context image! */
@@ -2737,10 +2739,13 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 
 	rq = active_request(rq);
 	if (!rq) {
+		/* Idle context; tidy up the ring so we can restart afresh */
 		ce->ring->head = ce->ring->tail;
 		goto out_replay;
 	}
 
+	/* Context has requests still in-flight; it should not be idle! */
+	GEM_BUG_ON(i915_active_is_idle(&ce->active));
 	ce->ring->head = intel_ring_wrap(ce->ring, rq->head);
 
 	/*
-- 
cgit v1.2.3


From 86027e312c36dfe6b614e32f7550d5fe20a6d9e0 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 10 Oct 2019 12:02:52 +0100
Subject: drm/i915/selftests: Check that registers are preserved between
 virtual engines

Make sure that we copy across the registers from one engine to the next,
as we hop around a virtual engine.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191010110252.17289-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/selftest_lrc.c | 180 +++++++++++++++++++++++++++++++++
 1 file changed, 180 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 198cf2f754f4..a691e429ca01 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -19,6 +19,33 @@
 #include "gem/selftests/igt_gem_utils.h"
 #include "gem/selftests/mock_context.h"
 
+static struct i915_vma *create_scratch(struct intel_gt *gt)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+	int err;
+
+	obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	i915_gem_object_set_cache_coherency(obj, I915_CACHING_CACHED);
+
+	vma = i915_vma_instance(obj, &gt->ggtt->vm, NULL);
+	if (IS_ERR(vma)) {
+		i915_gem_object_put(obj);
+		return vma;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL);
+	if (err) {
+		i915_gem_object_put(obj);
+		return ERR_PTR(err);
+	}
+
+	return vma;
+}
+
 static int live_sanitycheck(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -2076,6 +2103,158 @@ static int live_virtual_mask(void *arg)
 	return 0;
 }
 
+static int preserved_virtual_engine(struct drm_i915_private *i915,
+				    struct intel_engine_cs **siblings,
+				    unsigned int nsibling)
+{
+#define CS_GPR(engine, n) ((engine)->mmio_base + 0x600 + (n) * 4)
+
+	struct i915_request *last = NULL;
+	struct i915_gem_context *ctx;
+	struct intel_context *ve;
+	struct i915_vma *scratch;
+	struct igt_live_test t;
+	const int num_gpr = 16 * 2; /* each GPR is 2 dwords */
+	unsigned int n;
+	int err = 0;
+
+	ctx = kernel_context(i915);
+	if (!ctx)
+		return -ENOMEM;
+
+	scratch = create_scratch(siblings[0]->gt);
+	if (IS_ERR(scratch)) {
+		err = PTR_ERR(scratch);
+		goto out_close;
+	}
+
+	ve = intel_execlists_create_virtual(ctx, siblings, nsibling);
+	if (IS_ERR(ve)) {
+		err = PTR_ERR(ve);
+		goto out_scratch;
+	}
+
+	err = intel_context_pin(ve);
+	if (err)
+		goto out_put;
+
+	err = igt_live_test_begin(&t, i915, __func__, ve->engine->name);
+	if (err)
+		goto out_unpin;
+
+	for (n = 0; n < num_gpr; n++) {
+		struct intel_engine_cs *engine = siblings[n % nsibling];
+		struct i915_request *rq;
+		u32 *cs;
+
+		rq = i915_request_create(ve);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto out_end;
+		}
+
+		i915_request_put(last);
+		last = i915_request_get(rq);
+
+		cs = intel_ring_begin(rq, 8);
+		if (IS_ERR(cs)) {
+			i915_request_add(rq);
+			err = PTR_ERR(cs);
+			goto out_end;
+		}
+
+		*cs++ = MI_STORE_REGISTER_MEM_GEN8 | MI_USE_GGTT;
+		*cs++ = CS_GPR(engine, n);
+		*cs++ = i915_ggtt_offset(scratch) + n * sizeof(u32);
+		*cs++ = 0;
+
+		*cs++ = MI_LOAD_REGISTER_IMM(1);
+		*cs++ = CS_GPR(engine, (n + 1) % num_gpr);
+		*cs++ = n + 1;
+
+		*cs++ = MI_NOOP;
+		intel_ring_advance(rq, cs);
+
+		/* Restrict this request to run on a particular engine */
+		rq->execution_mask = engine->mask;
+		i915_request_add(rq);
+	}
+
+	if (i915_request_wait(last, 0, HZ / 5) < 0) {
+		err = -ETIME;
+	} else {
+		u32 *map = i915_gem_object_pin_map(scratch->obj, I915_MAP_WB);
+
+		for (n = 0; n < num_gpr; n++) {
+			if (map[n] != n) {
+				pr_err("Incorrect value[%d] found for GPR[%d]\n",
+				       map[n], n);
+				err = -EINVAL;
+				break;
+			}
+		}
+
+		i915_gem_object_unpin_map(scratch->obj);
+	}
+
+out_end:
+	if (igt_live_test_end(&t))
+		err = -EIO;
+	i915_request_put(last);
+out_unpin:
+	intel_context_unpin(ve);
+out_put:
+	intel_context_put(ve);
+out_scratch:
+	i915_vma_unpin_and_release(&scratch, 0);
+out_close:
+	kernel_context_close(ctx);
+	return err;
+
+#undef CS_GPR
+}
+
+static int live_virtual_preserved(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_engine_cs *siblings[MAX_ENGINE_INSTANCE + 1];
+	struct intel_gt *gt = &i915->gt;
+	unsigned int class, inst;
+
+	/*
+	 * Check that the context image retains non-privileged (user) registers
+	 * from one engine to the next. For this we check that the CS_GPR
+	 * are preserved.
+	 */
+
+	if (USES_GUC_SUBMISSION(i915))
+		return 0;
+
+	/* As we use CS_GPR we cannot run before they existed on all engines. */
+	if (INTEL_GEN(i915) < 9)
+		return 0;
+
+	for (class = 0; class <= MAX_ENGINE_CLASS; class++) {
+		int nsibling, err;
+
+		nsibling = 0;
+		for (inst = 0; inst <= MAX_ENGINE_INSTANCE; inst++) {
+			if (!gt->engine_class[class][inst])
+				continue;
+
+			siblings[nsibling++] = gt->engine_class[class][inst];
+		}
+		if (nsibling < 2)
+			continue;
+
+		err = preserved_virtual_engine(i915, siblings, nsibling);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int bond_virtual_engine(struct drm_i915_private *i915,
 			       unsigned int class,
 			       struct intel_engine_cs **siblings,
@@ -2277,6 +2456,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_preempt_smoke),
 		SUBTEST(live_virtual_engine),
 		SUBTEST(live_virtual_mask),
+		SUBTEST(live_virtual_preserved),
 		SUBTEST(live_virtual_bond),
 	};
 
-- 
cgit v1.2.3


From b33a654a5bd6bba0052ca2d86098826b309f27b8 Mon Sep 17 00:00:00 2001
From: Ulf Magnusson <ulfalizer@gmail.com>
Date: Fri, 27 Sep 2019 19:42:32 +0200
Subject: drm/tiny: Kconfig: Remove always-y THERMAL dep. from TINYDRM_REPAPER
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[cherry-picked to drm-misc-fixes: drm-misc-next commit dfef959803c7]

Commit 554b3529fe01 ("thermal/drivers/core: Remove the module Kconfig's
option") changed the type of THERMAL from tristate to bool, so
THERMAL || !THERMAL is now always y. Remove the redundant dependency.

Discovered through Kconfiglib detecting a dependency loop. The C tools
simplify the expression to y before running dependency loop detection,
and so don't see it. Changing the type of THERMAL back to tristate makes
the C tools detect the same loop.

Not sure if running dep. loop detection after simplification can be
called a bug. Fixing this nit unbreaks Kconfiglib on the kernel at
least.

Signed-off-by: Ulf Magnusson <ulfalizer@gmail.com>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20190927174218.GA32085@huvuddator
---
 drivers/gpu/drm/tiny/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig
index 504763423d46..a46ac284dd5e 100644
--- a/drivers/gpu/drm/tiny/Kconfig
+++ b/drivers/gpu/drm/tiny/Kconfig
@@ -63,7 +63,6 @@ config TINYDRM_REPAPER
 	depends on DRM && SPI
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
-	depends on THERMAL || !THERMAL
 	help
 	  DRM driver for the following Pervasive Displays panels:
 	  1.44" TFT EPD Panel (E1144CS021)
-- 
cgit v1.2.3


From b058b2552edb4a6ce62922bf904149bbafd5fd9d Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 20 Sep 2019 14:03:18 +0800
Subject: w1: ds250x: Fix build error without CRC16

If CRC16 is not set, building will fails:

drivers/w1/slaves/w1_ds250x.o: In function `w1_ds2505_read_page':
w1_ds250x.c:(.text+0x82f): undefined reference to `crc16'
w1_ds250x.c:(.text+0x90a): undefined reference to `crc16'
w1_ds250x.c:(.text+0x91a): undefined reference to `crc16'

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: 25ec8710d9c2 ("w1: add DS2501, DS2502, DS2505 EPROM device driver")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20190920060318.35020-1-yuehaibing@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/w1/slaves/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/w1/slaves/Kconfig b/drivers/w1/slaves/Kconfig
index ebed495b9e69..b7847636501d 100644
--- a/drivers/w1/slaves/Kconfig
+++ b/drivers/w1/slaves/Kconfig
@@ -103,6 +103,7 @@ config W1_SLAVE_DS2438
 
 config W1_SLAVE_DS250X
 	tristate "512b/1kb/16kb EPROM family support"
+	select CRC16
 	help
 	  Say Y here if you want to use a 1-wire
 	  512b/1kb/16kb EPROM family device (DS250x).
-- 
cgit v1.2.3


From a2f83e8b0c82c9500421a26c49eb198b25fcdea3 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Wed, 2 Oct 2019 06:14:17 -0400
Subject: dm snapshot: introduce account_start_copy() and account_end_copy()

This simple refactoring moves code for modifying the semaphore cow_count
into separate functions to prepare for changes that will extend these
methods to provide for a more sophisticated mechanism for COW
throttling.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Reviewed-by: Nikos Tsironis <ntsironis@arrikto.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-snap.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index f150f5c5492b..da3bd1794ee0 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -1512,6 +1512,16 @@ static void snapshot_dtr(struct dm_target *ti)
 	kfree(s);
 }
 
+static void account_start_copy(struct dm_snapshot *s)
+{
+	down(&s->cow_count);
+}
+
+static void account_end_copy(struct dm_snapshot *s)
+{
+	up(&s->cow_count);
+}
+
 /*
  * Flush a list of buffers.
  */
@@ -1732,7 +1742,7 @@ static void copy_callback(int read_err, unsigned long write_err, void *context)
 		rb_link_node(&pe->out_of_order_node, parent, p);
 		rb_insert_color(&pe->out_of_order_node, &s->out_of_order_tree);
 	}
-	up(&s->cow_count);
+	account_end_copy(s);
 }
 
 /*
@@ -1756,7 +1766,7 @@ static void start_copy(struct dm_snap_pending_exception *pe)
 	dest.count = src.count;
 
 	/* Hand over to kcopyd */
-	down(&s->cow_count);
+	account_start_copy(s);
 	dm_kcopyd_copy(s->kcopyd_client, &src, 1, &dest, 0, copy_callback, pe);
 }
 
@@ -1776,7 +1786,7 @@ static void start_full_bio(struct dm_snap_pending_exception *pe,
 	pe->full_bio = bio;
 	pe->full_bio_end_io = bio->bi_end_io;
 
-	down(&s->cow_count);
+	account_start_copy(s);
 	callback_data = dm_kcopyd_prepare_callback(s->kcopyd_client,
 						   copy_callback, pe);
 
@@ -1866,7 +1876,7 @@ static void zero_callback(int read_err, unsigned long write_err, void *context)
 	struct bio *bio = context;
 	struct dm_snapshot *s = bio->bi_private;
 
-	up(&s->cow_count);
+	account_end_copy(s);
 	bio->bi_status = write_err ? BLK_STS_IOERR : 0;
 	bio_endio(bio);
 }
@@ -1880,7 +1890,7 @@ static void zero_exception(struct dm_snapshot *s, struct dm_exception *e,
 	dest.sector = bio->bi_iter.bi_sector;
 	dest.count = s->store->chunk_size;
 
-	down(&s->cow_count);
+	account_start_copy(s);
 	WARN_ON_ONCE(bio->bi_private);
 	bio->bi_private = s;
 	dm_kcopyd_zero(s->kcopyd_client, 1, &dest, 0, zero_callback, bio);
-- 
cgit v1.2.3


From b21555786f18cd77f2311ad89074533109ae3ffa Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Wed, 2 Oct 2019 06:15:53 -0400
Subject: dm snapshot: rework COW throttling to fix deadlock

Commit 721b1d98fb517a ("dm snapshot: Fix excessive memory usage and
workqueue stalls") introduced a semaphore to limit the maximum number of
in-flight kcopyd (COW) jobs.

The implementation of this throttling mechanism is prone to a deadlock:

1. One or more threads write to the origin device causing COW, which is
   performed by kcopyd.

2. At some point some of these threads might reach the s->cow_count
   semaphore limit and block in down(&s->cow_count), holding a read lock
   on _origins_lock.

3. Someone tries to acquire a write lock on _origins_lock, e.g.,
   snapshot_ctr(), which blocks because the threads at step (2) already
   hold a read lock on it.

4. A COW operation completes and kcopyd runs dm-snapshot's completion
   callback, which ends up calling pending_complete().
   pending_complete() tries to resubmit any deferred origin bios. This
   requires acquiring a read lock on _origins_lock, which blocks.

   This happens because the read-write semaphore implementation gives
   priority to writers, meaning that as soon as a writer tries to enter
   the critical section, no readers will be allowed in, until all
   writers have completed their work.

   So, pending_complete() waits for the writer at step (3) to acquire
   and release the lock. This writer waits for the readers at step (2)
   to release the read lock and those readers wait for
   pending_complete() (the kcopyd thread) to signal the s->cow_count
   semaphore: DEADLOCK.

The above was thoroughly analyzed and documented by Nikos Tsironis as
part of his initial proposal for fixing this deadlock, see:
https://www.redhat.com/archives/dm-devel/2019-October/msg00001.html

Fix this deadlock by reworking COW throttling so that it waits without
holding any locks. Add a variable 'in_progress' that counts how many
kcopyd jobs are running. A function wait_for_in_progress() will sleep if
'in_progress' is over the limit. It drops _origins_lock in order to
avoid the deadlock.

Reported-by: Guruswamy Basavaiah <guru2018@gmail.com>
Reported-by: Nikos Tsironis <ntsironis@arrikto.com>
Reviewed-by: Nikos Tsironis <ntsironis@arrikto.com>
Tested-by: Nikos Tsironis <ntsironis@arrikto.com>
Fixes: 721b1d98fb51 ("dm snapshot: Fix excessive memory usage and workqueue stalls")
Cc: stable@vger.kernel.org # v5.0+
Depends-on: 4a3f111a73a8c ("dm snapshot: introduce account_start_copy() and account_end_copy()")
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-snap.c | 78 ++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 64 insertions(+), 14 deletions(-)

diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index da3bd1794ee0..4fb1a40e68a0 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -18,7 +18,6 @@
 #include <linux/vmalloc.h>
 #include <linux/log2.h>
 #include <linux/dm-kcopyd.h>
-#include <linux/semaphore.h>
 
 #include "dm.h"
 
@@ -107,8 +106,8 @@ struct dm_snapshot {
 	/* The on disk metadata handler */
 	struct dm_exception_store *store;
 
-	/* Maximum number of in-flight COW jobs. */
-	struct semaphore cow_count;
+	unsigned in_progress;
+	struct wait_queue_head in_progress_wait;
 
 	struct dm_kcopyd_client *kcopyd_client;
 
@@ -162,8 +161,8 @@ struct dm_snapshot {
  */
 #define DEFAULT_COW_THRESHOLD 2048
 
-static int cow_threshold = DEFAULT_COW_THRESHOLD;
-module_param_named(snapshot_cow_threshold, cow_threshold, int, 0644);
+static unsigned cow_threshold = DEFAULT_COW_THRESHOLD;
+module_param_named(snapshot_cow_threshold, cow_threshold, uint, 0644);
 MODULE_PARM_DESC(snapshot_cow_threshold, "Maximum number of chunks being copied on write");
 
 DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle,
@@ -1327,7 +1326,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad_hash_tables;
 	}
 
-	sema_init(&s->cow_count, (cow_threshold > 0) ? cow_threshold : INT_MAX);
+	init_waitqueue_head(&s->in_progress_wait);
 
 	s->kcopyd_client = dm_kcopyd_client_create(&dm_kcopyd_throttle);
 	if (IS_ERR(s->kcopyd_client)) {
@@ -1509,17 +1508,54 @@ static void snapshot_dtr(struct dm_target *ti)
 
 	dm_put_device(ti, s->origin);
 
+	WARN_ON(s->in_progress);
+
 	kfree(s);
 }
 
 static void account_start_copy(struct dm_snapshot *s)
 {
-	down(&s->cow_count);
+	spin_lock(&s->in_progress_wait.lock);
+	s->in_progress++;
+	spin_unlock(&s->in_progress_wait.lock);
 }
 
 static void account_end_copy(struct dm_snapshot *s)
 {
-	up(&s->cow_count);
+	spin_lock(&s->in_progress_wait.lock);
+	BUG_ON(!s->in_progress);
+	s->in_progress--;
+	if (likely(s->in_progress <= cow_threshold) &&
+	    unlikely(waitqueue_active(&s->in_progress_wait)))
+		wake_up_locked(&s->in_progress_wait);
+	spin_unlock(&s->in_progress_wait.lock);
+}
+
+static bool wait_for_in_progress(struct dm_snapshot *s, bool unlock_origins)
+{
+	if (unlikely(s->in_progress > cow_threshold)) {
+		spin_lock(&s->in_progress_wait.lock);
+		if (likely(s->in_progress > cow_threshold)) {
+			/*
+			 * NOTE: this throttle doesn't account for whether
+			 * the caller is servicing an IO that will trigger a COW
+			 * so excess throttling may result for chunks not required
+			 * to be COW'd.  But if cow_threshold was reached, extra
+			 * throttling is unlikely to negatively impact performance.
+			 */
+			DECLARE_WAITQUEUE(wait, current);
+			__add_wait_queue(&s->in_progress_wait, &wait);
+			__set_current_state(TASK_UNINTERRUPTIBLE);
+			spin_unlock(&s->in_progress_wait.lock);
+			if (unlock_origins)
+				up_read(&_origins_lock);
+			io_schedule();
+			remove_wait_queue(&s->in_progress_wait, &wait);
+			return false;
+		}
+		spin_unlock(&s->in_progress_wait.lock);
+	}
+	return true;
 }
 
 /*
@@ -1537,7 +1573,7 @@ static void flush_bios(struct bio *bio)
 	}
 }
 
-static int do_origin(struct dm_dev *origin, struct bio *bio);
+static int do_origin(struct dm_dev *origin, struct bio *bio, bool limit);
 
 /*
  * Flush a list of buffers.
@@ -1550,7 +1586,7 @@ static void retry_origin_bios(struct dm_snapshot *s, struct bio *bio)
 	while (bio) {
 		n = bio->bi_next;
 		bio->bi_next = NULL;
-		r = do_origin(s->origin, bio);
+		r = do_origin(s->origin, bio, false);
 		if (r == DM_MAPIO_REMAPPED)
 			generic_make_request(bio);
 		bio = n;
@@ -1926,6 +1962,11 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio)
 	if (!s->valid)
 		return DM_MAPIO_KILL;
 
+	if (bio_data_dir(bio) == WRITE) {
+		while (unlikely(!wait_for_in_progress(s, false)))
+			; /* wait_for_in_progress() has slept */
+	}
+
 	down_read(&s->lock);
 	dm_exception_table_lock(&lock);
 
@@ -2122,7 +2163,7 @@ redirect_to_origin:
 
 	if (bio_data_dir(bio) == WRITE) {
 		up_write(&s->lock);
-		return do_origin(s->origin, bio);
+		return do_origin(s->origin, bio, false);
 	}
 
 out_unlock:
@@ -2497,15 +2538,24 @@ next_snapshot:
 /*
  * Called on a write from the origin driver.
  */
-static int do_origin(struct dm_dev *origin, struct bio *bio)
+static int do_origin(struct dm_dev *origin, struct bio *bio, bool limit)
 {
 	struct origin *o;
 	int r = DM_MAPIO_REMAPPED;
 
+again:
 	down_read(&_origins_lock);
 	o = __lookup_origin(origin->bdev);
-	if (o)
+	if (o) {
+		if (limit) {
+			struct dm_snapshot *s;
+			list_for_each_entry(s, &o->snapshots, list)
+				if (unlikely(!wait_for_in_progress(s, true)))
+					goto again;
+		}
+
 		r = __origin_write(&o->snapshots, bio->bi_iter.bi_sector, bio);
+	}
 	up_read(&_origins_lock);
 
 	return r;
@@ -2618,7 +2668,7 @@ static int origin_map(struct dm_target *ti, struct bio *bio)
 		dm_accept_partial_bio(bio, available_sectors);
 
 	/* Only tell snapshots if this is a write */
-	return do_origin(o->dev, bio);
+	return do_origin(o->dev, bio, true);
 }
 
 /*
-- 
cgit v1.2.3


From 9a3a41dfe2239abe65944cfa1f8cd3aff5a03944 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Fri, 4 Oct 2019 13:34:52 +0200
Subject: drm/i915: Fix for_each_intel_plane_mask definition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Using for_each_intel_plane_mask() fails because of an extra bracket,
remove the bracket so we can use it in the next commit.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004113514.17064-3-maarten.lankhorst@linux.intel.com
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 2782f23ee887..4ded64fcbc6c 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -350,7 +350,7 @@ enum phy_fia {
 			    &(dev)->mode_config.plane_list,		\
 			    base.head)					\
 		for_each_if((plane_mask) &				\
-			    drm_plane_mask(&intel_plane->base)))
+			    drm_plane_mask(&intel_plane->base))
 
 #define for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane)	\
 	list_for_each_entry(intel_plane,				\
-- 
cgit v1.2.3


From af9fbfa657c86dd0c5ee0e24da3e2da79353c0fb Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Fri, 4 Oct 2019 13:34:53 +0200
Subject: drm/i915: Introduce and use
 intel_atomic_crtc_state_for_each_plane_state.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of looking at drm_plane_state, look at intel_plane_state directly.

This will allow us to make the watermarks bigjoiner aware, when we make it
work for bigjoiner slave pipes as well.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004113514.17064-4-maarten.lankhorst@linux.intel.com
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.h |  8 ++++
 drivers/gpu/drm/i915/intel_pm.c              | 60 ++++++++++++----------------
 2 files changed, 33 insertions(+), 35 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 4ded64fcbc6c..bc2cf4bec0e8 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -440,6 +440,14 @@ enum phy_fia {
 	     (__i)--) \
 		for_each_if(crtc)
 
+#define intel_atomic_crtc_state_for_each_plane_state( \
+		  plane, plane_state, \
+		  crtc_state) \
+	for_each_intel_plane_mask(((crtc_state)->base.state->dev), (plane), \
+				((crtc_state)->base.plane_mask)) \
+		for_each_if ((plane_state = \
+			      to_intel_plane_state(__drm_atomic_get_current_plane_state((crtc_state)->base.state, &plane->base))))
+
 void intel_link_compute_m_n(u16 bpp, int nlanes,
 			    int pixel_clock, int link_clock,
 			    struct intel_link_m_n *m_n,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index bfcf03ab5245..6aeaad587a20 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3089,8 +3089,8 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 	struct intel_pipe_wm *pipe_wm;
 	struct drm_device *dev = state->dev;
 	const struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_plane *plane;
-	const struct drm_plane_state *plane_state;
+	struct intel_plane *plane;
+	const struct intel_plane_state *plane_state;
 	const struct intel_plane_state *pristate = NULL;
 	const struct intel_plane_state *sprstate = NULL;
 	const struct intel_plane_state *curstate = NULL;
@@ -3099,15 +3099,13 @@ static int ilk_compute_pipe_wm(struct intel_crtc_state *crtc_state)
 
 	pipe_wm = &crtc_state->wm.ilk.optimal;
 
-	drm_atomic_crtc_state_for_each_plane_state(plane, plane_state, &crtc_state->base) {
-		const struct intel_plane_state *ps = to_intel_plane_state(plane_state);
-
-		if (plane->type == DRM_PLANE_TYPE_PRIMARY)
-			pristate = ps;
-		else if (plane->type == DRM_PLANE_TYPE_OVERLAY)
-			sprstate = ps;
-		else if (plane->type == DRM_PLANE_TYPE_CURSOR)
-			curstate = ps;
+	intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
+		if (plane->base.type == DRM_PLANE_TYPE_PRIMARY)
+			pristate = plane_state;
+		else if (plane->base.type == DRM_PLANE_TYPE_OVERLAY)
+			sprstate = plane_state;
+		else if (plane->base.type == DRM_PLANE_TYPE_CURSOR)
+			curstate = plane_state;
 	}
 
 	pipe_wm->pipe_enabled = crtc_state->base.active;
@@ -4124,8 +4122,8 @@ int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
 	struct drm_atomic_state *state = crtc_state->base.state;
-	struct drm_plane *plane;
-	const struct drm_plane_state *drm_plane_state;
+	const struct intel_plane_state *plane_state;
+	struct intel_plane *plane;
 	int crtc_clock, dotclk;
 	u32 pipe_max_pixel_rate;
 	uint_fixed_16_16_t pipe_downscale;
@@ -4134,12 +4132,10 @@ int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
 	if (!crtc_state->base.enable)
 		return 0;
 
-	drm_atomic_crtc_state_for_each_plane_state(plane, drm_plane_state, &crtc_state->base) {
+	intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
 		uint_fixed_16_16_t plane_downscale;
 		uint_fixed_16_16_t fp_9_div_8 = div_fixed16(9, 8);
 		int bpp;
-		const struct intel_plane_state *plane_state =
-			to_intel_plane_state(drm_plane_state);
 
 		if (!intel_wm_plane_visible(crtc_state, plane_state))
 			continue;
@@ -4227,18 +4223,16 @@ skl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
 				 u64 *uv_plane_data_rate)
 {
 	struct drm_atomic_state *state = crtc_state->base.state;
-	struct drm_plane *plane;
-	const struct drm_plane_state *drm_plane_state;
+	struct intel_plane *plane;
+	const struct intel_plane_state *plane_state;
 	u64 total_data_rate = 0;
 
 	if (WARN_ON(!state))
 		return 0;
 
 	/* Calculate and cache data rate for each plane */
-	drm_atomic_crtc_state_for_each_plane_state(plane, drm_plane_state, &crtc_state->base) {
-		enum plane_id plane_id = to_intel_plane(plane)->id;
-		const struct intel_plane_state *plane_state =
-			to_intel_plane_state(drm_plane_state);
+	intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
+		enum plane_id plane_id = plane->id;
 		u64 rate;
 
 		/* packed/y */
@@ -4259,18 +4253,16 @@ static u64
 icl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
 				 u64 *plane_data_rate)
 {
-	struct drm_plane *plane;
-	const struct drm_plane_state *drm_plane_state;
+	struct intel_plane *plane;
+	const struct intel_plane_state *plane_state;
 	u64 total_data_rate = 0;
 
 	if (WARN_ON(!crtc_state->base.state))
 		return 0;
 
 	/* Calculate and cache data rate for each plane */
-	drm_atomic_crtc_state_for_each_plane_state(plane, drm_plane_state, &crtc_state->base) {
-		const struct intel_plane_state *plane_state =
-			to_intel_plane_state(drm_plane_state);
-		enum plane_id plane_id = to_intel_plane(plane)->id;
+	intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
+		enum plane_id plane_id = plane->id;
 		u64 rate;
 
 		if (!plane_state->planar_linked_plane) {
@@ -4282,7 +4274,7 @@ icl_get_total_relative_data_rate(struct intel_crtc_state *crtc_state,
 
 			/*
 			 * The slave plane might not iterate in
-			 * drm_atomic_crtc_state_for_each_plane_state(),
+			 * intel_atomic_crtc_state_for_each_plane_state(),
 			 * and needs the master plane state which may be
 			 * NULL if we try get_new_plane_state(), so we
 			 * always calculate from the master.
@@ -5065,8 +5057,8 @@ static int skl_build_pipe_wm(struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
 	struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal;
-	struct drm_plane *plane;
-	const struct drm_plane_state *drm_plane_state;
+	struct intel_plane *plane;
+	const struct intel_plane_state *plane_state;
 	int ret;
 
 	/*
@@ -5075,10 +5067,8 @@ static int skl_build_pipe_wm(struct intel_crtc_state *crtc_state)
 	 */
 	memset(pipe_wm->planes, 0, sizeof(pipe_wm->planes));
 
-	drm_atomic_crtc_state_for_each_plane_state(plane, drm_plane_state,
-						   &crtc_state->base) {
-		const struct intel_plane_state *plane_state =
-			to_intel_plane_state(drm_plane_state);
+	intel_atomic_crtc_state_for_each_plane_state(plane, plane_state,
+						     crtc_state) {
 
 		if (INTEL_GEN(dev_priv) >= 11)
 			ret = icl_build_plane_wm(crtc_state, plane_state);
-- 
cgit v1.2.3


From 04c8b0bf4abc203df94f63f268a56a7a0efbb0f4 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Fri, 4 Oct 2019 13:34:55 +0200
Subject: drm/i915: Use intel_plane_state in prepare and cleanup plane_fb
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We need to look at the hw fb in the plane split, so replace all the places
that use drm_plane_state with intel_plane_state.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004113514.17064-6-maarten.lankhorst@linux.intel.com
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
[mlankhorst: Fix line wraps (Matt Roper)]
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 30 +++++++++++++++++-----------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 1a533ccdb54f..23dc7ae1243a 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -14358,12 +14358,14 @@ static void fb_obj_bump_render_priority(struct drm_i915_gem_object *obj)
  */
 int
 intel_prepare_plane_fb(struct drm_plane *plane,
-		       struct drm_plane_state *new_state)
+		       struct drm_plane_state *_new_plane_state)
 {
+	struct intel_plane_state *new_plane_state =
+		to_intel_plane_state(_new_plane_state);
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(new_state->state);
+		to_intel_atomic_state(new_plane_state->base.state);
 	struct drm_i915_private *dev_priv = to_i915(plane->dev);
-	struct drm_framebuffer *fb = new_state->fb;
+	struct drm_framebuffer *fb = new_plane_state->base.fb;
 	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	struct drm_i915_gem_object *old_obj = intel_fb_obj(plane->state->fb);
 	int ret;
@@ -14394,9 +14396,9 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 		}
 	}
 
-	if (new_state->fence) { /* explicit fencing */
+	if (new_plane_state->base.fence) { /* explicit fencing */
 		ret = i915_sw_fence_await_dma_fence(&intel_state->commit_ready,
-						    new_state->fence,
+						    new_plane_state->base.fence,
 						    I915_FENCE_TIMEOUT,
 						    GFP_KERNEL);
 		if (ret < 0)
@@ -14410,7 +14412,7 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 	if (ret)
 		return ret;
 
-	ret = intel_plane_pin_fb(to_intel_plane_state(new_state));
+	ret = intel_plane_pin_fb(new_plane_state);
 
 	i915_gem_object_unpin_pages(obj);
 	if (ret)
@@ -14419,7 +14421,7 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 	fb_obj_bump_render_priority(obj);
 	intel_frontbuffer_flush(obj->frontbuffer, ORIGIN_DIRTYFB);
 
-	if (!new_state->fence) { /* implicit fencing */
+	if (!new_plane_state->base.fence) { /* implicit fencing */
 		struct dma_fence *fence;
 
 		ret = i915_sw_fence_await_reservation(&intel_state->commit_ready,
@@ -14431,11 +14433,13 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 
 		fence = dma_resv_get_excl_rcu(obj->base.resv);
 		if (fence) {
-			add_rps_boost_after_vblank(new_state->crtc, fence);
+			add_rps_boost_after_vblank(new_plane_state->base.crtc,
+						   fence);
 			dma_fence_put(fence);
 		}
 	} else {
-		add_rps_boost_after_vblank(new_state->crtc, new_state->fence);
+		add_rps_boost_after_vblank(new_plane_state->base.crtc,
+					   new_plane_state->base.fence);
 	}
 
 	/*
@@ -14463,10 +14467,12 @@ intel_prepare_plane_fb(struct drm_plane *plane,
  */
 void
 intel_cleanup_plane_fb(struct drm_plane *plane,
-		       struct drm_plane_state *old_state)
+		       struct drm_plane_state *_old_plane_state)
 {
+	struct intel_plane_state *old_plane_state =
+		to_intel_plane_state(_old_plane_state);
 	struct intel_atomic_state *intel_state =
-		to_intel_atomic_state(old_state->state);
+		to_intel_atomic_state(old_plane_state->base.state);
 	struct drm_i915_private *dev_priv = to_i915(plane->dev);
 
 	if (intel_state->rps_interactive) {
@@ -14475,7 +14481,7 @@ intel_cleanup_plane_fb(struct drm_plane *plane,
 	}
 
 	/* Should only be called after a successful intel_prepare_plane_fb()! */
-	intel_plane_unpin_fb(to_intel_plane_state(old_state));
+	intel_plane_unpin_fb(old_plane_state);
 }
 
 int
-- 
cgit v1.2.3


From d8bd3e157a17b03d2b0f380e143bf8204f75df94 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Fri, 4 Oct 2019 13:34:56 +0200
Subject: drm/i915: Remove begin/finish_crtc_commit, v4.

This can all be done from the intel_update_crtc function. Split out the
pipe update into a separate function, just like is done for the planes.
Pull in all the changes done during fastset as well. It makes no sense
for it to still exist as a separate function.

Changes since v1:
- Inline intel_update_pipe_config()
Changes since v2:
- Add comments suggested by matt.
- Reorder commit_pipe_config() to remove all nesting. (Ville, Matt)
- Use intel_set_pipe_src_size((). (Matt)
Changes since v3:
- Move atomic_update_watermarks closer to the plane calls.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004113514.17064-7-maarten.lankhorst@linux.intel.com
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
[mlankhorst: Replace 8 spaces with tabs in comment]
---
 drivers/gpu/drm/i915/display/intel_display.c | 210 +++++++++++++--------------
 1 file changed, 99 insertions(+), 111 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 23dc7ae1243a..9db390188e9d 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -135,8 +135,6 @@ static void vlv_prepare_pll(struct intel_crtc *crtc,
 			    const struct intel_crtc_state *pipe_config);
 static void chv_prepare_pll(struct intel_crtc *crtc,
 			    const struct intel_crtc_state *pipe_config);
-static void intel_begin_crtc_commit(struct intel_atomic_state *, struct intel_crtc *);
-static void intel_finish_crtc_commit(struct intel_atomic_state *, struct intel_crtc *);
 static void intel_crtc_init_scalers(struct intel_crtc *crtc,
 				    struct intel_crtc_state *crtc_state);
 static void skylake_pfit_enable(const struct intel_crtc_state *crtc_state);
@@ -4401,45 +4399,6 @@ static void icl_set_pipe_chicken(struct intel_crtc *crtc)
 	I915_WRITE(PIPE_CHICKEN(pipe), tmp);
 }
 
-static void intel_update_pipe_config(const struct intel_crtc_state *old_crtc_state,
-				     const struct intel_crtc_state *new_crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-
-	/* drm_atomic_helper_update_legacy_modeset_state might not be called. */
-	crtc->base.mode = new_crtc_state->base.mode;
-
-	/*
-	 * Update pipe size and adjust fitter if needed: the reason for this is
-	 * that in compute_mode_changes we check the native mode (not the pfit
-	 * mode) to see if we can flip rather than do a full mode set. In the
-	 * fastboot case, we'll flip, but if we don't update the pipesrc and
-	 * pfit state, we'll end up with a big fb scanned out into the wrong
-	 * sized surface.
-	 */
-
-	I915_WRITE(PIPESRC(crtc->pipe),
-		   ((new_crtc_state->pipe_src_w - 1) << 16) |
-		   (new_crtc_state->pipe_src_h - 1));
-
-	/* on skylake this is done by detaching scalers */
-	if (INTEL_GEN(dev_priv) >= 9) {
-		skl_detach_scalers(new_crtc_state);
-
-		if (new_crtc_state->pch_pfit.enabled)
-			skylake_pfit_enable(new_crtc_state);
-	} else if (HAS_PCH_SPLIT(dev_priv)) {
-		if (new_crtc_state->pch_pfit.enabled)
-			ironlake_pfit_enable(new_crtc_state);
-		else if (old_crtc_state->pch_pfit.enabled)
-			ironlake_pfit_disable(old_crtc_state);
-	}
-
-	if (INTEL_GEN(dev_priv) >= 11)
-		icl_set_pipe_chicken(crtc);
-}
-
 static void intel_fdi_normal_train(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
@@ -13695,13 +13654,95 @@ u32 intel_crtc_get_vblank_counter(struct intel_crtc *crtc)
 	return crtc->base.funcs->get_vblank_counter(&crtc->base);
 }
 
+void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
+				  struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+
+	if (!IS_GEN(dev_priv, 2))
+		intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true);
+
+	if (crtc_state->has_pch_encoder) {
+		enum pipe pch_transcoder =
+			intel_crtc_pch_transcoder(crtc);
+
+		intel_set_pch_fifo_underrun_reporting(dev_priv, pch_transcoder, true);
+	}
+}
+
+static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state,
+			       const struct intel_crtc_state *new_crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+
+	/* drm_atomic_helper_update_legacy_modeset_state might not be called. */
+	crtc->base.mode = new_crtc_state->base.mode;
+
+	/*
+	 * Update pipe size and adjust fitter if needed: the reason for this is
+	 * that in compute_mode_changes we check the native mode (not the pfit
+	 * mode) to see if we can flip rather than do a full mode set. In the
+	 * fastboot case, we'll flip, but if we don't update the pipesrc and
+	 * pfit state, we'll end up with a big fb scanned out into the wrong
+	 * sized surface.
+	 */
+	intel_set_pipe_src_size(new_crtc_state);
+
+	/* on skylake this is done by detaching scalers */
+	if (INTEL_GEN(dev_priv) >= 9) {
+		skl_detach_scalers(new_crtc_state);
+
+		if (new_crtc_state->pch_pfit.enabled)
+			skylake_pfit_enable(new_crtc_state);
+	} else if (HAS_PCH_SPLIT(dev_priv)) {
+		if (new_crtc_state->pch_pfit.enabled)
+			ironlake_pfit_enable(new_crtc_state);
+		else if (old_crtc_state->pch_pfit.enabled)
+			ironlake_pfit_disable(old_crtc_state);
+	}
+
+	if (INTEL_GEN(dev_priv) >= 11)
+		icl_set_pipe_chicken(crtc);
+}
+
+static void commit_pipe_config(struct intel_atomic_state *state,
+			       struct intel_crtc_state *old_crtc_state,
+			       struct intel_crtc_state *new_crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	bool modeset = needs_modeset(new_crtc_state);
+
+	/*
+	 * During modesets pipe configuration was programmed as the
+	 * CRTC was enabled.
+	 */
+	if (!modeset) {
+		if (new_crtc_state->base.color_mgmt_changed ||
+		    new_crtc_state->update_pipe)
+			intel_color_commit(new_crtc_state);
+
+		if (INTEL_GEN(dev_priv) >= 9)
+			skl_detach_scalers(new_crtc_state);
+
+		if (INTEL_GEN(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
+			bdw_set_pipemisc(new_crtc_state);
+
+		if (new_crtc_state->update_pipe)
+			intel_pipe_fastset(old_crtc_state, new_crtc_state);
+	}
+
+	if (dev_priv->display.atomic_update_watermarks)
+		dev_priv->display.atomic_update_watermarks(state,
+							   new_crtc_state);
+}
+
 static void intel_update_crtc(struct intel_crtc *crtc,
 			      struct intel_atomic_state *state,
 			      struct intel_crtc_state *old_crtc_state,
 			      struct intel_crtc_state *new_crtc_state)
 {
-	struct drm_device *dev = state->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	bool modeset = needs_modeset(new_crtc_state);
 	struct intel_plane_state *new_plane_state =
 		intel_atomic_get_new_plane_state(state,
@@ -13725,14 +13766,27 @@ static void intel_update_crtc(struct intel_crtc *crtc,
 	else if (new_plane_state)
 		intel_fbc_enable(crtc, new_crtc_state, new_plane_state);
 
-	intel_begin_crtc_commit(state, crtc);
+	/* Perform vblank evasion around commit operation */
+	intel_pipe_update_start(new_crtc_state);
+
+	commit_pipe_config(state, old_crtc_state, new_crtc_state);
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		skl_update_planes_on_crtc(state, crtc);
 	else
 		i9xx_update_planes_on_crtc(state, crtc);
 
-	intel_finish_crtc_commit(state, crtc);
+	intel_pipe_update_end(new_crtc_state);
+
+	/*
+	 * We usually enable FIFO underrun interrupts as part of the
+	 * CRTC enable sequence during modesets.  But when we inherit a
+	 * valid pipe configuration from the BIOS we need to take care
+	 * of enabling them on the CRTC's first fastset.
+	 */
+	if (new_crtc_state->update_pipe && !modeset &&
+	    old_crtc_state->base.mode.private_flags & I915_MODE_FLAG_INHERITED)
+		intel_crtc_arm_fifo_underrun(crtc, new_crtc_state);
 }
 
 static void intel_old_crtc_state_disables(struct intel_atomic_state *state,
@@ -14522,72 +14576,6 @@ skl_max_scale(const struct intel_crtc_state *crtc_state,
 	return max_scale;
 }
 
-static void intel_begin_crtc_commit(struct intel_atomic_state *state,
-				    struct intel_crtc *crtc)
-{
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct intel_crtc_state *old_crtc_state =
-		intel_atomic_get_old_crtc_state(state, crtc);
-	struct intel_crtc_state *new_crtc_state =
-		intel_atomic_get_new_crtc_state(state, crtc);
-	bool modeset = needs_modeset(new_crtc_state);
-
-	/* Perform vblank evasion around commit operation */
-	intel_pipe_update_start(new_crtc_state);
-
-	if (modeset)
-		goto out;
-
-	if (new_crtc_state->base.color_mgmt_changed ||
-	    new_crtc_state->update_pipe)
-		intel_color_commit(new_crtc_state);
-
-	if (new_crtc_state->update_pipe)
-		intel_update_pipe_config(old_crtc_state, new_crtc_state);
-	else if (INTEL_GEN(dev_priv) >= 9)
-		skl_detach_scalers(new_crtc_state);
-
-	if (INTEL_GEN(dev_priv) >= 9 || IS_BROADWELL(dev_priv))
-		bdw_set_pipemisc(new_crtc_state);
-
-out:
-	if (dev_priv->display.atomic_update_watermarks)
-		dev_priv->display.atomic_update_watermarks(state,
-							   new_crtc_state);
-}
-
-void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
-				  struct intel_crtc_state *crtc_state)
-{
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-
-	if (!IS_GEN(dev_priv, 2))
-		intel_set_cpu_fifo_underrun_reporting(dev_priv, crtc->pipe, true);
-
-	if (crtc_state->has_pch_encoder) {
-		enum pipe pch_transcoder =
-			intel_crtc_pch_transcoder(crtc);
-
-		intel_set_pch_fifo_underrun_reporting(dev_priv, pch_transcoder, true);
-	}
-}
-
-static void intel_finish_crtc_commit(struct intel_atomic_state *state,
-				     struct intel_crtc *crtc)
-{
-	struct intel_crtc_state *old_crtc_state =
-		intel_atomic_get_old_crtc_state(state, crtc);
-	struct intel_crtc_state *new_crtc_state =
-		intel_atomic_get_new_crtc_state(state, crtc);
-
-	intel_pipe_update_end(new_crtc_state);
-
-	if (new_crtc_state->update_pipe &&
-	    !needs_modeset(new_crtc_state) &&
-	    old_crtc_state->base.mode.private_flags & I915_MODE_FLAG_INHERITED)
-		intel_crtc_arm_fifo_underrun(crtc, new_crtc_state);
-}
-
 /**
  * intel_plane_destroy - destroy a plane
  * @plane: plane to destroy
-- 
cgit v1.2.3


From 3a612765f4233993bf5cff302844bd3b6b5a7429 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Fri, 4 Oct 2019 13:34:54 +0200
Subject: drm/i915: Remove cursor use of properties for coordinates
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We have a src and dect rectangle, use it instead of relying on
the core drm properties.

Because the core by default clips the src/dst properties, after
the drm_atomic_helper_check_plane_state() we manually set the
unclipped src/dst rectangles. We still need the call for
visibility checks, but this way we are able to use the src/dst
rects in the check/commit code.

This removes the special case in the watermark code for cursor w/h.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004113514.17064-5-maarten.lankhorst@linux.intel.com
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
[mlankhorst: Clarify commit message to state we use unclipped src/dst
---
 drivers/gpu/drm/i915/display/intel_display.c | 57 +++++++++++++++------------
 drivers/gpu/drm/i915/intel_pm.c              | 58 ++++++++++------------------
 2 files changed, 53 insertions(+), 62 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 9db390188e9d..a146ec02a0c1 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -10538,16 +10538,16 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state)
 	/* ILK+ do this automagically */
 	if (HAS_GMCH(dev_priv) &&
 	    plane_state->base.rotation & DRM_MODE_ROTATE_180)
-		base += (plane_state->base.crtc_h *
-			 plane_state->base.crtc_w - 1) * fb->format->cpp[0];
+		base += (drm_rect_height(&plane_state->base.dst) *
+			 drm_rect_width(&plane_state->base.dst) - 1) * fb->format->cpp[0];
 
 	return base;
 }
 
 static u32 intel_cursor_position(const struct intel_plane_state *plane_state)
 {
-	int x = plane_state->base.crtc_x;
-	int y = plane_state->base.crtc_y;
+	int x = plane_state->base.dst.x1;
+	int y = plane_state->base.dst.y1;
 	u32 pos = 0;
 
 	if (x < 0) {
@@ -10569,8 +10569,8 @@ static bool intel_cursor_size_ok(const struct intel_plane_state *plane_state)
 {
 	const struct drm_mode_config *config =
 		&plane_state->base.plane->dev->mode_config;
-	int width = plane_state->base.crtc_w;
-	int height = plane_state->base.crtc_h;
+	int width = drm_rect_width(&plane_state->base.dst);
+	int height = drm_rect_height(&plane_state->base.dst);
 
 	return width > 0 && width <= config->cursor_width &&
 		height > 0 && height <= config->cursor_height;
@@ -10589,8 +10589,8 @@ static int intel_cursor_check_surface(struct intel_plane_state *plane_state)
 	if (!plane_state->base.visible)
 		return 0;
 
-	src_x = plane_state->base.src_x >> 16;
-	src_y = plane_state->base.src_y >> 16;
+	src_x = plane_state->base.src.x1 >> 16;
+	src_y = plane_state->base.src.y1 >> 16;
 
 	intel_add_fb_offsets(&src_x, &src_y, plane_state, 0);
 	offset = intel_plane_compute_aligned_offset(&src_x, &src_y,
@@ -10625,6 +10625,10 @@ static int intel_check_cursor(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
+	/* Use the unclipped src/dst rectangles, which we program to hw */
+	plane_state->base.src = drm_plane_state_src(&plane_state->base);
+	plane_state->base.dst = drm_plane_state_dest(&plane_state->base);
+
 	ret = intel_cursor_check_surface(plane_state);
 	if (ret)
 		return ret;
@@ -10667,7 +10671,7 @@ static u32 i845_cursor_ctl(const struct intel_crtc_state *crtc_state,
 
 static bool i845_cursor_size_ok(const struct intel_plane_state *plane_state)
 {
-	int width = plane_state->base.crtc_w;
+	int width = drm_rect_width(&plane_state->base.dst);
 
 	/*
 	 * 845g/865g are only limited by the width of their cursors,
@@ -10693,8 +10697,8 @@ static int i845_check_cursor(struct intel_crtc_state *crtc_state,
 	/* Check for which cursor types we support */
 	if (!i845_cursor_size_ok(plane_state)) {
 		DRM_DEBUG("Cursor dimension %dx%d not supported\n",
-			  plane_state->base.crtc_w,
-			  plane_state->base.crtc_h);
+			  drm_rect_width(&plane_state->base.dst),
+			  drm_rect_height(&plane_state->base.dst));
 		return -EINVAL;
 	}
 
@@ -10727,8 +10731,8 @@ static void i845_update_cursor(struct intel_plane *plane,
 	unsigned long irqflags;
 
 	if (plane_state && plane_state->base.visible) {
-		unsigned int width = plane_state->base.crtc_w;
-		unsigned int height = plane_state->base.crtc_h;
+		unsigned int width = drm_rect_width(&plane_state->base.src);
+		unsigned int height = drm_rect_height(&plane_state->base.dst);
 
 		cntl = plane_state->ctl |
 			i845_cursor_ctl_crtc(crtc_state);
@@ -10830,7 +10834,7 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 	if (IS_GEN(dev_priv, 6) || IS_IVYBRIDGE(dev_priv))
 		cntl |= MCURSOR_TRICKLE_FEED_DISABLE;
 
-	switch (plane_state->base.crtc_w) {
+	switch (drm_rect_width(&plane_state->base.dst)) {
 	case 64:
 		cntl |= MCURSOR_MODE_64_ARGB_AX;
 		break;
@@ -10841,7 +10845,7 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 		cntl |= MCURSOR_MODE_256_ARGB_AX;
 		break;
 	default:
-		MISSING_CASE(plane_state->base.crtc_w);
+		MISSING_CASE(drm_rect_width(&plane_state->base.dst));
 		return 0;
 	}
 
@@ -10855,8 +10859,8 @@ static bool i9xx_cursor_size_ok(const struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
 		to_i915(plane_state->base.plane->dev);
-	int width = plane_state->base.crtc_w;
-	int height = plane_state->base.crtc_h;
+	int width = drm_rect_width(&plane_state->base.dst);
+	int height = drm_rect_height(&plane_state->base.dst);
 
 	if (!intel_cursor_size_ok(plane_state))
 		return false;
@@ -10909,17 +10913,19 @@ static int i9xx_check_cursor(struct intel_crtc_state *crtc_state,
 	/* Check for which cursor types we support */
 	if (!i9xx_cursor_size_ok(plane_state)) {
 		DRM_DEBUG("Cursor dimension %dx%d not supported\n",
-			  plane_state->base.crtc_w,
-			  plane_state->base.crtc_h);
+			  drm_rect_width(&plane_state->base.dst),
+			  drm_rect_height(&plane_state->base.dst));
 		return -EINVAL;
 	}
 
 	WARN_ON(plane_state->base.visible &&
 		plane_state->color_plane[0].stride != fb->pitches[0]);
 
-	if (fb->pitches[0] != plane_state->base.crtc_w * fb->format->cpp[0]) {
+	if (fb->pitches[0] !=
+	    drm_rect_width(&plane_state->base.dst) * fb->format->cpp[0]) {
 		DRM_DEBUG_KMS("Invalid cursor stride (%u) (cursor width %d)\n",
-			      fb->pitches[0], plane_state->base.crtc_w);
+			      fb->pitches[0],
+			      drm_rect_width(&plane_state->base.dst));
 		return -EINVAL;
 	}
 
@@ -10934,7 +10940,7 @@ static int i9xx_check_cursor(struct intel_crtc_state *crtc_state,
 	 * Refuse the put the cursor into that compromised position.
 	 */
 	if (IS_CHERRYVIEW(dev_priv) && pipe == PIPE_C &&
-	    plane_state->base.visible && plane_state->base.crtc_x < 0) {
+	    plane_state->base.visible && plane_state->base.dst.x1 < 0) {
 		DRM_DEBUG_KMS("CHV cursor C not allowed to straddle the left screen edge\n");
 		return -EINVAL;
 	}
@@ -10954,11 +10960,14 @@ static void i9xx_update_cursor(struct intel_plane *plane,
 	unsigned long irqflags;
 
 	if (plane_state && plane_state->base.visible) {
+		unsigned width = drm_rect_width(&plane_state->base.dst);
+		unsigned height = drm_rect_height(&plane_state->base.dst);
+
 		cntl = plane_state->ctl |
 			i9xx_cursor_ctl_crtc(crtc_state);
 
-		if (plane_state->base.crtc_h != plane_state->base.crtc_w)
-			fbc_ctl = CUR_FBC_CTL_EN | (plane_state->base.crtc_h - 1);
+		if (width != height)
+			fbc_ctl = CUR_FBC_CTL_EN | (height - 1);
 
 		base = intel_cursor_base(plane_state);
 		pos = intel_cursor_position(plane_state);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 6aeaad587a20..53358e33df1b 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1117,10 +1117,7 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state,
 	clock = adjusted_mode->crtc_clock;
 	htotal = adjusted_mode->crtc_htotal;
 
-	if (plane->id == PLANE_CURSOR)
-		width = plane_state->base.crtc_w;
-	else
-		width = drm_rect_width(&plane_state->base.dst);
+	width = drm_rect_width(&plane_state->base.dst);
 
 	if (plane->id == PLANE_CURSOR) {
 		wm = intel_wm_method2(clock, htotal, width, cpp, latency);
@@ -2549,7 +2546,8 @@ static u32 ilk_compute_cur_wm(const struct intel_crtc_state *crtc_state,
 
 	return ilk_wm_method2(crtc_state->pixel_rate,
 			      crtc_state->base.adjusted_mode.crtc_htotal,
-			      plane_state->base.crtc_w, cpp, mem_value);
+			      drm_rect_width(&plane_state->base.dst),
+			      cpp, mem_value);
 }
 
 /* Only for WM_LP. */
@@ -4046,7 +4044,6 @@ static uint_fixed_16_16_t
 skl_plane_downscale_amount(const struct intel_crtc_state *crtc_state,
 			   const struct intel_plane_state *plane_state)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
 	u32 src_w, src_h, dst_w, dst_h;
 	uint_fixed_16_16_t fp_w_ratio, fp_h_ratio;
 	uint_fixed_16_16_t downscale_h, downscale_w;
@@ -4054,27 +4051,17 @@ skl_plane_downscale_amount(const struct intel_crtc_state *crtc_state,
 	if (WARN_ON(!intel_wm_plane_visible(crtc_state, plane_state)))
 		return u32_to_fixed16(0);
 
-	/* n.b., src is 16.16 fixed point, dst is whole integer */
-	if (plane->id == PLANE_CURSOR) {
-		/*
-		 * Cursors only support 0/180 degree rotation,
-		 * hence no need to account for rotation here.
-		 */
-		src_w = plane_state->base.src_w >> 16;
-		src_h = plane_state->base.src_h >> 16;
-		dst_w = plane_state->base.crtc_w;
-		dst_h = plane_state->base.crtc_h;
-	} else {
-		/*
-		 * Src coordinates are already rotated by 270 degrees for
-		 * the 90/270 degree plane rotation cases (to match the
-		 * GTT mapping), hence no need to account for rotation here.
-		 */
-		src_w = drm_rect_width(&plane_state->base.src) >> 16;
-		src_h = drm_rect_height(&plane_state->base.src) >> 16;
-		dst_w = drm_rect_width(&plane_state->base.dst);
-		dst_h = drm_rect_height(&plane_state->base.dst);
-	}
+	/*
+	 * Src coordinates are already rotated by 270 degrees for
+	 * the 90/270 degree plane rotation cases (to match the
+	 * GTT mapping), hence no need to account for rotation here.
+	 *
+	 * n.b., src is 16.16 fixed point, dst is whole integer.
+	 */
+	src_w = drm_rect_width(&plane_state->base.src) >> 16;
+	src_h = drm_rect_height(&plane_state->base.src) >> 16;
+	dst_w = drm_rect_width(&plane_state->base.dst);
+	dst_h = drm_rect_height(&plane_state->base.dst);
 
 	fp_w_ratio = div_fixed16(src_w, dst_w);
 	fp_h_ratio = div_fixed16(src_h, dst_h);
@@ -4698,20 +4685,15 @@ skl_compute_plane_wm_params(const struct intel_crtc_state *crtc_state,
 			    const struct intel_plane_state *plane_state,
 			    struct skl_wm_params *wp, int color_plane)
 {
-	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
 	const struct drm_framebuffer *fb = plane_state->base.fb;
 	int width;
 
-	if (plane->id == PLANE_CURSOR) {
-		width = plane_state->base.crtc_w;
-	} else {
-		/*
-		 * Src coordinates are already rotated by 270 degrees for
-		 * the 90/270 degree plane rotation cases (to match the
-		 * GTT mapping), hence no need to account for rotation here.
-		 */
-		width = drm_rect_width(&plane_state->base.src) >> 16;
-	}
+	/*
+	 * Src coordinates are already rotated by 270 degrees for
+	 * the 90/270 degree plane rotation cases (to match the
+	 * GTT mapping), hence no need to account for rotation here.
+	 */
+	width = drm_rect_width(&plane_state->base.src) >> 16;
 
 	return skl_compute_wm_params(crtc_state, width,
 				     fb->format, fb->modifier,
-- 
cgit v1.2.3


From 11bcf5f78905b90baae8fb01e16650664ed0cb00 Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Tue, 2 Apr 2019 11:30:37 +0800
Subject: drm/edid: Add 6 bpc quirk for SDC panel in Lenovo G50

Another panel that needs 6BPC quirk.

BugLink: https://bugs.launchpad.net/bugs/1819968
Cc: <stable@vger.kernel.org> # v4.8+
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190402033037.21877-1-kai.heng.feng@canonical.com
---
 drivers/gpu/drm/drm_edid.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 82a4ceed3fcf..6b0177112e18 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -159,6 +159,9 @@ static const struct edid_quirk {
 	/* Medion MD 30217 PG */
 	{ "MED", 0x7b8, EDID_QUIRK_PREFER_LARGE_75 },
 
+	/* Lenovo G50 */
+	{ "SDC", 18514, EDID_QUIRK_FORCE_6BPC },
+
 	/* Panel in Samsung NP700G7A-S01PL notebook reports 6bpc */
 	{ "SEC", 0xd033, EDID_QUIRK_FORCE_8BPC },
 
-- 
cgit v1.2.3


From 574878f98c05aaae7e046cd18be9195f8da38cbd Mon Sep 17 00:00:00 2001
From: Fuqian Huang <huangfq.daxian@gmail.com>
Date: Thu, 10 Oct 2019 16:32:09 +0800
Subject: xen/grant-table: remove unnecessary printing

xen_auto_xlat_grant_frames.vaddr is definitely NULL in this case.
So the address printing is unnecessary.

Signed-off-by: Fuqian Huang <huangfq.daxian@gmail.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/grant-table.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index 7ea6fb6a2e5d..49b381e104ef 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -1363,8 +1363,7 @@ static int gnttab_setup(void)
 	if (xen_feature(XENFEAT_auto_translated_physmap) && gnttab_shared.addr == NULL) {
 		gnttab_shared.addr = xen_auto_xlat_grant_frames.vaddr;
 		if (gnttab_shared.addr == NULL) {
-			pr_warn("gnttab share frames (addr=0x%08lx) is not mapped!\n",
-				(unsigned long)xen_auto_xlat_grant_frames.vaddr);
+			pr_warn("gnttab share frames is not mapped!\n");
 			return -ENOMEM;
 		}
 	}
-- 
cgit v1.2.3


From c3d79a83ca10d2026fd1cce096cde2d8e316592e Mon Sep 17 00:00:00 2001
From: Qiang Yu <yuq825@gmail.com>
Date: Sun, 22 Sep 2019 15:49:00 +0800
Subject: dma-buf/resv: fix exclusive fence get
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This causes kernel crash when testing lima driver.

Cc: Christian König <christian.koenig@amd.com>
Fixes: b8c036dfc66f ("dma-buf: simplify reservation_object_get_fences_rcu a bit")
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190922074900.853-1-yuq825@gmail.com
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 drivers/dma-buf/dma-resv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 42a8f3f11681..709002515550 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -471,7 +471,7 @@ unlock:
 	if (pfence_excl)
 		*pfence_excl = fence_excl;
 	else if (fence_excl)
-		shared[++shared_count] = fence_excl;
+		shared[shared_count++] = fence_excl;
 
 	if (!shared_count) {
 		kfree(shared);
-- 
cgit v1.2.3


From 5e48e55fb57a9026e6b3b6961def6d2aeb210659 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 10 Oct 2019 14:30:46 +0200
Subject: MAINTAINERS: Remove Simon as Renesas SoC Co-Maintainer

At the end of the v5.3 upstream kernel development cycle, Simon stepped
down from his role as Renesas SoC maintainer.

Remove his maintainership, git repository, and branch from the
MAINTAINERS file, and add an entry to the CREDITS file to honor his
work.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 CREDITS     | 4 ++++
 MAINTAINERS | 4 ----
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/CREDITS b/CREDITS
index 8b67a85844b5..031605d46b4d 100644
--- a/CREDITS
+++ b/CREDITS
@@ -1637,6 +1637,10 @@ S: Panoramastrasse 18
 S: D-69126 Heidelberg
 S: Germany
 
+N: Simon Horman
+M: horms@verge.net.au
+D: Renesas ARM/ARM64 SoC maintainer
+
 N: Christopher Horn
 E: chorn@warwick.net
 D: Miscellaneous sysctl hacks
diff --git a/MAINTAINERS b/MAINTAINERS
index 94ce075907a0..d44d6732510d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2165,12 +2165,10 @@ F:	arch/arm64/boot/dts/realtek/
 F:	Documentation/devicetree/bindings/arm/realtek.yaml
 
 ARM/RENESAS ARM64 ARCHITECTURE
-M:	Simon Horman <horms@verge.net.au>
 M:	Geert Uytterhoeven <geert+renesas@glider.be>
 M:	Magnus Damm <magnus.damm@gmail.com>
 L:	linux-renesas-soc@vger.kernel.org
 Q:	http://patchwork.kernel.org/project/linux-renesas-soc/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-devel.git next
 S:	Supported
 F:	arch/arm64/boot/dts/renesas/
@@ -2282,12 +2280,10 @@ S:	Maintained
 F:	drivers/media/platform/s5p-mfc/
 
 ARM/SHMOBILE ARM ARCHITECTURE
-M:	Simon Horman <horms@verge.net.au>
 M:	Geert Uytterhoeven <geert+renesas@glider.be>
 M:	Magnus Damm <magnus.damm@gmail.com>
 L:	linux-renesas-soc@vger.kernel.org
 Q:	http://patchwork.kernel.org/project/linux-renesas-soc/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-devel.git next
 S:	Supported
 F:	arch/arm/boot/dts/emev2*
-- 
cgit v1.2.3


From ee7f5225dc3cc7c19df1603597532ff34571f895 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 8 Oct 2019 14:41:55 -0500
Subject: xen: Stop abusing DT of_dma_configure API

As the removed comments say, these aren't DT based devices.
of_dma_configure() is going to stop allowing a NULL DT node and calling
it will no longer work.

The comment is also now out of date as of commit 9ab91e7c5c51 ("arm64:
default to the direct mapping in get_arch_dma_ops"). Direct mapping
is now the default rather than dma_dummy_ops.

According to Stefano and Oleksandr, the only other part needed is
setting the DMA masks and there's no reason to restrict the masks to
32-bits. So set the masks to 64 bits.

Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Julien Grall <julien.grall@arm.com>
Cc: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Cc: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: xen-devel@lists.xenproject.org
Signed-off-by: Rob Herring <robh@kernel.org>
Acked-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/gpu/drm/xen/xen_drm_front.c | 12 ++----------
 drivers/xen/gntdev.c                | 13 ++-----------
 2 files changed, 4 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c
index 84aa4d61dc42..3406dfc9a605 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.c
+++ b/drivers/gpu/drm/xen/xen_drm_front.c
@@ -716,17 +716,9 @@ static int xen_drv_probe(struct xenbus_device *xb_dev,
 	struct device *dev = &xb_dev->dev;
 	int ret;
 
-	/*
-	 * The device is not spawn from a device tree, so arch_setup_dma_ops
-	 * is not called, thus leaving the device with dummy DMA ops.
-	 * This makes the device return error on PRIME buffer import, which
-	 * is not correct: to fix this call of_dma_configure() with a NULL
-	 * node to set default DMA ops.
-	 */
-	dev->coherent_dma_mask = DMA_BIT_MASK(32);
-	ret = of_dma_configure(dev, NULL, true);
+	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (ret < 0) {
-		DRM_ERROR("Cannot setup DMA ops, ret %d", ret);
+		DRM_ERROR("Cannot setup DMA mask, ret %d", ret);
 		return ret;
 	}
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index a446a7221e13..81401f386c9c 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -22,6 +22,7 @@
 
 #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
 
+#include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -34,9 +35,6 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/refcount.h>
-#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
-#include <linux/of_device.h>
-#endif
 
 #include <xen/xen.h>
 #include <xen/grant_table.h>
@@ -625,14 +623,7 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 	flip->private_data = priv;
 #ifdef CONFIG_XEN_GRANT_DMA_ALLOC
 	priv->dma_dev = gntdev_miscdev.this_device;
-
-	/*
-	 * The device is not spawn from a device tree, so arch_setup_dma_ops
-	 * is not called, thus leaving the device with dummy DMA ops.
-	 * Fix this by calling of_dma_configure() with a NULL node to set
-	 * default DMA ops.
-	 */
-	of_dma_configure(priv->dma_dev, NULL, true);
+	dma_coerce_mask_and_coherent(priv->dma_dev, DMA_BIT_MASK(64));
 #endif
 	pr_debug("priv %p\n", priv);
 
-- 
cgit v1.2.3


From 862488105b84ca744b3d8ff131e0fcfe10644be1 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 19 Sep 2019 11:44:27 +0530
Subject: nbd: fix possible sysfs duplicate warning

1. nbd_put takes the mutex and drops nbd->ref to 0. It then does
idr_remove and drops the mutex.

2. nbd_genl_connect takes the mutex. idr_find/idr_for_each fails
to find an existing device, so it does nbd_dev_add.

3. just before the nbd_put could call nbd_dev_remove or not finished
totally, but if nbd_dev_add try to add_disk, we can hit:

debugfs: Directory 'nbd1' with parent 'block' already present!

This patch will make sure all the disk add/remove stuff are done
by holding the nbd_index_mutex lock.

Reported-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/nbd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index ac07e8c94c79..478aa86fc1f2 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -248,8 +248,8 @@ static void nbd_put(struct nbd_device *nbd)
 	if (refcount_dec_and_mutex_lock(&nbd->refs,
 					&nbd_index_mutex)) {
 		idr_remove(&nbd_index_idr, nbd->index);
-		mutex_unlock(&nbd_index_mutex);
 		nbd_dev_remove(nbd);
+		mutex_unlock(&nbd_index_mutex);
 	}
 }
 
-- 
cgit v1.2.3


From 9a61363a6310dda769b8c7601fc9de8ed81e6bc8 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Thu, 10 Oct 2019 16:05:19 +0100
Subject: drm/i915/perf: store the associated engine of a stream

We'll use this information later to verify that a client trying to
reconfigure the stream does so on the right engine. For now, we want to
pull the knowledge of which engine we use into a central property.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191010150520.26488-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_perf.c       | 30 ++++++++++++++++++++++++++----
 drivers/gpu/drm/i915/i915_perf_types.h |  5 +++++
 2 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 5a34cad7d824..1a5c6591b9bb 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -197,6 +197,7 @@
 
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_pm.h"
+#include "gt/intel_engine_user.h"
 #include "gt/intel_lrc_reg.h"
 
 #include "i915_drv.h"
@@ -347,6 +348,7 @@ static const struct i915_oa_format gen8_plus_oa_formats[I915_OA_FORMAT_MAX] = {
  * @oa_format: An OA unit HW report format
  * @oa_periodic: Whether to enable periodic OA unit sampling
  * @oa_period_exponent: The OA unit sampling period is derived from this
+ * @engine: The engine (typically rcs0) being monitored by the OA unit
  *
  * As read_properties_unlocked() enumerates and validates the properties given
  * to open a stream of metrics the configuration is built up in the structure
@@ -363,6 +365,8 @@ struct perf_open_properties {
 	int oa_format;
 	bool oa_periodic;
 	int oa_period_exponent;
+
+	struct intel_engine_cs *engine;
 };
 
 static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer);
@@ -1205,7 +1209,7 @@ static struct intel_context *oa_pin_context(struct i915_perf_stream *stream)
 	int err;
 
 	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
-		if (ce->engine->class != RENDER_CLASS)
+		if (ce->engine != stream->engine) /* first match! */
 			continue;
 
 		/*
@@ -2127,7 +2131,13 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	int format_size;
 	int ret;
 
-	/* If the sysfs metrics/ directory wasn't registered for some
+	if (!props->engine) {
+		DRM_DEBUG("OA engine not specified\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * If the sysfs metrics/ directory wasn't registered for some
 	 * reason then don't let userspace try their luck with config
 	 * IDs
 	 */
@@ -2146,7 +2156,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		return -ENODEV;
 	}
 
-	/* To avoid the complexity of having to accurately filter
+	/*
+	 * To avoid the complexity of having to accurately filter
 	 * counter reports and marshal to the appropriate client
 	 * we currently only allow exclusive access
 	 */
@@ -2160,6 +2171,9 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		return -EINVAL;
 	}
 
+	stream->engine = props->engine;
+	stream->gt = stream->engine->gt;
+
 	stream->sample_size = sizeof(struct drm_i915_perf_record_header);
 
 	format_size = perf->oa_formats[props->oa_format].size;
@@ -2711,7 +2725,6 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 	}
 
 	stream->perf = perf;
-	stream->gt = &perf->i915->gt;
 	stream->ctx = specific_ctx;
 
 	ret = i915_oa_stream_init(stream, param, props);
@@ -2796,6 +2809,15 @@ static int read_properties_unlocked(struct i915_perf *perf,
 		return -EINVAL;
 	}
 
+	/* At the moment we only support using i915-perf on the RCS. */
+	props->engine = intel_engine_lookup_user(perf->i915,
+						 I915_ENGINE_CLASS_RENDER,
+						 0);
+	if (!props->engine) {
+		DRM_DEBUG("No RENDER-capable engines\n");
+		return -EINVAL;
+	}
+
 	/* Considering that ID = 0 is reserved and assuming that we don't
 	 * (currently) expect any configurations to ever specify duplicate
 	 * values for a particular property ID then the last _PROP_MAX value is
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 2d17059d32ee..82cd3b295037 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -140,6 +140,11 @@ struct i915_perf_stream {
 	 */
 	intel_wakeref_t wakeref;
 
+	/**
+	 * @engine: Engine associated with this performance stream.
+	 */
+	struct intel_engine_cs *engine;
+
 	/**
 	 * @sample_flags: Flags representing the `DRM_I915_PERF_PROP_SAMPLE_*`
 	 * properties given when opening a stream, representing the contents
-- 
cgit v1.2.3


From 52111c4628a29973d8be266f45b464318912b199 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 10 Oct 2019 16:05:20 +0100
Subject: drm/i915/perf: Store shortcut to intel_uncore

Now that we have the engine stored in i915_perf, we have a means of
accessing intel_gt should we require it. However, we are currently only
using the intel_gt to find the right intel_uncore, so replace our
i915_perf.gt pointer with the more useful i915_perf.uncore.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191010150520.26488-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_perf.c       | 48 +++++++++++++++++-----------------
 drivers/gpu/drm/i915/i915_perf_types.h |  4 +--
 2 files changed, 26 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 1a5c6591b9bb..77c3cef64548 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -419,14 +419,14 @@ static int get_oa_config(struct i915_perf *perf,
 
 static u32 gen8_oa_hw_tail_read(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 
 	return intel_uncore_read(uncore, GEN8_OATAILPTR) & GEN8_OATAILPTR_MASK;
 }
 
 static u32 gen7_oa_hw_tail_read(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 	u32 oastatus1 = intel_uncore_read(uncore, GEN7_OASTATUS1);
 
 	return oastatus1 & GEN7_OASTATUS1_TAIL_MASK;
@@ -656,7 +656,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 				  size_t count,
 				  size_t *offset)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 	int report_size = stream->oa_buffer.format_size;
 	u8 *oa_buf_base = stream->oa_buffer.vaddr;
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
@@ -866,7 +866,7 @@ static int gen8_oa_read(struct i915_perf_stream *stream,
 			size_t count,
 			size_t *offset)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 	u32 oastatus;
 	int ret;
 
@@ -945,7 +945,7 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream,
 				  size_t count,
 				  size_t *offset)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 	int report_size = stream->oa_buffer.format_size;
 	u8 *oa_buf_base = stream->oa_buffer.vaddr;
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
@@ -1077,7 +1077,7 @@ static int gen7_oa_read(struct i915_perf_stream *stream,
 			size_t count,
 			size_t *offset)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 	u32 oastatus1;
 	int ret;
 
@@ -1352,8 +1352,8 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 
 	free_oa_buffer(stream);
 
-	intel_uncore_forcewake_put(stream->gt->uncore, FORCEWAKE_ALL);
-	intel_runtime_pm_put(stream->gt->uncore->rpm, stream->wakeref);
+	intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL);
+	intel_runtime_pm_put(stream->uncore->rpm, stream->wakeref);
 
 	if (stream->ctx)
 		oa_put_render_ctx_id(stream);
@@ -1368,7 +1368,7 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 
 static void gen7_init_oa_buffer(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
 	unsigned long flags;
 
@@ -1416,7 +1416,7 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream)
 
 static void gen8_init_oa_buffer(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
 	unsigned long flags;
 
@@ -1565,7 +1565,7 @@ static void delay_after_mux(void)
 
 static int hsw_enable_metric_set(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 	const struct i915_oa_config *oa_config = stream->oa_config;
 
 	/*
@@ -1594,7 +1594,7 @@ static int hsw_enable_metric_set(struct i915_perf_stream *stream)
 
 static void hsw_disable_metric_set(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 
 	intel_uncore_rmw(uncore, GEN6_UCGCTL1,
 			 GEN6_CSUNIT_CLOCK_GATE_DISABLE, 0);
@@ -1911,7 +1911,7 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 
 static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 	const struct i915_oa_config *oa_config = stream->oa_config;
 	int ret;
 
@@ -1964,7 +1964,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 
 static void gen8_disable_metric_set(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 
 	/* Reset all contexts' slices/subslices configurations. */
 	gen8_configure_all_contexts(stream, NULL);
@@ -1974,7 +1974,7 @@ static void gen8_disable_metric_set(struct i915_perf_stream *stream)
 
 static void gen10_disable_metric_set(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 
 	/* Reset all contexts' slices/subslices configurations. */
 	gen8_configure_all_contexts(stream, NULL);
@@ -1985,7 +1985,7 @@ static void gen10_disable_metric_set(struct i915_perf_stream *stream)
 
 static void gen7_oa_enable(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 	struct i915_gem_context *ctx = stream->ctx;
 	u32 ctx_id = stream->specific_ctx_id;
 	bool periodic = stream->periodic;
@@ -2015,7 +2015,7 @@ static void gen7_oa_enable(struct i915_perf_stream *stream)
 
 static void gen8_oa_enable(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 	u32 report_format = stream->oa_buffer.format;
 
 	/*
@@ -2060,7 +2060,7 @@ static void i915_oa_stream_enable(struct i915_perf_stream *stream)
 
 static void gen7_oa_disable(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 
 	intel_uncore_write(uncore, GEN7_OACONTROL, 0);
 	if (intel_wait_for_register(uncore,
@@ -2071,7 +2071,7 @@ static void gen7_oa_disable(struct i915_perf_stream *stream)
 
 static void gen8_oa_disable(struct i915_perf_stream *stream)
 {
-	struct intel_uncore *uncore = stream->gt->uncore;
+	struct intel_uncore *uncore = stream->uncore;
 
 	intel_uncore_write(uncore, GEN8_OACONTROL, 0);
 	if (intel_wait_for_register(uncore,
@@ -2172,7 +2172,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	}
 
 	stream->engine = props->engine;
-	stream->gt = stream->engine->gt;
+	stream->uncore = stream->engine->gt->uncore;
 
 	stream->sample_size = sizeof(struct drm_i915_perf_record_header);
 
@@ -2218,8 +2218,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	 *   In our case we are expecting that taking pm + FORCEWAKE
 	 *   references will effectively disable RC6.
 	 */
-	stream->wakeref = intel_runtime_pm_get(stream->gt->uncore->rpm);
-	intel_uncore_forcewake_get(stream->gt->uncore, FORCEWAKE_ALL);
+	stream->wakeref = intel_runtime_pm_get(stream->uncore->rpm);
+	intel_uncore_forcewake_get(stream->uncore, FORCEWAKE_ALL);
 
 	ret = alloc_oa_buffer(stream);
 	if (ret)
@@ -2251,8 +2251,8 @@ err_enable:
 err_oa_buf_alloc:
 	put_oa_config(stream->oa_config);
 
-	intel_uncore_forcewake_put(stream->gt->uncore, FORCEWAKE_ALL);
-	intel_runtime_pm_put(stream->gt->uncore->rpm, stream->wakeref);
+	intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL);
+	intel_runtime_pm_put(stream->uncore->rpm, stream->wakeref);
 
 err_config:
 	if (stream->ctx)
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 82cd3b295037..a91ae2d1a543 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -130,9 +130,9 @@ struct i915_perf_stream {
 	struct i915_perf *perf;
 
 	/**
-	 * @gt: intel_gt container
+	 * @uncore: mmio access path
 	 */
-	struct intel_gt *gt;
+	struct intel_uncore *uncore;
 
 	/**
 	 * @wakeref: As we keep the device awake while the perf stream is
-- 
cgit v1.2.3


From b068a86071ca743de28a607a0b22b41b1a3f5fb3 Mon Sep 17 00:00:00 2001
From: James Ausmus <james.ausmus@intel.com>
Date: Wed, 9 Oct 2019 10:23:14 -0700
Subject: drm/i915: Move SAGV block time to dev_priv
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In prep for newer platforms having more complicated ways to determine
the SAGV block time, move the variable to dev_priv, and extract the
setting to an initial setup function. While we're at it, update the if
ladder to follow the new gen -> old gen order preference, and warn on
any non-specified gen.

v2: Shorten the function name (Ville), return directly (Ville), move
sagv_block_time_us value to dev_priv (Ville)

v3: Change sagv_block_time_us to u32 (Lucas), Change fallback value to
-1 (Lucas), use intel_has_sagv for setup check rather than hand-rolling
(Lucas)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: James Ausmus <james.ausmus@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004221449.1317-1-james.ausmus@intel.com
Link: https://patchwork.freedesktop.org/patch/msgid/20191009172315.11004-1-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h |  2 ++
 drivers/gpu/drm/i915/intel_pm.c | 33 ++++++++++++++++++++++++---------
 2 files changed, 26 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d284b04c492b..c46b339064c0 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1267,6 +1267,8 @@ struct drm_i915_private {
 		I915_SAGV_NOT_CONTROLLED
 	} sagv_status;
 
+	u32 sagv_block_time_us;
+
 	struct {
 		/*
 		 * Raw watermark latency values:
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 53358e33df1b..f00e64f9320c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3638,6 +3638,26 @@ intel_has_sagv(struct drm_i915_private *dev_priv)
 		dev_priv->sagv_status != I915_SAGV_NOT_CONTROLLED;
 }
 
+static void
+skl_setup_sagv_block_time(struct drm_i915_private *dev_priv)
+{
+	if (IS_GEN(dev_priv, 11)) {
+		dev_priv->sagv_block_time_us = 10;
+		return;
+	} else if (IS_GEN(dev_priv, 10)) {
+		dev_priv->sagv_block_time_us = 20;
+		return;
+	} else if (IS_GEN(dev_priv, 9)) {
+		dev_priv->sagv_block_time_us = 30;
+		return;
+	} else {
+		MISSING_CASE(INTEL_GEN(dev_priv));
+	}
+
+	/* Default to an unusable block time */
+	dev_priv->sagv_block_time_us = -1;
+}
+
 /*
  * SAGV dynamically adjusts the system agent voltage and clock frequencies
  * depending on power and performance requirements. The display engine access
@@ -3726,18 +3746,10 @@ bool intel_can_enable_sagv(struct intel_atomic_state *state)
 	struct intel_crtc_state *crtc_state;
 	enum pipe pipe;
 	int level, latency;
-	int sagv_block_time_us;
 
 	if (!intel_has_sagv(dev_priv))
 		return false;
 
-	if (IS_GEN(dev_priv, 9))
-		sagv_block_time_us = 30;
-	else if (IS_GEN(dev_priv, 10))
-		sagv_block_time_us = 20;
-	else
-		sagv_block_time_us = 10;
-
 	/*
 	 * If there are no active CRTCs, no additional checks need be performed
 	 */
@@ -3784,7 +3796,7 @@ bool intel_can_enable_sagv(struct intel_atomic_state *state)
 		 * incur memory latencies higher than sagv_block_time_us we
 		 * can't enable SAGV.
 		 */
-		if (latency < sagv_block_time_us)
+		if (latency < dev_priv->sagv_block_time_us)
 			return false;
 	}
 
@@ -8985,6 +8997,9 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 	else if (IS_GEN(dev_priv, 5))
 		i915_ironlake_get_mem_freq(dev_priv);
 
+	if (intel_has_sagv(dev_priv))
+		skl_setup_sagv_block_time(dev_priv);
+
 	/* For FIFO watermark updates */
 	if (INTEL_GEN(dev_priv) >= 9) {
 		skl_setup_wm_latency(dev_priv);
-- 
cgit v1.2.3


From da80f04792fc0dddcc44201cb4ee96cb011755b6 Mon Sep 17 00:00:00 2001
From: James Ausmus <james.ausmus@intel.com>
Date: Wed, 9 Oct 2019 10:23:15 -0700
Subject: drm/i915/tgl: Read SAGV block time from PCODE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Starting from TGL, we now need to read the SAGV block time via a PCODE
mailbox, rather than having a static value.

BSpec: 49326

v2: Fix up pcode val data type (Ville), tighten variable scope (Ville)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: James Ausmus <james.ausmus@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004221449.1317-2-james.ausmus@intel.com
Link: https://patchwork.freedesktop.org/patch/msgid/20191009172315.11004-2-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h |  1 +
 drivers/gpu/drm/i915/intel_pm.c | 15 ++++++++++++++-
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 1dc067fc57ab..0fb9030b89f1 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -8878,6 +8878,7 @@ enum {
 #define     GEN9_SAGV_DISABLE			0x0
 #define     GEN9_SAGV_IS_DISABLED		0x1
 #define     GEN9_SAGV_ENABLE			0x3
+#define GEN12_PCODE_READ_SAGV_BLOCK_TIME_US	0x23
 #define GEN6_PCODE_DATA				_MMIO(0x138128)
 #define   GEN6_PCODE_FREQ_IA_RATIO_SHIFT	8
 #define   GEN6_PCODE_FREQ_RING_RATIO_SHIFT	16
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index f00e64f9320c..b306e2338f5a 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3641,7 +3641,20 @@ intel_has_sagv(struct drm_i915_private *dev_priv)
 static void
 skl_setup_sagv_block_time(struct drm_i915_private *dev_priv)
 {
-	if (IS_GEN(dev_priv, 11)) {
+	if (INTEL_GEN(dev_priv) >= 12) {
+		u32 val = 0;
+		int ret;
+
+		ret = sandybridge_pcode_read(dev_priv,
+					     GEN12_PCODE_READ_SAGV_BLOCK_TIME_US,
+					     &val, NULL);
+		if (!ret) {
+			dev_priv->sagv_block_time_us = val;
+			return;
+		}
+
+		DRM_DEBUG_DRIVER("Couldn't read SAGV block time!\n");
+	} else if (IS_GEN(dev_priv, 11)) {
 		dev_priv->sagv_block_time_us = 10;
 		return;
 	} else if (IS_GEN(dev_priv, 10)) {
-- 
cgit v1.2.3


From 38dffe1e4dde1d3174fdce09d67370412843ebb5 Mon Sep 17 00:00:00 2001
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
Date: Thu, 10 Oct 2019 23:01:57 +0800
Subject: MIPS: elf_hwcap: Export userspace ASEs

A Golang developer reported MIPS hwcap isn't reflecting instructions
that the processor actually supported so programs can't apply optimized
code at runtime.

Thus we export the ASEs that can be used in userspace programs.

Reported-by: Meng Zhuo <mengzhuo1203@gmail.com>
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: linux-mips@vger.kernel.org
Cc: Paul Burton <paul.burton@mips.com>
Cc: <stable@vger.kernel.org> # 4.14+
Signed-off-by: Paul Burton <paul.burton@mips.com>
---
 arch/mips/include/uapi/asm/hwcap.h | 11 +++++++++++
 arch/mips/kernel/cpu-probe.c       | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+)

diff --git a/arch/mips/include/uapi/asm/hwcap.h b/arch/mips/include/uapi/asm/hwcap.h
index a2aba4b059e6..1ade1daa4921 100644
--- a/arch/mips/include/uapi/asm/hwcap.h
+++ b/arch/mips/include/uapi/asm/hwcap.h
@@ -6,5 +6,16 @@
 #define HWCAP_MIPS_R6		(1 << 0)
 #define HWCAP_MIPS_MSA		(1 << 1)
 #define HWCAP_MIPS_CRC32	(1 << 2)
+#define HWCAP_MIPS_MIPS16	(1 << 3)
+#define HWCAP_MIPS_MDMX     (1 << 4)
+#define HWCAP_MIPS_MIPS3D   (1 << 5)
+#define HWCAP_MIPS_SMARTMIPS (1 << 6)
+#define HWCAP_MIPS_DSP      (1 << 7)
+#define HWCAP_MIPS_DSP2     (1 << 8)
+#define HWCAP_MIPS_DSP3     (1 << 9)
+#define HWCAP_MIPS_MIPS16E2 (1 << 10)
+#define HWCAP_LOONGSON_MMI  (1 << 11)
+#define HWCAP_LOONGSON_EXT  (1 << 12)
+#define HWCAP_LOONGSON_EXT2 (1 << 13)
 
 #endif /* _UAPI_ASM_HWCAP_H */
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index c2eb392597bf..f521cbf934e7 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -2180,6 +2180,39 @@ void cpu_probe(void)
 		elf_hwcap |= HWCAP_MIPS_MSA;
 	}
 
+	if (cpu_has_mips16)
+		elf_hwcap |= HWCAP_MIPS_MIPS16;
+
+	if (cpu_has_mdmx)
+		elf_hwcap |= HWCAP_MIPS_MDMX;
+
+	if (cpu_has_mips3d)
+		elf_hwcap |= HWCAP_MIPS_MIPS3D;
+
+	if (cpu_has_smartmips)
+		elf_hwcap |= HWCAP_MIPS_SMARTMIPS;
+
+	if (cpu_has_dsp)
+		elf_hwcap |= HWCAP_MIPS_DSP;
+
+	if (cpu_has_dsp2)
+		elf_hwcap |= HWCAP_MIPS_DSP2;
+
+	if (cpu_has_dsp3)
+		elf_hwcap |= HWCAP_MIPS_DSP3;
+
+	if (cpu_has_mips16e2)
+		elf_hwcap |= HWCAP_MIPS_MIPS16E2;
+
+	if (cpu_has_loongson_mmi)
+		elf_hwcap |= HWCAP_LOONGSON_MMI;
+
+	if (cpu_has_loongson_ext)
+		elf_hwcap |= HWCAP_LOONGSON_EXT;
+
+	if (cpu_has_loongson_ext2)
+		elf_hwcap |= HWCAP_LOONGSON_EXT2;
+
 	if (cpu_has_vz)
 		cpu_probe_vz(c);
 
-- 
cgit v1.2.3


From 2f2b4fd674cadd8c6b40eb629e140a14db4068fd Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Thu, 10 Oct 2019 18:54:03 +0000
Subject: MIPS: Disable Loongson MMI instructions for kernel build
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GCC 9.x automatically enables support for Loongson MMI instructions when
using some -march= flags, and then errors out when -msoft-float is
specified with:

  cc1: error: ‘-mloongson-mmi’ must be used with ‘-mhard-float’

The kernel shouldn't be using these MMI instructions anyway, just as it
doesn't use floating point instructions. Explicitly disable them in
order to fix the build with GCC 9.x.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Fixes: 3702bba5eb4f ("MIPS: Loongson: Add GCC 4.4 support for Loongson2E")
Fixes: 6f7a251a259e ("MIPS: Loongson: Add basic Loongson 2F support")
Fixes: 5188129b8c9f ("MIPS: Loongson-3: Improve -march option and move it to Platform")
Cc: Huacai Chen <chenhc@lemote.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: stable@vger.kernel.org # v2.6.32+
Cc: linux-mips@vger.kernel.org
---
 arch/mips/loongson64/Platform | 4 ++++
 arch/mips/vdso/Makefile       | 1 +
 2 files changed, 5 insertions(+)

diff --git a/arch/mips/loongson64/Platform b/arch/mips/loongson64/Platform
index c1a4d4dc4665..9f79908f5063 100644
--- a/arch/mips/loongson64/Platform
+++ b/arch/mips/loongson64/Platform
@@ -66,6 +66,10 @@ else
       $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64)
 endif
 
+# Some -march= flags enable MMI instructions, and GCC complains about that
+# support being enabled alongside -msoft-float. Thus explicitly disable MMI.
+cflags-y += $(call cc-option,-mno-loongson-mmi)
+
 #
 # Loongson Machines' Support
 #
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index 807f0f782f75..996a934ece7d 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -15,6 +15,7 @@ ccflags-vdso := \
 	$(filter -mmicromips,$(KBUILD_CFLAGS)) \
 	$(filter -march=%,$(KBUILD_CFLAGS)) \
 	$(filter -m%-float,$(KBUILD_CFLAGS)) \
+	$(filter -mno-loongson-%,$(KBUILD_CFLAGS)) \
 	-D__VDSO__
 
 ifdef CONFIG_CC_IS_CLANG
-- 
cgit v1.2.3


From 1047ec868332034d1fbcb2fae19fe6d4cb869ff2 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Fri, 4 Oct 2019 09:58:54 -0400
Subject: NFSv4: Fix leak of clp->cl_acceptor string

Our client can issue multiple SETCLIENTID operations to the same
server in some circumstances. Ensure that calls to
nfs4_proc_setclientid() after the first one do not overwrite the
previously allocated cl_acceptor string.

unreferenced object 0xffff888461031800 (size 32):
  comm "mount.nfs", pid 2227, jiffies 4294822467 (age 1407.749s)
  hex dump (first 32 bytes):
    6e 66 73 40 6b 6c 69 6d 74 2e 69 62 2e 31 30 31  nfs@klimt.ib.101
    35 67 72 61 6e 67 65 72 2e 6e 65 74 00 00 00 00  5granger.net....
  backtrace:
    [<00000000ab820188>] __kmalloc+0x128/0x176
    [<00000000eeaf4ec8>] gss_stringify_acceptor+0xbd/0x1a7 [auth_rpcgss]
    [<00000000e85e3382>] nfs4_proc_setclientid+0x34e/0x46c [nfsv4]
    [<000000003d9cf1fa>] nfs40_discover_server_trunking+0x7a/0xed [nfsv4]
    [<00000000b81c3787>] nfs4_discover_server_trunking+0x81/0x244 [nfsv4]
    [<000000000801b55f>] nfs4_init_client+0x1b0/0x238 [nfsv4]
    [<00000000977daf7f>] nfs4_set_client+0xfe/0x14d [nfsv4]
    [<0000000053a68a2a>] nfs4_create_server+0x107/0x1db [nfsv4]
    [<0000000088262019>] nfs4_remote_mount+0x2c/0x59 [nfsv4]
    [<00000000e84a2fd0>] legacy_get_tree+0x2d/0x4c
    [<00000000797e947c>] vfs_get_tree+0x20/0xc7
    [<00000000ecabaaa8>] fc_mount+0xe/0x36
    [<00000000f15fafc2>] vfs_kern_mount+0x74/0x8d
    [<00000000a3ff4e26>] nfs_do_root_mount+0x8a/0xa3 [nfsv4]
    [<00000000d1c2b337>] nfs4_try_mount+0x58/0xad [nfsv4]
    [<000000004c9bddee>] nfs_fs_mount+0x820/0x869 [nfs]

Fixes: f11b2a1cfbf5 ("nfs4: copy acceptor name from context ... ")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 fs/nfs/nfs4proc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 11eafcfc490b..ab8ca20fd579 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6106,6 +6106,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 
 	status = nfs4_call_sync_custom(&task_setup_data);
 	if (setclientid.sc_cred) {
+		kfree(clp->cl_acceptor);
 		clp->cl_acceptor = rpcauth_stringify_acceptor(setclientid.sc_cred);
 		put_rpccred(setclientid.sc_cred);
 	}
-- 
cgit v1.2.3


From af84537dbd1b39505d1f3d8023029b4a59666513 Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Wed, 2 Oct 2019 10:40:55 -0400
Subject: SUNRPC: fix race to sk_err after xs_error_report

Since commit 4f8943f80883 ("SUNRPC: Replace direct task wakeups from
softirq context") there has been a race to the value of the sk_err if both
XPRT_SOCK_WAKE_ERROR and XPRT_SOCK_WAKE_DISCONNECT are set.  In that case,
we may end up losing the sk_err value that existed when xs_error_report was
called.

Fix this by reverting to the previous behavior: instead of using SO_ERROR
to retrieve the value at a later time (which might also return sk_err_soft),
copy the sk_err value onto struct sock_xprt, and use that value to wake
pending tasks.

Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Fixes: 4f8943f80883 ("SUNRPC: Replace direct task wakeups from softirq context")
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
---
 include/linux/sunrpc/xprtsock.h |  1 +
 net/sunrpc/xprtsock.c           | 17 ++++++++---------
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h
index 7638dbe7bc50..a940de03808d 100644
--- a/include/linux/sunrpc/xprtsock.h
+++ b/include/linux/sunrpc/xprtsock.h
@@ -61,6 +61,7 @@ struct sock_xprt {
 	struct mutex		recv_mutex;
 	struct sockaddr_storage	srcaddr;
 	unsigned short		srcport;
+	int			xprt_err;
 
 	/*
 	 * UDP socket buffer size parameters
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 9ac88722fa83..70e52f567b2a 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1249,19 +1249,21 @@ static void xs_error_report(struct sock *sk)
 {
 	struct sock_xprt *transport;
 	struct rpc_xprt *xprt;
-	int err;
 
 	read_lock_bh(&sk->sk_callback_lock);
 	if (!(xprt = xprt_from_sock(sk)))
 		goto out;
 
 	transport = container_of(xprt, struct sock_xprt, xprt);
-	err = -sk->sk_err;
-	if (err == 0)
+	transport->xprt_err = -sk->sk_err;
+	if (transport->xprt_err == 0)
 		goto out;
 	dprintk("RPC:       xs_error_report client %p, error=%d...\n",
-			xprt, -err);
-	trace_rpc_socket_error(xprt, sk->sk_socket, err);
+			xprt, -transport->xprt_err);
+	trace_rpc_socket_error(xprt, sk->sk_socket, transport->xprt_err);
+
+	/* barrier ensures xprt_err is set before XPRT_SOCK_WAKE_ERROR */
+	smp_mb__before_atomic();
 	xs_run_error_worker(transport, XPRT_SOCK_WAKE_ERROR);
  out:
 	read_unlock_bh(&sk->sk_callback_lock);
@@ -2476,7 +2478,6 @@ static void xs_wake_write(struct sock_xprt *transport)
 static void xs_wake_error(struct sock_xprt *transport)
 {
 	int sockerr;
-	int sockerr_len = sizeof(sockerr);
 
 	if (!test_bit(XPRT_SOCK_WAKE_ERROR, &transport->sock_state))
 		return;
@@ -2485,9 +2486,7 @@ static void xs_wake_error(struct sock_xprt *transport)
 		goto out;
 	if (!test_and_clear_bit(XPRT_SOCK_WAKE_ERROR, &transport->sock_state))
 		goto out;
-	if (kernel_getsockopt(transport->sock, SOL_SOCKET, SO_ERROR,
-				(char *)&sockerr, &sockerr_len) != 0)
-		goto out;
+	sockerr = xchg(&transport->xprt_err, 0);
 	if (sockerr < 0)
 		xprt_wake_pending_tasks(&transport->xprt, sockerr);
 out:
-- 
cgit v1.2.3


From 4ebcb113edcc498888394821bca2e60ef89c6ff3 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 9 Oct 2019 20:55:48 +0200
Subject: r8169: fix jumbo packet handling on resume from suspend

Mariusz reported that invalid packets are sent after resume from
suspend if jumbo packets are active. It turned out that his BIOS
resets chip settings to non-jumbo on resume. Most chip settings are
re-initialized on resume from suspend by calling rtl_hw_start(),
so let's add configuring jumbo to this function.
There's nothing wrong with the commit marked as fixed, it's just
the first one where the patch applies cleanly.

Fixes: 7366016d2d4c ("r8169: read common register for PCI commit")
Reported-by: Mariusz Bialonczyk <manio@skyboo.net>
Tested-by: Mariusz Bialonczyk <manio@skyboo.net>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 drivers/net/ethernet/realtek/r8169_main.c | 35 ++++++++++---------------------
 1 file changed, 11 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 74f81fe03810..350b0d949611 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -4146,6 +4146,14 @@ static void rtl_hw_jumbo_disable(struct rtl8169_private *tp)
 	rtl_lock_config_regs(tp);
 }
 
+static void rtl_jumbo_config(struct rtl8169_private *tp, int mtu)
+{
+	if (mtu > ETH_DATA_LEN)
+		rtl_hw_jumbo_enable(tp);
+	else
+		rtl_hw_jumbo_disable(tp);
+}
+
 DECLARE_RTL_COND(rtl_chipcmd_cond)
 {
 	return RTL_R8(tp, ChipCmd) & CmdReset;
@@ -4442,11 +4450,6 @@ static void rtl8168g_set_pause_thresholds(struct rtl8169_private *tp,
 static void rtl_hw_start_8168bb(struct rtl8169_private *tp)
 {
 	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
-
-	if (tp->dev->mtu <= ETH_DATA_LEN) {
-		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B |
-					 PCI_EXP_DEVCTL_NOSNOOP_EN);
-	}
 }
 
 static void rtl_hw_start_8168bef(struct rtl8169_private *tp)
@@ -4462,9 +4465,6 @@ static void __rtl_hw_start_8168cp(struct rtl8169_private *tp)
 
 	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
 
-	if (tp->dev->mtu <= ETH_DATA_LEN)
-		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
-
 	rtl_disable_clock_request(tp);
 }
 
@@ -4490,9 +4490,6 @@ static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp)
 	rtl_set_def_aspm_entry_latency(tp);
 
 	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
-
-	if (tp->dev->mtu <= ETH_DATA_LEN)
-		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 }
 
 static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp)
@@ -4503,9 +4500,6 @@ static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp)
 
 	/* Magic. */
 	RTL_W8(tp, DBG_REG, 0x20);
-
-	if (tp->dev->mtu <= ETH_DATA_LEN)
-		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 }
 
 static void rtl_hw_start_8168c_1(struct rtl8169_private *tp)
@@ -4611,9 +4605,6 @@ static void rtl_hw_start_8168e_1(struct rtl8169_private *tp)
 
 	rtl_ephy_init(tp, e_info_8168e_1);
 
-	if (tp->dev->mtu <= ETH_DATA_LEN)
-		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
-
 	rtl_disable_clock_request(tp);
 
 	/* Reset tx FIFO pointer */
@@ -4636,9 +4627,6 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 
 	rtl_ephy_init(tp, e_info_8168e_2);
 
-	if (tp->dev->mtu <= ETH_DATA_LEN)
-		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
-
 	rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000);
 	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000);
 	rtl_set_fifo_size(tp, 0x10, 0x10, 0x02, 0x06);
@@ -5485,6 +5473,8 @@ static void rtl_hw_start(struct  rtl8169_private *tp)
 	rtl_set_rx_tx_desc_registers(tp);
 	rtl_lock_config_regs(tp);
 
+	rtl_jumbo_config(tp, tp->dev->mtu);
+
 	/* Initially a 10 us delay. Turned it into a PCI commit. - FR */
 	RTL_R16(tp, CPlusCmd);
 	RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb);
@@ -5498,10 +5488,7 @@ static int rtl8169_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	if (new_mtu > ETH_DATA_LEN)
-		rtl_hw_jumbo_enable(tp);
-	else
-		rtl_hw_jumbo_disable(tp);
+	rtl_jumbo_config(tp, new_mtu);
 
 	dev->mtu = new_mtu;
 	netdev_update_features(dev);
-- 
cgit v1.2.3


From 2168da4594040529f6a6cb413c22668a4402f83c Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 9 Oct 2019 12:18:31 -0700
Subject: net: update net_dim documentation after rename

Commit 8960b38932be ("linux/dim: Rename externally used net_dim
members") renamed the net_dim API, removing the "net_" prefix from the
structures and functions. The patch didn't update the net_dim.txt
documentation file.

Fix the documentation so that its examples match the current code.

Fixes: 8960b38932be ("linux/dim: Rename externally used net_dim members", 2019-06-25)
Fixes: c002bd529d71 ("linux/dim: Rename externally exposed macros", 2019-06-25)
Fixes: 4f75da3666c0 ("linux/dim: Move implementation to .c files")
Cc: Tal Gilboa <talgi@mellanox.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 Documentation/networking/net_dim.txt | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/Documentation/networking/net_dim.txt b/Documentation/networking/net_dim.txt
index 9cb31c5e2dcd..9bdb7d5a3ba3 100644
--- a/Documentation/networking/net_dim.txt
+++ b/Documentation/networking/net_dim.txt
@@ -92,16 +92,16 @@ under some conditions.
 Part III: Registering a Network Device to DIM
 ==============================================
 
-Net DIM API exposes the main function net_dim(struct net_dim *dim,
-struct net_dim_sample end_sample). This function is the entry point to the Net
+Net DIM API exposes the main function net_dim(struct dim *dim,
+struct dim_sample end_sample). This function is the entry point to the Net
 DIM algorithm and has to be called every time the driver would like to check if
 it should change interrupt moderation parameters. The driver should provide two
-data structures: struct net_dim and struct net_dim_sample. Struct net_dim
+data structures: struct dim and struct dim_sample. Struct dim
 describes the state of DIM for a specific object (RX queue, TX queue,
 other queues, etc.). This includes the current selected profile, previous data
 samples, the callback function provided by the driver and more.
-Struct net_dim_sample describes a data sample, which will be compared to the
-data sample stored in struct net_dim in order to decide on the algorithm's next
+Struct dim_sample describes a data sample, which will be compared to the
+data sample stored in struct dim in order to decide on the algorithm's next
 step. The sample should include bytes, packets and interrupts, measured by
 the driver.
 
@@ -110,9 +110,9 @@ main net_dim() function. The recommended method is to call net_dim() on each
 interrupt. Since Net DIM has a built-in moderation and it might decide to skip
 iterations under certain conditions, there is no need to moderate the net_dim()
 calls as well. As mentioned above, the driver needs to provide an object of type
-struct net_dim to the net_dim() function call. It is advised for each entity
-using Net DIM to hold a struct net_dim as part of its data structure and use it
-as the main Net DIM API object. The struct net_dim_sample should hold the latest
+struct dim to the net_dim() function call. It is advised for each entity
+using Net DIM to hold a struct dim as part of its data structure and use it
+as the main Net DIM API object. The struct dim_sample should hold the latest
 bytes, packets and interrupts count. No need to perform any calculations, just
 include the raw data.
 
@@ -132,19 +132,19 @@ usage is not complete but it should make the outline of the usage clear.
 
 my_driver.c:
 
-#include <linux/net_dim.h>
+#include <linux/dim.h>
 
 /* Callback for net DIM to schedule on a decision to change moderation */
 void my_driver_do_dim_work(struct work_struct *work)
 {
-	/* Get struct net_dim from struct work_struct */
-	struct net_dim *dim = container_of(work, struct net_dim,
-					   work);
+	/* Get struct dim from struct work_struct */
+	struct dim *dim = container_of(work, struct dim,
+				       work);
 	/* Do interrupt moderation related stuff */
 	...
 
 	/* Signal net DIM work is done and it should move to next iteration */
-	dim->state = NET_DIM_START_MEASURE;
+	dim->state = DIM_START_MEASURE;
 }
 
 /* My driver's interrupt handler */
@@ -152,13 +152,13 @@ int my_driver_handle_interrupt(struct my_driver_entity *my_entity, ...)
 {
 	...
 	/* A struct to hold current measured data */
-	struct net_dim_sample dim_sample;
+	struct dim_sample dim_sample;
 	...
 	/* Initiate data sample struct with current data */
-	net_dim_sample(my_entity->events,
-		       my_entity->packets,
-		       my_entity->bytes,
-		       &dim_sample);
+	dim_update_sample(my_entity->events,
+		          my_entity->packets,
+		          my_entity->bytes,
+		          &dim_sample);
 	/* Call net DIM */
 	net_dim(&my_entity->dim, dim_sample);
 	...
-- 
cgit v1.2.3


From 29ee2701529e1905c0e948688f9688c68c8d4ea4 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 10 Oct 2019 10:16:09 +0200
Subject: net/smc: fix SMCD link group creation with VLAN id

If creation of an SMCD link group with VLAN id fails, the initial
smc_ism_get_vlan() step has to be reverted as well.

Fixes: c6ba7c9ba43d ("net/smc: add base infrastructure for SMC-D and ISM")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/smc/smc_core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 4ca50ddf8d16..88556f0251ab 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -213,7 +213,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 	lgr = kzalloc(sizeof(*lgr), GFP_KERNEL);
 	if (!lgr) {
 		rc = SMC_CLC_DECL_MEM;
-		goto out;
+		goto ism_put_vlan;
 	}
 	lgr->is_smcd = ini->is_smcd;
 	lgr->sync_err = 0;
@@ -289,6 +289,9 @@ clear_llc_lnk:
 	smc_llc_link_clear(lnk);
 free_lgr:
 	kfree(lgr);
+ism_put_vlan:
+	if (ini->is_smcd && ini->vlan_id)
+		smc_ism_put_vlan(ini->ism_dev, ini->vlan_id);
 out:
 	if (rc < 0) {
 		if (rc == -ENOMEM)
-- 
cgit v1.2.3


From 882dcfe5a1785c20f45820cbe6fec4b8b647c946 Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Thu, 10 Oct 2019 10:16:10 +0200
Subject: net/smc: receive returns without data

smc_cdc_rxed_any_close_or_senddone() is used as an end condition for the
receive loop. This conflicts with smc_cdc_msg_recv_action() which could
run in parallel and set the bits checked by
smc_cdc_rxed_any_close_or_senddone() before the receive is processed.
In that case we could return from receive with no data, although data is
available. The same applies to smc_rx_wait().
Fix this by checking for RCV_SHUTDOWN only, which is set in
smc_cdc_msg_recv_action() after the receive was actually processed.

Fixes: 952310ccf2d8 ("smc: receive data from RMBE")
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/smc/smc_rx.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index 413a6abf227e..000002642288 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -211,8 +211,7 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo,
 	rc = sk_wait_event(sk, timeo,
 			   sk->sk_err ||
 			   sk->sk_shutdown & RCV_SHUTDOWN ||
-			   fcrit(conn) ||
-			   smc_cdc_rxed_any_close_or_senddone(conn),
+			   fcrit(conn),
 			   &wait);
 	remove_wait_queue(sk_sleep(sk), &wait);
 	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
@@ -310,7 +309,6 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
 			smc_rx_update_cons(smc, 0);
 
 		if (sk->sk_shutdown & RCV_SHUTDOWN ||
-		    smc_cdc_rxed_any_close_or_senddone(conn) ||
 		    conn->local_tx_ctrl.conn_state_flags.peer_conn_abort)
 			break;
 
-- 
cgit v1.2.3


From 107529e31a87acd475ff6a0f82745821b8f70fec Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Thu, 10 Oct 2019 10:16:11 +0200
Subject: net/smc: receive pending data after RCV_SHUTDOWN

smc_rx_recvmsg() first checks if data is available, and then if
RCV_SHUTDOWN is set. There is a race when smc_cdc_msg_recv_action() runs
in between these 2 checks, receives data and sets RCV_SHUTDOWN.
In that case smc_rx_recvmsg() would return from receive without to
process the available data.
Fix that with a final check for data available if RCV_SHUTDOWN is set.
Move the check for data into a function and call it twice.
And use the existing helper smc_rx_data_available().

Fixes: 952310ccf2d8 ("smc: receive data from RMBE")
Reviewed-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 net/smc/smc_rx.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index 000002642288..97e8369002d7 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -261,6 +261,18 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len,
 	return -EAGAIN;
 }
 
+static bool smc_rx_recvmsg_data_available(struct smc_sock *smc)
+{
+	struct smc_connection *conn = &smc->conn;
+
+	if (smc_rx_data_available(conn))
+		return true;
+	else if (conn->urg_state == SMC_URG_VALID)
+		/* we received a single urgent Byte - skip */
+		smc_rx_update_cons(smc, 0);
+	return false;
+}
+
 /* smc_rx_recvmsg - receive data from RMBE
  * @msg:	copy data to receive buffer
  * @pipe:	copy data to pipe if set - indicates splice() call
@@ -302,15 +314,18 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
 		if (read_done >= target || (pipe && read_done))
 			break;
 
-		if (atomic_read(&conn->bytes_to_rcv))
+		if (smc_rx_recvmsg_data_available(smc))
 			goto copy;
-		else if (conn->urg_state == SMC_URG_VALID)
-			/* we received a single urgent Byte - skip */
-			smc_rx_update_cons(smc, 0);
 
 		if (sk->sk_shutdown & RCV_SHUTDOWN ||
-		    conn->local_tx_ctrl.conn_state_flags.peer_conn_abort)
+		    conn->local_tx_ctrl.conn_state_flags.peer_conn_abort) {
+			/* smc_cdc_msg_recv_action() could have run after
+			 * above smc_rx_recvmsg_data_available()
+			 */
+			if (smc_rx_recvmsg_data_available(smc))
+				goto copy;
 			break;
+		}
 
 		if (read_done) {
 			if (sk->sk_err ||
-- 
cgit v1.2.3


From 7adf4eaf60f3d8c3584bed51fe7066d4dfc2cbe1 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 10 Oct 2019 21:42:58 -0600
Subject: io_uring: fix sequence logic for timeout requests

We have two ways a request can be deferred:

1) It's a regular request that depends on another one
2) It's a timeout that tracks completions

We have a shared helper to determine whether to defer, and that
attempts to make the right decision based on the request. But we
only have some of this information in the caller. Un-share the
two timeout/defer helpers so the caller can use the right one.

Fixes: 5262f567987d ("io_uring: IORING_OP_TIMEOUT support")
Reported-by: yangerkun <yangerkun@huawei.com>
Reviewed-by: Jackie Liu <liuyun01@kylinos.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 37 ++++++++++++++++++++-----------------
 1 file changed, 20 insertions(+), 17 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 2c44648217bd..38d274fc0f25 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -415,27 +415,27 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 	return ctx;
 }
 
+static inline bool __io_sequence_defer(struct io_ring_ctx *ctx,
+				       struct io_kiocb *req)
+{
+	return req->sequence != ctx->cached_cq_tail + ctx->rings->sq_dropped;
+}
+
 static inline bool io_sequence_defer(struct io_ring_ctx *ctx,
 				     struct io_kiocb *req)
 {
-	/* timeout requests always honor sequence */
-	if (!(req->flags & REQ_F_TIMEOUT) &&
-	    (req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN)
+	if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN)
 		return false;
 
-	return req->sequence != ctx->cached_cq_tail + ctx->rings->sq_dropped;
+	return __io_sequence_defer(ctx, req);
 }
 
-static struct io_kiocb *__io_get_deferred_req(struct io_ring_ctx *ctx,
-					      struct list_head *list)
+static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
 {
 	struct io_kiocb *req;
 
-	if (list_empty(list))
-		return NULL;
-
-	req = list_first_entry(list, struct io_kiocb, list);
-	if (!io_sequence_defer(ctx, req)) {
+	req = list_first_entry_or_null(&ctx->defer_list, struct io_kiocb, list);
+	if (req && !io_sequence_defer(ctx, req)) {
 		list_del_init(&req->list);
 		return req;
 	}
@@ -443,14 +443,17 @@ static struct io_kiocb *__io_get_deferred_req(struct io_ring_ctx *ctx,
 	return NULL;
 }
 
-static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
-{
-	return __io_get_deferred_req(ctx, &ctx->defer_list);
-}
-
 static struct io_kiocb *io_get_timeout_req(struct io_ring_ctx *ctx)
 {
-	return __io_get_deferred_req(ctx, &ctx->timeout_list);
+	struct io_kiocb *req;
+
+	req = list_first_entry_or_null(&ctx->timeout_list, struct io_kiocb, list);
+	if (req && !__io_sequence_defer(ctx, req)) {
+		list_del_init(&req->list);
+		return req;
+	}
+
+	return NULL;
 }
 
 static void __io_commit_cqring(struct io_ring_ctx *ctx)
-- 
cgit v1.2.3


From 2272905a4580f26630f7d652cc33935b59f96d4c Mon Sep 17 00:00:00 2001
From: Emmanuel Nicolet <emmanuel.nicolet@gmail.com>
Date: Tue, 8 Oct 2019 16:13:42 +0200
Subject: spufs: fix a crash in spufs_create_root()

The spu_fs_context was not set in fc->fs_private, this caused a crash
when accessing ctx->mode in spufs_create_root().

Fixes: d2e0981c3b9a ("vfs: Convert spufs to use the new mount API")
Signed-off-by: Emmanuel Nicolet <emmanuel.nicolet@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Link: https://lore.kernel.org/r/20191008141342.GA266797@gmail.com
---
 arch/powerpc/platforms/cell/spufs/inode.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 1d93e55a2de1..2dd452a047cd 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -761,6 +761,7 @@ static int spufs_init_fs_context(struct fs_context *fc)
 	ctx->gid = current_gid();
 	ctx->mode = 0755;
 
+	fc->fs_private = ctx;
 	fc->s_fs_info = sbi;
 	fc->ops = &spufs_context_ops;
 	return 0;
-- 
cgit v1.2.3


From 10deeac921647c929c67752d377f22e632d55d1c Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Fri, 20 Sep 2019 10:44:47 -0700
Subject: MAINTAINERS: kgdb: Add myself as a reviewer for kgdb/kdb

I'm interested in kdb / kgdb and have sent various fixes over the
years.  I'd like to get CCed on patches so I can be aware of them and
also help review.

Signed-off-by: Douglas Anderson <dianders@chromium.org>
Acked-by: Daniel Thompson <daniel.thompson@linaro.org>
Link: https://lore.kernel.org/r/20190920104404.1.I237e68e8825e2d6ac26f8e847f521fe2fcc3705a@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 296de2b51c83..acdd996774d6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9075,6 +9075,7 @@ F:	security/keys/
 KGDB / KDB /debug_core
 M:	Jason Wessel <jason.wessel@windriver.com>
 M:	Daniel Thompson <daniel.thompson@linaro.org>
+R:	Douglas Anderson <dianders@chromium.org>
 W:	http://kgdb.wiki.kernel.org/
 L:	kgdb-bugreport@lists.sourceforge.net
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jwessel/kgdb.git
-- 
cgit v1.2.3


From 442f1e746e8187b9deb1590176f6b0ff19686b11 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Mon, 30 Sep 2019 14:45:22 -0700
Subject: firmware: google: increment VPD key_len properly

Commit 4b708b7b1a2c ("firmware: google: check if size is valid when
decoding VPD data") adds length checks, but the new vpd_decode_entry()
function botched the logic -- it adds the key length twice, instead of
adding the key and value lengths separately.

On my local system, this means vpd.c's vpd_section_create_attribs() hits
an error case after the first attribute it parses, since it's no longer
looking at the correct offset. With this patch, I'm back to seeing all
the correct attributes in /sys/firmware/vpd/...

Fixes: 4b708b7b1a2c ("firmware: google: check if size is valid when decoding VPD data")
Cc: <stable@vger.kernel.org>
Cc: Hung-Te Lin <hungte@chromium.org>
Signed-off-by: Brian Norris <briannorris@chromium.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Reviewed-by: Guenter Roeck <groeck@chromium.org>
Link: https://lore.kernel.org/r/20190930214522.240680-1-briannorris@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/firmware/google/vpd_decode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/google/vpd_decode.c b/drivers/firmware/google/vpd_decode.c
index dda525c0f968..5c6f2a74f104 100644
--- a/drivers/firmware/google/vpd_decode.c
+++ b/drivers/firmware/google/vpd_decode.c
@@ -52,7 +52,7 @@ static int vpd_decode_entry(const u32 max_len, const u8 *input_buf,
 	if (max_len - consumed < *entry_len)
 		return VPD_FAIL;
 
-	consumed += decoded_len;
+	consumed += *entry_len;
 	*_consumed = consumed;
 	return VPD_OK;
 }
-- 
cgit v1.2.3


From 9c4a14f8cceeffa01334e3229888746aa7dd95fe Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 10 Oct 2019 08:14:25 +0100
Subject: drm/i915: Note the addition of timeslicing to the pretend scheduler

Since writing the comment that the scheduler is entirely passive, we've
added minimal timeslicing which adds the most primitive of active
elements (a timeout and reschedule).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191010071434.31195-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_scheduler_types.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h
index aad81acba9dc..d18e70550054 100644
--- a/drivers/gpu/drm/i915/i915_scheduler_types.h
+++ b/drivers/gpu/drm/i915/i915_scheduler_types.h
@@ -49,6 +49,15 @@ struct i915_sched_attr {
  * DAG of each request, we are able to insert it into a sorted queue when it
  * is ready, and are able to reorder its portion of the graph to accommodate
  * dynamic priority changes.
+ *
+ * Ok, there is now one active element to the "scheduler" in the backends.
+ * We let a new context run for a small amount of time before re-evaluating
+ * the run order. As we re-evaluate, we maintain the strict ordering of
+ * dependencies, but attempt to rotate the active contexts (the current context
+ * is put to the back of its priority queue, then reshuffling its dependents).
+ * This provides minimal timeslicing and prevents a userspace hog (e.g.
+ * something waiting on a user semaphore [VkEvent]) from denying service to
+ * others.
  */
 struct i915_sched_node {
 	struct list_head signalers_list; /* those before us, we depend upon */
-- 
cgit v1.2.3


From c97fb526ca0666e515e94f96e922dfc50467fd01 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 10 Oct 2019 08:14:26 +0100
Subject: drm/i915/execlists: Leave tell-tales as to why pending[] is bad

Before we BUG out with bad pending state, leave a telltale as to which
test failed.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191010071434.31195-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 30 +++++++++++++++++++++++++-----
 drivers/gpu/drm/i915/i915_gem.h     | 11 +++++++----
 2 files changed, 32 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index bd8ba98e35df..fd609ce4313a 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1089,25 +1089,45 @@ assert_pending_valid(const struct intel_engine_execlists *execlists,
 
 	trace_ports(execlists, msg, execlists->pending);
 
-	if (!execlists->pending[0])
+	if (!execlists->pending[0]) {
+		GEM_TRACE_ERR("Nothing pending for promotion!\n");
 		return false;
+	}
 
-	if (execlists->pending[execlists_num_ports(execlists)])
+	if (execlists->pending[execlists_num_ports(execlists)]) {
+		GEM_TRACE_ERR("Excess pending[%d] for promotion!\n",
+			      execlists_num_ports(execlists));
 		return false;
+	}
 
 	for (port = execlists->pending; (rq = *port); port++) {
-		if (ce == rq->hw_context)
+		if (ce == rq->hw_context) {
+			GEM_TRACE_ERR("Duplicate context in pending[%zd]\n",
+				      port - execlists->pending);
 			return false;
+		}
 
 		ce = rq->hw_context;
 		if (i915_request_completed(rq))
 			continue;
 
-		if (i915_active_is_idle(&ce->active))
+		if (i915_active_is_idle(&ce->active)) {
+			GEM_TRACE_ERR("Inactive context in pending[%zd]\n",
+				      port - execlists->pending);
+			return false;
+		}
+
+		if (!i915_vma_is_pinned(ce->state)) {
+			GEM_TRACE_ERR("Unpinned context in pending[%zd]\n",
+				      port - execlists->pending);
 			return false;
+		}
 
-		if (!i915_vma_is_pinned(ce->state))
+		if (!i915_vma_is_pinned(ce->ring->vma)) {
+			GEM_TRACE_ERR("Unpinned ringbuffer in pending[%zd]\n",
+				      port - execlists->pending);
 			return false;
+		}
 	}
 
 	return ce;
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 6795f1daa3d5..db20d2b0842b 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -37,10 +37,8 @@ struct drm_i915_private;
 #define GEM_SHOW_DEBUG() (drm_debug & DRM_UT_DRIVER)
 
 #define GEM_BUG_ON(condition) do { if (unlikely((condition))) {	\
-		pr_err("%s:%d GEM_BUG_ON(%s)\n", \
-		       __func__, __LINE__, __stringify(condition)); \
-		GEM_TRACE("%s:%d GEM_BUG_ON(%s)\n", \
-			  __func__, __LINE__, __stringify(condition)); \
+		GEM_TRACE_ERR("%s:%d GEM_BUG_ON(%s)\n", \
+			      __func__, __LINE__, __stringify(condition)); \
 		BUG(); \
 		} \
 	} while(0)
@@ -66,11 +64,16 @@ struct drm_i915_private;
 
 #if IS_ENABLED(CONFIG_DRM_I915_TRACE_GEM)
 #define GEM_TRACE(...) trace_printk(__VA_ARGS__)
+#define GEM_TRACE_ERR(...) do {						\
+	pr_err(__VA_ARGS__);						\
+	trace_printk(__VA_ARGS__);					\
+} while (0)
 #define GEM_TRACE_DUMP() ftrace_dump(DUMP_ALL)
 #define GEM_TRACE_DUMP_ON(expr) \
 	do { if (expr) ftrace_dump(DUMP_ALL); } while (0)
 #else
 #define GEM_TRACE(...) do { } while (0)
+#define GEM_TRACE_ERR(...) do { } while (0)
 #define GEM_TRACE_DUMP() do { } while (0)
 #define GEM_TRACE_DUMP_ON(expr) BUILD_BUG_ON_INVALID(expr)
 #endif
-- 
cgit v1.2.3


From 062795fcdcb2d22822fb42644b1d76a8ad8439b3 Mon Sep 17 00:00:00 2001
From: Christian Borntraeger <borntraeger@de.ibm.com>
Date: Tue, 8 Oct 2019 17:02:32 +0200
Subject: s390/uaccess: avoid (false positive) compiler warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Depending on inlining decisions by the compiler, __get/put_user_fn
might become out of line. Then the compiler is no longer able to tell
that size can only be 1,2,4 or 8 due to the check in __get/put_user
resulting in false positives like

./arch/s390/include/asm/uaccess.h: In function ‘__put_user_fn’:
./arch/s390/include/asm/uaccess.h:113:9: warning: ‘rc’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  113 |  return rc;
      |         ^~
./arch/s390/include/asm/uaccess.h: In function ‘__get_user_fn’:
./arch/s390/include/asm/uaccess.h:143:9: warning: ‘rc’ may be used uninitialized in this function [-Wmaybe-uninitialized]
  143 |  return rc;
      |         ^~

These functions are supposed to be always inlined. Mark it as such.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/include/asm/uaccess.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index bd2fd9a7821d..a470f1fa9f2a 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -83,7 +83,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n);
 	__rc;							\
 })
 
-static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
+static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
 {
 	unsigned long spec = 0x010000UL;
 	int rc;
@@ -113,7 +113,7 @@ static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
 	return rc;
 }
 
-static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
+static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
 {
 	unsigned long spec = 0x01UL;
 	int rc;
-- 
cgit v1.2.3


From cbbf2787782ca5d17b479deb962a07f0421a7932 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 11 Oct 2019 11:33:45 +0100
Subject: drm/i915/execlists: Only mark incomplete requests as -EIO on
 cancelling

Only the requests that have not completed do we want to change the
status of to signal the -EIO when cancelling the inflight set of requests
upon wedging.

Reported-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011103345.26013-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index fd609ce4313a..13fa61ed85de 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -247,8 +247,12 @@ static void __context_pin_release(struct intel_context *ce)
 
 static void mark_eio(struct i915_request *rq)
 {
-	if (!i915_request_signaled(rq))
-		dma_fence_set_error(&rq->fence, -EIO);
+	if (i915_request_completed(rq))
+		return;
+
+	GEM_BUG_ON(i915_request_signaled(rq));
+
+	dma_fence_set_error(&rq->fence, -EIO);
 	i915_request_mark_complete(rq);
 }
 
-- 
cgit v1.2.3


From c461e8df0c9bc46b3696dfb5d1df2f09d755af53 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 26 Sep 2019 13:43:10 -0400
Subject: tools/virtio: more stubs

fix test module build.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 tools/virtio/crypto/hash.h       | 0
 tools/virtio/linux/dma-mapping.h | 2 ++
 2 files changed, 2 insertions(+)
 create mode 100644 tools/virtio/crypto/hash.h

diff --git a/tools/virtio/crypto/hash.h b/tools/virtio/crypto/hash.h
new file mode 100644
index 000000000000..e69de29bb2d1
diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h
index f91aeb5fe571..8f41cd6bd5c0 100644
--- a/tools/virtio/linux/dma-mapping.h
+++ b/tools/virtio/linux/dma-mapping.h
@@ -29,4 +29,6 @@ enum dma_data_direction {
 #define dma_unmap_single(...) do { } while (0)
 #define dma_unmap_page(...) do { } while (0)
 
+#define dma_max_mapping_size(...) SIZE_MAX
+
 #endif
-- 
cgit v1.2.3


From 48f9bcf91461b43249949f4e172b5c0245dde751 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 5 Oct 2019 09:46:41 -0700
Subject: net: sctp: Rename fallthrough label to unhandled

fallthrough will become a pseudo reserved keyword so this only use of
fallthrough is better renamed to allow it.

Signed-off-by: Joe Perches <joe@perches.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 net/sctp/sm_make_chunk.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index e41ed2e0ae7d..48d63956a68c 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2155,7 +2155,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net,
 	case SCTP_PARAM_SET_PRIMARY:
 		if (ep->asconf_enable)
 			break;
-		goto fallthrough;
+		goto unhandled;
 
 	case SCTP_PARAM_HOST_NAME_ADDRESS:
 		/* Tell the peer, we won't support this param.  */
@@ -2166,11 +2166,11 @@ static enum sctp_ierror sctp_verify_param(struct net *net,
 	case SCTP_PARAM_FWD_TSN_SUPPORT:
 		if (ep->prsctp_enable)
 			break;
-		goto fallthrough;
+		goto unhandled;
 
 	case SCTP_PARAM_RANDOM:
 		if (!ep->auth_enable)
-			goto fallthrough;
+			goto unhandled;
 
 		/* SCTP-AUTH: Secion 6.1
 		 * If the random number is not 32 byte long the association
@@ -2187,7 +2187,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net,
 
 	case SCTP_PARAM_CHUNKS:
 		if (!ep->auth_enable)
-			goto fallthrough;
+			goto unhandled;
 
 		/* SCTP-AUTH: Section 3.2
 		 * The CHUNKS parameter MUST be included once in the INIT or
@@ -2203,7 +2203,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net,
 
 	case SCTP_PARAM_HMAC_ALGO:
 		if (!ep->auth_enable)
-			goto fallthrough;
+			goto unhandled;
 
 		hmacs = (struct sctp_hmac_algo_param *)param.p;
 		n_elt = (ntohs(param.p->length) -
@@ -2226,7 +2226,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net,
 			retval = SCTP_IERROR_ABORT;
 		}
 		break;
-fallthrough:
+unhandled:
 	default:
 		pr_debug("%s: unrecognized param:%d for chunk:%d\n",
 			 __func__, ntohs(param.p->type), cid);
-- 
cgit v1.2.3


From 294f69e662d1570703e9b56e95be37a9fd3afba5 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 5 Oct 2019 09:46:42 -0700
Subject: compiler_attributes.h: Add 'fallthrough' pseudo keyword for
 switch/case use

Reserve the pseudo keyword 'fallthrough' for the ability to convert the
various case block /* fallthrough */ style comments to appear to be an
actual reserved word with the same gcc case block missing fallthrough
warning capability.

All switch/case blocks now should end in one of:

	break;
	fallthrough;
	goto <label>;
	return [expression];
	continue;

In C mode, GCC supports the __fallthrough__ attribute since 7.1,
the same time the warning and the comment parsing were introduced.

fallthrough devolves to an empty "do {} while (0)" if the compiler
version (any version less than gcc 7) does not support the attribute.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Suggested-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/compiler_attributes.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 6b318efd8a74..cdf016596659 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -40,6 +40,7 @@
 # define __GCC4_has_attribute___noclone__             1
 # define __GCC4_has_attribute___nonstring__           0
 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8)
+# define __GCC4_has_attribute___fallthrough__         0
 #endif
 
 /*
@@ -185,6 +186,22 @@
 # define __noclone
 #endif
 
+/*
+ * Add the pseudo keyword 'fallthrough' so case statement blocks
+ * must end with any of these keywords:
+ *   break;
+ *   fallthrough;
+ *   goto <label>;
+ *   return [expression];
+ *
+ *  gcc: https://gcc.gnu.org/onlinedocs/gcc/Statement-Attributes.html#Statement-Attributes
+ */
+#if __has_attribute(__fallthrough__)
+# define fallthrough                    __attribute__((__fallthrough__))
+#else
+# define fallthrough                    do {} while (0)  /* fallthrough */
+#endif
+
 /*
  * Note the missing underscores.
  *
-- 
cgit v1.2.3


From b9918bdcac1ff7bf11f1ab64708267c73f9b2552 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Sat, 5 Oct 2019 09:46:43 -0700
Subject: Documentation/process: Add fallthrough pseudo-keyword

Describe the fallthrough pseudo-keyword.

Convert the coding-style.rst example to the keyword style.
Add description and links to deprecated.rst.

Miguel Ojeda comments on the eventual [[fallthrough]] syntax:
 "Note that C17/C18 does not have [[fallthrough]].

  C++17 introduced it, as it is mentioned above. I would keep the
  __attribute__((fallthrough)) -> [[fallthrough]] change you did,
  though, since that is indeed the standard syntax (given the paragraph
  references C++17).

  I was told by Aaron Ballman (who is proposing them for C) that it is
  more or less likely that it becomes standardized in C2x. However, it
  is still not added to the draft (other attributes are already,
  though). See N2268 and N2269:

     http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2268.pdf (fallthrough)
     http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2269.pdf (attributes in general)"

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/process/coding-style.rst |  2 +-
 Documentation/process/deprecated.rst   | 33 +++++++++++++++++++++++----------
 2 files changed, 24 insertions(+), 11 deletions(-)

diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst
index f4a2198187f9..ada573b7d703 100644
--- a/Documentation/process/coding-style.rst
+++ b/Documentation/process/coding-style.rst
@@ -56,7 +56,7 @@ instead of ``double-indenting`` the ``case`` labels.  E.g.:
 	case 'K':
 	case 'k':
 		mem <<= 10;
-		/* fall through */
+		fallthrough;
 	default:
 		break;
 	}
diff --git a/Documentation/process/deprecated.rst b/Documentation/process/deprecated.rst
index 053b24a6dd38..179f2a5625a0 100644
--- a/Documentation/process/deprecated.rst
+++ b/Documentation/process/deprecated.rst
@@ -122,14 +122,27 @@ memory adjacent to the stack (when built without `CONFIG_VMAP_STACK=y`)
 
 Implicit switch case fall-through
 ---------------------------------
-The C language allows switch cases to "fall through" when
-a "break" statement is missing at the end of a case. This,
-however, introduces ambiguity in the code, as it's not always
-clear if the missing break is intentional or a bug. As there
-have been a long list of flaws `due to missing "break" statements
+The C language allows switch cases to "fall-through" when a "break" statement
+is missing at the end of a case. This, however, introduces ambiguity in the
+code, as it's not always clear if the missing break is intentional or a bug.
+
+As there have been a long list of flaws `due to missing "break" statements
 <https://cwe.mitre.org/data/definitions/484.html>`_, we no longer allow
-"implicit fall-through". In order to identify an intentional fall-through
-case, we have adopted the marking used by static analyzers: a comment
-saying `/* Fall through */`. Once the C++17 `__attribute__((fallthrough))`
-is more widely handled by C compilers, static analyzers, and IDEs, we can
-switch to using that instead.
+"implicit fall-through".
+
+In order to identify intentional fall-through cases, we have adopted a
+pseudo-keyword macro 'fallthrough' which expands to gcc's extension
+__attribute__((__fallthrough__)).  `Statement Attributes
+<https://gcc.gnu.org/onlinedocs/gcc/Statement-Attributes.html>`_
+
+When the C17/C18  [[fallthrough]] syntax is more commonly supported by
+C compilers, static analyzers, and IDEs, we can switch to using that syntax
+for the macro pseudo-keyword.
+
+All switch/case blocks must end in one of:
+
+	break;
+	fallthrough;
+	continue;
+	goto <label>;
+	return [expression];
-- 
cgit v1.2.3


From 86109a691a454e08cbe0356400268cb2a81f1997 Mon Sep 17 00:00:00 2001
From: Chris von Recklinghausen <crecklin@redhat.com>
Date: Thu, 10 Oct 2019 13:22:47 -0400
Subject: arm64: Fix kcore macros after 52-bit virtual addressing fallout

We export the entire kernel address space (i.e. the whole of the TTBR1
address range) via /proc/kcore. The kc_vaddr_to_offset() and
kc_offset_to_vaddr() macros are intended to convert between a kernel
virtual address and its offset relative to the start of the TTBR1
address space.

Prior to commit:

  14c127c957c1c607 ("arm64: mm: Flip kernel VA space")

... the offset was calculated relative to VA_START, which at the time
was the start of the TTBR1 address space. At this time, PAGE_OFFSET
pointed to the high half of the TTBR1 address space where arm64's
linear map lived.

That commit swapped the position of VA_START and PAGE_OFFSET, but
failed to update kc_vaddr_to_offset() or kc_offset_to_vaddr(), so
since then the two macros behave incorrectly.

Note that VA_START was subsequently renamed to PAGE_END in commit:

  77ad4ce69321abbe ("arm64: memory: rename VA_START to PAGE_END")

As the generic implementations of the two macros calculate the offset
relative to PAGE_OFFSET (which is now the start of the TTBR1 address
space), we can delete the arm64 implementation and use those.

Fixes: 14c127c957c1c607 ("arm64: mm: Flip kernel VA space")
Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Chris von Recklinghausen <crecklin@redhat.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/pgtable.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7576df00eb50..8330810f699e 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -876,9 +876,6 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 
 #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0)
 
-#define kc_vaddr_to_offset(v)	((v) & ~PAGE_END)
-#define kc_offset_to_vaddr(o)	((o) | PAGE_END)
-
 #ifdef CONFIG_ARM64_PA_BITS_52
 #define phys_to_ttbr(addr)	(((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52)
 #else
-- 
cgit v1.2.3


From 2aa85f246c181b1fa89f27e8e20c5636426be624 Mon Sep 17 00:00:00 2001
From: Steve Wahl <steve.wahl@hpe.com>
Date: Tue, 24 Sep 2019 16:03:55 -0500
Subject: x86/boot/64: Make level2_kernel_pgt pages invalid outside kernel area

Our hardware (UV aka Superdome Flex) has address ranges marked
reserved by the BIOS. Access to these ranges is caught as an error,
causing the BIOS to halt the system.

Initial page tables mapped a large range of physical addresses that
were not checked against the list of BIOS reserved addresses, and
sometimes included reserved addresses in part of the mapped range.
Including the reserved range in the map allowed processor speculative
accesses to the reserved range, triggering a BIOS halt.

Used early in booting, the page table level2_kernel_pgt addresses 1
GiB divided into 2 MiB pages, and it was set up to linearly map a full
 1 GiB of physical addresses that included the physical address range
of the kernel image, as chosen by KASLR.  But this also included a
large range of unused addresses on either side of the kernel image.
And unlike the kernel image's physical address range, this extra
mapped space was not checked against the BIOS tables of usable RAM
addresses.  So there were times when the addresses chosen by KASLR
would result in processor accessible mappings of BIOS reserved
physical addresses.

The kernel code did not directly access any of this extra mapped
space, but having it mapped allowed the processor to issue speculative
accesses into reserved memory, causing system halts.

This was encountered somewhat rarely on a normal system boot, and much
more often when starting the crash kernel if "crashkernel=512M,high"
was specified on the command line (this heavily restricts the physical
address of the crash kernel, in our case usually within 1 GiB of
reserved space).

The solution is to invalidate the pages of this table outside the kernel
image's space before the page table is activated. It fixes this problem
on our hardware.

 [ bp: Touchups. ]

Signed-off-by: Steve Wahl <steve.wahl@hpe.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Brijesh Singh <brijesh.singh@amd.com>
Cc: dimitri.sivanich@hpe.com
Cc: Feng Tang <feng.tang@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jordan Borgner <mail@jordan-borgner.de>
Cc: Juergen Gross <jgross@suse.com>
Cc: mike.travis@hpe.com
Cc: russ.anderson@hpe.com
Cc: stable@vger.kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86-ml <x86@kernel.org>
Cc: Zhenzhong Duan <zhenzhong.duan@oracle.com>
Link: https://lkml.kernel.org/r/9c011ee51b081534a7a15065b1681d200298b530.1569358539.git.steve.wahl@hpe.com
---
 arch/x86/kernel/head64.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 29ffa495bd1c..206a4b6144c2 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -222,13 +222,31 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	 * we might write invalid pmds, when the kernel is relocated
 	 * cleanup_highmap() fixes this up along with the mappings
 	 * beyond _end.
+	 *
+	 * Only the region occupied by the kernel image has so far
+	 * been checked against the table of usable memory regions
+	 * provided by the firmware, so invalidate pages outside that
+	 * region. A page table entry that maps to a reserved area of
+	 * memory would allow processor speculation into that area,
+	 * and on some hardware (particularly the UV platform) even
+	 * speculative access to some reserved areas is caught as an
+	 * error, causing the BIOS to halt the system.
 	 */
 
 	pmd = fixup_pointer(level2_kernel_pgt, physaddr);
-	for (i = 0; i < PTRS_PER_PMD; i++) {
+
+	/* invalidate pages before the kernel image */
+	for (i = 0; i < pmd_index((unsigned long)_text); i++)
+		pmd[i] &= ~_PAGE_PRESENT;
+
+	/* fixup pages that are part of the kernel image */
+	for (; i <= pmd_index((unsigned long)_end); i++)
 		if (pmd[i] & _PAGE_PRESENT)
 			pmd[i] += load_delta;
-	}
+
+	/* invalidate pages after the kernel image */
+	for (; i < PTRS_PER_PMD; i++)
+		pmd[i] &= ~_PAGE_PRESENT;
 
 	/*
 	 * Fixup phys_base - remove the memory encryption mask to obtain
-- 
cgit v1.2.3


From 1869dbe87cb94dc9a218ae1d9301dea3678bd4ff Mon Sep 17 00:00:00 2001
From: Steve Wahl <steve.wahl@hpe.com>
Date: Tue, 24 Sep 2019 16:04:31 -0500
Subject: x86/boot/64: Round memory hole size up to next PMD page

The kernel image map is created using PMD pages, which can include
some extra space beyond what's actually needed.  Round the size of the
memory hole we search for up to the next PMD boundary, to be certain
all of the space to be mapped is usable RAM and includes no reserved
areas.

Signed-off-by: Steve Wahl <steve.wahl@hpe.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Brijesh Singh <brijesh.singh@amd.com>
Cc: dimitri.sivanich@hpe.com
Cc: Feng Tang <feng.tang@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jordan Borgner <mail@jordan-borgner.de>
Cc: Juergen Gross <jgross@suse.com>
Cc: mike.travis@hpe.com
Cc: russ.anderson@hpe.com
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86-ml <x86@kernel.org>
Cc: Zhenzhong Duan <zhenzhong.duan@oracle.com>
Link: https://lkml.kernel.org/r/df4f49f05c0c27f108234eb93db5c613d09ea62e.1569358539.git.steve.wahl@hpe.com
---
 arch/x86/boot/compressed/misc.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 53ac0cb2396d..9652d5c2afda 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -345,6 +345,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 {
 	const unsigned long kernel_total_size = VO__end - VO__text;
 	unsigned long virt_addr = LOAD_PHYSICAL_ADDR;
+	unsigned long needed_size;
 
 	/* Retain x86 boot parameters pointer passed from startup_32/64. */
 	boot_params = rmode;
@@ -379,26 +380,38 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 
+	/*
+	 * The memory hole needed for the kernel is the larger of either
+	 * the entire decompressed kernel plus relocation table, or the
+	 * entire decompressed kernel plus .bss and .brk sections.
+	 *
+	 * On X86_64, the memory is mapped with PMD pages. Round the
+	 * size up so that the full extent of PMD pages mapped is
+	 * included in the check against the valid memory table
+	 * entries. This ensures the full mapped area is usable RAM
+	 * and doesn't include any reserved areas.
+	 */
+	needed_size = max(output_len, kernel_total_size);
+#ifdef CONFIG_X86_64
+	needed_size = ALIGN(needed_size, MIN_KERNEL_ALIGN);
+#endif
+
 	/* Report initial kernel position details. */
 	debug_putaddr(input_data);
 	debug_putaddr(input_len);
 	debug_putaddr(output);
 	debug_putaddr(output_len);
 	debug_putaddr(kernel_total_size);
+	debug_putaddr(needed_size);
 
 #ifdef CONFIG_X86_64
 	/* Report address of 32-bit trampoline */
 	debug_putaddr(trampoline_32bit);
 #endif
 
-	/*
-	 * The memory hole needed for the kernel is the larger of either
-	 * the entire decompressed kernel plus relocation table, or the
-	 * entire decompressed kernel plus .bss and .brk sections.
-	 */
 	choose_random_location((unsigned long)input_data, input_len,
 				(unsigned long *)&output,
-				max(output_len, kernel_total_size),
+				needed_size,
 				&virt_addr);
 
 	/* Validate memory location choices. */
-- 
cgit v1.2.3


From 78e31c42261779a01bc73472d0f65f15378e9de3 Mon Sep 17 00:00:00 2001
From: Jeffrey Hugo <jeffrey.l.hugo@gmail.com>
Date: Fri, 11 Oct 2019 06:39:39 -0700
Subject: drm/msm/dsi: Implement reset correctly

On msm8998, vblank timeouts are observed because the DSI controller is not
reset properly, which ends up stalling the MDP.  This is because the reset
logic is not correct per the hardware documentation.

The documentation states that after asserting reset, software should wait
some time (no indication of how long), or poll the status register until it
returns 0 before deasserting reset.

wmb() is insufficient for this purpose since it just ensures ordering, not
timing between writes.  Since asserting and deasserting reset occurs on the
same register, ordering is already guaranteed by the architecture, making
the wmb extraneous.

Since we would define a timeout for polling the status register to avoid a
possible infinite loop, lets just use a static delay of 20 ms, since 16.666
ms is the time available to process one frame at 60 fps.

Fixes: a689554ba6ed ("drm/msm: Initial add DSI connector support")
Cc: Hai Li <hali@codeaurora.org>
Cc: Rob Clark <robdclark@gmail.com>
Signed-off-by: Jeffrey Hugo <jeffrey.l.hugo@gmail.com>
Reviewed-by: Sean Paul <sean@poorly.run>
[seanpaul renamed RESET_DELAY to DSI_RESET_TOGGLE_DELAY_MS]
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011133939.16551-1-jeffrey.l.hugo@gmail.com
---
 drivers/gpu/drm/msm/dsi/dsi_host.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 663ff9f4fac9..1e7b1be25bb0 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -26,6 +26,8 @@
 #include "dsi_cfg.h"
 #include "msm_kms.h"
 
+#define DSI_RESET_TOGGLE_DELAY_MS 20
+
 static int dsi_get_version(const void __iomem *base, u32 *major, u32 *minor)
 {
 	u32 ver;
@@ -986,7 +988,7 @@ static void dsi_sw_reset(struct msm_dsi_host *msm_host)
 	wmb(); /* clocks need to be enabled before reset */
 
 	dsi_write(msm_host, REG_DSI_RESET, 1);
-	wmb(); /* make sure reset happen */
+	msleep(DSI_RESET_TOGGLE_DELAY_MS); /* make sure reset happen */
 	dsi_write(msm_host, REG_DSI_RESET, 0);
 }
 
@@ -1396,7 +1398,7 @@ static void dsi_sw_reset_restore(struct msm_dsi_host *msm_host)
 
 	/* dsi controller can only be reset while clocks are running */
 	dsi_write(msm_host, REG_DSI_RESET, 1);
-	wmb();	/* make sure reset happen */
+	msleep(DSI_RESET_TOGGLE_DELAY_MS); /* make sure reset happen */
 	dsi_write(msm_host, REG_DSI_RESET, 0);
 	wmb();	/* controller out of reset */
 	dsi_write(msm_host, REG_DSI_CTRL, data0);
-- 
cgit v1.2.3


From 54895010a893cdbf0aaf34fbd7719d750b557eb2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 11 Oct 2019 18:38:23 +0100
Subject: drm/i915: Add an rcu_barrier option to i915_drop_caches

Sometimes a test has to wait for RCU to complete a grace period and
perform its callbacks, for example waiting for a close(fd) to actually
perform the fput(filp) and so trigger all the callbacks such as closing
GEM contexts. There is no trivial means of triggering an RCU barrier
from userspace, so add one for our convenience in
debugfs/i915_drop_caches

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011173823.20432-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_debugfs.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 277f31297f29..e575761550ac 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3599,6 +3599,7 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_wedged_fops,
 #define DROP_IDLE	BIT(6)
 #define DROP_RESET_ACTIVE	BIT(7)
 #define DROP_RESET_SEQNO	BIT(8)
+#define DROP_RCU	BIT(9)
 #define DROP_ALL (DROP_UNBOUND	| \
 		  DROP_BOUND	| \
 		  DROP_RETIRE	| \
@@ -3607,7 +3608,8 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_wedged_fops,
 		  DROP_SHRINK_ALL |\
 		  DROP_IDLE	| \
 		  DROP_RESET_ACTIVE | \
-		  DROP_RESET_SEQNO)
+		  DROP_RESET_SEQNO | \
+		  DROP_RCU)
 static int
 i915_drop_caches_get(void *data, u64 *val)
 {
@@ -3659,6 +3661,9 @@ i915_drop_caches_set(void *data, u64 val)
 		i915_gem_shrink_all(i915);
 	fs_reclaim_release(GFP_KERNEL);
 
+	if (val & DROP_RCU)
+		rcu_barrier();
+
 	if (val & DROP_FREED)
 		i915_gem_drain_freed_objects(i915);
 
-- 
cgit v1.2.3


From cd9ba7b6e479ee5f71070f0c095f185e7cdc2eac Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 11 Oct 2019 20:36:20 +0100
Subject: drm/i915/selftests: Serialise write to scratch with its vma binding

Add the missing serialisation on the request for a write into a vma to
wait until that vma is bound before being executed by the GPU.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011193620.14026-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/selftest_workarounds.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 1048be646c35..dc11f7ad50a2 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -786,6 +786,14 @@ static int read_whitelisted_registers(struct i915_gem_context *ctx,
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
+	i915_vma_lock(results);
+	err = i915_request_await_object(rq, results->obj, true);
+	if (err == 0)
+		err = i915_vma_move_to_active(results, rq, EXEC_OBJECT_WRITE);
+	i915_vma_unlock(results);
+	if (err)
+		goto err_req;
+
 	srm = MI_STORE_REGISTER_MEM;
 	if (INTEL_GEN(ctx->i915) >= 8)
 		srm++;
-- 
cgit v1.2.3


From 363c53875aef8fce69d4a2d0873919ccc7d9e2ad Mon Sep 17 00:00:00 2001
From: Evan Green <evgreen@chromium.org>
Date: Fri, 11 Oct 2019 17:22:09 -0700
Subject: Input: synaptics-rmi4 - avoid processing unknown IRQs

rmi_process_interrupt_requests() calls handle_nested_irq() for
each interrupt status bit it finds. If the irq domain mapping for
this bit had not yet been set up, then it ends up calling
handle_nested_irq(0), which causes a NULL pointer dereference.

There's already code that masks the irq_status bits coming out of the
hardware with current_irq_mask, presumably to avoid this situation.
However current_irq_mask seems to more reflect the actual mask set
in the hardware rather than the IRQs software has set up and registered
for. For example, in rmi_driver_reset_handler(), the current_irq_mask
is initialized based on what is read from the hardware. If the reset
value of this mask enables IRQs that Linux has not set up yet, then
we end up in this situation.

There appears to be a third unused bitmask that used to serve this
purpose, fn_irq_bits. Use that bitmask instead of current_irq_mask
to avoid calling handle_nested_irq() on IRQs that have not yet been
set up.

Signed-off-by: Evan Green <evgreen@chromium.org>
Reviewed-by: Andrew Duggan <aduggan@synaptics.com>
Link: https://lore.kernel.org/r/20191008223657.163366-1-evgreen@chromium.org
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/rmi4/rmi_driver.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index 772493b1f665..190b9974526b 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -146,7 +146,7 @@ static int rmi_process_interrupt_requests(struct rmi_device *rmi_dev)
 	}
 
 	mutex_lock(&data->irq_mutex);
-	bitmap_and(data->irq_status, data->irq_status, data->current_irq_mask,
+	bitmap_and(data->irq_status, data->irq_status, data->fn_irq_bits,
 	       data->irq_count);
 	/*
 	 * At this point, irq_status has all bits that are set in the
@@ -385,6 +385,8 @@ static int rmi_driver_set_irq_bits(struct rmi_device *rmi_dev,
 	bitmap_copy(data->current_irq_mask, data->new_irq_mask,
 		    data->num_of_irq_regs);
 
+	bitmap_or(data->fn_irq_bits, data->fn_irq_bits, mask, data->irq_count);
+
 error_unlock:
 	mutex_unlock(&data->irq_mutex);
 	return error;
@@ -398,6 +400,8 @@ static int rmi_driver_clear_irq_bits(struct rmi_device *rmi_dev,
 	struct device *dev = &rmi_dev->dev;
 
 	mutex_lock(&data->irq_mutex);
+	bitmap_andnot(data->fn_irq_bits,
+		      data->fn_irq_bits, mask, data->irq_count);
 	bitmap_andnot(data->new_irq_mask,
 		  data->current_irq_mask, mask, data->irq_count);
 
-- 
cgit v1.2.3


From 8d13c187c42e110625d60094668a8f778c092879 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 9 Oct 2019 13:12:37 -0500
Subject: Revert "drm/radeon: Fix EEH during kexec"

This reverts commit 6f7fe9a93e6c09bf988c5059403f5f88e17e21e6.

This breaks some boards.  Maybe just enable this on PPC for
now?

Bug: https://bugzilla.kernel.org/show_bug.cgi?id=205147
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/radeon/radeon_drv.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index d0bc91ed7c90..9e55076578c6 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -379,19 +379,11 @@ radeon_pci_remove(struct pci_dev *pdev)
 static void
 radeon_pci_shutdown(struct pci_dev *pdev)
 {
-	struct drm_device *ddev = pci_get_drvdata(pdev);
-
 	/* if we are running in a VM, make sure the device
 	 * torn down properly on reboot/shutdown
 	 */
 	if (radeon_device_is_virtual())
 		radeon_pci_remove(pdev);
-
-	/* Some adapters need to be suspended before a
-	* shutdown occurs in order to prevent an error
-	* during kexec.
-	*/
-	radeon_suspend_kms(ddev, true, true, false);
 }
 
 static int radeon_pmops_suspend(struct device *dev)
-- 
cgit v1.2.3


From 984d7a929ad68b7be9990fc9c5cfa5d5c9fc7942 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 10 Oct 2019 18:28:17 +0200
Subject: drm/amdgpu: Bail earlier when amdgpu.cik_/si_support is not set to 1

Bail from the pci_driver probe function instead of from the drm_driver
load function.

This avoid /dev/dri/card0 temporarily getting registered and then
unregistered again, sending unwanted add / remove udev events to
userspace.

Specifically this avoids triggering the (userspace) bug fixed by this
plymouth merge-request:
https://gitlab.freedesktop.org/plymouth/plymouth/merge_requests/59

Note that despite that being a userspace bug, not sending unnecessary
udev events is a good idea in general.

BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1490490
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 35 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 35 ---------------------------------
 2 files changed, 35 insertions(+), 35 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 6f8aaf655a9f..2a00a36106b2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1048,6 +1048,41 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 		return -ENODEV;
 	}
 
+#ifdef CONFIG_DRM_AMDGPU_SI
+	if (!amdgpu_si_support) {
+		switch (flags & AMD_ASIC_MASK) {
+		case CHIP_TAHITI:
+		case CHIP_PITCAIRN:
+		case CHIP_VERDE:
+		case CHIP_OLAND:
+		case CHIP_HAINAN:
+			dev_info(&pdev->dev,
+				 "SI support provided by radeon.\n");
+			dev_info(&pdev->dev,
+				 "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n"
+				);
+			return -ENODEV;
+		}
+	}
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+	if (!amdgpu_cik_support) {
+		switch (flags & AMD_ASIC_MASK) {
+		case CHIP_KAVERI:
+		case CHIP_BONAIRE:
+		case CHIP_HAWAII:
+		case CHIP_KABINI:
+		case CHIP_MULLINS:
+			dev_info(&pdev->dev,
+				 "CIK support provided by radeon.\n");
+			dev_info(&pdev->dev,
+				 "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n"
+				);
+			return -ENODEV;
+		}
+	}
+#endif
+
 	/* Get rid of things like offb */
 	ret = drm_fb_helper_remove_conflicting_pci_framebuffers(pdev, 0, "amdgpudrmfb");
 	if (ret)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index f2c097983f48..d55f5baa83d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -144,41 +144,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 	struct amdgpu_device *adev;
 	int r, acpi_status;
 
-#ifdef CONFIG_DRM_AMDGPU_SI
-	if (!amdgpu_si_support) {
-		switch (flags & AMD_ASIC_MASK) {
-		case CHIP_TAHITI:
-		case CHIP_PITCAIRN:
-		case CHIP_VERDE:
-		case CHIP_OLAND:
-		case CHIP_HAINAN:
-			dev_info(dev->dev,
-				 "SI support provided by radeon.\n");
-			dev_info(dev->dev,
-				 "Use radeon.si_support=0 amdgpu.si_support=1 to override.\n"
-				);
-			return -ENODEV;
-		}
-	}
-#endif
-#ifdef CONFIG_DRM_AMDGPU_CIK
-	if (!amdgpu_cik_support) {
-		switch (flags & AMD_ASIC_MASK) {
-		case CHIP_KAVERI:
-		case CHIP_BONAIRE:
-		case CHIP_HAWAII:
-		case CHIP_KABINI:
-		case CHIP_MULLINS:
-			dev_info(dev->dev,
-				 "CIK support provided by radeon.\n");
-			dev_info(dev->dev,
-				 "Use radeon.cik_support=0 amdgpu.cik_support=1 to override.\n"
-				);
-			return -ENODEV;
-		}
-	}
-#endif
-
 	adev = kzalloc(sizeof(struct amdgpu_device), GFP_KERNEL);
 	if (adev == NULL) {
 		return -ENOMEM;
-- 
cgit v1.2.3


From d12c50857c6edc1d18aa7a60c5a4d6d943137bc0 Mon Sep 17 00:00:00 2001
From: Xiaojie Yuan <xiaojie.yuan@amd.com>
Date: Thu, 10 Oct 2019 01:01:23 +0800
Subject: drm/amdgpu/sdma5: fix mask value of POLL_REGMEM packet for pipe sync
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

sdma will hang once sequence number to be polled reaches 0x1000_0000

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index fa2f70ce2e2b..f6e81680dd7e 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1129,7 +1129,7 @@ static void sdma_v5_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, addr & 0xfffffffc);
 	amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff);
 	amdgpu_ring_write(ring, seq); /* reference */
-	amdgpu_ring_write(ring, 0xfffffff); /* mask */
+	amdgpu_ring_write(ring, 0xffffffff); /* mask */
 	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
 			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(4)); /* retry count, poll interval */
 }
-- 
cgit v1.2.3


From f0308fb0708078d6c1d8a4d533941a7a191af634 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 10 Oct 2019 15:52:34 +0100
Subject: rxrpc: Fix possible NULL pointer access in ICMP handling

If an ICMP packet comes in on the UDP socket backing an AF_RXRPC socket as
the UDP socket is being shut down, rxrpc_error_report() may get called to
deal with it after sk_user_data on the UDP socket has been cleared, leading
to a NULL pointer access when this local endpoint record gets accessed.

Fix this by just returning immediately if sk_user_data was NULL.

The oops looks like the following:

#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
...
RIP: 0010:rxrpc_error_report+0x1bd/0x6a9
...
Call Trace:
 ? sock_queue_err_skb+0xbd/0xde
 ? __udp4_lib_err+0x313/0x34d
 __udp4_lib_err+0x313/0x34d
 icmp_unreach+0x1ee/0x207
 icmp_rcv+0x25b/0x28f
 ip_protocol_deliver_rcu+0x95/0x10e
 ip_local_deliver+0xe9/0x148
 __netif_receive_skb_one_core+0x52/0x6e
 process_backlog+0xdc/0x177
 net_rx_action+0xf9/0x270
 __do_softirq+0x1b6/0x39a
 ? smpboot_register_percpu_thread+0xce/0xce
 run_ksoftirqd+0x1d/0x42
 smpboot_thread_fn+0x19e/0x1b3
 kthread+0xf1/0xf6
 ? kthread_delayed_work_timer_fn+0x83/0x83
 ret_from_fork+0x24/0x30

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Reported-by: syzbot+611164843bd48cc2190c@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/peer_event.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index c97ebdc043e4..61451281d74a 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -151,6 +151,9 @@ void rxrpc_error_report(struct sock *sk)
 	struct rxrpc_peer *peer;
 	struct sk_buff *skb;
 
+	if (unlikely(!local))
+		return;
+
 	_enter("%p{%d}", sk, local->debug_id);
 
 	/* Clear the outstanding error value on the socket so that it doesn't
-- 
cgit v1.2.3


From a5efcde69b112d276416f8e6e5e9fd8ede13bfc5 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 11 Oct 2019 20:03:17 +0100
Subject: drm/i915/perf: Replace global wakeref tracking with engine-pm

As we now have a specific engine to use OA on, exchange the top-level
runtime-pm wakeref with the engine-pm. This still results in the same
top-level runtime-pm, but with more nuances to keep the engine and its
gt awake.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011190325.10979-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_perf.c       | 8 ++++----
 drivers/gpu/drm/i915/i915_perf_types.h | 6 ------
 2 files changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 77c3cef64548..c4a436dfb7db 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -196,7 +196,7 @@
 #include <linux/uuid.h>
 
 #include "gem/i915_gem_context.h"
-#include "gem/i915_gem_pm.h"
+#include "gt/intel_engine_pm.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_lrc_reg.h"
 
@@ -1353,7 +1353,7 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 	free_oa_buffer(stream);
 
 	intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL);
-	intel_runtime_pm_put(stream->uncore->rpm, stream->wakeref);
+	intel_engine_pm_put(stream->engine);
 
 	if (stream->ctx)
 		oa_put_render_ctx_id(stream);
@@ -2218,7 +2218,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	 *   In our case we are expecting that taking pm + FORCEWAKE
 	 *   references will effectively disable RC6.
 	 */
-	stream->wakeref = intel_runtime_pm_get(stream->uncore->rpm);
+	intel_engine_pm_get(stream->engine);
 	intel_uncore_forcewake_get(stream->uncore, FORCEWAKE_ALL);
 
 	ret = alloc_oa_buffer(stream);
@@ -2252,7 +2252,7 @@ err_oa_buf_alloc:
 	put_oa_config(stream->oa_config);
 
 	intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL);
-	intel_runtime_pm_put(stream->uncore->rpm, stream->wakeref);
+	intel_engine_pm_put(stream->engine);
 
 err_config:
 	if (stream->ctx)
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index a91ae2d1a543..eb8d1ebd5095 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -134,12 +134,6 @@ struct i915_perf_stream {
 	 */
 	struct intel_uncore *uncore;
 
-	/**
-	 * @wakeref: As we keep the device awake while the perf stream is
-	 * active, we track our runtime pm reference for later release.
-	 */
-	intel_wakeref_t wakeref;
-
 	/**
 	 * @engine: Engine associated with this performance stream.
 	 */
-- 
cgit v1.2.3


From d8ad5f52617b8a74cb3a511d06e24115360761c6 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 11 Oct 2019 20:03:25 +0100
Subject: drm/i915/execlists: Prevent merging requests with conflicting flags

We set out-of-bound parameters inside the i915_requests.flags field,
such as disabling preemption or marking the end-of-context. We should
not coalesce consecutive requests if they have differing instructions
as we only inspect the last active request in a context. Thus if we
allow a later request to be merged into the same execution context, it
will mask any of the earlier flags.

References: 2a98f4e65bba ("drm/i915: add infrastructure to hold off preemption on a request")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011190325.10979-9-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 13fa61ed85de..7f2d28bf9ea3 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1208,6 +1208,9 @@ static bool can_merge_rq(const struct i915_request *prev,
 	if (i915_request_completed(next))
 		return true;
 
+	if (unlikely(prev->flags ^ next->flags) & I915_REQUEST_NOPREEMPT)
+		return false;
+
 	if (!can_merge_ctx(prev->hw_context, next->hw_context))
 		return false;
 
-- 
cgit v1.2.3


From c3eb54aad982d05493ab374a6f0d0a6831dd2c6e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 12 Oct 2019 08:01:36 +0100
Subject: drm/i915: Mark up "sentinel" requests

Sometimes we want to emit a terminator request, a request that flushes
the pipeline and allows no request to come after it. This can be used
for a "preempt-to-idle" to ensure that upon processing the
context-switch to that request, all other active contexts have been
flushed.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191012070136.32058-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c |  6 +++++-
 drivers/gpu/drm/i915/i915_request.h | 10 ++++++++--
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 7f2d28bf9ea3..a07baeb897fe 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1208,7 +1208,8 @@ static bool can_merge_rq(const struct i915_request *prev,
 	if (i915_request_completed(next))
 		return true;
 
-	if (unlikely(prev->flags ^ next->flags) & I915_REQUEST_NOPREEMPT)
+	if (unlikely((prev->flags ^ next->flags) &
+		     (I915_REQUEST_NOPREEMPT | I915_REQUEST_SENTINEL)))
 		return false;
 
 	if (!can_merge_ctx(prev->hw_context, next->hw_context))
@@ -1659,6 +1660,9 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				if (last->hw_context == rq->hw_context)
 					goto done;
 
+				if (i915_request_has_sentinel(last))
+					goto done;
+
 				/*
 				 * If GVT overrides us we only ever submit
 				 * port[0], leaving port[1] empty. Note that we
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 6a95242b280d..96991d64759c 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -216,8 +216,9 @@ struct i915_request {
 	unsigned long emitted_jiffies;
 
 	unsigned long flags;
-#define I915_REQUEST_WAITBOOST BIT(0)
-#define I915_REQUEST_NOPREEMPT BIT(1)
+#define I915_REQUEST_WAITBOOST	BIT(0)
+#define I915_REQUEST_NOPREEMPT	BIT(1)
+#define I915_REQUEST_SENTINEL	BIT(2)
 
 	/** timeline->request entry for this request */
 	struct list_head link;
@@ -440,6 +441,11 @@ static inline bool i915_request_has_nopreempt(const struct i915_request *rq)
 	return unlikely(rq->flags & I915_REQUEST_NOPREEMPT);
 }
 
+static inline bool i915_request_has_sentinel(const struct i915_request *rq)
+{
+	return unlikely(rq->flags & I915_REQUEST_SENTINEL);
+}
+
 static inline struct intel_timeline *
 i915_request_timeline(struct i915_request *rq)
 {
-- 
cgit v1.2.3


From 6a45008ab7bb5e13b543de0c141b94aaa71d8397 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Sat, 12 Oct 2019 08:23:06 +0100
Subject: drm/i915/perf: allow for CS OA configs to be created lazily

Here we introduce a mechanism by which the execbuf part of the i915
driver will be able to request that a batch buffer containing the
programming for a particular OA config be created.

We'll execute these OA configuration buffers right before executing a
set of userspace commands so that a particular user batchbuffer be
executed with a given OA configuration.

This mechanism essentially allows the userspace driver to go through
several OA configuration without having to open/close the i915/perf
stream.

v2: No need for locking on object OA config object creation (Chris)
    Flush cpu mapping of OA config (Chris)

v3: Properly deal with the perf_metric lock (Chris/Lionel)

v4: Fix oa config unref/put when not found (Lionel)

v5: Allocate BOs for configurations on the stream instead of globally
    (Lionel)

v6: Fix 64bit division (Chris)

v7: Store allocated config BOs into the stream (Lionel)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191012072308.30312-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h |   1 +
 drivers/gpu/drm/i915/i915_perf.c             | 107 +++++++++++++++------------
 drivers/gpu/drm/i915/i915_perf.h             |  24 ++++++
 drivers/gpu/drm/i915/i915_perf_types.h       |  23 ++++--
 4 files changed, 102 insertions(+), 53 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index b0227ab2fe1b..0987100c786b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -138,6 +138,7 @@
 /* Gen11+. addr = base + (ctx_restore ? offset & GENMASK(12,2) : offset) */
 #define   MI_LRI_CS_MMIO		(1<<19)
 #define   MI_LRI_FORCE_POSTED		(1<<12)
+#define MI_LOAD_REGISTER_IMM_MAX_REGS (126)
 #define MI_STORE_REGISTER_MEM        MI_INSTR(0x24, 1)
 #define MI_STORE_REGISTER_MEM_GEN8   MI_INSTR(0x24, 2)
 #define   MI_SRM_LRM_GLOBAL_GTT		(1<<22)
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index c4a436dfb7db..50f2f972020d 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -369,52 +369,52 @@ struct perf_open_properties {
 	struct intel_engine_cs *engine;
 };
 
+struct i915_oa_config_bo {
+	struct llist_node node;
+
+	struct i915_oa_config *oa_config;
+	struct i915_vma *vma;
+};
+
 static enum hrtimer_restart oa_poll_check_timer_cb(struct hrtimer *hrtimer);
 
-static void free_oa_config(struct i915_oa_config *oa_config)
+void i915_oa_config_release(struct kref *ref)
 {
+	struct i915_oa_config *oa_config =
+		container_of(ref, typeof(*oa_config), ref);
+
 	if (!PTR_ERR(oa_config->flex_regs))
 		kfree(oa_config->flex_regs);
 	if (!PTR_ERR(oa_config->b_counter_regs))
 		kfree(oa_config->b_counter_regs);
 	if (!PTR_ERR(oa_config->mux_regs))
 		kfree(oa_config->mux_regs);
-	kfree(oa_config);
-}
-
-static void put_oa_config(struct i915_oa_config *oa_config)
-{
-	if (!atomic_dec_and_test(&oa_config->ref_count))
-		return;
 
-	free_oa_config(oa_config);
+	kfree_rcu(oa_config, rcu);
 }
 
-static int get_oa_config(struct i915_perf *perf,
-			 int metrics_set,
-			 struct i915_oa_config **out_config)
+struct i915_oa_config *
+i915_perf_get_oa_config(struct i915_perf *perf, int metrics_set)
 {
-	int ret;
-
-	if (metrics_set == 1) {
-		*out_config = &perf->test_config;
-		atomic_inc(&perf->test_config.ref_count);
-		return 0;
-	}
-
-	ret = mutex_lock_interruptible(&perf->metrics_lock);
-	if (ret)
-		return ret;
+	struct i915_oa_config *oa_config;
 
-	*out_config = idr_find(&perf->metrics_idr, metrics_set);
-	if (!*out_config)
-		ret = -EINVAL;
+	rcu_read_lock();
+	if (metrics_set == 1)
+		oa_config = &perf->test_config;
 	else
-		atomic_inc(&(*out_config)->ref_count);
+		oa_config = idr_find(&perf->metrics_idr, metrics_set);
+	if (oa_config)
+		oa_config = i915_oa_config_get(oa_config);
+	rcu_read_unlock();
 
-	mutex_unlock(&perf->metrics_lock);
+	return oa_config;
+}
 
-	return ret;
+static void free_oa_config_bo(struct i915_oa_config_bo *oa_bo)
+{
+	i915_oa_config_put(oa_bo->oa_config);
+	i915_vma_put(oa_bo->vma);
+	kfree(oa_bo);
 }
 
 static u32 gen8_oa_hw_tail_read(struct i915_perf_stream *stream)
@@ -1337,6 +1337,16 @@ free_oa_buffer(struct i915_perf_stream *stream)
 	stream->oa_buffer.vaddr = NULL;
 }
 
+static void
+free_oa_configs(struct i915_perf_stream *stream)
+{
+	struct i915_oa_config_bo *oa_bo, *tmp;
+
+	i915_oa_config_put(stream->oa_config);
+	llist_for_each_entry_safe(oa_bo, tmp, stream->oa_config_bos.first, node)
+		free_oa_config_bo(oa_bo);
+}
+
 static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 {
 	struct i915_perf *perf = stream->perf;
@@ -1358,7 +1368,7 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 	if (stream->ctx)
 		oa_put_render_ctx_id(stream);
 
-	put_oa_config(stream->oa_config);
+	free_oa_configs(stream);
 
 	if (perf->spurious_report_rs.missed) {
 		DRM_NOTE("%d spurious OA report notices suppressed due to ratelimiting\n",
@@ -1505,10 +1515,6 @@ static int alloc_oa_buffer(struct i915_perf_stream *stream)
 		goto err_unpin;
 	}
 
-	DRM_DEBUG_DRIVER("OA Buffer initialized, gtt offset = 0x%x, vaddr = %p\n",
-			 i915_ggtt_offset(stream->oa_buffer.vma),
-			 stream->oa_buffer.vaddr);
-
 	return 0;
 
 err_unpin:
@@ -2200,9 +2206,10 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		}
 	}
 
-	ret = get_oa_config(perf, props->metrics_set, &stream->oa_config);
-	if (ret) {
+	stream->oa_config = i915_perf_get_oa_config(perf, props->metrics_set);
+	if (!stream->oa_config) {
 		DRM_DEBUG("Invalid OA config id=%i\n", props->metrics_set);
+		ret = -EINVAL;
 		goto err_config;
 	}
 
@@ -2234,6 +2241,9 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		goto err_enable;
 	}
 
+	DRM_DEBUG("opening stream oa config uuid=%s\n",
+		  stream->oa_config->uuid);
+
 	hrtimer_init(&stream->poll_check_timer,
 		     CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	stream->poll_check_timer.function = oa_poll_check_timer_cb;
@@ -2249,7 +2259,7 @@ err_enable:
 	free_oa_buffer(stream);
 
 err_oa_buf_alloc:
-	put_oa_config(stream->oa_config);
+	free_oa_configs(stream);
 
 	intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL);
 	intel_engine_pm_put(stream->engine);
@@ -3057,7 +3067,8 @@ void i915_perf_register(struct drm_i915_private *i915)
 	if (ret)
 		goto sysfs_error;
 
-	atomic_set(&perf->test_config.ref_count, 1);
+	perf->test_config.perf = perf;
+	kref_init(&perf->test_config.ref);
 
 	goto exit;
 
@@ -3315,7 +3326,8 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 		return -ENOMEM;
 	}
 
-	atomic_set(&oa_config->ref_count, 1);
+	oa_config->perf = perf;
+	kref_init(&oa_config->ref);
 
 	if (!uuid_is_valid(args->uuid)) {
 		DRM_DEBUG("Invalid uuid format for OA config\n");
@@ -3414,7 +3426,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 sysfs_err:
 	mutex_unlock(&perf->metrics_lock);
 reg_err:
-	put_oa_config(oa_config);
+	i915_oa_config_put(oa_config);
 	DRM_DEBUG("Failed to add new OA config\n");
 	return err;
 }
@@ -3450,13 +3462,13 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 
 	ret = mutex_lock_interruptible(&perf->metrics_lock);
 	if (ret)
-		goto lock_err;
+		return ret;
 
 	oa_config = idr_find(&perf->metrics_idr, *arg);
 	if (!oa_config) {
 		DRM_DEBUG("Failed to remove unknown OA config\n");
 		ret = -ENOENT;
-		goto config_err;
+		goto err_unlock;
 	}
 
 	GEM_BUG_ON(*arg != oa_config->id);
@@ -3466,13 +3478,16 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 
 	idr_remove(&perf->metrics_idr, *arg);
 
+	mutex_unlock(&perf->metrics_lock);
+
 	DRM_DEBUG("Removed config %s id=%i\n", oa_config->uuid, oa_config->id);
 
-	put_oa_config(oa_config);
+	i915_oa_config_put(oa_config);
+
+	return 0;
 
-config_err:
+err_unlock:
 	mutex_unlock(&perf->metrics_lock);
-lock_err:
 	return ret;
 }
 
@@ -3642,7 +3657,7 @@ void i915_perf_init(struct drm_i915_private *i915)
 
 static int destroy_config(int id, void *p, void *data)
 {
-	put_oa_config(p);
+	i915_oa_config_put(p);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h
index ff412fb0dbbf..98e16be48a73 100644
--- a/drivers/gpu/drm/i915/i915_perf.h
+++ b/drivers/gpu/drm/i915/i915_perf.h
@@ -6,6 +6,7 @@
 #ifndef __I915_PERF_H__
 #define __I915_PERF_H__
 
+#include <linux/kref.h>
 #include <linux/types.h>
 
 #include "i915_perf_types.h"
@@ -13,6 +14,7 @@
 struct drm_device;
 struct drm_file;
 struct drm_i915_private;
+struct i915_oa_config;
 struct intel_context;
 struct intel_engine_cs;
 
@@ -27,7 +29,29 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file);
 int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file);
+
 void i915_oa_init_reg_state(const struct intel_context *ce,
 			    const struct intel_engine_cs *engine);
 
+struct i915_oa_config *
+i915_perf_get_oa_config(struct i915_perf *perf, int metrics_set);
+
+static inline struct i915_oa_config *
+i915_oa_config_get(struct i915_oa_config *oa_config)
+{
+	if (kref_get_unless_zero(&oa_config->ref))
+		return oa_config;
+	else
+		return NULL;
+}
+
+void i915_oa_config_release(struct kref *ref);
+static inline void i915_oa_config_put(struct i915_oa_config *oa_config)
+{
+	if (!oa_config)
+		return;
+
+	kref_put(&oa_config->ref, i915_oa_config_release);
+}
+
 #endif /* __I915_PERF_H__ */
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index eb8d1ebd5095..337cd7d2ad77 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -9,7 +9,7 @@
 #include <linux/atomic.h>
 #include <linux/device.h>
 #include <linux/hrtimer.h>
-#include <linux/list.h>
+#include <linux/llist.h>
 #include <linux/poll.h>
 #include <linux/sysfs.h>
 #include <linux/types.h>
@@ -22,6 +22,7 @@
 struct drm_i915_private;
 struct file;
 struct i915_gem_context;
+struct i915_perf;
 struct i915_vma;
 struct intel_context;
 struct intel_engine_cs;
@@ -37,6 +38,8 @@ struct i915_oa_reg {
 };
 
 struct i915_oa_config {
+	struct i915_perf *perf;
+
 	char uuid[UUID_STRING_LEN + 1];
 	int id;
 
@@ -51,7 +54,8 @@ struct i915_oa_config {
 	struct attribute *attrs[2];
 	struct device_attribute sysfs_metric_id;
 
-	atomic_t ref_count;
+	struct kref ref;
+	struct rcu_head rcu;
 };
 
 struct i915_perf_stream;
@@ -177,6 +181,12 @@ struct i915_perf_stream {
 	 */
 	struct i915_oa_config *oa_config;
 
+	/**
+	 * @oa_config_bos: A list of struct i915_oa_config_bo allocated lazily
+	 * each time @oa_config changes.
+	 */
+	struct llist_head oa_config_bos;
+
 	/**
 	 * @pinned_ctx: The OA context specific information.
 	 */
@@ -331,13 +341,13 @@ struct i915_perf {
 
 	/*
 	 * Lock associated with adding/modifying/removing OA configs
-	 * in dev_priv->perf.metrics_idr.
+	 * in perf->metrics_idr.
 	 */
 	struct mutex metrics_lock;
 
 	/*
-	 * List of dynamic configurations, you need to hold
-	 * dev_priv->perf.metrics_lock to access it.
+	 * List of dynamic configurations (struct i915_oa_config), you
+	 * need to hold perf->metrics_lock to access it.
 	 */
 	struct idr metrics_idr;
 
@@ -350,8 +360,7 @@ struct i915_perf {
 	/*
 	 * The stream currently using the OA unit. If accessed
 	 * outside a syscall associated to its file
-	 * descriptor, you need to hold
-	 * dev_priv->drm.struct_mutex.
+	 * descriptor.
 	 */
 	struct i915_perf_stream *exclusive_stream;
 
-- 
cgit v1.2.3


From daed3e44396d178cf2098b754bb8ef5ca4e918bc Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Sat, 12 Oct 2019 08:23:07 +0100
Subject: drm/i915/perf: implement active wait for noa configurations

NOA configuration take some amount of time to apply. That amount of
time depends on the size of the GT. There is no documented time for
this. For example, past experimentations with powergating
configuration changes seem to indicate a 60~70us delay. We go with
500us as default for now which should be over the required amount of
time (according to HW architects).

v2: Don't forget to save/restore registers used for the wait (Chris)

v3: Name used CS_GPR registers (Chris)
    Fix compile issue due to rebase (Lionel)

v4: Fix save/restore helpers (Umesh)

v5: Move noa_wait from drm_i915_private to i915_perf_stream (Lionel)

v6: Add missing struct declarations in i915_perf.h

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191012072308.30312-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h       |   4 +-
 drivers/gpu/drm/i915/gt/intel_gt_types.h           |   5 +
 drivers/gpu/drm/i915/i915_debugfs.c                |  32 +++
 drivers/gpu/drm/i915/i915_perf.c                   | 224 +++++++++++++++++++++
 drivers/gpu/drm/i915/i915_perf_types.h             |   8 +
 drivers/gpu/drm/i915/i915_reg.h                    |   4 +-
 .../gpu/drm/i915/selftests/i915_live_selftests.h   |   1 +
 drivers/gpu/drm/i915/selftests/i915_perf.c         | 216 ++++++++++++++++++++
 8 files changed, 492 insertions(+), 2 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/selftests/i915_perf.c

diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 0987100c786b..8e63cffcabe0 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -163,7 +163,8 @@
 #define MI_BATCH_BUFFER_START	MI_INSTR(0x31, 0)
 #define   MI_BATCH_GTT		    (2<<6) /* aliased with (1<<7) on gen4 */
 #define MI_BATCH_BUFFER_START_GEN8	MI_INSTR(0x31, 1)
-#define   MI_BATCH_RESOURCE_STREAMER (1<<10)
+#define   MI_BATCH_RESOURCE_STREAMER REG_BIT(10)
+#define   MI_BATCH_PREDICATE         REG_BIT(15) /* HSW+ on RCS only*/
 
 /*
  * 3D instructions used by the kernel
@@ -224,6 +225,7 @@
 #define   PIPE_CONTROL_CS_STALL				(1<<20)
 #define   PIPE_CONTROL_TLB_INVALIDATE			(1<<18)
 #define   PIPE_CONTROL_MEDIA_STATE_CLEAR		(1<<16)
+#define   PIPE_CONTROL_WRITE_TIMESTAMP			(3<<14)
 #define   PIPE_CONTROL_QW_WRITE				(1<<14)
 #define   PIPE_CONTROL_POST_SYNC_OP_MASK                (3<<14)
 #define   PIPE_CONTROL_DEPTH_STALL			(1<<13)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index 802f516a3430..be4b263621c8 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -109,6 +109,11 @@ enum intel_gt_scratch_field {
 	/* 8 bytes */
 	INTEL_GT_SCRATCH_FIELD_COHERENTL3_WA = 256,
 
+	/* 6 * 8 bytes */
+	INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR = 2048,
+
+	/* 4 bytes */
+	INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1 = 2096,
 };
 
 #endif /* __INTEL_GT_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index e575761550ac..a541b6ae534f 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3590,6 +3590,37 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_wedged_fops,
 			i915_wedged_get, i915_wedged_set,
 			"%llu\n");
 
+static int
+i915_perf_noa_delay_set(void *data, u64 val)
+{
+	struct drm_i915_private *i915 = data;
+	const u32 clk = RUNTIME_INFO(i915)->cs_timestamp_frequency_khz;
+
+	/*
+	 * This would lead to infinite waits as we're doing timestamp
+	 * difference on the CS with only 32bits.
+	 */
+	if (val > mul_u32_u32(U32_MAX, clk))
+		return -EINVAL;
+
+	atomic64_set(&i915->perf.noa_programming_delay, val);
+	return 0;
+}
+
+static int
+i915_perf_noa_delay_get(void *data, u64 *val)
+{
+	struct drm_i915_private *i915 = data;
+
+	*val = atomic64_read(&i915->perf.noa_programming_delay);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(i915_perf_noa_delay_fops,
+			i915_perf_noa_delay_get,
+			i915_perf_noa_delay_set,
+			"%llu\n");
+
 #define DROP_UNBOUND	BIT(0)
 #define DROP_BOUND	BIT(1)
 #define DROP_RETIRE	BIT(2)
@@ -4345,6 +4376,7 @@ static const struct i915_debugfs_files {
 	const char *name;
 	const struct file_operations *fops;
 } i915_debugfs_files[] = {
+	{"i915_perf_noa_delay", &i915_perf_noa_delay_fops},
 	{"i915_wedged", &i915_wedged_fops},
 	{"i915_cache_sharing", &i915_cache_sharing_fops},
 	{"i915_gem_drop_caches", &i915_drop_caches_fops},
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 50f2f972020d..81e8a7934001 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -198,6 +198,7 @@
 #include "gem/i915_gem_context.h"
 #include "gt/intel_engine_pm.h"
 #include "gt/intel_engine_user.h"
+#include "gt/intel_gt.h"
 #include "gt/intel_lrc_reg.h"
 
 #include "i915_drv.h"
@@ -1347,6 +1348,12 @@ free_oa_configs(struct i915_perf_stream *stream)
 		free_oa_config_bo(oa_bo);
 }
 
+static void
+free_noa_wait(struct i915_perf_stream *stream)
+{
+	i915_vma_unpin_and_release(&stream->noa_wait, 0);
+}
+
 static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 {
 	struct i915_perf *perf = stream->perf;
@@ -1369,6 +1376,7 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 		oa_put_render_ctx_id(stream);
 
 	free_oa_configs(stream);
+	free_noa_wait(stream);
 
 	if (perf->spurious_report_rs.missed) {
 		DRM_NOTE("%d spurious OA report notices suppressed due to ratelimiting\n",
@@ -1529,6 +1537,206 @@ err_unref:
 	return ret;
 }
 
+static u32 *save_restore_register(struct i915_perf_stream *stream, u32 *cs,
+				  bool save, i915_reg_t reg, u32 offset,
+				  u32 dword_count)
+{
+	u32 cmd;
+	u32 d;
+
+	cmd = save ? MI_STORE_REGISTER_MEM : MI_LOAD_REGISTER_MEM;
+	if (INTEL_GEN(stream->perf->i915) >= 8)
+		cmd++;
+
+	for (d = 0; d < dword_count; d++) {
+		*cs++ = cmd;
+		*cs++ = i915_mmio_reg_offset(reg) + 4 * d;
+		*cs++ = intel_gt_scratch_offset(stream->engine->gt,
+						offset) + 4 * d;
+		*cs++ = 0;
+	}
+
+	return cs;
+}
+
+static int alloc_noa_wait(struct i915_perf_stream *stream)
+{
+	struct drm_i915_private *i915 = stream->perf->i915;
+	struct drm_i915_gem_object *bo;
+	struct i915_vma *vma;
+	const u64 delay_ticks = 0xffffffffffffffff -
+		DIV64_U64_ROUND_UP(
+			atomic64_read(&stream->perf->noa_programming_delay) *
+			RUNTIME_INFO(i915)->cs_timestamp_frequency_khz,
+			1000000ull);
+	const u32 base = stream->engine->mmio_base;
+#define CS_GPR(x) GEN8_RING_CS_GPR(base, x)
+	u32 *batch, *ts0, *cs, *jump;
+	int ret, i;
+	enum {
+		START_TS,
+		NOW_TS,
+		DELTA_TS,
+		JUMP_PREDICATE,
+		DELTA_TARGET,
+		N_CS_GPR
+	};
+
+	bo = i915_gem_object_create_internal(i915, 4096);
+	if (IS_ERR(bo)) {
+		DRM_ERROR("Failed to allocate NOA wait batchbuffer\n");
+		return PTR_ERR(bo);
+	}
+
+	/*
+	 * We pin in GGTT because we jump into this buffer now because
+	 * multiple OA config BOs will have a jump to this address and it
+	 * needs to be fixed during the lifetime of the i915/perf stream.
+	 */
+	vma = i915_gem_object_ggtt_pin(bo, NULL, 0, 0, PIN_HIGH);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto err_unref;
+	}
+
+	batch = cs = i915_gem_object_pin_map(bo, I915_MAP_WB);
+	if (IS_ERR(batch)) {
+		ret = PTR_ERR(batch);
+		goto err_unpin;
+	}
+
+	/* Save registers. */
+	for (i = 0; i < N_CS_GPR; i++)
+		cs = save_restore_register(
+			stream, cs, true /* save */, CS_GPR(i),
+			INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR + 8 * i, 2);
+	cs = save_restore_register(
+		stream, cs, true /* save */, MI_PREDICATE_RESULT_1,
+		INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1, 1);
+
+	/* First timestamp snapshot location. */
+	ts0 = cs;
+
+	/*
+	 * Initial snapshot of the timestamp register to implement the wait.
+	 * We work with 32b values, so clear out the top 32b bits of the
+	 * register because the ALU works 64bits.
+	 */
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(CS_GPR(START_TS)) + 4;
+	*cs++ = 0;
+	*cs++ = MI_LOAD_REGISTER_REG | (3 - 2);
+	*cs++ = i915_mmio_reg_offset(RING_TIMESTAMP(base));
+	*cs++ = i915_mmio_reg_offset(CS_GPR(START_TS));
+
+	/*
+	 * This is the location we're going to jump back into until the
+	 * required amount of time has passed.
+	 */
+	jump = cs;
+
+	/*
+	 * Take another snapshot of the timestamp register. Take care to clear
+	 * up the top 32bits of CS_GPR(1) as we're using it for other
+	 * operations below.
+	 */
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(CS_GPR(NOW_TS)) + 4;
+	*cs++ = 0;
+	*cs++ = MI_LOAD_REGISTER_REG | (3 - 2);
+	*cs++ = i915_mmio_reg_offset(RING_TIMESTAMP(base));
+	*cs++ = i915_mmio_reg_offset(CS_GPR(NOW_TS));
+
+	/*
+	 * Do a diff between the 2 timestamps and store the result back into
+	 * CS_GPR(1).
+	 */
+	*cs++ = MI_MATH(5);
+	*cs++ = MI_MATH_LOAD(MI_MATH_REG_SRCA, MI_MATH_REG(NOW_TS));
+	*cs++ = MI_MATH_LOAD(MI_MATH_REG_SRCB, MI_MATH_REG(START_TS));
+	*cs++ = MI_MATH_SUB;
+	*cs++ = MI_MATH_STORE(MI_MATH_REG(DELTA_TS), MI_MATH_REG_ACCU);
+	*cs++ = MI_MATH_STORE(MI_MATH_REG(JUMP_PREDICATE), MI_MATH_REG_CF);
+
+	/*
+	 * Transfer the carry flag (set to 1 if ts1 < ts0, meaning the
+	 * timestamp have rolled over the 32bits) into the predicate register
+	 * to be used for the predicated jump.
+	 */
+	*cs++ = MI_LOAD_REGISTER_REG | (3 - 2);
+	*cs++ = i915_mmio_reg_offset(CS_GPR(JUMP_PREDICATE));
+	*cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1);
+
+	/* Restart from the beginning if we had timestamps roll over. */
+	*cs++ = (INTEL_GEN(i915) < 8 ?
+		 MI_BATCH_BUFFER_START :
+		 MI_BATCH_BUFFER_START_GEN8) |
+		MI_BATCH_PREDICATE;
+	*cs++ = i915_ggtt_offset(vma) + (ts0 - batch) * 4;
+	*cs++ = 0;
+
+	/*
+	 * Now add the diff between to previous timestamps and add it to :
+	 *      (((1 * << 64) - 1) - delay_ns)
+	 *
+	 * When the Carry Flag contains 1 this means the elapsed time is
+	 * longer than the expected delay, and we can exit the wait loop.
+	 */
+	*cs++ = MI_LOAD_REGISTER_IMM(2);
+	*cs++ = i915_mmio_reg_offset(CS_GPR(DELTA_TARGET));
+	*cs++ = lower_32_bits(delay_ticks);
+	*cs++ = i915_mmio_reg_offset(CS_GPR(DELTA_TARGET)) + 4;
+	*cs++ = upper_32_bits(delay_ticks);
+
+	*cs++ = MI_MATH(4);
+	*cs++ = MI_MATH_LOAD(MI_MATH_REG_SRCA, MI_MATH_REG(DELTA_TS));
+	*cs++ = MI_MATH_LOAD(MI_MATH_REG_SRCB, MI_MATH_REG(DELTA_TARGET));
+	*cs++ = MI_MATH_ADD;
+	*cs++ = MI_MATH_STOREINV(MI_MATH_REG(JUMP_PREDICATE), MI_MATH_REG_CF);
+
+	/*
+	 * Transfer the result into the predicate register to be used for the
+	 * predicated jump.
+	 */
+	*cs++ = MI_LOAD_REGISTER_REG | (3 - 2);
+	*cs++ = i915_mmio_reg_offset(CS_GPR(JUMP_PREDICATE));
+	*cs++ = i915_mmio_reg_offset(MI_PREDICATE_RESULT_1);
+
+	/* Predicate the jump.  */
+	*cs++ = (INTEL_GEN(i915) < 8 ?
+		 MI_BATCH_BUFFER_START :
+		 MI_BATCH_BUFFER_START_GEN8) |
+		MI_BATCH_PREDICATE;
+	*cs++ = i915_ggtt_offset(vma) + (jump - batch) * 4;
+	*cs++ = 0;
+
+	/* Restore registers. */
+	for (i = 0; i < N_CS_GPR; i++)
+		cs = save_restore_register(
+			stream, cs, false /* restore */, CS_GPR(i),
+			INTEL_GT_SCRATCH_FIELD_PERF_CS_GPR + 8 * i, 2);
+	cs = save_restore_register(
+		stream, cs, false /* restore */, MI_PREDICATE_RESULT_1,
+		INTEL_GT_SCRATCH_FIELD_PERF_PREDICATE_RESULT_1, 1);
+
+	/* And return to the ring. */
+	*cs++ = MI_BATCH_BUFFER_END;
+
+	GEM_BUG_ON(cs - batch > PAGE_SIZE / sizeof(*batch));
+
+	i915_gem_object_flush_map(bo);
+	i915_gem_object_unpin_map(bo);
+
+	stream->noa_wait = vma;
+	return 0;
+
+err_unpin:
+	__i915_vma_unpin(vma);
+err_unref:
+	i915_gem_object_put(bo);
+	return ret;
+}
+
 static void config_oa_regs(struct intel_uncore *uncore,
 			   const struct i915_oa_reg *regs,
 			   u32 n_regs)
@@ -2206,6 +2414,12 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		}
 	}
 
+	ret = alloc_noa_wait(stream);
+	if (ret) {
+		DRM_DEBUG("Unable to allocate NOA wait batch buffer\n");
+		goto err_noa_wait_alloc;
+	}
+
 	stream->oa_config = i915_perf_get_oa_config(perf, props->metrics_set);
 	if (!stream->oa_config) {
 		DRM_DEBUG("Invalid OA config id=%i\n", props->metrics_set);
@@ -2265,6 +2479,9 @@ err_oa_buf_alloc:
 	intel_engine_pm_put(stream->engine);
 
 err_config:
+	free_noa_wait(stream);
+
+err_noa_wait_alloc:
 	if (stream->ctx)
 		oa_put_render_ctx_id(stream);
 
@@ -3651,6 +3868,9 @@ void i915_perf_init(struct drm_i915_private *i915)
 		ratelimit_set_flags(&perf->spurious_report_rs,
 				    RATELIMIT_MSG_ON_RELEASE);
 
+		atomic64_set(&perf->noa_programming_delay,
+			     500 * 1000 /* 500us */);
+
 		perf->i915 = i915;
 	}
 }
@@ -3680,3 +3900,7 @@ void i915_perf_fini(struct drm_i915_private *i915)
 	memset(&perf->ops, 0, sizeof(perf->ops));
 	perf->i915 = NULL;
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftests/i915_perf.c"
+#endif
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 337cd7d2ad77..d35a3c1946c3 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -266,6 +266,12 @@ struct i915_perf_stream {
 		 */
 		u32 head;
 	} oa_buffer;
+
+	/**
+	 * A batch buffer doing a wait on the GPU for the NOA logic to be
+	 * reprogrammed.
+	 */
+	struct i915_vma *noa_wait;
 };
 
 /**
@@ -385,6 +391,8 @@ struct i915_perf {
 
 	struct i915_oa_ops ops;
 	const struct i915_oa_format *oa_formats;
+
+	atomic64_t noa_programming_delay;
 };
 
 #endif /* _I915_PERF_TYPES_H_ */
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 0fb9030b89f1..e24991e54897 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -545,7 +545,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MI_PREDICATE_SRC0_UDW	_MMIO(0x2400 + 4)
 #define MI_PREDICATE_SRC1	_MMIO(0x2408)
 #define MI_PREDICATE_SRC1_UDW	_MMIO(0x2408 + 4)
-
+#define MI_PREDICATE_DATA       _MMIO(0x2410)
+#define MI_PREDICATE_RESULT     _MMIO(0x2418)
+#define MI_PREDICATE_RESULT_1   _MMIO(0x241c)
 #define MI_PREDICATE_RESULT_2	_MMIO(0x2214)
 #define  LOWER_SLICE_ENABLED	(1 << 0)
 #define  LOWER_SLICE_DISABLED	(0 << 0)
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index 6713efea350b..6daf6599ec79 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -35,3 +35,4 @@ selftest(reset, intel_reset_live_selftests)
 selftest(hangcheck, intel_hangcheck_live_selftests)
 selftest(execlists, intel_execlists_live_selftests)
 selftest(guc, intel_guc_live_selftest)
+selftest(perf, i915_perf_live_selftests)
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c
new file mode 100644
index 000000000000..dc6d689e4251
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/i915_perf.c
@@ -0,0 +1,216 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/kref.h>
+
+#include "gem/i915_gem_pm.h"
+#include "gt/intel_gt.h"
+
+#include "i915_selftest.h"
+
+#include "igt_flush_test.h"
+#include "lib_sw_fence.h"
+
+static struct i915_perf_stream *
+test_stream(struct i915_perf *perf)
+{
+	struct drm_i915_perf_open_param param = {};
+	struct perf_open_properties props = {
+		.engine = intel_engine_lookup_user(perf->i915,
+						   I915_ENGINE_CLASS_RENDER,
+						   0),
+		.sample_flags = SAMPLE_OA_REPORT,
+		.oa_format = I915_OA_FORMAT_C4_B8,
+		.metrics_set = 1,
+	};
+	struct i915_perf_stream *stream;
+
+	stream = kzalloc(sizeof(*stream), GFP_KERNEL);
+	if (!stream)
+		return NULL;
+
+	stream->perf = perf;
+
+	mutex_lock(&perf->lock);
+	if (i915_oa_stream_init(stream, &param, &props)) {
+		kfree(stream);
+		stream =  NULL;
+	}
+	mutex_unlock(&perf->lock);
+
+	return stream;
+}
+
+static void stream_destroy(struct i915_perf_stream *stream)
+{
+	struct i915_perf *perf = stream->perf;
+
+	mutex_lock(&perf->lock);
+	i915_perf_destroy_locked(stream);
+	mutex_unlock(&perf->lock);
+}
+
+static int live_sanitycheck(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct i915_perf_stream *stream;
+
+	/* Quick check we can create a perf stream */
+
+	stream = test_stream(&i915->perf);
+	if (!stream)
+		return -EINVAL;
+
+	stream_destroy(stream);
+	return 0;
+}
+
+static int write_timestamp(struct i915_request *rq, int slot)
+{
+	u32 *cs;
+	int len;
+
+	cs = intel_ring_begin(rq, 6);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	len = 5;
+	if (INTEL_GEN(rq->i915) >= 8)
+		len++;
+
+	*cs++ = GFX_OP_PIPE_CONTROL(len);
+	*cs++ = PIPE_CONTROL_GLOBAL_GTT_IVB |
+		PIPE_CONTROL_STORE_DATA_INDEX |
+		PIPE_CONTROL_WRITE_TIMESTAMP;
+	*cs++ = slot * sizeof(u32);
+	*cs++ = 0;
+	*cs++ = 0;
+	*cs++ = 0;
+
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
+static ktime_t poll_status(struct i915_request *rq, int slot)
+{
+	while (!intel_read_status_page(rq->engine, slot) &&
+	       !i915_request_completed(rq))
+		cpu_relax();
+
+	return ktime_get();
+}
+
+static int live_noa_delay(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct i915_perf_stream *stream;
+	struct i915_request *rq;
+	ktime_t t0, t1;
+	u64 expected;
+	u32 delay;
+	int err;
+	int i;
+
+	/* Check that the GPU delays matches expectations */
+
+	stream = test_stream(&i915->perf);
+	if (!stream)
+		return -ENOMEM;
+
+	expected = atomic64_read(&stream->perf->noa_programming_delay);
+
+	if (stream->engine->class != RENDER_CLASS) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	for (i = 0; i < 4; i++)
+		intel_write_status_page(stream->engine, 0x100 + i, 0);
+
+	rq = i915_request_create(stream->engine->kernel_context);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto out;
+	}
+
+	if (rq->engine->emit_init_breadcrumb &&
+	    i915_request_timeline(rq)->has_initial_breadcrumb) {
+		err = rq->engine->emit_init_breadcrumb(rq);
+		if (err) {
+			i915_request_add(rq);
+			goto out;
+		}
+	}
+
+	err = write_timestamp(rq, 0x100);
+	if (err) {
+		i915_request_add(rq);
+		goto out;
+	}
+
+	err = rq->engine->emit_bb_start(rq,
+					i915_ggtt_offset(stream->noa_wait), 0,
+					I915_DISPATCH_SECURE);
+	if (err) {
+		i915_request_add(rq);
+		goto out;
+	}
+
+	err = write_timestamp(rq, 0x102);
+	if (err) {
+		i915_request_add(rq);
+		goto out;
+	}
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+
+	preempt_disable();
+	t0 = poll_status(rq, 0x100);
+	t1 = poll_status(rq, 0x102);
+	preempt_enable();
+
+	pr_info("CPU delay: %lluns, expected %lluns\n",
+		ktime_sub(t1, t0), expected);
+
+	delay = intel_read_status_page(stream->engine, 0x102);
+	delay -= intel_read_status_page(stream->engine, 0x100);
+	delay = div_u64(mul_u32_u32(delay, 1000 * 1000),
+			RUNTIME_INFO(i915)->cs_timestamp_frequency_khz);
+	pr_info("GPU delay: %uns, expected %lluns\n",
+		delay, expected);
+
+	if (4 * delay < 3 * expected || 2 * delay > 3 * expected) {
+		pr_err("GPU delay [%uus] outside of expected threshold! [%lluus, %lluus]\n",
+		       delay / 1000,
+		       div_u64(3 * expected, 4000),
+		       div_u64(3 * expected, 2000));
+		err = -EINVAL;
+	}
+
+	i915_request_put(rq);
+out:
+	stream_destroy(stream);
+	return err;
+}
+
+int i915_perf_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_sanitycheck),
+		SUBTEST(live_noa_delay),
+	};
+	struct i915_perf *perf = &i915->perf;
+
+	if (!perf->metrics_kobj || !perf->ops.enable_metric_set)
+		return 0;
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return i915_subtests(tests, i915);
+}
-- 
cgit v1.2.3


From 15d0ace1f876e01b9745cb22ee32e3770fe3a6d5 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Sat, 12 Oct 2019 08:23:08 +0100
Subject: drm/i915/perf: execute OA configuration from command stream

We haven't run into issues with programming the global OA/NOA
registers configuration from CPU so far, but HW engineers actually
recommend doing this from the command streamer. On TGL in particular
one of the clock domain in which some of that programming goes might
not be powered when we poke things from the CPU.

Since we have a command buffer prepared for the execbuffer side of
things, we can reuse that approach here too.

This also allows us to significantly reduce the amount of time we hold
the main lock.

v2: Drop the global lock as much as possible

v3: Take global lock to pin global

v4: Create i915 request in emit_oa_config() to avoid deadlocks (Lionel)

v5: Move locking to the stream (Lionel)

v6: Move active reconfiguration request into i915_perf_stream (Lionel)

v7: Pin VMA outside request creation (Chris)
    Lock VMA before move to active (Chris)

v8: Fix double free on stream->initial_oa_config_bo (Lionel)
    Don't allow interruption when waiting on active config request
    (Lionel)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191012072308.30312-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_perf.c | 199 ++++++++++++++++++++++++++++++---------
 1 file changed, 156 insertions(+), 43 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 81e8a7934001..74f50120c151 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1731,56 +1731,181 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
 	return 0;
 
 err_unpin:
-	__i915_vma_unpin(vma);
+	i915_vma_unpin_and_release(&vma, 0);
 err_unref:
 	i915_gem_object_put(bo);
 	return ret;
 }
 
-static void config_oa_regs(struct intel_uncore *uncore,
-			   const struct i915_oa_reg *regs,
-			   u32 n_regs)
+static u32 *write_cs_mi_lri(u32 *cs,
+			    const struct i915_oa_reg *reg_data,
+			    u32 n_regs)
 {
 	u32 i;
 
 	for (i = 0; i < n_regs; i++) {
-		const struct i915_oa_reg *reg = regs + i;
+		if ((i % MI_LOAD_REGISTER_IMM_MAX_REGS) == 0) {
+			u32 n_lri = min_t(u32,
+					  n_regs - i,
+					  MI_LOAD_REGISTER_IMM_MAX_REGS);
+
+			*cs++ = MI_LOAD_REGISTER_IMM(n_lri);
+		}
+		*cs++ = i915_mmio_reg_offset(reg_data[i].addr);
+		*cs++ = reg_data[i].value;
+	}
+
+	return cs;
+}
+
+static int num_lri_dwords(int num_regs)
+{
+	int count = 0;
+
+	if (num_regs > 0) {
+		count += DIV_ROUND_UP(num_regs, MI_LOAD_REGISTER_IMM_MAX_REGS);
+		count += num_regs * 2;
+	}
+
+	return count;
+}
+
+static struct i915_oa_config_bo *
+alloc_oa_config_buffer(struct i915_perf_stream *stream,
+		       struct i915_oa_config *oa_config)
+{
+	struct drm_i915_gem_object *obj;
+	struct i915_oa_config_bo *oa_bo;
+	size_t config_length = 0;
+	u32 *cs;
+	int err;
+
+	oa_bo = kzalloc(sizeof(*oa_bo), GFP_KERNEL);
+	if (!oa_bo)
+		return ERR_PTR(-ENOMEM);
+
+	config_length += num_lri_dwords(oa_config->mux_regs_len);
+	config_length += num_lri_dwords(oa_config->b_counter_regs_len);
+	config_length += num_lri_dwords(oa_config->flex_regs_len);
+	config_length++; /* MI_BATCH_BUFFER_END */
+	config_length = ALIGN(sizeof(u32) * config_length, I915_GTT_PAGE_SIZE);
+
+	obj = i915_gem_object_create_shmem(stream->perf->i915, config_length);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto err_free;
+	}
+
+	cs = i915_gem_object_pin_map(obj, I915_MAP_WB);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		goto err_oa_bo;
+	}
 
-		intel_uncore_write(uncore, reg->addr, reg->value);
+	cs = write_cs_mi_lri(cs,
+			     oa_config->mux_regs,
+			     oa_config->mux_regs_len);
+	cs = write_cs_mi_lri(cs,
+			     oa_config->b_counter_regs,
+			     oa_config->b_counter_regs_len);
+	cs = write_cs_mi_lri(cs,
+			     oa_config->flex_regs,
+			     oa_config->flex_regs_len);
+
+	*cs++ = MI_BATCH_BUFFER_END;
+
+	i915_gem_object_flush_map(obj);
+	i915_gem_object_unpin_map(obj);
+
+	oa_bo->vma = i915_vma_instance(obj,
+				       &stream->engine->gt->ggtt->vm,
+				       NULL);
+	if (IS_ERR(oa_bo->vma)) {
+		err = PTR_ERR(oa_bo->vma);
+		goto err_oa_bo;
 	}
+
+	oa_bo->oa_config = i915_oa_config_get(oa_config);
+	llist_add(&oa_bo->node, &stream->oa_config_bos);
+
+	return oa_bo;
+
+err_oa_bo:
+	i915_gem_object_put(obj);
+err_free:
+	kfree(oa_bo);
+	return ERR_PTR(err);
 }
 
-static void delay_after_mux(void)
+static struct i915_vma *
+get_oa_vma(struct i915_perf_stream *stream, struct i915_oa_config *oa_config)
 {
+	struct i915_oa_config_bo *oa_bo;
+
 	/*
-	 * It apparently takes a fairly long time for a new MUX
-	 * configuration to be be applied after these register writes.
-	 * This delay duration was derived empirically based on the
-	 * render_basic config but hopefully it covers the maximum
-	 * configuration latency.
-	 *
-	 * As a fallback, the checks in _append_oa_reports() to skip
-	 * invalid OA reports do also seem to work to discard reports
-	 * generated before this config has completed - albeit not
-	 * silently.
-	 *
-	 * Unfortunately this is essentially a magic number, since we
-	 * don't currently know of a reliable mechanism for predicting
-	 * how long the MUX config will take to apply and besides
-	 * seeing invalid reports we don't know of a reliable way to
-	 * explicitly check that the MUX config has landed.
-	 *
-	 * It's even possible we've miss characterized the underlying
-	 * problem - it just seems like the simplest explanation why
-	 * a delay at this location would mitigate any invalid reports.
+	 * Look for the buffer in the already allocated BOs attached
+	 * to the stream.
 	 */
-	usleep_range(15000, 20000);
+	llist_for_each_entry(oa_bo, stream->oa_config_bos.first, node) {
+		if (oa_bo->oa_config == oa_config &&
+		    memcmp(oa_bo->oa_config->uuid,
+			   oa_config->uuid,
+			   sizeof(oa_config->uuid)) == 0)
+			goto out;
+	}
+
+	oa_bo = alloc_oa_config_buffer(stream, oa_config);
+	if (IS_ERR(oa_bo))
+		return ERR_CAST(oa_bo);
+
+out:
+	return i915_vma_get(oa_bo->vma);
+}
+
+static int emit_oa_config(struct i915_perf_stream *stream,
+			  struct intel_context *ce)
+{
+	struct i915_request *rq;
+	struct i915_vma *vma;
+	int err;
+
+	vma = get_oa_vma(stream, stream->oa_config);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+
+	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
+	if (err)
+		goto err_vma_put;
+
+	rq = i915_request_create(ce);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto err_vma_unpin;
+	}
+
+	i915_vma_lock(vma);
+	err = i915_request_await_object(rq, vma->obj, 0);
+	if (!err)
+		err = i915_vma_move_to_active(vma, rq, 0);
+	i915_vma_unlock(vma);
+	if (err)
+		goto err_add_request;
+
+	err = rq->engine->emit_bb_start(rq,
+					vma->node.start, 0,
+					I915_DISPATCH_SECURE);
+err_add_request:
+	i915_request_add(rq);
+err_vma_unpin:
+	i915_vma_unpin(vma);
+err_vma_put:
+	i915_vma_put(vma);
+	return err;
 }
 
 static int hsw_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
-	const struct i915_oa_config *oa_config = stream->oa_config;
 
 	/*
 	 * PRM:
@@ -1797,13 +1922,7 @@ static int hsw_enable_metric_set(struct i915_perf_stream *stream)
 	intel_uncore_rmw(uncore, GEN6_UCGCTL1,
 			 0, GEN6_CSUNIT_CLOCK_GATE_DISABLE);
 
-	config_oa_regs(uncore, oa_config->mux_regs, oa_config->mux_regs_len);
-	delay_after_mux();
-
-	config_oa_regs(uncore, oa_config->b_counter_regs,
-		       oa_config->b_counter_regs_len);
-
-	return 0;
+	return emit_oa_config(stream, stream->engine->kernel_context);
 }
 
 static void hsw_disable_metric_set(struct i915_perf_stream *stream)
@@ -2167,13 +2286,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	if (ret)
 		return ret;
 
-	config_oa_regs(uncore, oa_config->mux_regs, oa_config->mux_regs_len);
-	delay_after_mux();
-
-	config_oa_regs(uncore, oa_config->b_counter_regs,
-		       oa_config->b_counter_regs_len);
-
-	return 0;
+	return emit_oa_config(stream, stream->engine->kernel_context);
 }
 
 static void gen8_disable_metric_set(struct i915_perf_stream *stream)
-- 
cgit v1.2.3


From 9066288b2aab1804dc1eebec6ff88474363b89cb Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 8 Oct 2019 08:50:03 -0700
Subject: perf/x86/intel: Add Comet Lake CPU support

Comet Lake is the new 10th Gen Intel processor. From the perspective
of Intel PMU, there is nothing changed compared with Sky Lake.
Share the perf code with Sky Lake.

The patch has been tested on real hardware.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/1570549810-25049-3-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 27ee47a7be66..9d91a472e1bb 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4983,6 +4983,8 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_SKYLAKE:
 	case INTEL_FAM6_KABYLAKE_L:
 	case INTEL_FAM6_KABYLAKE:
+	case INTEL_FAM6_COMETLAKE_L:
+	case INTEL_FAM6_COMETLAKE:
 		x86_add_quirk(intel_pebs_isolation_quirk);
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
-- 
cgit v1.2.3


From 9674b1cc0f94c34f76e58c102623a866836f269e Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 8 Oct 2019 08:50:04 -0700
Subject: perf/x86/msr: Add Comet Lake CPU support

Comet Lake is the new 10th Gen Intel processor. PPERF and SMI_COUNT MSRs
are also supported.

The External Design Specification (EDS) is not published yet. It comes
from an authoritative internal source.

The patch has been tested on real hardware.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/1570549810-25049-4-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/msr.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index b1afc77f0704..c177bbe2ce6b 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -89,6 +89,8 @@ static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_KABYLAKE_L:
 	case INTEL_FAM6_KABYLAKE:
+	case INTEL_FAM6_COMETLAKE_L:
+	case INTEL_FAM6_COMETLAKE:
 	case INTEL_FAM6_ICELAKE_L:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
-- 
cgit v1.2.3


From 1ffa6c04dae39776a3c222bdf88051e394386c01 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 8 Oct 2019 08:50:05 -0700
Subject: perf/x86/cstate: Add Comet Lake CPU support

Comet Lake is the new 10th Gen Intel processor. From the perspective of
Intel cstate residency counters, there is nothing changed compared with
Kaby Lake.

Share hswult_cstates with Kaby Lake.
Update the comments for Comet Lake.
Kaby Lake is missed in the comments for some Residency Counters. Update
the comments for Kaby Lake as well.

The External Design Specification (EDS) is not published yet. It comes
from an authoritative internal source.

The patch has been tested on real hardware.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/1570549810-25049-5-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/cstate.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 9f2f39003d96..21c65e15c8f8 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -45,46 +45,48 @@
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,GLM,
-						CNL
+ *						CNL,KBL,CML
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL
+ *						SKL,KNL,GLM,CNL,KBL,CML
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
- *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
- *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
+ *						KBL,CML
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
- *						GLM,CNL
+ *						GLM,CNL,KBL,CML
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL,GLM,CNL
+ *						SKL,KNL,GLM,CNL,KBL,CML
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
- *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL
+ *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
+ *						KBL,CML
  *			       Scope: Package (physical package)
  *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
  *			       perf code: 0x04
- *			       Available model: HSW ULT,KBL,CNL
+ *			       Available model: HSW ULT,KBL,CNL,CML
  *			       Scope: Package (physical package)
  *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
  *			       perf code: 0x05
- *			       Available model: HSW ULT,KBL,CNL
+ *			       Available model: HSW ULT,KBL,CNL,CML
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT,KBL,GLM,CNL
+ *			       Available model: HSW ULT,KBL,GLM,CNL,CML
  *			       Scope: Package (physical package)
  *
  */
@@ -614,6 +616,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_L, hswult_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE,   hswult_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE_L, hswult_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_COMETLAKE, hswult_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_L, cnl_cstates),
 
-- 
cgit v1.2.3


From 1a5da78d00ce0152994946debd1417513dc35eb3 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 8 Oct 2019 08:50:06 -0700
Subject: perf/x86/msr: Add new CPU model numbers for Ice Lake

PPERF and SMI_COUNT MSRs are also supported by Ice Lake desktop and
server.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/1570549810-25049-6-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/msr.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index c177bbe2ce6b..8515512e98ef 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -92,6 +92,9 @@ static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_COMETLAKE_L:
 	case INTEL_FAM6_COMETLAKE:
 	case INTEL_FAM6_ICELAKE_L:
+	case INTEL_FAM6_ICELAKE:
+	case INTEL_FAM6_ICELAKE_X:
+	case INTEL_FAM6_ICELAKE_D:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
 		break;
-- 
cgit v1.2.3


From f1857a2467755e5faa3c727d7146b6db960abee1 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 8 Oct 2019 08:50:07 -0700
Subject: perf/x86/cstate: Update C-state counters for Ice Lake

There is no Core C3 C-State counter for Ice Lake.
Package C8/C9/C10 C-State counters are added for Ice Lake.

Introduce a new event list, icl_cstates, for Ice Lake.
Update the comments accordingly.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: f08c47d1f86c ("perf/x86/intel/cstate: Add Icelake support")
Link: https://lkml.kernel.org/r/1570549810-25049-7-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/cstate.c | 36 +++++++++++++++++++++++++-----------
 1 file changed, 25 insertions(+), 11 deletions(-)

diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 21c65e15c8f8..4d232acce7cc 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -50,43 +50,44 @@
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL,KBL,CML
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
- *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
+ *						ICL
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
  *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
- *						KBL,CML
+ *						KBL,CML,ICL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
- *						GLM,CNL,KBL,CML
+ *						GLM,CNL,KBL,CML,ICL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL,GLM,CNL,KBL,CML
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
- *						KBL,CML
+ *						KBL,CML,ICL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
  *			       perf code: 0x04
- *			       Available model: HSW ULT,KBL,CNL,CML
+ *			       Available model: HSW ULT,KBL,CNL,CML,ICL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
  *			       perf code: 0x05
- *			       Available model: HSW ULT,KBL,CNL,CML
+ *			       Available model: HSW ULT,KBL,CNL,CML,ICL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT,KBL,GLM,CNL,CML
+ *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL
  *			       Scope: Package (physical package)
  *
  */
@@ -546,6 +547,19 @@ static const struct cstate_model cnl_cstates __initconst = {
 				  BIT(PERF_CSTATE_PKG_C10_RES),
 };
 
+static const struct cstate_model icl_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C6_RES) |
+				  BIT(PERF_CSTATE_CORE_C7_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES) |
+				  BIT(PERF_CSTATE_PKG_C7_RES) |
+				  BIT(PERF_CSTATE_PKG_C8_RES) |
+				  BIT(PERF_CSTATE_PKG_C9_RES) |
+				  BIT(PERF_CSTATE_PKG_C10_RES),
+};
+
 static const struct cstate_model slm_cstates __initconst = {
 	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
 				  BIT(PERF_CSTATE_CORE_C6_RES),
@@ -629,8 +643,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE,   snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE,   icl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
-- 
cgit v1.2.3


From 23645a76ba816652d6898def2ee69c6a6250c9b1 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 8 Oct 2019 08:50:08 -0700
Subject: perf/x86/intel: Add Tiger Lake CPU support

Tiger Lake is the followon to Ice Lake. From the perspective of Intel
core PMU, there is little changes compared with Ice Lake, e.g. small
changes in event list. But it doesn't impact on core PMU functionality.
Share the perf code with Ice Lake. The event list patch will be submitted
later separately.

The patch has been tested on real hardware.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/1570549810-25049-8-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 9d91a472e1bb..fcef678c3423 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -5033,6 +5033,8 @@ __init int intel_pmu_init(void)
 		/* fall through */
 	case INTEL_FAM6_ICELAKE_L:
 	case INTEL_FAM6_ICELAKE:
+	case INTEL_FAM6_TIGERLAKE_L:
+	case INTEL_FAM6_TIGERLAKE:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
-- 
cgit v1.2.3


From 0917b95079af82c69d8f5bab301faeebcd2cb3cd Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 8 Oct 2019 08:50:09 -0700
Subject: perf/x86/msr: Add Tiger Lake CPU support

Tiger Lake is the followon to Ice Lake. PPERF and SMI_COUNT MSRs are
also supported.

The External Design Specification (EDS) is not published yet. It comes
from an authoritative internal source.

The patch has been tested on real hardware.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/1570549810-25049-9-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/msr.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 8515512e98ef..6f86650b3f77 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -95,6 +95,8 @@ static bool test_intel(int idx, void *data)
 	case INTEL_FAM6_ICELAKE:
 	case INTEL_FAM6_ICELAKE_X:
 	case INTEL_FAM6_ICELAKE_D:
+	case INTEL_FAM6_TIGERLAKE_L:
+	case INTEL_FAM6_TIGERLAKE:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
 		break;
-- 
cgit v1.2.3


From 52e92f409dede388b7dc3ee13491fbf7a80db935 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 8 Oct 2019 08:50:10 -0700
Subject: perf/x86/cstate: Add Tiger Lake CPU support

Tiger Lake is the followon to Ice Lake. From the perspective of Intel
cstate residency counters, there is nothing changed compared with
Ice Lake.

Share icl_cstates with Ice Lake.
Update the comments for Tiger Lake.

The External Design Specification (EDS) is not published yet. It comes
from an authoritative internal source.

The patch has been tested on real hardware.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/1570549810-25049-10-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/cstate.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 4d232acce7cc..e1daf4151e11 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -50,44 +50,44 @@
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
  *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
- *						ICL
+ *						ICL,TGL
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
  *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
- *						KBL,CML,ICL
+ *						KBL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
- *						GLM,CNL,KBL,CML,ICL
+ *						GLM,CNL,KBL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
- *						SKL,KNL,GLM,CNL,KBL,CML,ICL
+ *						SKL,KNL,GLM,CNL,KBL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
- *						KBL,CML,ICL
+ *						KBL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
  *			       perf code: 0x04
- *			       Available model: HSW ULT,KBL,CNL,CML,ICL
+ *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
  *			       perf code: 0x05
- *			       Available model: HSW ULT,KBL,CNL,CML,ICL
+ *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL
+ *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL
  *			       Scope: Package (physical package)
  *
  */
@@ -645,6 +645,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_L, icl_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE,   icl_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE_L, icl_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_TIGERLAKE, icl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
-- 
cgit v1.2.3


From 5f5c382ecfdd06e17316d1c9f1362522c20cdfef Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 12 Oct 2019 10:10:56 +0100
Subject: drm/i915/perf: Prefer using the pinned_ctx for emitting delays on
 config

When we are watching a particular context, we want the OA config to be
applied inline with that context such that it takes effect before the
next submission.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191012091056.28686-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_perf.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 74f50120c151..b4e2332d35cb 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1903,6 +1903,11 @@ err_vma_put:
 	return err;
 }
 
+static struct intel_context *oa_context(struct i915_perf_stream *stream)
+{
+	return stream->pinned_ctx ?: stream->engine->kernel_context;
+}
+
 static int hsw_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
@@ -1922,7 +1927,7 @@ static int hsw_enable_metric_set(struct i915_perf_stream *stream)
 	intel_uncore_rmw(uncore, GEN6_UCGCTL1,
 			 0, GEN6_CSUNIT_CLOCK_GATE_DISABLE);
 
-	return emit_oa_config(stream, stream->engine->kernel_context);
+	return emit_oa_config(stream, oa_context(stream));
 }
 
 static void hsw_disable_metric_set(struct i915_perf_stream *stream)
@@ -2286,7 +2291,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	if (ret)
 		return ret;
 
-	return emit_oa_config(stream, stream->engine->kernel_context);
+	return emit_oa_config(stream, oa_context(stream));
 }
 
 static void gen8_disable_metric_set(struct i915_perf_stream *stream)
-- 
cgit v1.2.3


From 3ed270b129a45c7c502c819a4286b464a52dac61 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 11 Oct 2019 13:54:58 -0400
Subject: tracefs: Revert ccbd54ff54e8 ("tracefs: Restrict tracefs when the
 kernel is locked down")

Running the latest kernel through my "make instances" stress tests, I
triggered the following bug (with KASAN and kmemleak enabled):

mkdir invoked oom-killer:
gfp_mask=0x40cd0(GFP_KERNEL|__GFP_COMP|__GFP_RECLAIMABLE), order=0,
oom_score_adj=0
CPU: 1 PID: 2229 Comm: mkdir Not tainted 5.4.0-rc2-test #325
Hardware name: MSI MS-7823/CSM-H87M-G43 (MS-7823), BIOS V1.6 02/22/2014
Call Trace:
 dump_stack+0x64/0x8c
 dump_header+0x43/0x3b7
 ? trace_hardirqs_on+0x48/0x4a
 oom_kill_process+0x68/0x2d5
 out_of_memory+0x2aa/0x2d0
 __alloc_pages_nodemask+0x96d/0xb67
 __alloc_pages_node+0x19/0x1e
 alloc_slab_page+0x17/0x45
 new_slab+0xd0/0x234
 ___slab_alloc.constprop.86+0x18f/0x336
 ? alloc_inode+0x2c/0x74
 ? irq_trace+0x12/0x1e
 ? tracer_hardirqs_off+0x1d/0xd7
 ? __slab_alloc.constprop.85+0x21/0x53
 __slab_alloc.constprop.85+0x31/0x53
 ? __slab_alloc.constprop.85+0x31/0x53
 ? alloc_inode+0x2c/0x74
 kmem_cache_alloc+0x50/0x179
 ? alloc_inode+0x2c/0x74
 alloc_inode+0x2c/0x74
 new_inode_pseudo+0xf/0x48
 new_inode+0x15/0x25
 tracefs_get_inode+0x23/0x7c
 ? lookup_one_len+0x54/0x6c
 tracefs_create_file+0x53/0x11d
 trace_create_file+0x15/0x33
 event_create_dir+0x2a3/0x34b
 __trace_add_new_event+0x1c/0x26
 event_trace_add_tracer+0x56/0x86
 trace_array_create+0x13e/0x1e1
 instance_mkdir+0x8/0x17
 tracefs_syscall_mkdir+0x39/0x50
 ? get_dname+0x31/0x31
 vfs_mkdir+0x78/0xa3
 do_mkdirat+0x71/0xb0
 sys_mkdir+0x19/0x1b
 do_fast_syscall_32+0xb0/0xed

I bisected this down to the addition of the proxy_ops into tracefs for
lockdown. It appears that the allocation of the proxy_ops and then freeing
it in the destroy_inode callback, is causing havoc with the memory system.
Reading the documentation about destroy_inode and talking with Linus about
this, this is buggy and wrong. When defining the destroy_inode() method, it
is expected that the destroy_inode() will also free the inode, and not just
the extra allocations done in the creation of the inode. The faulty commit
causes a memory leak of the inode data structure when they are deleted.

Instead of allocating the proxy_ops (and then having to free it) the checks
should be done by the open functions themselves, and not hack into the
tracefs directory. First revert the tracefs updates for locked_down and then
later we can add the locked_down checks in the kernel/trace files.

Link: http://lkml.kernel.org/r/20191011135458.7399da44@gandalf.local.home

Fixes: ccbd54ff54e8 ("tracefs: Restrict tracefs when the kernel is locked down")
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 fs/tracefs/inode.c | 42 +-----------------------------------------
 1 file changed, 1 insertion(+), 41 deletions(-)

diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 9fc14e38927f..eeeae0475da9 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -20,7 +20,6 @@
 #include <linux/parser.h>
 #include <linux/magic.h>
 #include <linux/slab.h>
-#include <linux/security.h>
 
 #define TRACEFS_DEFAULT_MODE	0700
 
@@ -28,25 +27,6 @@ static struct vfsmount *tracefs_mount;
 static int tracefs_mount_count;
 static bool tracefs_registered;
 
-static int default_open_file(struct inode *inode, struct file *filp)
-{
-	struct dentry *dentry = filp->f_path.dentry;
-	struct file_operations *real_fops;
-	int ret;
-
-	if (!dentry)
-		return -EINVAL;
-
-	ret = security_locked_down(LOCKDOWN_TRACEFS);
-	if (ret)
-		return ret;
-
-	real_fops = dentry->d_fsdata;
-	if (!real_fops->open)
-		return 0;
-	return real_fops->open(inode, filp);
-}
-
 static ssize_t default_read_file(struct file *file, char __user *buf,
 				 size_t count, loff_t *ppos)
 {
@@ -241,12 +221,6 @@ static int tracefs_apply_options(struct super_block *sb)
 	return 0;
 }
 
-static void tracefs_destroy_inode(struct inode *inode)
-{
-	if (S_ISREG(inode->i_mode))
-		kfree(inode->i_fop);
-}
-
 static int tracefs_remount(struct super_block *sb, int *flags, char *data)
 {
 	int err;
@@ -283,7 +257,6 @@ static int tracefs_show_options(struct seq_file *m, struct dentry *root)
 static const struct super_operations tracefs_super_operations = {
 	.statfs		= simple_statfs,
 	.remount_fs	= tracefs_remount,
-	.destroy_inode  = tracefs_destroy_inode,
 	.show_options	= tracefs_show_options,
 };
 
@@ -414,7 +387,6 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
 				   const struct file_operations *fops)
 {
-	struct file_operations *proxy_fops;
 	struct dentry *dentry;
 	struct inode *inode;
 
@@ -430,20 +402,8 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 	if (unlikely(!inode))
 		return failed_creating(dentry);
 
-	proxy_fops = kzalloc(sizeof(struct file_operations), GFP_KERNEL);
-	if (unlikely(!proxy_fops)) {
-		iput(inode);
-		return failed_creating(dentry);
-	}
-
-	if (!fops)
-		fops = &tracefs_file_operations;
-
-	dentry->d_fsdata = (void *)fops;
-	memcpy(proxy_fops, fops, sizeof(*proxy_fops));
-	proxy_fops->open = default_open_file;
 	inode->i_mode = mode;
-	inode->i_fop = proxy_fops;
+	inode->i_fop = fops ? fops : &tracefs_file_operations;
 	inode->i_private = data;
 	d_instantiate(dentry, inode);
 	fsnotify_create(dentry->d_parent->d_inode, dentry);
-- 
cgit v1.2.3


From 9ef16693aff8137faa21d16ffe65bb9832d24d71 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 11 Oct 2019 17:56:57 -0400
Subject: ftrace: Get a reference counter for the trace_array on filter files

The ftrace set_ftrace_filter and set_ftrace_notrace files are specific for
an instance now. They need to take a reference to the instance otherwise
there could be a race between accessing the files and deleting the instance.

It wasn't until the :mod: caching where these file operations started
referencing the trace_array directly.

Cc: stable@vger.kernel.org
Fixes: 673feb9d76ab3 ("ftrace: Add :mod: caching infrastructure to trace_array")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 62a50bf399d6..32c2eb167de0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3540,21 +3540,22 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 	struct ftrace_hash *hash;
 	struct list_head *mod_head;
 	struct trace_array *tr = ops->private;
-	int ret = 0;
+	int ret = -ENOMEM;
 
 	ftrace_ops_init(ops);
 
 	if (unlikely(ftrace_disabled))
 		return -ENODEV;
 
+	if (tr && trace_array_get(tr) < 0)
+		return -ENODEV;
+
 	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
 	if (!iter)
-		return -ENOMEM;
+		goto out;
 
-	if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX)) {
-		kfree(iter);
-		return -ENOMEM;
-	}
+	if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX))
+		goto out;
 
 	iter->ops = ops;
 	iter->flags = flag;
@@ -3584,13 +3585,13 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 
 		if (!iter->hash) {
 			trace_parser_put(&iter->parser);
-			kfree(iter);
-			ret = -ENOMEM;
 			goto out_unlock;
 		}
 	} else
 		iter->hash = hash;
 
+	ret = 0;
+
 	if (file->f_mode & FMODE_READ) {
 		iter->pg = ftrace_pages_start;
 
@@ -3602,7 +3603,6 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 			/* Failed */
 			free_ftrace_hash(iter->hash);
 			trace_parser_put(&iter->parser);
-			kfree(iter);
 		}
 	} else
 		file->private_data = iter;
@@ -3610,6 +3610,13 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
  out_unlock:
 	mutex_unlock(&ops->func_hash->regex_lock);
 
+ out:
+	if (ret) {
+		kfree(iter);
+		if (tr)
+			trace_array_put(tr);
+	}
+
 	return ret;
 }
 
@@ -5037,6 +5044,8 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
 
 	mutex_unlock(&iter->ops->func_hash->regex_lock);
 	free_ftrace_hash(iter->hash);
+	if (iter->tr)
+		trace_array_put(iter->tr);
 	kfree(iter);
 
 	return 0;
-- 
cgit v1.2.3


From 194c2c74f5532e62c218adeb8e2b683119503907 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 11 Oct 2019 18:19:17 -0400
Subject: tracing: Get trace_array reference for available_tracers files

As instances may have different tracers available, we need to look at the
trace_array descriptor that shows the list of the available tracers for the
instance. But there's a race between opening the file and an admin
deleting the instance. The trace_array_get() needs to be called before
accessing the trace_array.

Cc: stable@vger.kernel.org
Fixes: 607e2ea167e56 ("tracing: Set up infrastructure to allow tracers for instances")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 252f79c435f8..fa7d813b04c6 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4355,9 +4355,14 @@ static int show_traces_open(struct inode *inode, struct file *file)
 	if (tracing_disabled)
 		return -ENODEV;
 
+	if (trace_array_get(tr) < 0)
+		return -ENODEV;
+
 	ret = seq_open(file, &show_traces_seq_ops);
-	if (ret)
+	if (ret) {
+		trace_array_put(tr);
 		return ret;
+	}
 
 	m = file->private_data;
 	m->private = tr;
@@ -4365,6 +4370,14 @@ static int show_traces_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static int show_traces_release(struct inode *inode, struct file *file)
+{
+	struct trace_array *tr = inode->i_private;
+
+	trace_array_put(tr);
+	return seq_release(inode, file);
+}
+
 static ssize_t
 tracing_write_stub(struct file *filp, const char __user *ubuf,
 		   size_t count, loff_t *ppos)
@@ -4395,8 +4408,8 @@ static const struct file_operations tracing_fops = {
 static const struct file_operations show_traces_fops = {
 	.open		= show_traces_open,
 	.read		= seq_read,
-	.release	= seq_release,
 	.llseek		= seq_lseek,
+	.release	= show_traces_release,
 };
 
 static ssize_t
-- 
cgit v1.2.3


From aa07d71f1bc7ea20e442e812b5de9d632b7f84c6 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 11 Oct 2019 19:12:21 -0400
Subject: tracing: Have trace events system open call tracing_open_generic_tr()

Instead of having the trace events system open call open code the taking of
the trace_array descriptor (with trace_array_get()) and then calling
trace_open_generic(), have it use the tracing_open_generic_tr() that does
the combination of the two. This requires making tracing_open_generic_tr()
global.

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c        |  2 +-
 kernel/trace/trace.h        |  1 +
 kernel/trace/trace_events.c | 17 +++--------------
 3 files changed, 5 insertions(+), 15 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index fa7d813b04c6..94f1b9124939 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4156,7 +4156,7 @@ bool tracing_is_disabled(void)
  * Open and update trace_array ref count.
  * Must have the current trace_array passed to it.
  */
-static int tracing_open_generic_tr(struct inode *inode, struct file *filp)
+int tracing_open_generic_tr(struct inode *inode, struct file *filp)
 {
 	struct trace_array *tr = inode->i_private;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f801d154ff6a..854dbf4050f8 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -681,6 +681,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf);
 void tracing_reset_current(int cpu);
 void tracing_reset_all_online_cpus(void);
 int tracing_open_generic(struct inode *inode, struct file *filp);
+int tracing_open_generic_tr(struct inode *inode, struct file *filp);
 bool tracing_is_disabled(void);
 bool tracer_tracing_is_on(struct trace_array *tr);
 void tracer_tracing_on(struct trace_array *tr);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index b89cdfe20bc1..9613a757c902 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1440,28 +1440,17 @@ static int system_tr_open(struct inode *inode, struct file *filp)
 	struct trace_array *tr = inode->i_private;
 	int ret;
 
-	if (tracing_is_disabled())
-		return -ENODEV;
-
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
-
 	/* Make a temporary dir that has no system but points to tr */
 	dir = kzalloc(sizeof(*dir), GFP_KERNEL);
-	if (!dir) {
-		trace_array_put(tr);
+	if (!dir)
 		return -ENOMEM;
-	}
-
-	dir->tr = tr;
 
-	ret = tracing_open_generic(inode, filp);
+	ret = tracing_open_generic_tr(inode, filp);
 	if (ret < 0) {
-		trace_array_put(tr);
 		kfree(dir);
 		return ret;
 	}
-
+	dir->tr = tr;
 	filp->private_data = dir;
 
 	return 0;
-- 
cgit v1.2.3


From 8530dec63e7b486e3761cc3d74a22de301845ff5 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 11 Oct 2019 17:39:57 -0400
Subject: tracing: Add tracing_check_open_get_tr()

Currently, most files in the tracefs directory test if tracing_disabled is
set. If so, it should return -ENODEV. The tracing_disabled is called when
tracing is found to be broken. Originally it was done in case the ring
buffer was found to be corrupted, and we wanted to prevent reading it from
crashing the kernel. But it's also called if a tracing selftest fails on
boot. It's a one way switch. That is, once it is triggered, tracing is
disabled until reboot.

As most tracefs files can also be used by instances in the tracefs
directory, they need to be carefully done. Each instance has a trace_array
associated to it, and when the instance is removed, the trace_array is
freed. But if an instance is opened with a reference to the trace_array,
then it requires looking up the trace_array to get its ref counter (as there
could be a race with it being deleted and the open itself). Once it is
found, a reference is added to prevent the instance from being removed (and
the trace_array associated with it freed).

Combine the two checks (tracing_disabled and trace_array_get()) into a
single helper function. This will also make it easier to add lockdown to
tracefs later.

Link: http://lkml.kernel.org/r/20191011135458.7399da44@gandalf.local.home

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c            |   7 ++-
 kernel/trace/trace.c             | 117 ++++++++++++++++++++++-----------------
 kernel/trace/trace.h             |   1 +
 kernel/trace/trace_dynevent.c    |   4 ++
 kernel/trace/trace_events.c      |  10 ++--
 kernel/trace/trace_events_hist.c |   2 +-
 6 files changed, 81 insertions(+), 60 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 32c2eb167de0..8b765a55e01c 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3547,7 +3547,7 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
 	if (unlikely(ftrace_disabled))
 		return -ENODEV;
 
-	if (tr && trace_array_get(tr) < 0)
+	if (tracing_check_open_get_tr(tr))
 		return -ENODEV;
 
 	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
@@ -6546,8 +6546,9 @@ ftrace_pid_open(struct inode *inode, struct file *file)
 	struct seq_file *m;
 	int ret = 0;
 
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC))
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 94f1b9124939..26ee280f852b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -304,6 +304,17 @@ void trace_array_put(struct trace_array *this_tr)
 	mutex_unlock(&trace_types_lock);
 }
 
+int tracing_check_open_get_tr(struct trace_array *tr)
+{
+	if (tracing_disabled)
+		return -ENODEV;
+
+	if (tr && trace_array_get(tr) < 0)
+		return -ENODEV;
+
+	return 0;
+}
+
 int call_filter_check_discard(struct trace_event_call *call, void *rec,
 			      struct ring_buffer *buffer,
 			      struct ring_buffer_event *event)
@@ -4140,8 +4151,11 @@ release:
 
 int tracing_open_generic(struct inode *inode, struct file *filp)
 {
-	if (tracing_disabled)
-		return -ENODEV;
+	int ret;
+
+	ret = tracing_check_open_get_tr(NULL);
+	if (ret)
+		return ret;
 
 	filp->private_data = inode->i_private;
 	return 0;
@@ -4159,12 +4173,11 @@ bool tracing_is_disabled(void)
 int tracing_open_generic_tr(struct inode *inode, struct file *filp)
 {
 	struct trace_array *tr = inode->i_private;
+	int ret;
 
-	if (tracing_disabled)
-		return -ENODEV;
-
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	filp->private_data = inode->i_private;
 
@@ -4233,10 +4246,11 @@ static int tracing_open(struct inode *inode, struct file *file)
 {
 	struct trace_array *tr = inode->i_private;
 	struct trace_iterator *iter;
-	int ret = 0;
+	int ret;
 
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	/* If this file was open for write, then erase contents */
 	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
@@ -4352,11 +4366,9 @@ static int show_traces_open(struct inode *inode, struct file *file)
 	struct seq_file *m;
 	int ret;
 
-	if (tracing_disabled)
-		return -ENODEV;
-
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	ret = seq_open(file, &show_traces_seq_ops);
 	if (ret) {
@@ -4710,11 +4722,9 @@ static int tracing_trace_options_open(struct inode *inode, struct file *file)
 	struct trace_array *tr = inode->i_private;
 	int ret;
 
-	if (tracing_disabled)
-		return -ENODEV;
-
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	ret = single_open(file, tracing_trace_options_show, inode->i_private);
 	if (ret < 0)
@@ -5051,8 +5061,11 @@ static const struct seq_operations tracing_saved_tgids_seq_ops = {
 
 static int tracing_saved_tgids_open(struct inode *inode, struct file *filp)
 {
-	if (tracing_disabled)
-		return -ENODEV;
+	int ret;
+
+	ret = tracing_check_open_get_tr(NULL);
+	if (ret)
+		return ret;
 
 	return seq_open(filp, &tracing_saved_tgids_seq_ops);
 }
@@ -5128,8 +5141,11 @@ static const struct seq_operations tracing_saved_cmdlines_seq_ops = {
 
 static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp)
 {
-	if (tracing_disabled)
-		return -ENODEV;
+	int ret;
+
+	ret = tracing_check_open_get_tr(NULL);
+	if (ret)
+		return ret;
 
 	return seq_open(filp, &tracing_saved_cmdlines_seq_ops);
 }
@@ -5293,8 +5309,11 @@ static const struct seq_operations tracing_eval_map_seq_ops = {
 
 static int tracing_eval_map_open(struct inode *inode, struct file *filp)
 {
-	if (tracing_disabled)
-		return -ENODEV;
+	int ret;
+
+	ret = tracing_check_open_get_tr(NULL);
+	if (ret)
+		return ret;
 
 	return seq_open(filp, &tracing_eval_map_seq_ops);
 }
@@ -5817,13 +5836,11 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 {
 	struct trace_array *tr = inode->i_private;
 	struct trace_iterator *iter;
-	int ret = 0;
-
-	if (tracing_disabled)
-		return -ENODEV;
+	int ret;
 
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	mutex_lock(&trace_types_lock);
 
@@ -6560,11 +6577,9 @@ static int tracing_clock_open(struct inode *inode, struct file *file)
 	struct trace_array *tr = inode->i_private;
 	int ret;
 
-	if (tracing_disabled)
-		return -ENODEV;
-
-	if (trace_array_get(tr))
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	ret = single_open(file, tracing_clock_show, inode->i_private);
 	if (ret < 0)
@@ -6594,11 +6609,9 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file)
 	struct trace_array *tr = inode->i_private;
 	int ret;
 
-	if (tracing_disabled)
-		return -ENODEV;
-
-	if (trace_array_get(tr))
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	ret = single_open(file, tracing_time_stamp_mode_show, inode->i_private);
 	if (ret < 0)
@@ -6651,10 +6664,11 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file)
 	struct trace_array *tr = inode->i_private;
 	struct trace_iterator *iter;
 	struct seq_file *m;
-	int ret = 0;
+	int ret;
 
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	if (file->f_mode & FMODE_READ) {
 		iter = __tracing_open(inode, file, true);
@@ -7118,8 +7132,9 @@ static int tracing_err_log_open(struct inode *inode, struct file *file)
 	struct trace_array *tr = inode->i_private;
 	int ret = 0;
 
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	/* If this file was opened for write, then erase contents */
 	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC))
@@ -7170,11 +7185,9 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp)
 	struct ftrace_buffer_info *info;
 	int ret;
 
-	if (tracing_disabled)
-		return -ENODEV;
-
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info) {
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 854dbf4050f8..d685c61085c0 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -338,6 +338,7 @@ extern struct mutex trace_types_lock;
 
 extern int trace_array_get(struct trace_array *tr);
 extern void trace_array_put(struct trace_array *tr);
+extern int tracing_check_open_get_tr(struct trace_array *tr);
 
 extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs);
 extern int tracing_set_clock(struct trace_array *tr, const char *clockstr);
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index a41fed46c285..89779eb84a07 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -174,6 +174,10 @@ static int dyn_event_open(struct inode *inode, struct file *file)
 {
 	int ret;
 
+	ret = tracing_check_open_get_tr(NULL);
+	if (ret)
+		return ret;
+
 	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
 		ret = dyn_events_release_all(NULL);
 		if (ret < 0)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 9613a757c902..71ab0a3660f4 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1794,8 +1794,9 @@ ftrace_event_set_open(struct inode *inode, struct file *file)
 	struct trace_array *tr = inode->i_private;
 	int ret;
 
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC))
@@ -1814,8 +1815,9 @@ ftrace_event_set_pid_open(struct inode *inode, struct file *file)
 	struct trace_array *tr = inode->i_private;
 	int ret;
 
-	if (trace_array_get(tr) < 0)
-		return -ENODEV;
+	ret = tracing_check_open_get_tr(tr);
+	if (ret)
+		return ret;
 
 	if ((file->f_mode & FMODE_WRITE) &&
 	    (file->f_flags & O_TRUNC))
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 9468bd8d44a2..dd18d76bf1bd 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -1680,7 +1680,7 @@ static int save_hist_vars(struct hist_trigger_data *hist_data)
 	if (var_data)
 		return 0;
 
-	if (trace_array_get(tr) < 0)
+	if (tracing_check_open_get_tr(tr))
 		return -ENODEV;
 
 	var_data = kzalloc(sizeof(*var_data), GFP_KERNEL);
-- 
cgit v1.2.3


From 17911ff38aa58d3c95c07589dbf5d3564c4cf3c5 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 11 Oct 2019 17:22:50 -0400
Subject: tracing: Add locked_down checks to the open calls of files created
 for tracefs

Added various checks on open tracefs calls to see if tracefs is in lockdown
mode, and if so, to return -EPERM.

Note, the event format files (which are basically standard on all machines)
as well as the enabled_functions file (which shows what is currently being
traced) are not lockde down. Perhaps they should be, but it seems counter
intuitive to lockdown information to help you know if the system has been
modified.

Link: http://lkml.kernel.org/r/CAHk-=wj7fGPKUspr579Cii-w_y60PtRaiDgKuxVtBAMK0VNNkA@mail.gmail.com

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c               | 23 ++++++++++++++++++++++-
 kernel/trace/trace.c                |  8 ++++++++
 kernel/trace/trace_events.c         |  8 ++++++++
 kernel/trace/trace_events_hist.c    | 11 +++++++++++
 kernel/trace/trace_events_trigger.c |  8 +++++++-
 kernel/trace/trace_kprobe.c         | 12 +++++++++++-
 kernel/trace/trace_printk.c         |  7 +++++++
 kernel/trace/trace_stack.c          |  8 ++++++++
 kernel/trace/trace_stat.c           |  6 +++++-
 kernel/trace/trace_uprobe.c         | 11 +++++++++++
 10 files changed, 98 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8b765a55e01c..f296d89be757 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -18,6 +18,7 @@
 #include <linux/clocksource.h>
 #include <linux/sched/task.h>
 #include <linux/kallsyms.h>
+#include <linux/security.h>
 #include <linux/seq_file.h>
 #include <linux/tracefs.h>
 #include <linux/hardirq.h>
@@ -3486,6 +3487,11 @@ static int
 ftrace_avail_open(struct inode *inode, struct file *file)
 {
 	struct ftrace_iterator *iter;
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
 
 	if (unlikely(ftrace_disabled))
 		return -ENODEV;
@@ -3505,6 +3511,15 @@ ftrace_enabled_open(struct inode *inode, struct file *file)
 {
 	struct ftrace_iterator *iter;
 
+	/*
+	 * This shows us what functions are currently being
+	 * traced and by what. Not sure if we want lockdown
+	 * to hide such critical information for an admin.
+	 * Although, perhaps it can show information we don't
+	 * want people to see, but if something is tracing
+	 * something, we probably want to know about it.
+	 */
+
 	iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
 	if (!iter)
 		return -ENOMEM;
@@ -3625,6 +3640,7 @@ ftrace_filter_open(struct inode *inode, struct file *file)
 {
 	struct ftrace_ops *ops = inode->i_private;
 
+	/* Checks for tracefs lockdown */
 	return ftrace_regex_open(ops,
 			FTRACE_ITER_FILTER | FTRACE_ITER_DO_PROBES,
 			inode, file);
@@ -3635,6 +3651,7 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
 {
 	struct ftrace_ops *ops = inode->i_private;
 
+	/* Checks for tracefs lockdown */
 	return ftrace_regex_open(ops, FTRACE_ITER_NOTRACE,
 				 inode, file);
 }
@@ -5203,9 +5220,13 @@ static int
 __ftrace_graph_open(struct inode *inode, struct file *file,
 		    struct ftrace_graph_data *fgd)
 {
-	int ret = 0;
+	int ret;
 	struct ftrace_hash *new_hash = NULL;
 
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	if (file->f_mode & FMODE_WRITE) {
 		const int size_bits = FTRACE_HASH_DEFAULT_BITS;
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 26ee280f852b..2b4eff383505 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,6 +17,7 @@
 #include <linux/stacktrace.h>
 #include <linux/writeback.h>
 #include <linux/kallsyms.h>
+#include <linux/security.h>
 #include <linux/seq_file.h>
 #include <linux/notifier.h>
 #include <linux/irqflags.h>
@@ -306,6 +307,12 @@ void trace_array_put(struct trace_array *this_tr)
 
 int tracing_check_open_get_tr(struct trace_array *tr)
 {
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	if (tracing_disabled)
 		return -ENODEV;
 
@@ -6813,6 +6820,7 @@ static int snapshot_raw_open(struct inode *inode, struct file *filp)
 	struct ftrace_buffer_info *info;
 	int ret;
 
+	/* The following checks for tracefs lockdown */
 	ret = tracing_buffers_open(inode, filp);
 	if (ret < 0)
 		return ret;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 71ab0a3660f4..fba87d10f0c1 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -12,6 +12,7 @@
 #define pr_fmt(fmt) fmt
 
 #include <linux/workqueue.h>
+#include <linux/security.h>
 #include <linux/spinlock.h>
 #include <linux/kthread.h>
 #include <linux/tracefs.h>
@@ -1294,6 +1295,8 @@ static int trace_format_open(struct inode *inode, struct file *file)
 	struct seq_file *m;
 	int ret;
 
+	/* Do we want to hide event format files on tracefs lockdown? */
+
 	ret = seq_open(file, &trace_format_seq_ops);
 	if (ret < 0)
 		return ret;
@@ -1760,6 +1763,10 @@ ftrace_event_open(struct inode *inode, struct file *file,
 	struct seq_file *m;
 	int ret;
 
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	ret = seq_open(file, seq_ops);
 	if (ret < 0)
 		return ret;
@@ -1784,6 +1791,7 @@ ftrace_event_avail_open(struct inode *inode, struct file *file)
 {
 	const struct seq_operations *seq_ops = &show_event_seq_ops;
 
+	/* Checks for tracefs lockdown */
 	return ftrace_event_open(inode, file, seq_ops);
 }
 
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index dd18d76bf1bd..57648c5aa679 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -7,6 +7,7 @@
 
 #include <linux/module.h>
 #include <linux/kallsyms.h>
+#include <linux/security.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/stacktrace.h>
@@ -1448,6 +1449,10 @@ static int synth_events_open(struct inode *inode, struct file *file)
 {
 	int ret;
 
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
 		ret = dyn_events_release_all(&synth_event_ops);
 		if (ret < 0)
@@ -5515,6 +5520,12 @@ static int hist_show(struct seq_file *m, void *v)
 
 static int event_hist_open(struct inode *inode, struct file *file)
 {
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	return single_open(file, hist_show, file);
 }
 
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 2a2912cb4533..2cd53ca21b51 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2013 Tom Zanussi <tom.zanussi@linux.intel.com>
  */
 
+#include <linux/security.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/mutex.h>
@@ -173,7 +174,11 @@ static const struct seq_operations event_triggers_seq_ops = {
 
 static int event_trigger_regex_open(struct inode *inode, struct file *file)
 {
-	int ret = 0;
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
 
 	mutex_lock(&event_mutex);
 
@@ -292,6 +297,7 @@ event_trigger_write(struct file *filp, const char __user *ubuf,
 static int
 event_trigger_open(struct inode *inode, struct file *filp)
 {
+	/* Checks for tracefs lockdown */
 	return event_trigger_regex_open(inode, filp);
 }
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 324ffbea3556..1552a95c743b 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -7,11 +7,11 @@
  */
 #define pr_fmt(fmt)	"trace_kprobe: " fmt
 
+#include <linux/security.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
 #include <linux/rculist.h>
 #include <linux/error-injection.h>
-#include <linux/security.h>
 
 #include <asm/setup.h>  /* for COMMAND_LINE_SIZE */
 
@@ -936,6 +936,10 @@ static int probes_open(struct inode *inode, struct file *file)
 {
 	int ret;
 
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
 		ret = dyn_events_release_all(&trace_kprobe_ops);
 		if (ret < 0)
@@ -988,6 +992,12 @@ static const struct seq_operations profile_seq_op = {
 
 static int profile_open(struct inode *inode, struct file *file)
 {
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	return seq_open(file, &profile_seq_op);
 }
 
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index c3fd849d4a8f..d4e31e969206 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -6,6 +6,7 @@
  *
  */
 #include <linux/seq_file.h>
+#include <linux/security.h>
 #include <linux/uaccess.h>
 #include <linux/kernel.h>
 #include <linux/ftrace.h>
@@ -348,6 +349,12 @@ static const struct seq_operations show_format_seq_ops = {
 static int
 ftrace_formats_open(struct inode *inode, struct file *file)
 {
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	return seq_open(file, &show_format_seq_ops);
 }
 
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index ec9a34a97129..4df9a209f7ca 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -5,6 +5,7 @@
  */
 #include <linux/sched/task_stack.h>
 #include <linux/stacktrace.h>
+#include <linux/security.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
 #include <linux/spinlock.h>
@@ -470,6 +471,12 @@ static const struct seq_operations stack_trace_seq_ops = {
 
 static int stack_trace_open(struct inode *inode, struct file *file)
 {
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	return seq_open(file, &stack_trace_seq_ops);
 }
 
@@ -487,6 +494,7 @@ stack_trace_filter_open(struct inode *inode, struct file *file)
 {
 	struct ftrace_ops *ops = inode->i_private;
 
+	/* Checks for tracefs lockdown */
 	return ftrace_regex_open(ops, FTRACE_ITER_FILTER,
 				 inode, file);
 }
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 75bf1bcb4a8a..9ab0a1a7ad5e 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -9,7 +9,7 @@
  *
  */
 
-
+#include <linux/security.h>
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/rbtree.h>
@@ -238,6 +238,10 @@ static int tracing_stat_open(struct inode *inode, struct file *file)
 	struct seq_file *m;
 	struct stat_session *session = inode->i_private;
 
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	ret = stat_seq_init(session);
 	if (ret)
 		return ret;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index dd884341f5c5..352073d36585 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -7,6 +7,7 @@
  */
 #define pr_fmt(fmt)	"trace_uprobe: " fmt
 
+#include <linux/security.h>
 #include <linux/ctype.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
@@ -769,6 +770,10 @@ static int probes_open(struct inode *inode, struct file *file)
 {
 	int ret;
 
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
 		ret = dyn_events_release_all(&trace_uprobe_ops);
 		if (ret)
@@ -818,6 +823,12 @@ static const struct seq_operations profile_seq_op = {
 
 static int profile_open(struct inode *inode, struct file *file)
 {
+	int ret;
+
+	ret = security_locked_down(LOCKDOWN_TRACEFS);
+	if (ret)
+		return ret;
+
 	return seq_open(file, &profile_seq_op);
 }
 
-- 
cgit v1.2.3


From bf8e602186ec402ed937b2cbd6c39a34c0029757 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Fri, 11 Oct 2019 20:41:41 -0400
Subject: tracing: Do not create tracefs files if tracefs lockdown is in effect

If on boot up, lockdown is activated for tracefs, don't even bother creating
the files. This can also prevent instances from being created if lockdown is
in effect.

Link: http://lkml.kernel.org/r/CAHk-=whC6Ji=fWnjh2+eS4b15TnbsS4VPVtvBOwCy1jjEG_JHQ@mail.gmail.com

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 fs/tracefs/inode.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index eeeae0475da9..0caa151cae4e 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -16,6 +16,7 @@
 #include <linux/namei.h>
 #include <linux/tracefs.h>
 #include <linux/fsnotify.h>
+#include <linux/security.h>
 #include <linux/seq_file.h>
 #include <linux/parser.h>
 #include <linux/magic.h>
@@ -390,6 +391,9 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 	struct dentry *dentry;
 	struct inode *inode;
 
+	if (security_locked_down(LOCKDOWN_TRACEFS))
+		return NULL;
+
 	if (!(mode & S_IFMT))
 		mode |= S_IFREG;
 	BUG_ON(!S_ISREG(mode));
-- 
cgit v1.2.3


From 7f8557b88d6aa5bf31f25f6013d81355a1b1d48d Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Wed, 9 Oct 2019 11:05:38 -0400
Subject: recordmcount: Fix nop_mcount() function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The removal of the longjmp code in recordmcount.c mistakenly made the return
of make_nop() being negative an exit of nop_mcount(). It should not exit the
routine, but instead just not process that part of the code. By exiting with
an error code, it would cause the update of recordmcount to fail some files
which would fail the build if ftrace function tracing was enabled.

Link: http://lkml.kernel.org/r/20191009110538.5909fec6@gandalf.local.home

Reported-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Tested-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Fixes: 3f1df12019f3 ("recordmcount: Rewrite error/success handling")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 scripts/recordmcount.h | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index 8f0a278ce0af..74eab03e31d4 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -389,11 +389,8 @@ static int nop_mcount(Elf_Shdr const *const relhdr,
 			mcountsym = get_mcountsym(sym0, relp, str0);
 
 		if (mcountsym == Elf_r_sym(relp) && !is_fake_mcount(relp)) {
-			if (make_nop) {
+			if (make_nop)
 				ret = make_nop((void *)ehdr, _w(shdr->sh_offset) + _w(relp->r_offset));
-				if (ret < 0)
-					return -1;
-			}
 			if (warn_on_notrace_sect && !once) {
 				printf("Section %s has mcount callers being ignored\n",
 				       txtname);
-- 
cgit v1.2.3


From 98dc19c11470ee6048aba723d77079ad2cda8a52 Mon Sep 17 00:00:00 2001
From: "Srivatsa S. Bhat (VMware)" <srivatsa@csail.mit.edu>
Date: Thu, 10 Oct 2019 11:50:46 -0700
Subject: tracing/hwlat: Report total time spent in all NMIs during the sample

nmi_total_ts is supposed to record the total time spent in *all* NMIs
that occur on the given CPU during the (active portion of the)
sampling window. However, the code seems to be overwriting this
variable for each NMI, thereby only recording the time spent in the
most recent NMI. Fix it by accumulating the duration instead.

Link: http://lkml.kernel.org/r/157073343544.17189.13911783866738671133.stgit@srivatsa-ubuntu

Fixes: 7b2c86250122 ("tracing: Add NMI tracing in hwlat detector")
Cc: stable@vger.kernel.org
Signed-off-by: Srivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_hwlat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index fa95139445b2..a0251a78807d 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -150,7 +150,7 @@ void trace_hwlat_callback(bool enter)
 		if (enter)
 			nmi_ts_start = time_get();
 		else
-			nmi_total_ts = time_get() - nmi_ts_start;
+			nmi_total_ts += time_get() - nmi_ts_start;
 	}
 
 	if (enter)
-- 
cgit v1.2.3


From fc64e4ad80d4b72efce116f87b3174f0b7196f8e Mon Sep 17 00:00:00 2001
From: "Srivatsa S. Bhat (VMware)" <srivatsa@csail.mit.edu>
Date: Thu, 10 Oct 2019 11:51:01 -0700
Subject: tracing/hwlat: Don't ignore outer-loop duration when calculating
 max_latency

max_latency is intended to record the maximum ever observed hardware
latency, which may occur in either part of the loop (inner/outer). So
we need to also consider the outer-loop sample when updating
max_latency.

Link: http://lkml.kernel.org/r/157073345463.17189.18124025522664682811.stgit@srivatsa-ubuntu

Fixes: e7c15cd8a113 ("tracing: Added hardware latency tracer")
Cc: stable@vger.kernel.org
Signed-off-by: Srivatsa S. Bhat (VMware) <srivatsa@csail.mit.edu>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_hwlat.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index a0251a78807d..862f4b0139fc 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -256,6 +256,8 @@ static int get_sample(void)
 		/* Keep a running maximum ever recorded hardware latency */
 		if (sample > tr->max_latency)
 			tr->max_latency = sample;
+		if (outer_sample > tr->max_latency)
+			tr->max_latency = outer_sample;
 	}
 
 out:
-- 
cgit v1.2.3


From d303de1fcf344ff7c15ed64c3f48a991c9958775 Mon Sep 17 00:00:00 2001
From: Petr Mladek <pmladek@suse.com>
Date: Fri, 11 Oct 2019 16:21:34 +0200
Subject: tracing: Initialize iter->seq after zeroing in tracing_read_pipe()

A customer reported the following softlockup:

[899688.160002] NMI watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [test.sh:16464]
[899688.160002] CPU: 0 PID: 16464 Comm: test.sh Not tainted 4.12.14-6.23-azure #1 SLE12-SP4
[899688.160002] RIP: 0010:up_write+0x1a/0x30
[899688.160002] Kernel panic - not syncing: softlockup: hung tasks
[899688.160002] RIP: 0010:up_write+0x1a/0x30
[899688.160002] RSP: 0018:ffffa86784d4fde8 EFLAGS: 00000257 ORIG_RAX: ffffffffffffff12
[899688.160002] RAX: ffffffff970fea00 RBX: 0000000000000001 RCX: 0000000000000000
[899688.160002] RDX: ffffffff00000001 RSI: 0000000000000080 RDI: ffffffff970fea00
[899688.160002] RBP: ffffffffffffffff R08: ffffffffffffffff R09: 0000000000000000
[899688.160002] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8b59014720d8
[899688.160002] R13: ffff8b59014720c0 R14: ffff8b5901471090 R15: ffff8b5901470000
[899688.160002]  tracing_read_pipe+0x336/0x3c0
[899688.160002]  __vfs_read+0x26/0x140
[899688.160002]  vfs_read+0x87/0x130
[899688.160002]  SyS_read+0x42/0x90
[899688.160002]  do_syscall_64+0x74/0x160

It caught the process in the middle of trace_access_unlock(). There is
no loop. So, it must be looping in the caller tracing_read_pipe()
via the "waitagain" label.

Crashdump analyze uncovered that iter->seq was completely zeroed
at this point, including iter->seq.seq.size. It means that
print_trace_line() was never able to print anything and
there was no forward progress.

The culprit seems to be in the code:

	/* reset all but tr, trace, and overruns */
	memset(&iter->seq, 0,
	       sizeof(struct trace_iterator) -
	       offsetof(struct trace_iterator, seq));

It was added by the commit 53d0aa773053ab182877 ("ftrace:
add logic to record overruns"). It was v2.6.27-rc1.
It was the time when iter->seq looked like:

     struct trace_seq {
	unsigned char		buffer[PAGE_SIZE];
	unsigned int		len;
     };

There was no "size" variable and zeroing was perfectly fine.

The solution is to reinitialize the structure after or without
zeroing.

Link: http://lkml.kernel.org/r/20191011142134.11997-1-pmladek@suse.com

Signed-off-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2b4eff383505..6a0ee9178365 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6036,6 +6036,7 @@ waitagain:
 	       sizeof(struct trace_iterator) -
 	       offsetof(struct trace_iterator, seq));
 	cpumask_clear(iter->started);
+	trace_seq_init(&iter->seq);
 	iter->pos = -1;
 
 	trace_event_read_lock();
-- 
cgit v1.2.3


From c2fba936d3047fc5ea1458549daa19844ef243a4 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sun, 13 Oct 2019 10:52:11 +0100
Subject: drm/i915/perf: Avoid polluting the i915_oa_config with error pointers

Use a local variable to track the allocation errors to avoid polluting
the struct and keep the free simple.

Reported-by: kbuild test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191013095211.2922-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_perf.c | 52 +++++++++++++++++++---------------------
 1 file changed, 25 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index b4e2332d35cb..366580701ba2 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -384,12 +384,9 @@ void i915_oa_config_release(struct kref *ref)
 	struct i915_oa_config *oa_config =
 		container_of(ref, typeof(*oa_config), ref);
 
-	if (!PTR_ERR(oa_config->flex_regs))
-		kfree(oa_config->flex_regs);
-	if (!PTR_ERR(oa_config->b_counter_regs))
-		kfree(oa_config->b_counter_regs);
-	if (!PTR_ERR(oa_config->mux_regs))
-		kfree(oa_config->mux_regs);
+	kfree(oa_config->flex_regs);
+	kfree(oa_config->b_counter_regs);
+	kfree(oa_config->mux_regs);
 
 	kfree_rcu(oa_config, rcu);
 }
@@ -3631,6 +3628,7 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 	struct i915_perf *perf = &to_i915(dev)->perf;
 	struct drm_i915_perf_oa_config *args = data;
 	struct i915_oa_config *oa_config, *tmp;
+	static struct i915_oa_reg *regs;
 	int err, id;
 
 	if (!perf->i915) {
@@ -3676,30 +3674,30 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 	memcpy(oa_config->uuid, args->uuid, sizeof(args->uuid));
 
 	oa_config->mux_regs_len = args->n_mux_regs;
-	oa_config->mux_regs =
-		alloc_oa_regs(perf,
-			      perf->ops.is_valid_mux_reg,
-			      u64_to_user_ptr(args->mux_regs_ptr),
-			      args->n_mux_regs);
+	regs = alloc_oa_regs(perf,
+			     perf->ops.is_valid_mux_reg,
+			     u64_to_user_ptr(args->mux_regs_ptr),
+			     args->n_mux_regs);
 
-	if (IS_ERR(oa_config->mux_regs)) {
+	if (IS_ERR(regs)) {
 		DRM_DEBUG("Failed to create OA config for mux_regs\n");
-		err = PTR_ERR(oa_config->mux_regs);
+		err = PTR_ERR(regs);
 		goto reg_err;
 	}
+	oa_config->mux_regs = regs;
 
 	oa_config->b_counter_regs_len = args->n_boolean_regs;
-	oa_config->b_counter_regs =
-		alloc_oa_regs(perf,
-			      perf->ops.is_valid_b_counter_reg,
-			      u64_to_user_ptr(args->boolean_regs_ptr),
-			      args->n_boolean_regs);
+	regs = alloc_oa_regs(perf,
+			     perf->ops.is_valid_b_counter_reg,
+			     u64_to_user_ptr(args->boolean_regs_ptr),
+			     args->n_boolean_regs);
 
-	if (IS_ERR(oa_config->b_counter_regs)) {
+	if (IS_ERR(regs)) {
 		DRM_DEBUG("Failed to create OA config for b_counter_regs\n");
-		err = PTR_ERR(oa_config->b_counter_regs);
+		err = PTR_ERR(regs);
 		goto reg_err;
 	}
+	oa_config->b_counter_regs = regs;
 
 	if (INTEL_GEN(perf->i915) < 8) {
 		if (args->n_flex_regs != 0) {
@@ -3708,17 +3706,17 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data,
 		}
 	} else {
 		oa_config->flex_regs_len = args->n_flex_regs;
-		oa_config->flex_regs =
-			alloc_oa_regs(perf,
-				      perf->ops.is_valid_flex_reg,
-				      u64_to_user_ptr(args->flex_regs_ptr),
-				      args->n_flex_regs);
+		regs = alloc_oa_regs(perf,
+				     perf->ops.is_valid_flex_reg,
+				     u64_to_user_ptr(args->flex_regs_ptr),
+				     args->n_flex_regs);
 
-		if (IS_ERR(oa_config->flex_regs)) {
+		if (IS_ERR(regs)) {
 			DRM_DEBUG("Failed to create OA config for flex_regs\n");
-			err = PTR_ERR(oa_config->flex_regs);
+			err = PTR_ERR(regs);
 			goto reg_err;
 		}
+		oa_config->flex_regs = regs;
 	}
 
 	err = mutex_lock_interruptible(&perf->metrics_lock);
-- 
cgit v1.2.3


From edc5774c097f6463e9fb2373832e7db726247809 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 13 Oct 2019 09:37:16 -0400
Subject: tools/virtio: xen stub

Fixes test module build.

Reported-by: Jan Kiszka <jan.kiszka@web.de>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 tools/virtio/xen/xen.h | 6 ++++++
 1 file changed, 6 insertions(+)
 create mode 100644 tools/virtio/xen/xen.h

diff --git a/tools/virtio/xen/xen.h b/tools/virtio/xen/xen.h
new file mode 100644
index 000000000000..f569387d1403
--- /dev/null
+++ b/tools/virtio/xen/xen.h
@@ -0,0 +1,6 @@
+#ifndef XEN_XEN_STUB_H
+#define XEN_XEN_STUB_H
+
+#define xen_domain() 0
+
+#endif
-- 
cgit v1.2.3


From 245cdd9fbd396483d501db83047116e2530f245f Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Mon, 7 Oct 2019 13:56:59 -0400
Subject: vhost/test: stop device before reset

When device stop was moved out of reset, test device wasn't updated to
stop before reset, this resulted in a use after free.  Fix by invoking
stop appropriately.

Fixes: b211616d7125 ("vhost: move -net specific code out")
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/test.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index 7804869c6a31..056308008288 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -161,6 +161,7 @@ static int vhost_test_release(struct inode *inode, struct file *f)
 
 	vhost_test_stop(n, &private);
 	vhost_test_flush(n);
+	vhost_dev_stop(&n->dev);
 	vhost_dev_cleanup(&n->dev);
 	/* We do an extra flush before freeing memory,
 	 * since jobs can re-queue themselves. */
@@ -237,6 +238,7 @@ static long vhost_test_reset_owner(struct vhost_test *n)
 	}
 	vhost_test_stop(n, &priv);
 	vhost_test_flush(n);
+	vhost_dev_stop(&n->dev);
 	vhost_dev_reset_owner(&n->dev, umem);
 done:
 	mutex_unlock(&n->dev.mutex);
-- 
cgit v1.2.3


From d983ea6f16b835dcde2ee9a58a1e764ce68bfccc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:38 -0700
Subject: tcp: add rcu protection around tp->fastopen_rsk

Both tcp_v4_err() and tcp_v6_err() do the following operations
while they do not own the socket lock :

	fastopen = tp->fastopen_rsk;
 	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;

The problem is that without appropriate barrier, the compiler
might reload tp->fastopen_rsk and trigger a NULL deref.

request sockets are protected by RCU, we can simply add
the missing annotations and barriers to solve the issue.

Fixes: 168a8f58059a ("tcp: TCP Fast Open Server - main code path")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h             |  6 +++---
 net/core/request_sock.c         |  2 +-
 net/ipv4/inet_connection_sock.c |  4 ++--
 net/ipv4/tcp.c                  | 11 ++++++++---
 net/ipv4/tcp_fastopen.c         |  2 +-
 net/ipv4/tcp_input.c            | 13 +++++++++----
 net/ipv4/tcp_ipv4.c             |  4 ++--
 net/ipv4/tcp_minisocks.c        |  2 +-
 net/ipv4/tcp_output.c           |  2 +-
 net/ipv4/tcp_timer.c            | 11 ++++++-----
 net/ipv6/tcp_ipv6.c             |  2 +-
 11 files changed, 35 insertions(+), 24 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 99617e528ea2..668e25a76d69 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -393,7 +393,7 @@ struct tcp_sock {
 	/* fastopen_rsk points to request_sock that resulted in this big
 	 * socket. Used to retransmit SYNACKs etc.
 	 */
-	struct request_sock *fastopen_rsk;
+	struct request_sock __rcu *fastopen_rsk;
 	u32	*saved_syn;
 };
 
@@ -447,8 +447,8 @@ static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
 
 static inline bool tcp_passive_fastopen(const struct sock *sk)
 {
-	return (sk->sk_state == TCP_SYN_RECV &&
-		tcp_sk(sk)->fastopen_rsk != NULL);
+	return sk->sk_state == TCP_SYN_RECV &&
+	       rcu_access_pointer(tcp_sk(sk)->fastopen_rsk) != NULL;
 }
 
 static inline void fastopen_queue_tune(struct sock *sk, int backlog)
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index c9bb00008528..f35c2e998406 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -96,7 +96,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
 
 	fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq;
 
-	tcp_sk(sk)->fastopen_rsk = NULL;
+	RCU_INIT_POINTER(tcp_sk(sk)->fastopen_rsk, NULL);
 	spin_lock_bh(&fastopenq->lock);
 	fastopenq->qlen--;
 	tcp_rsk(req)->tfo_listener = false;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index dbcf34ec8dd2..eb30fc1770de 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -906,7 +906,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 	percpu_counter_inc(sk->sk_prot->orphan_count);
 
 	if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) {
-		BUG_ON(tcp_sk(child)->fastopen_rsk != req);
+		BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req);
 		BUG_ON(sk != req->rsk_listener);
 
 		/* Paranoid, to prevent race condition if
@@ -915,7 +915,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 		 * Also to satisfy an assertion in
 		 * tcp_v4_destroy_sock().
 		 */
-		tcp_sk(child)->fastopen_rsk = NULL;
+		RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL);
 	}
 	inet_csk_destroy_sock(child);
 }
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8781a92ea4b6..c59d0bd29c5c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -543,7 +543,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 	/* Connected or passive Fast Open socket? */
 	if (state != TCP_SYN_SENT &&
-	    (state != TCP_SYN_RECV || tp->fastopen_rsk)) {
+	    (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) {
 		int target = sock_rcvlowat(sk, 0, INT_MAX);
 
 		if (tp->urg_seq == tp->copied_seq &&
@@ -2487,7 +2487,10 @@ adjudge_to_death:
 	}
 
 	if (sk->sk_state == TCP_CLOSE) {
-		struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
+		struct request_sock *req;
+
+		req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
+						lockdep_sock_is_held(sk));
 		/* We could get here with a non-NULL req if the socket is
 		 * aborted (e.g., closed with unread data) before 3WHS
 		 * finishes.
@@ -3831,8 +3834,10 @@ EXPORT_SYMBOL(tcp_md5_hash_key);
 
 void tcp_done(struct sock *sk)
 {
-	struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
+	struct request_sock *req;
 
+	req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
+					lockdep_sock_is_held(sk));
 	if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
 		TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
 
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 3fd451271a70..a915ade0c818 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -253,7 +253,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	 */
 	tp = tcp_sk(child);
 
-	tp->fastopen_rsk = req;
+	rcu_assign_pointer(tp->fastopen_rsk, req);
 	tcp_rsk(req)->tfo_listener = true;
 
 	/* RFC1323: The window in SYN & SYN/ACK segments is never
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3578357abe30..5f9b102c3b55 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2666,7 +2666,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack,
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool recovered = !before(tp->snd_una, tp->high_seq);
 
-	if ((flag & FLAG_SND_UNA_ADVANCED || tp->fastopen_rsk) &&
+	if ((flag & FLAG_SND_UNA_ADVANCED || rcu_access_pointer(tp->fastopen_rsk)) &&
 	    tcp_try_undo_loss(sk, false))
 		return;
 
@@ -2990,7 +2990,7 @@ void tcp_rearm_rto(struct sock *sk)
 	/* If the retrans timer is currently being used by Fast Open
 	 * for SYN-ACK retrans purpose, stay put.
 	 */
-	if (tp->fastopen_rsk)
+	if (rcu_access_pointer(tp->fastopen_rsk))
 		return;
 
 	if (!tp->packets_out) {
@@ -6087,6 +6087,8 @@ reset_and_undo:
 
 static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
 {
+	struct request_sock *req;
+
 	tcp_try_undo_loss(sk, false);
 
 	/* Reset rtx states to prevent spurious retransmits_timed_out() */
@@ -6096,7 +6098,9 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk)
 	/* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1,
 	 * we no longer need req so release it.
 	 */
-	reqsk_fastopen_remove(sk, tcp_sk(sk)->fastopen_rsk, false);
+	req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
+					lockdep_sock_is_held(sk));
+	reqsk_fastopen_remove(sk, req, false);
 
 	/* Re-arm the timer because data may have been sent out.
 	 * This is similar to the regular data transmission case
@@ -6171,7 +6175,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 
 	tcp_mstamp_refresh(tp);
 	tp->rx_opt.saw_tstamp = 0;
-	req = tp->fastopen_rsk;
+	req = rcu_dereference_protected(tp->fastopen_rsk,
+					lockdep_sock_is_held(sk));
 	if (req) {
 		bool req_stolen;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 492bf6a6b023..ffa366099eb2 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -478,7 +478,7 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	icsk = inet_csk(sk);
 	tp = tcp_sk(sk);
 	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
-	fastopen = tp->fastopen_rsk;
+	fastopen = rcu_dereference(tp->fastopen_rsk);
 	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
 	if (sk->sk_state != TCP_LISTEN &&
 	    !between(seq, snd_una, tp->snd_nxt)) {
@@ -2121,7 +2121,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	if (inet_csk(sk)->icsk_bind_hash)
 		inet_put_port(sk);
 
-	BUG_ON(tp->fastopen_rsk);
+	BUG_ON(rcu_access_pointer(tp->fastopen_rsk));
 
 	/* If socket is aborted during connect operation */
 	tcp_free_fastopen_req(tp);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index bb140a5db8c0..5401dbd39c8f 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -541,7 +541,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	newtp->rx_opt.mss_clamp = req->mss;
 	tcp_ecn_openreq_child(newtp, req);
 	newtp->fastopen_req = NULL;
-	newtp->fastopen_rsk = NULL;
+	RCU_INIT_POINTER(newtp->fastopen_rsk, NULL);
 
 	__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index fec6d67bfd14..84ae4d1449ea 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2482,7 +2482,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 	/* Don't do any loss probe on a Fast Open connection before 3WHS
 	 * finishes.
 	 */
-	if (tp->fastopen_rsk)
+	if (rcu_access_pointer(tp->fastopen_rsk))
 		return false;
 
 	early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 05be564414e9..dd5a6317a801 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -386,15 +386,13 @@ abort:		tcp_write_err(sk);
  *	Timer for Fast Open socket to retransmit SYNACK. Note that the
  *	sk here is the child socket, not the parent (listener) socket.
  */
-static void tcp_fastopen_synack_timer(struct sock *sk)
+static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int max_retries = icsk->icsk_syn_retries ? :
 	    sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct request_sock *req;
 
-	req = tcp_sk(sk)->fastopen_rsk;
 	req->rsk_ops->syn_ack_timeout(req);
 
 	if (req->num_timeout >= max_retries) {
@@ -435,11 +433,14 @@ void tcp_retransmit_timer(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct request_sock *req;
 
-	if (tp->fastopen_rsk) {
+	req = rcu_dereference_protected(tp->fastopen_rsk,
+					lockdep_sock_is_held(sk));
+	if (req) {
 		WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
 			     sk->sk_state != TCP_FIN_WAIT1);
-		tcp_fastopen_synack_timer(sk);
+		tcp_fastopen_synack_timer(sk, req);
 		/* Before we receive ACK to our SYN-ACK don't retransmit
 		 * anything else (e.g., data or FIN segments).
 		 */
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e3d9f4559c99..45a95e032bdf 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -406,7 +406,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	tp = tcp_sk(sk);
 	/* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */
-	fastopen = tp->fastopen_rsk;
+	fastopen = rcu_dereference(tp->fastopen_rsk);
 	snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una;
 	if (sk->sk_state != TCP_LISTEN &&
 	    !between(seq, snd_una, tp->snd_nxt)) {
-- 
cgit v1.2.3


From dba7d9b8c739df27ff3a234c81d6c6b23e3986fa Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:39 -0700
Subject: tcp: annotate tp->rcv_nxt lockless reads

There are few places where we fetch tp->rcv_nxt while
this field can change from IRQ or other cpu.

We need to add READ_ONCE() annotations, and also make
sure write sides use corresponding WRITE_ONCE() to avoid
store-tearing.

Note that tcp_inq_hint() was already using READ_ONCE(tp->rcv_nxt)

syzbot reported :

BUG: KCSAN: data-race in tcp_poll / tcp_queue_rcv

write to 0xffff888120425770 of 4 bytes by interrupt on cpu 0:
 tcp_rcv_nxt_update net/ipv4/tcp_input.c:3365 [inline]
 tcp_queue_rcv+0x180/0x380 net/ipv4/tcp_input.c:4638
 tcp_rcv_established+0xbf1/0xf50 net/ipv4/tcp_input.c:5616
 tcp_v4_do_rcv+0x381/0x4e0 net/ipv4/tcp_ipv4.c:1542
 tcp_v4_rcv+0x1a03/0x1bf0 net/ipv4/tcp_ipv4.c:1923
 ip_protocol_deliver_rcu+0x51/0x470 net/ipv4/ip_input.c:204
 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231
 NF_HOOK include/linux/netfilter.h:305 [inline]
 NF_HOOK include/linux/netfilter.h:299 [inline]
 ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252
 dst_input include/net/dst.h:442 [inline]
 ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413
 NF_HOOK include/linux/netfilter.h:305 [inline]
 NF_HOOK include/linux/netfilter.h:299 [inline]
 ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523
 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5004
 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5118
 netif_receive_skb_internal+0x59/0x190 net/core/dev.c:5208
 napi_skb_finish net/core/dev.c:5671 [inline]
 napi_gro_receive+0x28f/0x330 net/core/dev.c:5704
 receive_buf+0x284/0x30b0 drivers/net/virtio_net.c:1061

read to 0xffff888120425770 of 4 bytes by task 7254 on cpu 1:
 tcp_stream_is_readable net/ipv4/tcp.c:480 [inline]
 tcp_poll+0x204/0x6b0 net/ipv4/tcp.c:554
 sock_poll+0xed/0x250 net/socket.c:1256
 vfs_poll include/linux/poll.h:90 [inline]
 ep_item_poll.isra.0+0x90/0x190 fs/eventpoll.c:892
 ep_send_events_proc+0x113/0x5c0 fs/eventpoll.c:1749
 ep_scan_ready_list.constprop.0+0x189/0x500 fs/eventpoll.c:704
 ep_send_events fs/eventpoll.c:1793 [inline]
 ep_poll+0xe3/0x900 fs/eventpoll.c:1930
 do_epoll_wait+0x162/0x180 fs/eventpoll.c:2294
 __do_sys_epoll_pwait fs/eventpoll.c:2325 [inline]
 __se_sys_epoll_pwait fs/eventpoll.c:2311 [inline]
 __x64_sys_epoll_pwait+0xcd/0x170 fs/eventpoll.c:2311
 do_syscall_64+0xcf/0x2f0 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 7254 Comm: syz-fuzzer Not tainted 5.3.0+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c           | 4 ++--
 net/ipv4/tcp_diag.c      | 2 +-
 net/ipv4/tcp_input.c     | 6 +++---
 net/ipv4/tcp_ipv4.c      | 3 ++-
 net/ipv4/tcp_minisocks.c | 7 +++++--
 net/ipv6/tcp_ipv6.c      | 3 ++-
 6 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c59d0bd29c5c..883ee863db43 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -477,7 +477,7 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
 static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 					  int target, struct sock *sk)
 {
-	return (tp->rcv_nxt - tp->copied_seq >= target) ||
+	return (READ_ONCE(tp->rcv_nxt) - tp->copied_seq >= target) ||
 		(sk->sk_prot->stream_memory_read ?
 		sk->sk_prot->stream_memory_read(sk) : false);
 }
@@ -2935,7 +2935,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		else if (tp->repair_queue == TCP_SEND_QUEUE)
 			tp->write_seq = val;
 		else if (tp->repair_queue == TCP_RECV_QUEUE)
-			tp->rcv_nxt = val;
+			WRITE_ONCE(tp->rcv_nxt, val);
 		else
 			err = -EINVAL;
 		break;
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 81a8221d650a..cd219161f106 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -26,7 +26,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 	} else if (sk->sk_type == SOCK_STREAM) {
 		const struct tcp_sock *tp = tcp_sk(sk);
 
-		r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
+		r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - tp->copied_seq, 0);
 		r->idiag_wqueue = tp->write_seq - tp->snd_una;
 	}
 	if (info)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5f9b102c3b55..5b7c8768ed5f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3362,7 +3362,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq)
 
 	sock_owned_by_me((struct sock *)tp);
 	tp->bytes_received += delta;
-	tp->rcv_nxt = seq;
+	WRITE_ONCE(tp->rcv_nxt, seq);
 }
 
 /* Update our send window.
@@ -5932,7 +5932,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		/* Ok.. it's good. Set up sequence numbers and
 		 * move to established.
 		 */
-		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+		WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
@@ -6035,7 +6035,7 @@ discard:
 			tp->tcp_header_len = sizeof(struct tcphdr);
 		}
 
-		tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+		WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
 		tp->copied_seq = tp->rcv_nxt;
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ffa366099eb2..5089dd6bee0f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2455,7 +2455,8 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 		/* Because we don't lock the socket,
 		 * we might find a transient negative value.
 		 */
-		rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
+		rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+				      tp->copied_seq, 0);
 
 	seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
 			"%08X %5u %8d %lu %d %pK %lu %lu %u %u %d",
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 5401dbd39c8f..adc6ce486a38 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -462,6 +462,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	struct tcp_request_sock *treq = tcp_rsk(req);
 	struct inet_connection_sock *newicsk;
 	struct tcp_sock *oldtp, *newtp;
+	u32 seq;
 
 	if (!newsk)
 		return NULL;
@@ -475,8 +476,10 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	/* Now setup tcp_sock */
 	newtp->pred_flags = 0;
 
-	newtp->rcv_wup = newtp->copied_seq =
-	newtp->rcv_nxt = treq->rcv_isn + 1;
+	seq = treq->rcv_isn + 1;
+	newtp->rcv_wup = seq;
+	newtp->copied_seq = seq;
+	WRITE_ONCE(newtp->rcv_nxt, seq);
 	newtp->segs_in = 1;
 
 	newtp->snd_sml = newtp->snd_una =
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 45a95e032bdf..89ea0a7018b5 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1895,7 +1895,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 		/* Because we don't lock the socket,
 		 * we might find a transient negative value.
 		 */
-		rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
+		rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+				      tp->copied_seq, 0);
 
 	seq_printf(seq,
 		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
-- 
cgit v1.2.3


From 7db48e983930285b765743ebd665aecf9850582b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:40 -0700
Subject: tcp: annotate tp->copied_seq lockless reads

There are few places where we fetch tp->copied_seq while
this field can change from IRQ or other cpu.

We need to add READ_ONCE() annotations, and also make
sure write sides use corresponding WRITE_ONCE() to avoid
store-tearing.

Note that tcp_inq_hint() was already using READ_ONCE(tp->copied_seq)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c           | 20 ++++++++++----------
 net/ipv4/tcp_diag.c      |  3 ++-
 net/ipv4/tcp_input.c     |  6 +++---
 net/ipv4/tcp_ipv4.c      |  2 +-
 net/ipv4/tcp_minisocks.c |  2 +-
 net/ipv4/tcp_output.c    |  2 +-
 net/ipv6/tcp_ipv6.c      |  2 +-
 7 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 883ee863db43..c322ad071e17 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -477,7 +477,7 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
 static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 					  int target, struct sock *sk)
 {
-	return (READ_ONCE(tp->rcv_nxt) - tp->copied_seq >= target) ||
+	return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) ||
 		(sk->sk_prot->stream_memory_read ?
 		sk->sk_prot->stream_memory_read(sk) : false);
 }
@@ -546,7 +546,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	    (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) {
 		int target = sock_rcvlowat(sk, 0, INT_MAX);
 
-		if (tp->urg_seq == tp->copied_seq &&
+		if (tp->urg_seq == READ_ONCE(tp->copied_seq) &&
 		    !sock_flag(sk, SOCK_URGINLINE) &&
 		    tp->urg_data)
 			target++;
@@ -607,7 +607,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		unlock_sock_fast(sk, slow);
 		break;
 	case SIOCATMARK:
-		answ = tp->urg_data && tp->urg_seq == tp->copied_seq;
+		answ = tp->urg_data && tp->urg_seq == READ_ONCE(tp->copied_seq);
 		break;
 	case SIOCOUTQ:
 		if (sk->sk_state == TCP_LISTEN)
@@ -1668,9 +1668,9 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		sk_eat_skb(sk, skb);
 		if (!desc->count)
 			break;
-		tp->copied_seq = seq;
+		WRITE_ONCE(tp->copied_seq, seq);
 	}
-	tp->copied_seq = seq;
+	WRITE_ONCE(tp->copied_seq, seq);
 
 	tcp_rcv_space_adjust(sk);
 
@@ -1819,7 +1819,7 @@ static int tcp_zerocopy_receive(struct sock *sk,
 out:
 	up_read(&current->mm->mmap_sem);
 	if (length) {
-		tp->copied_seq = seq;
+		WRITE_ONCE(tp->copied_seq, seq);
 		tcp_rcv_space_adjust(sk);
 
 		/* Clean up data we have read: This will do ACK frames. */
@@ -2117,7 +2117,7 @@ found_ok_skb:
 			if (urg_offset < used) {
 				if (!urg_offset) {
 					if (!sock_flag(sk, SOCK_URGINLINE)) {
-						++*seq;
+						WRITE_ONCE(*seq, *seq + 1);
 						urg_hole++;
 						offset++;
 						used--;
@@ -2139,7 +2139,7 @@ found_ok_skb:
 			}
 		}
 
-		*seq += used;
+		WRITE_ONCE(*seq, *seq + used);
 		copied += used;
 		len -= used;
 
@@ -2166,7 +2166,7 @@ skip_copy:
 
 found_fin_ok:
 		/* Process the FIN. */
-		++*seq;
+		WRITE_ONCE(*seq, *seq + 1);
 		if (!(flags & MSG_PEEK))
 			sk_eat_skb(sk, skb);
 		break;
@@ -2588,7 +2588,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 		__kfree_skb(sk->sk_rx_skb_cache);
 		sk->sk_rx_skb_cache = NULL;
 	}
-	tp->copied_seq = tp->rcv_nxt;
+	WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 	tp->urg_data = 0;
 	tcp_write_queue_purge(sk);
 	tcp_fastopen_active_disable_ofo_check(sk);
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index cd219161f106..66273c8a55c2 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -26,7 +26,8 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 	} else if (sk->sk_type == SOCK_STREAM) {
 		const struct tcp_sock *tp = tcp_sk(sk);
 
-		r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - tp->copied_seq, 0);
+		r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) -
+					     READ_ONCE(tp->copied_seq), 0);
 		r->idiag_wqueue = tp->write_seq - tp->snd_una;
 	}
 	if (info)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5b7c8768ed5f..a30aae3a6a18 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5961,7 +5961,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		/* Remember, tcp_poll() does not lock socket!
 		 * Change state from SYN-SENT only after copied_seq
 		 * is initialized. */
-		tp->copied_seq = tp->rcv_nxt;
+		WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 
 		smc_check_reset_syn(tp);
 
@@ -6036,7 +6036,7 @@ discard:
 		}
 
 		WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1);
-		tp->copied_seq = tp->rcv_nxt;
+		WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 		tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
 
 		/* RFC1323: The window in SYN & SYN/ACK segments is
@@ -6216,7 +6216,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			tcp_try_undo_spurious_syn(sk);
 			tp->retrans_stamp = 0;
 			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
-			tp->copied_seq = tp->rcv_nxt;
+			WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 		}
 		smp_mb();
 		tcp_set_state(sk, TCP_ESTABLISHED);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5089dd6bee0f..39560f482e0b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2456,7 +2456,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 		 * we might find a transient negative value.
 		 */
 		rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
-				      tp->copied_seq, 0);
+				      READ_ONCE(tp->copied_seq), 0);
 
 	seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
 			"%08X %5u %8d %lu %d %pK %lu %lu %u %u %d",
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index adc6ce486a38..c4731d26ab4a 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -478,7 +478,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 
 	seq = treq->rcv_isn + 1;
 	newtp->rcv_wup = seq;
-	newtp->copied_seq = seq;
+	WRITE_ONCE(newtp->copied_seq, seq);
 	WRITE_ONCE(newtp->rcv_nxt, seq);
 	newtp->segs_in = 1;
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 84ae4d1449ea..7dda12720169 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3433,7 +3433,7 @@ static void tcp_connect_init(struct sock *sk)
 	else
 		tp->rcv_tstamp = tcp_jiffies32;
 	tp->rcv_wup = tp->rcv_nxt;
-	tp->copied_seq = tp->rcv_nxt;
+	WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 
 	inet_csk(sk)->icsk_rto = tcp_timeout_init(sk);
 	inet_csk(sk)->icsk_retransmits = 0;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 89ea0a7018b5..a62c7042fc4a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1896,7 +1896,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 		 * we might find a transient negative value.
 		 */
 		rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) -
-				      tp->copied_seq, 0);
+				      READ_ONCE(tp->copied_seq), 0);
 
 	seq_printf(seq,
 		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
-- 
cgit v1.2.3


From 0f31746452e6793ad6271337438af8f4defb8940 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:41 -0700
Subject: tcp: annotate tp->write_seq lockless reads

There are few places where we fetch tp->write_seq while
this field can change from IRQ or other cpu.

We need to add READ_ONCE() annotations, and also make
sure write sides use corresponding WRITE_ONCE() to avoid
store-tearing.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h        |  2 +-
 net/ipv4/tcp.c           | 20 ++++++++++++--------
 net/ipv4/tcp_diag.c      |  2 +-
 net/ipv4/tcp_ipv4.c      | 21 ++++++++++++---------
 net/ipv4/tcp_minisocks.c |  2 +-
 net/ipv4/tcp_output.c    |  4 ++--
 net/ipv6/tcp_ipv6.c      | 13 +++++++------
 7 files changed, 36 insertions(+), 28 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 35f6f7e0fdc2..8e7c3f6801a9 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1917,7 +1917,7 @@ static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
 static inline bool tcp_stream_memory_free(const struct sock *sk, int wake)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
-	u32 notsent_bytes = tp->write_seq - tp->snd_nxt;
+	u32 notsent_bytes = READ_ONCE(tp->write_seq) - tp->snd_nxt;
 
 	return (notsent_bytes << wake) < tcp_notsent_lowat(tp);
 }
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c322ad071e17..96dd65cbeb85 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -616,7 +616,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
 			answ = 0;
 		else
-			answ = tp->write_seq - tp->snd_una;
+			answ = READ_ONCE(tp->write_seq) - tp->snd_una;
 		break;
 	case SIOCOUTQNSD:
 		if (sk->sk_state == TCP_LISTEN)
@@ -625,7 +625,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
 			answ = 0;
 		else
-			answ = tp->write_seq - tp->snd_nxt;
+			answ = READ_ONCE(tp->write_seq) - tp->snd_nxt;
 		break;
 	default:
 		return -ENOIOCTLCMD;
@@ -1035,7 +1035,7 @@ new_segment:
 		sk->sk_wmem_queued += copy;
 		sk_mem_charge(sk, copy);
 		skb->ip_summed = CHECKSUM_PARTIAL;
-		tp->write_seq += copy;
+		WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
 		TCP_SKB_CB(skb)->end_seq += copy;
 		tcp_skb_pcount_set(skb, 0);
 
@@ -1362,7 +1362,7 @@ new_segment:
 		if (!copied)
 			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
 
-		tp->write_seq += copy;
+		WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
 		TCP_SKB_CB(skb)->end_seq += copy;
 		tcp_skb_pcount_set(skb, 0);
 
@@ -2562,6 +2562,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int old_state = sk->sk_state;
+	u32 seq;
 
 	if (old_state != TCP_CLOSE)
 		tcp_set_state(sk, TCP_CLOSE);
@@ -2604,9 +2605,12 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->srtt_us = 0;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 	tp->rcv_rtt_last_tsecr = 0;
-	tp->write_seq += tp->max_window + 2;
-	if (tp->write_seq == 0)
-		tp->write_seq = 1;
+
+	seq = tp->write_seq + tp->max_window + 2;
+	if (!seq)
+		seq = 1;
+	WRITE_ONCE(tp->write_seq, seq);
+
 	icsk->icsk_backoff = 0;
 	tp->snd_cwnd = 2;
 	icsk->icsk_probes_out = 0;
@@ -2933,7 +2937,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		if (sk->sk_state != TCP_CLOSE)
 			err = -EPERM;
 		else if (tp->repair_queue == TCP_SEND_QUEUE)
-			tp->write_seq = val;
+			WRITE_ONCE(tp->write_seq, val);
 		else if (tp->repair_queue == TCP_RECV_QUEUE)
 			WRITE_ONCE(tp->rcv_nxt, val);
 		else
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 66273c8a55c2..549506162dde 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -28,7 +28,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 
 		r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) -
 					     READ_ONCE(tp->copied_seq), 0);
-		r->idiag_wqueue = tp->write_seq - tp->snd_una;
+		r->idiag_wqueue = READ_ONCE(tp->write_seq) - tp->snd_una;
 	}
 	if (info)
 		tcp_get_info(sk, info);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 39560f482e0b..6be568334848 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -164,9 +164,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 		 * without appearing to create any others.
 		 */
 		if (likely(!tp->repair)) {
-			tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
-			if (tp->write_seq == 0)
-				tp->write_seq = 1;
+			u32 seq = tcptw->tw_snd_nxt + 65535 + 2;
+
+			if (!seq)
+				seq = 1;
+			WRITE_ONCE(tp->write_seq, seq);
 			tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
 			tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
 		}
@@ -253,7 +255,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		tp->rx_opt.ts_recent	   = 0;
 		tp->rx_opt.ts_recent_stamp = 0;
 		if (likely(!tp->repair))
-			tp->write_seq	   = 0;
+			WRITE_ONCE(tp->write_seq, 0);
 	}
 
 	inet->inet_dport = usin->sin_port;
@@ -291,10 +293,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	if (likely(!tp->repair)) {
 		if (!tp->write_seq)
-			tp->write_seq = secure_tcp_seq(inet->inet_saddr,
-						       inet->inet_daddr,
-						       inet->inet_sport,
-						       usin->sin_port);
+			WRITE_ONCE(tp->write_seq,
+				   secure_tcp_seq(inet->inet_saddr,
+						  inet->inet_daddr,
+						  inet->inet_sport,
+						  usin->sin_port));
 		tp->tsoffset = secure_tcp_ts_off(sock_net(sk),
 						 inet->inet_saddr,
 						 inet->inet_daddr);
@@ -2461,7 +2464,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 	seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
 			"%08X %5u %8d %lu %d %pK %lu %lu %u %u %d",
 		i, src, srcp, dest, destp, state,
-		tp->write_seq - tp->snd_una,
+		READ_ONCE(tp->write_seq) - tp->snd_una,
 		rx_queue,
 		timer_active,
 		jiffies_delta_to_clock_t(timer_expires - jiffies),
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index c4731d26ab4a..339944690329 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -498,7 +498,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	newtp->total_retrans = req->num_retrans;
 
 	tcp_init_xmit_timers(newsk);
-	newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
+	WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1);
 
 	if (sock_flag(newsk, SOCK_KEEPOPEN))
 		inet_csk_reset_keepalive_timer(newsk,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7dda12720169..c17c2a78809d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1196,7 +1196,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	/* Advance write_seq and place onto the write_queue. */
-	tp->write_seq = TCP_SKB_CB(skb)->end_seq;
+	WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq);
 	__skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
 	sk->sk_wmem_queued += skb->truesize;
@@ -3449,7 +3449,7 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
 	__skb_header_release(skb);
 	sk->sk_wmem_queued += skb->truesize;
 	sk_mem_charge(sk, skb->truesize);
-	tp->write_seq = tcb->end_seq;
+	WRITE_ONCE(tp->write_seq, tcb->end_seq);
 	tp->packets_out += tcp_skb_pcount(skb);
 }
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index a62c7042fc4a..4804b6dc5e65 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -215,7 +215,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	    !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) {
 		tp->rx_opt.ts_recent = 0;
 		tp->rx_opt.ts_recent_stamp = 0;
-		tp->write_seq = 0;
+		WRITE_ONCE(tp->write_seq, 0);
 	}
 
 	sk->sk_v6_daddr = usin->sin6_addr;
@@ -311,10 +311,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	if (likely(!tp->repair)) {
 		if (!tp->write_seq)
-			tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32,
-							 sk->sk_v6_daddr.s6_addr32,
-							 inet->inet_sport,
-							 inet->inet_dport);
+			WRITE_ONCE(tp->write_seq,
+				   secure_tcpv6_seq(np->saddr.s6_addr32,
+						    sk->sk_v6_daddr.s6_addr32,
+						    inet->inet_sport,
+						    inet->inet_dport));
 		tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk),
 						   np->saddr.s6_addr32,
 						   sk->sk_v6_daddr.s6_addr32);
@@ -1907,7 +1908,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 		   dest->s6_addr32[0], dest->s6_addr32[1],
 		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
 		   state,
-		   tp->write_seq - tp->snd_una,
+		   READ_ONCE(tp->write_seq) - tp->snd_una,
 		   rx_queue,
 		   timer_active,
 		   jiffies_delta_to_clock_t(timer_expires - jiffies),
-- 
cgit v1.2.3


From e0d694d638dba768b47be31c22e1a9b4f862f561 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:42 -0700
Subject: tcp: annotate tp->snd_nxt lockless reads

There are few places where we fetch tp->snd_nxt while
this field can change from IRQ or other cpu.

We need to add READ_ONCE() annotations, and also make
sure write sides use corresponding WRITE_ONCE() to avoid
store-tearing.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h        |  3 ++-
 net/ipv4/tcp.c           |  3 ++-
 net/ipv4/tcp_minisocks.c |  6 ++++--
 net/ipv4/tcp_output.c    | 10 +++++-----
 4 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 8e7c3f6801a9..e1d08f69fd39 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1917,7 +1917,8 @@ static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
 static inline bool tcp_stream_memory_free(const struct sock *sk, int wake)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
-	u32 notsent_bytes = READ_ONCE(tp->write_seq) - tp->snd_nxt;
+	u32 notsent_bytes = READ_ONCE(tp->write_seq) -
+			    READ_ONCE(tp->snd_nxt);
 
 	return (notsent_bytes << wake) < tcp_notsent_lowat(tp);
 }
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 96dd65cbeb85..652568750cb1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -625,7 +625,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
 			answ = 0;
 		else
-			answ = READ_ONCE(tp->write_seq) - tp->snd_nxt;
+			answ = READ_ONCE(tp->write_seq) -
+			       READ_ONCE(tp->snd_nxt);
 		break;
 	default:
 		return -ENOIOCTLCMD;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 339944690329..c802bc80c400 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -482,8 +482,10 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	WRITE_ONCE(newtp->rcv_nxt, seq);
 	newtp->segs_in = 1;
 
-	newtp->snd_sml = newtp->snd_una =
-	newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
+	seq = treq->snt_isn + 1;
+	newtp->snd_sml = newtp->snd_una = seq;
+	WRITE_ONCE(newtp->snd_nxt, seq);
+	newtp->snd_up = seq;
 
 	INIT_LIST_HEAD(&newtp->tsq_node);
 	INIT_LIST_HEAD(&newtp->tsorted_sent_queue);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c17c2a78809d..a115a991dfb5 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -67,7 +67,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int prior_packets = tp->packets_out;
 
-	tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
+	WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq);
 
 	__skb_unlink(skb, &sk->sk_write_queue);
 	tcp_rbtree_insert(&sk->tcp_rtx_queue, skb);
@@ -3142,7 +3142,7 @@ void tcp_send_fin(struct sock *sk)
 			 * if FIN had been sent. This is because retransmit path
 			 * does not change tp->snd_nxt.
 			 */
-			tp->snd_nxt++;
+			WRITE_ONCE(tp->snd_nxt, tp->snd_nxt + 1);
 			return;
 		}
 	} else {
@@ -3426,7 +3426,7 @@ static void tcp_connect_init(struct sock *sk)
 	tp->snd_una = tp->write_seq;
 	tp->snd_sml = tp->write_seq;
 	tp->snd_up = tp->write_seq;
-	tp->snd_nxt = tp->write_seq;
+	WRITE_ONCE(tp->snd_nxt, tp->write_seq);
 
 	if (likely(!tp->repair))
 		tp->rcv_nxt = 0;
@@ -3586,11 +3586,11 @@ int tcp_connect(struct sock *sk)
 	/* We change tp->snd_nxt after the tcp_transmit_skb() call
 	 * in order to make this packet get counted in tcpOutSegs.
 	 */
-	tp->snd_nxt = tp->write_seq;
+	WRITE_ONCE(tp->snd_nxt, tp->write_seq);
 	tp->pushed_seq = tp->write_seq;
 	buff = tcp_send_head(sk);
 	if (unlikely(buff)) {
-		tp->snd_nxt	= TCP_SKB_CB(buff)->seq;
+		WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(buff)->seq);
 		tp->pushed_seq	= TCP_SKB_CB(buff)->seq;
 	}
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);
-- 
cgit v1.2.3


From d9b55bf7b6788ec0bd1db1acefbc4feb1399144a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:43 -0700
Subject: tcp: annotate tp->urg_seq lockless reads

There two places where we fetch tp->urg_seq while
this field can change from IRQ or other cpu.

We need to add READ_ONCE() annotations, and also make
sure write side use corresponding WRITE_ONCE() to avoid
store-tearing.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c       | 5 +++--
 net/ipv4/tcp_input.c | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 652568750cb1..577a8c6eef9f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -546,7 +546,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	    (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) {
 		int target = sock_rcvlowat(sk, 0, INT_MAX);
 
-		if (tp->urg_seq == READ_ONCE(tp->copied_seq) &&
+		if (READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) &&
 		    !sock_flag(sk, SOCK_URGINLINE) &&
 		    tp->urg_data)
 			target++;
@@ -607,7 +607,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		unlock_sock_fast(sk, slow);
 		break;
 	case SIOCATMARK:
-		answ = tp->urg_data && tp->urg_seq == READ_ONCE(tp->copied_seq);
+		answ = tp->urg_data &&
+		       READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq);
 		break;
 	case SIOCOUTQ:
 		if (sk->sk_state == TCP_LISTEN)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a30aae3a6a18..16342e043ab3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5356,7 +5356,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th)
 	}
 
 	tp->urg_data = TCP_URG_NOTYET;
-	tp->urg_seq = ptr;
+	WRITE_ONCE(tp->urg_seq, ptr);
 
 	/* Disable header prediction. */
 	tp->pred_flags = 0;
-- 
cgit v1.2.3


From ebb3b78db7bf842270a46fd4fe7cc45c78fa5ed6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:44 -0700
Subject: tcp: annotate sk->sk_rcvbuf lockless reads

For the sake of tcp_poll(), there are few places where we fetch
sk->sk_rcvbuf while this field can change from IRQ or other cpu.

We need to add READ_ONCE() annotations, and also make sure write
sides use corresponding WRITE_ONCE() to avoid store-tearing.

Note that other transports probably need similar fixes.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h           | 4 ++--
 include/trace/events/sock.h | 2 +-
 net/core/filter.c           | 3 ++-
 net/core/skbuff.c           | 2 +-
 net/core/sock.c             | 5 +++--
 net/ipv4/tcp.c              | 4 ++--
 net/ipv4/tcp_input.c        | 7 ++++---
 7 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index e1d08f69fd39..ab4eb5eb5d07 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1380,14 +1380,14 @@ static inline int tcp_win_from_space(const struct sock *sk, int space)
 /* Note: caller must be prepared to deal with negative returns */
 static inline int tcp_space(const struct sock *sk)
 {
-	return tcp_win_from_space(sk, sk->sk_rcvbuf -
+	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) -
 				  READ_ONCE(sk->sk_backlog.len) -
 				  atomic_read(&sk->sk_rmem_alloc));
 }
 
 static inline int tcp_full_space(const struct sock *sk)
 {
-	return tcp_win_from_space(sk, sk->sk_rcvbuf);
+	return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf));
 }
 
 extern void tcp_openreq_init_rwin(struct request_sock *req,
diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
index a0c4b8a30966..f720c32e7dfd 100644
--- a/include/trace/events/sock.h
+++ b/include/trace/events/sock.h
@@ -82,7 +82,7 @@ TRACE_EVENT(sock_rcvqueue_full,
 	TP_fast_assign(
 		__entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc);
 		__entry->truesize   = skb->truesize;
-		__entry->sk_rcvbuf  = sk->sk_rcvbuf;
+		__entry->sk_rcvbuf  = READ_ONCE(sk->sk_rcvbuf);
 	),
 
 	TP_printk("rmem_alloc=%d truesize=%u sk_rcvbuf=%d",
diff --git a/net/core/filter.c b/net/core/filter.c
index a50c0b6846f2..7deceaeeed7b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4252,7 +4252,8 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 		case SO_RCVBUF:
 			val = min_t(u32, val, sysctl_rmem_max);
 			sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
-			sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
+			WRITE_ONCE(sk->sk_rcvbuf,
+				   max_t(int, val * 2, SOCK_MIN_RCVBUF));
 			break;
 		case SO_SNDBUF:
 			val = min_t(u32, val, sysctl_wmem_max);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 529133611ea2..8c178703467b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4415,7 +4415,7 @@ static void skb_set_err_queue(struct sk_buff *skb)
 int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 {
 	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
-	    (unsigned int)sk->sk_rcvbuf)
+	    (unsigned int)READ_ONCE(sk->sk_rcvbuf))
 		return -ENOMEM;
 
 	skb_orphan(skb);
diff --git a/net/core/sock.c b/net/core/sock.c
index 2a053999df11..8c8f61e70141 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -831,7 +831,8 @@ set_rcvbuf:
 		 * returning the value we actually used in getsockopt
 		 * is the most desirable behavior.
 		 */
-		sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF);
+		WRITE_ONCE(sk->sk_rcvbuf,
+			   max_t(int, val * 2, SOCK_MIN_RCVBUF));
 		break;
 
 	case SO_RCVBUFFORCE:
@@ -3204,7 +3205,7 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem)
 	memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS);
 
 	mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
-	mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
+	mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf);
 	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
 	mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
 	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 577a8c6eef9f..bc0481aa6633 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -451,7 +451,7 @@ void tcp_init_sock(struct sock *sk)
 	icsk->icsk_sync_mss = tcp_sync_mss;
 
 	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
-	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
+	WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
 
 	sk_sockets_allocated_inc(sk);
 	sk->sk_route_forced_caps = NETIF_F_GSO;
@@ -1711,7 +1711,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 
 	val <<= 1;
 	if (val > sk->sk_rcvbuf) {
-		sk->sk_rcvbuf = val;
+		WRITE_ONCE(sk->sk_rcvbuf, val);
 		tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val);
 	}
 	return 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 16342e043ab3..6995df20710a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -483,8 +483,9 @@ static void tcp_clamp_window(struct sock *sk)
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
 	    !tcp_under_memory_pressure(sk) &&
 	    sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
-		sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
-				    net->ipv4.sysctl_tcp_rmem[2]);
+		WRITE_ONCE(sk->sk_rcvbuf,
+			   min(atomic_read(&sk->sk_rmem_alloc),
+			       net->ipv4.sysctl_tcp_rmem[2]));
 	}
 	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
 		tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -648,7 +649,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
 		rcvbuf = min_t(u64, rcvwin * rcvmem,
 			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
 		if (rcvbuf > sk->sk_rcvbuf) {
-			sk->sk_rcvbuf = rcvbuf;
+			WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
 
 			/* Make the window clamp follow along.  */
 			tp->window_clamp = tcp_win_from_space(sk, rcvbuf);
-- 
cgit v1.2.3


From e292f05e0df73f9fcc93329663936e1ded97a988 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:45 -0700
Subject: tcp: annotate sk->sk_sndbuf lockless reads

For the sake of tcp_poll(), there are few places where we fetch
sk->sk_sndbuf while this field can change from IRQ or other cpu.

We need to add READ_ONCE() annotations, and also make sure write
sides use corresponding WRITE_ONCE() to avoid store-tearing.

Note that other transports probably need similar fixes.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h   | 18 +++++++++++-------
 net/core/filter.c    |  3 ++-
 net/core/sock.c      | 15 +++++++++------
 net/ipv4/tcp.c       |  2 +-
 net/ipv4/tcp_input.c |  3 ++-
 5 files changed, 25 insertions(+), 16 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 79f54e1f8827..3d1e7502333e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -883,7 +883,7 @@ static inline int sk_stream_min_wspace(const struct sock *sk)
 
 static inline int sk_stream_wspace(const struct sock *sk)
 {
-	return sk->sk_sndbuf - sk->sk_wmem_queued;
+	return READ_ONCE(sk->sk_sndbuf) - sk->sk_wmem_queued;
 }
 
 void sk_stream_write_space(struct sock *sk);
@@ -1207,7 +1207,7 @@ static inline void sk_refcnt_debug_release(const struct sock *sk)
 
 static inline bool __sk_stream_memory_free(const struct sock *sk, int wake)
 {
-	if (sk->sk_wmem_queued >= sk->sk_sndbuf)
+	if (sk->sk_wmem_queued >= READ_ONCE(sk->sk_sndbuf))
 		return false;
 
 	return sk->sk_prot->stream_memory_free ?
@@ -2220,10 +2220,14 @@ static inline void sk_wake_async(const struct sock *sk, int how, int band)
 
 static inline void sk_stream_moderate_sndbuf(struct sock *sk)
 {
-	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) {
-		sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1);
-		sk->sk_sndbuf = max_t(u32, sk->sk_sndbuf, SOCK_MIN_SNDBUF);
-	}
+	u32 val;
+
+	if (sk->sk_userlocks & SOCK_SNDBUF_LOCK)
+		return;
+
+	val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1);
+
+	WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF));
 }
 
 struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
@@ -2251,7 +2255,7 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag);
  */
 static inline bool sock_writeable(const struct sock *sk)
 {
-	return refcount_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1);
+	return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1);
 }
 
 static inline gfp_t gfp_any(void)
diff --git a/net/core/filter.c b/net/core/filter.c
index 7deceaeeed7b..3fed5755494b 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4258,7 +4258,8 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 		case SO_SNDBUF:
 			val = min_t(u32, val, sysctl_wmem_max);
 			sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
-			sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
+			WRITE_ONCE(sk->sk_sndbuf,
+				   max_t(int, val * 2, SOCK_MIN_SNDBUF));
 			break;
 		case SO_MAX_PACING_RATE: /* 32bit version */
 			if (val != ~0U)
diff --git a/net/core/sock.c b/net/core/sock.c
index 8c8f61e70141..cd075bc86407 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -785,7 +785,8 @@ set_sndbuf:
 		 */
 		val = min_t(int, val, INT_MAX / 2);
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
-		sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
+		WRITE_ONCE(sk->sk_sndbuf,
+			   max_t(int, val * 2, SOCK_MIN_SNDBUF));
 		/* Wake up sending tasks if we upped the value. */
 		sk->sk_write_space(sk);
 		break;
@@ -2089,8 +2090,10 @@ EXPORT_SYMBOL(sock_i_ino);
 struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
 			     gfp_t priority)
 {
-	if (force || refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
+	if (force ||
+	    refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) {
 		struct sk_buff *skb = alloc_skb(size, priority);
+
 		if (skb) {
 			skb_set_owner_w(skb, sk);
 			return skb;
@@ -2191,7 +2194,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
 			break;
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-		if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf)
+		if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf))
 			break;
 		if (sk->sk_shutdown & SEND_SHUTDOWN)
 			break;
@@ -2226,7 +2229,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 		if (sk->sk_shutdown & SEND_SHUTDOWN)
 			goto failure;
 
-		if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf)
+		if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf))
 			break;
 
 		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -2807,7 +2810,7 @@ static void sock_def_write_space(struct sock *sk)
 	/* Do not wake up a writer until he can make "significant"
 	 * progress.  --DaveM
 	 */
-	if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
+	if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) {
 		wq = rcu_dereference(sk->sk_wq);
 		if (skwq_has_sleeper(wq))
 			wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT |
@@ -3207,7 +3210,7 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem)
 	mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
 	mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf);
 	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
-	mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
+	mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf);
 	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
 	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
 	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bc0481aa6633..111853262972 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -450,7 +450,7 @@ void tcp_init_sock(struct sock *sk)
 
 	icsk->icsk_sync_mss = tcp_sync_mss;
 
-	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
+	WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
 	WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
 
 	sk_sockets_allocated_inc(sk);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6995df20710a..a2e52ad7cdab 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -359,7 +359,8 @@ static void tcp_sndbuf_expand(struct sock *sk)
 	sndmem *= nr_segs * per_mss;
 
 	if (sk->sk_sndbuf < sndmem)
-		sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]);
+		WRITE_ONCE(sk->sk_sndbuf,
+			   min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]));
 }
 
 /* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
-- 
cgit v1.2.3


From ab4e846a82d0ae00176de19f2db3c5c64f8eb5f2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 10 Oct 2019 20:17:46 -0700
Subject: tcp: annotate sk->sk_wmem_queued lockless reads

For the sake of tcp_poll(), there are few places where we fetch
sk->sk_wmem_queued while this field can change from IRQ or other cpu.

We need to add READ_ONCE() annotations, and also make sure write
sides use corresponding WRITE_ONCE() to avoid store-tearing.

sk_wmem_queued_add() helper is added so that we can in
the future convert to ADD_ONCE() or equivalent if/when
available.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h          | 15 ++++++++++-----
 include/trace/events/sock.h |  2 +-
 net/core/datagram.c         |  2 +-
 net/core/sock.c             |  2 +-
 net/ipv4/inet_diag.c        |  2 +-
 net/ipv4/tcp.c              |  4 ++--
 net/ipv4/tcp_output.c       | 14 +++++++-------
 net/sched/em_meta.c         |  2 +-
 8 files changed, 24 insertions(+), 19 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 3d1e7502333e..f69b58bff7e5 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -878,12 +878,17 @@ static inline bool sk_acceptq_is_full(const struct sock *sk)
  */
 static inline int sk_stream_min_wspace(const struct sock *sk)
 {
-	return sk->sk_wmem_queued >> 1;
+	return READ_ONCE(sk->sk_wmem_queued) >> 1;
 }
 
 static inline int sk_stream_wspace(const struct sock *sk)
 {
-	return READ_ONCE(sk->sk_sndbuf) - sk->sk_wmem_queued;
+	return READ_ONCE(sk->sk_sndbuf) - READ_ONCE(sk->sk_wmem_queued);
+}
+
+static inline void sk_wmem_queued_add(struct sock *sk, int val)
+{
+	WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val);
 }
 
 void sk_stream_write_space(struct sock *sk);
@@ -1207,7 +1212,7 @@ static inline void sk_refcnt_debug_release(const struct sock *sk)
 
 static inline bool __sk_stream_memory_free(const struct sock *sk, int wake)
 {
-	if (sk->sk_wmem_queued >= READ_ONCE(sk->sk_sndbuf))
+	if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf))
 		return false;
 
 	return sk->sk_prot->stream_memory_free ?
@@ -1467,7 +1472,7 @@ DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key);
 static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
 {
 	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
-	sk->sk_wmem_queued -= skb->truesize;
+	sk_wmem_queued_add(sk, -skb->truesize);
 	sk_mem_uncharge(sk, skb->truesize);
 	if (static_branch_unlikely(&tcp_tx_skb_cache_key) &&
 	    !sk->sk_tx_skb_cache && !skb_cloned(skb)) {
@@ -2014,7 +2019,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro
 	skb->len	     += copy;
 	skb->data_len	     += copy;
 	skb->truesize	     += copy;
-	sk->sk_wmem_queued   += copy;
+	sk_wmem_queued_add(sk, copy);
 	sk_mem_charge(sk, copy);
 	return 0;
 }
diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
index f720c32e7dfd..51fe9f6719eb 100644
--- a/include/trace/events/sock.h
+++ b/include/trace/events/sock.h
@@ -115,7 +115,7 @@ TRACE_EVENT(sock_exceed_buf_limit,
 		__entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc);
 		__entry->sysctl_wmem = sk_get_wmem0(sk, prot);
 		__entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc);
-		__entry->wmem_queued = sk->sk_wmem_queued;
+		__entry->wmem_queued = READ_ONCE(sk->sk_wmem_queued);
 		__entry->kind = kind;
 	),
 
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 4cc8dc5db2b7..c210fc116103 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -640,7 +640,7 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
 		skb->len += copied;
 		skb->truesize += truesize;
 		if (sk && sk->sk_type == SOCK_STREAM) {
-			sk->sk_wmem_queued += truesize;
+			sk_wmem_queued_add(sk, truesize);
 			sk_mem_charge(sk, truesize);
 		} else {
 			refcount_add(truesize, &skb->sk->sk_wmem_alloc);
diff --git a/net/core/sock.c b/net/core/sock.c
index cd075bc86407..a515392ba84b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3212,7 +3212,7 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem)
 	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
 	mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf);
 	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
-	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
+	mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued);
 	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
 	mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
 	mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index bbb005eb5218..7dc79b973e6e 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -193,7 +193,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 	if (ext & (1 << (INET_DIAG_MEMINFO - 1))) {
 		struct inet_diag_meminfo minfo = {
 			.idiag_rmem = sk_rmem_alloc_get(sk),
-			.idiag_wmem = sk->sk_wmem_queued,
+			.idiag_wmem = READ_ONCE(sk->sk_wmem_queued),
 			.idiag_fmem = sk->sk_forward_alloc,
 			.idiag_tmem = sk_wmem_alloc_get(sk),
 		};
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 111853262972..b2ac4f074e2d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -659,7 +659,7 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb)
 	tcb->sacked  = 0;
 	__skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
-	sk->sk_wmem_queued += skb->truesize;
+	sk_wmem_queued_add(sk, skb->truesize);
 	sk_mem_charge(sk, skb->truesize);
 	if (tp->nonagle & TCP_NAGLE_PUSH)
 		tp->nonagle &= ~TCP_NAGLE_PUSH;
@@ -1034,7 +1034,7 @@ new_segment:
 		skb->len += copy;
 		skb->data_len += copy;
 		skb->truesize += copy;
-		sk->sk_wmem_queued += copy;
+		sk_wmem_queued_add(sk, copy);
 		sk_mem_charge(sk, copy);
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a115a991dfb5..0488607c5cd3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1199,7 +1199,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 	WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq);
 	__skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
-	sk->sk_wmem_queued += skb->truesize;
+	sk_wmem_queued_add(sk, skb->truesize);
 	sk_mem_charge(sk, skb->truesize);
 }
 
@@ -1333,7 +1333,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 		return -ENOMEM; /* We'll just try again later. */
 	skb_copy_decrypted(buff, skb);
 
-	sk->sk_wmem_queued += buff->truesize;
+	sk_wmem_queued_add(sk, buff->truesize);
 	sk_mem_charge(sk, buff->truesize);
 	nlen = skb->len - len - nsize;
 	buff->truesize += nlen;
@@ -1443,7 +1443,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 
 	if (delta_truesize) {
 		skb->truesize	   -= delta_truesize;
-		sk->sk_wmem_queued -= delta_truesize;
+		sk_wmem_queued_add(sk, -delta_truesize);
 		sk_mem_uncharge(sk, delta_truesize);
 		sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
 	}
@@ -1888,7 +1888,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 		return -ENOMEM;
 	skb_copy_decrypted(buff, skb);
 
-	sk->sk_wmem_queued += buff->truesize;
+	sk_wmem_queued_add(sk, buff->truesize);
 	sk_mem_charge(sk, buff->truesize);
 	buff->truesize += nlen;
 	skb->truesize -= nlen;
@@ -2152,7 +2152,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
 	if (!nskb)
 		return -1;
-	sk->sk_wmem_queued += nskb->truesize;
+	sk_wmem_queued_add(sk, nskb->truesize);
 	sk_mem_charge(sk, nskb->truesize);
 
 	skb = tcp_send_head(sk);
@@ -3222,7 +3222,7 @@ int tcp_send_synack(struct sock *sk)
 			tcp_rtx_queue_unlink_and_free(skb, sk);
 			__skb_header_release(nskb);
 			tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb);
-			sk->sk_wmem_queued += nskb->truesize;
+			sk_wmem_queued_add(sk, nskb->truesize);
 			sk_mem_charge(sk, nskb->truesize);
 			skb = nskb;
 		}
@@ -3447,7 +3447,7 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
 
 	tcb->end_seq += skb->len;
 	__skb_header_release(skb);
-	sk->sk_wmem_queued += skb->truesize;
+	sk_wmem_queued_add(sk, skb->truesize);
 	sk_mem_charge(sk, skb->truesize);
 	WRITE_ONCE(tp->write_seq, tcb->end_seq);
 	tp->packets_out += tcp_skb_pcount(skb);
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 4c9122fc35c9..3177dcb17316 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -446,7 +446,7 @@ META_COLLECTOR(int_sk_wmem_queued)
 		*err = -1;
 		return;
 	}
-	dst->value = sk->sk_wmem_queued;
+	dst->value = READ_ONCE(sk->sk_wmem_queued);
 }
 
 META_COLLECTOR(int_sk_fwd_alloc)
-- 
cgit v1.2.3


From c23936fad79ea2bea749db19b8921bb4dc524905 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Thu, 10 Oct 2019 22:46:06 +0200
Subject: net: lpc_eth: avoid resetting twice

__lpc_eth_shutdown is called after __lpc_eth_reset but it is already
calling __lpc_eth_reset. Avoid resetting the IP twice.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/nxp/lpc_eth.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index 141571e2ec11..544012a67221 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1356,9 +1356,6 @@ static int lpc_eth_drv_probe(struct platform_device *pdev)
 	if (!is_valid_ether_addr(ndev->dev_addr))
 		eth_hw_addr_random(ndev);
 
-	/* Reset the ethernet controller */
-	__lpc_eth_reset(pldat);
-
 	/* then shut everything down to save power */
 	__lpc_eth_shutdown(pldat);
 
-- 
cgit v1.2.3


From 11d49ce9f7946dfed4dcf5dbde865c78058b50ab Mon Sep 17 00:00:00 2001
From: Cédric Le Goater <clg@kaod.org>
Date: Fri, 11 Oct 2019 07:52:54 +0200
Subject: net/ibmvnic: Fix EOI when running in XIVE mode.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pSeries machines on POWER9 processors can run with the XICS (legacy)
interrupt mode or with the XIVE exploitation interrupt mode. These
interrupt contollers have different interfaces for interrupt
management : XICS uses hcalls and XIVE loads and stores on a page.
H_EOI being a XICS interface the enable_scrq_irq() routine can fail
when the machine runs in XIVE mode.

Fix that by calling the EOI handler of the interrupt chip.

Fixes: f23e0643cd0b ("ibmvnic: Clear pending interrupt after device reset")
Signed-off-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 2b073a3c0b84..f59d9a8e35e2 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2878,12 +2878,10 @@ static int enable_scrq_irq(struct ibmvnic_adapter *adapter,
 
 	if (test_bit(0, &adapter->resetting) &&
 	    adapter->reset_reason == VNIC_RESET_MOBILITY) {
-		u64 val = (0xff000000) | scrq->hw_irq;
+		struct irq_desc *desc = irq_to_desc(scrq->irq);
+		struct irq_chip *chip = irq_desc_get_chip(desc);
 
-		rc = plpar_hcall_norets(H_EOI, val);
-		if (rc)
-			dev_err(dev, "H_EOI FAILED irq 0x%llx. rc=%ld\n",
-				val, rc);
+		chip->irq_eoi(&desc->irq_data);
 	}
 
 	rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address,
-- 
cgit v1.2.3


From 33902b4a4227877896dd9368ac10f4ca0d100de5 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 11 Oct 2019 17:46:53 +0800
Subject: netdevsim: Fix error handling in nsim_fib_init and nsim_fib_exit

In nsim_fib_init(), if register_fib_notifier failed, nsim_fib_net_ops
should be unregistered before return.

In nsim_fib_exit(), unregister_fib_notifier should be called before
nsim_fib_net_ops be unregistered, otherwise may cause use-after-free:

BUG: KASAN: use-after-free in nsim_fib_event_nb+0x342/0x570 [netdevsim]
Read of size 8 at addr ffff8881daaf4388 by task kworker/0:3/3499

CPU: 0 PID: 3499 Comm: kworker/0:3 Not tainted 5.3.0-rc7+ #30
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
Workqueue: ipv6_addrconf addrconf_dad_work [ipv6]
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0xa9/0x10e lib/dump_stack.c:113
 print_address_description+0x65/0x380 mm/kasan/report.c:351
 __kasan_report+0x149/0x18d mm/kasan/report.c:482
 kasan_report+0xe/0x20 mm/kasan/common.c:618
 nsim_fib_event_nb+0x342/0x570 [netdevsim]
 notifier_call_chain+0x52/0xf0 kernel/notifier.c:95
 __atomic_notifier_call_chain+0x78/0x140 kernel/notifier.c:185
 call_fib_notifiers+0x30/0x60 net/core/fib_notifier.c:30
 call_fib6_entry_notifiers+0xc1/0x100 [ipv6]
 fib6_add+0x92e/0x1b10 [ipv6]
 __ip6_ins_rt+0x40/0x60 [ipv6]
 ip6_ins_rt+0x84/0xb0 [ipv6]
 __ipv6_ifa_notify+0x4b6/0x550 [ipv6]
 ipv6_ifa_notify+0xa5/0x180 [ipv6]
 addrconf_dad_completed+0xca/0x640 [ipv6]
 addrconf_dad_work+0x296/0x960 [ipv6]
 process_one_work+0x5c0/0xc00 kernel/workqueue.c:2269
 worker_thread+0x5c/0x670 kernel/workqueue.c:2415
 kthread+0x1d7/0x200 kernel/kthread.c:255
 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:352

Allocated by task 3388:
 save_stack+0x19/0x80 mm/kasan/common.c:69
 set_track mm/kasan/common.c:77 [inline]
 __kasan_kmalloc.constprop.3+0xa0/0xd0 mm/kasan/common.c:493
 kmalloc include/linux/slab.h:557 [inline]
 kzalloc include/linux/slab.h:748 [inline]
 ops_init+0xa9/0x220 net/core/net_namespace.c:127
 __register_pernet_operations net/core/net_namespace.c:1135 [inline]
 register_pernet_operations+0x1d4/0x420 net/core/net_namespace.c:1212
 register_pernet_subsys+0x24/0x40 net/core/net_namespace.c:1253
 nsim_fib_init+0x12/0x70 [netdevsim]
 veth_get_link_ksettings+0x2b/0x50 [veth]
 do_one_initcall+0xd4/0x454 init/main.c:939
 do_init_module+0xe0/0x330 kernel/module.c:3490
 load_module+0x3c2f/0x4620 kernel/module.c:3841
 __do_sys_finit_module+0x163/0x190 kernel/module.c:3931
 do_syscall_64+0x72/0x2e0 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Freed by task 3534:
 save_stack+0x19/0x80 mm/kasan/common.c:69
 set_track mm/kasan/common.c:77 [inline]
 __kasan_slab_free+0x130/0x180 mm/kasan/common.c:455
 slab_free_hook mm/slub.c:1423 [inline]
 slab_free_freelist_hook mm/slub.c:1474 [inline]
 slab_free mm/slub.c:3016 [inline]
 kfree+0xe9/0x2d0 mm/slub.c:3957
 ops_free net/core/net_namespace.c:151 [inline]
 ops_free_list.part.7+0x156/0x220 net/core/net_namespace.c:184
 ops_free_list net/core/net_namespace.c:182 [inline]
 __unregister_pernet_operations net/core/net_namespace.c:1165 [inline]
 unregister_pernet_operations+0x221/0x2a0 net/core/net_namespace.c:1224
 unregister_pernet_subsys+0x1d/0x30 net/core/net_namespace.c:1271
 nsim_fib_exit+0x11/0x20 [netdevsim]
 nsim_module_exit+0x16/0x21 [netdevsim]
 __do_sys_delete_module kernel/module.c:1015 [inline]
 __se_sys_delete_module kernel/module.c:958 [inline]
 __x64_sys_delete_module+0x244/0x330 kernel/module.c:958
 do_syscall_64+0x72/0x2e0 arch/x86/entry/common.c:296
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: 59c84b9fcf42 ("netdevsim: Restore per-network namespace accounting for fib entries")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/fib.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c
index f61d094746c0..1a251f76d09b 100644
--- a/drivers/net/netdevsim/fib.c
+++ b/drivers/net/netdevsim/fib.c
@@ -241,8 +241,8 @@ static struct pernet_operations nsim_fib_net_ops = {
 
 void nsim_fib_exit(void)
 {
-	unregister_pernet_subsys(&nsim_fib_net_ops);
 	unregister_fib_notifier(&nsim_fib_nb);
+	unregister_pernet_subsys(&nsim_fib_net_ops);
 }
 
 int nsim_fib_init(void)
@@ -258,6 +258,7 @@ int nsim_fib_init(void)
 	err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent);
 	if (err < 0) {
 		pr_err("Failed to register fib notifier\n");
+		unregister_pernet_subsys(&nsim_fib_net_ops);
 		goto err_out;
 	}
 
-- 
cgit v1.2.3


From 4f5cafb5cb8471e54afdc9054d973535614f7675 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 13 Oct 2019 16:37:36 -0700
Subject: Linux 5.4-rc3

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index f87a5d6ab78b..ffd7a912fc46 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Nesting Opossum
 
 # *DOCUMENTATION*
-- 
cgit v1.2.3


From 280bc0cecb77240bf6be7f86a9da90e3451829b9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sun, 13 Oct 2019 12:45:09 +0100
Subject: drm/i915/selftests: Fixup naked 64b divide

drivers/gpu/drm/i915/intel_memory_region.o: in function `igt_mock_contiguous':
drivers/gpu/drm/i915/selftests/intel_memory_region.c:166: undefined reference to `__umoddi3'

v2: promote target to u64 for consistency across all builds

Reported-by: kbuild test robot <lkp@intel.com>
Fixes: 2f0b97ca0211 ("drm/i915/region: support contiguous allocations")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191013114509.3405-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/intel_memory_region.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 4e44c81e8e5b..56091e7e599e 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -128,9 +128,9 @@ static int igt_mock_contiguous(void *arg)
 	LIST_HEAD(objects);
 	LIST_HEAD(holes);
 	I915_RND_STATE(prng);
-	resource_size_t target;
 	resource_size_t total;
 	resource_size_t min;
+	u64 target;
 	int err = 0;
 
 	total = resource_size(&mem->region);
@@ -163,7 +163,9 @@ static int igt_mock_contiguous(void *arg)
 	igt_object_release(obj);
 
 	/* Internal fragmentation should not bleed into the object size */
-	target = round_up(prandom_u32_state(&prng) % total, PAGE_SIZE);
+	target = i915_prandom_u64_state(&prng);
+	div64_u64_rem(target, total, &target);
+	target = round_up(target, PAGE_SIZE);
 	target = max_t(u64, PAGE_SIZE, target);
 
 	obj = igt_object_create(mem, &objects, target,
@@ -172,8 +174,8 @@ static int igt_mock_contiguous(void *arg)
 		return PTR_ERR(obj);
 
 	if (obj->base.size != target) {
-		pr_err("%s obj->base.size(%llx) != target(%llx)\n", __func__,
-		       (u64)obj->base.size, (u64)target);
+		pr_err("%s obj->base.size(%zx) != target(%llx)\n", __func__,
+		       obj->base.size, target);
 		err = -EINVAL;
 		goto err_close_objects;
 	}
@@ -236,7 +238,7 @@ static int igt_mock_contiguous(void *arg)
 					I915_BO_ALLOC_CONTIGUOUS);
 		if (should_fail != IS_ERR(obj)) {
 			pr_err("%s target allocation(%llx) mismatch\n",
-			       __func__, (u64)target);
+			       __func__, target);
 			err = -EINVAL;
 			goto err_close_objects;
 		}
-- 
cgit v1.2.3


From d79749f7716d9dc32fa2d5075f6ec29aac63c76d Mon Sep 17 00:00:00 2001
From: Miaoqing Pan <miaoqing@codeaurora.org>
Date: Thu, 29 Aug 2019 10:45:12 +0800
Subject: ath10k: fix latency issue for QCA988x

(kvalo: cherry picked from commit 1340cc631bd00431e2f174525c971f119df9efa1 in
wireless-drivers-next to wireless-drivers as this a frequently reported
regression)

Bad latency is found on QCA988x, the issue was introduced by
commit 4504f0e5b571 ("ath10k: sdio: workaround firmware UART
pin configuration bug"). If uart_pin_workaround is false, this
change will set uart pin even if uart_print is false.

Tested HW: QCA9880
Tested FW: 10.2.4-1.0-00037

Fixes: 4504f0e5b571 ("ath10k: sdio: workaround firmware UART pin configuration bug")
Signed-off-by: Miaoqing Pan <miaoqing@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/core.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index dc45d16e8d21..383d4fa555a8 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -2118,12 +2118,15 @@ static int ath10k_init_uart(struct ath10k *ar)
 		return ret;
 	}
 
-	if (!uart_print && ar->hw_params.uart_pin_workaround) {
-		ret = ath10k_bmi_write32(ar, hi_dbg_uart_txpin,
-					 ar->hw_params.uart_pin);
-		if (ret) {
-			ath10k_warn(ar, "failed to set UART TX pin: %d", ret);
-			return ret;
+	if (!uart_print) {
+		if (ar->hw_params.uart_pin_workaround) {
+			ret = ath10k_bmi_write32(ar, hi_dbg_uart_txpin,
+						 ar->hw_params.uart_pin);
+			if (ret) {
+				ath10k_warn(ar, "failed to set UART TX pin: %d",
+					    ret);
+				return ret;
+			}
 		}
 
 		return 0;
-- 
cgit v1.2.3


From 1fd37669bc873cee180f1505a20b16e557b7b472 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 12 Oct 2019 09:02:08 +0100
Subject: drm/i915/display: Squelch kerneldoc warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Just a parameter rename,

drivers/gpu/drm/i915/display/intel_display.c:14425: warning: Function parameter or member '_new_plane_state' not described in 'intel_prepare_plane_fb'
drivers/gpu/drm/i915/display/intel_display.c:14425: warning: Excess function parameter 'new_state' description in 'intel_prepare_plane_fb'
drivers/gpu/drm/i915/display/intel_display.c:14534: warning: Function parameter or member '_old_plane_state' not described in 'intel_cleanup_plane_fb'
drivers/gpu/drm/i915/display/intel_display.c:14534: warning: Excess function parameter 'old_state' description in 'intel_cleanup_plane_fb'

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191012080208.18774-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/display/intel_display.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index a146ec02a0c1..3cf39fc153b3 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -14410,7 +14410,7 @@ static void fb_obj_bump_render_priority(struct drm_i915_gem_object *obj)
 /**
  * intel_prepare_plane_fb - Prepare fb for usage on plane
  * @plane: drm plane to prepare for
- * @new_state: the plane state being prepared
+ * @_new_plane_state: the plane state being prepared
  *
  * Prepares a framebuffer for usage on a display plane.  Generally this
  * involves pinning the underlying object and updating the frontbuffer tracking
@@ -14524,7 +14524,7 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 /**
  * intel_cleanup_plane_fb - Cleans up an fb after plane use
  * @plane: drm plane to clean up for
- * @old_state: the state from the previous modeset
+ * @_old_plane_state: the state from the previous modeset
  *
  * Cleans up a framebuffer that has just been removed from a plane.
  */
-- 
cgit v1.2.3


From 9c27462c896d4852ece6086338e52777a3cb110e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 14 Oct 2019 10:07:48 +0100
Subject: drm/i915/selftests: Check known register values within the context

Check the logical ring context by asserting that the registers hold
expected start during execution. (It's a bit chicken-and-egg for how
could we manage to execute our request if the registers were not being
updated. Still, it's nice to verify that the HW is working as expected.)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191014090757.32111-6-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/selftest_lrc.c | 126 +++++++++++++++++++++++++++++++++
 1 file changed, 126 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index a691e429ca01..0aa36b1b2389 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -2599,10 +2599,136 @@ static int live_lrc_layout(void *arg)
 	return err;
 }
 
+static int __live_lrc_state(struct i915_gem_context *fixme,
+			    struct intel_engine_cs *engine,
+			    struct i915_vma *scratch)
+{
+	struct intel_context *ce;
+	struct i915_request *rq;
+	enum {
+		RING_START_IDX = 0,
+		RING_TAIL_IDX,
+		MAX_IDX
+	};
+	u32 expected[MAX_IDX];
+	u32 *cs;
+	int err;
+	int n;
+
+	ce = intel_context_create(fixme, engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	err = intel_context_pin(ce);
+	if (err)
+		goto err_put;
+
+	rq = i915_request_create(ce);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto err_unpin;
+	}
+
+	cs = intel_ring_begin(rq, 4 * MAX_IDX);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		i915_request_add(rq);
+		goto err_unpin;
+	}
+
+	*cs++ = MI_STORE_REGISTER_MEM_GEN8 | MI_USE_GGTT;
+	*cs++ = i915_mmio_reg_offset(RING_START(engine->mmio_base));
+	*cs++ = i915_ggtt_offset(scratch) + RING_START_IDX * sizeof(u32);
+	*cs++ = 0;
+
+	expected[RING_START_IDX] = i915_ggtt_offset(ce->ring->vma);
+
+	*cs++ = MI_STORE_REGISTER_MEM_GEN8 | MI_USE_GGTT;
+	*cs++ = i915_mmio_reg_offset(RING_TAIL(engine->mmio_base));
+	*cs++ = i915_ggtt_offset(scratch) + RING_TAIL_IDX * sizeof(u32);
+	*cs++ = 0;
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+
+	intel_engine_flush_submission(engine);
+	expected[RING_TAIL_IDX] = ce->ring->tail;
+
+	if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+		err = -ETIME;
+		goto err_rq;
+	}
+
+	cs = i915_gem_object_pin_map(scratch->obj, I915_MAP_WB);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		goto err_rq;
+	}
+
+	for (n = 0; n < MAX_IDX; n++) {
+		if (cs[n] != expected[n]) {
+			pr_err("%s: Stored register[%d] value[0x%x] did not match expected[0x%x]\n",
+			       engine->name, n, cs[n], expected[n]);
+			err = -EINVAL;
+			break;
+		}
+	}
+
+	i915_gem_object_unpin_map(scratch->obj);
+
+err_rq:
+	i915_request_put(rq);
+err_unpin:
+	intel_context_unpin(ce);
+err_put:
+	intel_context_put(ce);
+	return err;
+}
+
+static int live_lrc_state(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	struct i915_gem_context *fixme;
+	struct i915_vma *scratch;
+	enum intel_engine_id id;
+	int err = 0;
+
+	/*
+	 * Check the live register state matches what we expect for this
+	 * intel_context.
+	 */
+
+	fixme = kernel_context(gt->i915);
+	if (!fixme)
+		return -ENOMEM;
+
+	scratch = create_scratch(gt);
+	if (IS_ERR(scratch)) {
+		err = PTR_ERR(scratch);
+		goto out_close;
+	}
+
+	for_each_engine(engine, gt->i915, id) {
+		err = __live_lrc_state(fixme, engine, scratch);
+		if (err)
+			break;
+	}
+
+	if (igt_flush_test(gt->i915))
+		err = -EIO;
+
+	i915_vma_unpin_and_release(&scratch, 0);
+out_close:
+	kernel_context_close(fixme);
+	return err;
+}
+
 int intel_lrc_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(live_lrc_layout),
+		SUBTEST(live_lrc_state),
 	};
 
 	if (!HAS_LOGICAL_RING_CONTEXTS(i915))
-- 
cgit v1.2.3


From 9506c23dfaf5980ab1eb33e26968bcf9b2269bb5 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 14 Oct 2019 10:07:49 +0100
Subject: drm/i915/selftests: Check that GPR are cleared for new contexts

We want the general purpose registers to be clear in all new contexts so
that we can be confident that no information is leaked from one to the
next.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191014090757.32111-7-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/selftest_lrc.c | 185 +++++++++++++++++++++++++++++----
 1 file changed, 166 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 0aa36b1b2389..1276da059dc6 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -19,6 +19,9 @@
 #include "gem/selftests/igt_gem_utils.h"
 #include "gem/selftests/mock_context.h"
 
+#define CS_GPR(engine, n) ((engine)->mmio_base + 0x600 + (n) * 4)
+#define NUM_GPR_DW (16 * 2) /* each GPR is 2 dwords */
+
 static struct i915_vma *create_scratch(struct intel_gt *gt)
 {
 	struct drm_i915_gem_object *obj;
@@ -2107,16 +2110,14 @@ static int preserved_virtual_engine(struct drm_i915_private *i915,
 				    struct intel_engine_cs **siblings,
 				    unsigned int nsibling)
 {
-#define CS_GPR(engine, n) ((engine)->mmio_base + 0x600 + (n) * 4)
-
 	struct i915_request *last = NULL;
 	struct i915_gem_context *ctx;
 	struct intel_context *ve;
 	struct i915_vma *scratch;
 	struct igt_live_test t;
-	const int num_gpr = 16 * 2; /* each GPR is 2 dwords */
 	unsigned int n;
 	int err = 0;
+	u32 *cs;
 
 	ctx = kernel_context(i915);
 	if (!ctx)
@@ -2142,10 +2143,9 @@ static int preserved_virtual_engine(struct drm_i915_private *i915,
 	if (err)
 		goto out_unpin;
 
-	for (n = 0; n < num_gpr; n++) {
+	for (n = 0; n < NUM_GPR_DW; n++) {
 		struct intel_engine_cs *engine = siblings[n % nsibling];
 		struct i915_request *rq;
-		u32 *cs;
 
 		rq = i915_request_create(ve);
 		if (IS_ERR(rq)) {
@@ -2169,7 +2169,7 @@ static int preserved_virtual_engine(struct drm_i915_private *i915,
 		*cs++ = 0;
 
 		*cs++ = MI_LOAD_REGISTER_IMM(1);
-		*cs++ = CS_GPR(engine, (n + 1) % num_gpr);
+		*cs++ = CS_GPR(engine, (n + 1) % NUM_GPR_DW);
 		*cs++ = n + 1;
 
 		*cs++ = MI_NOOP;
@@ -2182,21 +2182,26 @@ static int preserved_virtual_engine(struct drm_i915_private *i915,
 
 	if (i915_request_wait(last, 0, HZ / 5) < 0) {
 		err = -ETIME;
-	} else {
-		u32 *map = i915_gem_object_pin_map(scratch->obj, I915_MAP_WB);
+		goto out_end;
+	}
 
-		for (n = 0; n < num_gpr; n++) {
-			if (map[n] != n) {
-				pr_err("Incorrect value[%d] found for GPR[%d]\n",
-				       map[n], n);
-				err = -EINVAL;
-				break;
-			}
-		}
+	cs = i915_gem_object_pin_map(scratch->obj, I915_MAP_WB);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		goto out_end;
+	}
 
-		i915_gem_object_unpin_map(scratch->obj);
+	for (n = 0; n < NUM_GPR_DW; n++) {
+		if (cs[n] != n) {
+			pr_err("Incorrect value[%d] found for GPR[%d]\n",
+			       cs[n], n);
+			err = -EINVAL;
+			break;
+		}
 	}
 
+	i915_gem_object_unpin_map(scratch->obj);
+
 out_end:
 	if (igt_live_test_end(&t))
 		err = -EIO;
@@ -2210,8 +2215,6 @@ out_scratch:
 out_close:
 	kernel_context_close(ctx);
 	return err;
-
-#undef CS_GPR
 }
 
 static int live_virtual_preserved(void *arg)
@@ -2724,11 +2727,155 @@ out_close:
 	return err;
 }
 
+static int gpr_make_dirty(struct intel_engine_cs *engine)
+{
+	struct i915_request *rq;
+	u32 *cs;
+	int n;
+
+	rq = i915_request_create(engine->kernel_context);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	cs = intel_ring_begin(rq, 2 * NUM_GPR_DW + 2);
+	if (IS_ERR(cs)) {
+		i915_request_add(rq);
+		return PTR_ERR(cs);
+	}
+
+	*cs++ = MI_LOAD_REGISTER_IMM(NUM_GPR_DW);
+	for (n = 0; n < NUM_GPR_DW; n++) {
+		*cs++ = CS_GPR(engine, n);
+		*cs++ = STACK_MAGIC;
+	}
+	*cs++ = MI_NOOP;
+
+	intel_ring_advance(rq, cs);
+	i915_request_add(rq);
+
+	return 0;
+}
+
+static int __live_gpr_clear(struct i915_gem_context *fixme,
+			    struct intel_engine_cs *engine,
+			    struct i915_vma *scratch)
+{
+	struct intel_context *ce;
+	struct i915_request *rq;
+	u32 *cs;
+	int err;
+	int n;
+
+	if (INTEL_GEN(engine->i915) < 9 && engine->class != RENDER_CLASS)
+		return 0; /* GPR only on rcs0 for gen8 */
+
+	err = gpr_make_dirty(engine);
+	if (err)
+		return err;
+
+	ce = intel_context_create(fixme, engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	rq = intel_context_create_request(ce);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto err_put;
+	}
+
+	cs = intel_ring_begin(rq, 4 * NUM_GPR_DW);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		i915_request_add(rq);
+		goto err_put;
+	}
+
+	for (n = 0; n < NUM_GPR_DW; n++) {
+		*cs++ = MI_STORE_REGISTER_MEM_GEN8 | MI_USE_GGTT;
+		*cs++ = CS_GPR(engine, n);
+		*cs++ = i915_ggtt_offset(scratch) + n * sizeof(u32);
+		*cs++ = 0;
+	}
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+
+	if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+		err = -ETIME;
+		goto err_rq;
+	}
+
+	cs = i915_gem_object_pin_map(scratch->obj, I915_MAP_WB);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		goto err_rq;
+	}
+
+	for (n = 0; n < NUM_GPR_DW; n++) {
+		if (cs[n]) {
+			pr_err("%s: GPR[%d].%s was not zero, found 0x%08x!\n",
+			       engine->name,
+			       n / 2, n & 1 ? "udw" : "ldw",
+			       cs[n]);
+			err = -EINVAL;
+			break;
+		}
+	}
+
+	i915_gem_object_unpin_map(scratch->obj);
+
+err_rq:
+	i915_request_put(rq);
+err_put:
+	intel_context_put(ce);
+	return err;
+}
+
+static int live_gpr_clear(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	struct i915_gem_context *fixme;
+	struct i915_vma *scratch;
+	enum intel_engine_id id;
+	int err = 0;
+
+	/*
+	 * Check that GPR registers are cleared in new contexts as we need
+	 * to avoid leaking any information from previous contexts.
+	 */
+
+	fixme = kernel_context(gt->i915);
+	if (!fixme)
+		return -ENOMEM;
+
+	scratch = create_scratch(gt);
+	if (IS_ERR(scratch)) {
+		err = PTR_ERR(scratch);
+		goto out_close;
+	}
+
+	for_each_engine(engine, gt->i915, id) {
+		err = __live_gpr_clear(fixme, engine, scratch);
+		if (err)
+			break;
+	}
+
+	if (igt_flush_test(gt->i915))
+		err = -EIO;
+
+	i915_vma_unpin_and_release(&scratch, 0);
+out_close:
+	kernel_context_close(fixme);
+	return err;
+}
+
 int intel_lrc_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(live_lrc_layout),
 		SUBTEST(live_lrc_state),
+		SUBTEST(live_gpr_clear),
 	};
 
 	if (!HAS_LOGICAL_RING_CONTEXTS(i915))
-- 
cgit v1.2.3


From 73a88e4ce31055c415f1ddb55e3f08c9393cf4e3 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 23 Sep 2019 10:47:22 +0200
Subject: drm/ttm: fix busy reference in ttm_mem_evict_first
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The busy BO might actually be already deleted,
so grab only a list reference.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Thomas Hellström <thellstrom@vmware.com>
Link: https://patchwork.freedesktop.org/patch/332877/
---
 drivers/gpu/drm/ttm/ttm_bo.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 20ff56f27aa4..ea59459c4128 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -878,11 +878,11 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 
 	if (!bo) {
 		if (busy_bo)
-			ttm_bo_get(busy_bo);
+			kref_get(&busy_bo->list_kref);
 		spin_unlock(&glob->lru_lock);
 		ret = ttm_mem_evict_wait_busy(busy_bo, ctx, ticket);
 		if (busy_bo)
-			ttm_bo_put(busy_bo);
+			kref_put(&busy_bo->list_kref, ttm_bo_release_list);
 		return ret;
 	}
 
-- 
cgit v1.2.3


From 941f2f72dbbe0cf8c2d6e0b180a8021a0ec477fa Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Thu, 12 Sep 2019 20:38:54 +0200
Subject: drm/ttm: Restore ttm prefaulting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 4daa4fba3a38 ("gpu: drm: ttm: Adding new return type vm_fault_t")
broke TTM prefaulting. Since vmf_insert_mixed() typically always returns
VM_FAULT_NOPAGE, prefaulting stops after the second PTE.

Restore (almost) the original behaviour. Unfortunately we can no longer
with the new vm_fault_t return type determine whether a prefaulting
PTE insertion hit an already populated PTE, and terminate the insertion
loop. Instead we continue with the pre-determined number of prefaults.

Fixes: 4daa4fba3a38 ("gpu: drm: ttm: Adding new return type vm_fault_t")
Cc: Souptick Joarder <jrdr.linux@gmail.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Cc: stable@vger.kernel.org # v4.19+
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/330387/
---
 drivers/gpu/drm/ttm/ttm_bo_vm.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 76eedb963693..46dc3de7e81b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -278,15 +278,13 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 		else
 			ret = vmf_insert_pfn(&cvma, address, pfn);
 
-		/*
-		 * Somebody beat us to this PTE or prefaulting to
-		 * an already populated PTE, or prefaulting error.
-		 */
-
-		if (unlikely((ret == VM_FAULT_NOPAGE && i > 0)))
-			break;
-		else if (unlikely(ret & VM_FAULT_ERROR))
-			goto out_io_unlock;
+		/* Never error on prefaulted PTEs */
+		if (unlikely((ret & VM_FAULT_ERROR))) {
+			if (i == 0)
+				goto out_io_unlock;
+			else
+				break;
+		}
 
 		address += PAGE_SIZE;
 		if (unlikely(++page_offset >= page_last))
-- 
cgit v1.2.3


From 7fbc899ddeaa9aaef0ba646529089149572c84ee Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 10 Oct 2019 13:24:17 +0200
Subject: drm/ttm: fix handling in ttm_bo_add_mem_to_lru
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We should not add the BO to the swap LRU when the new mem is fixed and
the TTM object about to be destroyed.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Link: https://patchwork.freedesktop.org/patch/335246/
---
 drivers/gpu/drm/ttm/ttm_bo.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index ea59459c4128..98819462f025 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -185,8 +185,9 @@ static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
 	list_add_tail(&bo->lru, &man->lru[bo->priority]);
 	kref_get(&bo->list_kref);
 
-	if (bo->ttm && !(bo->ttm->page_flags &
-			 (TTM_PAGE_FLAG_SG | TTM_PAGE_FLAG_SWAPPED))) {
+	if (!(man->flags & TTM_MEMTYPE_FLAG_FIXED) && bo->ttm &&
+	    !(bo->ttm->page_flags & (TTM_PAGE_FLAG_SG |
+				     TTM_PAGE_FLAG_SWAPPED))) {
 		list_add_tail(&bo->swap, &bdev->glob->swap_lru[bo->priority]);
 		kref_get(&bo->list_kref);
 	}
-- 
cgit v1.2.3


From 89b6d1831d21554a5737a201b78a6ad6c5517b46 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sun, 13 Oct 2019 21:30:12 +0100
Subject: drm/i915/execlists: Tweak virtual unsubmission

Since commit e2144503bf3b ("drm/i915: Prevent bonded requests from
overtaking each other on preemption") we have restricted requests to run
on their chosen engine across preemption events. We can take this
restriction into account to know that we will want to resubmit those
requests onto the same physical engine, and so can shortcircuit the
virtual engine selection process and keep the request on the same
engine during unwind.

References: e2144503bf3b ("drm/i915: Prevent bonded requests from overtaking each other on preemption")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Ramlingam C <ramalingam.c@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191013203012.25208-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 6 +++---
 drivers/gpu/drm/i915/i915_request.c | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index a07baeb897fe..ee21307ab5fe 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -847,7 +847,6 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 	list_for_each_entry_safe_reverse(rq, rn,
 					 &engine->active.requests,
 					 sched.link) {
-		struct intel_engine_cs *owner;
 
 		if (i915_request_completed(rq))
 			continue; /* XXX */
@@ -862,8 +861,7 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 		 * engine so that it can be moved across onto another physical
 		 * engine as load dictates.
 		 */
-		owner = rq->hw_context->engine;
-		if (likely(owner == engine)) {
+		if (likely(rq->execution_mask == engine->mask)) {
 			GEM_BUG_ON(rq_prio(rq) == I915_PRIORITY_INVALID);
 			if (rq_prio(rq) != prio) {
 				prio = rq_prio(rq);
@@ -874,6 +872,8 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 			list_move(&rq->sched.link, pl);
 			active = rq;
 		} else {
+			struct intel_engine_cs *owner = rq->hw_context->engine;
+
 			/*
 			 * Decouple the virtual breadcrumb before moving it
 			 * back to the virtual engine -- we don't want the
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 437f9fc6282e..b8a54572a4f8 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -649,6 +649,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->gem_context = ce->gem_context;
 	rq->engine = ce->engine;
 	rq->ring = ce->ring;
+	rq->execution_mask = ce->engine->mask;
 
 	rcu_assign_pointer(rq->timeline, tl);
 	rq->hwsp_seqno = tl->hwsp_seqno;
@@ -671,7 +672,6 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->batch = NULL;
 	rq->capture_list = NULL;
 	rq->flags = 0;
-	rq->execution_mask = ALL_ENGINES;
 
 	INIT_LIST_HEAD(&rq->execute_cb);
 
-- 
cgit v1.2.3


From 832392db9747b9c95724d37fc6a5dadd3d4ec514 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 11 Oct 2019 13:22:58 +0300
Subject: platform/x86: i2c-multi-instantiate: Fail the probe if no IRQ
 provided

For APIC case of interrupt we don't fail a ->probe() of the driver,
which makes kernel to print a lot of warnings from the children.

We have two options here:
- switch to platform_get_irq_optional(), though it won't stop children
  to be probed and failed
- fail the ->probe() of i2c-multi-instantiate

Since the in reality we never had devices in the wild where IRQ resource
is optional, the latter solution suits the best.

Fixes: 799d3379a672 ("platform/x86: i2c-multi-instantiate: Introduce IOAPIC IRQ support")
Reported-by: Ammy Yi <ammy.yi@intel.com>
Cc: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Cc: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
---
 drivers/platform/x86/i2c-multi-instantiate.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/i2c-multi-instantiate.c b/drivers/platform/x86/i2c-multi-instantiate.c
index ea68f6ed66ae..ffb8d5d1eb5f 100644
--- a/drivers/platform/x86/i2c-multi-instantiate.c
+++ b/drivers/platform/x86/i2c-multi-instantiate.c
@@ -108,6 +108,7 @@ static int i2c_multi_inst_probe(struct platform_device *pdev)
 			if (ret < 0) {
 				dev_dbg(dev, "Error requesting irq at index %d: %d\n",
 					inst_data[i].irq_idx, ret);
+				goto error;
 			}
 			board_info.irq = ret;
 			break;
-- 
cgit v1.2.3


From ff229eee3d897f52bd001c841f2d3cce8853ecdc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 8 Oct 2019 10:32:04 -0700
Subject: hrtimer: Annotate lockless access to timer->base

Followup to commit dd2261ed45aa ("hrtimer: Protect lockless access
to timer->base")

lock_hrtimer_base() fetches timer->base without lock exclusion.

Compiler is allowed to read timer->base twice (even if considered dumb)
which could end up trying to lock migration_base and return
&migration_base.

  base = timer->base;
  if (likely(base != &migration_base)) {

       /* compiler reads timer->base again, and now (base == &migration_base)

       raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
       if (likely(base == timer->base))
            return base; /* == &migration_base ! */

Similarly the write sides must use WRITE_ONCE() to avoid store tearing.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20191008173204.180879-1-edumazet@google.com
---
 kernel/time/hrtimer.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 0d4dc241c0fb..65605530ee34 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -164,7 +164,7 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 	struct hrtimer_clock_base *base;
 
 	for (;;) {
-		base = timer->base;
+		base = READ_ONCE(timer->base);
 		if (likely(base != &migration_base)) {
 			raw_spin_lock_irqsave(&base->cpu_base->lock, *flags);
 			if (likely(base == timer->base))
@@ -244,7 +244,7 @@ again:
 			return base;
 
 		/* See the comment in lock_hrtimer_base() */
-		timer->base = &migration_base;
+		WRITE_ONCE(timer->base, &migration_base);
 		raw_spin_unlock(&base->cpu_base->lock);
 		raw_spin_lock(&new_base->cpu_base->lock);
 
@@ -253,10 +253,10 @@ again:
 			raw_spin_unlock(&new_base->cpu_base->lock);
 			raw_spin_lock(&base->cpu_base->lock);
 			new_cpu_base = this_cpu_base;
-			timer->base = base;
+			WRITE_ONCE(timer->base, base);
 			goto again;
 		}
-		timer->base = new_base;
+		WRITE_ONCE(timer->base, new_base);
 	} else {
 		if (new_cpu_base != this_cpu_base &&
 		    hrtimer_check_target(timer, new_base)) {
-- 
cgit v1.2.3


From 41e35ffb380bde1379e4030bb5b2ac824d5139cf Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 11 Oct 2019 23:20:30 +0300
Subject: drm/i915: Favor last VBT child device with conflicting AUX ch/DDC pin
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The first come first served apporoach to handling the VBT
child device AUX ch conflicts has backfired. We have machines
in the wild where the VBT specifies both port A eDP and
port E DP (in that order) with port E being the real one.

So let's try to flip the preference around and let the last
child device win once again.

Cc: stable@vger.kernel.org
Cc: Jani Nikula <jani.nikula@intel.com>
Tested-by: Masami Ichikawa <masami256@gmail.com>
Tested-by: Torsten <freedesktop201910@liggy.de>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111966
Fixes: 36a0f92020dc ("drm/i915/bios: make child device order the priority order")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011202030.8829-1-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_bios.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 9628b485b179..f0307b04cc13 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1270,7 +1270,7 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("port %c trying to use the same DDC pin (0x%x) as port %c, "
 			      "disabling port %c DVI/HDMI support\n",
 			      port_name(port), info->alternate_ddc_pin,
-			      port_name(p), port_name(port));
+			      port_name(p), port_name(p));
 
 		/*
 		 * If we have multiple ports supposedly sharing the
@@ -1278,9 +1278,14 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
 		 * port. Otherwise they share the same ddc bin and
 		 * system couldn't communicate with them separately.
 		 *
-		 * Give child device order the priority, first come first
-		 * served.
+		 * Give inverse child device order the priority,
+		 * last one wins. Yes, there are real machines
+		 * (eg. Asrock B250M-HDV) where VBT has both
+		 * port A and port E with the same AUX ch and
+		 * we must pick port E :(
 		 */
+		info = &dev_priv->vbt.ddi_port_info[p];
+
 		info->supports_dvi = false;
 		info->supports_hdmi = false;
 		info->alternate_ddc_pin = 0;
@@ -1316,7 +1321,7 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("port %c trying to use the same AUX CH (0x%x) as port %c, "
 			      "disabling port %c DP support\n",
 			      port_name(port), info->alternate_aux_channel,
-			      port_name(p), port_name(port));
+			      port_name(p), port_name(p));
 
 		/*
 		 * If we have multiple ports supposedlt sharing the
@@ -1324,9 +1329,14 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
 		 * port. Otherwise they share the same aux channel
 		 * and system couldn't communicate with them separately.
 		 *
-		 * Give child device order the priority, first come first
-		 * served.
+		 * Give inverse child device order the priority,
+		 * last one wins. Yes, there are real machines
+		 * (eg. Asrock B250M-HDV) where VBT has both
+		 * port A and port E with the same AUX ch and
+		 * we must pick port E :(
 		 */
+		info = &dev_priv->vbt.ddi_port_info[p];
+
 		info->supports_dp = false;
 		info->alternate_aux_channel = 0;
 	}
-- 
cgit v1.2.3


From 770597ecb2075390c01c425b8b1f551347f1bd70 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 5 Sep 2019 07:52:33 -0600
Subject: nvme-pci: Free tagset if no IO queues

If a controller becomes degraded after a reset, we will not be able to
perform any IO. We currently teardown previously created request
queues and namespaces, but we had kept the unusable tagset. Free
it after all queues using it have been released.

Tested-by: Edmund Nadolski <edmund.nadolski@intel.com>
Reviewed-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 78e403823646..5c04581899f4 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2490,14 +2490,20 @@ static void nvme_release_prp_pools(struct nvme_dev *dev)
 	dma_pool_destroy(dev->prp_small_pool);
 }
 
+static void nvme_free_tagset(struct nvme_dev *dev)
+{
+	if (dev->tagset.tags)
+		blk_mq_free_tag_set(&dev->tagset);
+	dev->ctrl.tagset = NULL;
+}
+
 static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 {
 	struct nvme_dev *dev = to_nvme_dev(ctrl);
 
 	nvme_dbbuf_dma_free(dev);
 	put_device(dev->dev);
-	if (dev->tagset.tags)
-		blk_mq_free_tag_set(&dev->tagset);
+	nvme_free_tagset(dev);
 	if (dev->ctrl.admin_q)
 		blk_put_queue(dev->ctrl.admin_q);
 	kfree(dev->queues);
@@ -2616,6 +2622,7 @@ static void nvme_reset_work(struct work_struct *work)
 		nvme_kill_queues(&dev->ctrl);
 		nvme_remove_namespaces(&dev->ctrl);
 		new_state = NVME_CTRL_ADMIN_ONLY;
+		nvme_free_tagset(dev);
 	} else {
 		nvme_start_queues(&dev->ctrl);
 		nvme_wait_freeze(&dev->ctrl);
-- 
cgit v1.2.3


From 5d02a5c1d6e14534ca4729b055c89a2cd022ca00 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Tue, 3 Sep 2019 09:22:24 -0600
Subject: nvme: Remove ADMIN_ONLY state

The admin only state was intended to fence off actions that don't
apply to a non-IO capable controller. The only actual user of this is
the scan_work, and pci was the only transport to ever set this state.
The consequence of having this state is placing an additional burden on
every other action that applies to both live and admin only controllers.

Remove the admin only state and place the admin only burden on the only
place that actually cares: scan_work.

This also prepares to make it easier to temporarily pause a LIVE state
so that we don't need to remember which state the controller had been in
prior to the pause.

Tested-by: Edmund Nadolski <edmund.nadolski@intel.com>
Reviewed-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c    | 23 ++++-------------------
 drivers/nvme/host/fabrics.h |  3 +--
 drivers/nvme/host/nvme.h    |  1 -
 drivers/nvme/host/pci.c     | 21 ++++++---------------
 4 files changed, 11 insertions(+), 37 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index ef1d8f81f69e..e451e77005dc 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -116,7 +116,7 @@ static void nvme_queue_scan(struct nvme_ctrl *ctrl)
 	/*
 	 * Only new queue scan work when admin and IO queues are both alive
 	 */
-	if (ctrl->state == NVME_CTRL_LIVE)
+	if (ctrl->state == NVME_CTRL_LIVE && ctrl->tagset)
 		queue_work(nvme_wq, &ctrl->scan_work);
 }
 
@@ -137,8 +137,7 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 	ret = nvme_reset_ctrl(ctrl);
 	if (!ret) {
 		flush_work(&ctrl->reset_work);
-		if (ctrl->state != NVME_CTRL_LIVE &&
-		    ctrl->state != NVME_CTRL_ADMIN_ONLY)
+		if (ctrl->state != NVME_CTRL_LIVE)
 			ret = -ENETRESET;
 	}
 
@@ -315,15 +314,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 
 	old_state = ctrl->state;
 	switch (new_state) {
-	case NVME_CTRL_ADMIN_ONLY:
-		switch (old_state) {
-		case NVME_CTRL_CONNECTING:
-			changed = true;
-			/* FALLTHRU */
-		default:
-			break;
-		}
-		break;
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
 		case NVME_CTRL_NEW:
@@ -339,7 +329,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		switch (old_state) {
 		case NVME_CTRL_NEW:
 		case NVME_CTRL_LIVE:
-		case NVME_CTRL_ADMIN_ONLY:
 			changed = true;
 			/* FALLTHRU */
 		default:
@@ -359,7 +348,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	case NVME_CTRL_DELETING:
 		switch (old_state) {
 		case NVME_CTRL_LIVE:
-		case NVME_CTRL_ADMIN_ONLY:
 		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
 			changed = true;
@@ -2873,7 +2861,6 @@ static int nvme_dev_open(struct inode *inode, struct file *file)
 
 	switch (ctrl->state) {
 	case NVME_CTRL_LIVE:
-	case NVME_CTRL_ADMIN_ONLY:
 		break;
 	default:
 		return -EWOULDBLOCK;
@@ -3167,7 +3154,6 @@ static ssize_t nvme_sysfs_show_state(struct device *dev,
 	static const char *const state_name[] = {
 		[NVME_CTRL_NEW]		= "new",
 		[NVME_CTRL_LIVE]	= "live",
-		[NVME_CTRL_ADMIN_ONLY]	= "only-admin",
 		[NVME_CTRL_RESETTING]	= "resetting",
 		[NVME_CTRL_CONNECTING]	= "connecting",
 		[NVME_CTRL_DELETING]	= "deleting",
@@ -3678,11 +3664,10 @@ static void nvme_scan_work(struct work_struct *work)
 	struct nvme_id_ctrl *id;
 	unsigned nn;
 
-	if (ctrl->state != NVME_CTRL_LIVE)
+	/* No tagset on a live ctrl means IO queues could not created */
+	if (ctrl->state != NVME_CTRL_LIVE || !ctrl->tagset)
 		return;
 
-	WARN_ON_ONCE(!ctrl->tagset);
-
 	if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) {
 		dev_info(ctrl->device, "rescanning namespaces.\n");
 		nvme_clear_changed_ns_log(ctrl);
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 93f08d77c896..a0ec40ab62ee 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -182,8 +182,7 @@ bool nvmf_ip_options_match(struct nvme_ctrl *ctrl,
 static inline bool nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		bool queue_live)
 {
-	if (likely(ctrl->state == NVME_CTRL_LIVE ||
-		   ctrl->state == NVME_CTRL_ADMIN_ONLY))
+	if (likely(ctrl->state == NVME_CTRL_LIVE))
 		return true;
 	return __nvmf_check_ready(ctrl, rq, queue_live);
 }
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 38a83ef5bcd3..2ba577271ada 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -161,7 +161,6 @@ static inline u16 nvme_req_qid(struct request *req)
 enum nvme_ctrl_state {
 	NVME_CTRL_NEW,
 	NVME_CTRL_LIVE,
-	NVME_CTRL_ADMIN_ONLY,    /* Only admin queue live */
 	NVME_CTRL_RESETTING,
 	NVME_CTRL_CONNECTING,
 	NVME_CTRL_DELETING,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 5c04581899f4..e7e79d6af9ba 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2263,10 +2263,7 @@ static bool __nvme_disable_io_queues(struct nvme_dev *dev, u8 opcode)
 	return true;
 }
 
-/*
- * return error value only when tagset allocation failed
- */
-static int nvme_dev_add(struct nvme_dev *dev)
+static void nvme_dev_add(struct nvme_dev *dev)
 {
 	int ret;
 
@@ -2296,7 +2293,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 		if (ret) {
 			dev_warn(dev->ctrl.device,
 				"IO queues tagset allocation failed %d\n", ret);
-			return ret;
+			return;
 		}
 		dev->ctrl.tagset = &dev->tagset;
 	} else {
@@ -2307,7 +2304,6 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	}
 
 	nvme_dbbuf_set(dev);
-	return 0;
 }
 
 static int nvme_pci_enable(struct nvme_dev *dev)
@@ -2527,7 +2523,6 @@ static void nvme_reset_work(struct work_struct *work)
 		container_of(work, struct nvme_dev, ctrl.reset_work);
 	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
 	int result;
-	enum nvme_ctrl_state new_state = NVME_CTRL_LIVE;
 
 	if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) {
 		result = -ENODEV;
@@ -2621,14 +2616,11 @@ static void nvme_reset_work(struct work_struct *work)
 		dev_warn(dev->ctrl.device, "IO queues not created\n");
 		nvme_kill_queues(&dev->ctrl);
 		nvme_remove_namespaces(&dev->ctrl);
-		new_state = NVME_CTRL_ADMIN_ONLY;
 		nvme_free_tagset(dev);
 	} else {
 		nvme_start_queues(&dev->ctrl);
 		nvme_wait_freeze(&dev->ctrl);
-		/* hit this only when allocate tagset fails */
-		if (nvme_dev_add(dev))
-			new_state = NVME_CTRL_ADMIN_ONLY;
+		nvme_dev_add(dev);
 		nvme_unfreeze(&dev->ctrl);
 	}
 
@@ -2636,9 +2628,9 @@ static void nvme_reset_work(struct work_struct *work)
 	 * If only admin queue live, keep it to do further investigation or
 	 * recovery.
 	 */
-	if (!nvme_change_ctrl_state(&dev->ctrl, new_state)) {
+	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_LIVE)) {
 		dev_warn(dev->ctrl.device,
-			"failed to mark controller state %d\n", new_state);
+			"failed to mark controller live state\n");
 		result = -ENODEV;
 		goto out;
 	}
@@ -2945,8 +2937,7 @@ static int nvme_suspend(struct device *dev)
 	nvme_wait_freeze(ctrl);
 	nvme_sync_queues(ctrl);
 
-	if (ctrl->state != NVME_CTRL_LIVE &&
-	    ctrl->state != NVME_CTRL_ADMIN_ONLY)
+	if (ctrl->state != NVME_CTRL_LIVE)
 		goto unfreeze;
 
 	ret = nvme_get_power_state(ctrl, &ndev->last_ps);
-- 
cgit v1.2.3


From 92b98e88d59ab17e65f261fbb5db272143ccf414 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 5 Sep 2019 08:09:33 -0600
Subject: nvme: Restart request timers in resetting state

A controller in the resetting state has not yet completed its recovery
actions. The pci and fc transports were already handling this, so update
the remaining transports to not attempt additional recovery in this
state. Instead, just restart the request timer.

Tested-by: Edmund Nadolski <edmund.nadolski@intel.com>
Reviewed-by: James Smart <james.smart@broadcom.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/rdma.c | 8 ++++++++
 drivers/nvme/host/tcp.c  | 8 ++++++++
 2 files changed, 16 insertions(+)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 4d280160dd3f..f19a28b4e997 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1701,6 +1701,14 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
 	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
 		 rq->tag, nvme_rdma_queue_idx(queue));
 
+	/*
+	 * Restart the timer if a controller reset is already scheduled. Any
+	 * timed out commands would be handled before entering the connecting
+	 * state.
+	 */
+	if (ctrl->ctrl.state == NVME_CTRL_RESETTING)
+		return BLK_EH_RESET_TIMER;
+
 	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
 		/*
 		 * Teardown immediately if controller times out while starting
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 385a5212c10f..33de2fddfbb2 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2044,6 +2044,14 @@ nvme_tcp_timeout(struct request *rq, bool reserved)
 	struct nvme_tcp_ctrl *ctrl = req->queue->ctrl;
 	struct nvme_tcp_cmd_pdu *pdu = req->pdu;
 
+	/*
+	 * Restart the timer if a controller reset is already scheduled. Any
+	 * timed out commands would be handled before entering the connecting
+	 * state.
+	 */
+	if (ctrl->ctrl.state == NVME_CTRL_RESETTING)
+		return BLK_EH_RESET_TIMER;
+
 	dev_warn(ctrl->ctrl.device,
 		"queue %d: timeout request %#x type %d\n",
 		nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type);
-- 
cgit v1.2.3


From 4c75f877853cfa81b12374a07208e07b077f39b8 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Fri, 6 Sep 2019 11:23:08 -0600
Subject: nvme: Prevent resets during paused controller state

A paused controller is doing critical internal activation work in the
background. Prevent subsequent controller resets from occurring during
this period by setting the controller state to RESETTING first. A helper
function, nvme_try_sched_reset_work(), is introduced for these paths so
they may continue with scheduling the reset_work after they've completed
their uninterruptible critical section.

Tested-by: Edmund Nadolski <edmund.nadolski@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e451e77005dc..e94fa693dd4b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -120,6 +120,21 @@ static void nvme_queue_scan(struct nvme_ctrl *ctrl)
 		queue_work(nvme_wq, &ctrl->scan_work);
 }
 
+/*
+ * Use this function to proceed with scheduling reset_work for a controller
+ * that had previously been set to the resetting state. This is intended for
+ * code paths that can't be interrupted by other reset attempts. A hot removal
+ * may prevent this from succeeding.
+ */
+static int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
+{
+	if (ctrl->state != NVME_CTRL_RESETTING)
+		return -EBUSY;
+	if (!queue_work(nvme_reset_wq, &ctrl->reset_work))
+		return -EBUSY;
+	return 0;
+}
+
 int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
 {
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
@@ -3828,13 +3843,13 @@ static void nvme_fw_act_work(struct work_struct *work)
 		if (time_after(jiffies, fw_act_timeout)) {
 			dev_warn(ctrl->device,
 				"Fw activation timeout, reset controller\n");
-			nvme_reset_ctrl(ctrl);
-			break;
+			nvme_try_sched_reset(ctrl);
+			return;
 		}
 		msleep(100);
 	}
 
-	if (ctrl->state != NVME_CTRL_LIVE)
+	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_LIVE))
 		return;
 
 	nvme_start_queues(ctrl);
@@ -3854,7 +3869,13 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 		nvme_queue_scan(ctrl);
 		break;
 	case NVME_AER_NOTICE_FW_ACT_STARTING:
-		queue_work(nvme_wq, &ctrl->fw_act_work);
+		/*
+		 * We are (ab)using the RESETTING state to prevent subsequent
+		 * recovery actions from interfering with the controller's
+		 * firmware activation.
+		 */
+		if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
+			queue_work(nvme_wq, &ctrl->fw_act_work);
 		break;
 #ifdef CONFIG_NVME_MULTIPATH
 	case NVME_AER_NOTICE_ANA:
-- 
cgit v1.2.3


From c1ac9a4b0797ca8bb4470f863a5f78ef1ab13bed Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Wed, 4 Sep 2019 10:06:11 -0600
Subject: nvme: Wait for reset state when required

Prevent simultaneous controller disabling/enabling tasks from interfering
with each other through a function to wait until the task successfully
transitioned the controller to the RESETTING state. This ensures disabling
the controller will not be interrupted by another reset path, otherwise
a concurrent reset may leave the controller in the wrong state.

Tested-by: Edmund Nadolski <edmund.nadolski@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 41 +++++++++++++++++++++++++++++++++++++++--
 drivers/nvme/host/nvme.h |  4 ++++
 drivers/nvme/host/pci.c  | 46 +++++++++++++++++++++++++++++++---------------
 3 files changed, 74 insertions(+), 17 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e94fa693dd4b..fa7ba09dca77 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -126,7 +126,7 @@ static void nvme_queue_scan(struct nvme_ctrl *ctrl)
  * code paths that can't be interrupted by other reset attempts. A hot removal
  * may prevent this from succeeding.
  */
-static int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
+int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
 {
 	if (ctrl->state != NVME_CTRL_RESETTING)
 		return -EBUSY;
@@ -134,6 +134,7 @@ static int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
 		return -EBUSY;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nvme_try_sched_reset);
 
 int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
 {
@@ -384,8 +385,10 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		break;
 	}
 
-	if (changed)
+	if (changed) {
 		ctrl->state = new_state;
+		wake_up_all(&ctrl->state_wq);
+	}
 
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 	if (changed && ctrl->state == NVME_CTRL_LIVE)
@@ -394,6 +397,39 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 }
 EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
 
+/*
+ * Returns true for sink states that can't ever transition back to live.
+ */
+static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
+{
+	switch (ctrl->state) {
+	case NVME_CTRL_NEW:
+	case NVME_CTRL_LIVE:
+	case NVME_CTRL_RESETTING:
+	case NVME_CTRL_CONNECTING:
+		return false;
+	case NVME_CTRL_DELETING:
+	case NVME_CTRL_DEAD:
+		return true;
+	default:
+		WARN_ONCE(1, "Unhandled ctrl state:%d", ctrl->state);
+		return true;
+	}
+}
+
+/*
+ * Waits for the controller state to be resetting, or returns false if it is
+ * not possible to ever transition to that state.
+ */
+bool nvme_wait_reset(struct nvme_ctrl *ctrl)
+{
+	wait_event(ctrl->state_wq,
+		   nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) ||
+		   nvme_state_terminal(ctrl));
+	return ctrl->state == NVME_CTRL_RESETTING;
+}
+EXPORT_SYMBOL_GPL(nvme_wait_reset);
+
 static void nvme_free_ns_head(struct kref *ref)
 {
 	struct nvme_ns_head *head =
@@ -3998,6 +4034,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	INIT_WORK(&ctrl->async_event_work, nvme_async_event_work);
 	INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work);
 	INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work);
+	init_waitqueue_head(&ctrl->state_wq);
 
 	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
 	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 2ba577271ada..22e8401352c2 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -15,6 +15,7 @@
 #include <linux/sed-opal.h>
 #include <linux/fault-inject.h>
 #include <linux/rcupdate.h>
+#include <linux/wait.h>
 
 #include <trace/events/block.h>
 
@@ -198,6 +199,7 @@ struct nvme_ctrl {
 	struct cdev cdev;
 	struct work_struct reset_work;
 	struct work_struct delete_work;
+	wait_queue_head_t state_wq;
 
 	struct nvme_subsystem *subsys;
 	struct list_head subsys_entry;
@@ -448,6 +450,7 @@ void nvme_complete_rq(struct request *req);
 bool nvme_cancel_request(struct request *req, void *data, bool reserved);
 bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 		enum nvme_ctrl_state new_state);
+bool nvme_wait_reset(struct nvme_ctrl *ctrl);
 int nvme_disable_ctrl(struct nvme_ctrl *ctrl);
 int nvme_enable_ctrl(struct nvme_ctrl *ctrl);
 int nvme_shutdown_ctrl(struct nvme_ctrl *ctrl);
@@ -498,6 +501,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count);
 void nvme_stop_keep_alive(struct nvme_ctrl *ctrl);
 int nvme_reset_ctrl(struct nvme_ctrl *ctrl);
 int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
+int nvme_try_sched_reset(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 
 int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index e7e79d6af9ba..4b181969c432 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2463,6 +2463,14 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	mutex_unlock(&dev->shutdown_lock);
 }
 
+static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown)
+{
+	if (!nvme_wait_reset(&dev->ctrl))
+		return -EBUSY;
+	nvme_dev_disable(dev, shutdown);
+	return 0;
+}
+
 static int nvme_setup_prp_pools(struct nvme_dev *dev)
 {
 	dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
@@ -2510,6 +2518,11 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 
 static void nvme_remove_dead_ctrl(struct nvme_dev *dev)
 {
+	/*
+	 * Set state to deleting now to avoid blocking nvme_wait_reset(), which
+	 * may be holding this pci_dev's device lock.
+	 */
+	nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
 	nvme_get_ctrl(&dev->ctrl);
 	nvme_dev_disable(dev, false);
 	nvme_kill_queues(&dev->ctrl);
@@ -2835,19 +2848,28 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 static void nvme_reset_prepare(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
-	nvme_dev_disable(dev, false);
+
+	/*
+	 * We don't need to check the return value from waiting for the reset
+	 * state as pci_dev device lock is held, making it impossible to race
+	 * with ->remove().
+	 */
+	nvme_disable_prepare_reset(dev, false);
+	nvme_sync_queues(&dev->ctrl);
 }
 
 static void nvme_reset_done(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
-	nvme_reset_ctrl_sync(&dev->ctrl);
+
+	if (!nvme_try_sched_reset(&dev->ctrl))
+		flush_work(&dev->ctrl.reset_work);
 }
 
 static void nvme_shutdown(struct pci_dev *pdev)
 {
 	struct nvme_dev *dev = pci_get_drvdata(pdev);
-	nvme_dev_disable(dev, true);
+	nvme_disable_prepare_reset(dev, true);
 }
 
 /*
@@ -2900,7 +2922,7 @@ static int nvme_resume(struct device *dev)
 
 	if (ndev->last_ps == U32_MAX ||
 	    nvme_set_power_state(ctrl, ndev->last_ps) != 0)
-		nvme_reset_ctrl(ctrl);
+		return nvme_try_sched_reset(&ndev->ctrl);
 	return 0;
 }
 
@@ -2928,10 +2950,8 @@ static int nvme_suspend(struct device *dev)
 	 */
 	if (pm_suspend_via_firmware() || !ctrl->npss ||
 	    !pcie_aspm_enabled(pdev) ||
-	    (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND)) {
-		nvme_dev_disable(ndev, true);
-		return 0;
-	}
+	    (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND))
+		return nvme_disable_prepare_reset(ndev, true);
 
 	nvme_start_freeze(ctrl);
 	nvme_wait_freeze(ctrl);
@@ -2963,9 +2983,8 @@ static int nvme_suspend(struct device *dev)
 		 * Clearing npss forces a controller reset on resume. The
 		 * correct value will be resdicovered then.
 		 */
-		nvme_dev_disable(ndev, true);
+		ret = nvme_disable_prepare_reset(ndev, true);
 		ctrl->npss = 0;
-		ret = 0;
 	}
 unfreeze:
 	nvme_unfreeze(ctrl);
@@ -2975,9 +2994,7 @@ unfreeze:
 static int nvme_simple_suspend(struct device *dev)
 {
 	struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev));
-
-	nvme_dev_disable(ndev, true);
-	return 0;
+	return nvme_disable_prepare_reset(ndev, true);
 }
 
 static int nvme_simple_resume(struct device *dev)
@@ -2985,8 +3002,7 @@ static int nvme_simple_resume(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct nvme_dev *ndev = pci_get_drvdata(pdev);
 
-	nvme_reset_ctrl(&ndev->ctrl);
-	return 0;
+	return nvme_try_sched_reset(&ndev->ctrl);
 }
 
 static const struct dev_pm_ops nvme_dev_pm_ops = {
-- 
cgit v1.2.3


From ac1c4e18858cb1da6abe1932a7ca001c37f62372 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 10 Oct 2019 17:34:12 +0200
Subject: nvme-tcp: Initialize sk->sk_ll_usec only with NET_RX_BUSY_POLL

The access to sk->sk_ll_usec should be hidden behind
CONFIG_NET_RX_BUSY_POLL like the definition of sk_ll_usec.

Put access to ->sk_ll_usec behind CONFIG_NET_RX_BUSY_POLL.

Fixes: 1a9460cef5711 ("nvme-tcp: support simple polling")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 33de2fddfbb2..820dac10fa9e 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1386,7 +1386,9 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl,
 	queue->sock->sk->sk_data_ready = nvme_tcp_data_ready;
 	queue->sock->sk->sk_state_change = nvme_tcp_state_change;
 	queue->sock->sk->sk_write_space = nvme_tcp_write_space;
+#ifdef CONFIG_NET_RX_BUSY_POLL
 	queue->sock->sk->sk_ll_usec = 1;
+#endif
 	write_unlock_bh(&queue->sock->sk->sk_callback_lock);
 
 	return 0;
-- 
cgit v1.2.3


From 2abd839aa7e615f2bbc50c8ba7deb9e40d186768 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Fri, 4 Oct 2019 14:46:24 +0100
Subject: kmemleak: Do not corrupt the object_list during clean-up

In case of an error (e.g. memory pool too small), kmemleak disables
itself and cleans up the already allocated metadata objects. However, if
this happens early before the RCU callback mechanism is available,
put_object() skips call_rcu() and frees the object directly. This is not
safe with the RCU list traversal in __kmemleak_do_cleanup().

Change the list traversal in __kmemleak_do_cleanup() to
list_for_each_entry_safe() and remove the rcu_read_{lock,unlock} since
the kmemleak is already disabled at this point. In addition, avoid an
unnecessary metadata object rb-tree look-up since it already has the
struct kmemleak_object pointer.

Fixes: c5665868183f ("mm: kmemleak: use the memory pool for early allocations")
Reported-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reported-by: Marc Dionne <marc.c.dionne@gmail.com>
Reported-by: Ted Ts'o <tytso@mit.edu>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/kmemleak.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 03a8d84badad..244607663363 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -526,6 +526,16 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias)
 	return object;
 }
 
+/*
+ * Remove an object from the object_tree_root and object_list. Must be called
+ * with the kmemleak_lock held _if_ kmemleak is still enabled.
+ */
+static void __remove_object(struct kmemleak_object *object)
+{
+	rb_erase(&object->rb_node, &object_tree_root);
+	list_del_rcu(&object->object_list);
+}
+
 /*
  * Look up an object in the object search tree and remove it from both
  * object_tree_root and object_list. The returned object's use_count should be
@@ -538,10 +548,8 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali
 
 	write_lock_irqsave(&kmemleak_lock, flags);
 	object = lookup_object(ptr, alias);
-	if (object) {
-		rb_erase(&object->rb_node, &object_tree_root);
-		list_del_rcu(&object->object_list);
-	}
+	if (object)
+		__remove_object(object);
 	write_unlock_irqrestore(&kmemleak_lock, flags);
 
 	return object;
@@ -1834,12 +1842,16 @@ static const struct file_operations kmemleak_fops = {
 
 static void __kmemleak_do_cleanup(void)
 {
-	struct kmemleak_object *object;
+	struct kmemleak_object *object, *tmp;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(object, &object_list, object_list)
-		delete_object_full(object->pointer);
-	rcu_read_unlock();
+	/*
+	 * Kmemleak has already been disabled, no need for RCU list traversal
+	 * or kmemleak_lock held.
+	 */
+	list_for_each_entry_safe(object, tmp, &object_list, object_list) {
+		__remove_object(object);
+		__delete_object(object);
+	}
 }
 
 /*
-- 
cgit v1.2.3


From 53448aed7b805cf36ecc59ed5fe8e53815ce4fe8 Mon Sep 17 00:00:00 2001
From: Vivek Kasireddy <vivek.kasireddy@intel.com>
Date: Thu, 10 Oct 2019 17:26:18 -0700
Subject: drm/i915/ehl: Port C's hotplug interrupt is associated with TC1 bits

On platforms that have the MCC PCH, Port C's hotplug interrupt
bits are mapped to TC1 bits.

Suggested-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011002618.3087-1-vivek.kasireddy@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c | 3 +++
 drivers/gpu/drm/i915/i915_irq.c         | 8 ++++----
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 38aa09cfbed3..830c71e5c861 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -5282,6 +5282,9 @@ static bool icl_combo_port_connected(struct drm_i915_private *dev_priv,
 {
 	enum port port = intel_dig_port->base.port;
 
+	if (HAS_PCH_MCC(dev_priv) && port == PORT_C)
+		return I915_READ(SDEISR) & SDE_TC_HOTPLUG_ICP(PORT_TC1);
+
 	return I915_READ(SDEISR) & SDE_DDI_HOTPLUG_ICP(port);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 3af7f7914c40..a7c968b01af3 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2249,8 +2249,8 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		tc_port_hotplug_long_detect = tgp_tc_port_hotplug_long_detect;
 		pins = hpd_tgp;
 	} else if (HAS_PCH_MCC(dev_priv)) {
-		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_TGP;
-		tc_hotplug_trigger = 0;
+		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP;
+		tc_hotplug_trigger = pch_iir & SDE_TC_HOTPLUG_ICP(PORT_TC1);
 		pins = hpd_icp;
 	} else {
 		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP;
@@ -3377,8 +3377,8 @@ static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv,
 static void mcc_hpd_irq_setup(struct drm_i915_private *dev_priv)
 {
 	icp_hpd_irq_setup(dev_priv,
-			  SDE_DDI_MASK_TGP, 0,
-			  TGP_DDI_HPD_ENABLE_MASK, 0,
+			  SDE_DDI_MASK_ICP, SDE_TC_HOTPLUG_ICP(PORT_TC1),
+			  ICP_DDI_HPD_ENABLE_MASK, ICP_TC_HPD_ENABLE(PORT_TC1),
 			  hpd_icp);
 }
 
-- 
cgit v1.2.3


From 6595d144decec396bf2e2efee27e50634a4b627f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 9 Oct 2019 20:21:05 +0100
Subject: xtensa: fix {get,put}_user() for 64bit values

First of all, on short copies __copy_{to,from}_user() return the amount
of bytes left uncopied, *not* -EFAULT.  get_user() and put_user() are
expected to return -EFAULT on failure.

Another problem is get_user(v32, (__u64 __user *)p); that should
fetch 64bit value and the assign it to v32, truncating it in process.
Current code, OTOH, reads 8 bytes of data and stores them at the
address of v32, stomping on the 4 bytes that follow v32 itself.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/include/asm/uaccess.h | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index 6792928ba84a..f568c00392ec 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -100,7 +100,7 @@ do {									\
 	case 4: __put_user_asm(x, ptr, retval, 4, "s32i", __cb); break;	\
 	case 8: {							\
 		     __typeof__(*ptr) __v64 = x;			\
-		     retval = __copy_to_user(ptr, &__v64, 8);		\
+		     retval = __copy_to_user(ptr, &__v64, 8) ? -EFAULT : 0;	\
 		     break;						\
 	        }							\
 	default: __put_user_bad();					\
@@ -198,7 +198,16 @@ do {									\
 	case 1: __get_user_asm(x, ptr, retval, 1, "l8ui", __cb);  break;\
 	case 2: __get_user_asm(x, ptr, retval, 2, "l16ui", __cb); break;\
 	case 4: __get_user_asm(x, ptr, retval, 4, "l32i", __cb);  break;\
-	case 8: retval = __copy_from_user(&x, ptr, 8);    break;	\
+	case 8: {							\
+		u64 __x;						\
+		if (unlikely(__copy_from_user(&__x, ptr, 8))) {		\
+			retval = -EFAULT;				\
+			(x) = 0;					\
+		} else {						\
+			(x) = *(__force __typeof__((ptr)))&__x;		\
+		}							\
+		break;							\
+	}								\
 	default: (x) = __get_user_bad();				\
 	}								\
 } while (0)
-- 
cgit v1.2.3


From eda6d764ac33d9ce8d656fa381f05b3feae09085 Mon Sep 17 00:00:00 2001
From: Steven Price <steven.price@arm.com>
Date: Mon, 14 Oct 2019 16:15:15 +0100
Subject: drm/panfrost: Add missing GPU feature registers

Three feature registers were declared but never actually read from the
GPU. Add THREAD_MAX_THREADS, THREAD_MAX_WORKGROUP_SIZE and
THREAD_MAX_BARRIER_SIZE so that the complete set are available.

Fixes: 4bced8bea094 ("drm/panfrost: Export all GPU feature registers")
Signed-off-by: Steven Price <steven.price@arm.com>
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20191014151515.13839-1-steven.price@arm.com
---
 drivers/gpu/drm/panfrost/panfrost_gpu.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index f67ed925c0ef..8822ec13a0d6 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -208,6 +208,9 @@ static void panfrost_gpu_init_features(struct panfrost_device *pfdev)
 	pfdev->features.mem_features = gpu_read(pfdev, GPU_MEM_FEATURES);
 	pfdev->features.mmu_features = gpu_read(pfdev, GPU_MMU_FEATURES);
 	pfdev->features.thread_features = gpu_read(pfdev, GPU_THREAD_FEATURES);
+	pfdev->features.max_threads = gpu_read(pfdev, GPU_THREAD_MAX_THREADS);
+	pfdev->features.thread_max_workgroup_sz = gpu_read(pfdev, GPU_THREAD_MAX_WORKGROUP_SIZE);
+	pfdev->features.thread_max_barrier_sz = gpu_read(pfdev, GPU_THREAD_MAX_BARRIER_SIZE);
 	pfdev->features.coherency_features = gpu_read(pfdev, GPU_COHERENCY_FEATURES);
 	for (i = 0; i < 4; i++)
 		pfdev->features.texture_features[i] = gpu_read(pfdev, GPU_TEXTURE_FEATURES(i));
-- 
cgit v1.2.3


From 2f01b7864188b895e0f18250b650328da4fe3cb2 Mon Sep 17 00:00:00 2001
From: Vincent Chen <vincent.chen@sifive.com>
Date: Mon, 23 Sep 2019 08:45:17 +0800
Subject: riscv: remove the switch statement in do_trap_break()

To make the code more straightforward, replace the switch statement
with an if statement.

Suggested-by: Paul Walmsley <paul.walmsley@sifive.com>
Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
[paul.walmsley@sifive.com: cleaned up patch description; updated to
 apply]
Link: https://lore.kernel.org/linux-riscv/20190927224711.GI4700@infradead.org/
Link: https://lore.kernel.org/linux-riscv/CABvJ_xiHJSB7P5QekuLRP=LBPzXXghAfuUpPUYb=a_HbnOQ6BA@mail.gmail.com/
Link: https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org/thread/VDCU2WOB6KQISREO4V5DTXEI2M7VOV55/
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
---
 arch/riscv/kernel/traps.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 93742df9067f..1ac75f7d0bff 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -124,24 +124,24 @@ static inline unsigned long get_break_insn_length(unsigned long pc)
 
 asmlinkage void do_trap_break(struct pt_regs *regs)
 {
-	if (!user_mode(regs)) {
+	if (user_mode(regs)) {
+		force_sig_fault(SIGTRAP, TRAP_BRKPT,
+				(void __user *)(regs->sepc));
+		return;
+	}
+#ifdef CONFIG_GENERIC_BUG
+	{
 		enum bug_trap_type type;
 
 		type = report_bug(regs->sepc, regs);
-		switch (type) {
-#ifdef CONFIG_GENERIC_BUG
-		case BUG_TRAP_TYPE_WARN:
+		if (type == BUG_TRAP_TYPE_WARN) {
 			regs->sepc += get_break_insn_length(regs->sepc);
 			return;
-		case BUG_TRAP_TYPE_BUG:
-#endif /* CONFIG_GENERIC_BUG */
-		default:
-			die(regs, "Kernel BUG");
 		}
-	} else {
-		force_sig_fault(SIGTRAP, TRAP_BRKPT,
-				(void __user *)(regs->sepc));
 	}
+#endif /* CONFIG_GENERIC_BUG */
+
+	die(regs, "Kernel BUG");
 }
 
 #ifdef CONFIG_GENERIC_BUG
-- 
cgit v1.2.3


From 2993c9b04e616df0848b655d7202a707a70fc876 Mon Sep 17 00:00:00 2001
From: Paul Walmsley <paul.walmsley@sifive.com>
Date: Wed, 9 Oct 2019 12:42:44 -0700
Subject: riscv: dts: HiFive Unleashed: add default chosen/stdout-path

Add a default "stdout-path" to the kernel DTS file, as is present in many
of the board DTS files elsewhere in the kernel tree. With this line
present, earlyconsole can be enabled by simply passing "earlycon" on the
kernel command line.  No specific device details are necessary, since the
kernel will use the stdout-path as the default.

Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
Reviewed-by: Atish Patra <atish.patra@wdc.com>
---
 arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
index 104d334511cd..88cfcb96bf23 100644
--- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
+++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
@@ -13,6 +13,7 @@
 	compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000";
 
 	chosen {
+		stdout-path = "serial0";
 	};
 
 	cpus {
-- 
cgit v1.2.3


From 4c8eb19cf9dc5fcc489757acbf93be90baf25848 Mon Sep 17 00:00:00 2001
From: Paul Walmsley <paul.walmsley@sifive.com>
Date: Thu, 10 Oct 2019 15:57:58 -0700
Subject: riscv: tlbflush: remove confusing comment on local_flush_tlb_all()

Remove a confusing comment on our local_flush_tlb_all()
implementation.  Per an internal discussion with Andrew, while it's
true that the fence.i is not necessary, it's not the case that an
sfence.vma implies a fence.i.  We also drop the section about
"flush[ing] the entire local TLB" to better align with the language in
section 4.2.1 "Supervisor Memory-Management Fence Instruction" of the
RISC-V Privileged Specification v20190608.

Fixes: c901e45a999a1 ("RISC-V: `sfence.vma` orderes the instruction cache")
Reported-by: Alan Kao <alankao@andestech.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Andrew Waterman <andrew@sifive.com>
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
---
 arch/riscv/include/asm/tlbflush.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 37ae4e367ad2..f02188a5b0f4 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -10,10 +10,6 @@
 #include <linux/mm_types.h>
 #include <asm/smp.h>
 
-/*
- * Flush entire local TLB.  'sfence.vma' implicitly fences with the instruction
- * cache as well, so a 'fence.i' is not necessary.
- */
 static inline void local_flush_tlb_all(void)
 {
 	__asm__ __volatile__ ("sfence.vma" : : : "memory");
-- 
cgit v1.2.3


From 81dde26de9c08bb04c4962a15608778aaffb3cf9 Mon Sep 17 00:00:00 2001
From: Jean Delvare <jdelvare@suse.de>
Date: Mon, 14 Oct 2019 21:41:24 +0200
Subject: firmware: dmi: Fix unlikely out-of-bounds read in save_mem_devices

Before reading the Extended Size field, we should ensure it fits in
the DMI record. There is already a record length check but it does
not cover that field.

It would take a seriously corrupted DMI table to hit that bug, so no
need to worry, but we should still fix it.

Signed-off-by: Jean Delvare <jdelvare@suse.de>
Fixes: 6deae96b42eb ("firmware, DMI: Add function to look up a handle and return DIMM size")
Cc: Tony Luck <tony.luck@intel.com>
Cc: Borislav Petkov <bp@suse.de>
---
 drivers/firmware/dmi_scan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index 35ed56b9c34f..1e21fc3e9851 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -408,7 +408,7 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v)
 		bytes = ~0ull;
 	else if (size & 0x8000)
 		bytes = (u64)(size & 0x7fff) << 10;
-	else if (size != 0x7fff)
+	else if (size != 0x7fff || dm->length < 0x20)
 		bytes = (u64)size << 20;
 	else
 		bytes = (u64)get_unaligned((u32 *)&d[0x1C]) << 20;
-- 
cgit v1.2.3


From b67114db64adcb0aaff0fe0bb2a84ede0a99aaf2 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Fri, 4 Oct 2019 13:10:09 +0200
Subject: parisc: sysctl.c: Use CONFIG_PARISC instead of __hppa_ define

Signed-off-by: Helge Deller <deller@gmx.de>
---
 kernel/sysctl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 00fcea236eba..b6f2f35d0bcf 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -163,7 +163,7 @@ static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
 #ifdef CONFIG_SPARC
 #endif
 
-#ifdef __hppa__
+#ifdef CONFIG_PARISC
 extern int pwrsw_enabled;
 #endif
 
@@ -620,7 +620,7 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#ifdef __hppa__
+#ifdef CONFIG_PARISC
 	{
 		.procname	= "soft-power",
 		.data		= &pwrsw_enabled,
-- 
cgit v1.2.3


From 0703ad217ebd441dd730af71f8d9cdbf144fbc03 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Mon, 12 Aug 2019 14:50:36 -0700
Subject: parisc: prefer __section from compiler_attributes.h

Reported-by: Sedat Dilek <sedat.dilek@gmail.com>
Suggested-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/include/asm/cache.h | 2 +-
 arch/parisc/include/asm/ldcw.h  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h
index 73ca89a47f49..e5de3f897633 100644
--- a/arch/parisc/include/asm/cache.h
+++ b/arch/parisc/include/asm/cache.h
@@ -22,7 +22,7 @@
 
 #define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(.data..read_mostly)
 
 void parisc_cache_init(void);	/* initializes cache-flushing */
 void disable_sr_hashing_asm(int); /* low level support for above */
diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h
index 3eb4bfc1fb36..e080143e79a3 100644
--- a/arch/parisc/include/asm/ldcw.h
+++ b/arch/parisc/include/asm/ldcw.h
@@ -52,7 +52,7 @@
 })
 
 #ifdef CONFIG_SMP
-# define __lock_aligned __attribute__((__section__(".data..lock_aligned")))
+# define __lock_aligned __section(.data..lock_aligned)
 #endif
 
 #endif /* __PARISC_LDCW_H */
-- 
cgit v1.2.3


From 513f7f747e1cba81f28a436911fba0b485878ebd Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Fri, 4 Oct 2019 19:23:37 +0200
Subject: parisc: Fix vmap memory leak in ioremap()/iounmap()

Sven noticed that calling ioremap() and iounmap() multiple times leads
to a vmap memory leak:
	vmap allocation for size 4198400 failed:
	use vmalloc=<size> to increase size

It seems we missed calling vunmap() in iounmap().

Signed-off-by: Helge Deller <deller@gmx.de>
Noticed-by: Sven Schnelle <svens@stackframe.org>
Cc: <stable@vger.kernel.org> # v3.16+
---
 arch/parisc/mm/ioremap.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c
index 92a9b5f12f98..f29f682352f0 100644
--- a/arch/parisc/mm/ioremap.c
+++ b/arch/parisc/mm/ioremap.c
@@ -3,7 +3,7 @@
  * arch/parisc/mm/ioremap.c
  *
  * (C) Copyright 1995 1996 Linus Torvalds
- * (C) Copyright 2001-2006 Helge Deller <deller@gmx.de>
+ * (C) Copyright 2001-2019 Helge Deller <deller@gmx.de>
  * (C) Copyright 2005 Kyle McMartin <kyle@parisc-linux.org>
  */
 
@@ -84,7 +84,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l
 	addr = (void __iomem *) area->addr;
 	if (ioremap_page_range((unsigned long)addr, (unsigned long)addr + size,
 			       phys_addr, pgprot)) {
-		vfree(addr);
+		vunmap(addr);
 		return NULL;
 	}
 
@@ -92,9 +92,11 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l
 }
 EXPORT_SYMBOL(__ioremap);
 
-void iounmap(const volatile void __iomem *addr)
+void iounmap(const volatile void __iomem *io_addr)
 {
-	if (addr > high_memory)
-		return vfree((void *) (PAGE_MASK & (unsigned long __force) addr));
+	unsigned long addr = (unsigned long)io_addr & PAGE_MASK;
+
+	if (is_vmalloc_addr((void *)addr))
+		vunmap((void *)addr);
 }
 EXPORT_SYMBOL(iounmap);
-- 
cgit v1.2.3


From c32c47aa364096124c9c69c1a44918433832562b Mon Sep 17 00:00:00 2001
From: Sven Schnelle <svens@stackframe.org>
Date: Tue, 24 Sep 2019 17:01:31 +0200
Subject: parisc: Remove 32-bit DMA enforcement from sba_iommu

This breaks booting from sata_sil24 with the recent DMA change.
According to James Bottomley this was in to improve performance by
kicking the device into 32 bit descriptors, which are usually more
efficient, especially with older dual descriptor format cards like we
have on parisc systems.
Remove it for now to make DMA working again.

Fixes: dcc02c19cc06 ("sata_sil24: use dma_set_mask_and_coherent")
Signed-off-by: Sven Schnelle <svens@stackframe.org>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/parisc/sba_iommu.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index ed50502cc65a..de8e4e347249 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -678,14 +678,6 @@ static int sba_dma_supported( struct device *dev, u64 mask)
 		return(0);
 	}
 
-	/* Documentation/DMA-API-HOWTO.txt tells drivers to try 64-bit
-	 * first, then fall back to 32-bit if that fails.
-	 * We are just "encouraging" 32-bit DMA masks here since we can
-	 * never allow IOMMU bypass unless we add special support for ZX1.
-	 */
-	if (mask > ~0U)
-		return 0;
-
 	ioc = GET_IOC(dev);
 	if (!ioc)
 		return 0;
-- 
cgit v1.2.3


From 7a7c5e715e722c86d602c56a09e77f000364e263 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <damien.lemoal@wdc.com>
Date: Wed, 9 Oct 2019 07:39:54 +0900
Subject: block: Fix elv_support_iosched()

A BIO based request queue does not have a tag_set, which prevent testing
for the flag BLK_MQ_F_NO_SCHED indicating that the queue does not
require an elevator. This leads to an incorrect initialization of a
default elevator in some cases such as BIO based null_blk
(queue_mode == BIO) with zoned mode enabled as the default elevator in
this case is mq-deadline instead of "none".

Fix this by testing for a NULL queue mq_ops field which indicates that
the queue is BIO based and should not have an elevator.

Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/elevator.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/block/elevator.c b/block/elevator.c
index 5437059c9261..076ba7308e65 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -616,7 +616,8 @@ out:
 
 static inline bool elv_support_iosched(struct request_queue *q)
 {
-	if (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED))
+	if (!q->mq_ops ||
+	    (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED)))
 		return false;
 	return true;
 }
-- 
cgit v1.2.3


From c0437642966fd32b827034af6f00eecd80b89325 Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Wed, 9 Oct 2019 19:41:24 -0700
Subject: xtensa: clean up assembly arguments in uaccess macros

Numeric assembly arguments are hard to understand and assembly code that
uses them is hard to modify. Use named arguments in __check_align_*,
__get_user_asm and __put_user_asm. Modify macro parameter names so that
they don't affect argument names. Use '+' constraint for the [err]
argument instead of having it as both input and output.

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/include/asm/uaccess.h | 42 +++++++++++++++++++--------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index f568c00392ec..da4d35445063 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -132,14 +132,14 @@ do {									\
 #define __check_align_1  ""
 
 #define __check_align_2				\
-	"   _bbci.l %3,  0, 1f		\n"	\
-	"   movi    %0, %4		\n"	\
+	"   _bbci.l %[addr], 0, 1f	\n"	\
+	"   movi    %[err], %[efault]	\n"	\
 	"   _j      2f			\n"
 
 #define __check_align_4				\
-	"   _bbsi.l %3,  0, 0f		\n"	\
-	"   _bbci.l %3,  1, 1f		\n"	\
-	"0: movi    %0, %4		\n"	\
+	"   _bbsi.l %[addr], 0, 0f	\n"	\
+	"   _bbci.l %[addr], 1, 1f	\n"	\
+	"0: movi    %[err], %[efault]	\n"	\
 	"   _j      2f			\n"
 
 
@@ -151,24 +151,24 @@ do {									\
  * WARNING: If you modify this macro at all, verify that the
  * __check_align_* macros still work.
  */
-#define __put_user_asm(x, addr, err, align, insn, cb)	\
+#define __put_user_asm(x_, addr_, err_, align, insn, cb)\
 __asm__ __volatile__(					\
 	__check_align_##align				\
-	"1: "insn"  %2, %3, 0		\n"		\
+	"1: "insn"  %[x], %[addr], 0	\n"		\
 	"2:				\n"		\
 	"   .section  .fixup,\"ax\"	\n"		\
 	"   .align 4			\n"		\
 	"   .literal_position		\n"		\
 	"5:				\n"		\
-	"   movi   %1, 2b		\n"		\
-	"   movi   %0, %4		\n"		\
-	"   jx     %1			\n"		\
+	"   movi   %[tmp], 2b		\n"		\
+	"   movi   %[err], %[efault]	\n"		\
+	"   jx     %[tmp]		\n"		\
 	"   .previous			\n"		\
 	"   .section  __ex_table,\"a\"	\n"		\
 	"   .long	1b, 5b		\n"		\
 	"   .previous"					\
-	:"=r" (err), "=r" (cb)				\
-	:"r" ((int)(x)), "r" (addr), "i" (-EFAULT), "0" (err))
+	:[err] "+r"(err_), [tmp] "=r"(cb)		\
+	:[x] "r"(x_), [addr] "r"(addr_), [efault] "i"(-EFAULT))
 
 #define __get_user_nocheck(x, ptr, size)			\
 ({								\
@@ -217,25 +217,25 @@ do {									\
  * WARNING: If you modify this macro at all, verify that the
  * __check_align_* macros still work.
  */
-#define __get_user_asm(x, addr, err, align, insn, cb) \
-__asm__ __volatile__(			\
+#define __get_user_asm(x_, addr_, err_, align, insn, cb) \
+__asm__ __volatile__(				\
 	__check_align_##align			\
-	"1: "insn"  %2, %3, 0		\n"	\
+	"1: "insn"  %[x], %[addr], 0	\n"	\
 	"2:				\n"	\
 	"   .section  .fixup,\"ax\"	\n"	\
 	"   .align 4			\n"	\
 	"   .literal_position		\n"	\
 	"5:				\n"	\
-	"   movi   %1, 2b		\n"	\
-	"   movi   %2, 0		\n"	\
-	"   movi   %0, %4		\n"	\
-	"   jx     %1			\n"	\
+	"   movi   %[tmp], 2b		\n"	\
+	"   movi   %[x], 0		\n"	\
+	"   movi   %[err], %[efault]	\n"	\
+	"   jx     %[tmp]		\n"	\
 	"   .previous			\n"	\
 	"   .section  __ex_table,\"a\"	\n"	\
 	"   .long	1b, 5b		\n"	\
 	"   .previous"				\
-	:"=r" (err), "=r" (cb), "=r" (x)	\
-	:"r" (addr), "i" (-EFAULT), "0" (err))
+	:[err] "+r"(err_), [tmp] "=r"(cb), [x] "=r"(x_)\
+	:[addr] "r"(addr_), [efault] "i"(-EFAULT))
 
 
 /*
-- 
cgit v1.2.3


From 3c00660db18371c632adae4836ed2b2d3d78ecb6 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 14 Oct 2019 13:13:36 +0100
Subject: drm/i915/execlists: Assert tasklet is locked for process_csb()

We rely on only the tasklet being allowed to call into process_csb(), so
assert that is locked when we do. As the tasklet uses a simple bitlock,
there is no strong lockdep checking so we must make do with a plain
assertion that the tasklet is running and assume that we are the
tasklet!

v2: Fixup intel_gt_sanitize() to prepare each engine for the reset so
that the locks are marked as held during the reset
v3: Check for existent function pointers for very early sanitisation.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191014121336.30137-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_gt_pm.c | 13 ++++++++++---
 drivers/gpu/drm/i915/gt/intel_lrc.c   |  7 +++++++
 drivers/gpu/drm/i915/i915_gem.h       |  5 +++++
 3 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index 87e34e0b6427..bd1bd3e00a94 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -136,11 +136,18 @@ void intel_gt_sanitize(struct intel_gt *gt, bool force)
 
 	intel_uc_sanitize(&gt->uc);
 
-	if (!reset_engines(gt) && !force)
-		return;
+	for_each_engine(engine, gt->i915, id)
+		if (engine->reset.prepare)
+			engine->reset.prepare(engine);
+
+	if (reset_engines(gt) || force) {
+		for_each_engine(engine, gt->i915, id)
+			__intel_engine_reset(engine, false);
+	}
 
 	for_each_engine(engine, gt->i915, id)
-		__intel_engine_reset(engine, false);
+		if (engine->reset.finish)
+			engine->reset.finish(engine);
 }
 
 void intel_gt_pm_disable(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index ee21307ab5fe..26b6b699193b 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1842,6 +1842,13 @@ static void process_csb(struct intel_engine_cs *engine)
 	const u8 num_entries = execlists->csb_size;
 	u8 head, tail;
 
+	/*
+	 * As we modify our execlists state tracking we require exclusive
+	 * access. Either we are inside the tasklet, or the tasklet is disabled
+	 * and we assume that is only inside the reset paths and so serialised.
+	 */
+	GEM_BUG_ON(!tasklet_is_locked(&execlists->tasklet) &&
+		   !reset_in_progress(execlists));
 	GEM_BUG_ON(USES_GUC_SUBMISSION(engine->i915));
 
 	/*
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index db20d2b0842b..f6f9675848b8 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -86,6 +86,11 @@ static inline void tasklet_lock(struct tasklet_struct *t)
 		cpu_relax();
 }
 
+static inline bool tasklet_is_locked(const struct tasklet_struct *t)
+{
+	return test_bit(TASKLET_STATE_RUN, &t->state);
+}
+
 static inline void __tasklet_disable_sync_once(struct tasklet_struct *t)
 {
 	if (!atomic_fetch_inc(&t->count))
-- 
cgit v1.2.3


From b8d49f28aa03e4678e450e588b10c0faf96e4118 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Mon, 14 Oct 2019 21:14:01 +0100
Subject: drm/i915/perf: introduce a versioning of the i915-perf uapi

Reporting this version will help application figure out what level of
the support the running kernel provides.

v2: Add i915_perf_ioctl_version() (Chris)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191014201404.22468-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_getparam.c |  4 ++++
 drivers/gpu/drm/i915/i915_perf.c     | 10 ++++++++++
 drivers/gpu/drm/i915/i915_perf.h     |  1 +
 include/uapi/drm/i915_drm.h          | 21 +++++++++++++++++++++
 4 files changed, 36 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index f4b3cbb1adce..ad33fbe90a28 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -5,6 +5,7 @@
 #include "gt/intel_engine_user.h"
 
 #include "i915_drv.h"
+#include "i915_perf.h"
 
 int i915_getparam_ioctl(struct drm_device *dev, void *data,
 			struct drm_file *file_priv)
@@ -156,6 +157,9 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 	case I915_PARAM_MMAP_GTT_COHERENT:
 		value = INTEL_INFO(i915)->has_coherent_ggtt;
 		break;
+	case I915_PARAM_PERF_REVISION:
+		value = i915_perf_ioctl_version();
+		break;
 	default:
 		DRM_DEBUG("Unknown parameter %d\n", param->param);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 366580701ba2..220e3384af30 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -4017,6 +4017,16 @@ void i915_perf_fini(struct drm_i915_private *i915)
 	perf->i915 = NULL;
 }
 
+/**
+ * i915_perf_ioctl_version - Version of the i915-perf subsystem
+ *
+ * This version number is used by userspace to detect available features.
+ */
+int i915_perf_ioctl_version(void)
+{
+	return 1;
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/i915_perf.c"
 #endif
diff --git a/drivers/gpu/drm/i915/i915_perf.h b/drivers/gpu/drm/i915/i915_perf.h
index 98e16be48a73..4ceebce72060 100644
--- a/drivers/gpu/drm/i915/i915_perf.h
+++ b/drivers/gpu/drm/i915/i915_perf.h
@@ -22,6 +22,7 @@ void i915_perf_init(struct drm_i915_private *i915);
 void i915_perf_fini(struct drm_i915_private *i915);
 void i915_perf_register(struct drm_i915_private *i915);
 void i915_perf_unregister(struct drm_i915_private *i915);
+int i915_perf_ioctl_version(void);
 
 int i915_perf_open_ioctl(struct drm_device *dev, void *data,
 			 struct drm_file *file);
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 30c542144016..c50c712b3771 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -611,6 +611,13 @@ typedef struct drm_i915_irq_wait {
  * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT.
  */
 #define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53
+
+/*
+ * Revision of the i915-perf uAPI. The value returned helps determine what
+ * i915-perf features are available. See drm_i915_perf_property_id.
+ */
+#define I915_PARAM_PERF_REVISION	54
+
 /* Must be kept compact -- no holes and well documented */
 
 typedef struct drm_i915_getparam {
@@ -1844,23 +1851,31 @@ enum drm_i915_perf_property_id {
 	 * Open the stream for a specific context handle (as used with
 	 * execbuffer2). A stream opened for a specific context this way
 	 * won't typically require root privileges.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_CTX_HANDLE = 1,
 
 	/**
 	 * A value of 1 requests the inclusion of raw OA unit reports as
 	 * part of stream samples.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_SAMPLE_OA,
 
 	/**
 	 * The value specifies which set of OA unit metrics should be
 	 * be configured, defining the contents of any OA unit reports.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_OA_METRICS_SET,
 
 	/**
 	 * The value specifies the size and layout of OA unit reports.
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_OA_FORMAT,
 
@@ -1870,6 +1885,8 @@ enum drm_i915_perf_property_id {
 	 * from this exponent as follows:
 	 *
 	 *   80ns * 2^(period_exponent + 1)
+	 *
+	 * This property is available in perf revision 1.
 	 */
 	DRM_I915_PERF_PROP_OA_EXPONENT,
 
@@ -1901,6 +1918,8 @@ struct drm_i915_perf_open_param {
  * to close and re-open a stream with the same configuration.
  *
  * It's undefined whether any pending data for the stream will be lost.
+ *
+ * This ioctl is available in perf revision 1.
  */
 #define I915_PERF_IOCTL_ENABLE	_IO('i', 0x0)
 
@@ -1908,6 +1927,8 @@ struct drm_i915_perf_open_param {
  * Disable data capture for a stream.
  *
  * It is an error to try and read a stream that is disabled.
+ *
+ * This ioctl is available in perf revision 1.
  */
 #define I915_PERF_IOCTL_DISABLE	_IO('i', 0x1)
 
-- 
cgit v1.2.3


From 4f6ccc74a85cbb4cdd373c374dc76398dc7603a1 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Mon, 14 Oct 2019 21:14:02 +0100
Subject: drm/i915: add support for perf configuration queries

Listing configurations at the moment is supported only through sysfs.
This might cause issues for applications wanting to list
configurations from a container where sysfs isn't available.

This change adds a way to query the number of configurations and their
content through the i915 query uAPI.

v2: Fix sparse warnings (Lionel)
    Add support to query configuration using uuid (Lionel)

v3: Fix some inconsistency in uapi header (Lionel)
    Fix unlocking when not locked issue (Lionel)
    Add debug messages (Lionel)

v4: Fix missing unlock (Dan)

v5: Drop lock when copying config content to userspace (Chris)

v6: Drop lock when copying config list to userspace (Chris)
    Fix deadlock when calling i915_perf_get_oa_config() under
    perf.metrics_lock (Lionel)
    Add i915_oa_config_get() (Chris)

Link: https://gitlab.freedesktop.org/mesa/mesa/merge_requests/932
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191014201404.22468-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_perf.c  |   3 +-
 drivers/gpu/drm/i915/i915_query.c | 296 ++++++++++++++++++++++++++++++++++++++
 include/uapi/drm/i915_drm.h       |  62 +++++++-
 3 files changed, 358 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 220e3384af30..109782ea30ad 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -3806,8 +3806,7 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data,
 
 	GEM_BUG_ON(*arg != oa_config->id);
 
-	sysfs_remove_group(perf->metrics_kobj,
-			   &oa_config->sysfs_metric);
+	sysfs_remove_group(perf->metrics_kobj, &oa_config->sysfs_metric);
 
 	idr_remove(&perf->metrics_idr, *arg);
 
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index abac5042da2b..c27cfef9281c 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -7,6 +7,7 @@
 #include <linux/nospec.h>
 
 #include "i915_drv.h"
+#include "i915_perf.h"
 #include "i915_query.h"
 #include <uapi/drm/i915_drm.h>
 
@@ -140,10 +141,305 @@ query_engine_info(struct drm_i915_private *i915,
 	return len;
 }
 
+static int can_copy_perf_config_registers_or_number(u32 user_n_regs,
+						    u64 user_regs_ptr,
+						    u32 kernel_n_regs)
+{
+	/*
+	 * We'll just put the number of registers, and won't copy the
+	 * register.
+	 */
+	if (user_n_regs == 0)
+		return 0;
+
+	if (user_n_regs < kernel_n_regs)
+		return -EINVAL;
+
+	if (!access_ok(u64_to_user_ptr(user_regs_ptr),
+		       2 * sizeof(u32) * kernel_n_regs))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int copy_perf_config_registers_or_number(const struct i915_oa_reg *kernel_regs,
+						u32 kernel_n_regs,
+						u64 user_regs_ptr,
+						u32 *user_n_regs)
+{
+	u32 r;
+
+	if (*user_n_regs == 0) {
+		*user_n_regs = kernel_n_regs;
+		return 0;
+	}
+
+	*user_n_regs = kernel_n_regs;
+
+	for (r = 0; r < kernel_n_regs; r++) {
+		u32 __user *user_reg_ptr =
+			u64_to_user_ptr(user_regs_ptr + sizeof(u32) * r * 2);
+		u32 __user *user_val_ptr =
+			u64_to_user_ptr(user_regs_ptr + sizeof(u32) * r * 2 +
+					sizeof(u32));
+		int ret;
+
+		ret = __put_user(i915_mmio_reg_offset(kernel_regs[r].addr),
+				 user_reg_ptr);
+		if (ret)
+			return -EFAULT;
+
+		ret = __put_user(kernel_regs[r].value, user_val_ptr);
+		if (ret)
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int query_perf_config_data(struct drm_i915_private *i915,
+				  struct drm_i915_query_item *query_item,
+				  bool use_uuid)
+{
+	struct drm_i915_query_perf_config __user *user_query_config_ptr =
+		u64_to_user_ptr(query_item->data_ptr);
+	struct drm_i915_perf_oa_config __user *user_config_ptr =
+		u64_to_user_ptr(query_item->data_ptr +
+				sizeof(struct drm_i915_query_perf_config));
+	struct drm_i915_perf_oa_config user_config;
+	struct i915_perf *perf = &i915->perf;
+	struct i915_oa_config *oa_config;
+	char uuid[UUID_STRING_LEN + 1];
+	u64 config_id;
+	u32 flags, total_size;
+	int ret;
+
+	if (!perf->i915)
+		return -ENODEV;
+
+	total_size =
+		sizeof(struct drm_i915_query_perf_config) +
+		sizeof(struct drm_i915_perf_oa_config);
+
+	if (query_item->length == 0)
+		return total_size;
+
+	if (query_item->length < total_size) {
+		DRM_DEBUG("Invalid query config data item size=%u expected=%u\n",
+			  query_item->length, total_size);
+		return -EINVAL;
+	}
+
+	if (!access_ok(user_query_config_ptr, total_size))
+		return -EFAULT;
+
+	if (__get_user(flags, &user_query_config_ptr->flags))
+		return -EFAULT;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	if (use_uuid) {
+		struct i915_oa_config *tmp;
+		int id;
+
+		BUILD_BUG_ON(sizeof(user_query_config_ptr->uuid) >= sizeof(uuid));
+
+		memset(&uuid, 0, sizeof(uuid));
+		if (__copy_from_user(uuid, user_query_config_ptr->uuid,
+				     sizeof(user_query_config_ptr->uuid)))
+			return -EFAULT;
+
+		oa_config = NULL;
+		rcu_read_lock();
+		idr_for_each_entry(&perf->metrics_idr, tmp, id) {
+			if (!strcmp(tmp->uuid, uuid)) {
+				oa_config = i915_oa_config_get(tmp);
+				break;
+			}
+		}
+		rcu_read_unlock();
+	} else {
+		if (__get_user(config_id, &user_query_config_ptr->config))
+			return -EFAULT;
+
+		oa_config = i915_perf_get_oa_config(perf, config_id);
+	}
+	if (!oa_config)
+		return -ENOENT;
+
+	if (__copy_from_user(&user_config, user_config_ptr,
+			     sizeof(user_config))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = can_copy_perf_config_registers_or_number(user_config.n_boolean_regs,
+						       user_config.boolean_regs_ptr,
+						       oa_config->b_counter_regs_len);
+	if (ret)
+		goto out;
+
+	ret = can_copy_perf_config_registers_or_number(user_config.n_flex_regs,
+						       user_config.flex_regs_ptr,
+						       oa_config->flex_regs_len);
+	if (ret)
+		goto out;
+
+	ret = can_copy_perf_config_registers_or_number(user_config.n_mux_regs,
+						       user_config.mux_regs_ptr,
+						       oa_config->mux_regs_len);
+	if (ret)
+		goto out;
+
+	ret = copy_perf_config_registers_or_number(oa_config->b_counter_regs,
+						   oa_config->b_counter_regs_len,
+						   user_config.boolean_regs_ptr,
+						   &user_config.n_boolean_regs);
+	if (ret)
+		goto out;
+
+	ret = copy_perf_config_registers_or_number(oa_config->flex_regs,
+						   oa_config->flex_regs_len,
+						   user_config.flex_regs_ptr,
+						   &user_config.n_flex_regs);
+	if (ret)
+		goto out;
+
+	ret = copy_perf_config_registers_or_number(oa_config->mux_regs,
+						   oa_config->mux_regs_len,
+						   user_config.mux_regs_ptr,
+						   &user_config.n_mux_regs);
+	if (ret)
+		goto out;
+
+	memcpy(user_config.uuid, oa_config->uuid, sizeof(user_config.uuid));
+
+	if (__copy_to_user(user_config_ptr, &user_config,
+			   sizeof(user_config))) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = total_size;
+
+out:
+	i915_oa_config_put(oa_config);
+	return ret;
+}
+
+static size_t sizeof_perf_config_list(size_t count)
+{
+	return sizeof(struct drm_i915_query_perf_config) + sizeof(u64) * count;
+}
+
+static size_t sizeof_perf_metrics(struct i915_perf *perf)
+{
+	struct i915_oa_config *tmp;
+	size_t i;
+	int id;
+
+	i = 1;
+	rcu_read_lock();
+	idr_for_each_entry(&perf->metrics_idr, tmp, id)
+		i++;
+	rcu_read_unlock();
+
+	return sizeof_perf_config_list(i);
+}
+
+static int query_perf_config_list(struct drm_i915_private *i915,
+				  struct drm_i915_query_item *query_item)
+{
+	struct drm_i915_query_perf_config __user *user_query_config_ptr =
+		u64_to_user_ptr(query_item->data_ptr);
+	struct i915_perf *perf = &i915->perf;
+	u64 *oa_config_ids = NULL;
+	int alloc, n_configs;
+	u32 flags;
+	int ret;
+
+	if (!perf->i915)
+		return -ENODEV;
+
+	if (query_item->length == 0)
+		return sizeof_perf_metrics(perf);
+
+	if (get_user(flags, &user_query_config_ptr->flags))
+		return -EFAULT;
+
+	if (flags != 0)
+		return -EINVAL;
+
+	n_configs = 1;
+	do {
+		struct i915_oa_config *tmp;
+		u64 *ids;
+		int id;
+
+		ids = krealloc(oa_config_ids,
+			       n_configs * sizeof(*oa_config_ids),
+			       GFP_KERNEL);
+		if (!ids)
+			return -ENOMEM;
+
+		alloc = fetch_and_zero(&n_configs);
+
+		ids[n_configs++] = 1ull; /* reserved for test_config */
+		rcu_read_lock();
+		idr_for_each_entry(&perf->metrics_idr, tmp, id) {
+			if (n_configs < alloc)
+				ids[n_configs] = id;
+			n_configs++;
+		}
+		rcu_read_unlock();
+
+		oa_config_ids = ids;
+	} while (n_configs > alloc);
+
+	if (query_item->length < sizeof_perf_config_list(n_configs)) {
+		DRM_DEBUG("Invalid query config list item size=%u expected=%zu\n",
+			  query_item->length,
+			  sizeof_perf_config_list(n_configs));
+		kfree(oa_config_ids);
+		return -EINVAL;
+	}
+
+	if (put_user(n_configs, &user_query_config_ptr->config)) {
+		kfree(oa_config_ids);
+		return -EFAULT;
+	}
+
+	ret = copy_to_user(user_query_config_ptr + 1,
+			   oa_config_ids,
+			   n_configs * sizeof(*oa_config_ids));
+	kfree(oa_config_ids);
+	if (ret)
+		return -EFAULT;
+
+	return sizeof_perf_config_list(n_configs);
+}
+
+static int query_perf_config(struct drm_i915_private *i915,
+			     struct drm_i915_query_item *query_item)
+{
+	switch (query_item->flags) {
+	case DRM_I915_QUERY_PERF_CONFIG_LIST:
+		return query_perf_config_list(i915, query_item);
+	case DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID:
+		return query_perf_config_data(i915, query_item, true);
+	case DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID:
+		return query_perf_config_data(i915, query_item, false);
+	default:
+		return -EINVAL;
+	}
+}
+
 static int (* const i915_query_funcs[])(struct drm_i915_private *dev_priv,
 					struct drm_i915_query_item *query_item) = {
 	query_topology_info,
 	query_engine_info,
+	query_perf_config,
 };
 
 int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index c50c712b3771..0c7b2815fbf1 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -2005,6 +2005,7 @@ struct drm_i915_query_item {
 	__u64 query_id;
 #define DRM_I915_QUERY_TOPOLOGY_INFO    1
 #define DRM_I915_QUERY_ENGINE_INFO	2
+#define DRM_I915_QUERY_PERF_CONFIG      3
 /* Must be kept compact -- no holes and well documented */
 
 	/*
@@ -2016,9 +2017,18 @@ struct drm_i915_query_item {
 	__s32 length;
 
 	/*
-	 * Unused for now. Must be cleared to zero.
+	 * When query_id == DRM_I915_QUERY_TOPOLOGY_INFO, must be 0.
+	 *
+	 * When query_id == DRM_I915_QUERY_PERF_CONFIG, must be one of the
+	 * following :
+	 *         - DRM_I915_QUERY_PERF_CONFIG_LIST
+	 *         - DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID
+	 *         - DRM_I915_QUERY_PERF_CONFIG_FOR_UUID
 	 */
 	__u32 flags;
+#define DRM_I915_QUERY_PERF_CONFIG_LIST          1
+#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2
+#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID   3
 
 	/*
 	 * Data will be written at the location pointed by data_ptr when the
@@ -2146,6 +2156,56 @@ struct drm_i915_query_engine_info {
 	struct drm_i915_engine_info engines[];
 };
 
+/*
+ * Data written by the kernel with query DRM_I915_QUERY_PERF_CONFIG.
+ */
+struct drm_i915_query_perf_config {
+	union {
+		/*
+		 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets
+		 * this fields to the number of configurations available.
+		 */
+		__u64 n_configs;
+
+		/*
+		 * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID,
+		 * i915 will use the value in this field as configuration
+		 * identifier to decide what data to write into config_ptr.
+		 */
+		__u64 config;
+
+		/*
+		 * When query_id == DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID,
+		 * i915 will use the value in this field as configuration
+		 * identifier to decide what data to write into config_ptr.
+		 *
+		 * String formatted like "%08x-%04x-%04x-%04x-%012x"
+		 */
+		char uuid[36];
+	};
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_LIST, i915 will
+	 * write an array of __u64 of configuration identifiers.
+	 *
+	 * When query_item.flags == DRM_I915_QUERY_PERF_CONFIG_DATA, i915 will
+	 * write a struct drm_i915_perf_oa_config. If the following fields of
+	 * drm_i915_perf_oa_config are set not set to 0, i915 will write into
+	 * the associated pointers the values of submitted when the
+	 * configuration was created :
+	 *
+	 *         - n_mux_regs
+	 *         - n_boolean_regs
+	 *         - n_flex_regs
+	 */
+	__u8 data[];
+};
+
 #if defined(__cplusplus)
 }
 #endif
-- 
cgit v1.2.3


From 7831e9a965ea2ca91855995d62197bc8078bb762 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 14 Oct 2019 21:14:03 +0100
Subject: drm/i915/perf: Allow dynamic reconfiguration of the OA stream

Introduce a new perf_ioctl command to change the OA configuration of the
active stream. This allows the OA stream to be reconfigured between
batch buffers, giving greater flexibility in sampling. We inject a
request into the OA context to reconfigure the stream asynchronously on
the GPU in between and ordered with execbuffer calls.

Original patch for dynamic reconfiguration by Lionel Landwerlin.

Link: https://gitlab.freedesktop.org/mesa/mesa/merge_requests/932
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191014201404.22468-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_perf.c | 46 +++++++++++++++++++++++++++++++++++++++-
 include/uapi/drm/i915_drm.h      | 13 ++++++++++++
 2 files changed, 58 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 109782ea30ad..372c91f6a28e 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -2862,6 +2862,40 @@ static void i915_perf_disable_locked(struct i915_perf_stream *stream)
 		stream->ops->disable(stream);
 }
 
+static long i915_perf_config_locked(struct i915_perf_stream *stream,
+				    unsigned long metrics_set)
+{
+	struct i915_oa_config *config;
+	long ret = stream->oa_config->id;
+
+	config = i915_perf_get_oa_config(stream->perf, metrics_set);
+	if (!config)
+		return -EINVAL;
+
+	if (config != stream->oa_config) {
+		int err;
+
+		/*
+		 * If OA is bound to a specific context, emit the
+		 * reconfiguration inline from that context. The update
+		 * will then be ordered with respect to submission on that
+		 * context.
+		 *
+		 * When set globally, we use a low priority kernel context,
+		 * so it will effectively take effect when idle.
+		 */
+		err = emit_oa_config(stream, oa_context(stream));
+		if (err == 0)
+			config = xchg(&stream->oa_config, config);
+		else
+			ret = err;
+	}
+
+	i915_oa_config_put(config);
+
+	return ret;
+}
+
 /**
  * i915_perf_ioctl - support ioctl() usage with i915 perf stream FDs
  * @stream: An i915 perf stream
@@ -2885,6 +2919,8 @@ static long i915_perf_ioctl_locked(struct i915_perf_stream *stream,
 	case I915_PERF_IOCTL_DISABLE:
 		i915_perf_disable_locked(stream);
 		return 0;
+	case I915_PERF_IOCTL_CONFIG:
+		return i915_perf_config_locked(stream, arg);
 	}
 
 	return -EINVAL;
@@ -4023,7 +4059,15 @@ void i915_perf_fini(struct drm_i915_private *i915)
  */
 int i915_perf_ioctl_version(void)
 {
-	return 1;
+	/*
+	 * 1: Initial version
+	 *   I915_PERF_IOCTL_ENABLE
+	 *   I915_PERF_IOCTL_DISABLE
+	 *
+	 * 2: Added runtime modification of OA config.
+	 *   I915_PERF_IOCTL_CONFIG
+	 */
+	return 2;
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 0c7b2815fbf1..b008ce8b4e6f 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1932,6 +1932,19 @@ struct drm_i915_perf_open_param {
  */
 #define I915_PERF_IOCTL_DISABLE	_IO('i', 0x1)
 
+/**
+ * Change metrics_set captured by a stream.
+ *
+ * If the stream is bound to a specific context, the configuration change
+ * will performed inline with that context such that it takes effect before
+ * the next execbuf submission.
+ *
+ * Returns the previously bound metrics set id, or a negative error code.
+ *
+ * This ioctl is available in perf revision 2.
+ */
+#define I915_PERF_IOCTL_CONFIG	_IO('i', 0x2)
+
 /**
  * Common to all i915 perf records
  */
-- 
cgit v1.2.3


From 9cd20ef7803cc53a00c6eb7198b3d870ac7b3766 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Mon, 14 Oct 2019 21:14:04 +0100
Subject: drm/i915/perf: allow holding preemption on filtered ctx

We would like to make use of perf in Vulkan. The Vulkan API is much
lower level than OpenGL, with applications directly exposed to the
concept of command buffers (pretty much equivalent to our batch
buffers). In Vulkan, queries are always limited in scope to a command
buffer. In OpenGL, the lack of command buffer concept meant that
queries' duration could span multiple command buffers.

With that restriction gone in Vulkan, we would like to simplify
measuring performance just by measuring the deltas between the counter
snapshots written by 2 MI_RECORD_PERF_COUNT commands, rather than the
more complex scheme we currently have in the GL driver, using 2
MI_RECORD_PERF_COUNT commands and doing some post processing on the
stream of OA reports, coming from the global OA buffer, to remove any
unrelated deltas in between the 2 MI_RECORD_PERF_COUNT.

Disabling preemption only apply to a single context with which want to
query performance counters for and is considered a privileged
operation, by default protected by CAP_SYS_ADMIN. It is possible to
enable it for a normal user by disabling the paranoid stream setting.

v2: Store preemption setting in intel_context (Chris)

v3: Use priorities to avoid preemption rather than the HW mechanism

v4: Just modify the port priority reporting function

v5: Add nopreempt flag on gem context and always flag requests
    appropriately, regarless of OA reconfiguration.

Link: https://gitlab.freedesktop.org/mesa/mesa/merge_requests/932
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191014201404.22468-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_context.h       | 18 ++++++++++++
 drivers/gpu/drm/i915/gem/i915_gem_context_types.h |  1 +
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c    |  3 ++
 drivers/gpu/drm/i915/i915_perf.c                  | 34 +++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_perf_types.h            |  8 ++++++
 include/uapi/drm/i915_drm.h                       | 11 ++++++++
 6 files changed, 72 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h
index 9234586830d1..cfe80590f0ed 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h
@@ -114,6 +114,24 @@ i915_gem_context_clear_user_engines(struct i915_gem_context *ctx)
 	clear_bit(CONTEXT_USER_ENGINES, &ctx->flags);
 }
 
+static inline bool
+i915_gem_context_nopreempt(const struct i915_gem_context *ctx)
+{
+	return test_bit(CONTEXT_NOPREEMPT, &ctx->flags);
+}
+
+static inline void
+i915_gem_context_set_nopreempt(struct i915_gem_context *ctx)
+{
+	set_bit(CONTEXT_NOPREEMPT, &ctx->flags);
+}
+
+static inline void
+i915_gem_context_clear_nopreempt(struct i915_gem_context *ctx)
+{
+	clear_bit(CONTEXT_NOPREEMPT, &ctx->flags);
+}
+
 static inline bool i915_gem_context_is_kernel(struct i915_gem_context *ctx)
 {
 	return !ctx->file_priv;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index ab8e1367dfc8..fe97b8ba4fda 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -146,6 +146,7 @@ struct i915_gem_context {
 #define CONTEXT_CLOSED			1
 #define CONTEXT_FORCE_SINGLE_SUBMISSION	2
 #define CONTEXT_USER_ENGINES		3
+#define CONTEXT_NOPREEMPT		4
 
 	struct mutex mutex;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 580c15e74a0a..98cd92320afb 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2079,6 +2079,9 @@ static int eb_submit(struct i915_execbuffer *eb)
 	if (err)
 		return err;
 
+	if (i915_gem_context_nopreempt(eb->gem_context))
+		eb->request->flags |= I915_REQUEST_NOPREEMPT;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 372c91f6a28e..54ec1c4190ac 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -344,6 +344,8 @@ static const struct i915_oa_format gen8_plus_oa_formats[I915_OA_FORMAT_MAX] = {
  * struct perf_open_properties - for validated properties given to open a stream
  * @sample_flags: `DRM_I915_PERF_PROP_SAMPLE_*` properties are tracked as flags
  * @single_context: Whether a single or all gpu contexts should be monitored
+ * @hold_preemption: Whether the preemption is disabled for the filtered
+ *                   context
  * @ctx_handle: A gem ctx handle for use with @single_context
  * @metrics_set: An ID for an OA unit metric set advertised via sysfs
  * @oa_format: An OA unit HW report format
@@ -359,6 +361,7 @@ struct perf_open_properties {
 	u32 sample_flags;
 
 	u64 single_context:1;
+	u64 hold_preemption:1;
 	u64 ctx_handle;
 
 	/* OA sampling state */
@@ -2514,6 +2517,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	if (WARN_ON(stream->oa_buffer.format_size == 0))
 		return -EINVAL;
 
+	stream->hold_preemption = props->hold_preemption;
+
 	stream->oa_buffer.format =
 		perf->oa_formats[props->oa_format].format;
 
@@ -2834,6 +2839,9 @@ static void i915_perf_enable_locked(struct i915_perf_stream *stream)
 
 	if (stream->ops->enable)
 		stream->ops->enable(stream);
+
+	if (stream->hold_preemption)
+		i915_gem_context_set_nopreempt(stream->ctx);
 }
 
 /**
@@ -2858,6 +2866,9 @@ static void i915_perf_disable_locked(struct i915_perf_stream *stream)
 	/* Allow stream->ops->disable() to refer to this */
 	stream->enabled = false;
 
+	if (stream->hold_preemption)
+		i915_gem_context_clear_nopreempt(stream->ctx);
+
 	if (stream->ops->disable)
 		stream->ops->disable(stream);
 }
@@ -3067,6 +3078,15 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 		}
 	}
 
+	if (props->hold_preemption) {
+		if (!props->single_context) {
+			DRM_DEBUG("preemption disable with no context\n");
+			ret = -EINVAL;
+			goto err;
+		}
+		privileged_op = true;
+	}
+
 	/*
 	 * On Haswell the OA unit supports clock gating off for a specific
 	 * context and in this mode there's no visibility of metrics for the
@@ -3081,7 +3101,7 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 	 * MI_REPORT_PERF_COUNT commands and so consider it a privileged op to
 	 * enable the OA unit by default.
 	 */
-	if (IS_HASWELL(perf->i915) && specific_ctx)
+	if (IS_HASWELL(perf->i915) && specific_ctx && !props->hold_preemption)
 		privileged_op = false;
 
 	/* Similar to perf's kernel.perf_paranoid_cpu sysctl option
@@ -3091,7 +3111,7 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 	 */
 	if (privileged_op &&
 	    i915_perf_stream_paranoid && !capable(CAP_SYS_ADMIN)) {
-		DRM_DEBUG("Insufficient privileges to open system-wide i915 perf stream\n");
+		DRM_DEBUG("Insufficient privileges to open i915 perf stream\n");
 		ret = -EACCES;
 		goto err_ctx;
 	}
@@ -3293,6 +3313,9 @@ static int read_properties_unlocked(struct i915_perf *perf,
 			props->oa_periodic = true;
 			props->oa_period_exponent = value;
 			break;
+		case DRM_I915_PERF_PROP_HOLD_PREEMPTION:
+			props->hold_preemption = !!value;
+			break;
 		case DRM_I915_PERF_PROP_MAX:
 			MISSING_CASE(id);
 			return -EINVAL;
@@ -4066,8 +4089,13 @@ int i915_perf_ioctl_version(void)
 	 *
 	 * 2: Added runtime modification of OA config.
 	 *   I915_PERF_IOCTL_CONFIG
+	 *
+	 * 3: Add DRM_I915_PERF_PROP_HOLD_PREEMPTION parameter to hold
+	 *    preemption on a particular context so that performance data is
+	 *    accessible from a delta of MI_RPC reports without looking at the
+	 *    OA buffer.
 	 */
-	return 2;
+	return 3;
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index d35a3c1946c3..a1f733fc905a 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -170,6 +170,14 @@ struct i915_perf_stream {
 	 */
 	bool enabled;
 
+	/**
+	 * @hold_preemption: Whether preemption is put on hold for command
+	 * submissions done on the @ctx. This is useful for some drivers that
+	 * cannot easily post process the OA buffer context to subtract delta
+	 * of performance counters not associated with @ctx.
+	 */
+	bool hold_preemption;
+
 	/**
 	 * @ops: The callbacks providing the implementation of this specific
 	 * type of configured stream.
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index b008ce8b4e6f..63d40cba97e0 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1890,6 +1890,17 @@ enum drm_i915_perf_property_id {
 	 */
 	DRM_I915_PERF_PROP_OA_EXPONENT,
 
+	/**
+	 * Specifying this property is only valid when specify a context to
+	 * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property
+	 * will hold preemption of the particular context we want to gather
+	 * performance data about. The execbuf2 submissions must include a
+	 * drm_i915_gem_execbuffer_ext_perf parameter for this to apply.
+	 *
+	 * This property is available in perf revision 3.
+	 */
+	DRM_I915_PERF_PROP_HOLD_PREEMPTION,
+
 	DRM_I915_PERF_PROP_MAX /* non-ABI */
 };
 
-- 
cgit v1.2.3


From c9c63f3c7a9081e4768291514991d3208ae8a697 Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Thu, 10 Oct 2019 20:55:35 -0700
Subject: xtensa: fix type conversion in __get_user_[no]check

__get_user_[no]check uses temporary buffer of type long to store result
of __get_user_size and do sign extension on it when necessary. This
doesn't work correctly for 64-bit data. Fix it by moving temporary
buffer/sign extension logic to __get_user_asm.

Don't do assignment of __get_user_bad result to (x) as it may not always
be integer-compatible now and issue warning even when it's going to be
optimized. Instead do (x) = 0; and call __get_user_bad separately.

Zero initialize __x in __get_user_asm and use '+' constraint for its
assembly argument, so that its value is preserved in error cases. This
may add at most 1 cycle to the fast path, but saves an instruction and
two padding bytes in the fixup section for each use of this macro and
works for both misaligned store and store exception.

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/include/asm/uaccess.h | 55 +++++++++++++++++++++------------------
 1 file changed, 29 insertions(+), 26 deletions(-)

diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index da4d35445063..3f80386f1883 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -172,19 +172,19 @@ __asm__ __volatile__(					\
 
 #define __get_user_nocheck(x, ptr, size)			\
 ({								\
-	long __gu_err, __gu_val;				\
-	__get_user_size(__gu_val, (ptr), (size), __gu_err);	\
-	(x) = (__force __typeof__(*(ptr)))__gu_val;		\
+	long __gu_err;						\
+	__get_user_size((x), (ptr), (size), __gu_err);		\
 	__gu_err;						\
 })
 
 #define __get_user_check(x, ptr, size)					\
 ({									\
-	long __gu_err = -EFAULT, __gu_val = 0;				\
+	long __gu_err = -EFAULT;					\
 	const __typeof__(*(ptr)) *__gu_addr = (ptr);			\
-	if (access_ok(__gu_addr, size))			\
-		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
-	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
+	if (access_ok(__gu_addr, size))					\
+		__get_user_size((x), __gu_addr, (size), __gu_err);	\
+	else								\
+		(x) = 0;						\
 	__gu_err;							\
 })
 
@@ -208,7 +208,7 @@ do {									\
 		}							\
 		break;							\
 	}								\
-	default: (x) = __get_user_bad();				\
+	default: (x) = 0; __get_user_bad();				\
 	}								\
 } while (0)
 
@@ -218,24 +218,27 @@ do {									\
  * __check_align_* macros still work.
  */
 #define __get_user_asm(x_, addr_, err_, align, insn, cb) \
-__asm__ __volatile__(				\
-	__check_align_##align			\
-	"1: "insn"  %[x], %[addr], 0	\n"	\
-	"2:				\n"	\
-	"   .section  .fixup,\"ax\"	\n"	\
-	"   .align 4			\n"	\
-	"   .literal_position		\n"	\
-	"5:				\n"	\
-	"   movi   %[tmp], 2b		\n"	\
-	"   movi   %[x], 0		\n"	\
-	"   movi   %[err], %[efault]	\n"	\
-	"   jx     %[tmp]		\n"	\
-	"   .previous			\n"	\
-	"   .section  __ex_table,\"a\"	\n"	\
-	"   .long	1b, 5b		\n"	\
-	"   .previous"				\
-	:[err] "+r"(err_), [tmp] "=r"(cb), [x] "=r"(x_)\
-	:[addr] "r"(addr_), [efault] "i"(-EFAULT))
+do {							\
+	u32 __x = 0;					\
+	__asm__ __volatile__(				\
+		__check_align_##align			\
+		"1: "insn"  %[x], %[addr], 0	\n"	\
+		"2:				\n"	\
+		"   .section  .fixup,\"ax\"	\n"	\
+		"   .align 4			\n"	\
+		"   .literal_position		\n"	\
+		"5:				\n"	\
+		"   movi   %[tmp], 2b		\n"	\
+		"   movi   %[err], %[efault]	\n"	\
+		"   jx     %[tmp]		\n"	\
+		"   .previous			\n"	\
+		"   .section  __ex_table,\"a\"	\n"	\
+		"   .long	1b, 5b		\n"	\
+		"   .previous"				\
+		:[err] "+r"(err_), [tmp] "=r"(cb), [x] "+r"(__x) \
+		:[addr] "r"(addr_), [efault] "i"(-EFAULT)); \
+	(x_) = (__force __typeof__(*(addr_)))__x;	\
+} while (0)
 
 
 /*
-- 
cgit v1.2.3


From 5556cfe8d994d5e7b4d50fd91597b8dc0b3a82fd Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 14 Oct 2019 14:11:40 -0700
Subject: mm, page_owner: fix off-by-one error in __set_page_owner_handle()

Patch series "followups to debug_pagealloc improvements through
page_owner", v3.

These are followups to [1] which made it to Linus meanwhile.  Patches 1
and 3 are based on Kirill's review, patch 2 on KASAN request [2].  It
would be nice if all of this made it to 5.4 with [1] already there (or
at least Patch 1).

This patch (of 3):

As noted by Kirill, commit 7e2f2a0cd17c ("mm, page_owner: record page
owner for each subpage") has introduced an off-by-one error in
__set_page_owner_handle() when looking up page_ext for subpages.  As a
result, the head page page_owner info is set twice, while for the last
tail page, it's not set at all.

Fix this and also make the code more efficient by advancing the page_ext
pointer we already have, instead of calling lookup_page_ext() for each
subpage.  Since the full size of struct page_ext is not known at compile
time, we can't use a simple page_ext++ statement, so introduce a
page_ext_next() inline function for that.

Link: http://lkml.kernel.org/r/20190930122916.14969-2-vbabka@suse.cz
Fixes: 7e2f2a0cd17c ("mm, page_owner: record page owner for each subpage")
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Kirill A. Shutemov <kirill@shutemov.name>
Reported-by: Miles Chen <miles.chen@mediatek.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Walter Wu <walter-zh.wu@mediatek.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_ext.h |  8 ++++++++
 mm/page_ext.c            | 23 +++++++++--------------
 mm/page_owner.c          | 15 +++++++--------
 3 files changed, 24 insertions(+), 22 deletions(-)

diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index 682fd465df06..5e856512bafb 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -36,6 +36,7 @@ struct page_ext {
 	unsigned long flags;
 };
 
+extern unsigned long page_ext_size;
 extern void pgdat_page_ext_init(struct pglist_data *pgdat);
 
 #ifdef CONFIG_SPARSEMEM
@@ -52,6 +53,13 @@ static inline void page_ext_init(void)
 
 struct page_ext *lookup_page_ext(const struct page *page);
 
+static inline struct page_ext *page_ext_next(struct page_ext *curr)
+{
+	void *next = curr;
+	next += page_ext_size;
+	return next;
+}
+
 #else /* !CONFIG_PAGE_EXTENSION */
 struct page_ext;
 
diff --git a/mm/page_ext.c b/mm/page_ext.c
index 5f5769c7db3b..4ade843ff588 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -67,8 +67,9 @@ static struct page_ext_operations *page_ext_ops[] = {
 #endif
 };
 
+unsigned long page_ext_size = sizeof(struct page_ext);
+
 static unsigned long total_usage;
-static unsigned long extra_mem;
 
 static bool __init invoke_need_callbacks(void)
 {
@@ -78,9 +79,8 @@ static bool __init invoke_need_callbacks(void)
 
 	for (i = 0; i < entries; i++) {
 		if (page_ext_ops[i]->need && page_ext_ops[i]->need()) {
-			page_ext_ops[i]->offset = sizeof(struct page_ext) +
-						extra_mem;
-			extra_mem += page_ext_ops[i]->size;
+			page_ext_ops[i]->offset = page_ext_size;
+			page_ext_size += page_ext_ops[i]->size;
 			need = true;
 		}
 	}
@@ -99,14 +99,9 @@ static void __init invoke_init_callbacks(void)
 	}
 }
 
-static unsigned long get_entry_size(void)
-{
-	return sizeof(struct page_ext) + extra_mem;
-}
-
 static inline struct page_ext *get_entry(void *base, unsigned long index)
 {
-	return base + get_entry_size() * index;
+	return base + page_ext_size * index;
 }
 
 #if !defined(CONFIG_SPARSEMEM)
@@ -156,7 +151,7 @@ static int __init alloc_node_page_ext(int nid)
 		!IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES))
 		nr_pages += MAX_ORDER_NR_PAGES;
 
-	table_size = get_entry_size() * nr_pages;
+	table_size = page_ext_size * nr_pages;
 
 	base = memblock_alloc_try_nid(
 			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
@@ -234,7 +229,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
 	if (section->page_ext)
 		return 0;
 
-	table_size = get_entry_size() * PAGES_PER_SECTION;
+	table_size = page_ext_size * PAGES_PER_SECTION;
 	base = alloc_page_ext(table_size, nid);
 
 	/*
@@ -254,7 +249,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
 	 * we need to apply a mask.
 	 */
 	pfn &= PAGE_SECTION_MASK;
-	section->page_ext = (void *)base - get_entry_size() * pfn;
+	section->page_ext = (void *)base - page_ext_size * pfn;
 	total_usage += table_size;
 	return 0;
 }
@@ -267,7 +262,7 @@ static void free_page_ext(void *addr)
 		struct page *page = virt_to_page(addr);
 		size_t table_size;
 
-		table_size = get_entry_size() * PAGES_PER_SECTION;
+		table_size = page_ext_size * PAGES_PER_SECTION;
 
 		BUG_ON(PageReserved(page));
 		kmemleak_free(addr);
diff --git a/mm/page_owner.c b/mm/page_owner.c
index dee931184788..d3cf5d336ccf 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -156,10 +156,10 @@ void __reset_page_owner(struct page *page, unsigned int order)
 		handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
 #endif
 
+	page_ext = lookup_page_ext(page);
+	if (unlikely(!page_ext))
+		return;
 	for (i = 0; i < (1 << order); i++) {
-		page_ext = lookup_page_ext(page + i);
-		if (unlikely(!page_ext))
-			continue;
 		__clear_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags);
 #ifdef CONFIG_DEBUG_PAGEALLOC
 		if (debug_pagealloc_enabled()) {
@@ -167,6 +167,7 @@ void __reset_page_owner(struct page *page, unsigned int order)
 			page_owner->free_handle = handle;
 		}
 #endif
+		page_ext = page_ext_next(page_ext);
 	}
 }
 
@@ -186,7 +187,7 @@ static inline void __set_page_owner_handle(struct page *page,
 		__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
 		__set_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags);
 
-		page_ext = lookup_page_ext(page + i);
+		page_ext = page_ext_next(page_ext);
 	}
 }
 
@@ -224,12 +225,10 @@ void __split_page_owner(struct page *page, unsigned int order)
 	if (unlikely(!page_ext))
 		return;
 
-	page_owner = get_page_owner(page_ext);
-	page_owner->order = 0;
-	for (i = 1; i < (1 << order); i++) {
-		page_ext = lookup_page_ext(page + i);
+	for (i = 0; i < (1 << order); i++) {
 		page_owner = get_page_owner(page_ext);
 		page_owner->order = 0;
+		page_ext = page_ext_next(page_ext);
 	}
 }
 
-- 
cgit v1.2.3


From 0fe9a448a029a11d7211fcc2ebe9023d7fd31792 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 14 Oct 2019 14:11:44 -0700
Subject: mm, page_owner: decouple freeing stack trace from debug_pagealloc

Commit 8974558f49a6 ("mm, page_owner, debug_pagealloc: save and dump
freeing stack trace") enhanced page_owner to also store freeing stack
trace, when debug_pagealloc is also enabled.  KASAN would also like to
do this [1] to improve error reports to debug e.g. UAF issues.

Kirill has suggested that the freeing stack trace saving should be also
possible to be enabled separately from KASAN or debug_pagealloc, i.e.
with an extra boot option.  Qian argued that we have enough options
already, and avoiding the extra overhead is not worth the complications
in the case of a debugging option.  Kirill noted that the extra stack
handle in struct page_owner requires 0.1% of memory.

This patch therefore enables free stack saving whenever page_owner is
enabled, regardless of whether debug_pagealloc or KASAN is also enabled.
KASAN kernels booted with page_owner=on will thus benefit from the
improved error reports.

[1] https://bugzilla.kernel.org/show_bug.cgi?id=203967

[vbabka@suse.cz: v3]
  Link: http://lkml.kernel.org/r/20191007091808.7096-3-vbabka@suse.cz
Link: http://lkml.kernel.org/r/20190930122916.14969-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Qian Cai <cai@lca.pw>
Suggested-by: Dmitry Vyukov <dvyukov@google.com>
Suggested-by: Walter Wu <walter-zh.wu@mediatek.com>
Suggested-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Suggested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Suggested-by: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/dev-tools/kasan.rst |  3 +++
 mm/page_owner.c                   | 28 +++++++---------------------
 2 files changed, 10 insertions(+), 21 deletions(-)

diff --git a/Documentation/dev-tools/kasan.rst b/Documentation/dev-tools/kasan.rst
index b72d07d70239..525296121d89 100644
--- a/Documentation/dev-tools/kasan.rst
+++ b/Documentation/dev-tools/kasan.rst
@@ -41,6 +41,9 @@ smaller binary while the latter is 1.1 - 2 times faster.
 Both KASAN modes work with both SLUB and SLAB memory allocators.
 For better bug detection and nicer reporting, enable CONFIG_STACKTRACE.
 
+To augment reports with last allocation and freeing stack of the physical page,
+it is recommended to enable also CONFIG_PAGE_OWNER and boot with page_owner=on.
+
 To disable instrumentation for specific files or directories, add a line
 similar to the following to the respective kernel Makefile:
 
diff --git a/mm/page_owner.c b/mm/page_owner.c
index d3cf5d336ccf..de1916ac3e24 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -24,12 +24,10 @@ struct page_owner {
 	short last_migrate_reason;
 	gfp_t gfp_mask;
 	depot_stack_handle_t handle;
-#ifdef CONFIG_DEBUG_PAGEALLOC
 	depot_stack_handle_t free_handle;
-#endif
 };
 
-static bool page_owner_disabled = true;
+static bool page_owner_enabled = false;
 DEFINE_STATIC_KEY_FALSE(page_owner_inited);
 
 static depot_stack_handle_t dummy_handle;
@@ -44,7 +42,7 @@ static int __init early_page_owner_param(char *buf)
 		return -EINVAL;
 
 	if (strcmp(buf, "on") == 0)
-		page_owner_disabled = false;
+		page_owner_enabled = true;
 
 	return 0;
 }
@@ -52,10 +50,7 @@ early_param("page_owner", early_page_owner_param);
 
 static bool need_page_owner(void)
 {
-	if (page_owner_disabled)
-		return false;
-
-	return true;
+	return page_owner_enabled;
 }
 
 static __always_inline depot_stack_handle_t create_dummy_stack(void)
@@ -84,7 +79,7 @@ static noinline void register_early_stack(void)
 
 static void init_page_owner(void)
 {
-	if (page_owner_disabled)
+	if (!page_owner_enabled)
 		return;
 
 	register_dummy_stack();
@@ -148,25 +143,18 @@ void __reset_page_owner(struct page *page, unsigned int order)
 {
 	int i;
 	struct page_ext *page_ext;
-#ifdef CONFIG_DEBUG_PAGEALLOC
 	depot_stack_handle_t handle = 0;
 	struct page_owner *page_owner;
 
-	if (debug_pagealloc_enabled())
-		handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
-#endif
+	handle = save_stack(GFP_NOWAIT | __GFP_NOWARN);
 
 	page_ext = lookup_page_ext(page);
 	if (unlikely(!page_ext))
 		return;
 	for (i = 0; i < (1 << order); i++) {
 		__clear_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags);
-#ifdef CONFIG_DEBUG_PAGEALLOC
-		if (debug_pagealloc_enabled()) {
-			page_owner = get_page_owner(page_ext);
-			page_owner->free_handle = handle;
-		}
-#endif
+		page_owner = get_page_owner(page_ext);
+		page_owner->free_handle = handle;
 		page_ext = page_ext_next(page_ext);
 	}
 }
@@ -450,7 +438,6 @@ void __dump_page_owner(struct page *page)
 		stack_trace_print(entries, nr_entries, 0);
 	}
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
 	handle = READ_ONCE(page_owner->free_handle);
 	if (!handle) {
 		pr_alert("page_owner free stack trace missing\n");
@@ -459,7 +446,6 @@ void __dump_page_owner(struct page *page)
 		pr_alert("page last free stack trace:\n");
 		stack_trace_print(entries, nr_entries, 0);
 	}
-#endif
 
 	if (page_owner->last_migrate_reason != -1)
 		pr_alert("page has been migrated, last migrate reason: %s\n",
-- 
cgit v1.2.3


From fdf3bf809162592b54c278b9b0e84f3e126f8844 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 14 Oct 2019 14:11:47 -0700
Subject: mm, page_owner: rename flag indicating that page is allocated

Commit 37389167a281 ("mm, page_owner: keep owner info when freeing the
page") has introduced a flag PAGE_EXT_OWNER_ACTIVE to indicate that page
is tracked as being allocated.  Kirril suggested naming it
PAGE_EXT_OWNER_ALLOCATED to make it more clear, as "active is somewhat
loaded term for a page".

Link: http://lkml.kernel.org/r/20190930122916.14969-4-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Suggested-by: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Walter Wu <walter-zh.wu@mediatek.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_ext.h |  2 +-
 mm/page_owner.c          | 12 ++++++------
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index 5e856512bafb..cfce186f0c4e 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -18,7 +18,7 @@ struct page_ext_operations {
 
 enum page_ext_flags {
 	PAGE_EXT_OWNER,
-	PAGE_EXT_OWNER_ACTIVE,
+	PAGE_EXT_OWNER_ALLOCATED,
 #if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
 	PAGE_EXT_YOUNG,
 	PAGE_EXT_IDLE,
diff --git a/mm/page_owner.c b/mm/page_owner.c
index de1916ac3e24..e327bcd0380e 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -152,7 +152,7 @@ void __reset_page_owner(struct page *page, unsigned int order)
 	if (unlikely(!page_ext))
 		return;
 	for (i = 0; i < (1 << order); i++) {
-		__clear_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags);
+		__clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
 		page_owner = get_page_owner(page_ext);
 		page_owner->free_handle = handle;
 		page_ext = page_ext_next(page_ext);
@@ -173,7 +173,7 @@ static inline void __set_page_owner_handle(struct page *page,
 		page_owner->gfp_mask = gfp_mask;
 		page_owner->last_migrate_reason = -1;
 		__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
-		__set_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags);
+		__set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags);
 
 		page_ext = page_ext_next(page_ext);
 	}
@@ -247,7 +247,7 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage)
 	 * the new page, which will be freed.
 	 */
 	__set_bit(PAGE_EXT_OWNER, &new_ext->flags);
-	__set_bit(PAGE_EXT_OWNER_ACTIVE, &new_ext->flags);
+	__set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags);
 }
 
 void pagetypeinfo_showmixedcount_print(struct seq_file *m,
@@ -307,7 +307,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 			if (unlikely(!page_ext))
 				continue;
 
-			if (!test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags))
+			if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
 				continue;
 
 			page_owner = get_page_owner(page_ext);
@@ -422,7 +422,7 @@ void __dump_page_owner(struct page *page)
 		return;
 	}
 
-	if (test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags))
+	if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
 		pr_alert("page_owner tracks the page as allocated\n");
 	else
 		pr_alert("page_owner tracks the page as freed\n");
@@ -512,7 +512,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 		 * Although we do have the info about past allocation of free
 		 * pages, it's not relevant for current memory usage.
 		 */
-		if (!test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags))
+		if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags))
 			continue;
 
 		page_owner = get_page_owner(page_ext);
-- 
cgit v1.2.3


From e4f8e513c3d353c134ad4eef9fd0bba12406c7c8 Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Mon, 14 Oct 2019 14:11:51 -0700
Subject: mm/slub: fix a deadlock in show_slab_objects()

A long time ago we fixed a similar deadlock in show_slab_objects() [1].
However, it is apparently due to the commits like 01fb58bcba63 ("slab:
remove synchronous synchronize_sched() from memcg cache deactivation
path") and 03afc0e25f7f ("slab: get_online_mems for
kmem_cache_{create,destroy,shrink}"), this kind of deadlock is back by
just reading files in /sys/kernel/slab which will generate a lockdep
splat below.

Since the "mem_hotplug_lock" here is only to obtain a stable online node
mask while racing with NUMA node hotplug, in the worst case, the results
may me miscalculated while doing NUMA node hotplug, but they shall be
corrected by later reads of the same files.

  WARNING: possible circular locking dependency detected
  ------------------------------------------------------
  cat/5224 is trying to acquire lock:
  ffff900012ac3120 (mem_hotplug_lock.rw_sem){++++}, at:
  show_slab_objects+0x94/0x3a8

  but task is already holding lock:
  b8ff009693eee398 (kn->count#45){++++}, at: kernfs_seq_start+0x44/0xf0

  which lock already depends on the new lock.

  the existing dependency chain (in reverse order) is:

  -> #2 (kn->count#45){++++}:
         lock_acquire+0x31c/0x360
         __kernfs_remove+0x290/0x490
         kernfs_remove+0x30/0x44
         sysfs_remove_dir+0x70/0x88
         kobject_del+0x50/0xb0
         sysfs_slab_unlink+0x2c/0x38
         shutdown_cache+0xa0/0xf0
         kmemcg_cache_shutdown_fn+0x1c/0x34
         kmemcg_workfn+0x44/0x64
         process_one_work+0x4f4/0x950
         worker_thread+0x390/0x4bc
         kthread+0x1cc/0x1e8
         ret_from_fork+0x10/0x18

  -> #1 (slab_mutex){+.+.}:
         lock_acquire+0x31c/0x360
         __mutex_lock_common+0x16c/0xf78
         mutex_lock_nested+0x40/0x50
         memcg_create_kmem_cache+0x38/0x16c
         memcg_kmem_cache_create_func+0x3c/0x70
         process_one_work+0x4f4/0x950
         worker_thread+0x390/0x4bc
         kthread+0x1cc/0x1e8
         ret_from_fork+0x10/0x18

  -> #0 (mem_hotplug_lock.rw_sem){++++}:
         validate_chain+0xd10/0x2bcc
         __lock_acquire+0x7f4/0xb8c
         lock_acquire+0x31c/0x360
         get_online_mems+0x54/0x150
         show_slab_objects+0x94/0x3a8
         total_objects_show+0x28/0x34
         slab_attr_show+0x38/0x54
         sysfs_kf_seq_show+0x198/0x2d4
         kernfs_seq_show+0xa4/0xcc
         seq_read+0x30c/0x8a8
         kernfs_fop_read+0xa8/0x314
         __vfs_read+0x88/0x20c
         vfs_read+0xd8/0x10c
         ksys_read+0xb0/0x120
         __arm64_sys_read+0x54/0x88
         el0_svc_handler+0x170/0x240
         el0_svc+0x8/0xc

  other info that might help us debug this:

  Chain exists of:
    mem_hotplug_lock.rw_sem --> slab_mutex --> kn->count#45

   Possible unsafe locking scenario:

         CPU0                    CPU1
         ----                    ----
    lock(kn->count#45);
                                 lock(slab_mutex);
                                 lock(kn->count#45);
    lock(mem_hotplug_lock.rw_sem);

   *** DEADLOCK ***

  3 locks held by cat/5224:
   #0: 9eff00095b14b2a0 (&p->lock){+.+.}, at: seq_read+0x4c/0x8a8
   #1: 0eff008997041480 (&of->mutex){+.+.}, at: kernfs_seq_start+0x34/0xf0
   #2: b8ff009693eee398 (kn->count#45){++++}, at:
  kernfs_seq_start+0x44/0xf0

  stack backtrace:
  Call trace:
   dump_backtrace+0x0/0x248
   show_stack+0x20/0x2c
   dump_stack+0xd0/0x140
   print_circular_bug+0x368/0x380
   check_noncircular+0x248/0x250
   validate_chain+0xd10/0x2bcc
   __lock_acquire+0x7f4/0xb8c
   lock_acquire+0x31c/0x360
   get_online_mems+0x54/0x150
   show_slab_objects+0x94/0x3a8
   total_objects_show+0x28/0x34
   slab_attr_show+0x38/0x54
   sysfs_kf_seq_show+0x198/0x2d4
   kernfs_seq_show+0xa4/0xcc
   seq_read+0x30c/0x8a8
   kernfs_fop_read+0xa8/0x314
   __vfs_read+0x88/0x20c
   vfs_read+0xd8/0x10c
   ksys_read+0xb0/0x120
   __arm64_sys_read+0x54/0x88
   el0_svc_handler+0x170/0x240
   el0_svc+0x8/0xc

I think it is important to mention that this doesn't expose the
show_slab_objects to use-after-free.  There is only a single path that
might really race here and that is the slab hotplug notifier callback
__kmem_cache_shrink (via slab_mem_going_offline_callback) but that path
doesn't really destroy kmem_cache_node data structures.

[1] http://lkml.iu.edu/hypermail/linux/kernel/1101.0/02850.html

[akpm@linux-foundation.org: add comment explaining why we don't need mem_hotplug_lock]
Link: http://lkml.kernel.org/r/1570192309-10132-1-git-send-email-cai@lca.pw
Fixes: 01fb58bcba63 ("slab: remove synchronous synchronize_sched() from memcg cache deactivation path")
Fixes: 03afc0e25f7f ("slab: get_online_mems for kmem_cache_{create,destroy,shrink}")
Signed-off-by: Qian Cai <cai@lca.pw>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/slub.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 3d63ae320d31..442f111d1e98 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4846,7 +4846,17 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 		}
 	}
 
-	get_online_mems();
+	/*
+	 * It is impossible to take "mem_hotplug_lock" here with "kernfs_mutex"
+	 * already held which will conflict with an existing lock order:
+	 *
+	 * mem_hotplug_lock->slab_mutex->kernfs_mutex
+	 *
+	 * We don't really need mem_hotplug_lock (to hold off
+	 * slab_mem_going_offline_callback) here because slab's memory hot
+	 * unplug code doesn't destroy the kmem_cache->node[] data.
+	 */
+
 #ifdef CONFIG_SLUB_DEBUG
 	if (flags & SO_ALL) {
 		struct kmem_cache_node *n;
@@ -4887,7 +4897,6 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 			x += sprintf(buf + x, " N%d=%lu",
 					node, nodes[node]);
 #endif
-	put_online_mems();
 	kfree(nodes);
 	return x + sprintf(buf + x, "\n");
 }
-- 
cgit v1.2.3


From 3c52b0af059e11a063970aed1ad143b9284a79c7 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 14 Oct 2019 14:11:54 -0700
Subject: lib/generic-radix-tree.c: add kmemleak annotations

Kmemleak is falsely reporting a leak of the slab allocation in
sctp_stream_init_ext():

  BUG: memory leak
  unreferenced object 0xffff8881114f5d80 (size 96):
   comm "syz-executor934", pid 7160, jiffies 4294993058 (age 31.950s)
   hex dump (first 32 bytes):
     00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
     00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
   backtrace:
     [<00000000ce7a1326>] kmemleak_alloc_recursive  include/linux/kmemleak.h:55 [inline]
     [<00000000ce7a1326>] slab_post_alloc_hook mm/slab.h:439 [inline]
     [<00000000ce7a1326>] slab_alloc mm/slab.c:3326 [inline]
     [<00000000ce7a1326>] kmem_cache_alloc_trace+0x13d/0x280 mm/slab.c:3553
     [<000000007abb7ac9>] kmalloc include/linux/slab.h:547 [inline]
     [<000000007abb7ac9>] kzalloc include/linux/slab.h:742 [inline]
     [<000000007abb7ac9>] sctp_stream_init_ext+0x2b/0xa0  net/sctp/stream.c:157
     [<0000000048ecb9c1>] sctp_sendmsg_to_asoc+0x946/0xa00  net/sctp/socket.c:1882
     [<000000004483ca2b>] sctp_sendmsg+0x2a8/0x990 net/sctp/socket.c:2102
     [...]

But it's freed later.  Kmemleak misses the allocation because its
pointer is stored in the generic radix tree sctp_stream::out, and the
generic radix tree uses raw pages which aren't tracked by kmemleak.

Fix this by adding the kmemleak hooks to the generic radix tree code.

Link: http://lkml.kernel.org/r/20191004065039.727564-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@google.com>
Reported-by: <syzbot+7f3b6b106be8dcdcdeec@syzkaller.appspotmail.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Cc: Vlad Yasevich <vyasevich@gmail.com>
Cc: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/generic-radix-tree.c | 32 ++++++++++++++++++++++++++------
 1 file changed, 26 insertions(+), 6 deletions(-)

diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c
index ae25e2fa2187..f25eb111c051 100644
--- a/lib/generic-radix-tree.c
+++ b/lib/generic-radix-tree.c
@@ -2,6 +2,7 @@
 #include <linux/export.h>
 #include <linux/generic-radix-tree.h>
 #include <linux/gfp.h>
+#include <linux/kmemleak.h>
 
 #define GENRADIX_ARY		(PAGE_SIZE / sizeof(struct genradix_node *))
 #define GENRADIX_ARY_SHIFT	ilog2(GENRADIX_ARY)
@@ -75,6 +76,27 @@ void *__genradix_ptr(struct __genradix *radix, size_t offset)
 }
 EXPORT_SYMBOL(__genradix_ptr);
 
+static inline struct genradix_node *genradix_alloc_node(gfp_t gfp_mask)
+{
+	struct genradix_node *node;
+
+	node = (struct genradix_node *)__get_free_page(gfp_mask|__GFP_ZERO);
+
+	/*
+	 * We're using pages (not slab allocations) directly for kernel data
+	 * structures, so we need to explicitly inform kmemleak of them in order
+	 * to avoid false positive memory leak reports.
+	 */
+	kmemleak_alloc(node, PAGE_SIZE, 1, gfp_mask);
+	return node;
+}
+
+static inline void genradix_free_node(struct genradix_node *node)
+{
+	kmemleak_free(node);
+	free_page((unsigned long)node);
+}
+
 /*
  * Returns pointer to the specified byte @offset within @radix, allocating it if
  * necessary - newly allocated slots are always zeroed out:
@@ -97,8 +119,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
 			break;
 
 		if (!new_node) {
-			new_node = (void *)
-				__get_free_page(gfp_mask|__GFP_ZERO);
+			new_node = genradix_alloc_node(gfp_mask);
 			if (!new_node)
 				return NULL;
 		}
@@ -121,8 +142,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
 		n = READ_ONCE(*p);
 		if (!n) {
 			if (!new_node) {
-				new_node = (void *)
-					__get_free_page(gfp_mask|__GFP_ZERO);
+				new_node = genradix_alloc_node(gfp_mask);
 				if (!new_node)
 					return NULL;
 			}
@@ -133,7 +153,7 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
 	}
 
 	if (new_node)
-		free_page((unsigned long) new_node);
+		genradix_free_node(new_node);
 
 	return &n->data[offset];
 }
@@ -191,7 +211,7 @@ static void genradix_free_recurse(struct genradix_node *n, unsigned level)
 				genradix_free_recurse(n->children[i], level - 1);
 	}
 
-	free_page((unsigned long) n);
+	genradix_free_node(n);
 }
 
 int __genradix_prealloc(struct __genradix *radix, size_t size,
-- 
cgit v1.2.3


From 0f181f9fbea8bc7ea2f7e13ae7f8c256b39e254c Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Mon, 14 Oct 2019 14:11:57 -0700
Subject: mm/slub.c: init_on_free=1 should wipe freelist ptr for bulk
 allocations

slab_alloc_node() already zeroed out the freelist pointer if
init_on_free was on.  Thibaut Sautereau noticed that the same needs to
be done for kmem_cache_alloc_bulk(), which performs the allocations
separately.

kmem_cache_alloc_bulk() is currently used in two places in the kernel,
so this change is unlikely to have a major performance impact.

SLAB doesn't require a similar change, as auto-initialization makes the
allocator store the freelist pointers off-slab.

Link: http://lkml.kernel.org/r/20191007091605.30530-1-glider@google.com
Fixes: 6471384af2a6 ("mm: security: introduce init_on_alloc=1 and init_on_free=1 boot options")
Signed-off-by: Alexander Potapenko <glider@google.com>
Reported-by: Thibaut Sautereau <thibaut@sautereau.fr>
Reported-by: Kees Cook <keescook@chromium.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Laura Abbott <labbott@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/slub.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 442f111d1e98..b25c807a111f 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2671,6 +2671,17 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	return p;
 }
 
+/*
+ * If the object has been wiped upon free, make sure it's fully initialized by
+ * zeroing out freelist pointer.
+ */
+static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
+						   void *obj)
+{
+	if (unlikely(slab_want_init_on_free(s)) && obj)
+		memset((void *)((char *)obj + s->offset), 0, sizeof(void *));
+}
+
 /*
  * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
  * have the fastpath folded into their functions. So no function call
@@ -2759,12 +2770,8 @@ redo:
 		prefetch_freepointer(s, next_object);
 		stat(s, ALLOC_FASTPATH);
 	}
-	/*
-	 * If the object has been wiped upon free, make sure it's fully
-	 * initialized by zeroing out freelist pointer.
-	 */
-	if (unlikely(slab_want_init_on_free(s)) && object)
-		memset(object + s->offset, 0, sizeof(void *));
+
+	maybe_wipe_obj_freeptr(s, object);
 
 	if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object)
 		memset(object, 0, s->object_size);
@@ -3178,10 +3185,13 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 				goto error;
 
 			c = this_cpu_ptr(s->cpu_slab);
+			maybe_wipe_obj_freeptr(s, p[i]);
+
 			continue; /* goto for-loop */
 		}
 		c->freelist = get_freepointer(s, object);
 		p[i] = object;
+		maybe_wipe_obj_freeptr(s, p[i]);
 	}
 	c->tid = next_tid(c->tid);
 	local_irq_enable();
-- 
cgit v1.2.3


From 03a9349ac0e095dea6ef8b5b7b14f9c23e5fabe6 Mon Sep 17 00:00:00 2001
From: Alexander Potapenko <glider@google.com>
Date: Mon, 14 Oct 2019 14:12:00 -0700
Subject: lib/test_meminit: add a kmem_cache_alloc_bulk() test

Make sure allocations from kmem_cache_alloc_bulk() and
kmem_cache_free_bulk() are properly initialized.

Link: http://lkml.kernel.org/r/20191007091605.30530-2-glider@google.com
Signed-off-by: Alexander Potapenko <glider@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Thibaut Sautereau <thibaut@sautereau.fr>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 lib/test_meminit.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/lib/test_meminit.c b/lib/test_meminit.c
index 9729f271d150..9742e5cb853a 100644
--- a/lib/test_meminit.c
+++ b/lib/test_meminit.c
@@ -297,6 +297,32 @@ out:
 	return 1;
 }
 
+static int __init do_kmem_cache_size_bulk(int size, int *total_failures)
+{
+	struct kmem_cache *c;
+	int i, iter, maxiter = 1024;
+	int num, bytes;
+	bool fail = false;
+	void *objects[10];
+
+	c = kmem_cache_create("test_cache", size, size, 0, NULL);
+	for (iter = 0; (iter < maxiter) && !fail; iter++) {
+		num = kmem_cache_alloc_bulk(c, GFP_KERNEL, ARRAY_SIZE(objects),
+					    objects);
+		for (i = 0; i < num; i++) {
+			bytes = count_nonzero_bytes(objects[i], size);
+			if (bytes)
+				fail = true;
+			fill_with_garbage(objects[i], size);
+		}
+
+		if (num)
+			kmem_cache_free_bulk(c, num, objects);
+	}
+	*total_failures += fail;
+	return 1;
+}
+
 /*
  * Test kmem_cache allocation by creating caches of different sizes, with and
  * without constructors, with and without SLAB_TYPESAFE_BY_RCU.
@@ -318,6 +344,7 @@ static int __init test_kmemcache(int *total_failures)
 			num_tests += do_kmem_cache_size(size, ctor, rcu, zero,
 							&failures);
 		}
+		num_tests += do_kmem_cache_size_bulk(size, &failures);
 	}
 	REPORT_FAILURES_IN_FN();
 	*total_failures += failures;
-- 
cgit v1.2.3


From 3f36d8669457605910cb7a40089b485949569c41 Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Mon, 14 Oct 2019 14:12:04 -0700
Subject: mm, hugetlb: allow hugepage allocations to reclaim as needed

Commit b39d0ee2632d ("mm, page_alloc: avoid expensive reclaim when
compaction may not succeed") has chnaged the allocator to bail out from
the allocator early to prevent from a potentially excessive memory
reclaim.  __GFP_RETRY_MAYFAIL is designed to retry the allocation,
reclaim and compaction loop as long as there is a reasonable chance to
make forward progress.  Neither COMPACT_SKIPPED nor COMPACT_DEFERRED at
the INIT_COMPACT_PRIORITY compaction attempt gives this feedback.

The most obvious affected subsystem is hugetlbfs which allocates huge
pages based on an admin request (or via admin configured overcommit).  I
have done a simple test which tries to allocate half of the memory for
hugetlb pages while the memory is full of a clean page cache.  This is
not an unusual situation because we try to cache as much of the memory
as possible and sysctl/sysfs interface to allocate huge pages is there
for flexibility to allocate hugetlb pages at any time.

System has 1GB of RAM and we are requesting 515MB worth of hugetlb pages
after the memory is prefilled by a clean page cache:

  root@test1:~# cat hugetlb_test.sh

  set -x
  echo 0 > /proc/sys/vm/nr_hugepages
  echo 3 > /proc/sys/vm/drop_caches
  echo 1 > /proc/sys/vm/compact_memory
  dd if=/mnt/data/file-1G of=/dev/null bs=$((4<<10))
  TS=$(date +%s)
  echo 256 > /proc/sys/vm/nr_hugepages
  cat /proc/sys/vm/nr_hugepages

The results for 2 consecutive runs on clean 5.3

  root@test1:~# sh hugetlb_test.sh
  + echo 0
  + echo 3
  + echo 1
  + dd if=/mnt/data/file-1G of=/dev/null bs=4096
  262144+0 records in
  262144+0 records out
  1073741824 bytes (1.1 GB) copied, 21.0694 s, 51.0 MB/s
  + date +%s
  + TS=1569905284
  + echo 256
  + cat /proc/sys/vm/nr_hugepages
  256
  root@test1:~# sh hugetlb_test.sh
  + echo 0
  + echo 3
  + echo 1
  + dd if=/mnt/data/file-1G of=/dev/null bs=4096
  262144+0 records in
  262144+0 records out
  1073741824 bytes (1.1 GB) copied, 21.7548 s, 49.4 MB/s
  + date +%s
  + TS=1569905311
  + echo 256
  + cat /proc/sys/vm/nr_hugepages
  256

Now with b39d0ee2632d applied

  root@test1:~# sh hugetlb_test.sh
  + echo 0
  + echo 3
  + echo 1
  + dd if=/mnt/data/file-1G of=/dev/null bs=4096
  262144+0 records in
  262144+0 records out
  1073741824 bytes (1.1 GB) copied, 20.1815 s, 53.2 MB/s
  + date +%s
  + TS=1569905516
  + echo 256
  + cat /proc/sys/vm/nr_hugepages
  11
  root@test1:~# sh hugetlb_test.sh
  + echo 0
  + echo 3
  + echo 1
  + dd if=/mnt/data/file-1G of=/dev/null bs=4096
  262144+0 records in
  262144+0 records out
  1073741824 bytes (1.1 GB) copied, 21.9485 s, 48.9 MB/s
  + date +%s
  + TS=1569905541
  + echo 256
  + cat /proc/sys/vm/nr_hugepages
  12

The success rate went down by factor of 20!

Although hugetlb allocation requests might fail and it is reasonable to
expect them to under extremely fragmented memory or when the memory is
under a heavy pressure but the above situation is not that case.

Fix the regression by reverting back to the previous behavior for
__GFP_RETRY_MAYFAIL requests and disable the beail out heuristic for
those requests.

Mike said:

: hugetlbfs allocations are commonly done via sysctl/sysfs shortly after
: boot where this may not be as much of an issue.  However, I am aware of at
: least three use cases where allocations are made after the system has been
: up and running for quite some time:
:
: - DB reconfiguration.  If sysctl/sysfs fails to get required number of
:   huge pages, system is rebooted to perform allocation after boot.
:
: - VM provisioning.  If unable get required number of huge pages, fall
:   back to base pages.
:
: - An application that does not preallocate pool, but rather allocates
:   pages at fault time for optimal NUMA locality.
:
: In all cases, I would expect b39d0ee2632d to cause regressions and
: noticable behavior changes.
:
: My quick/limited testing in
: https://lkml.kernel.org/r/3468b605-a3a9-6978-9699-57c52a90bd7e@oracle.com
: was insufficient.  It was also mentioned that if something like
: b39d0ee2632d went forward, I would like exemptions for __GFP_RETRY_MAYFAIL
: requests as in this patch.

[mhocko@suse.com: reworded changelog]
Link: http://lkml.kernel.org/r/20191007075548.12456-1-mhocko@kernel.org
Fixes: b39d0ee2632d ("mm, page_alloc: avoid expensive reclaim when compaction may not succeed")
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c0b2e0306720..ecc3dbad606b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4473,12 +4473,14 @@ retry_cpuset:
 		if (page)
 			goto got_pg;
 
-		 if (order >= pageblock_order && (gfp_mask & __GFP_IO)) {
+		 if (order >= pageblock_order && (gfp_mask & __GFP_IO) &&
+		     !(gfp_mask & __GFP_RETRY_MAYFAIL)) {
 			/*
 			 * If allocating entire pageblock(s) and compaction
 			 * failed because all zones are below low watermarks
 			 * or is prohibited because it recently failed at this
-			 * order, fail immediately.
+			 * order, fail immediately unless the allocator has
+			 * requested compaction and reclaim retry.
 			 *
 			 * Reclaim is
 			 *  - potentially very expensive because zones are far
-- 
cgit v1.2.3


From a2e9a5afce080226edbf1882d63d99bf32070e9e Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 14 Oct 2019 14:12:07 -0700
Subject: mm, compaction: fix wrong pfn handling in __reset_isolation_pfn()

Florian and Dave reported [1] a NULL pointer dereference in
__reset_isolation_pfn().  While the exact cause is unclear, staring at
the code revealed two bugs, which might be related.

One bug is that if zone starts in the middle of pageblock, block_page
might correspond to different pfn than block_pfn, and then the
pfn_valid_within() checks will check different pfn's than those accessed
via struct page.  This might result in acessing an unitialized page in
CONFIG_HOLES_IN_ZONE configs.

The other bug is that end_page refers to the first page of next
pageblock and not last page of current pageblock.  The online and valid
check is then wrong and with sections, the while (page < end_page) loop
might wander off actual struct page arrays.

[1] https://lore.kernel.org/linux-xfs/87o8z1fvqu.fsf@mid.deneb.enyo.de/

Link: http://lkml.kernel.org/r/20191008152915.24704-1-vbabka@suse.cz
Fixes: 6b0868c820ff ("mm/compaction.c: correct zone boundary handling when resetting pageblock skip hints")
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reported-by: Florian Weimer <fw@deneb.enyo.de>
Reported-by: Dave Chinner <david@fromorbit.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/compaction.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c
index ce08b39d85d4..672d3c78c6ab 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -270,14 +270,15 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
 
 	/* Ensure the start of the pageblock or zone is online and valid */
 	block_pfn = pageblock_start_pfn(pfn);
-	block_page = pfn_to_online_page(max(block_pfn, zone->zone_start_pfn));
+	block_pfn = max(block_pfn, zone->zone_start_pfn);
+	block_page = pfn_to_online_page(block_pfn);
 	if (block_page) {
 		page = block_page;
 		pfn = block_pfn;
 	}
 
 	/* Ensure the end of the pageblock or zone is online and valid */
-	block_pfn += pageblock_nr_pages;
+	block_pfn = pageblock_end_pfn(pfn) - 1;
 	block_pfn = min(block_pfn, zone_end_pfn(zone) - 1);
 	end_page = pfn_to_online_page(block_pfn);
 	if (!end_page)
@@ -303,7 +304,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
 
 		page += (1 << PAGE_ALLOC_COSTLY_ORDER);
 		pfn += (1 << PAGE_ALLOC_COSTLY_ORDER);
-	} while (page < end_page);
+	} while (page <= end_page);
 
 	return false;
 }
-- 
cgit v1.2.3


From c70d868f272befca09081190ae477c51fcbee5dd Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 14 Oct 2019 14:12:11 -0700
Subject: fs/direct-io.c: fix kernel-doc warning

Fix kernel-doc warning in fs/direct-io.c:

  fs/direct-io.c:258: warning: Excess function parameter 'offset' description in 'dio_complete'

Also, don't mark this function as having kernel-doc notation since it is
not exported.

Link: http://lkml.kernel.org/r/97908511-4328-4a56-17fe-f43a1d7aa470@infradead.org
Fixes: 6d544bb4d901 ("dio: centralize completion in dio_complete()")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Zach Brown <zab@zabbo.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/direct-io.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/direct-io.c b/fs/direct-io.c
index ae196784f487..9329ced91f1d 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -241,9 +241,8 @@ void dio_warn_stale_pagecache(struct file *filp)
 	}
 }
 
-/**
+/*
  * dio_complete() - called when all DIO BIO I/O has been completed
- * @offset: the byte offset in the file of the completed operation
  *
  * This drops i_dio_count, lets interested parties know that a DIO operation
  * has completed, and calculates the resulting return code for the operation.
-- 
cgit v1.2.3


From 8e88bfba77eec6231c6a72076c28bbb7634a0e8c Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 14 Oct 2019 14:12:14 -0700
Subject: fs/libfs.c: fix kernel-doc warning

Fix kernel-doc warning in fs/libfs.c:

  fs/libfs.c:496: warning: Excess function parameter 'available' description in 'simple_write_end'

Link: http://lkml.kernel.org/r/5fc9d70b-e377-0ec9-066a-970d49579041@infradead.org
Fixes: ad2a722f196d ("libfs: Open code simple_commit_write into only user")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Boaz Harrosh <boazh@netapp.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/libfs.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/libfs.c b/fs/libfs.c
index 540611b99b9a..1463b038ffc4 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -473,8 +473,7 @@ EXPORT_SYMBOL(simple_write_begin);
 
 /**
  * simple_write_end - .write_end helper for non-block-device FSes
- * @available: See .write_end of address_space_operations
- * @file: 		"
+ * @file: See .write_end of address_space_operations
  * @mapping: 		"
  * @pos: 		"
  * @len: 		"
-- 
cgit v1.2.3


From b46ec1da5eb7d728938c8d115c4c291c7c71a98d Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 14 Oct 2019 14:12:17 -0700
Subject: fs/fs-writeback.c: fix kernel-doc warning

Fix kernel-doc warning in fs/fs-writeback.c:

  fs/fs-writeback.c:913: warning: Excess function parameter 'nr_pages' description in 'cgroup_writeback_by_id'

Link: http://lkml.kernel.org/r/756645ac-0ce8-d47e-d30a-04d9e4923a4f@infradead.org
Fixes: d62241c7a406 ("writeback, memcg: Implement cgroup_writeback_by_id()")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fs-writeback.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e88421d9a48d..8461a6322039 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -905,7 +905,7 @@ restart:
  * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs
  * @bdi_id: target bdi id
  * @memcg_id: target memcg css id
- * @nr_pages: number of pages to write, 0 for best-effort dirty flushing
+ * @nr: number of pages to write, 0 for best-effort dirty flushing
  * @reason: reason why some writeback work initiated
  * @done: target wb_completion
  *
-- 
cgit v1.2.3


From 2a7e582f429bd983816ad366cf0f1fcf87ec6ba6 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 14 Oct 2019 14:12:20 -0700
Subject: bitmap.h: fix kernel-doc warning and typo

Fix kernel-doc warning in <linux/bitmap.h>:

  include/linux/bitmap.h:341: warning: Function parameter or member 'nbits' not described in 'bitmap_or_equal'

Also fix small typo (bitnaps).

Link: http://lkml.kernel.org/r/0729ea7a-2c0d-b2c5-7dd3-3629ee0803e2@infradead.org
Fixes: b9fa6442f704 ("cpumask: Implement cpumask_or_equal()")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bitmap.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 90528f12bdfa..29fc933df3bf 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -326,10 +326,11 @@ static inline int bitmap_equal(const unsigned long *src1,
 }
 
 /**
- * bitmap_or_equal - Check whether the or of two bitnaps is equal to a third
+ * bitmap_or_equal - Check whether the or of two bitmaps is equal to a third
  * @src1:	Pointer to bitmap 1
  * @src2:	Pointer to bitmap 2 will be or'ed with bitmap 1
  * @src3:	Pointer to bitmap 3. Compare to the result of *@src1 | *@src2
+ * @nbits:	number of bits in each of these bitmaps
  *
  * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise
  */
-- 
cgit v1.2.3


From 13bea898cd9153be91baa92de68ec32ff0b99362 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 14 Oct 2019 14:12:23 -0700
Subject: xarray.h: fix kernel-doc warning

Fix (Sphinx) kernel-doc warning in <linux/xarray.h>:

  include/linux/xarray.h:232: WARNING: Unexpected indentation.

Link: http://lkml.kernel.org/r/89ba2134-ce23-7c10-5ee1-ef83b35aa984@infradead.org
Fixes: a3e4d3f97ec8 ("XArray: Redesign xa_alloc API")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/xarray.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index 5921599b6dc4..86eecbd98e84 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -230,8 +230,8 @@ static inline int xa_err(void *entry)
  * This structure is used either directly or via the XA_LIMIT() macro
  * to communicate the range of IDs that are valid for allocation.
  * Two common ranges are predefined for you:
- *  * xa_limit_32b	- [0 - UINT_MAX]
- *  * xa_limit_31b	- [0 - INT_MAX]
+ * * xa_limit_32b	- [0 - UINT_MAX]
+ * * xa_limit_31b	- [0 - INT_MAX]
  */
 struct xa_limit {
 	u32 max;
-- 
cgit v1.2.3


From 87bf4f71af4fb162033fbd98b4252ec11a715dbe Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 14 Oct 2019 14:12:26 -0700
Subject: mm/slab.c: fix kernel-doc warning for __ksize()

Fix kernel-doc warning in mm/slab.c:

  mm/slab.c:4215: warning: Function parameter or member 'objp' not described in '__ksize'

Also add Return: documentation section for this function.

Link: http://lkml.kernel.org/r/68c9fd7d-f09e-d376-e292-c7b2bdf1774d@infradead.org
Fixes: 10d1f8cb3965 ("mm/slab: refactor common ksize KASAN logic into slab_common.c")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Marco Elver <elver@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/slab.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/slab.c b/mm/slab.c
index 9df370558e5d..66e5d8032bae 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4206,9 +4206,12 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
 
 /**
  * __ksize -- Uninstrumented ksize.
+ * @objp: pointer to the object
  *
  * Unlike ksize(), __ksize() is uninstrumented, and does not provide the same
  * safety checks as ksize() with KASAN instrumentation enabled.
+ *
+ * Return: size of the actual memory used by @objp in bytes
  */
 size_t __ksize(const void *objp)
 {
-- 
cgit v1.2.3


From 3d7fed4ad8ccb691d217efbb0f934e6a4df5ef91 Mon Sep 17 00:00:00 2001
From: Jane Chu <jane.chu@oracle.com>
Date: Mon, 14 Oct 2019 14:12:29 -0700
Subject: mm/memory-failure: poison read receives SIGKILL instead of SIGBUS if
 mmaped more than once

Mmap /dev/dax more than once, then read the poison location using
address from one of the mappings.  The other mappings due to not having
the page mapped in will cause SIGKILLs delivered to the process.
SIGKILL succeeds over SIGBUS, so user process loses the opportunity to
handle the UE.

Although one may add MAP_POPULATE to mmap(2) to work around the issue,
MAP_POPULATE makes mapping 128GB of pmem several magnitudes slower, so
isn't always an option.

Details -

  ndctl inject-error --block=10 --count=1 namespace6.0

  ./read_poison -x dax6.0 -o 5120 -m 2
  mmaped address 0x7f5bb6600000
  mmaped address 0x7f3cf3600000
  doing local read at address 0x7f3cf3601400
  Killed

Console messages in instrumented kernel -

  mce: Uncorrected hardware memory error in user-access at edbe201400
  Memory failure: tk->addr = 7f5bb6601000
  Memory failure: address edbe201: call dev_pagemap_mapping_shift
  dev_pagemap_mapping_shift: page edbe201: no PUD
  Memory failure: tk->size_shift == 0
  Memory failure: Unable to find user space address edbe201 in read_poison
  Memory failure: tk->addr = 7f3cf3601000
  Memory failure: address edbe201: call dev_pagemap_mapping_shift
  Memory failure: tk->size_shift = 21
  Memory failure: 0xedbe201: forcibly killing read_poison:22434 because of failure to unmap corrupted page
    => to deliver SIGKILL
  Memory failure: 0xedbe201: Killing read_poison:22434 due to hardware memory corruption
    => to deliver SIGBUS

Link: http://lkml.kernel.org/r/1565112345-28754-3-git-send-email-jane.chu@oracle.com
Signed-off-by: Jane Chu <jane.chu@oracle.com>
Suggested-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memory-failure.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 7ef849da8278..0ae72b6acee7 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -199,7 +199,6 @@ struct to_kill {
 	struct task_struct *tsk;
 	unsigned long addr;
 	short size_shift;
-	char addr_valid;
 };
 
 /*
@@ -324,22 +323,27 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
 		}
 	}
 	tk->addr = page_address_in_vma(p, vma);
-	tk->addr_valid = 1;
 	if (is_zone_device_page(p))
 		tk->size_shift = dev_pagemap_mapping_shift(p, vma);
 	else
 		tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT;
 
 	/*
-	 * In theory we don't have to kill when the page was
-	 * munmaped. But it could be also a mremap. Since that's
-	 * likely very rare kill anyways just out of paranoia, but use
-	 * a SIGKILL because the error is not contained anymore.
+	 * Send SIGKILL if "tk->addr == -EFAULT". Also, as
+	 * "tk->size_shift" is always non-zero for !is_zone_device_page(),
+	 * so "tk->size_shift == 0" effectively checks no mapping on
+	 * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times
+	 * to a process' address space, it's possible not all N VMAs
+	 * contain mappings for the page, but at least one VMA does.
+	 * Only deliver SIGBUS with payload derived from the VMA that
+	 * has a mapping for the page.
 	 */
-	if (tk->addr == -EFAULT || tk->size_shift == 0) {
+	if (tk->addr == -EFAULT) {
 		pr_info("Memory failure: Unable to find user space address %lx in %s\n",
 			page_to_pfn(p), tsk->comm);
-		tk->addr_valid = 0;
+	} else if (tk->size_shift == 0) {
+		kfree(tk);
+		return;
 	}
 	get_task_struct(tsk);
 	tk->tsk = tsk;
@@ -366,7 +370,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail,
 			 * make sure the process doesn't catch the
 			 * signal and then access the memory. Just kill it.
 			 */
-			if (fail || tk->addr_valid == 0) {
+			if (fail || tk->addr == -EFAULT) {
 				pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
 				       pfn, tk->tsk->comm, tk->tsk->pid);
 				do_send_sig_info(SIGKILL, SEND_SIG_PRIV,
-- 
cgit v1.2.3


From 8b39da985194aac2998dd9e3a22d00b596cebf1e Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Mon, 14 Oct 2019 15:48:19 -0700
Subject: xtensa: drop EXPORT_SYMBOL for outs*/ins*

Custom outs*/ins* implementations are long gone from the xtensa port,
remove matching EXPORT_SYMBOLs.
This fixes the following build warnings issued by modpost since commit
15bfc2348d54 ("modpost: check for static EXPORT_SYMBOL* functions"):

  WARNING: "insb" [vmlinux] is a static EXPORT_SYMBOL
  WARNING: "insw" [vmlinux] is a static EXPORT_SYMBOL
  WARNING: "insl" [vmlinux] is a static EXPORT_SYMBOL
  WARNING: "outsb" [vmlinux] is a static EXPORT_SYMBOL
  WARNING: "outsw" [vmlinux] is a static EXPORT_SYMBOL
  WARNING: "outsl" [vmlinux] is a static EXPORT_SYMBOL

Cc: stable@vger.kernel.org
Fixes: d38efc1f150f ("xtensa: adopt generic io routines")
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/kernel/xtensa_ksyms.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 04f19de46700..4092555828b1 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -119,13 +119,6 @@ EXPORT_SYMBOL(__invalidate_icache_range);
 // FIXME EXPORT_SYMBOL(screen_info);
 #endif
 
-EXPORT_SYMBOL(outsb);
-EXPORT_SYMBOL(outsw);
-EXPORT_SYMBOL(outsl);
-EXPORT_SYMBOL(insb);
-EXPORT_SYMBOL(insw);
-EXPORT_SYMBOL(insl);
-
 extern long common_exception_return;
 EXPORT_SYMBOL(common_exception_return);
 
-- 
cgit v1.2.3


From 6658f87f219427ee776c498e07c878eb5cad1be2 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 9 Oct 2019 18:23:27 +0300
Subject: gpio: merrifield: Restore use of irq_base
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

During conversion to internal IRQ chip initialization the commit
  8f86a5b4ad67 ("gpio: merrifield: Pass irqchip when adding gpiochip")
lost the irq_base assignment.

drivers/gpio/gpio-merrifield.c: In function ‘mrfld_gpio_probe’:
drivers/gpio/gpio-merrifield.c:405:17: warning: variable ‘irq_base’ set but not used [-Wunused-but-set-variable]

Assign the girq->first to it.

Fixes: 8f86a5b4ad67 ("gpio: merrifield: Pass irqchip when adding gpiochip")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-merrifield.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpio/gpio-merrifield.c b/drivers/gpio/gpio-merrifield.c
index 4f27ddfe1e2f..9596024c9161 100644
--- a/drivers/gpio/gpio-merrifield.c
+++ b/drivers/gpio/gpio-merrifield.c
@@ -455,6 +455,7 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	if (!girq->parents)
 		return -ENOMEM;
 	girq->parents[0] = pdev->irq;
+	girq->first = irq_base;
 	girq->default_type = IRQ_TYPE_NONE;
 	girq->handler = handle_bad_irq;
 
-- 
cgit v1.2.3


From 9411e3aaa6342eb730daa55cf3377463a37d2aa7 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 9 Oct 2019 17:34:44 +0300
Subject: gpiolib: Initialize the hardware with a callback

After changing the drivers to use GPIO core to add an IRQ chip
it appears that some of them requires a hardware initialization
before adding the IRQ chip.

Add an optional callback ->init_hw() to allow that drivers
to initialize hardware if needed.

This change is a part of the fix NULL pointer dereference
brought to the several drivers recently.

Cc: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c      | 22 +++++++++++++++++++++-
 include/linux/gpio/driver.h |  8 ++++++++
 2 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 5833e4f380d6..104ed299d5ea 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -86,6 +86,7 @@ static int gpiochip_add_irqchip(struct gpio_chip *gpiochip,
 				struct lock_class_key *lock_key,
 				struct lock_class_key *request_key);
 static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip);
+static int gpiochip_irqchip_init_hw(struct gpio_chip *gpiochip);
 static int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gpiochip);
 static void gpiochip_irqchip_free_valid_mask(struct gpio_chip *gpiochip);
 
@@ -1406,6 +1407,10 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 
 	machine_gpiochip_add(chip);
 
+	ret = gpiochip_irqchip_init_hw(chip);
+	if (ret)
+		goto err_remove_acpi_chip;
+
 	ret = gpiochip_irqchip_init_valid_mask(chip);
 	if (ret)
 		goto err_remove_acpi_chip;
@@ -1622,6 +1627,16 @@ static struct gpio_chip *find_chip_by_name(const char *name)
  * The following is irqchip helper code for gpiochips.
  */
 
+static int gpiochip_irqchip_init_hw(struct gpio_chip *gc)
+{
+	struct gpio_irq_chip *girq = &gc->irq;
+
+	if (!girq->init_hw)
+		return 0;
+
+	return girq->init_hw(gc);
+}
+
 static int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gc)
 {
 	struct gpio_irq_chip *girq = &gc->irq;
@@ -2446,8 +2461,13 @@ static inline int gpiochip_add_irqchip(struct gpio_chip *gpiochip,
 {
 	return 0;
 }
-
 static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip) {}
+
+static inline int gpiochip_irqchip_init_hw(struct gpio_chip *gpiochip)
+{
+	return 0;
+}
+
 static inline int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gpiochip)
 {
 	return 0;
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index f8245d67f070..5dd9c982e2cb 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -201,6 +201,14 @@ struct gpio_irq_chip {
 	 */
 	bool threaded;
 
+	/**
+	 * @init_hw: optional routine to initialize hardware before
+	 * an IRQ chip will be added. This is quite useful when
+	 * a particular driver wants to clear IRQ related registers
+	 * in order to avoid undesired events.
+	 */
+	int (*init_hw)(struct gpio_chip *chip);
+
 	/**
 	 * @init_valid_mask: optional routine to initialize @valid_mask, to be
 	 * used if not all GPIO lines are valid interrupts. Sometimes some
-- 
cgit v1.2.3


From a752fbb4b4644d09964e76c69ccd1acc700e907a Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 9 Oct 2019 18:23:27 +0300
Subject: gpio: intel-mid: Move hardware initialization to callback

The driver wants to initialize related registers before IRQ chip will be added.
That's why move it to a corresponding callback. It also fixes the NULL pointer
dereference.

Fixes: 8069e69a9792 ("gpio: intel-mid: Pass irqchip when adding gpiochip")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-intel-mid.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/gpio-intel-mid.c b/drivers/gpio/gpio-intel-mid.c
index 4d835f9089df..86a10c808ef6 100644
--- a/drivers/gpio/gpio-intel-mid.c
+++ b/drivers/gpio/gpio-intel-mid.c
@@ -293,8 +293,9 @@ static void intel_mid_irq_handler(struct irq_desc *desc)
 	chip->irq_eoi(data);
 }
 
-static void intel_mid_irq_init_hw(struct intel_mid_gpio *priv)
+static int intel_mid_irq_init_hw(struct gpio_chip *chip)
 {
+	struct intel_mid_gpio *priv = gpiochip_get_data(chip);
 	void __iomem *reg;
 	unsigned base;
 
@@ -309,6 +310,8 @@ static void intel_mid_irq_init_hw(struct intel_mid_gpio *priv)
 		reg = gpio_reg(&priv->chip, base, GEDR);
 		writel(~0, reg);
 	}
+
+	return 0;
 }
 
 static int __maybe_unused intel_gpio_runtime_idle(struct device *dev)
@@ -372,6 +375,7 @@ static int intel_gpio_probe(struct pci_dev *pdev,
 
 	girq = &priv->chip.irq;
 	girq->chip = &intel_mid_irqchip;
+	girq->init_hw = intel_mid_irq_init_hw;
 	girq->parent_handler = intel_mid_irq_handler;
 	girq->num_parents = 1;
 	girq->parents = devm_kcalloc(&pdev->dev, girq->num_parents,
@@ -384,9 +388,8 @@ static int intel_gpio_probe(struct pci_dev *pdev,
 	girq->default_type = IRQ_TYPE_NONE;
 	girq->handler = handle_simple_irq;
 
-	intel_mid_irq_init_hw(priv);
-
 	pci_set_drvdata(pdev, priv);
+
 	retval = devm_gpiochip_add_data(&pdev->dev, &priv->chip, priv);
 	if (retval) {
 		dev_err(&pdev->dev, "gpiochip_add error %d\n", retval);
-- 
cgit v1.2.3


From a33912061607979380e070af63a9adeef0a16246 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 9 Oct 2019 18:58:45 +0300
Subject: gpio: lynxpoint: Move hardware initialization to callback

The driver wants to initialize related registers before IRQ chip will be added.
That's why move it to a corresponding callback. It also fixes the NULL pointer
dereference.

Fixes: 7b1e889436a1 ("gpio: lynxpoint: Pass irqchip when adding gpiochip")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-lynxpoint.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c
index 6bb9741ad036..082cd143f430 100644
--- a/drivers/gpio/gpio-lynxpoint.c
+++ b/drivers/gpio/gpio-lynxpoint.c
@@ -294,8 +294,9 @@ static struct irq_chip lp_irqchip = {
 	.flags = IRQCHIP_SKIP_SET_WAKE,
 };
 
-static void lp_gpio_irq_init_hw(struct lp_gpio *lg)
+static int lp_gpio_irq_init_hw(struct gpio_chip *chip)
 {
+	struct lp_gpio *lg = gpiochip_get_data(chip);
 	unsigned long reg;
 	unsigned base;
 
@@ -307,6 +308,8 @@ static void lp_gpio_irq_init_hw(struct lp_gpio *lg)
 		reg = lp_gpio_reg(&lg->chip, base, LP_INT_STAT);
 		outl(0xffffffff, reg);
 	}
+
+	return 0;
 }
 
 static int lp_gpio_probe(struct platform_device *pdev)
@@ -364,6 +367,7 @@ static int lp_gpio_probe(struct platform_device *pdev)
 
 		girq = &gc->irq;
 		girq->chip = &lp_irqchip;
+		girq->init_hw = lp_gpio_irq_init_hw;
 		girq->parent_handler = lp_gpio_irq_handler;
 		girq->num_parents = 1;
 		girq->parents = devm_kcalloc(&pdev->dev, girq->num_parents,
@@ -374,8 +378,6 @@ static int lp_gpio_probe(struct platform_device *pdev)
 		girq->parents[0] = (unsigned)irq_rc->start;
 		girq->default_type = IRQ_TYPE_NONE;
 		girq->handler = handle_simple_irq;
-
-		lp_gpio_irq_init_hw(lg);
 	}
 
 	ret = devm_gpiochip_add_data(dev, gc, lg);
-- 
cgit v1.2.3


From 4c87540940cbc7ddbe9674087919c605fd5c2ef1 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 9 Oct 2019 18:23:27 +0300
Subject: gpio: merrifield: Move hardware initialization to callback

The driver wants to initialize related registers before IRQ chip will be added.
That's why move it to a corresponding callback. It also fixes the NULL pointer
dereference.

Fixes: 8f86a5b4ad67 ("gpio: merrifield: Pass irqchip when adding gpiochip")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-merrifield.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/gpio-merrifield.c b/drivers/gpio/gpio-merrifield.c
index 9596024c9161..2f1e9da81c1e 100644
--- a/drivers/gpio/gpio-merrifield.c
+++ b/drivers/gpio/gpio-merrifield.c
@@ -362,8 +362,9 @@ static void mrfld_irq_handler(struct irq_desc *desc)
 	chained_irq_exit(irqchip, desc);
 }
 
-static void mrfld_irq_init_hw(struct mrfld_gpio *priv)
+static int mrfld_irq_init_hw(struct gpio_chip *chip)
 {
+	struct mrfld_gpio *priv = gpiochip_get_data(chip);
 	void __iomem *reg;
 	unsigned int base;
 
@@ -375,6 +376,8 @@ static void mrfld_irq_init_hw(struct mrfld_gpio *priv)
 		reg = gpio_reg(&priv->chip, base, GFER);
 		writel(0, reg);
 	}
+
+	return 0;
 }
 
 static const char *mrfld_gpio_get_pinctrl_dev_name(struct mrfld_gpio *priv)
@@ -447,6 +450,7 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 
 	girq = &priv->chip.irq;
 	girq->chip = &mrfld_irqchip;
+	girq->init_hw = mrfld_irq_init_hw;
 	girq->parent_handler = mrfld_irq_handler;
 	girq->num_parents = 1;
 	girq->parents = devm_kcalloc(&pdev->dev, girq->num_parents,
@@ -459,8 +463,6 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	girq->default_type = IRQ_TYPE_NONE;
 	girq->handler = handle_bad_irq;
 
-	mrfld_irq_init_hw(priv);
-
 	pci_set_drvdata(pdev, priv);
 	retval = devm_gpiochip_add_data(&pdev->dev, &priv->chip, priv);
 	if (retval) {
-- 
cgit v1.2.3


From 75e99bf5ed8fa74bc80d693d8e0a24eeaa38202b Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 9 Oct 2019 18:59:11 +0300
Subject: gpio: lynxpoint: set default handler to be handle_bad_irq()

We switch the default handler to be handle_bad_irq() instead of
handle_simple_irq() (which was not correct anyway).

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-lynxpoint.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c
index 082cd143f430..e9e47c0d5be7 100644
--- a/drivers/gpio/gpio-lynxpoint.c
+++ b/drivers/gpio/gpio-lynxpoint.c
@@ -377,7 +377,7 @@ static int lp_gpio_probe(struct platform_device *pdev)
 			return -ENOMEM;
 		girq->parents[0] = (unsigned)irq_rc->start;
 		girq->default_type = IRQ_TYPE_NONE;
-		girq->handler = handle_simple_irq;
+		girq->handler = handle_bad_irq;
 	}
 
 	ret = devm_gpiochip_add_data(dev, gc, lg);
-- 
cgit v1.2.3


From 06b0d7fe7e5ff3ba4c7e265ef41135e8bcc232bb Mon Sep 17 00:00:00 2001
From: Igor Russkikh <Igor.Russkikh@aquantia.com>
Date: Fri, 11 Oct 2019 13:45:19 +0000
Subject: net: aquantia: temperature retrieval fix
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Chip temperature is a two byte word, colocated internally with cable
length data. We do all readouts from HW memory by dwords, thus
we should clear extra high bytes, otherwise temperature output
gets weird as soon as we attach a cable to the NIC.

Fixes: 8f8940118654 ("net: aquantia: add infrastructure to readout chip temperature")
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index da726489e3c8..7bc51f8d6f2f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -337,7 +337,7 @@ static int aq_fw2x_get_phy_temp(struct aq_hw_s *self, int *temp)
 	/* Convert PHY temperature from 1/256 degree Celsius
 	 * to 1/1000 degree Celsius.
 	 */
-	*temp = temp_res  * 1000 / 256;
+	*temp = (temp_res & 0xFFFF) * 1000 / 256;
 
 	return 0;
 }
-- 
cgit v1.2.3


From ed4d81c4b3f28ccf624f11fd66f67aec5b58859c Mon Sep 17 00:00:00 2001
From: Igor Russkikh <Igor.Russkikh@aquantia.com>
Date: Fri, 11 Oct 2019 13:45:20 +0000
Subject: net: aquantia: when cleaning hw cache it should be toggled

>From HW specification to correctly reset HW caches (this is a required
workaround when stopping the device), register bit should actually
be toggled.

It was previosly always just set. Due to the way driver stops HW this
never actually caused any issues, but it still may, so cleaning this up.

Fixes: 7a1bb49461b1 ("net: aquantia: fix potential IOMMU fault after driver unbind")
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c | 16 ++++++++++++++--
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c    | 17 +++++++++++++++--
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h    |  7 +++++--
 .../aquantia/atlantic/hw_atl/hw_atl_llh_internal.h    | 19 +++++++++++++++++++
 4 files changed, 53 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 30f7fc4c97ff..3459fadb7ddd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -968,14 +968,26 @@ static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self)
 
 static int hw_atl_b0_hw_stop(struct aq_hw_s *self)
 {
+	int err;
+	u32 val;
+
 	hw_atl_b0_hw_irq_disable(self, HW_ATL_B0_INT_MASK);
 
 	/* Invalidate Descriptor Cache to prevent writing to the cached
 	 * descriptors and to the data pointer of those descriptors
 	 */
-	hw_atl_rdm_rx_dma_desc_cache_init_set(self, 1);
+	hw_atl_rdm_rx_dma_desc_cache_init_tgl(self);
 
-	return aq_hw_err_from_flags(self);
+	err = aq_hw_err_from_flags(self);
+
+	if (err)
+		goto err_exit;
+
+	readx_poll_timeout_atomic(hw_atl_rdm_rx_dma_desc_cache_init_done_get,
+				  self, val, val == 1, 1000U, 10000U);
+
+err_exit:
+	return err;
 }
 
 static int hw_atl_b0_hw_ring_tx_stop(struct aq_hw_s *self,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index 1149812ae463..6f340695e6bd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -606,12 +606,25 @@ void hw_atl_rpb_rx_flow_ctl_mode_set(struct aq_hw_s *aq_hw, u32 rx_flow_ctl_mode
 			    HW_ATL_RPB_RX_FC_MODE_SHIFT, rx_flow_ctl_mode);
 }
 
-void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init)
+void hw_atl_rdm_rx_dma_desc_cache_init_tgl(struct aq_hw_s *aq_hw)
 {
+	u32 val;
+
+	val = aq_hw_read_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR,
+				 HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK,
+				 HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT);
+
 	aq_hw_write_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR,
 			    HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK,
 			    HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT,
-			    init);
+			    val ^ 1);
+}
+
+u32 hw_atl_rdm_rx_dma_desc_cache_init_done_get(struct aq_hw_s *aq_hw)
+{
+	return aq_hw_read_reg_bit(aq_hw, RDM_RX_DMA_DESC_CACHE_INIT_DONE_ADR,
+				  RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSK,
+				  RDM_RX_DMA_DESC_CACHE_INIT_DONE_SHIFT);
 }
 
 void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
index 0c37abbabca5..c3ee278c3747 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
@@ -313,8 +313,11 @@ void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw,
 					    u32 rx_pkt_buff_size_per_tc,
 					    u32 buffer);
 
-/* set rdm rx dma descriptor cache init */
-void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init);
+/* toggle rdm rx dma descriptor cache init */
+void hw_atl_rdm_rx_dma_desc_cache_init_tgl(struct aq_hw_s *aq_hw);
+
+/* get rdm rx dma descriptor cache init done */
+u32 hw_atl_rdm_rx_dma_desc_cache_init_done_get(struct aq_hw_s *aq_hw);
 
 /* set rx xoff enable (per tc) */
 void hw_atl_rpb_rx_xoff_en_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_xoff_en_per_tc,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
index c3febcdfa92e..35887ad89025 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
@@ -318,6 +318,25 @@
 /* default value of bitfield rdm_desc_init_i */
 #define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_DEFAULT 0x0
 
+/* rdm_desc_init_done_i bitfield definitions
+ * preprocessor definitions for the bitfield rdm_desc_init_done_i.
+ * port="pif_rdm_desc_init_done_i"
+ */
+
+/* register address for bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_ADR 0x00005a10
+/* bitmask for bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSK 0x00000001U
+/* inverted bitmask for bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_MSKN 0xfffffffe
+/* lower bit position of bitfield  rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_SHIFT 0U
+/* width of bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_WIDTH 1
+/* default value of bitfield rdm_desc_init_done_i */
+#define RDM_RX_DMA_DESC_CACHE_INIT_DONE_DEFAULT 0x0
+
+
 /* rx int_desc_wrb_en bitfield definitions
  * preprocessor definitions for the bitfield "int_desc_wrb_en".
  * port="pif_rdm_int_desc_wrb_en_i"
-- 
cgit v1.2.3


From d08b9a0a3ebdf71b0aabe576c7dd48e57e80e0f0 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Fri, 11 Oct 2019 13:45:22 +0000
Subject: net: aquantia: do not pass lro session with invalid tcp checksum

Individual descriptors on LRO TCP session should be checked
for CRC errors. It was discovered that HW recalculates
L4 checksums on LRO session and does not break it up on bad L4
csum.

Thus, driver should aggregate HW LRO L4 statuses from all individual
buffers of LRO session and drop packet if one of the buffers has bad
L4 checksum.

Fixes: f38f1ee8aeb2 ("net: aquantia: check rx csum for all packets in LRO session")
Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 3901d7994ca1..76bdbe1596d6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -313,6 +313,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 					break;
 
 				buff->is_error |= buff_->is_error;
+				buff->is_cso_err |= buff_->is_cso_err;
 
 			} while (!buff_->is_eop);
 
@@ -320,7 +321,7 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 				err = 0;
 				goto err_exit;
 			}
-			if (buff->is_error) {
+			if (buff->is_error || buff->is_cso_err) {
 				buff_ = buff;
 				do {
 					next_ = buff_->next,
-- 
cgit v1.2.3


From 9f051db566da1e8110659ab4ab188af1c2510bb4 Mon Sep 17 00:00:00 2001
From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Date: Fri, 11 Oct 2019 13:45:23 +0000
Subject: net: aquantia: correctly handle macvlan and multicast coexistence

macvlan and multicast handling is now mixed up.
The explicit issue is that macvlan interface gets broken (no traffic)
after clearing MULTICAST flag on the real interface.

We now do separate logic and consider both ALLMULTI and MULTICAST
flags on the device.

Fixes: 11ba961c9161 ("net: aquantia: Fix IFF_ALLMULTI flag functionality")
Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_main.c   |  4 +--
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    | 32 +++++++++++-----------
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  |  7 +++--
 3 files changed, 21 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index b4a0fb281e69..bb65dd39f847 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -194,9 +194,7 @@ static void aq_ndev_set_multicast_settings(struct net_device *ndev)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
 
-	aq_nic_set_packet_filter(aq_nic, ndev->flags);
-
-	aq_nic_set_multicast_list(aq_nic, ndev);
+	(void)aq_nic_set_multicast_list(aq_nic, ndev);
 }
 
 static int aq_ndo_vlan_rx_add_vid(struct net_device *ndev, __be16 proto,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 8f66e7817811..2a18439b36fb 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -631,9 +631,12 @@ err_exit:
 
 int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev)
 {
-	unsigned int packet_filter = self->packet_filter;
+	const struct aq_hw_ops *hw_ops = self->aq_hw_ops;
+	struct aq_nic_cfg_s *cfg = &self->aq_nic_cfg;
+	unsigned int packet_filter = ndev->flags;
 	struct netdev_hw_addr *ha = NULL;
 	unsigned int i = 0U;
+	int err = 0;
 
 	self->mc_list.count = 0;
 	if (netdev_uc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
@@ -641,29 +644,26 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev)
 	} else {
 		netdev_for_each_uc_addr(ha, ndev) {
 			ether_addr_copy(self->mc_list.ar[i++], ha->addr);
-
-			if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
-				break;
 		}
 	}
 
-	if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
-		packet_filter |= IFF_ALLMULTI;
-	} else {
-		netdev_for_each_mc_addr(ha, ndev) {
-			ether_addr_copy(self->mc_list.ar[i++], ha->addr);
-
-			if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
-				break;
+	cfg->is_mc_list_enabled = !!(packet_filter & IFF_MULTICAST);
+	if (cfg->is_mc_list_enabled) {
+		if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
+			packet_filter |= IFF_ALLMULTI;
+		} else {
+			netdev_for_each_mc_addr(ha, ndev) {
+				ether_addr_copy(self->mc_list.ar[i++],
+						ha->addr);
+			}
 		}
 	}
 
 	if (i > 0 && i <= AQ_HW_MULTICAST_ADDRESS_MAX) {
-		packet_filter |= IFF_MULTICAST;
 		self->mc_list.count = i;
-		self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
-						       self->mc_list.ar,
-						       self->mc_list.count);
+		err = hw_ops->hw_multicast_list_set(self->aq_hw,
+						    self->mc_list.ar,
+						    self->mc_list.count);
 	}
 	return aq_nic_set_packet_filter(self, packet_filter);
 }
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 3459fadb7ddd..2ad3fa6316ce 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -818,14 +818,15 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 				     cfg->is_vlan_force_promisc);
 
 	hw_atl_rpfl2multicast_flr_en_set(self,
-					 IS_FILTER_ENABLED(IFF_ALLMULTI), 0);
+					 IS_FILTER_ENABLED(IFF_ALLMULTI) &&
+					 IS_FILTER_ENABLED(IFF_MULTICAST), 0);
 
 	hw_atl_rpfl2_accept_all_mc_packets_set(self,
-					       IS_FILTER_ENABLED(IFF_ALLMULTI));
+					      IS_FILTER_ENABLED(IFF_ALLMULTI) &&
+					      IS_FILTER_ENABLED(IFF_MULTICAST));
 
 	hw_atl_rpfl2broadcast_en_set(self, IS_FILTER_ENABLED(IFF_BROADCAST));
 
-	cfg->is_mc_list_enabled = IS_FILTER_ENABLED(IFF_MULTICAST);
 
 	for (i = HW_ATL_B0_MAC_MIN; i < HW_ATL_B0_MAC_MAX; ++i)
 		hw_atl_rpfl2_uc_flr_en_set(self,
-- 
cgit v1.2.3


From ec52c7134b1fcef0edfc56d55072fd4f261ef198 Mon Sep 17 00:00:00 2001
From: Julien Grall <julien.grall@arm.com>
Date: Mon, 14 Oct 2019 11:21:13 +0100
Subject: arm64: cpufeature: Treat ID_AA64ZFR0_EL1 as RAZ when SVE is not
 enabled

If CONFIG_ARM64_SVE=n then we fail to report ID_AA64ZFR0_EL1 as 0 when
read by userspace, despite being required by the architecture. Although
this is theoretically a change in ABI, userspace will first check for
the presence of SVE via the HWCAP or the ID_AA64PFR0_EL1.SVE field
before probing the ID_AA64ZFR0_EL1 register. Given that these are
reported correctly for this configuration, we can safely tighten up the
current behaviour.

Ensure ID_AA64ZFR0_EL1 is treated as RAZ when CONFIG_ARM64_SVE=n.

Signed-off-by: Julien Grall <julien.grall@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Dave Martin <dave.martin@arm.com>
Fixes: 06a916feca2b ("arm64: Expose SVE2 features for userspace")
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/cpufeature.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index cabebf1a7976..80f459ad0190 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -176,11 +176,16 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
-- 
cgit v1.2.3


From 8c551f919a73c1dfa690a70a691be1da394145e8 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@soleen.com>
Date: Mon, 14 Oct 2019 10:48:24 -0400
Subject: arm64: hibernate: check pgd table allocation

There is a bug in create_safe_exec_page(), when page table is allocated
it is not checked that table is allocated successfully:

But it is dereferenced in: pgd_none(READ_ONCE(*pgdp)).  Check that
allocation was successful.

Fixes: 82869ac57b5d ("arm64: kernel: Add support for hibernate/suspend-to-disk")
Reviewed-by: James Morse <james.morse@arm.com>
Signed-off-by: Pavel Tatashin <pasha.tatashin@soleen.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/hibernate.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index e0a7fce0e01c..a96b2921d22c 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -201,6 +201,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 				 gfp_t mask)
 {
 	int rc = 0;
+	pgd_t *trans_pgd;
 	pgd_t *pgdp;
 	pud_t *pudp;
 	pmd_t *pmdp;
@@ -215,7 +216,13 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	memcpy((void *)dst, src_start, length);
 	__flush_icache_range(dst, dst + length);
 
-	pgdp = pgd_offset_raw(allocator(mask), dst_addr);
+	trans_pgd = allocator(mask);
+	if (!trans_pgd) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	pgdp = pgd_offset_raw(trans_pgd, dst_addr);
 	if (pgd_none(READ_ONCE(*pgdp))) {
 		pudp = allocator(mask);
 		if (!pudp) {
-- 
cgit v1.2.3


From e211288b72f15259da86eed6eca680758dbe9e74 Mon Sep 17 00:00:00 2001
From: Roman Kagan <rkagan@virtuozzo.com>
Date: Thu, 10 Oct 2019 12:33:05 +0000
Subject: x86/hyperv: Make vapic support x2apic mode

Now that there's Hyper-V IOMMU driver, Linux can switch to x2apic mode
when supported by the vcpus.

However, the apic access functions for Hyper-V enlightened apic assume
xapic mode only.

As a result, Linux fails to bring up secondary cpus when run as a guest
in QEMU/KVM with both hv_apic and x2apic enabled.

According to Michael Kelley, when in x2apic mode, the Hyper-V synthetic
apic MSRs behave exactly the same as the corresponding architectural
x2apic MSRs, so there's no need to override the apic accessors.  The
only exception is hv_apic_eoi_write, which benefits from lazy EOI when
available; however, its implementation works for both xapic and x2apic
modes.

Fixes: 29217a474683 ("iommu/hyper-v: Add Hyper-V stub IOMMU driver")
Fixes: 6b48cb5f8347 ("X86/Hyper-V: Enlighten APIC access")
Suggested-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Roman Kagan <rkagan@virtuozzo.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20191010123258.16919-1-rkagan@virtuozzo.com
---
 arch/x86/hyperv/hv_apic.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 5c056b8aebef..e01078e93dd3 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -260,11 +260,21 @@ void __init hv_apic_init(void)
 	}
 
 	if (ms_hyperv.hints & HV_X64_APIC_ACCESS_RECOMMENDED) {
-		pr_info("Hyper-V: Using MSR based APIC access\n");
+		pr_info("Hyper-V: Using enlightened APIC (%s mode)",
+			x2apic_enabled() ? "x2apic" : "xapic");
+		/*
+		 * With x2apic, architectural x2apic MSRs are equivalent to the
+		 * respective synthetic MSRs, so there's no need to override
+		 * the apic accessors.  The only exception is
+		 * hv_apic_eoi_write, because it benefits from lazy EOI when
+		 * available, but it works for both xapic and x2apic modes.
+		 */
 		apic_set_eoi_write(hv_apic_eoi_write);
-		apic->read      = hv_apic_read;
-		apic->write     = hv_apic_write;
-		apic->icr_write = hv_apic_icr_write;
-		apic->icr_read  = hv_apic_icr_read;
+		if (!x2apic_enabled()) {
+			apic->read      = hv_apic_read;
+			apic->write     = hv_apic_write;
+			apic->icr_write = hv_apic_icr_write;
+			apic->icr_read  = hv_apic_icr_read;
+		}
 	}
 }
-- 
cgit v1.2.3


From 7a22e03b0c02988e91003c505b34d752a51de344 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Tue, 1 Oct 2019 13:50:19 -0700
Subject: x86/apic/x2apic: Fix a NULL pointer deref when handling a dying cpu

Check that the per-cpu cluster mask pointer has been set prior to
clearing a dying cpu's bit.  The per-cpu pointer is not set until the
target cpu reaches smp_callin() during CPUHP_BRINGUP_CPU, whereas the
teardown function, x2apic_dead_cpu(), is associated with the earlier
CPUHP_X2APIC_PREPARE.  If an error occurs before the cpu is awakened,
e.g. if do_boot_cpu() itself fails, x2apic_dead_cpu() will dereference
the NULL pointer and cause a panic.

  smpboot: do_boot_cpu failed(-22) to wakeup CPU#1
  BUG: kernel NULL pointer dereference, address: 0000000000000008
  RIP: 0010:x2apic_dead_cpu+0x1a/0x30
  Call Trace:
   cpuhp_invoke_callback+0x9a/0x580
   _cpu_up+0x10d/0x140
   do_cpu_up+0x69/0xb0
   smp_init+0x63/0xa9
   kernel_init_freeable+0xd7/0x229
   ? rest_init+0xa0/0xa0
   kernel_init+0xa/0x100
   ret_from_fork+0x35/0x40

Fixes: 023a611748fd5 ("x86/apic/x2apic: Simplify cluster management")
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20191001205019.5789-1-sean.j.christopherson@intel.com
---
 arch/x86/kernel/apic/x2apic_cluster.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 45e92cba92f5..b0889c48a2ac 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -156,7 +156,8 @@ static int x2apic_dead_cpu(unsigned int dead_cpu)
 {
 	struct cluster_mask *cmsk = per_cpu(cluster_masks, dead_cpu);
 
-	cpumask_clear_cpu(dead_cpu, &cmsk->mask);
+	if (cmsk)
+		cpumask_clear_cpu(dead_cpu, &cmsk->mask);
 	free_cpumask_var(per_cpu(ipi_mask, dead_cpu));
 	return 0;
 }
-- 
cgit v1.2.3


From f9258156c73c2b2aa96731cd78bc23c4c4aac83d Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko@sntech.de>
Date: Wed, 25 Sep 2019 20:43:46 +0200
Subject: iommu/rockchip: Don't use platform_get_irq to implicitly count irqs

Till now the Rockchip iommu driver walked through the irq list via
platform_get_irq() until it encountered an ENXIO error. With the
recent change to add a central error message, this always results
in such an error for each iommu on probe and shutdown.

To not confuse people, switch to platform_count_irqs() to get the
actual number of interrupts before walking through them.

Fixes: 7723f4c5ecdb ("driver core: platform: Add an error message to platform_get_irq*()")
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Tested-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/rockchip-iommu.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c
index 26290f310f90..4dcbf68dfda4 100644
--- a/drivers/iommu/rockchip-iommu.c
+++ b/drivers/iommu/rockchip-iommu.c
@@ -100,6 +100,7 @@ struct rk_iommu {
 	struct device *dev;
 	void __iomem **bases;
 	int num_mmu;
+	int num_irq;
 	struct clk_bulk_data *clocks;
 	int num_clocks;
 	bool reset_disabled;
@@ -1136,7 +1137,7 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	struct rk_iommu *iommu;
 	struct resource *res;
 	int num_res = pdev->num_resources;
-	int err, i, irq;
+	int err, i;
 
 	iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
 	if (!iommu)
@@ -1163,6 +1164,10 @@ static int rk_iommu_probe(struct platform_device *pdev)
 	if (iommu->num_mmu == 0)
 		return PTR_ERR(iommu->bases[0]);
 
+	iommu->num_irq = platform_irq_count(pdev);
+	if (iommu->num_irq < 0)
+		return iommu->num_irq;
+
 	iommu->reset_disabled = device_property_read_bool(dev,
 					"rockchip,disable-mmu-reset");
 
@@ -1219,8 +1224,9 @@ static int rk_iommu_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(dev);
 
-	i = 0;
-	while ((irq = platform_get_irq(pdev, i++)) != -ENXIO) {
+	for (i = 0; i < iommu->num_irq; i++) {
+		int irq = platform_get_irq(pdev, i);
+
 		if (irq < 0)
 			return irq;
 
@@ -1245,10 +1251,13 @@ err_unprepare_clocks:
 static void rk_iommu_shutdown(struct platform_device *pdev)
 {
 	struct rk_iommu *iommu = platform_get_drvdata(pdev);
-	int i = 0, irq;
+	int i;
+
+	for (i = 0; i < iommu->num_irq; i++) {
+		int irq = platform_get_irq(pdev, i);
 
-	while ((irq = platform_get_irq(pdev, i++)) != -ENXIO)
 		devm_free_irq(iommu->dev, irq, iommu);
+	}
 
 	pm_runtime_force_suspend(&pdev->dev);
 }
-- 
cgit v1.2.3


From 56184a20a80037c39fccc78b683cf593a2db4c5f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 15 Oct 2019 10:39:15 +0100
Subject: drm/i915: Drop obj.page_pin_count after a failed vma->set_pages()

Before we attempt to set_pages on the vma, we claim a
obj.pages_pin_count for it. If we subsequently fail to set the pages on
the vma, we need to drop our pinning before returning the error.

Reported-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015093915.3995-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_vma.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 9fdcd4e2c799..7d936254bde7 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -802,8 +802,11 @@ static int vma_get_pages(struct i915_vma *vma)
 		}
 
 		err = vma->ops->set_pages(vma);
-		if (err)
+		if (err) {
+			if (vma->obj)
+				i915_gem_object_unpin_pages(vma->obj);
 			goto unlock;
+		}
 	}
 	atomic_inc(&vma->pages_count);
 
-- 
cgit v1.2.3


From 454a325a9768aa9202843f2a4aea7bef94495d94 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 15 Oct 2019 11:01:55 +0100
Subject: drm/i915: Remove leftover vma->obj->pages_pin_count on insert/remove

We now do the page pin count upfront in vma_get_pages/vma_put_pages, so
that we do the allocations before we enter the vm->mutex. Our vma
page references we are tracked in vma->pages_count and the extra
obj->pages_pin_count being performed later in i915_vma_insert and
i915_vma_remove is redundant, and worse throws off the shrinker's logic
on when it can free an object by unbinding it.

Reported-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reported-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015100155.10376-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_vma.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 7d936254bde7..e90c4d0af8fd 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -703,7 +703,6 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	list_add_tail(&vma->vm_link, &vma->vm->bound_list);
 
 	if (vma->obj) {
-		atomic_inc(&vma->obj->mm.pages_pin_count);
 		atomic_inc(&vma->obj->bind_count);
 		assert_bind_count(vma->obj);
 	}
@@ -726,14 +725,12 @@ i915_vma_remove(struct i915_vma *vma)
 	if (vma->obj) {
 		struct drm_i915_gem_object *obj = vma->obj;
 
-		atomic_dec(&obj->bind_count);
-
 		/*
 		 * And finally now the object is completely decoupled from this
 		 * vma, we can drop its hold on the backing storage and allow
 		 * it to be reaped by the shrinker.
 		 */
-		i915_gem_object_unpin_pages(obj);
+		atomic_dec(&obj->bind_count);
 		assert_bind_count(obj);
 	}
 
-- 
cgit v1.2.3


From 8b390c15818ccf34a4e44e18ed590cb06bbbcb88 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 15 Oct 2019 10:32:04 +0100
Subject: drm/i915/execlists: Clear semaphore immediately upon ELSP promotion

There is no significance to our delay before clearing the semaphore the
engine is waiting on, so release it as soon as we acknowledge the CS
update following our preemption request. This should allow the GPU to
resume work earlier, if it was stuck on the semaphore at the end of a
request.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015093204.25693-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 26b6b699193b..1e9e2cc168f7 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1910,6 +1910,9 @@ static void process_csb(struct intel_engine_cs *engine)
 		else
 			promote = gen8_csb_parse(execlists, buf + 2 * head);
 		if (promote) {
+			if (!inject_preempt_hang(execlists))
+				ring_set_paused(engine, 0);
+
 			/* cancel old inflight, prepare for switch */
 			trace_ports(execlists, "preempted", execlists->active);
 			while (*execlists->active)
@@ -1926,9 +1929,6 @@ static void process_csb(struct intel_engine_cs *engine)
 			if (enable_timeslice(execlists))
 				mod_timer(&execlists->timer, jiffies + 1);
 
-			if (!inject_preempt_hang(execlists))
-				ring_set_paused(engine, 0);
-
 			WRITE_ONCE(execlists->pending[0], NULL);
 		} else {
 			GEM_BUG_ON(!*execlists->active);
-- 
cgit v1.2.3


From ec37d4e999041ae8eb507d8d444a28b338670336 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 1 Oct 2019 20:06:22 +0200
Subject: iommu/ipmmu-vmsa: Only call platform_get_irq() when interrupt is
 mandatory

As platform_get_irq() now prints an error when the interrupt does not
exist, calling it gratuitously causes scary messages like:

    ipmmu-vmsa e6740000.mmu: IRQ index 0 not found

Fix this by moving the call to platform_get_irq() down, where the
existence of the interrupt is mandatory.

Fixes: 7723f4c5ecdb8d83 ("driver core: platform: Add an error message to platform_get_irq*()")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/ipmmu-vmsa.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 9da8309f7170..237103465b82 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -1086,8 +1086,6 @@ static int ipmmu_probe(struct platform_device *pdev)
 
 	mmu->num_ctx = min(IPMMU_CTX_MAX, mmu->features->number_of_contexts);
 
-	irq = platform_get_irq(pdev, 0);
-
 	/*
 	 * Determine if this IPMMU instance is a root device by checking for
 	 * the lack of has_cache_leaf_nodes flag or renesas,ipmmu-main property.
@@ -1106,6 +1104,7 @@ static int ipmmu_probe(struct platform_device *pdev)
 
 	/* Root devices have mandatory IRQs */
 	if (ipmmu_is_root(mmu)) {
+		irq = platform_get_irq(pdev, 0);
 		if (irq < 0) {
 			dev_err(&pdev->dev, "no IRQ found\n");
 			return irq;
-- 
cgit v1.2.3


From ec21f17a9437e11bb29e5fa375aa31b472793c15 Mon Sep 17 00:00:00 2001
From: "Suthikulpanit, Suravee" <Suravee.Suthikulpanit@amd.com>
Date: Mon, 14 Oct 2019 20:06:05 +0000
Subject: iommu/amd: Fix incorrect PASID decoding from event log

IOMMU Event Log encodes 20-bit PASID for events:
    ILLEGAL_DEV_TABLE_ENTRY
    IO_PAGE_FAULT
    PAGE_TAB_HARDWARE_ERROR
    INVALID_DEVICE_REQUEST
as:
    PASID[15:0]  = bit 47:32
    PASID[19:16] = bit 19:16

Note that INVALID_PPR_REQUEST event has different encoding
from the rest of the events as the following:
    PASID[15:0]  = bit 31:16
    PASID[19:16] = bit 45:42

So, fixes the decoding logic.

Fixes: d64c0486ed50 ("iommu/amd: Update the PASID information printed to the system log")
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Gary R Hook <gary.hook@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd_iommu.c       | 5 +++--
 drivers/iommu/amd_iommu_types.h | 4 ++--
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 2369b8af81f3..bcd89ea50a8b 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -583,7 +583,8 @@ static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 retry:
 	type    = (event[1] >> EVENT_TYPE_SHIFT)  & EVENT_TYPE_MASK;
 	devid   = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
-	pasid   = PPR_PASID(*(u64 *)&event[0]);
+	pasid   = (event[0] & EVENT_DOMID_MASK_HI) |
+		  (event[1] & EVENT_DOMID_MASK_LO);
 	flags   = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
 	address = (u64)(((u64)event[3]) << 32) | event[2];
 
@@ -616,7 +617,7 @@ retry:
 			address, flags);
 		break;
 	case EVENT_TYPE_PAGE_TAB_ERR:
-		dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
+		dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x pasid=0x%04x address=0x%llx flags=0x%04x]\n",
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			pasid, address, flags);
 		break;
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index c9c1612d52e0..17bd5a349119 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -130,8 +130,8 @@
 #define EVENT_TYPE_INV_PPR_REQ	0x9
 #define EVENT_DEVID_MASK	0xffff
 #define EVENT_DEVID_SHIFT	0
-#define EVENT_DOMID_MASK	0xffff
-#define EVENT_DOMID_SHIFT	0
+#define EVENT_DOMID_MASK_LO	0xffff
+#define EVENT_DOMID_MASK_HI	0xf0000
 #define EVENT_FLAGS_MASK	0xfff
 #define EVENT_FLAGS_SHIFT	0x10
 
-- 
cgit v1.2.3


From bb71fb0072f14611f6c5bb5a1a5bf8ac942fa1c3 Mon Sep 17 00:00:00 2001
From: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Date: Thu, 19 Sep 2019 22:53:04 +0300
Subject: drm/i915/dp: Extend program of VSC Header and DB for Colorimetry
 Format
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It refactors and renames a function which handled vsc sdp header and data
block setup for supporting colorimetry format.
Function intel_dp_setup_vsc_sdp handles vsc sdp header and data block
setup for pixel encoding / colorimetry format.
In order to use colorspace information of a connector, it adds an argument
of drm_connector_state type.

Setup VSC header and data block in function intel_dp_setup_vsc_sdp for
pixel encoding / colorimetry format as per dp 1.4a spec, section 2.2.5.7.1,
table 2-119: VSC SDP Header Bytes, section 2.2.5.7.5,
table 2-120: VSC SDP Payload for DB16 through DB18.

Signed-off-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919195311.13972-2-gwan-gyeong.mun@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c     |  2 +-
 drivers/gpu/drm/i915/display/intel_display.h |  2 -
 drivers/gpu/drm/i915/display/intel_dp.c      | 68 +++++++++++++++++++++++-----
 drivers/gpu/drm/i915/display/intel_dp.h      |  3 ++
 4 files changed, 60 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 6c1315c7bcde..079dae20deb5 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3851,7 +3851,7 @@ static void intel_enable_ddi_dp(struct intel_encoder *encoder,
 
 	intel_edp_backlight_on(crtc_state, conn_state);
 	intel_psr_enable(intel_dp, crtc_state);
-	intel_dp_ycbcr_420_enable(intel_dp, crtc_state);
+	intel_dp_vsc_enable(intel_dp, crtc_state, conn_state);
 	intel_edp_drrs_enable(intel_dp, crtc_state);
 
 	if (crtc_state->has_audio)
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index bc2cf4bec0e8..bed203ec1df8 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -539,8 +539,6 @@ void intel_dp_get_m_n(struct intel_crtc *crtc,
 		      struct intel_crtc_state *pipe_config);
 void intel_dp_set_m_n(const struct intel_crtc_state *crtc_state,
 		      enum link_m_n_set m_n);
-void intel_dp_ycbcr_420_enable(struct intel_dp *intel_dp,
-			       const struct intel_crtc_state *crtc_state);
 int intel_dotclock_calculate(int link_freq, const struct intel_link_m_n *m_n);
 bool bxt_find_best_dpll(struct intel_crtc_state *crtc_state,
 			struct dpll *best_clock);
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 6594f2af1257..7aa027881ff3 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4474,8 +4474,9 @@ intel_dp_get_sink_irq_esi(struct intel_dp *intel_dp, u8 *sink_irq_vector)
 }
 
 static void
-intel_pixel_encoding_setup_vsc(struct intel_dp *intel_dp,
-			       const struct intel_crtc_state *crtc_state)
+intel_dp_setup_vsc_sdp(struct intel_dp *intel_dp,
+		       const struct intel_crtc_state *crtc_state,
+		       const struct drm_connector_state *conn_state)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct dp_sdp vsc_sdp = {};
@@ -4496,13 +4497,55 @@ intel_pixel_encoding_setup_vsc(struct intel_dp *intel_dp,
 	 */
 	vsc_sdp.sdp_header.HB3 = 0x13;
 
-	/*
-	 * YCbCr 420 = 3h DB16[7:4] ITU-R BT.601 = 0h, ITU-R BT.709 = 1h
-	 * DB16[3:0] DP 1.4a spec, Table 2-120
-	 */
-	vsc_sdp.db[16] = 0x3 << 4; /* 0x3 << 4 , YCbCr 420*/
-	/* RGB->YCBCR color conversion uses the BT.709 color space. */
-	vsc_sdp.db[16] |= 0x1; /* 0x1, ITU-R BT.709 */
+	/* DP 1.4a spec, Table 2-120 */
+	switch (crtc_state->output_format) {
+	case INTEL_OUTPUT_FORMAT_YCBCR444:
+		vsc_sdp.db[16] = 0x1 << 4; /* YCbCr 444 : DB16[7:4] = 1h */
+		break;
+	case INTEL_OUTPUT_FORMAT_YCBCR420:
+		vsc_sdp.db[16] = 0x3 << 4; /* YCbCr 420 : DB16[7:4] = 3h */
+		break;
+	case INTEL_OUTPUT_FORMAT_RGB:
+	default:
+		/* RGB: DB16[7:4] = 0h */
+		break;
+	}
+
+	switch (conn_state->colorspace) {
+	case DRM_MODE_COLORIMETRY_BT709_YCC:
+		vsc_sdp.db[16] |= 0x1;
+		break;
+	case DRM_MODE_COLORIMETRY_XVYCC_601:
+		vsc_sdp.db[16] |= 0x2;
+		break;
+	case DRM_MODE_COLORIMETRY_XVYCC_709:
+		vsc_sdp.db[16] |= 0x3;
+		break;
+	case DRM_MODE_COLORIMETRY_SYCC_601:
+		vsc_sdp.db[16] |= 0x4;
+		break;
+	case DRM_MODE_COLORIMETRY_OPYCC_601:
+		vsc_sdp.db[16] |= 0x5;
+		break;
+	case DRM_MODE_COLORIMETRY_BT2020_CYCC:
+	case DRM_MODE_COLORIMETRY_BT2020_RGB:
+		vsc_sdp.db[16] |= 0x6;
+		break;
+	case DRM_MODE_COLORIMETRY_BT2020_YCC:
+		vsc_sdp.db[16] |= 0x7;
+		break;
+	case DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65:
+	case DRM_MODE_COLORIMETRY_DCI_P3_RGB_THEATER:
+		vsc_sdp.db[16] |= 0x4; /* DCI-P3 (SMPTE RP 431-2) */
+		break;
+	default:
+		/* sRGB (IEC 61966-2-1) / ITU-R BT.601: DB16[0:3] = 0h */
+
+		/* RGB->YCBCR color conversion uses the BT.709 color space. */
+		if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420)
+			vsc_sdp.db[16] |= 0x1; /* 0x1, ITU-R BT.709 */
+		break;
+	}
 
 	/*
 	 * For pixel encoding formats YCbCr444, YCbCr422, YCbCr420, and Y Only,
@@ -4554,13 +4597,14 @@ intel_pixel_encoding_setup_vsc(struct intel_dp *intel_dp,
 			crtc_state, DP_SDP_VSC, &vsc_sdp, sizeof(vsc_sdp));
 }
 
-void intel_dp_ycbcr_420_enable(struct intel_dp *intel_dp,
-			       const struct intel_crtc_state *crtc_state)
+void intel_dp_vsc_enable(struct intel_dp *intel_dp,
+			 const struct intel_crtc_state *crtc_state,
+			 const struct drm_connector_state *conn_state)
 {
 	if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_YCBCR420)
 		return;
 
-	intel_pixel_encoding_setup_vsc(intel_dp, crtc_state);
+	intel_dp_setup_vsc_sdp(intel_dp, crtc_state, conn_state);
 }
 
 static u8 intel_dp_autotest_link_training(struct intel_dp *intel_dp)
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index a194b5b6da05..ce2b87f51a30 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -108,6 +108,9 @@ bool intel_dp_read_dpcd(struct intel_dp *intel_dp);
 bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp);
 int intel_dp_link_required(int pixel_clock, int bpp);
 int intel_dp_max_data_rate(int max_link_clock, int max_lanes);
+void intel_dp_vsc_enable(struct intel_dp *intel_dp,
+			 const struct intel_crtc_state *crtc_state,
+			 const struct drm_connector_state *conn_state);
 bool intel_digital_port_connected(struct intel_encoder *encoder);
 
 static inline unsigned int intel_dp_unused_lane_mask(int lane_count)
-- 
cgit v1.2.3


From 0c06fa156006c746bbde36961119143596dd1425 Mon Sep 17 00:00:00 2001
From: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Date: Thu, 19 Sep 2019 22:53:05 +0300
Subject: drm/i915/dp: Add support of BT.2020 Colorimetry to DP MSA
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When BT.2020 Colorimetry output is used for DP, we should program BT.2020
Colorimetry to MSA and VSC SDP. In order to handle colorspace of
drm_connector_state, it moves a calling of intel_ddi_set_pipe_settings()
function into intel_ddi_pre_enable_dp(). And it also rename
intel_ddi_set_pipe_settings() to intel_ddi_set_dp_msa().

As per DP 1.4a spec section 2.2.4 [MSA Data Transport]
The MSA data that the DP Source device transports for reproducing the main
video stream. Attribute data is sent once per frame during the main video
stream’s vertical blanking period.

In order to distinguish needed colorimetry for VSC SDP, it adds
intel_dp_needs_vsc_sdp function.
If the output colorspace requires vsc sdp or output format is YCbCr 4:2:0,
it uses MSA with VSC SDP.

As per DP 1.4a spec section 2.2.4.3 [MSA Field for Indication of
Color Encoding Format and Content Color Gamut] while sending
BT.2020 Colorimetry signals we should program MSA MISC1 fields which
indicate VSC SDP for the Pixel Encoding/Colorimetry Format.

v2: Remove useless parentheses
v3: Addressed review comments from Ville
    - In order to checking output format and output colorspace on
      intel_dp_needs_vsc_sdp(), it passes entire intel_crtc_state struct
      value.
    - Remove a pointless variable.
v9: Addressed review comments from Ville
    - Remove a duplicated output color space from intel_crtc_state.
    - In order to handle colorspace of drm_connector_state, it moves a
      calling of intel_ddi_set_pipe_settings() function into
      intel_ddi_pre_enable_dp().

Signed-off-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919195311.13972-3-gwan-gyeong.mun@intel.com
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c     | 14 +++++++++-----
 drivers/gpu/drm/i915/display/intel_ddi.h     |  3 ++-
 drivers/gpu/drm/i915/display/intel_display.c |  1 -
 drivers/gpu/drm/i915/display/intel_dp.c      | 29 +++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/display/intel_dp.h      |  2 ++
 5 files changed, 41 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 079dae20deb5..a8555e396b2a 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -1741,7 +1741,8 @@ static void intel_ddi_clock_get(struct intel_encoder *encoder,
 		hsw_ddi_clock_get(encoder, pipe_config);
 }
 
-void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state)
+void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
+			  const struct drm_connector_state *conn_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
@@ -1792,11 +1793,12 @@ void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state)
 	/*
 	 * As per DP 1.4a spec section 2.2.4.3 [MSA Field for Indication
 	 * of Color Encoding Format and Content Color Gamut] while sending
-	 * YCBCR 420 signals we should program MSA MISC1 fields which
-	 * indicate VSC SDP for the Pixel Encoding/Colorimetry Format.
+	 * YCBCR 420, HDR BT.2020 signals we should program MSA MISC1 fields
+	 * which indicate VSC SDP for the Pixel Encoding/Colorimetry Format.
 	 */
-	if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420)
+	if (intel_dp_needs_vsc_sdp(crtc_state, conn_state))
 		temp |= TRANS_MSA_USE_VSC_SDP;
+
 	I915_WRITE(TRANS_MSA_MISC(cpu_transcoder), temp);
 }
 
@@ -3594,6 +3596,8 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
 		tgl_ddi_pre_enable_dp(encoder, crtc_state, conn_state);
 	else
 		hsw_ddi_pre_enable_dp(encoder, crtc_state, conn_state);
+
+	intel_ddi_set_dp_msa(crtc_state, conn_state);
 }
 
 static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
@@ -4009,7 +4013,7 @@ static void intel_ddi_update_pipe_dp(struct intel_encoder *encoder,
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 
-	intel_ddi_set_pipe_settings(crtc_state);
+	intel_ddi_set_dp_msa(crtc_state, conn_state);
 
 	intel_psr_update(intel_dp, crtc_state);
 	intel_edp_drrs_enable(intel_dp, crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.h b/drivers/gpu/drm/i915/display/intel_ddi.h
index a08365da2643..19aeab1246ee 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.h
+++ b/drivers/gpu/drm/i915/display/intel_ddi.h
@@ -30,7 +30,8 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
 void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state);
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state);
 void intel_ddi_disable_pipe_clock(const  struct intel_crtc_state *crtc_state);
-void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state);
+void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
+			  const struct drm_connector_state *conn_state);
 bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector);
 void intel_ddi_get_config(struct intel_encoder *encoder,
 			  struct intel_crtc_state *pipe_config);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 3cf39fc153b3..5d77f5bae0d9 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -6468,7 +6468,6 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	if (INTEL_GEN(dev_priv) >= 11)
 		icl_set_pipe_chicken(intel_crtc);
 
-	intel_ddi_set_pipe_settings(pipe_config);
 	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_ddi_enable_transcoder_func(pipe_config);
 
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 7aa027881ff3..d8dd7035ca46 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2297,6 +2297,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 		pipe_config->has_pch_encoder = true;
 
 	pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB;
+
 	if (lspcon->active)
 		lspcon_ycbcr420_config(&intel_connector->base, pipe_config);
 	else
@@ -4473,6 +4474,32 @@ intel_dp_get_sink_irq_esi(struct intel_dp *intel_dp, u8 *sink_irq_vector)
 		DP_DPRX_ESI_LEN;
 }
 
+bool
+intel_dp_needs_vsc_sdp(const struct intel_crtc_state *crtc_state,
+		       const struct drm_connector_state *conn_state)
+{
+	/*
+	 * As per DP 1.4a spec section 2.2.4.3 [MSA Field for Indication
+	 * of Color Encoding Format and Content Color Gamut], in order to
+	 * sending YCBCR 420 or HDR BT.2020 signals we should use DP VSC SDP.
+	 */
+	if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR420)
+		return true;
+
+	switch (conn_state->colorspace) {
+	case DRM_MODE_COLORIMETRY_SYCC_601:
+	case DRM_MODE_COLORIMETRY_OPYCC_601:
+	case DRM_MODE_COLORIMETRY_BT2020_YCC:
+	case DRM_MODE_COLORIMETRY_BT2020_RGB:
+	case DRM_MODE_COLORIMETRY_BT2020_CYCC:
+		return true;
+	default:
+		break;
+	}
+
+	return false;
+}
+
 static void
 intel_dp_setup_vsc_sdp(struct intel_dp *intel_dp,
 		       const struct intel_crtc_state *crtc_state,
@@ -4601,7 +4628,7 @@ void intel_dp_vsc_enable(struct intel_dp *intel_dp,
 			 const struct intel_crtc_state *crtc_state,
 			 const struct drm_connector_state *conn_state)
 {
-	if (crtc_state->output_format != INTEL_OUTPUT_FORMAT_YCBCR420)
+	if (!intel_dp_needs_vsc_sdp(crtc_state, conn_state))
 		return;
 
 	intel_dp_setup_vsc_sdp(intel_dp, crtc_state, conn_state);
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index ce2b87f51a30..b05b9f62347f 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -108,6 +108,8 @@ bool intel_dp_read_dpcd(struct intel_dp *intel_dp);
 bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp);
 int intel_dp_link_required(int pixel_clock, int bpp);
 int intel_dp_max_data_rate(int max_link_clock, int max_lanes);
+bool intel_dp_needs_vsc_sdp(const struct intel_crtc_state *crtc_state,
+			    const struct drm_connector_state *conn_state);
 void intel_dp_vsc_enable(struct intel_dp *intel_dp,
 			 const struct intel_crtc_state *crtc_state,
 			 const struct drm_connector_state *conn_state);
-- 
cgit v1.2.3


From 9d1bb6f0222c425235ddb592e54c778c7b67b2fc Mon Sep 17 00:00:00 2001
From: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Date: Thu, 19 Sep 2019 22:53:08 +0300
Subject: drm/i915/dp: Attach colorspace property
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It attaches the colorspace connector property to a DisplayPort connector.
Based on colorspace change, modeset will be triggered to switch to a new
colorspace.

And in order to distinguish colorspace bwtween DP and HDMI connector, it
adds a handling of drm_mode_create_dp_colorspace_property() to
intel_attach_colorspace_property().

Based on colorspace property value create a VSC SDP packet with appropriate
colorspace. This would help to enable wider color gamut like BT2020 on a
sink device.

v9: Addressed review comments from Ville
  - Add a handling of drm_mode_create_dp_colorspace_property() to
    intel_attach_colorspace_property(). This hunk moved from the previous
    commit.

Signed-off-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919195311.13972-6-gwan-gyeong.mun@intel.com
---
 drivers/gpu/drm/i915/display/intel_connector.c | 21 ++++++++++++++++++---
 drivers/gpu/drm/i915/display/intel_dp.c        |  2 ++
 2 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_connector.c b/drivers/gpu/drm/i915/display/intel_connector.c
index ba2ef165a01a..1133c4e97bb4 100644
--- a/drivers/gpu/drm/i915/display/intel_connector.c
+++ b/drivers/gpu/drm/i915/display/intel_connector.c
@@ -277,7 +277,22 @@ intel_attach_aspect_ratio_property(struct drm_connector *connector)
 void
 intel_attach_colorspace_property(struct drm_connector *connector)
 {
-	if (!drm_mode_create_hdmi_colorspace_property(connector))
-		drm_object_attach_property(&connector->base,
-					   connector->colorspace_property, 0);
+	switch (connector->connector_type) {
+	case DRM_MODE_CONNECTOR_HDMIA:
+	case DRM_MODE_CONNECTOR_HDMIB:
+		if (drm_mode_create_hdmi_colorspace_property(connector))
+			return;
+		break;
+	case DRM_MODE_CONNECTOR_DisplayPort:
+	case DRM_MODE_CONNECTOR_eDP:
+		if (drm_mode_create_dp_colorspace_property(connector))
+			return;
+		break;
+	default:
+		DRM_DEBUG_KMS("Colorspace property not supported\n");
+		return;
+	}
+
+	drm_object_attach_property(&connector->base,
+				   connector->colorspace_property, 0);
 }
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index d8dd7035ca46..4bc4afe96ba9 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -6476,6 +6476,8 @@ intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connect
 	else if (INTEL_GEN(dev_priv) >= 5)
 		drm_connector_attach_max_bpc_property(connector, 6, 12);
 
+	intel_attach_colorspace_property(connector);
+
 	if (intel_dp_is_edp(intel_dp)) {
 		u32 allowed_scalers;
 
-- 
cgit v1.2.3


From 922430dd4022eb7afef29c0f98972265a0053b8d Mon Sep 17 00:00:00 2001
From: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Date: Thu, 19 Sep 2019 22:53:09 +0300
Subject: drm/i915: Add new GMP register size for GEN11
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

According to Bspec, GEN11 and prior GEN11 have different register size for
HDR Metadata Infoframe SDP packet. It adds new VIDEO_DIP_GMP_DATA_SIZE for
GEN11. And it makes handle different register size for
HDMI_PACKET_TYPE_GAMUT_METADATA on hsw_dip_data_size() for each GEN
platforms. It addresses Uma's review comments.

v9: Add WARN_ON() when buffer size if larger than register size. [Ville]

Signed-off-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919195311.13972-7-gwan-gyeong.mun@intel.com
---
 drivers/gpu/drm/i915/display/intel_hdmi.c | 12 ++++++++++--
 drivers/gpu/drm/i915/i915_reg.h           |  1 +
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 0a6846c5ba95..92d1cbbbee2b 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -189,13 +189,19 @@ hsw_dip_data_reg(struct drm_i915_private *dev_priv,
 	}
 }
 
-static int hsw_dip_data_size(unsigned int type)
+static int hsw_dip_data_size(struct drm_i915_private *dev_priv,
+			     unsigned int type)
 {
 	switch (type) {
 	case DP_SDP_VSC:
 		return VIDEO_DIP_VSC_DATA_SIZE;
 	case DP_SDP_PPS:
 		return VIDEO_DIP_PPS_DATA_SIZE;
+	case HDMI_PACKET_TYPE_GAMUT_METADATA:
+		if (INTEL_GEN(dev_priv) >= 11)
+			return VIDEO_DIP_GMP_DATA_SIZE;
+		else
+			return VIDEO_DIP_DATA_SIZE;
 	default:
 		return VIDEO_DIP_DATA_SIZE;
 	}
@@ -514,7 +520,9 @@ static void hsw_write_infoframe(struct intel_encoder *encoder,
 	int i;
 	u32 val = I915_READ(ctl_reg);
 
-	data_size = hsw_dip_data_size(type);
+	data_size = hsw_dip_data_size(dev_priv, type);
+
+	WARN_ON(len > data_size);
 
 	val &= ~hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index e24991e54897..d741d34e1895 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4692,6 +4692,7 @@ enum {
  * (Haswell and newer) to see which VIDEO_DIP_DATA byte corresponds to each byte
  * of the infoframe structure specified by CEA-861. */
 #define   VIDEO_DIP_DATA_SIZE	32
+#define   VIDEO_DIP_GMP_DATA_SIZE	36
 #define   VIDEO_DIP_VSC_DATA_SIZE	36
 #define   VIDEO_DIP_PPS_DATA_SIZE	132
 #define VIDEO_DIP_CTL		_MMIO(0x61170)
-- 
cgit v1.2.3


From b246cf215e4c62a0baa4dfc35510198f228dc951 Mon Sep 17 00:00:00 2001
From: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Date: Thu, 19 Sep 2019 22:53:10 +0300
Subject: drm/i915/dp: Program an Infoframe SDP Header and DB for HDR Static
 Metadata
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Function intel_dp_setup_hdr_metadata_infoframe_sdp handles Infoframe SDP
header and data block setup for HDR Static Metadata. It enables writing of
HDR metadata infoframe SDP to panel. Support for HDR video was introduced
in DisplayPort 1.4. It implements the CTA-861-G standard for transport of
static HDR metadata. The HDR Metadata will be provided by userspace
compositors, based on blending policies and passed to the driver through
a blob property.

Because each of GEN11 and prior GEN11 have different register size for
HDR Metadata Infoframe SDP packet, it adds and uses different register
size.

Setup Infoframe SDP header and data block in function
intel_dp_setup_hdr_metadata_infoframe_sdp for HDR Static Metadata as per
dp 1.4 spec and CTA-861-F spec.
As per DP 1.4 spec, 2.2.2.5 SDP Formats. It enables Dynamic Range and
Mastering Infoframe for HDR content, which is defined in CTA-861-F spec.
According to DP 1.4 spec and CEA-861-F spec Table 5, in order to transmit
static HDR metadata, we have to use Non-audio INFOFRAME SDP v1.3.

+--------------------------------+-------------------------------+
|      [ Packet Type Value ]     |       [ Packet Type ]         |
+--------------------------------+-------------------------------+
| 80h + Non-audio INFOFRAME Type | CEA-861-F Non-audio INFOFRAME |
+--------------------------------+-------------------------------+
|      [Transmission Timing]                                     |
+----------------------------------------------------------------+
| As per CEA-861-F for INFOFRAME, including CEA-861.3 within     |
| which Dynamic Range and Mastering INFOFRAME are defined        |
+----------------------------------------------------------------+

v2: Add a missed blank line after function declaration.
v3: Remove not handled return values from
    intel_dp_setup_hdr_metadata_infoframe_sdp(). [Uma]
v9: Addressed review comments from Ville.
    - Add BUILD_BUG_ON to check a changing of struct dp_sdp size.
    - Change a passed size toward write_infoframe() for DP infoframe sdp
      packet for HDR static metadata.

Signed-off-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919195311.13972-8-gwan-gyeong.mun@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c |  1 +
 drivers/gpu/drm/i915/display/intel_dp.c  | 92 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_dp.h  |  3 ++
 3 files changed, 96 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index a8555e396b2a..e9fca3b2f6ec 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3856,6 +3856,7 @@ static void intel_enable_ddi_dp(struct intel_encoder *encoder,
 	intel_edp_backlight_on(crtc_state, conn_state);
 	intel_psr_enable(intel_dp, crtc_state);
 	intel_dp_vsc_enable(intel_dp, crtc_state, conn_state);
+	intel_dp_hdr_metadata_enable(intel_dp, crtc_state, conn_state);
 	intel_edp_drrs_enable(intel_dp, crtc_state);
 
 	if (crtc_state->has_audio)
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 4bc4afe96ba9..edb95a4cdb21 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4624,6 +4624,86 @@ intel_dp_setup_vsc_sdp(struct intel_dp *intel_dp,
 			crtc_state, DP_SDP_VSC, &vsc_sdp, sizeof(vsc_sdp));
 }
 
+static void
+intel_dp_setup_hdr_metadata_infoframe_sdp(struct intel_dp *intel_dp,
+					  const struct intel_crtc_state *crtc_state,
+					  const struct drm_connector_state *conn_state)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct dp_sdp infoframe_sdp = {};
+	struct hdmi_drm_infoframe drm_infoframe = {};
+	const int infoframe_size = HDMI_INFOFRAME_HEADER_SIZE + HDMI_DRM_INFOFRAME_SIZE;
+	unsigned char buf[HDMI_INFOFRAME_HEADER_SIZE + HDMI_DRM_INFOFRAME_SIZE];
+	ssize_t len;
+	int ret;
+
+	ret = drm_hdmi_infoframe_set_hdr_metadata(&drm_infoframe, conn_state);
+	if (ret) {
+		DRM_DEBUG_KMS("couldn't set HDR metadata in infoframe\n");
+		return;
+	}
+
+	len = hdmi_drm_infoframe_pack_only(&drm_infoframe, buf, sizeof(buf));
+	if (len < 0) {
+		DRM_DEBUG_KMS("buffer size is smaller than hdr metadata infoframe\n");
+		return;
+	}
+
+	if (len != infoframe_size) {
+		DRM_DEBUG_KMS("wrong static hdr metadata size\n");
+		return;
+	}
+
+	/*
+	 * Set up the infoframe sdp packet for HDR static metadata.
+	 * Prepare VSC Header for SU as per DP 1.4a spec,
+	 * Table 2-100 and Table 2-101
+	 */
+
+	/* Packet ID, 00h for non-Audio INFOFRAME */
+	infoframe_sdp.sdp_header.HB0 = 0;
+	/*
+	 * Packet Type 80h + Non-audio INFOFRAME Type value
+	 * HDMI_INFOFRAME_TYPE_DRM: 0x87,
+	 */
+	infoframe_sdp.sdp_header.HB1 = drm_infoframe.type;
+	/*
+	 * Least Significant Eight Bits of (Data Byte Count – 1)
+	 * infoframe_size - 1,
+	 */
+	infoframe_sdp.sdp_header.HB2 = 0x1D;
+	/* INFOFRAME SDP Version Number */
+	infoframe_sdp.sdp_header.HB3 = (0x13 << 2);
+	/* CTA Header Byte 2 (INFOFRAME Version Number) */
+	infoframe_sdp.db[0] = drm_infoframe.version;
+	/* CTA Header Byte 3 (Length of INFOFRAME): HDMI_DRM_INFOFRAME_SIZE */
+	infoframe_sdp.db[1] = drm_infoframe.length;
+	/*
+	 * Copy HDMI_DRM_INFOFRAME_SIZE size from a buffer after
+	 * HDMI_INFOFRAME_HEADER_SIZE
+	 */
+	BUILD_BUG_ON(sizeof(infoframe_sdp.db) < HDMI_DRM_INFOFRAME_SIZE + 2);
+	memcpy(&infoframe_sdp.db[2], &buf[HDMI_INFOFRAME_HEADER_SIZE],
+	       HDMI_DRM_INFOFRAME_SIZE);
+
+	/*
+	 * Size of DP infoframe sdp packet for HDR static metadata is consist of
+	 * - DP SDP Header(struct dp_sdp_header): 4 bytes
+	 * - Two Data Blocks: 2 bytes
+	 *    CTA Header Byte2 (INFOFRAME Version Number)
+	 *    CTA Header Byte3 (Length of INFOFRAME)
+	 * - HDMI_DRM_INFOFRAME_SIZE: 26 bytes
+	 *
+	 * Prior to GEN11's GMP register size is identical to DP HDR static metadata
+	 * infoframe size. But GEN11+ has larger than that size, write_infoframe
+	 * will pad rest of the size.
+	 */
+	intel_dig_port->write_infoframe(&intel_dig_port->base, crtc_state,
+					HDMI_PACKET_TYPE_GAMUT_METADATA,
+					&infoframe_sdp,
+					sizeof(struct dp_sdp_header) + 2 + HDMI_DRM_INFOFRAME_SIZE);
+}
+
 void intel_dp_vsc_enable(struct intel_dp *intel_dp,
 			 const struct intel_crtc_state *crtc_state,
 			 const struct drm_connector_state *conn_state)
@@ -4634,6 +4714,18 @@ void intel_dp_vsc_enable(struct intel_dp *intel_dp,
 	intel_dp_setup_vsc_sdp(intel_dp, crtc_state, conn_state);
 }
 
+void intel_dp_hdr_metadata_enable(struct intel_dp *intel_dp,
+				  const struct intel_crtc_state *crtc_state,
+				  const struct drm_connector_state *conn_state)
+{
+	if (!conn_state->hdr_output_metadata)
+		return;
+
+	intel_dp_setup_hdr_metadata_infoframe_sdp(intel_dp,
+						  crtc_state,
+						  conn_state);
+}
+
 static u8 intel_dp_autotest_link_training(struct intel_dp *intel_dp)
 {
 	int status = 0;
diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h
index b05b9f62347f..3da166054788 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.h
+++ b/drivers/gpu/drm/i915/display/intel_dp.h
@@ -113,6 +113,9 @@ bool intel_dp_needs_vsc_sdp(const struct intel_crtc_state *crtc_state,
 void intel_dp_vsc_enable(struct intel_dp *intel_dp,
 			 const struct intel_crtc_state *crtc_state,
 			 const struct drm_connector_state *conn_state);
+void intel_dp_hdr_metadata_enable(struct intel_dp *intel_dp,
+				  const struct intel_crtc_state *crtc_state,
+				  const struct drm_connector_state *conn_state);
 bool intel_digital_port_connected(struct intel_encoder *encoder);
 
 static inline unsigned int intel_dp_unused_lane_mask(int lane_count)
-- 
cgit v1.2.3


From 0299dfa7ad54f95ae9502fc425184f865d326d3b Mon Sep 17 00:00:00 2001
From: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Date: Thu, 19 Sep 2019 22:53:11 +0300
Subject: drm/i915/dp: Attach HDR metadata property to DP connector
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It attaches HDR metadata property to DP connector on GLK+.
It enables HDR metadata infoframe sdp on GLK+ to be used to send
HDR metadata to DP sink.

v2: Minor style fix

Signed-off-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919195311.13972-9-gwan-gyeong.mun@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index edb95a4cdb21..dd5dc1e38495 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -6570,6 +6570,11 @@ intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connect
 
 	intel_attach_colorspace_property(connector);
 
+	if (IS_GEMINILAKE(dev_priv) || INTEL_GEN(dev_priv) >= 11)
+		drm_object_attach_property(&connector->base,
+					   connector->dev->mode_config.hdr_output_metadata_property,
+					   0);
+
 	if (intel_dp_is_edp(intel_dp)) {
 		u32 allowed_scalers;
 
-- 
cgit v1.2.3


From 3e706dff0891f56844166597aa4d37c43700e2f5 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jul 2019 17:50:47 +0300
Subject: drm/i915: Switch to using DP_MSA_MISC_* defines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that we have standard defines for the MSA MISC bits lets use
them on HSW+ where we program these directly into the TRANS_MSA_MISC
register.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190718145053.25808-7-ville.syrjala@linux.intel.com
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 17 ++++++++---------
 drivers/gpu/drm/i915/i915_reg.h          | 13 +------------
 2 files changed, 9 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index e9fca3b2f6ec..80f8e2698be0 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -1754,20 +1754,20 @@ void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
 
 	WARN_ON(transcoder_is_dsi(cpu_transcoder));
 
-	temp = TRANS_MSA_SYNC_CLK;
+	temp = DP_MSA_MISC_SYNC_CLOCK;
 
 	switch (crtc_state->pipe_bpp) {
 	case 18:
-		temp |= TRANS_MSA_6_BPC;
+		temp |= DP_MSA_MISC_6_BPC;
 		break;
 	case 24:
-		temp |= TRANS_MSA_8_BPC;
+		temp |= DP_MSA_MISC_8_BPC;
 		break;
 	case 30:
-		temp |= TRANS_MSA_10_BPC;
+		temp |= DP_MSA_MISC_10_BPC;
 		break;
 	case 36:
-		temp |= TRANS_MSA_12_BPC;
+		temp |= DP_MSA_MISC_12_BPC;
 		break;
 	default:
 		MISSING_CASE(crtc_state->pipe_bpp);
@@ -1779,7 +1779,7 @@ void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
 		crtc_state->output_format != INTEL_OUTPUT_FORMAT_RGB);
 
 	if (crtc_state->limited_color_range)
-		temp |= TRANS_MSA_CEA_RANGE;
+		temp |= DP_MSA_MISC_COLOR_CEA_RGB;
 
 	/*
 	 * As per DP 1.2 spec section 2.3.4.3 while sending
@@ -1787,8 +1787,7 @@ void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
 	 * colorspace information.
 	 */
 	if (crtc_state->output_format == INTEL_OUTPUT_FORMAT_YCBCR444)
-		temp |= TRANS_MSA_SAMPLING_444 | TRANS_MSA_CLRSP_YCBCR |
-			TRANS_MSA_YCBCR_BT709;
+		temp |= DP_MSA_MISC_COLOR_YCBCR_444_BT709;
 
 	/*
 	 * As per DP 1.4a spec section 2.2.4.3 [MSA Field for Indication
@@ -1797,7 +1796,7 @@ void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
 	 * which indicate VSC SDP for the Pixel Encoding/Colorimetry Format.
 	 */
 	if (intel_dp_needs_vsc_sdp(crtc_state, conn_state))
-		temp |= TRANS_MSA_USE_VSC_SDP;
+		temp |= DP_MSA_MISC_COLOR_VSC_SDP;
 
 	I915_WRITE(TRANS_MSA_MISC(cpu_transcoder), temp);
 }
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index d741d34e1895..7dd126cc3ac3 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -9759,18 +9759,7 @@ enum skl_power_gate {
 #define _TRANSC_MSA_MISC		0x62410
 #define _TRANS_EDP_MSA_MISC		0x6f410
 #define TRANS_MSA_MISC(tran) _MMIO_TRANS2(tran, _TRANSA_MSA_MISC)
-
-#define  TRANS_MSA_SYNC_CLK		(1 << 0)
-#define  TRANS_MSA_SAMPLING_444		(2 << 1)
-#define  TRANS_MSA_CLRSP_YCBCR		(1 << 3)
-#define  TRANS_MSA_YCBCR_BT709		(1 << 4)
-#define  TRANS_MSA_6_BPC		(0 << 5)
-#define  TRANS_MSA_8_BPC		(1 << 5)
-#define  TRANS_MSA_10_BPC		(2 << 5)
-#define  TRANS_MSA_12_BPC		(3 << 5)
-#define  TRANS_MSA_16_BPC		(4 << 5)
-#define  TRANS_MSA_CEA_RANGE		(1 << 3)
-#define  TRANS_MSA_USE_VSC_SDP		(1 << 14)
+/* See DP_MSA_MISC_* for the bit definitions */
 
 /* LCPLL Control */
 #define LCPLL_CTL			_MMIO(0x130040)
-- 
cgit v1.2.3


From 131d3b1af10599b13c7bcd9bb137b5419cd12798 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 8 Jul 2019 15:53:14 +0300
Subject: drm/i915: Stop using drm_atomic_helper_check_planes()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We need to insert stuff between the plane and crtc .atomic_check()
drm_atomic_helper_check_planes() doesn't allow us to do that so
stop using it and hand roll the loops instead.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190708125325.16576-9-ville.syrjala@linux.intel.com
Reviewed-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
---
 drivers/gpu/drm/i915/display/intel_atomic_plane.c | 10 ++--
 drivers/gpu/drm/i915/display/intel_atomic_plane.h |  2 +
 drivers/gpu/drm/i915/display/intel_display.c      | 57 ++++++++++++++++++-----
 3 files changed, 50 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index 98b7766eaa7a..a6cff5a160fb 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -195,14 +195,11 @@ get_crtc_from_states(const struct intel_plane_state *old_plane_state,
 	return NULL;
 }
 
-static int intel_plane_atomic_check(struct drm_plane *_plane,
-				    struct drm_plane_state *_new_plane_state)
+int intel_plane_atomic_check(struct intel_atomic_state *state,
+			     struct intel_plane *plane)
 {
-	struct intel_plane *plane = to_intel_plane(_plane);
-	struct intel_atomic_state *state =
-		to_intel_atomic_state(_new_plane_state->state);
 	struct intel_plane_state *new_plane_state =
-		to_intel_plane_state(_new_plane_state);
+		intel_atomic_get_new_plane_state(state, plane);
 	const struct intel_plane_state *old_plane_state =
 		intel_atomic_get_old_plane_state(state, plane);
 	struct intel_crtc *crtc =
@@ -369,5 +366,4 @@ void i9xx_update_planes_on_crtc(struct intel_atomic_state *state,
 const struct drm_plane_helper_funcs intel_plane_helper_funcs = {
 	.prepare_fb = intel_prepare_plane_fb,
 	.cleanup_fb = intel_cleanup_plane_fb,
-	.atomic_check = intel_plane_atomic_check,
 };
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.h b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
index cb7ef4f9eafd..dc85af02e9b7 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.h
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
@@ -41,6 +41,8 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 					struct intel_crtc_state *crtc_state,
 					const struct intel_plane_state *old_plane_state,
 					struct intel_plane_state *intel_state);
+int intel_plane_atomic_check(struct intel_atomic_state *state,
+			     struct intel_plane *plane);
 int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_state,
 				    struct intel_crtc_state *crtc_state,
 				    const struct intel_plane_state *old_plane_state,
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 5d77f5bae0d9..00bee5abf87a 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -11783,15 +11783,14 @@ static bool c8_planes_changed(const struct intel_crtc_state *new_crtc_state)
 	return !old_crtc_state->c8_planes != !new_crtc_state->c8_planes;
 }
 
-static int intel_crtc_atomic_check(struct drm_crtc *_crtc,
-				   struct drm_crtc_state *_crtc_state)
+static int intel_crtc_atomic_check(struct intel_atomic_state *state,
+				   struct intel_crtc *crtc)
 {
-	struct intel_crtc *crtc = to_intel_crtc(_crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_crtc_state *crtc_state =
-		to_intel_crtc_state(_crtc_state);
-	int ret;
+		intel_atomic_get_new_crtc_state(state, crtc);
 	bool mode_changed = needs_modeset(crtc_state);
+	int ret;
 
 	if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv) &&
 	    mode_changed && !crtc_state->base.active)
@@ -11863,10 +11862,6 @@ static int intel_crtc_atomic_check(struct drm_crtc *_crtc,
 	return ret;
 }
 
-static const struct drm_crtc_helper_funcs intel_helper_funcs = {
-	.atomic_check = intel_crtc_atomic_check,
-};
-
 static void intel_modeset_update_connector_atomic_state(struct drm_device *dev)
 {
 	struct intel_connector *connector;
@@ -13541,6 +13536,42 @@ static void intel_crtc_check_fastset(const struct intel_crtc_state *old_crtc_sta
 	new_crtc_state->has_drrs = old_crtc_state->has_drrs;
 }
 
+static int intel_atomic_check_planes(struct intel_atomic_state *state)
+{
+	struct intel_plane_state *plane_state;
+	struct intel_plane *plane;
+	int i, ret;
+
+	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
+		ret = intel_plane_atomic_check(state, plane);
+		if (ret) {
+			DRM_DEBUG_ATOMIC("[PLANE:%d:%s] atomic driver check failed\n",
+					 plane->base.base.id, plane->base.name);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int intel_atomic_check_crtcs(struct intel_atomic_state *state)
+{
+	struct intel_crtc_state *crtc_state;
+	struct intel_crtc *crtc;
+	int i;
+
+	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
+		int ret = intel_crtc_atomic_check(state, crtc);
+		if (ret) {
+			DRM_DEBUG_ATOMIC("[CRTC:%d:%s] atomic driver check failed\n",
+					 crtc->base.base.id, crtc->base.name);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 /**
  * intel_atomic_check - validate state object
  * @dev: drm device
@@ -13604,7 +13635,11 @@ static int intel_atomic_check(struct drm_device *dev,
 	if (ret)
 		goto fail;
 
-	ret = drm_atomic_helper_check_planes(dev, &state->base);
+	ret = intel_atomic_check_planes(state);
+	if (ret)
+		goto fail;
+
+	ret = intel_atomic_check_crtcs(state);
 	if (ret)
 		goto fail;
 
@@ -15175,8 +15210,6 @@ static int intel_crtc_init(struct drm_i915_private *dev_priv, enum pipe pipe)
 		dev_priv->plane_to_crtc_mapping[i9xx_plane] = intel_crtc;
 	}
 
-	drm_crtc_helper_add(&intel_crtc->base, &intel_helper_funcs);
-
 	intel_color_init(intel_crtc);
 
 	WARN_ON(drm_crtc_index(&intel_crtc->base) != intel_crtc->pipe);
-- 
cgit v1.2.3


From 3e30d70805d577e458592dcf59dcf8a2391d08a5 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 8 Jul 2019 15:53:16 +0300
Subject: drm/i915: Make .modeset_calc_cdclk() mandatory
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While not all platforms allow us to change the cdclk frequency
we should still verify that the fixed cdclk frequency isn't
too low. To that end let's cook up a .modeset_calc_cdclk()
implementation that only does the min_cdclk vs. actual cdclk
frequency check for such platforms.

Also we mustn't forget about double wide pipe on gen2/3 when
doing this.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190708125325.16576-11-ville.syrjala@linux.intel.com
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
---
 drivers/gpu/drm/i915/display/intel_cdclk.c   | 31 ++++++++++++++++++++++------
 drivers/gpu/drm/i915/display/intel_display.c |  8 +++----
 2 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 43564295b864..3d867963a6d1 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1900,9 +1900,11 @@ intel_set_cdclk_post_plane_update(struct drm_i915_private *dev_priv,
 		intel_set_cdclk(dev_priv, new_state, pipe);
 }
 
-static int intel_pixel_rate_to_cdclk(struct drm_i915_private *dev_priv,
-				     int pixel_rate)
+static int intel_pixel_rate_to_cdclk(const struct intel_crtc_state *crtc_state)
 {
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	int pixel_rate = crtc_state->pixel_rate;
+
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		return DIV_ROUND_UP(pixel_rate, 2);
 	else if (IS_GEN(dev_priv, 9) ||
@@ -1910,6 +1912,8 @@ static int intel_pixel_rate_to_cdclk(struct drm_i915_private *dev_priv,
 		return pixel_rate;
 	else if (IS_CHERRYVIEW(dev_priv))
 		return DIV_ROUND_UP(pixel_rate * 100, 95);
+	else if (crtc_state->double_wide)
+		return DIV_ROUND_UP(pixel_rate * 100, 90 * 2);
 	else
 		return DIV_ROUND_UP(pixel_rate * 100, 90);
 }
@@ -1923,7 +1927,7 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 	if (!crtc_state->base.enable)
 		return 0;
 
-	min_cdclk = intel_pixel_rate_to_cdclk(dev_priv, crtc_state->pixel_rate);
+	min_cdclk = intel_pixel_rate_to_cdclk(crtc_state);
 
 	/* pixel rate mustn't exceed 95% of cdclk with IPS on BDW */
 	if (IS_BROADWELL(dev_priv) && hsw_crtc_state_ips_capable(crtc_state))
@@ -2277,15 +2281,28 @@ static int intel_modeset_all_pipes(struct intel_atomic_state *state)
 	return 0;
 }
 
+static int fixed_modeset_calc_cdclk(struct intel_atomic_state *state)
+{
+	int min_cdclk;
+
+	/*
+	 * We can't change the cdclk frequency, but we still want to
+	 * check that the required minimum frequency doesn't exceed
+	 * the actual cdclk frequency.
+	 */
+	min_cdclk = intel_compute_min_cdclk(state);
+	if (min_cdclk < 0)
+		return min_cdclk;
+
+	return 0;
+}
+
 int intel_modeset_calc_cdclk(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	enum pipe pipe;
 	int ret;
 
-	if (!dev_priv->display.modeset_calc_cdclk)
-		return 0;
-
 	ret = dev_priv->display.modeset_calc_cdclk(state);
 	if (ret)
 		return ret;
@@ -2596,6 +2613,8 @@ void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv)
 	} else if (IS_VALLEYVIEW(dev_priv)) {
 		dev_priv->display.set_cdclk = vlv_set_cdclk;
 		dev_priv->display.modeset_calc_cdclk = vlv_modeset_calc_cdclk;
+	} else {
+		dev_priv->display.modeset_calc_cdclk = fixed_modeset_calc_cdclk;
 	}
 
 	if (INTEL_GEN(dev_priv) >= 10 || IS_GEN9_LP(dev_priv))
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 00bee5abf87a..1dc98a2d0b03 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -16816,11 +16816,9 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 
 			intel_crtc_compute_pixel_rate(crtc_state);
 
-			if (dev_priv->display.modeset_calc_cdclk) {
-				min_cdclk = intel_crtc_compute_min_cdclk(crtc_state);
-				if (WARN_ON(min_cdclk < 0))
-					min_cdclk = 0;
-			}
+			min_cdclk = intel_crtc_compute_min_cdclk(crtc_state);
+			if (WARN_ON(min_cdclk < 0))
+				min_cdclk = 0;
 
 			drm_calc_timestamping_constants(&crtc->base,
 							&crtc_state->base.adjusted_mode);
-- 
cgit v1.2.3


From 5812d04c4c7455627d8722e04ab99a737cfe9713 Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <maxg@mellanox.com>
Date: Sun, 13 Oct 2019 19:57:37 +0300
Subject: nvmet-loop: fix possible leakage during error flow

During nvme_loop_queue_rq error flow, one must call nvme_cleanup_cmd since
it's symmetric to nvme_setup_cmd.

Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/loop.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 748a39fca771..11f5aea97d1b 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -157,8 +157,10 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		iod->sg_table.sgl = iod->first_sgl;
 		if (sg_alloc_table_chained(&iod->sg_table,
 				blk_rq_nr_phys_segments(req),
-				iod->sg_table.sgl, SG_CHUNK_SIZE))
+				iod->sg_table.sgl, SG_CHUNK_SIZE)) {
+			nvme_cleanup_cmd(req);
 			return BLK_STS_RESOURCE;
+		}
 
 		iod->req.sg = iod->sg_table.sgl;
 		iod->req.sg_cnt = blk_rq_map_sg(req->q, req, iod->sg_table.sgl);
-- 
cgit v1.2.3


From 28a4cac48c7e897a0b4e7d79a53a8e4fe40337ae Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <maxg@mellanox.com>
Date: Sun, 13 Oct 2019 19:57:38 +0300
Subject: nvme-tcp: fix possible leakage during error flow

During nvme_tcp_setup_cmd_pdu error flow, one must call nvme_cleanup_cmd
since it's symmetric to nvme_setup_cmd.

Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 820dac10fa9e..770dbcbc999e 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2136,6 +2136,7 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns,
 
 	ret = nvme_tcp_map_data(queue, rq);
 	if (unlikely(ret)) {
+		nvme_cleanup_cmd(rq);
 		dev_err(queue->ctrl->ctrl.device,
 			"Failed to map data (%d)\n", ret);
 		return ret;
-- 
cgit v1.2.3


From 85f0ae7e435afb261af33f9a605b973c0c8c1139 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Sat, 21 Sep 2019 22:18:46 +0900
Subject: kbuild: update comment about KBUILD_ALLDIRS

Commit 000ec95fbe75 ("kbuild: pkg: rename scripts/package/Makefile to
scripts/Makefile.package") missed to update this comment.

Fixes: 000ec95fbe75 ("kbuild: pkg: rename scripts/package/Makefile to scripts/Makefile.package")
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index ffd7a912fc46..19efe04b398c 100644
--- a/Makefile
+++ b/Makefile
@@ -1037,7 +1037,7 @@ export KBUILD_VMLINUX_OBJS := $(head-y) $(init-y) $(core-y) $(libs-y2) \
 export KBUILD_VMLINUX_LIBS := $(libs-y1)
 export KBUILD_LDS          := arch/$(SRCARCH)/kernel/vmlinux.lds
 export LDFLAGS_vmlinux
-# used by scripts/package/Makefile
+# used by scripts/Makefile.package
 export KBUILD_ALLDIRS := $(sort $(filter-out arch/%,$(vmlinux-alldirs)) LICENSES arch include scripts tools)
 
 vmlinux-deps := $(KBUILD_LDS) $(KBUILD_VMLINUX_OBJS) $(KBUILD_VMLINUX_LIBS)
-- 
cgit v1.2.3


From 991b78fbd2231175293bd1d7c0768fb4e4382e14 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 5 Oct 2019 08:01:59 -0700
Subject: scripts: setlocalversion: fix a bashism

Fix bashism reported by checkbashisms by using only one '=':

possible bashism in scripts/setlocalversion line 96 (should be 'b = a'):
	if [ "`hg log -r . --template '{latesttagdistance}'`" == "1" ]; then

Fixes: 38b3439d84f4 ("setlocalversion: update mercurial tag parsing")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Mike Crowe <mcrowe@zipitwireless.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/setlocalversion | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/setlocalversion b/scripts/setlocalversion
index 220dae0db3f1..a2998b118ef9 100755
--- a/scripts/setlocalversion
+++ b/scripts/setlocalversion
@@ -93,7 +93,7 @@ scm_version()
 	# Check for mercurial and a mercurial repo.
 	if test -d .hg && hgid=`hg id 2>/dev/null`; then
 		# Do we have an tagged version?  If so, latesttagdistance == 1
-		if [ "`hg log -r . --template '{latesttagdistance}'`" == "1" ]; then
+		if [ "`hg log -r . --template '{latesttagdistance}'`" = "1" ]; then
 			id=`hg log -r . --template '{latesttag}'`
 			printf '%s%s' -hg "$id"
 		else
-- 
cgit v1.2.3


From dcdef1abbc50c57c982be3964cf2250660ba906e Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 30 Sep 2019 16:42:13 +0300
Subject: drm/i915: Use drm_rect_translate_to()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the newly introduced drm_rect_translate_to() instead
of hand rolling it.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190930134214.24702-3-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 1dc98a2d0b03..7cab9368e697 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3476,9 +3476,8 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state)
 	 * Put the final coordinates back so that the src
 	 * coordinate checks will see the right values.
 	 */
-	drm_rect_translate(&plane_state->base.src,
-			   (x << 16) - plane_state->base.src.x1,
-			   (y << 16) - plane_state->base.src.y1);
+	drm_rect_translate_to(&plane_state->base.src,
+			      x << 16, y << 16);
 
 	return 0;
 }
@@ -3700,9 +3699,8 @@ int i9xx_check_plane_surface(struct intel_plane_state *plane_state)
 	 * Put the final coordinates back so that the src
 	 * coordinate checks will see the right values.
 	 */
-	drm_rect_translate(&plane_state->base.src,
-			   (src_x << 16) - plane_state->base.src.x1,
-			   (src_y << 16) - plane_state->base.src.y1);
+	drm_rect_translate_to(&plane_state->base.src,
+			      src_x << 16, src_y << 16);
 
 	/* HSW/BDW do this automagically in hardware */
 	if (!IS_HASWELL(dev_priv) && !IS_BROADWELL(dev_priv)) {
-- 
cgit v1.2.3


From fc1a0fb53875724c3498e1402ac339de3fee20d8 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 30 Sep 2019 16:42:14 +0300
Subject: drm/i915: Use drm_rect_init()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the new drm_rect_init() helper where appropriate.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190930134214.24702-4-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 10 ++--------
 drivers/gpu/drm/i915/display/intel_sprite.c  |  6 ++----
 2 files changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 7cab9368e697..7d7d1859775a 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -2733,10 +2733,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 				size++;
 
 			/* rotate the x/y offsets to match the GTT view */
-			r.x1 = x;
-			r.y1 = y;
-			r.x2 = x + width;
-			r.y2 = y + height;
+			drm_rect_init(&r, x, y, width, height);
 			drm_rect_rotate(&r,
 					rot_info->plane[i].width * tile_width,
 					rot_info->plane[i].height * tile_height,
@@ -2858,10 +2855,7 @@ intel_plane_remap_gtt(struct intel_plane_state *plane_state)
 			struct drm_rect r;
 
 			/* rotate the x/y offsets to match the GTT view */
-			r.x1 = x;
-			r.y1 = y;
-			r.x2 = x + width;
-			r.y2 = y + height;
+			drm_rect_init(&r, x, y, width, height);
 			drm_rect_rotate(&r,
 					info->plane[i].width * tile_width,
 					info->plane[i].height * tile_height,
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index 633fa8069348..5ae12ab3c5b7 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -287,10 +287,8 @@ int intel_plane_check_src_coordinates(struct intel_plane_state *plane_state)
 	src_y = src->y1 >> 16;
 	src_h = drm_rect_height(src) >> 16;
 
-	src->x1 = src_x << 16;
-	src->x2 = (src_x + src_w) << 16;
-	src->y1 = src_y << 16;
-	src->y2 = (src_y + src_h) << 16;
+	drm_rect_init(src, src_x << 16, src_y << 16,
+		      src_w << 16, src_h << 16);
 
 	if (!fb->format->is_yuv)
 		return 0;
-- 
cgit v1.2.3


From 5da0fb1ab34ccfe6d49210b4f5a739c59fcbf25e Mon Sep 17 00:00:00 2001
From: yangerkun <yangerkun@huawei.com>
Date: Tue, 15 Oct 2019 21:59:29 +0800
Subject: io_uring: consider the overflow of sequence for timeout req

Now we recalculate the sequence of timeout with 'req->sequence =
ctx->cached_sq_head + count - 1', judge the right place to insert
for timeout_list by compare the number of request we still expected for
completion. But we have not consider about the situation of overflow:

1. ctx->cached_sq_head + count - 1 may overflow. And a bigger count for
the new timeout req can have a small req->sequence.

2. cached_sq_head of now may overflow compare with before req. And it
will lead the timeout req with small req->sequence.

This overflow will lead to the misorder of timeout_list, which can lead
to the wrong order of the completion of timeout_list. Fix it by reuse
req->submit.sequence to store the count, and change the logic of
inserting sort in io_timeout.

Signed-off-by: yangerkun <yangerkun@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 38d274fc0f25..d2cb277da2f4 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1884,7 +1884,7 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
 
 static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
-	unsigned count, req_dist, tail_index;
+	unsigned count;
 	struct io_ring_ctx *ctx = req->ctx;
 	struct list_head *entry;
 	struct timespec64 ts;
@@ -1907,21 +1907,36 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		count = 1;
 
 	req->sequence = ctx->cached_sq_head + count - 1;
+	/* reuse it to store the count */
+	req->submit.sequence = count;
 	req->flags |= REQ_F_TIMEOUT;
 
 	/*
 	 * Insertion sort, ensuring the first entry in the list is always
 	 * the one we need first.
 	 */
-	tail_index = ctx->cached_cq_tail - ctx->rings->sq_dropped;
-	req_dist = req->sequence - tail_index;
 	spin_lock_irq(&ctx->completion_lock);
 	list_for_each_prev(entry, &ctx->timeout_list) {
 		struct io_kiocb *nxt = list_entry(entry, struct io_kiocb, list);
-		unsigned dist;
+		unsigned nxt_sq_head;
+		long long tmp, tmp_nxt;
 
-		dist = nxt->sequence - tail_index;
-		if (req_dist >= dist)
+		/*
+		 * Since cached_sq_head + count - 1 can overflow, use type long
+		 * long to store it.
+		 */
+		tmp = (long long)ctx->cached_sq_head + count - 1;
+		nxt_sq_head = nxt->sequence - nxt->submit.sequence + 1;
+		tmp_nxt = (long long)nxt_sq_head + nxt->submit.sequence - 1;
+
+		/*
+		 * cached_sq_head may overflow, and it will never overflow twice
+		 * once there is some timeout req still be valid.
+		 */
+		if (ctx->cached_sq_head < nxt_sq_head)
+			tmp_nxt += UINT_MAX;
+
+		if (tmp >= tmp_nxt)
 			break;
 	}
 	list_add(&req->list, entry);
-- 
cgit v1.2.3


From 193065024072c0d6f2972142d5df5a00b33324c6 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 15 Oct 2019 14:26:06 +0100
Subject: drm/i915: Flush tasklet submission before sleeping on
 i915_request_wait

If the system is being slow and userspace is racing ahead of the GPU and
finds itself waiting for the GPU to catch up, before the process sleeps
give the tasklet a kick, bypassing ksoftirqd. If the system is
overloaded, then ksoftirqd may be delayed incurring additional latency
to our user.

This should not be a frequent problem, but in the past we have observed
several hundred millisecond delays before ksoftirqd services an
interrupt, so burn a few cycles to lend a helping hand.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015132606.14349-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_request.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index b8a54572a4f8..f1cadad4e81c 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1496,6 +1496,7 @@ long i915_request_wait(struct i915_request *rq,
 			break;
 		}
 
+		intel_engine_flush_submission(rq->engine);
 		timeout = io_schedule_timeout(timeout);
 	}
 	__set_current_state(TASK_RUNNING);
-- 
cgit v1.2.3


From 1d3f87233e26362fc3d4e59f0f31a71b570f90b9 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Thu, 26 Sep 2019 16:05:11 -0400
Subject: ceph: just skip unrecognized info in ceph_reply_info_extra

In the future, we're going to want to extend the ceph_reply_info_extra
for create replies. Currently though, the kernel code doesn't accept an
extra blob that is larger than the expected data.

Change the code to skip over any unrecognized fields at the end of the
extra blob, rather than returning -EIO.

Cc: stable@vger.kernel.org
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 fs/ceph/mds_client.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a8a8f84f3bbf..a5163296d9d9 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -384,8 +384,8 @@ static int parse_reply_info_readdir(void **p, void *end,
 	}
 
 done:
-	if (*p != end)
-		goto bad;
+	/* Skip over any unrecognized fields */
+	*p = end;
 	return 0;
 
 bad:
@@ -406,12 +406,10 @@ static int parse_reply_info_filelock(void **p, void *end,
 		goto bad;
 
 	info->filelock_reply = *p;
-	*p += sizeof(*info->filelock_reply);
 
-	if (unlikely(*p != end))
-		goto bad;
+	/* Skip over any unrecognized fields */
+	*p = end;
 	return 0;
-
 bad:
 	return -EIO;
 }
@@ -425,18 +423,21 @@ static int parse_reply_info_create(void **p, void *end,
 {
 	if (features == (u64)-1 ||
 	    (features & CEPH_FEATURE_REPLY_CREATE_INODE)) {
+		/* Malformed reply? */
 		if (*p == end) {
 			info->has_create_ino = false;
 		} else {
 			info->has_create_ino = true;
-			info->ino = ceph_decode_64(p);
+			ceph_decode_64_safe(p, end, info->ino, bad);
 		}
+	} else {
+		if (*p != end)
+			goto bad;
 	}
 
-	if (unlikely(*p != end))
-		goto bad;
+	/* Skip over any unrecognized fields */
+	*p = end;
 	return 0;
-
 bad:
 	return -EIO;
 }
-- 
cgit v1.2.3


From 25e6be21230d3208d687dad90b6e43419013c351 Mon Sep 17 00:00:00 2001
From: Dongsheng Yang <dongsheng.yang@easystack.cn>
Date: Fri, 27 Sep 2019 15:33:22 +0000
Subject: rbd: cancel lock_dwork if the wait is interrupted

There is a warning message in my test with below steps:

  # rbd bench --io-type write --io-size 4K --io-threads 1 --io-pattern rand test &
  # sleep 5
  # pkill -9 rbd
  # rbd map test &
  # sleep 5
  # pkill rbd

The reason is that the rbd_add_acquire_lock() is interruptable,
that means, when we kill the waiting on ->acquire_wait, the lock_dwork
could be still running.

1. do_rbd_add()					2. lock_dwork
rbd_add_acquire_lock()
  - queue_delayed_work()
						lock_dwork queued
    - wait_for_completion_killable_timeout()  <-- kill happen
rbd_dev_image_unlock()	<-- UNLOCKED now, nothing to do.
rbd_dev_device_release()
rbd_dev_image_release()
  - ...
						lock successed here
     - cancel_delayed_work_sync(&rbd_dev->lock_dwork)

Then when we reach the rbd_dev_free(), WARN_ON is triggered because
lock_state is not RBD_LOCK_STATE_UNLOCKED.

To fix it, this commit make sure the lock_dwork was finished before
calling rbd_dev_image_unlock().

On the other hand, this would not happend in do_rbd_remove(), because
after rbd mapped, lock_dwork will only be queued for IO request, and
request will continue unless lock_dwork finished. when we call
rbd_dev_image_unlock() in do_rbd_remove(), all requests are done.
That means, lock_state should not be locked again after
rbd_dev_image_unlock().

[ Cancel lock_dwork in rbd_add_acquire_lock(), only if the wait is
  interrupted. ]

Fixes: 637cd060537d ("rbd: new exclusive lock wait/wake code")
Signed-off-by: Dongsheng Yang <dongsheng.yang@easystack.cn>
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
---
 drivers/block/rbd.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 7c4350c0fb77..39136675dae5 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -6639,10 +6639,13 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
 	queue_delayed_work(rbd_dev->task_wq, &rbd_dev->lock_dwork, 0);
 	ret = wait_for_completion_killable_timeout(&rbd_dev->acquire_wait,
 			    ceph_timeout_jiffies(rbd_dev->opts->lock_timeout));
-	if (ret > 0)
+	if (ret > 0) {
 		ret = rbd_dev->acquire_err;
-	else if (!ret)
-		ret = -ETIMEDOUT;
+	} else {
+		cancel_delayed_work_sync(&rbd_dev->lock_dwork);
+		if (!ret)
+			ret = -ETIMEDOUT;
+	}
 
 	if (ret) {
 		rbd_warn(rbd_dev, "failed to acquire exclusive lock: %ld", ret);
-- 
cgit v1.2.3


From 5e0cd1ef64744e41e029dfca7d0ae285c486f386 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 15 Oct 2019 08:46:07 -0700
Subject: xfs: change the seconds fields in xfs_bulkstat to signed

64-bit time is a signed quantity in the kernel, so the bulkstat
structure should reflect that.  Note that the structure size stays
the same and that we have not yet published userspace headers for this
new ioctl so there are no users to break.

Fixes: 7035f9724f84 ("xfs: introduce new v5 bulkstat structure")
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_fs.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 39dd2b908106..e9371a8e0e26 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -366,11 +366,11 @@ struct xfs_bulkstat {
 	uint64_t	bs_blocks;	/* number of blocks		*/
 	uint64_t	bs_xflags;	/* extended flags		*/
 
-	uint64_t	bs_atime;	/* access time, seconds		*/
-	uint64_t	bs_mtime;	/* modify time, seconds		*/
+	int64_t		bs_atime;	/* access time, seconds		*/
+	int64_t		bs_mtime;	/* modify time, seconds		*/
 
-	uint64_t	bs_ctime;	/* inode change time, seconds	*/
-	uint64_t	bs_btime;	/* creation time, seconds	*/
+	int64_t		bs_ctime;	/* inode change time, seconds	*/
+	int64_t		bs_btime;	/* creation time, seconds	*/
 
 	uint32_t	bs_gen;		/* generation count		*/
 	uint32_t	bs_uid;		/* user id			*/
-- 
cgit v1.2.3


From 9d179b865449b351ad5cb76dbea480c9170d4a27 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 15 Oct 2019 09:03:47 -0700
Subject: blkcg: Fix multiple bugs in blkcg_activate_policy()

blkcg_activate_policy() has the following bugs.

* cf09a8ee19ad ("blkcg: pass @q and @blkcg into
  blkcg_pol_alloc_pd_fn()") added @blkcg to ->pd_alloc_fn(); however,
  blkcg_activate_policy() ends up using pd's allocated for the root
  blkcg for all preallocations, so ->pd_init_fn() for non-root blkcgs
  can be passed in pd's which are allocated for the root blkcg.

  For blk-iocost, this means that ->pd_init_fn() can write beyond the
  end of the allocated object as it determines the length of the flex
  array at the end based on the blkcg's nesting level.

* Each pd is initialized as they get allocated.  If alloc fails, the
  policy will get freed with pd's initialized on it.

* After the above partial failure, the partial pds are not freed.

This patch fixes all the above issues by

* Restructuring blkcg_activate_policy() so that alloc and init passes
  are separate.  Init takes place only after all allocs succeeded and
  on failure all allocated pds are freed.

* Unifying and fixing the cleanup of the remaining pd_prealloc.

Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: cf09a8ee19ad ("blkcg: pass @q and @blkcg into blkcg_pol_alloc_pd_fn()")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c | 69 ++++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 51 insertions(+), 18 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index b6f20be0fc78..5d21027b1faf 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1362,7 +1362,7 @@ int blkcg_activate_policy(struct request_queue *q,
 			  const struct blkcg_policy *pol)
 {
 	struct blkg_policy_data *pd_prealloc = NULL;
-	struct blkcg_gq *blkg;
+	struct blkcg_gq *blkg, *pinned_blkg = NULL;
 	int ret;
 
 	if (blkcg_policy_enabled(q, pol))
@@ -1370,49 +1370,82 @@ int blkcg_activate_policy(struct request_queue *q,
 
 	if (queue_is_mq(q))
 		blk_mq_freeze_queue(q);
-pd_prealloc:
-	if (!pd_prealloc) {
-		pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q, &blkcg_root);
-		if (!pd_prealloc) {
-			ret = -ENOMEM;
-			goto out_bypass_end;
-		}
-	}
-
+retry:
 	spin_lock_irq(&q->queue_lock);
 
-	/* blkg_list is pushed at the head, reverse walk to init parents first */
+	/* blkg_list is pushed at the head, reverse walk to allocate parents first */
 	list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) {
 		struct blkg_policy_data *pd;
 
 		if (blkg->pd[pol->plid])
 			continue;
 
-		pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q, &blkcg_root);
-		if (!pd)
-			swap(pd, pd_prealloc);
+		/* If prealloc matches, use it; otherwise try GFP_NOWAIT */
+		if (blkg == pinned_blkg) {
+			pd = pd_prealloc;
+			pd_prealloc = NULL;
+		} else {
+			pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q,
+					      blkg->blkcg);
+		}
+
 		if (!pd) {
+			/*
+			 * GFP_NOWAIT failed.  Free the existing one and
+			 * prealloc for @blkg w/ GFP_KERNEL.
+			 */
+			if (pinned_blkg)
+				blkg_put(pinned_blkg);
+			blkg_get(blkg);
+			pinned_blkg = blkg;
+
 			spin_unlock_irq(&q->queue_lock);
-			goto pd_prealloc;
+
+			if (pd_prealloc)
+				pol->pd_free_fn(pd_prealloc);
+			pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q,
+						       blkg->blkcg);
+			if (pd_prealloc)
+				goto retry;
+			else
+				goto enomem;
 		}
 
 		blkg->pd[pol->plid] = pd;
 		pd->blkg = blkg;
 		pd->plid = pol->plid;
-		if (pol->pd_init_fn)
-			pol->pd_init_fn(pd);
 	}
 
+	/* all allocated, init in the same order */
+	if (pol->pd_init_fn)
+		list_for_each_entry_reverse(blkg, &q->blkg_list, q_node)
+			pol->pd_init_fn(blkg->pd[pol->plid]);
+
 	__set_bit(pol->plid, q->blkcg_pols);
 	ret = 0;
 
 	spin_unlock_irq(&q->queue_lock);
-out_bypass_end:
+out:
 	if (queue_is_mq(q))
 		blk_mq_unfreeze_queue(q);
+	if (pinned_blkg)
+		blkg_put(pinned_blkg);
 	if (pd_prealloc)
 		pol->pd_free_fn(pd_prealloc);
 	return ret;
+
+enomem:
+	/* alloc failed, nothing's initialized yet, free everything */
+	spin_lock_irq(&q->queue_lock);
+	list_for_each_entry(blkg, &q->blkg_list, q_node) {
+		if (blkg->pd[pol->plid]) {
+			pol->pd_free_fn(blkg->pd[pol->plid]);
+			blkg->pd[pol->plid] = NULL;
+		}
+	}
+	spin_unlock_irq(&q->queue_lock);
+	ret = -ENOMEM;
+	goto out;
 }
 EXPORT_SYMBOL_GPL(blkcg_activate_policy);
 
-- 
cgit v1.2.3


From 307f4065b9d7c1e887e8bdfb2487e4638559fea1 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 15 Oct 2019 08:49:27 -0700
Subject: blk-rq-qos: fix first node deletion of rq_qos_del()

rq_qos_del() incorrectly assigns the node being deleted to the head if
it was the first on the list in the !prev path.  Fix it by iterating
with ** instead.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Fixes: a79050434b45 ("blk-rq-qos: refactor out common elements of blk-wbt")
Cc: stable@vger.kernel.org # v4.19+
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-rq-qos.h | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index e8cb68f6958a..2bc43e94f4c4 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -108,16 +108,13 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
 
 static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
 {
-	struct rq_qos *cur, *prev = NULL;
-	for (cur = q->rq_qos; cur; cur = cur->next) {
-		if (cur == rqos) {
-			if (prev)
-				prev->next = rqos->next;
-			else
-				q->rq_qos = cur;
+	struct rq_qos **cur;
+
+	for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) {
+		if (*cur == rqos) {
+			*cur = rqos->next;
 			break;
 		}
-		prev = cur;
 	}
 
 	blk_mq_debugfs_unregister_rqos(rqos);
-- 
cgit v1.2.3


From 5b3ec8134f5f9fa1ed0a538441a495521078bbee Mon Sep 17 00:00:00 2001
From: Steven Price <steven.price@arm.com>
Date: Wed, 9 Oct 2019 10:44:55 +0100
Subject: drm/panfrost: Handle resetting on timeout better

Panfrost uses multiple schedulers (one for each slot, so 2 in reality),
and on a timeout has to stop all the schedulers to safely perform a
reset. However more than one scheduler can trigger a timeout at the same
time. This race condition results in jobs being freed while they are
still in use.

When stopping other slots use cancel_delayed_work_sync() to ensure that
any timeout started for that slot has completed. Also use
mutex_trylock() to obtain reset_lock. This means that only one thread
attempts the reset, the other threads will simply complete without doing
anything (the first thread will wait for this in the call to
cancel_delayed_work_sync()).

While we're here and since the function is already dependent on
sched_job not being NULL, let's remove the unnecessary checks.

Fixes: aa20236784ab ("drm/panfrost: Prevent concurrent resets")
Tested-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Steven Price <steven.price@arm.com>
Cc: stable@vger.kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20191009094456.9704-1-steven.price@arm.com
---
 drivers/gpu/drm/panfrost/panfrost_job.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index a58551668d9a..21f34d44aac2 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -381,13 +381,19 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
 		job_read(pfdev, JS_TAIL_LO(js)),
 		sched_job);
 
-	mutex_lock(&pfdev->reset_lock);
+	if (!mutex_trylock(&pfdev->reset_lock))
+		return;
 
-	for (i = 0; i < NUM_JOB_SLOTS; i++)
-		drm_sched_stop(&pfdev->js->queue[i].sched, sched_job);
+	for (i = 0; i < NUM_JOB_SLOTS; i++) {
+		struct drm_gpu_scheduler *sched = &pfdev->js->queue[i].sched;
+
+		drm_sched_stop(sched, sched_job);
+		if (js != i)
+			/* Ensure any timeouts on other slots have finished */
+			cancel_delayed_work_sync(&sched->work_tdr);
+	}
 
-	if (sched_job)
-		drm_sched_increase_karma(sched_job);
+	drm_sched_increase_karma(sched_job);
 
 	spin_lock_irqsave(&pfdev->js->job_lock, flags);
 	for (i = 0; i < NUM_JOB_SLOTS; i++) {
-- 
cgit v1.2.3


From 8e0d0ad206f08506c893326ca7c9c3d9cc042cef Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 15 Oct 2019 09:56:36 -0700
Subject: sparc64: disable fast-GUP due to unexplained oopses

HAVE_FAST_GUP enables the lockless quick page table walker for simple
cases, and is a nice optimization for some random loads that can then
use get_user_pages_fast() rather than the more careful page walker.

However, for some unexplained reason, it seems to be subtly broken on
sparc64.  The breakage is only with some compiler versions and some
hardware, and nobody seems to have figured out what triggers it,
although there's a simple reprodicer for the problem when it does
trigger.

The problem was introduced with the conversion to the generic GUP code
in commit 7b9afb86b632 ("sparc64: use the generic get_user_pages_fast
code"), but nothing looks obviously wrong in that conversion.  It may be
a compiler bug that just hits us with the code reorganization.  Or it
may be something very specific to sparc64.

This disables HAVE_FAST_GUP entirely.  That makes things like futexes a
bit slower, but at least they work.  If we can figure out the trigger,
that would be lovely, but it's been three months already..

Link: https://lore.kernel.org/lkml/20190717215956.GA30369@altlinux.org/
Fixes: 7b9afb86b632 ("sparc64: use the generic get_user_pages_fast code")
Reported-by: Dmitry V Levin <ldv@altlinux.org>
Reported-by: Anatoly Pugachev <matorola@gmail.com>
Requested-by: Meelis Roos <mroos@linux.ee>
Suggested-by: Christoph Hellwig <hch@infradead.org>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/sparc/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index fbc1aecf0f94..eb24cb1afc11 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -29,7 +29,6 @@ config SPARC
 	select RTC_DRV_M48T59
 	select RTC_SYSTOHC
 	select HAVE_ARCH_JUMP_LABEL if SPARC64
-	select HAVE_FAST_GUP if SPARC64
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_PCI_IOMAP
-- 
cgit v1.2.3


From da5d2ca8adde6adadcc42e3dd87bcc01e7e4f3f9 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:44:11 +0300
Subject: drm/i915/icl: Wa_1607087056

Avoid possible hang in tsg,vfe units by keeping
l3 clocks runnings.

Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015154411.9984-1-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 5 +++++
 drivers/gpu/drm/i915/i915_reg.h             | 2 ++
 2 files changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index ba65e5018978..81d299b27fbc 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -892,6 +892,11 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	wa_write_or(wal,
 		    GAMT_CHKN_BIT_REG,
 		    GAMT_CHKN_DISABLE_L3_COH_PIPE);
+
+	/* Wa_1607087056:icl */
+	wa_write_or(wal,
+		    SLICE_UNIT_LEVEL_CLKGATE,
+		    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
 }
 
 static void
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 7dd126cc3ac3..821159c4cd32 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4050,6 +4050,8 @@ enum {
 #define  SARBUNIT_CLKGATE_DIS		(1 << 5)
 #define  RCCUNIT_CLKGATE_DIS		(1 << 7)
 #define  MSCUNIT_CLKGATE_DIS		(1 << 10)
+#define  L3_CLKGATE_DIS			REG_BIT(16)
+#define  L3_CR2X_CLKGATE_DIS		REG_BIT(17)
 
 #define SUBSLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x9524)
 #define  GWUNIT_CLKGATE_DIS		(1 << 16)
-- 
cgit v1.2.3


From 613716bbe721236a09167b64124c13c85ee69962 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:44:39 +0300
Subject: drm/i915/tgl: Add IS_TGL_REVID

We are going to need this macro on limiting
the workaround scope.

Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015154449.10338-1-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/i915_drv.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c46b339064c0..f6aee1e01a7f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1686,6 +1686,11 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define IS_ICL_REVID(p, since, until) \
 	(IS_ICELAKE(p) && IS_REVID(p, since, until))
 
+#define TGL_REVID_A0		0x0
+
+#define IS_TGL_REVID(p, since, until) \
+	(IS_TIGERLAKE(p) && IS_REVID(p, since, until))
+
 #define IS_LP(dev_priv)	(INTEL_INFO(dev_priv)->is_lp)
 #define IS_GEN9_LP(dev_priv)	(IS_GEN(dev_priv, 9) && IS_LP(dev_priv))
 #define IS_GEN9_BC(dev_priv)	(IS_GEN(dev_priv, 9) && !IS_LP(dev_priv))
-- 
cgit v1.2.3


From 62037ffff229b7d94f1db5ef8d2e2ec819832ef3 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:44:40 +0300
Subject: drm/i915/tgl: Include ro parts of l3 to invalidate

Aim for completeness and invalidate also the ro parts
in l3 cache. This might allow to get rid of the preparser
disable/enable workaround on invalidation path.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015154449.10338-2-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 1 +
 drivers/gpu/drm/i915/gt/intel_lrc.c          | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index 8e63cffcabe0..afc869dc785f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -233,6 +233,7 @@
 #define   PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH	(1<<12) /* gen6+ */
 #define   PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE	(1<<11) /* MBZ on ILK */
 #define   PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE		(1<<10) /* GM45+ only */
+#define   PIPE_CONTROL_L3_RO_CACHE_INVALIDATE		REG_BIT(10) /* gen12 */
 #define   PIPE_CONTROL_INDIRECT_STATE_DISABLE		(1<<9)
 #define   PIPE_CONTROL_NOTIFY				(1<<8)
 #define   PIPE_CONTROL_FLUSH_ENABLE			(1<<7) /* gen7+ */
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 1e9e2cc168f7..217f6513e117 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -3230,6 +3230,7 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_VF_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_CONST_CACHE_INVALIDATE;
 		flags |= PIPE_CONTROL_STATE_CACHE_INVALIDATE;
+		flags |= PIPE_CONTROL_L3_RO_CACHE_INVALIDATE;
 
 		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 		flags |= PIPE_CONTROL_QW_WRITE;
-- 
cgit v1.2.3


From 4aa0b5d457f5d29522b5db4aeb4587fc4dc24054 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:44:41 +0300
Subject: drm/i915/tgl: Add HDC Pipeline Flush

Add hdc pipeline flush to ensure memory state is coherent
in L3 when we are done.

v2: Flush also in breadcrumbs (Chris)

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015154449.10338-3-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_gpu_commands.h | 1 +
 drivers/gpu/drm/i915/gt/intel_lrc.c          | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
index afc869dc785f..4294f146f13c 100644
--- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
+++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h
@@ -235,6 +235,7 @@
 #define   PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE		(1<<10) /* GM45+ only */
 #define   PIPE_CONTROL_L3_RO_CACHE_INVALIDATE		REG_BIT(10) /* gen12 */
 #define   PIPE_CONTROL_INDIRECT_STATE_DISABLE		(1<<9)
+#define   PIPE_CONTROL_HDC_PIPELINE_FLUSH		REG_BIT(9)  /* gen12 */
 #define   PIPE_CONTROL_NOTIFY				(1<<8)
 #define   PIPE_CONTROL_FLUSH_ENABLE			(1<<7) /* gen7+ */
 #define   PIPE_CONTROL_DC_FLUSH_ENABLE			(1<<5)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 217f6513e117..d1b10f00d729 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -3205,6 +3205,7 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
 		flags |= PIPE_CONTROL_DC_FLUSH_ENABLE;
 		flags |= PIPE_CONTROL_FLUSH_ENABLE;
+		flags |= PIPE_CONTROL_HDC_PIPELINE_FLUSH;
 
 		flags |= PIPE_CONTROL_STORE_DATA_INDEX;
 		flags |= PIPE_CONTROL_QW_WRITE;
@@ -3415,7 +3416,8 @@ gen12_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 				      PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
 				      PIPE_CONTROL_DEPTH_CACHE_FLUSH |
 				      PIPE_CONTROL_DC_FLUSH_ENABLE |
-				      PIPE_CONTROL_FLUSH_ENABLE);
+				      PIPE_CONTROL_FLUSH_ENABLE |
+				      PIPE_CONTROL_HDC_PIPELINE_FLUSH);
 
 	return gen12_emit_fini_breadcrumb_footer(request, cs);
 }
-- 
cgit v1.2.3


From 36a6b5d964d995b536b1925ec42052ee40ba92c4 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:44:42 +0300
Subject: drm/i915/tgl: Add extra hdc flush workaround

In order to ensure constant caches are invalidated
properly with a0, we need extra hdc flush after invalidation.

v2: use IS_TGL_REVID (Chris)

References: HSDES#1604544889
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015154449.10338-4-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index d1b10f00d729..62d5ece95c9d 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -3253,6 +3253,26 @@ static int gen12_emit_flush_render(struct i915_request *request,
 
 		*cs++ = preparser_disable(false);
 		intel_ring_advance(request, cs);
+
+		/*
+		 * Wa_1604544889:tgl
+		 */
+		if (IS_TGL_REVID(request->i915, TGL_REVID_A0, TGL_REVID_A0)) {
+			flags = 0;
+			flags |= PIPE_CONTROL_CS_STALL;
+			flags |= PIPE_CONTROL_HDC_PIPELINE_FLUSH;
+
+			flags |= PIPE_CONTROL_STORE_DATA_INDEX;
+			flags |= PIPE_CONTROL_QW_WRITE;
+
+			cs = intel_ring_begin(request, 6);
+			if (IS_ERR(cs))
+				return PTR_ERR(cs);
+
+			cs = gen8_emit_pipe_control(cs, flags,
+						    LRC_PPHWSP_SCRATCH_ADDR);
+			intel_ring_advance(request, cs);
+		}
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 99739f9431f9fa8b4706dfa4c99389b400b8af23 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:44:43 +0300
Subject: drm/i915/tgl: Keep FF dop clock enabled for A0

To ensure correct state data for compute workloads, we
need to keep the ff dop clock enabled.

References: HSDES#1606700617
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015154449.10338-5-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 9 ++++++++-
 drivers/gpu/drm/i915/i915_reg.h             | 1 +
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 81d299b27fbc..bc5fdb4e47b1 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -567,7 +567,7 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
-	/* Wa_1409142259 */
+	/* Wa_1409142259:tgl */
 	WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 			  GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
 }
@@ -1265,6 +1265,13 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 {
 	struct drm_i915_private *i915 = engine->i915;
 
+	if (IS_TGL_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) {
+		/* Wa_1606700617:tgl */
+		wa_masked_en(wal,
+			     GEN9_CS_DEBUG_MODE1,
+			     FF_DOP_CLOCK_GATE_DISABLE);
+	}
+
 	if (IS_GEN(i915, 11)) {
 		/* This is not an Wa. Enable for better image quality */
 		wa_masked_en(wal,
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 821159c4cd32..4b58861b5114 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7673,6 +7673,7 @@ enum {
 #define  GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE  (1 << 10)
 
 #define GEN9_CS_DEBUG_MODE1		_MMIO(0x20ec)
+#define   FF_DOP_CLOCK_GATE_DISABLE	REG_BIT(1)
 #define GEN9_CTX_PREEMPT_REG		_MMIO(0x2248)
 #define GEN8_CS_CHICKEN1		_MMIO(0x2580)
 #define GEN9_PREEMPT_3D_OBJECT_LEVEL		(1 << 0)
-- 
cgit v1.2.3


From 65df78bda385a905d086a787fd186506aea87df4 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:44:44 +0300
Subject: drm/i915/tgl: Wa_1409420604

Avoid possible hang in CPSS unit.

Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015154449.10338-6-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 5 +++++
 drivers/gpu/drm/i915/i915_reg.h             | 3 +++
 2 files changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index bc5fdb4e47b1..7fea61b00b99 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -902,6 +902,11 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 static void
 tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
+	/* Wa_1409420604:tgl */
+	if (IS_TGL_REVID(i915, TGL_REVID_A0, TGL_REVID_A0))
+		wa_write_or(wal,
+			    SUBSLICE_UNIT_LEVEL_CLKGATE2,
+			    CPSSUNIT_CLKGATE_DIS);
 }
 
 static void
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4b58861b5114..449648a28a67 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4056,6 +4056,9 @@ enum {
 #define SUBSLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x9524)
 #define  GWUNIT_CLKGATE_DIS		(1 << 16)
 
+#define SUBSLICE_UNIT_LEVEL_CLKGATE2	_MMIO(0x9528)
+#define  CPSSUNIT_CLKGATE_DIS		REG_BIT(9)
+
 #define UNSLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x9434)
 #define  VFUNIT_CLKGATE_DIS		(1 << 20)
 
-- 
cgit v1.2.3


From 2cbe2d8c562eab58347b39342e37c7a2adbe7fef Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:44:45 +0300
Subject: drm/i915/tgl: Wa_1409170338

Avoid possible hang in tsg,vfe units by keeping
l3 clocks runnings.

Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015154449.10338-7-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 7fea61b00b99..4f9be2eee132 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -907,6 +907,12 @@ tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		wa_write_or(wal,
 			    SUBSLICE_UNIT_LEVEL_CLKGATE2,
 			    CPSSUNIT_CLKGATE_DIS);
+
+	/* Wa_1409180338:tgl */
+	if (IS_TGL_REVID(i915, TGL_REVID_A0, TGL_REVID_A0))
+		wa_write_or(wal,
+			    SLICE_UNIT_LEVEL_CLKGATE,
+			    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
 }
 
 static void
-- 
cgit v1.2.3


From 2e19af943822710cf00621eb32cc82394441bb60 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:44:46 +0300
Subject: drm/i915/tgl: Wa_1409600907

To avoid possible hang, we need to add depth stall if we flush the
depth cache.

Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015154449.10338-8-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 62d5ece95c9d..d64b4d868b75 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -3203,6 +3203,8 @@ static int gen12_emit_flush_render(struct i915_request *request,
 		flags |= PIPE_CONTROL_TILE_CACHE_FLUSH;
 		flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH;
 		flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH;
+		/* Wa_1409600907:tgl */
+		flags |= PIPE_CONTROL_DEPTH_STALL;
 		flags |= PIPE_CONTROL_DC_FLUSH_ENABLE;
 		flags |= PIPE_CONTROL_FLUSH_ENABLE;
 		flags |= PIPE_CONTROL_HDC_PIPELINE_FLUSH;
@@ -3435,6 +3437,8 @@ gen12_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 				      PIPE_CONTROL_TILE_CACHE_FLUSH |
 				      PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
 				      PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+				      /* Wa_1409600907:tgl */
+				      PIPE_CONTROL_DEPTH_STALL |
 				      PIPE_CONTROL_DC_FLUSH_ENABLE |
 				      PIPE_CONTROL_FLUSH_ENABLE |
 				      PIPE_CONTROL_HDC_PIPELINE_FLUSH);
-- 
cgit v1.2.3


From 79bfa607e60f12daa3db8b1b3834219818a153e2 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:44:47 +0300
Subject: drm/i915/tgl: Wa_1607138336

Avoid possible deadlock on context switch.

Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015154449.10338-9-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 5 +++++
 drivers/gpu/drm/i915/i915_reg.h             | 2 ++
 2 files changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 4f9be2eee132..483725137291 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1281,6 +1281,11 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		wa_masked_en(wal,
 			     GEN9_CS_DEBUG_MODE1,
 			     FF_DOP_CLOCK_GATE_DISABLE);
+
+		/* Wa_1607138336:tgl */
+		wa_write_or(wal,
+			    GEN9_CTX_PREEMPT_REG,
+			    GEN12_DISABLE_POSH_BUSY_FF_DOP_CG);
 	}
 
 	if (IS_GEN(i915, 11)) {
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 449648a28a67..baf5939df1ec 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7678,6 +7678,8 @@ enum {
 #define GEN9_CS_DEBUG_MODE1		_MMIO(0x20ec)
 #define   FF_DOP_CLOCK_GATE_DISABLE	REG_BIT(1)
 #define GEN9_CTX_PREEMPT_REG		_MMIO(0x2248)
+#define   GEN12_DISABLE_POSH_BUSY_FF_DOP_CG REG_BIT(11)
+
 #define GEN8_CS_CHICKEN1		_MMIO(0x2580)
 #define GEN9_PREEMPT_3D_OBJECT_LEVEL		(1 << 0)
 #define GEN9_PREEMPT_GPGPU_LEVEL(hi, lo)	(((hi) << 2) | ((lo) << 1))
-- 
cgit v1.2.3


From 99db8c59e056e1e1a97845dbd38a3a6f47be6b7d Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:44:48 +0300
Subject: drm/i915/tgl: Wa_1607030317, Wa_1607186500, Wa_1607297627

Disable semaphore idle messages and wait for event
power downs.

Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015154449.10338-10-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_workarounds.c | 8 ++++++++
 drivers/gpu/drm/i915/i915_reg.h             | 1 +
 2 files changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 483725137291..af8a8183154a 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -1286,6 +1286,14 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		wa_write_or(wal,
 			    GEN9_CTX_PREEMPT_REG,
 			    GEN12_DISABLE_POSH_BUSY_FF_DOP_CG);
+
+		/* Wa_1607030317:tgl */
+		/* Wa_1607186500:tgl */
+		/* Wa_1607297627:tgl */
+		wa_masked_en(wal,
+			     GEN6_RC_SLEEP_PSMI_CONTROL,
+			     GEN12_WAIT_FOR_EVENT_POWER_DOWN_DISABLE |
+			     GEN8_RC_SEMA_IDLE_MSG_DISABLE);
 	}
 
 	if (IS_GEN(i915, 11)) {
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index baf5939df1ec..855db888516c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2885,6 +2885,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 #define GEN6_RC_SLEEP_PSMI_CONTROL	_MMIO(0x2050)
 #define   GEN6_PSMI_SLEEP_MSG_DISABLE	(1 << 0)
+#define   GEN12_WAIT_FOR_EVENT_POWER_DOWN_DISABLE REG_BIT(7)
 #define   GEN8_RC_SEMA_IDLE_MSG_DISABLE	(1 << 12)
 #define   GEN8_FF_DOP_CLOCK_GATE_DISABLE	(1 << 10)
 
-- 
cgit v1.2.3


From 08fff7aeddc9dd72161b4c8fc27fbab12b4b9352 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:44:49 +0300
Subject: drm/i915/tgl: Wa_1607138340

Avoid possible cs hang with semaphores by disabling
lite restore.

Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015154449.10338-11-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index d64b4d868b75..44f213fd7604 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1048,6 +1048,10 @@ static u64 execlists_update_context(const struct i915_request *rq)
 	desc = ce->lrc_desc;
 	ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE;
 
+	/* Wa_1607138340:tgl */
+	if (IS_TGL_REVID(rq->i915, TGL_REVID_A0, TGL_REVID_A0))
+		desc |= CTX_DESC_FORCE_RESTORE;
+
 	return desc;
 }
 
-- 
cgit v1.2.3


From b0818f80c8c1bc215bba276bd61c216014fab23b Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Fri, 11 Oct 2019 18:14:55 -0700
Subject: blackhole_netdev: fix syzkaller reported issue

While invalidating the dst, we assign backhole_netdev instead of
loopback device. However, this device does not have idev pointer
and hence no ip6_ptr even if IPv6 is enabled. Possibly this has
triggered the syzbot reported crash.

The syzbot report does not have reproducer, however, this is the
only device that doesn't have matching idev created.

Crash instruction is :

static inline bool ip6_ignore_linkdown(const struct net_device *dev)
{
        const struct inet6_dev *idev = __in6_dev_get(dev);

        return !!idev->cnf.ignore_routes_with_linkdown; <= crash
}

Also ipv6 always assumes presence of idev and never checks for it
being NULL (as does the above referenced code). So adding a idev
for the blackhole_netdev to avoid this class of crashes in the future.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c |  7 ++++++-
 net/ipv6/route.c    | 15 ++++++---------
 2 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 34ccef18b40e..4c87594d1389 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6996,7 +6996,7 @@ static struct rtnl_af_ops inet6_ops __read_mostly = {
 
 int __init addrconf_init(void)
 {
-	struct inet6_dev *idev;
+	struct inet6_dev *idev, *bdev;
 	int i, err;
 
 	err = ipv6_addr_label_init();
@@ -7036,10 +7036,14 @@ int __init addrconf_init(void)
 	 */
 	rtnl_lock();
 	idev = ipv6_add_dev(init_net.loopback_dev);
+	bdev = ipv6_add_dev(blackhole_netdev);
 	rtnl_unlock();
 	if (IS_ERR(idev)) {
 		err = PTR_ERR(idev);
 		goto errlo;
+	} else if (IS_ERR(bdev)) {
+		err = PTR_ERR(bdev);
+		goto errlo;
 	}
 
 	ip6_route_init_special_entries();
@@ -7124,6 +7128,7 @@ void addrconf_cleanup(void)
 		addrconf_ifdown(dev, 1);
 	}
 	addrconf_ifdown(init_net.loopback_dev, 2);
+	addrconf_ifdown(blackhole_netdev, 2);
 
 	/*
 	 *	Check hash table.
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a63ff85fe141..742120728869 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -155,10 +155,9 @@ void rt6_uncached_list_del(struct rt6_info *rt)
 
 static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
 {
-	struct net_device *loopback_dev = net->loopback_dev;
 	int cpu;
 
-	if (dev == loopback_dev)
+	if (dev == net->loopback_dev)
 		return;
 
 	for_each_possible_cpu(cpu) {
@@ -171,7 +170,7 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
 			struct net_device *rt_dev = rt->dst.dev;
 
 			if (rt_idev->dev == dev) {
-				rt->rt6i_idev = in6_dev_get(loopback_dev);
+				rt->rt6i_idev = in6_dev_get(blackhole_netdev);
 				in6_dev_put(rt_idev);
 			}
 
@@ -386,13 +385,11 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 {
 	struct rt6_info *rt = (struct rt6_info *)dst;
 	struct inet6_dev *idev = rt->rt6i_idev;
-	struct net_device *loopback_dev =
-		dev_net(dev)->loopback_dev;
 
-	if (idev && idev->dev != loopback_dev) {
-		struct inet6_dev *loopback_idev = in6_dev_get(loopback_dev);
-		if (loopback_idev) {
-			rt->rt6i_idev = loopback_idev;
+	if (idev && idev->dev != dev_net(dev)->loopback_dev) {
+		struct inet6_dev *ibdev = in6_dev_get(blackhole_netdev);
+		if (ibdev) {
+			rt->rt6i_idev = ibdev;
 			in6_dev_put(idev);
 		}
 	}
-- 
cgit v1.2.3


From 92696286f3bb37ba50e4bd8d1beb24afb759a799 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 11 Oct 2019 12:53:49 -0700
Subject: net: bcmgenet: Set phydev->dev_flags only for internal PHYs

phydev->dev_flags is entirely dependent on the PHY device driver which
is going to be used, setting the internal GENET PHY revision in those
bits only makes sense when drivers/net/phy/bcm7xxx.c is the PHY driver
being used.

Fixes: 487320c54143 ("net: bcmgenet: communicate integrated PHY revision to PHY driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmmii.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 970e478a9017..94d1dd5d56bf 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -273,11 +273,12 @@ int bcmgenet_mii_probe(struct net_device *dev)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct device_node *dn = priv->pdev->dev.of_node;
 	struct phy_device *phydev;
-	u32 phy_flags;
+	u32 phy_flags = 0;
 	int ret;
 
 	/* Communicate the integrated PHY revision */
-	phy_flags = priv->gphy_rev;
+	if (priv->internal_phy)
+		phy_flags = priv->gphy_rev;
 
 	/* Initialize link state variables that bcmgenet_mii_setup() uses */
 	priv->old_link = -1;
-- 
cgit v1.2.3


From f913eac8e555bc776565a21ce84bf2bcc3715cbb Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Fri, 11 Oct 2019 20:43:03 -0600
Subject: net: Update address for vrf and l3mdev in MAINTAINERS

Use my kernel.org address for all entries in MAINTAINERS.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 55199ef7fa74..49e4b004917b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9126,7 +9126,7 @@ F:	drivers/auxdisplay/ks0108.c
 F:	include/linux/ks0108.h
 
 L3MDEV
-M:	David Ahern <dsa@cumulusnetworks.com>
+M:	David Ahern <dsahern@kernel.org>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	net/l3mdev
@@ -17439,7 +17439,7 @@ F:	include/linux/regulator/
 K:	regulator_get_optional
 
 VRF
-M:	David Ahern <dsa@cumulusnetworks.com>
+M:	David Ahern <dsahern@kernel.org>
 M:	Shrijeet Mukherjee <shrijeet@gmail.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
-- 
cgit v1.2.3


From ddc790e92b3afa4e366ffb41818cfcd19015031e Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 11 Oct 2019 21:03:33 -0700
Subject: net: ethernet: broadcom: have drivers select DIMLIB as needed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

NET_VENDOR_BROADCOM is intended to control a kconfig menu only.
It should not have anything to do with code generation.
As such, it should not select DIMLIB for all drivers under
NET_VENDOR_BROADCOM.  Instead each driver that needs DIMLIB should
select it (being the symbols SYSTEMPORT, BNXT, and BCMGENET).

Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1907021810220.13058@ramsan.of.borg/

Fixes: 4f75da3666c0 ("linux/dim: Move implementation to .c files")
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Uwe Kleine-König <uwe@kleine-koenig.org>
Cc: Tal Gilboa <talgi@mellanox.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Cc: netdev@vger.kernel.org
Cc: linux-rdma@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: Doug Ledford <dledford@redhat.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Leon Romanovsky <leonro@mellanox.com>
Cc: Or Gerlitz <ogerlitz@mellanox.com>
Cc: Sagi Grimberg <sagi@grimberg.me>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/Kconfig | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index e24f5d2b6afe..53055ce5dfd6 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -8,7 +8,6 @@ config NET_VENDOR_BROADCOM
 	default y
 	depends on (SSB_POSSIBLE && HAS_DMA) || PCI || BCM63XX || \
 		   SIBYTE_SB1xxx_SOC
-	select DIMLIB
 	---help---
 	  If you have a network (Ethernet) chipset belonging to this class,
 	  say Y.
@@ -69,6 +68,7 @@ config BCMGENET
 	select FIXED_PHY
 	select BCM7XXX_PHY
 	select MDIO_BCM_UNIMAC
+	select DIMLIB
 	help
 	  This driver supports the built-in Ethernet MACs found in the
 	  Broadcom BCM7xxx Set Top Box family chipset.
@@ -188,6 +188,7 @@ config SYSTEMPORT
 	select MII
 	select PHYLIB
 	select FIXED_PHY
+	select DIMLIB
 	help
 	  This driver supports the built-in Ethernet MACs found in the
 	  Broadcom BCM7xxx Set Top Box family chipset using an internal
@@ -200,6 +201,7 @@ config BNXT
 	select LIBCRC32C
 	select NET_DEVLINK
 	select PAGE_POOL
+	select DIMLIB
 	---help---
 	  This driver supports Broadcom NetXtreme-C/E 10/25/40/50 gigabit
 	  Ethernet cards.  To compile this driver as a module, choose M here:
-- 
cgit v1.2.3


From 09d6ac8dc51a033ae0043c1fe40b4d02563c2496 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 15 Oct 2019 12:54:17 -0700
Subject: libata/ahci: Fix PCS quirk application

Commit c312ef176399 "libata/ahci: Drop PCS quirk for Denverton and
beyond" got the polarity wrong on the check for which board-ids should
have the quirk applied. The board type board_ahci_pcs7 is defined at the
end of the list such that "pcs7" boards can be special cased in the
future if they need the quirk. All prior Intel board ids "<
board_ahci_pcs7" should proceed with applying the quirk.

Reported-by: Andreas Friedrich <afrie@gmx.net>
Reported-by: Stephen Douthit <stephend@silicom-usa.com>
Fixes: c312ef176399 ("libata/ahci: Drop PCS quirk for Denverton and beyond")
Cc: <stable@vger.kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/ata/ahci.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index dd92faf197d5..05c2b32dcc4d 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1600,7 +1600,9 @@ static void ahci_intel_pcs_quirk(struct pci_dev *pdev, struct ahci_host_priv *hp
 	 */
 	if (!id || id->vendor != PCI_VENDOR_ID_INTEL)
 		return;
-	if (((enum board_ids) id->driver_data) < board_ahci_pcs7)
+
+	/* Skip applying the quirk on Denverton and beyond */
+	if (((enum board_ids) id->driver_data) >= board_ahci_pcs7)
 		return;
 
 	/*
-- 
cgit v1.2.3


From 0a370db816f8632bc71d7d0c6f59a82d2934f0df Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Fri, 6 Sep 2019 15:50:12 +0200
Subject: drm: rcar-du: kms: Expand comment in vsps parsing routine

Expand comment in the 'vsps' parsing routine to specify the LIF
channel index defaults to 0 in case the second cell of the property
is not specified to remain compatible with older DT bindings.

Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
---
 drivers/gpu/drm/rcar-du/rcar_du_kms.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
index 2dc9caee8767..0d59f390de19 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
@@ -585,7 +585,11 @@ static int rcar_du_vsps_init(struct rcar_du_device *rcdu)
 
 		vsps[j].crtcs_mask |= BIT(i);
 
-		/* Store the VSP pointer and pipe index in the CRTC. */
+		/*
+		 * Store the VSP pointer and pipe index in the CRTC. If the
+		 * second cell of the 'vsps' specifier isn't present, default
+		 * to 0 to remain compatible with older DT bindings.
+		 */
 		rcdu->crtcs[i].vsp = &rcdu->vsps[j];
 		rcdu->crtcs[i].vsp_pipe = cells >= 1 ? args.args[0] : 0;
 	}
-- 
cgit v1.2.3


From 3986457110a054466bf02f9c4a85aa2bba96177b Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 17 Sep 2019 08:23:53 +0200
Subject: drm: rcar_lvds: Fix color mismatches on R-Car H2 ES2.0 and later

Commit 5cca30ebe089be23 ("drm/rcar-du: Add LVDS_LANES quirk") states
that LVDS lanes 1 and 3 are inverted on R-Car H2 ES1 only, and that the
problem has been fixed in newer revisions.

However, the code didn't take into account the actual hardware revision,
thus applying the quirk also on newer hardware revisions, causing green
color reversals.

Fix this by applying the quirk when running on R-Car H2 ES1.x only.

Reported-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Fixes: 5cca30ebe089be23 ("drm/rcar-du: Add LVDS_LANES quirk")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Reviewed-by: Ulrich Hecht <uli+renesas@fpond.eu>
Reviewed-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
---
 drivers/gpu/drm/rcar-du/rcar_lvds.c | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index 3fc7e6899cab..50c11a7f0467 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -16,6 +16,7 @@
 #include <linux/of_graph.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/sys_soc.h>
 
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
@@ -842,8 +843,23 @@ static int rcar_lvds_get_clocks(struct rcar_lvds *lvds)
 	return 0;
 }
 
+static const struct rcar_lvds_device_info rcar_lvds_r8a7790es1_info = {
+	.gen = 2,
+	.quirks = RCAR_LVDS_QUIRK_LANES,
+	.pll_setup = rcar_lvds_pll_setup_gen2,
+};
+
+static const struct soc_device_attribute lvds_quirk_matches[] = {
+	{
+		.soc_id = "r8a7790", .revision = "ES1.*",
+		.data = &rcar_lvds_r8a7790es1_info,
+	},
+	{ /* sentinel */ }
+};
+
 static int rcar_lvds_probe(struct platform_device *pdev)
 {
+	const struct soc_device_attribute *attr;
 	struct rcar_lvds *lvds;
 	struct resource *mem;
 	int ret;
@@ -857,6 +873,10 @@ static int rcar_lvds_probe(struct platform_device *pdev)
 	lvds->dev = &pdev->dev;
 	lvds->info = of_device_get_match_data(&pdev->dev);
 
+	attr = soc_device_match(lvds_quirk_matches);
+	if (attr)
+		lvds->info = attr->data;
+
 	ret = rcar_lvds_parse_dt(lvds);
 	if (ret < 0)
 		return ret;
@@ -893,12 +913,6 @@ static const struct rcar_lvds_device_info rcar_lvds_gen2_info = {
 	.pll_setup = rcar_lvds_pll_setup_gen2,
 };
 
-static const struct rcar_lvds_device_info rcar_lvds_r8a7790_info = {
-	.gen = 2,
-	.quirks = RCAR_LVDS_QUIRK_LANES,
-	.pll_setup = rcar_lvds_pll_setup_gen2,
-};
-
 static const struct rcar_lvds_device_info rcar_lvds_gen3_info = {
 	.gen = 3,
 	.quirks = RCAR_LVDS_QUIRK_PWD,
@@ -930,7 +944,7 @@ static const struct of_device_id rcar_lvds_of_table[] = {
 	{ .compatible = "renesas,r8a7744-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a774a1-lvds", .data = &rcar_lvds_gen3_info },
 	{ .compatible = "renesas,r8a774c0-lvds", .data = &rcar_lvds_r8a77990_info },
-	{ .compatible = "renesas,r8a7790-lvds", .data = &rcar_lvds_r8a7790_info },
+	{ .compatible = "renesas,r8a7790-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a7791-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a7793-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a7795-lvds", .data = &rcar_lvds_gen3_info },
-- 
cgit v1.2.3


From 2d4794f19a86fbfa5e74537b6cc1171414877724 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das@bp.renesas.com>
Date: Mon, 30 Sep 2019 10:15:02 +0100
Subject: dt-bindings: display: renesas: du: Document the r8a774b1 bindings

Document the RZ/G2N (R8A774B1) SoC in the R-Car DU bindings.

Signed-off-by: Biju Das <biju.das@bp.renesas.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Acked-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/display/renesas,du.txt | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/display/renesas,du.txt b/Documentation/devicetree/bindings/display/renesas,du.txt
index c97dfacad281..17cb2771364b 100644
--- a/Documentation/devicetree/bindings/display/renesas,du.txt
+++ b/Documentation/devicetree/bindings/display/renesas,du.txt
@@ -8,6 +8,7 @@ Required Properties:
     - "renesas,du-r8a7745" for R8A7745 (RZ/G1E) compatible DU
     - "renesas,du-r8a77470" for R8A77470 (RZ/G1C) compatible DU
     - "renesas,du-r8a774a1" for R8A774A1 (RZ/G2M) compatible DU
+    - "renesas,du-r8a774b1" for R8A774B1 (RZ/G2N) compatible DU
     - "renesas,du-r8a774c0" for R8A774C0 (RZ/G2E) compatible DU
     - "renesas,du-r8a7779" for R8A7779 (R-Car H1) compatible DU
     - "renesas,du-r8a7790" for R8A7790 (R-Car H2) compatible DU
@@ -60,6 +61,7 @@ corresponding to each DU output.
  R8A7745 (RZ/G1E)       DPAD 0         DPAD 1         -              -
  R8A77470 (RZ/G1C)      DPAD 0         DPAD 1         LVDS 0         -
  R8A774A1 (RZ/G2M)      DPAD 0         HDMI 0         LVDS 0         -
+ R8A774B1 (RZ/G2N)      DPAD 0         HDMI 0         LVDS 0         -
  R8A774C0 (RZ/G2E)      DPAD 0         LVDS 0         LVDS 1         -
  R8A7779 (R-Car H1)     DPAD 0         DPAD 1         -              -
  R8A7790 (R-Car H2)     DPAD 0         LVDS 0         LVDS 1         -
-- 
cgit v1.2.3


From 47968ea96af335b56a0db6c305146e720363558c Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das@bp.renesas.com>
Date: Mon, 30 Sep 2019 10:15:03 +0100
Subject: drm: rcar-du: Add R8A774B1 support

Add support for the R8A774B1 DU (which is very similar to the R8A77965 DU
except that it lacks TCON and CMM); it has one RGB output, one LVDS output
and one HDMI output.

Signed-off-by: Biju Das <biju.das@bp.renesas.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
---
 drivers/gpu/drm/rcar-du/rcar_du_drv.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
index 9c93eb4fad8b..f266c17b907a 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
@@ -131,6 +131,35 @@ static const struct rcar_du_device_info rcar_du_r8a774a1_info = {
 	.dpll_mask =  BIT(1),
 };
 
+static const struct rcar_du_device_info rcar_du_r8a774b1_info = {
+	.gen = 3,
+	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK
+		  | RCAR_DU_FEATURE_VSP1_SOURCE
+		  | RCAR_DU_FEATURE_INTERLACED
+		  | RCAR_DU_FEATURE_TVM_SYNC,
+	.channels_mask = BIT(3) | BIT(1) | BIT(0),
+	.routes = {
+		/*
+		 * R8A774B1 has one RGB output, one LVDS output and one HDMI
+		 * output.
+		 */
+		[RCAR_DU_OUTPUT_DPAD0] = {
+			.possible_crtcs = BIT(2),
+			.port = 0,
+		},
+		[RCAR_DU_OUTPUT_HDMI0] = {
+			.possible_crtcs = BIT(1),
+			.port = 1,
+		},
+		[RCAR_DU_OUTPUT_LVDS0] = {
+			.possible_crtcs = BIT(0),
+			.port = 2,
+		},
+	},
+	.num_lvds = 1,
+	.dpll_mask =  BIT(1),
+};
+
 static const struct rcar_du_device_info rcar_du_r8a774c0_info = {
 	.gen = 3,
 	.features = RCAR_DU_FEATURE_CRTC_IRQ_CLOCK
@@ -416,6 +445,7 @@ static const struct of_device_id rcar_du_of_table[] = {
 	{ .compatible = "renesas,du-r8a7745", .data = &rzg1_du_r8a7745_info },
 	{ .compatible = "renesas,du-r8a77470", .data = &rzg1_du_r8a77470_info },
 	{ .compatible = "renesas,du-r8a774a1", .data = &rcar_du_r8a774a1_info },
+	{ .compatible = "renesas,du-r8a774b1", .data = &rcar_du_r8a774b1_info },
 	{ .compatible = "renesas,du-r8a774c0", .data = &rcar_du_r8a774c0_info },
 	{ .compatible = "renesas,du-r8a7779", .data = &rcar_du_r8a7779_info },
 	{ .compatible = "renesas,du-r8a7790", .data = &rcar_du_r8a7790_info },
-- 
cgit v1.2.3


From 86db9f28224e8f6089b80e1391bdda0eabdf473b Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das@bp.renesas.com>
Date: Mon, 30 Sep 2019 10:15:04 +0100
Subject: dt-bindings: display: renesas: lvds: Document r8a774b1 bindings

Document the RZ/G2N (R8A774B1) LVDS bindings.

Signed-off-by: Biju Das <biju.das@bp.renesas.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Acked-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt b/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt
index c6a196d0b075..c62ce2494ed9 100644
--- a/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt
+++ b/Documentation/devicetree/bindings/display/bridge/renesas,lvds.txt
@@ -10,6 +10,7 @@ Required properties:
   - "renesas,r8a7743-lvds" for R8A7743 (RZ/G1M) compatible LVDS encoders
   - "renesas,r8a7744-lvds" for R8A7744 (RZ/G1N) compatible LVDS encoders
   - "renesas,r8a774a1-lvds" for R8A774A1 (RZ/G2M) compatible LVDS encoders
+  - "renesas,r8a774b1-lvds" for R8A774B1 (RZ/G2N) compatible LVDS encoders
   - "renesas,r8a774c0-lvds" for R8A774C0 (RZ/G2E) compatible LVDS encoders
   - "renesas,r8a7790-lvds" for R8A7790 (R-Car H2) compatible LVDS encoders
   - "renesas,r8a7791-lvds" for R8A7791 (R-Car M2-W) compatible LVDS encoders
-- 
cgit v1.2.3


From cfbcf6eb67e1cebe46978b1dd76116948bdeb7db Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das@bp.renesas.com>
Date: Mon, 30 Sep 2019 10:15:05 +0100
Subject: drm: rcar-du: lvds: Add r8a774b1 support

The LVDS encoders on RZ/G2N SoC is similar to R-Car M3-N. Add support for
RZ/G2N (R8A774B1) SoC to the LVDS encoder driver.

Signed-off-by: Biju Das <biju.das@bp.renesas.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
---
 drivers/gpu/drm/rcar-du/rcar_lvds.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index 50c11a7f0467..8c6c172bbf2e 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -943,6 +943,7 @@ static const struct of_device_id rcar_lvds_of_table[] = {
 	{ .compatible = "renesas,r8a7743-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a7744-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a774a1-lvds", .data = &rcar_lvds_gen3_info },
+	{ .compatible = "renesas,r8a774b1-lvds", .data = &rcar_lvds_gen3_info },
 	{ .compatible = "renesas,r8a774c0-lvds", .data = &rcar_lvds_r8a77990_info },
 	{ .compatible = "renesas,r8a7790-lvds", .data = &rcar_lvds_gen2_info },
 	{ .compatible = "renesas,r8a7791-lvds", .data = &rcar_lvds_gen2_info },
-- 
cgit v1.2.3


From f3a36d469621e52a04392820fa96bc4f2a9d29e7 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das@bp.renesas.com>
Date: Mon, 30 Sep 2019 10:28:51 +0100
Subject: dt-bindings: display: renesas: Add r8a774b1 support

Document RZ/G2N (R8A774B1) SoC bindings.

Signed-off-by: Biju Das <biju.das@bp.renesas.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
---
 Documentation/devicetree/bindings/display/bridge/renesas,dw-hdmi.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/display/bridge/renesas,dw-hdmi.txt b/Documentation/devicetree/bindings/display/bridge/renesas,dw-hdmi.txt
index db680413e89c..819f3e31013c 100644
--- a/Documentation/devicetree/bindings/display/bridge/renesas,dw-hdmi.txt
+++ b/Documentation/devicetree/bindings/display/bridge/renesas,dw-hdmi.txt
@@ -13,6 +13,7 @@ Required properties:
 
 - compatible : Shall contain one or more of
   - "renesas,r8a774a1-hdmi" for R8A774A1 (RZ/G2M) compatible HDMI TX
+  - "renesas,r8a774b1-hdmi" for R8A774B1 (RZ/G2N) compatible HDMI TX
   - "renesas,r8a7795-hdmi" for R8A7795 (R-Car H3) compatible HDMI TX
   - "renesas,r8a7796-hdmi" for R8A7796 (R-Car M3-W) compatible HDMI TX
   - "renesas,r8a77965-hdmi" for R8A77965 (R-Car M3-N) compatible HDMI TX
-- 
cgit v1.2.3


From 0c401fdf27ba52830c39670dc81cd8379756bd65 Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Tue, 15 Oct 2019 13:52:03 -0700
Subject: xtensa: virt: fix PCI IO ports mapping

virt device tree incorrectly uses 0xf0000000 on both sides of PCI IO
ports address space mapping. This results in incorrect port address
assignment in PCI IO BARs and subsequent crash on attempt to access
them. Use 0 as base address in PCI IO ports address space.

Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/boot/dts/virt.dts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/xtensa/boot/dts/virt.dts b/arch/xtensa/boot/dts/virt.dts
index a9dcd87b6eb1..611b98a02a65 100644
--- a/arch/xtensa/boot/dts/virt.dts
+++ b/arch/xtensa/boot/dts/virt.dts
@@ -56,7 +56,7 @@
 		reg = <0xf0100000 0x03f00000>;
 
 		     // BUS_ADDRESS(3)  CPU_PHYSICAL(1)  SIZE(2)
-		ranges = <0x01000000 0x0 0xf0000000  0xf0000000  0x0 0x00010000>,
+		ranges = <0x01000000 0x0 0x00000000  0xf0000000  0x0 0x00010000>,
 			 <0x02000000 0x0 0xf4000000  0xf4000000  0x0 0x08000000>;
 
 		     // PCI_DEVICE(3)  INT#(1)  CONTROLLER(PHANDLE)  CONTROLLER_DATA(2)
-- 
cgit v1.2.3


From 45144d42f299455911cc29366656c7324a3a7c97 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 14 Oct 2019 13:25:00 +0200
Subject: PCI: PM: Fix pci_power_up()

There is an arbitrary difference between the system resume and
runtime resume code paths for PCI devices regarding the delay to
apply when switching the devices from D3cold to D0.

Namely, pci_restore_standard_config() used in the runtime resume
code path calls pci_set_power_state() which in turn invokes
__pci_start_power_transition() to power up the device through the
platform firmware and that function applies the transition delay
(as per PCI Express Base Specification Revision 2.0, Section 6.6.1).
However, pci_pm_default_resume_early() used in the system resume
code path calls pci_power_up() which doesn't apply the delay at
all and that causes issues to occur during resume from
suspend-to-idle on some systems where the delay is required.

Since there is no reason for that difference to exist, modify
pci_power_up() to follow pci_set_power_state() more closely and
invoke __pci_start_power_transition() from there to call the
platform firmware to power up the device (in case that's necessary).

Fixes: db288c9c5f9d ("PCI / PM: restore the original behavior of pci_set_power_state()")
Reported-by: Daniel Drake <drake@endlessm.com>
Tested-by: Daniel Drake <drake@endlessm.com>
Link: https://lore.kernel.org/linux-pm/CAD8Lp44TYxrMgPLkHCqF9hv6smEurMXvmmvmtyFhZ6Q4SE+dig@mail.gmail.com/T/#m21be74af263c6a34f36e0fc5c77c5449d9406925
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: 3.10+ <stable@vger.kernel.org> # 3.10+
---
 drivers/pci/pci.c | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e7982af9a5d8..a97e2571a527 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -958,19 +958,6 @@ void pci_refresh_power_state(struct pci_dev *dev)
 	pci_update_current_state(dev, dev->current_state);
 }
 
-/**
- * pci_power_up - Put the given device into D0 forcibly
- * @dev: PCI device to power up
- */
-void pci_power_up(struct pci_dev *dev)
-{
-	if (platform_pci_power_manageable(dev))
-		platform_pci_set_power_state(dev, PCI_D0);
-
-	pci_raw_set_power_state(dev, PCI_D0);
-	pci_update_current_state(dev, PCI_D0);
-}
-
 /**
  * pci_platform_power_transition - Use platform to change device power state
  * @dev: PCI device to handle.
@@ -1153,6 +1140,17 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 }
 EXPORT_SYMBOL(pci_set_power_state);
 
+/**
+ * pci_power_up - Put the given device into D0 forcibly
+ * @dev: PCI device to power up
+ */
+void pci_power_up(struct pci_dev *dev)
+{
+	__pci_start_power_transition(dev, PCI_D0);
+	pci_raw_set_power_state(dev, PCI_D0);
+	pci_update_current_state(dev, PCI_D0);
+}
+
 /**
  * pci_choose_state - Choose the power state of a PCI device
  * @dev: PCI device to be suspended
-- 
cgit v1.2.3


From b31141d390f1d47f1f3e1aef04909dc48e894611 Mon Sep 17 00:00:00 2001
From: Nishad Kamdar <nishadkamdar@gmail.com>
Date: Sat, 12 Oct 2019 17:48:56 +0530
Subject: net: dsa: microchip: Use the correct style for SPDX License
 Identifier

This patch corrects the SPDX License Identifier style
in header files related to Distributed Switch Architecture
drivers for Microchip KSZ series switch support.
For C header files Documentation/process/license-rules.rst
mandates C-like comments (opposed to C source files where
C++ style should be used)

Changes made by using a script provided by Joe Perches here:
https://lkml.org/lkml/2019/2/7/46.

Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Nishad Kamdar <nishadkamdar@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz9477_reg.h | 4 ++--
 drivers/net/dsa/microchip/ksz_common.h  | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h
index 2938e892b631..16939f29faa5 100644
--- a/drivers/net/dsa/microchip/ksz9477_reg.h
+++ b/drivers/net/dsa/microchip/ksz9477_reg.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Microchip KSZ9477 register definitions
  *
  * Copyright (C) 2017-2018 Microchip Technology Inc.
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index dd60d0837fc6..64c2677693d2 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Microchip switch driver common header
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Microchip switch driver common header
  *
  * Copyright (C) 2017-2019 Microchip Technology Inc.
  */
-- 
cgit v1.2.3


From a03681dd5d1bf7b0ed3aad3162f7810af4c4e05b Mon Sep 17 00:00:00 2001
From: Nishad Kamdar <nishadkamdar@gmail.com>
Date: Sat, 12 Oct 2019 18:42:28 +0530
Subject: net: cavium: Use the correct style for SPDX License Identifier

This patch corrects the SPDX License Identifier style
in header files related to Cavium Ethernet drivers.
For C header files Documentation/process/license-rules.rst
mandates C-like comments (opposed to C source files where
C++ style should be used)

Changes made by using a script provided by Joe Perches here:
https://lkml.org/lkml/2019/2/7/46.

Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Nishad Kamdar <nishadkamdar@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/common/cavium_ptp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/common/cavium_ptp.h b/drivers/net/ethernet/cavium/common/cavium_ptp.h
index be2bafc7beeb..a04eccbc78e8 100644
--- a/drivers/net/ethernet/cavium/common/cavium_ptp.h
+++ b/drivers/net/ethernet/cavium/common/cavium_ptp.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /* cavium_ptp.h - PTP 1588 clock on Cavium hardware
  * Copyright (c) 2003-2015, 2017 Cavium, Inc.
  */
-- 
cgit v1.2.3


From dedc5a08da07874c6e0d411e7f39c5c2cf137014 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 12 Oct 2019 13:55:06 +0200
Subject: net: avoid errors when trying to pop MLPS header on non-MPLS packets

the following script:

 # tc qdisc add dev eth0 clsact
 # tc filter add dev eth0 egress matchall action mpls pop

implicitly makes the kernel drop all packets transmitted by eth0, if they
don't have a MPLS header. This behavior is uncommon: other encapsulations
(like VLAN) just let the packet pass unmodified. Since the result of MPLS
'pop' operation would be the same regardless of the presence / absence of
MPLS header(s) in the original packet, we can let skb_mpls_pop() return 0
when dealing with non-MPLS packets.

For the OVS use-case, this is acceptable because __ovs_nla_copy_actions()
already ensures that MPLS 'pop' operation only occurs with packets having
an MPLS Ethernet type (and there are no other callers in current code, so
the semantic change should be ok).

v2: better documentation of use-cases for skb_mpls_pop(), thanks to Simon
    Horman

Fixes: 2a2ea50870ba ("net: sched: add mpls manipulation actions to TC")
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8c178703467b..03b6809ebde4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5536,7 +5536,7 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto)
 	int err;
 
 	if (unlikely(!eth_p_mpls(skb->protocol)))
-		return -EINVAL;
+		return 0;
 
 	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
 	if (unlikely(err))
-- 
cgit v1.2.3


From fa4e0f8855fcba600e0be2575ee29c69166f74bd Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Sat, 12 Oct 2019 13:55:07 +0200
Subject: net/sched: fix corrupted L2 header with MPLS 'push' and 'pop' actions

the following script:

 # tc qdisc add dev eth0 clsact
 # tc filter add dev eth0 egress protocol ip matchall \
 > action mpls push protocol mpls_uc label 0x355aa bos 1

causes corruption of all IP packets transmitted by eth0. On TC egress, we
can't rely on the value of skb->mac_len, because it's 0 and a MPLS 'push'
operation will result in an overwrite of the first 4 octets in the packet
L2 header (e.g. the Destination Address if eth0 is an Ethernet); the same
error pattern is present also in the MPLS 'pop' operation. Fix this error
in act_mpls data plane, computing 'mac_len' as the difference between the
network header and the mac header (when not at TC ingress), and use it in
MPLS 'push'/'pop' core functions.

v2: unbreak 'make htmldocs' because of missing documentation of 'mac_len'
    in skb_mpls_pop(), reported by kbuild test robot

CC: Lorenzo Bianconi <lorenzo@kernel.org>
Fixes: 2a2ea50870ba ("net: sched: add mpls manipulation actions to TC")
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Acked-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h    |  5 +++--
 net/core/skbuff.c         | 19 +++++++++++--------
 net/openvswitch/actions.c |  5 +++--
 net/sched/act_mpls.c      | 12 ++++++++----
 4 files changed, 25 insertions(+), 16 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4351577b14d7..7914fdaf4226 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3510,8 +3510,9 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len);
 int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci);
 int skb_vlan_pop(struct sk_buff *skb);
 int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci);
-int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto);
-int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto);
+int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
+		  int mac_len);
+int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len);
 int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse);
 int skb_mpls_dec_ttl(struct sk_buff *skb);
 struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 03b6809ebde4..867e61df00db 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5477,12 +5477,14 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
  * @skb: buffer
  * @mpls_lse: MPLS label stack entry to push
  * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848)
+ * @mac_len: length of the MAC header
  *
  * Expects skb->data at mac header.
  *
  * Returns 0 on success, -errno otherwise.
  */
-int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto)
+int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto,
+		  int mac_len)
 {
 	struct mpls_shim_hdr *lse;
 	int err;
@@ -5499,15 +5501,15 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto)
 		return err;
 
 	if (!skb->inner_protocol) {
-		skb_set_inner_network_header(skb, skb->mac_len);
+		skb_set_inner_network_header(skb, mac_len);
 		skb_set_inner_protocol(skb, skb->protocol);
 	}
 
 	skb_push(skb, MPLS_HLEN);
 	memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
-		skb->mac_len);
+		mac_len);
 	skb_reset_mac_header(skb);
-	skb_set_network_header(skb, skb->mac_len);
+	skb_set_network_header(skb, mac_len);
 
 	lse = mpls_hdr(skb);
 	lse->label_stack_entry = mpls_lse;
@@ -5526,29 +5528,30 @@ EXPORT_SYMBOL_GPL(skb_mpls_push);
  *
  * @skb: buffer
  * @next_proto: ethertype of header after popped MPLS header
+ * @mac_len: length of the MAC header
  *
  * Expects skb->data at mac header.
  *
  * Returns 0 on success, -errno otherwise.
  */
-int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto)
+int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len)
 {
 	int err;
 
 	if (unlikely(!eth_p_mpls(skb->protocol)))
 		return 0;
 
-	err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
+	err = skb_ensure_writable(skb, mac_len + MPLS_HLEN);
 	if (unlikely(err))
 		return err;
 
 	skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
 	memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
-		skb->mac_len);
+		mac_len);
 
 	__skb_pull(skb, MPLS_HLEN);
 	skb_reset_mac_header(skb);
-	skb_set_network_header(skb, skb->mac_len);
+	skb_set_network_header(skb, mac_len);
 
 	if (skb->dev && skb->dev->type == ARPHRD_ETHER) {
 		struct ethhdr *hdr;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 3572e11b6f21..1c77f520f474 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -165,7 +165,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 {
 	int err;
 
-	err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype);
+	err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype,
+			    skb->mac_len);
 	if (err)
 		return err;
 
@@ -178,7 +179,7 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
 {
 	int err;
 
-	err = skb_mpls_pop(skb, ethertype);
+	err = skb_mpls_pop(skb, ethertype, skb->mac_len);
 	if (err)
 		return err;
 
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index e168df0e008a..4cf6c553bb0b 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -55,7 +55,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 	struct tcf_mpls *m = to_mpls(a);
 	struct tcf_mpls_params *p;
 	__be32 new_lse;
-	int ret;
+	int ret, mac_len;
 
 	tcf_lastuse_update(&m->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb);
@@ -63,8 +63,12 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 	/* Ensure 'data' points at mac_header prior calling mpls manipulating
 	 * functions.
 	 */
-	if (skb_at_tc_ingress(skb))
+	if (skb_at_tc_ingress(skb)) {
 		skb_push_rcsum(skb, skb->mac_len);
+		mac_len = skb->mac_len;
+	} else {
+		mac_len = skb_network_header(skb) - skb_mac_header(skb);
+	}
 
 	ret = READ_ONCE(m->tcf_action);
 
@@ -72,12 +76,12 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 
 	switch (p->tcfm_action) {
 	case TCA_MPLS_ACT_POP:
-		if (skb_mpls_pop(skb, p->tcfm_proto))
+		if (skb_mpls_pop(skb, p->tcfm_proto, mac_len))
 			goto drop;
 		break;
 	case TCA_MPLS_ACT_PUSH:
 		new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol));
-		if (skb_mpls_push(skb, new_lse, p->tcfm_proto))
+		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len))
 			goto drop;
 		break;
 	case TCA_MPLS_ACT_MODIFY:
-- 
cgit v1.2.3


From c324345ce89c3cc50226372960619c7ee940f616 Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Tue, 15 Oct 2019 17:37:37 -0700
Subject: Revert "Input: elantech - enable SMBus on new (2018+) systems"

This reverts commit 883a2a80f79ca5c0c105605fafabd1f3df99b34c.

Apparently use dmi_get_bios_year() as manufacturing date isn't accurate
and this breaks older laptops with new BIOS update.

So let's revert this patch.

There are still new HP laptops still need to use SMBus to support all
features, but it'll be enabled via a whitelist.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Acked-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20191001070845.9720-1-kai.heng.feng@canonical.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/mouse/elantech.c | 55 ++++++++++++++++++++++--------------------
 1 file changed, 29 insertions(+), 26 deletions(-)

diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 04fe43440a3c..2d8434b7b623 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1827,31 +1827,6 @@ static int elantech_create_smbus(struct psmouse *psmouse,
 				  leave_breadcrumbs);
 }
 
-static bool elantech_use_host_notify(struct psmouse *psmouse,
-				     struct elantech_device_info *info)
-{
-	if (ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version))
-		return true;
-
-	switch (info->bus) {
-	case ETP_BUS_PS2_ONLY:
-		/* expected case */
-		break;
-	case ETP_BUS_SMB_HST_NTFY_ONLY:
-	case ETP_BUS_PS2_SMB_HST_NTFY:
-		/* SMbus implementation is stable since 2018 */
-		if (dmi_get_bios_year() >= 2018)
-			return true;
-		/* fall through */
-	default:
-		psmouse_dbg(psmouse,
-			    "Ignoring SMBus bus provider %d\n", info->bus);
-		break;
-	}
-
-	return false;
-}
-
 /**
  * elantech_setup_smbus - called once the PS/2 devices are enumerated
  * and decides to instantiate a SMBus InterTouch device.
@@ -1871,7 +1846,7 @@ static int elantech_setup_smbus(struct psmouse *psmouse,
 		 * i2c_blacklist_pnp_ids.
 		 * Old ICs are up to the user to decide.
 		 */
-		if (!elantech_use_host_notify(psmouse, info) ||
+		if (!ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version) ||
 		    psmouse_matches_pnp_id(psmouse, i2c_blacklist_pnp_ids))
 			return -ENXIO;
 	}
@@ -1891,6 +1866,34 @@ static int elantech_setup_smbus(struct psmouse *psmouse,
 	return 0;
 }
 
+static bool elantech_use_host_notify(struct psmouse *psmouse,
+				     struct elantech_device_info *info)
+{
+	if (ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version))
+		return true;
+
+	switch (info->bus) {
+	case ETP_BUS_PS2_ONLY:
+		/* expected case */
+		break;
+	case ETP_BUS_SMB_ALERT_ONLY:
+		/* fall-through  */
+	case ETP_BUS_PS2_SMB_ALERT:
+		psmouse_dbg(psmouse, "Ignoring SMBus provider through alert protocol.\n");
+		break;
+	case ETP_BUS_SMB_HST_NTFY_ONLY:
+		/* fall-through  */
+	case ETP_BUS_PS2_SMB_HST_NTFY:
+		return true;
+	default:
+		psmouse_dbg(psmouse,
+			    "Ignoring SMBus bus provider %d.\n",
+			    info->bus);
+	}
+
+	return false;
+}
+
 int elantech_init_smbus(struct psmouse *psmouse)
 {
 	struct elantech_device_info info;
-- 
cgit v1.2.3


From 4e3eff5beafa5c97cdf2af2181f46479941a7f45 Mon Sep 17 00:00:00 2001
From: MarkLee <Mark-MC.Lee@mediatek.com>
Date: Mon, 14 Oct 2019 15:15:17 +0800
Subject: net: ethernet: mediatek: Fix MT7629 missing GMII mode support

In the original design, mtk_phy_connect function will set ge_mode=1
if phy-mode is GMII(PHY_INTERFACE_MODE_GMII) and then set the correct
ge_mode to ETHSYS_SYSCFG0 register. This logic was broken after apply
mediatek PHYLINK patch(Fixes tag), the new mtk_mac_config function will
not set ge_mode=1 for GMII mode hence the final ETHSYS_SYSCFG0 setting
will be incorrect for mt7629 GMII mode. This patch add the missing logic
back to fix it.

Fixes: b8fc9f30821e ("net: ethernet: mediatek: Add basic PHYLINK support")
Signed-off-by: MarkLee <Mark-MC.Lee@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index c61069340f4f..703adb96429e 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -261,6 +261,7 @@ static void mtk_mac_config(struct phylink_config *config, unsigned int mode,
 		ge_mode = 0;
 		switch (state->interface) {
 		case PHY_INTERFACE_MODE_MII:
+		case PHY_INTERFACE_MODE_GMII:
 			ge_mode = 1;
 			break;
 		case PHY_INTERFACE_MODE_REVMII:
-- 
cgit v1.2.3


From 2618500dd370da413cb1f616111e1bd8d9f5f94f Mon Sep 17 00:00:00 2001
From: MarkLee <Mark-MC.Lee@mediatek.com>
Date: Mon, 14 Oct 2019 15:15:18 +0800
Subject: arm: dts: mediatek: Update mt7629 dts to reflect the latest
 dt-binding

* Removes mediatek,physpeed property from dtsi that is useless in PHYLINK
* Use the fixed-link property speed = <2500> to set the phy in 2.5Gbit.
* Set gmac1 to gmii mode that connect to a internal gphy

Signed-off-by: MarkLee <Mark-MC.Lee@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/boot/dts/mt7629-rfb.dts | 13 ++++++++++++-
 arch/arm/boot/dts/mt7629.dtsi    |  2 --
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/arch/arm/boot/dts/mt7629-rfb.dts b/arch/arm/boot/dts/mt7629-rfb.dts
index 3621b7d2b22a..9980c10c6e29 100644
--- a/arch/arm/boot/dts/mt7629-rfb.dts
+++ b/arch/arm/boot/dts/mt7629-rfb.dts
@@ -66,9 +66,21 @@
 	pinctrl-1 = <&ephy_leds_pins>;
 	status = "okay";
 
+	gmac0: mac@0 {
+		compatible = "mediatek,eth-mac";
+		reg = <0>;
+		phy-mode = "2500base-x";
+		fixed-link {
+			speed = <2500>;
+			full-duplex;
+			pause;
+		};
+	};
+
 	gmac1: mac@1 {
 		compatible = "mediatek,eth-mac";
 		reg = <1>;
+		phy-mode = "gmii";
 		phy-handle = <&phy0>;
 	};
 
@@ -78,7 +90,6 @@
 
 		phy0: ethernet-phy@0 {
 			reg = <0>;
-			phy-mode = "gmii";
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/mt7629.dtsi b/arch/arm/boot/dts/mt7629.dtsi
index 9608bc2ccb3f..867b88103b9d 100644
--- a/arch/arm/boot/dts/mt7629.dtsi
+++ b/arch/arm/boot/dts/mt7629.dtsi
@@ -468,14 +468,12 @@
 			compatible = "mediatek,mt7629-sgmiisys", "syscon";
 			reg = <0x1b128000 0x3000>;
 			#clock-cells = <1>;
-			mediatek,physpeed = "2500";
 		};
 
 		sgmiisys1: syscon@1b130000 {
 			compatible = "mediatek,mt7629-sgmiisys", "syscon";
 			reg = <0x1b130000 0x3000>;
 			#clock-cells = <1>;
-			mediatek,physpeed = "2500";
 		};
 	};
 };
-- 
cgit v1.2.3


From cab209e571a9375f7dc6db69a6c40d2d98e57e3b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Oct 2019 06:47:57 -0700
Subject: tcp: fix a possible lockdep splat in tcp_done()

syzbot found that if __inet_inherit_port() returns an error,
we call tcp_done() after inet_csk_prepare_forced_close(),
meaning the socket lock is no longer held.

We might fix this in a different way in net-next, but
for 5.4 it seems safer to relax the lockdep check.

Fixes: d983ea6f16b8 ("tcp: add rcu protection around tp->fastopen_rsk")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b2ac4f074e2d..42187a3b82f4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3842,8 +3842,12 @@ void tcp_done(struct sock *sk)
 {
 	struct request_sock *req;
 
-	req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
-					lockdep_sock_is_held(sk));
+	/* We might be called with a new socket, after
+	 * inet_csk_prepare_forced_close() has been called
+	 * so we can not use lockdep_sock_is_held(sk)
+	 */
+	req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1);
+
 	if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
 		TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
 
-- 
cgit v1.2.3


From b790b5549bdf498ab0ecc5632610a9149532fa38 Mon Sep 17 00:00:00 2001
From: Nishad Kamdar <nishadkamdar@gmail.com>
Date: Mon, 14 Oct 2019 21:51:20 +0530
Subject: net: dsa: sja1105: Use the correct style for SPDX License Identifier

This patch corrects the SPDX License Identifier style
in header files related to Distributed Switch Architecture
drivers for NXP SJA1105 series Ethernet switch support.
It uses an expilict block comment for the SPDX License
Identifier.

Changes made by using a script provided by Joe Perches here:
https://lkml.org/lkml/2019/2/7/46.

Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Nishad Kamdar <nishadkamdar@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105.h                | 4 ++--
 drivers/net/dsa/sja1105/sja1105_dynamic_config.h | 4 ++--
 drivers/net/dsa/sja1105/sja1105_ptp.h            | 4 ++--
 drivers/net/dsa/sja1105/sja1105_static_config.h  | 4 ++--
 drivers/net/dsa/sja1105/sja1105_tas.h            | 4 ++--
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
index e53e494c22e0..fbb564c3beb8 100644
--- a/drivers/net/dsa/sja1105/sja1105.h
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (c) 2018, Sensor-Technik Wiedemann GmbH
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018, Sensor-Technik Wiedemann GmbH
  * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
  */
 #ifndef _SJA1105_H
diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.h b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h
index 740dadf43f01..1fc0d13dc623 100644
--- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.h
+++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
  */
 #ifndef _SJA1105_DYNAMIC_CONFIG_H
 #define _SJA1105_DYNAMIC_CONFIG_H
diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h
index af456b0a4d27..394e12a6ad59 100644
--- a/drivers/net/dsa/sja1105/sja1105_ptp.h
+++ b/drivers/net/dsa/sja1105/sja1105_ptp.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
  */
 #ifndef _SJA1105_PTP_H
 #define _SJA1105_PTP_H
diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h
index 7f87022a2d61..f4a5c5c04311 100644
--- a/drivers/net/dsa/sja1105/sja1105_static_config.h
+++ b/drivers/net/dsa/sja1105/sja1105_static_config.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright (c) 2016-2018, NXP Semiconductors
+/* SPDX-License-Identifier: BSD-3-Clause */
+/* Copyright (c) 2016-2018, NXP Semiconductors
  * Copyright (c) 2018-2019, Vladimir Oltean <olteanv@gmail.com>
  */
 #ifndef _SJA1105_STATIC_CONFIG_H
diff --git a/drivers/net/dsa/sja1105/sja1105_tas.h b/drivers/net/dsa/sja1105/sja1105_tas.h
index 0b803c30e640..0aad212d88b2 100644
--- a/drivers/net/dsa/sja1105/sja1105_tas.h
+++ b/drivers/net/dsa/sja1105/sja1105_tas.h
@@ -1,5 +1,5 @@
-/* SPDX-License-Identifier: GPL-2.0
- * Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com>
  */
 #ifndef _SJA1105_TAS_H
 #define _SJA1105_TAS_H
-- 
cgit v1.2.3


From 39f13ea2f61b439ebe0060393e9c39925c9ee28c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Oct 2019 11:22:30 -0700
Subject: net: avoid potential infinite loop in tc_ctl_action()

tc_ctl_action() has the ability to loop forever if tcf_action_add()
returns -EAGAIN.

This special case has been done in case a module needed to be loaded,
but it turns out that tcf_add_notify() could also return -EAGAIN
if the socket sk_rcvbuf limit is hit.

We need to separate the two cases, and only loop for the module
loading case.

While we are at it, add a limit of 10 attempts since unbounded
loops are always scary.

syzbot repro was something like :

socket(PF_NETLINK, SOCK_RAW|SOCK_NONBLOCK, NETLINK_ROUTE) = 3
write(3, ..., 38) = 38
setsockopt(3, SOL_SOCKET, SO_RCVBUF, [0], 4) = 0
sendmsg(3, {msg_name(0)=NULL, msg_iov(1)=[{..., 388}], msg_controllen=0, msg_flags=0x10}, ...)

NMI backtrace for cpu 0
CPU: 0 PID: 1054 Comm: khungtaskd Not tainted 5.4.0-rc1+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x172/0x1f0 lib/dump_stack.c:113
 nmi_cpu_backtrace.cold+0x70/0xb2 lib/nmi_backtrace.c:101
 nmi_trigger_cpumask_backtrace+0x23b/0x28b lib/nmi_backtrace.c:62
 arch_trigger_cpumask_backtrace+0x14/0x20 arch/x86/kernel/apic/hw_nmi.c:38
 trigger_all_cpu_backtrace include/linux/nmi.h:146 [inline]
 check_hung_uninterruptible_tasks kernel/hung_task.c:205 [inline]
 watchdog+0x9d0/0xef0 kernel/hung_task.c:289
 kthread+0x361/0x430 kernel/kthread.c:255
 ret_from_fork+0x24/0x30 arch/x86/entry/entry_64.S:352
Sending NMI from CPU 0 to CPUs 1:
NMI backtrace for cpu 1
CPU: 1 PID: 8859 Comm: syz-executor910 Not tainted 5.4.0-rc1+ #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:arch_local_save_flags arch/x86/include/asm/paravirt.h:751 [inline]
RIP: 0010:lockdep_hardirqs_off+0x1df/0x2e0 kernel/locking/lockdep.c:3453
Code: 5c 08 00 00 5b 41 5c 41 5d 5d c3 48 c7 c0 58 1d f3 88 48 ba 00 00 00 00 00 fc ff df 48 c1 e8 03 80 3c 10 00 0f 85 d3 00 00 00 <48> 83 3d 21 9e 99 07 00 0f 84 b9 00 00 00 9c 58 0f 1f 44 00 00 f6
RSP: 0018:ffff8880a6f3f1b8 EFLAGS: 00000046
RAX: 1ffffffff11e63ab RBX: ffff88808c9c6080 RCX: 0000000000000000
RDX: dffffc0000000000 RSI: 0000000000000000 RDI: ffff88808c9c6914
RBP: ffff8880a6f3f1d0 R08: ffff88808c9c6080 R09: fffffbfff16be5d1
R10: fffffbfff16be5d0 R11: 0000000000000003 R12: ffffffff8746591f
R13: ffff88808c9c6080 R14: ffffffff8746591f R15: 0000000000000003
FS:  00000000011e4880(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffffffff600400 CR3: 00000000a8920000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 trace_hardirqs_off+0x62/0x240 kernel/trace/trace_preemptirq.c:45
 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:108 [inline]
 _raw_spin_lock_irqsave+0x6f/0xcd kernel/locking/spinlock.c:159
 __wake_up_common_lock+0xc8/0x150 kernel/sched/wait.c:122
 __wake_up+0xe/0x10 kernel/sched/wait.c:142
 netlink_unlock_table net/netlink/af_netlink.c:466 [inline]
 netlink_unlock_table net/netlink/af_netlink.c:463 [inline]
 netlink_broadcast_filtered+0x705/0xb80 net/netlink/af_netlink.c:1514
 netlink_broadcast+0x3a/0x50 net/netlink/af_netlink.c:1534
 rtnetlink_send+0xdd/0x110 net/core/rtnetlink.c:714
 tcf_add_notify net/sched/act_api.c:1343 [inline]
 tcf_action_add+0x243/0x370 net/sched/act_api.c:1362
 tc_ctl_action+0x3b5/0x4bc net/sched/act_api.c:1410
 rtnetlink_rcv_msg+0x463/0xb00 net/core/rtnetlink.c:5386
 netlink_rcv_skb+0x177/0x450 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x1d/0x30 net/core/rtnetlink.c:5404
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0x531/0x710 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x8a5/0xd60 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg+0xd7/0x130 net/socket.c:657
 ___sys_sendmsg+0x803/0x920 net/socket.c:2311
 __sys_sendmsg+0x105/0x1d0 net/socket.c:2356
 __do_sys_sendmsg net/socket.c:2365 [inline]
 __se_sys_sendmsg net/socket.c:2363 [inline]
 __x64_sys_sendmsg+0x78/0xb0 net/socket.c:2363
 do_syscall_64+0xfa/0x760 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x440939

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot+cf0adbb9c28c8866c788@syzkaller.appspotmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 4e7429c6f864..69d4676a402f 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1353,11 +1353,16 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 			  struct netlink_ext_ack *extack)
 {
 	size_t attr_size = 0;
-	int ret = 0;
+	int loop, ret;
 	struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
 
-	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions,
-			      &attr_size, true, extack);
+	for (loop = 0; loop < 10; loop++) {
+		ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0,
+				      actions, &attr_size, true, extack);
+		if (ret != -EAGAIN)
+			break;
+	}
+
 	if (ret < 0)
 		return ret;
 	ret = tcf_add_notify(net, n, actions, portid, attr_size, extack);
@@ -1407,11 +1412,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n,
 		 */
 		if (n->nlmsg_flags & NLM_F_REPLACE)
 			ovr = 1;
-replay:
 		ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr,
 				     extack);
-		if (ret == -EAGAIN)
-			goto replay;
 		break;
 	case RTM_DELACTION:
 		ret = tca_action_gd(net, tca[TCA_ACT_TAB], n,
-- 
cgit v1.2.3


From 28aa7c86c2b49f659c8460a89e53b506c45979bb Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Mon, 14 Oct 2019 13:38:22 -0700
Subject: sched: etf: Fix ordering of packets with same txtime

When a application sends many packets with the same txtime, they may
be transmitted out of order (different from the order in which they
were enqueued).

This happens because when inserting elements into the tree, when the
txtime of two packets are the same, the new packet is inserted at the
left side of the tree, causing the reordering. The only effect of this
change should be that packets with the same txtime will be transmitted
in the order they are enqueued.

The application in question (the AVTP GStreamer plugin, still in
development) is sending video traffic, in which each video frame have
a single presentation time, the problem is that when packetizing,
multiple packets end up with the same txtime.

The receiving side was rejecting packets because they were being
received out of order.

Fixes: 25db26a91364 ("net/sched: Introduce the ETF Qdisc")
Reported-by: Ederson de Souza <ederson.desouza@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_etf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index cebfb65d8556..b1da5589a0c6 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -177,7 +177,7 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
 
 		parent = *p;
 		skb = rb_to_skb(parent);
-		if (ktime_after(txtime, skb->tstamp)) {
+		if (ktime_compare(txtime, skb->tstamp) >= 0) {
 			p = &parent->rb_right;
 			leftmost = false;
 		} else {
-- 
cgit v1.2.3


From 63dfb7938b13fa2c2fbcb45f34d065769eb09414 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 15 Oct 2019 15:24:38 +0800
Subject: sctp: change sctp_prot .no_autobind with true

syzbot reported a memory leak:

  BUG: memory leak, unreferenced object 0xffff888120b3d380 (size 64):
  backtrace:

    [...] slab_alloc mm/slab.c:3319 [inline]
    [...] kmem_cache_alloc+0x13f/0x2c0 mm/slab.c:3483
    [...] sctp_bucket_create net/sctp/socket.c:8523 [inline]
    [...] sctp_get_port_local+0x189/0x5a0 net/sctp/socket.c:8270
    [...] sctp_do_bind+0xcc/0x200 net/sctp/socket.c:402
    [...] sctp_bindx_add+0x4b/0xd0 net/sctp/socket.c:497
    [...] sctp_setsockopt_bindx+0x156/0x1b0 net/sctp/socket.c:1022
    [...] sctp_setsockopt net/sctp/socket.c:4641 [inline]
    [...] sctp_setsockopt+0xaea/0x2dc0 net/sctp/socket.c:4611
    [...] sock_common_setsockopt+0x38/0x50 net/core/sock.c:3147
    [...] __sys_setsockopt+0x10f/0x220 net/socket.c:2084
    [...] __do_sys_setsockopt net/socket.c:2100 [inline]

It was caused by when sending msgs without binding a port, in the path:
inet_sendmsg() -> inet_send_prepare() -> inet_autobind() ->
.get_port/sctp_get_port(), sp->bind_hash will be set while bp->port is
not. Later when binding another port by sctp_setsockopt_bindx(), a new
bucket will be created as bp->port is not set.

sctp's autobind is supposed to call sctp_autobind() where it does all
things including setting bp->port. Since sctp_autobind() is called in
sctp_sendmsg() if the sk is not yet bound, it should have skipped the
auto bind.

THis patch is to avoid calling inet_autobind() in inet_send_prepare()
by changing sctp_prot .no_autobind with true, also remove the unused
.get_port.

Reported-by: syzbot+d44f7bbebdea49dbc84a@syzkaller.appspotmail.com
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/socket.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 939b8d2595bc..5ca0ec0e823c 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -9500,7 +9500,7 @@ struct proto sctp_prot = {
 	.backlog_rcv =	sctp_backlog_rcv,
 	.hash        =	sctp_hash,
 	.unhash      =	sctp_unhash,
-	.get_port    =	sctp_get_port,
+	.no_autobind =	true,
 	.obj_size    =  sizeof(struct sctp_sock),
 	.useroffset  =  offsetof(struct sctp_sock, subscribe),
 	.usersize    =  offsetof(struct sctp_sock, initmsg) -
@@ -9542,7 +9542,7 @@ struct proto sctpv6_prot = {
 	.backlog_rcv	= sctp_backlog_rcv,
 	.hash		= sctp_hash,
 	.unhash		= sctp_unhash,
-	.get_port	= sctp_get_port,
+	.no_autobind	= true,
 	.obj_size	= sizeof(struct sctp6_sock),
 	.useroffset	= offsetof(struct sctp6_sock, sctp.subscribe),
 	.usersize	= offsetof(struct sctp6_sock, sctp.initmsg) -
-- 
cgit v1.2.3


From 61c1d33daf7b5146f44d4363b3322f8cda6a6c43 Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Tue, 15 Oct 2019 16:42:45 +0200
Subject: net: i82596: fix dma_alloc_attr for sni_82596

Commit 7f683b920479 ("i825xx: switch to switch to dma_alloc_attrs")
switched dma allocation over to dma_alloc_attr, but didn't convert
the SNI part to request consistent DMA memory. This broke sni_82596
since driver doesn't do dma_cache_sync for performance reasons.
Fix this by using different DMA_ATTRs for lasi_82596 and sni_82596.

Fixes: 7f683b920479 ("i825xx: switch to switch to dma_alloc_attrs")
Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/i825xx/lasi_82596.c | 4 +++-
 drivers/net/ethernet/i825xx/lib82596.c   | 4 ++--
 drivers/net/ethernet/i825xx/sni_82596.c  | 4 +++-
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/i825xx/lasi_82596.c b/drivers/net/ethernet/i825xx/lasi_82596.c
index 211c5f74b4c8..aec7e98bcc85 100644
--- a/drivers/net/ethernet/i825xx/lasi_82596.c
+++ b/drivers/net/ethernet/i825xx/lasi_82596.c
@@ -96,6 +96,8 @@
 
 #define OPT_SWAP_PORT	0x0001	/* Need to wordswp on the MPU port */
 
+#define LIB82596_DMA_ATTR	DMA_ATTR_NON_CONSISTENT
+
 #define DMA_WBACK(ndev, addr, len) \
 	do { dma_cache_sync((ndev)->dev.parent, (void *)addr, len, DMA_TO_DEVICE); } while (0)
 
@@ -200,7 +202,7 @@ static int __exit lan_remove_chip(struct parisc_device *pdev)
 
 	unregister_netdev (dev);
 	dma_free_attrs(&pdev->dev, sizeof(struct i596_private), lp->dma,
-		       lp->dma_addr, DMA_ATTR_NON_CONSISTENT);
+		       lp->dma_addr, LIB82596_DMA_ATTR);
 	free_netdev (dev);
 	return 0;
 }
diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c
index 1274ad24d6af..f9742af7f142 100644
--- a/drivers/net/ethernet/i825xx/lib82596.c
+++ b/drivers/net/ethernet/i825xx/lib82596.c
@@ -1065,7 +1065,7 @@ static int i82596_probe(struct net_device *dev)
 
 	dma = dma_alloc_attrs(dev->dev.parent, sizeof(struct i596_dma),
 			      &lp->dma_addr, GFP_KERNEL,
-			      DMA_ATTR_NON_CONSISTENT);
+			      LIB82596_DMA_ATTR);
 	if (!dma) {
 		printk(KERN_ERR "%s: Couldn't get shared memory\n", __FILE__);
 		return -ENOMEM;
@@ -1087,7 +1087,7 @@ static int i82596_probe(struct net_device *dev)
 	i = register_netdev(dev);
 	if (i) {
 		dma_free_attrs(dev->dev.parent, sizeof(struct i596_dma),
-			       dma, lp->dma_addr, DMA_ATTR_NON_CONSISTENT);
+			       dma, lp->dma_addr, LIB82596_DMA_ATTR);
 		return i;
 	}
 
diff --git a/drivers/net/ethernet/i825xx/sni_82596.c b/drivers/net/ethernet/i825xx/sni_82596.c
index 6eb6c2ff7f09..6436a98c5953 100644
--- a/drivers/net/ethernet/i825xx/sni_82596.c
+++ b/drivers/net/ethernet/i825xx/sni_82596.c
@@ -24,6 +24,8 @@
 
 static const char sni_82596_string[] = "snirm_82596";
 
+#define LIB82596_DMA_ATTR	0
+
 #define DMA_WBACK(priv, addr, len)     do { } while (0)
 #define DMA_INV(priv, addr, len)       do { } while (0)
 #define DMA_WBACK_INV(priv, addr, len) do { } while (0)
@@ -152,7 +154,7 @@ static int sni_82596_driver_remove(struct platform_device *pdev)
 
 	unregister_netdev(dev);
 	dma_free_attrs(dev->dev.parent, sizeof(struct i596_private), lp->dma,
-		       lp->dma_addr, DMA_ATTR_NON_CONSISTENT);
+		       lp->dma_addr, LIB82596_DMA_ATTR);
 	iounmap(lp->ca);
 	iounmap(lp->mpu_port);
 	free_netdev (dev);
-- 
cgit v1.2.3


From 539825a536040e09a2f26eb54bef206e8e8086b5 Mon Sep 17 00:00:00 2001
From: "Ben Dooks (Codethink)" <ben.dooks@codethink.co.uk>
Date: Tue, 15 Oct 2019 17:15:58 +0100
Subject: davinci_cpdma: make cpdma_chan_split_pool static

The cpdma_chan_split_pool() function is not used outside of
the driver, so make it static to avoid the following sparse
warning:

drivers/net/ethernet/ti/davinci_cpdma.c:725:5: warning: symbol 'cpdma_chan_split_pool' was not declared. Should it be static?

Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/davinci_cpdma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index a65edd2770e6..37ba708ac781 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -722,7 +722,7 @@ static void cpdma_chan_set_descs(struct cpdma_ctlr *ctlr,
  * cpdma_chan_split_pool - Splits ctrl pool between all channels.
  * Has to be called under ctlr lock
  */
-int cpdma_chan_split_pool(struct cpdma_ctlr *ctlr)
+static int cpdma_chan_split_pool(struct cpdma_ctlr *ctlr)
 {
 	int tx_per_ch_desc = 0, rx_per_ch_desc = 0;
 	int free_rx_num = 0, free_tx_num = 0;
-- 
cgit v1.2.3


From bad28d889caea00bc9415c59fa6a433a72eeaf5e Mon Sep 17 00:00:00 2001
From: "Ben Dooks (Codethink)" <ben.dooks@codethink.co.uk>
Date: Tue, 15 Oct 2019 17:17:48 +0100
Subject: net: stmmac: make tc_flow_parsers static

The tc_flow_parsers is not used outside of the driver, so
make it static to avoid the following sparse warning:

drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c:516:3: warning: symbol 'tc_flow_parsers' was not declared. Should it be static?

Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index e231098061b6..f9a9a9d82233 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -510,7 +510,7 @@ static struct stmmac_flow_entry *tc_find_flow(struct stmmac_priv *priv,
 	return NULL;
 }
 
-struct {
+static struct {
 	int (*fn)(struct stmmac_priv *priv, struct flow_cls_offload *cls,
 		  struct stmmac_flow_entry *entry);
 } tc_flow_parsers[] = {
-- 
cgit v1.2.3


From efb86fede98cdc70b674692ff617b1162f642c49 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 15 Oct 2019 10:45:47 -0700
Subject: net: bcmgenet: Fix RGMII_MODE_EN value for GENET v1/2/3

The RGMII_MODE_EN bit value was 0 for GENET versions 1 through 3, and
became 6 for GENET v4 and above, account for that difference.

Fixes: aa09677cba42 ("net: bcmgenet: add MDIO routines")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Acked-by: Doug Berger <opendmb@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.h | 1 +
 drivers/net/ethernet/broadcom/genet/bcmmii.c   | 6 +++++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 4a8fc03d82fd..dbc69d8fa05f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -366,6 +366,7 @@ struct bcmgenet_mib_counters {
 #define  EXT_PWR_DOWN_PHY_EN		(1 << 20)
 
 #define EXT_RGMII_OOB_CTRL		0x0C
+#define  RGMII_MODE_EN_V123		(1 << 0)
 #define  RGMII_LINK			(1 << 4)
 #define  OOB_DISABLE			(1 << 5)
 #define  RGMII_MODE_EN			(1 << 6)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 94d1dd5d56bf..e7c291bf4ed1 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -258,7 +258,11 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 	 */
 	if (priv->ext_phy) {
 		reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL);
-		reg |= RGMII_MODE_EN | id_mode_dis;
+		reg |= id_mode_dis;
+		if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv))
+			reg |= RGMII_MODE_EN_V123;
+		else
+			reg |= RGMII_MODE_EN;
 		bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
 	}
 
-- 
cgit v1.2.3


From 77b6d09f4ae66d42cd63b121af67780ae3d1a5e9 Mon Sep 17 00:00:00 2001
From: Valentin Vidic <vvidic@valentin-vidic.from.hr>
Date: Tue, 15 Oct 2019 22:20:20 +0200
Subject: net: usb: sr9800: fix uninitialized local variable

Make sure res does not contain random value if the call to
sr_read_cmd fails for some reason.

Reported-by: syzbot+f1842130bbcfb335bac1@syzkaller.appspotmail.com
Signed-off-by: Valentin Vidic <vvidic@valentin-vidic.from.hr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/sr9800.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c
index c5d4a0060124..681e0def6356 100644
--- a/drivers/net/usb/sr9800.c
+++ b/drivers/net/usb/sr9800.c
@@ -335,7 +335,7 @@ static void sr_set_multicast(struct net_device *net)
 static int sr_mdio_read(struct net_device *net, int phy_id, int loc)
 {
 	struct usbnet *dev = netdev_priv(net);
-	__le16 res;
+	__le16 res = 0;
 
 	mutex_lock(&dev->phy_mutex);
 	sr_set_sw_mii(dev);
-- 
cgit v1.2.3


From 5bf4e52ff0317db083fafee010dc806f8d4cb0cb Mon Sep 17 00:00:00 2001
From: Greentime Hu <greentime.hu@sifive.com>
Date: Tue, 8 Oct 2019 14:45:24 +0800
Subject: RISC-V: fix virtual address overlapped in FIXADDR_START and
 VMEMMAP_START

This patch fixes the virtual address layout in pgtable.h.  The virtual
address of FIXADDR_START and VMEMMAP_START should not be overlapped.

Fixes: d95f1a542c3d ("RISC-V: Implement sparsemem")
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
[paul.walmsley@sifive.com: fixed patch description]
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
---
 arch/riscv/include/asm/pgtable.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 7255f2d8395b..42292d99cc74 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -87,14 +87,6 @@ extern pgd_t swapper_pg_dir[];
 #define VMALLOC_END      (PAGE_OFFSET - 1)
 #define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)
 
-#define FIXADDR_TOP      VMALLOC_START
-#ifdef CONFIG_64BIT
-#define FIXADDR_SIZE     PMD_SIZE
-#else
-#define FIXADDR_SIZE     PGDIR_SIZE
-#endif
-#define FIXADDR_START    (FIXADDR_TOP - FIXADDR_SIZE)
-
 /*
  * Roughly size the vmemmap space to be large enough to fit enough
  * struct pages to map half the virtual address space. Then
@@ -108,6 +100,14 @@ extern pgd_t swapper_pg_dir[];
 
 #define vmemmap		((struct page *)VMEMMAP_START)
 
+#define FIXADDR_TOP      (VMEMMAP_START)
+#ifdef CONFIG_64BIT
+#define FIXADDR_SIZE     PMD_SIZE
+#else
+#define FIXADDR_SIZE     PGDIR_SIZE
+#endif
+#define FIXADDR_START    (FIXADDR_TOP - FIXADDR_SIZE)
+
 /*
  * ZERO_PAGE is a global shared page that is always zero,
  * used for zero-mapped memory areas, etc.
-- 
cgit v1.2.3


From 775fd6bfefc66a8c33e91dd9687ed530643b954d Mon Sep 17 00:00:00 2001
From: Max Filippov <jcmvbkbc@gmail.com>
Date: Tue, 15 Oct 2019 21:51:43 -0700
Subject: xtensa: fix change_bit in exclusive access option

change_bit implementation for XCHAL_HAVE_EXCLUSIVE case changes all bits
except the one required due to copy-paste error from clear_bit.

Cc: stable@vger.kernel.org # v5.2+
Fixes: f7c34874f04a ("xtensa: add exclusive atomics support")
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/include/asm/bitops.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/xtensa/include/asm/bitops.h b/arch/xtensa/include/asm/bitops.h
index aeb15f4c755b..be8b2be5a98b 100644
--- a/arch/xtensa/include/asm/bitops.h
+++ b/arch/xtensa/include/asm/bitops.h
@@ -148,7 +148,7 @@ static inline void change_bit(unsigned int bit, volatile unsigned long *p)
 			"       getex   %0\n"
 			"       beqz    %0, 1b\n"
 			: "=&a" (tmp)
-			: "a" (~mask), "a" (p)
+			: "a" (mask), "a" (p)
 			: "memory");
 }
 
-- 
cgit v1.2.3


From 8574685547bdc4f11cc528f386e5396212409f9c Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 15 Oct 2019 09:59:11 +0100
Subject: drm/i915/selftests: Drop stale struct_mutex

A lately added test was missed when applying the struct_mutex removal
patches. Do so now.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015085911.10317-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/selftest_lrc.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 1276da059dc6..9c1f34fb5882 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -107,7 +107,6 @@ static int live_unlite_restore(struct drm_i915_private *i915, int prio)
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx;
 	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
 	struct igt_spinner spin;
 	int err = -ENOMEM;
 
@@ -116,11 +115,8 @@ static int live_unlite_restore(struct drm_i915_private *i915, int prio)
 	 * on the same engine from the same parent context.
 	 */
 
-	mutex_lock(&i915->drm.struct_mutex);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-
 	if (igt_spinner_init(&spin, &i915->gt))
-		goto err_unlock;
+		return err;
 
 	ctx = kernel_context(i915);
 	if (!ctx)
@@ -264,9 +260,6 @@ err_ce:
 	kernel_context_close(ctx);
 err_spin:
 	igt_spinner_fini(&spin);
-err_unlock:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 }
 
-- 
cgit v1.2.3


From 2d8b39a62a5d386a73f339e46fe05354a3a4895b Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 15 Oct 2019 19:35:20 +0200
Subject: ACPI: processor: Avoid NULL pointer dereferences at init time

If there are neither processor objects nor processor device objects
in the ACPI tables, the per-CPU processors table will not be
initialized and attempting to dereference pointers from there will
cause the kernel to crash.  This happens in acpi_processor_ppc_init()
and acpi_thermal_cpufreq_init() after commit d15ce412737a ("ACPI:
cpufreq: Switch to QoS requests instead of cpufreq notifier")
which didn't add the requisite NULL pointer checks in there.

Add the NULL pointer checks to acpi_processor_ppc_init() and
acpi_thermal_cpufreq_init(), and to the corresponding "exit"
routines.

While at it, drop redundant return instructions from
acpi_processor_ppc_init() and acpi_thermal_cpufreq_init().

Fixes: d15ce412737a ("ACPI: cpufreq: Switch to QoS requests instead of cpufreq notifier")
Reported-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
---
 drivers/acpi/processor_perflib.c | 10 ++++++----
 drivers/acpi/processor_thermal.c | 10 ++++++----
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 2261713d1aec..930a49fa4dfc 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -162,21 +162,23 @@ void acpi_processor_ppc_init(int cpu)
 	struct acpi_processor *pr = per_cpu(processors, cpu);
 	int ret;
 
+	if (!pr)
+		return;
+
 	ret = dev_pm_qos_add_request(get_cpu_device(cpu),
 				     &pr->perflib_req, DEV_PM_QOS_MAX_FREQUENCY,
 				     INT_MAX);
-	if (ret < 0) {
+	if (ret < 0)
 		pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu,
 		       ret);
-		return;
-	}
 }
 
 void acpi_processor_ppc_exit(int cpu)
 {
 	struct acpi_processor *pr = per_cpu(processors, cpu);
 
-	dev_pm_qos_remove_request(&pr->perflib_req);
+	if (pr)
+		dev_pm_qos_remove_request(&pr->perflib_req);
 }
 
 static int acpi_processor_get_performance_control(struct acpi_processor *pr)
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index ec2638f1df4f..8227c7dd75b1 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -130,21 +130,23 @@ void acpi_thermal_cpufreq_init(int cpu)
 	struct acpi_processor *pr = per_cpu(processors, cpu);
 	int ret;
 
+	if (!pr)
+		return;
+
 	ret = dev_pm_qos_add_request(get_cpu_device(cpu),
 				     &pr->thermal_req, DEV_PM_QOS_MAX_FREQUENCY,
 				     INT_MAX);
-	if (ret < 0) {
+	if (ret < 0)
 		pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu,
 		       ret);
-		return;
-	}
 }
 
 void acpi_thermal_cpufreq_exit(int cpu)
 {
 	struct acpi_processor *pr = per_cpu(processors, cpu);
 
-	dev_pm_qos_remove_request(&pr->thermal_req);
+	if (pr)
+		dev_pm_qos_remove_request(&pr->thermal_req);
 }
 #else				/* ! CONFIG_CPU_FREQ */
 static int cpufreq_get_max_state(unsigned int cpu)
-- 
cgit v1.2.3


From f418dddffc8007945fd5962380ebde770a240cf5 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Wed, 16 Oct 2019 23:27:32 +1100
Subject: usercopy: Avoid soft lockups in test_check_nonzero_user()

On a machine with a 64K PAGE_SIZE, the nested for loops in
test_check_nonzero_user() can lead to soft lockups, eg:

  watchdog: BUG: soft lockup - CPU#4 stuck for 22s! [modprobe:611]
  Modules linked in: test_user_copy(+) vmx_crypto gf128mul crc32c_vpmsum virtio_balloon ip_tables x_tables autofs4
  CPU: 4 PID: 611 Comm: modprobe Tainted: G             L    5.4.0-rc1-gcc-8.2.0-00001-gf5a1a536fa14-dirty #1151
  ...
  NIP __might_sleep+0x20/0xc0
  LR  __might_fault+0x40/0x60
  Call Trace:
    check_zeroed_user+0x12c/0x200
    test_user_copy_init+0x67c/0x1210 [test_user_copy]
    do_one_initcall+0x60/0x340
    do_init_module+0x7c/0x2f0
    load_module+0x2d94/0x30e0
    __do_sys_finit_module+0xc8/0x150
    system_call+0x5c/0x68

Even with a 4K PAGE_SIZE the test takes multiple seconds. Instead
tweak it to only scan a 1024 byte region, but make it cross the
page boundary.

Fixes: f5a1a536fa14 ("lib: introduce copy_struct_from_user() helper")
Suggested-by: Aleksa Sarai <cyphar@cyphar.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Aleksa Sarai <cyphar@cyphar.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/20191016122732.13467-1-mpe@ellerman.id.au
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
---
 lib/test_user_copy.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c
index ad2372727b1b..5ff04d8fe971 100644
--- a/lib/test_user_copy.c
+++ b/lib/test_user_copy.c
@@ -47,9 +47,25 @@ static bool is_zeroed(void *from, size_t size)
 static int test_check_nonzero_user(char *kmem, char __user *umem, size_t size)
 {
 	int ret = 0;
-	size_t start, end, i;
-	size_t zero_start = size / 4;
-	size_t zero_end = size - zero_start;
+	size_t start, end, i, zero_start, zero_end;
+
+	if (test(size < 2 * PAGE_SIZE, "buffer too small"))
+		return -EINVAL;
+
+	/*
+	 * We want to cross a page boundary to exercise the code more
+	 * effectively. We also don't want to make the size we scan too large,
+	 * otherwise the test can take a long time and cause soft lockups. So
+	 * scan a 1024 byte region across the page boundary.
+	 */
+	size = 1024;
+	start = PAGE_SIZE - (size / 2);
+
+	kmem += start;
+	umem += start;
+
+	zero_start = size / 4;
+	zero_end = size - zero_start;
 
 	/*
 	 * We conduct a series of check_nonzero_user() tests on a block of
-- 
cgit v1.2.3


From 2229adc81380c46908d46a91f05a6c1650456769 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 Oct 2019 11:08:51 +0100
Subject: drm/i915/execlist: Trim immediate timeslice expiry

We perform timeslicing immediately upon receipt of a request that may be
put into the second ELSP slot. The idea behind this was that since we
didn't install the timer if the second ELSP slot was empty, we would not
have any idea of how long ELSP[0] had been running and so giving the
newcomer a chance on the GPU was fair. However, this causes us extra
busy work that we may be able to avoid if we wait a jiffie for the first
timeslice as normal.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016100851.4979-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c | 30 +++++++++++++++++++++---------
 drivers/gpu/drm/i915/gt/intel_lrc.c       |  6 ++++--
 drivers/gpu/drm/i915/i915_gem.h           | 14 ++++++++++++++
 3 files changed, 39 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index c9d639c6becb..5051a1fd2565 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1241,6 +1241,17 @@ static struct intel_timeline *get_timeline(struct i915_request *rq)
 	return tl;
 }
 
+static const char *repr_timer(const struct timer_list *t)
+{
+	if (!READ_ONCE(t->expires))
+		return "inactive";
+
+	if (timer_pending(t))
+		return "active";
+
+	return "expired";
+}
+
 static void intel_engine_print_registers(struct intel_engine_cs *engine,
 					 struct drm_printer *m)
 {
@@ -1302,19 +1313,20 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 		unsigned int idx;
 		u8 read, write;
 
-		drm_printf(m, "\tExeclist status: 0x%08x %08x, entries %u\n",
-			   ENGINE_READ(engine, RING_EXECLIST_STATUS_LO),
-			   ENGINE_READ(engine, RING_EXECLIST_STATUS_HI),
-			   num_entries);
+		drm_printf(m, "\tExeclist tasklet queued? %s (%s), timeslice? %s\n",
+			   yesno(test_bit(TASKLET_STATE_SCHED,
+					  &engine->execlists.tasklet.state)),
+			   enableddisabled(!atomic_read(&engine->execlists.tasklet.count)),
+			   repr_timer(&engine->execlists.timer));
 
 		read = execlists->csb_head;
 		write = READ_ONCE(*execlists->csb_write);
 
-		drm_printf(m, "\tExeclist CSB read %d, write %d, tasklet queued? %s (%s)\n",
-			   read, write,
-			   yesno(test_bit(TASKLET_STATE_SCHED,
-					  &engine->execlists.tasklet.state)),
-			   enableddisabled(!atomic_read(&engine->execlists.tasklet.count)));
+		drm_printf(m, "\tExeclist status: 0x%08x %08x; CSB read:%d, write:%d, entries:%d\n",
+			   ENGINE_READ(engine, RING_EXECLIST_STATUS_LO),
+			   ENGINE_READ(engine, RING_EXECLIST_STATUS_HI),
+			   read, write, num_entries);
+
 		if (read >= num_entries)
 			read = 0;
 		if (write >= num_entries)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 44f213fd7604..e9fe9f79cedd 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1473,7 +1473,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			last->hw_context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 			last = NULL;
 		} else if (need_timeslice(engine, last) &&
-			   !timer_pending(&engine->execlists.timer)) {
+			   timer_expired(&engine->execlists.timer)) {
 			GEM_TRACE("%s: expired last=%llx:%lld, prio=%d, hint=%d\n",
 				  engine->name,
 				  last->fence.context,
@@ -1932,6 +1932,8 @@ static void process_csb(struct intel_engine_cs *engine)
 
 			if (enable_timeslice(execlists))
 				mod_timer(&execlists->timer, jiffies + 1);
+			else
+				cancel_timer(&execlists->timer);
 
 			WRITE_ONCE(execlists->pending[0], NULL);
 		} else {
@@ -3452,7 +3454,7 @@ gen12_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 
 static void execlists_park(struct intel_engine_cs *engine)
 {
-	del_timer(&engine->execlists.timer);
+	cancel_timer(&engine->execlists.timer);
 }
 
 void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index f6f9675848b8..2011f8e9a9f1 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -112,4 +112,18 @@ static inline bool __tasklet_is_scheduled(struct tasklet_struct *t)
 	return test_bit(TASKLET_STATE_SCHED, &t->state);
 }
 
+static inline void cancel_timer(struct timer_list *t)
+{
+	if (!READ_ONCE(t->expires))
+		return;
+
+	del_timer(t);
+	WRITE_ONCE(t->expires, 0);
+}
+
+static inline bool timer_expired(const struct timer_list *t)
+{
+	return READ_ONCE(t->expires) && !timer_pending(t);
+}
+
 #endif /* __I915_GEM_H__ */
-- 
cgit v1.2.3


From 993254292b9e0be97555cd3475bcdb946c558381 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 7 Oct 2019 14:49:43 +0300
Subject: drm/i915: Refactor timestamping constants update
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Once we do the hw vs. uapi split we can no longer use
drm_atomic_helper_calc_timestamping_constants() as it'll
consult the uapi state instead of the hw state.

So let's just update the vblank timestamping constants whenever
we update the scanline offset. We use both to convert the hw
scanline count to something which matches the software timing
values.

First I thought to put these into intel_crtc_vblank_on() but
we may want to get the scanline counter value before that (eg.
from some early tracepoints), so let's stick to updating them
a bit earlier than intel_crtc_vblank_on().

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191007114943.29307-3-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 7d7d1859775a..cc1cf9a4f609 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -13316,10 +13316,15 @@ intel_modeset_verify_disabled(struct drm_i915_private *dev_priv,
 	verify_disabled_dpll_state(dev_priv);
 }
 
-static void update_scanline_offset(const struct intel_crtc_state *crtc_state)
+static void
+intel_crtc_update_active_timings(const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	const struct drm_display_mode *adjusted_mode =
+		&crtc_state->base.adjusted_mode;
+
+	drm_calc_timestamping_constants(&crtc->base, adjusted_mode);
 
 	/*
 	 * The scanline counter increments at the leading edge of hsync.
@@ -13349,7 +13354,6 @@ static void update_scanline_offset(const struct intel_crtc_state *crtc_state)
 	 * answer that's slightly in the future.
 	 */
 	if (IS_GEN(dev_priv, 2)) {
-		const struct drm_display_mode *adjusted_mode = &crtc_state->base.adjusted_mode;
 		int vtotal;
 
 		vtotal = adjusted_mode->crtc_vtotal;
@@ -13360,8 +13364,9 @@ static void update_scanline_offset(const struct intel_crtc_state *crtc_state)
 	} else if (HAS_DDI(dev_priv) &&
 		   intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
 		crtc->scanline_offset = 2;
-	} else
+	} else {
 		crtc->scanline_offset = 1;
+	}
 }
 
 static void intel_modeset_clear_plls(struct intel_atomic_state *state)
@@ -13784,7 +13789,8 @@ static void intel_update_crtc(struct intel_crtc *crtc,
 						 to_intel_plane(crtc->base.primary));
 
 	if (modeset) {
-		update_scanline_offset(new_crtc_state);
+		intel_crtc_update_active_timings(new_crtc_state);
+
 		dev_priv->display.crtc_enable(new_crtc_state, state);
 
 		/* vblanks work again, re-enable pipe CRC. */
@@ -16812,9 +16818,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			if (WARN_ON(min_cdclk < 0))
 				min_cdclk = 0;
 
-			drm_calc_timestamping_constants(&crtc->base,
-							&crtc_state->base.adjusted_mode);
-			update_scanline_offset(crtc_state);
+			intel_crtc_update_active_timings(crtc_state);
 		}
 
 		dev_priv->min_cdclk[crtc->pipe] = min_cdclk;
-- 
cgit v1.2.3


From 4078c983feb930bc2a3e3f8ffa6fa65fdf466c8f Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 27 Sep 2019 16:14:27 +0300
Subject: drm/i915: Switch intel_legacy_cursor_update() to intel_ types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prefer the intel_ types in intel_legacy_cursor_update() over the
drm_ types. Should make it easier to adapt this to the uapi vs. hw
state split.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190927131432.15978-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 84 ++++++++++++++--------------
 1 file changed, 42 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index cc1cf9a4f609..cc4489591721 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -14704,8 +14704,8 @@ static const struct drm_plane_funcs i8xx_plane_funcs = {
 };
 
 static int
-intel_legacy_cursor_update(struct drm_plane *plane,
-			   struct drm_crtc *crtc,
+intel_legacy_cursor_update(struct drm_plane *_plane,
+			   struct drm_crtc *_crtc,
 			   struct drm_framebuffer *fb,
 			   int crtc_x, int crtc_y,
 			   unsigned int crtc_w, unsigned int crtc_h,
@@ -14713,10 +14713,13 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 			   u32 src_w, u32 src_h,
 			   struct drm_modeset_acquire_ctx *ctx)
 {
-	struct drm_plane_state *old_plane_state, *new_plane_state;
-	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct intel_plane *plane = to_intel_plane(_plane);
+	struct intel_crtc *crtc = to_intel_crtc(_crtc);
+	struct intel_plane_state *old_plane_state =
+		to_intel_plane_state(plane->base.state);
+	struct intel_plane_state *new_plane_state;
 	struct intel_crtc_state *crtc_state =
-		to_intel_crtc_state(crtc->state);
+		to_intel_crtc_state(crtc->base.state);
 	struct intel_crtc_state *new_crtc_state;
 	int ret;
 
@@ -14728,14 +14731,13 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 	    crtc_state->update_pipe)
 		goto slow;
 
-	old_plane_state = plane->state;
 	/*
 	 * Don't do an async update if there is an outstanding commit modifying
 	 * the plane.  This prevents our async update's changes from getting
 	 * overridden by a previous synchronous update's state.
 	 */
-	if (old_plane_state->commit &&
-	    !try_wait_for_completion(&old_plane_state->commit->hw_done))
+	if (old_plane_state->base.commit &&
+	    !try_wait_for_completion(&old_plane_state->base.commit->hw_done))
 		goto slow;
 
 	/*
@@ -14743,52 +14745,51 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 	 * take the slowpath. Only changing fb or position should be
 	 * in the fastpath.
 	 */
-	if (old_plane_state->crtc != crtc ||
-	    old_plane_state->src_w != src_w ||
-	    old_plane_state->src_h != src_h ||
-	    old_plane_state->crtc_w != crtc_w ||
-	    old_plane_state->crtc_h != crtc_h ||
-	    !old_plane_state->fb != !fb)
+	if (old_plane_state->base.crtc != &crtc->base ||
+	    old_plane_state->base.src_w != src_w ||
+	    old_plane_state->base.src_h != src_h ||
+	    old_plane_state->base.crtc_w != crtc_w ||
+	    old_plane_state->base.crtc_h != crtc_h ||
+	    !old_plane_state->base.fb != !fb)
 		goto slow;
 
-	new_plane_state = intel_plane_duplicate_state(plane);
+	new_plane_state = to_intel_plane_state(intel_plane_duplicate_state(&plane->base));
 	if (!new_plane_state)
 		return -ENOMEM;
 
-	new_crtc_state = to_intel_crtc_state(intel_crtc_duplicate_state(crtc));
+	new_crtc_state = to_intel_crtc_state(intel_crtc_duplicate_state(&crtc->base));
 	if (!new_crtc_state) {
 		ret = -ENOMEM;
 		goto out_free;
 	}
 
-	drm_atomic_set_fb_for_plane(new_plane_state, fb);
+	drm_atomic_set_fb_for_plane(&new_plane_state->base, fb);
 
-	new_plane_state->src_x = src_x;
-	new_plane_state->src_y = src_y;
-	new_plane_state->src_w = src_w;
-	new_plane_state->src_h = src_h;
-	new_plane_state->crtc_x = crtc_x;
-	new_plane_state->crtc_y = crtc_y;
-	new_plane_state->crtc_w = crtc_w;
-	new_plane_state->crtc_h = crtc_h;
+	new_plane_state->base.src_x = src_x;
+	new_plane_state->base.src_y = src_y;
+	new_plane_state->base.src_w = src_w;
+	new_plane_state->base.src_h = src_h;
+	new_plane_state->base.crtc_x = crtc_x;
+	new_plane_state->base.crtc_y = crtc_y;
+	new_plane_state->base.crtc_w = crtc_w;
+	new_plane_state->base.crtc_h = crtc_h;
 
 	ret = intel_plane_atomic_check_with_state(crtc_state, new_crtc_state,
-						  to_intel_plane_state(old_plane_state),
-						  to_intel_plane_state(new_plane_state));
+						  old_plane_state, new_plane_state);
 	if (ret)
 		goto out_free;
 
-	ret = intel_plane_pin_fb(to_intel_plane_state(new_plane_state));
+	ret = intel_plane_pin_fb(new_plane_state);
 	if (ret)
 		goto out_free;
 
-	intel_frontbuffer_flush(to_intel_frontbuffer(fb), ORIGIN_FLIP);
-	intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->fb),
-				to_intel_frontbuffer(fb),
-				intel_plane->frontbuffer_bit);
+	intel_frontbuffer_flush(to_intel_frontbuffer(new_plane_state->base.fb), ORIGIN_FLIP);
+	intel_frontbuffer_track(to_intel_frontbuffer(old_plane_state->base.fb),
+				to_intel_frontbuffer(new_plane_state->base.fb),
+				plane->frontbuffer_bit);
 
 	/* Swap plane state */
-	plane->state = new_plane_state;
+	plane->base.state = &new_plane_state->base;
 
 	/*
 	 * We cannot swap crtc_state as it may be in use by an atomic commit or
@@ -14802,25 +14803,24 @@ intel_legacy_cursor_update(struct drm_plane *plane,
 	 */
 	crtc_state->active_planes = new_crtc_state->active_planes;
 
-	if (plane->state->visible)
-		intel_update_plane(intel_plane, crtc_state,
-				   to_intel_plane_state(plane->state));
+	if (new_plane_state->base.visible)
+		intel_update_plane(plane, crtc_state, new_plane_state);
 	else
-		intel_disable_plane(intel_plane, crtc_state);
+		intel_disable_plane(plane, crtc_state);
 
-	intel_plane_unpin_fb(to_intel_plane_state(old_plane_state));
+	intel_plane_unpin_fb(old_plane_state);
 
 out_free:
 	if (new_crtc_state)
-		intel_crtc_destroy_state(crtc, &new_crtc_state->base);
+		intel_crtc_destroy_state(&crtc->base, &new_crtc_state->base);
 	if (ret)
-		intel_plane_destroy_state(plane, new_plane_state);
+		intel_plane_destroy_state(&plane->base, &new_plane_state->base);
 	else
-		intel_plane_destroy_state(plane, old_plane_state);
+		intel_plane_destroy_state(&plane->base, &old_plane_state->base);
 	return ret;
 
 slow:
-	return drm_atomic_helper_update_plane(plane, crtc, fb,
+	return drm_atomic_helper_update_plane(&plane->base, &crtc->base, fb,
 					      crtc_x, crtc_y, crtc_w, crtc_h,
 					      src_x, src_y, src_w, src_h, ctx);
 }
-- 
cgit v1.2.3


From de3b67afc0602f81fc6309544f97d4425c2e2cf6 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 27 Sep 2019 16:14:28 +0300
Subject: drm/i915: Prepare the connector/encoder mask readout for hw vs. uapi
 state split
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prepare the connector/encoder mask readout for the uapi vs. hw
state split. We'll want to do all readout into the hw state.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190927131432.15978-2-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index cc4489591721..c72c9a4bb973 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -16757,24 +16757,28 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 	drm_connector_list_iter_begin(dev, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter) {
 		if (connector->get_hw_state(connector)) {
+			struct intel_crtc_state *crtc_state;
+			struct intel_crtc *crtc;
+
 			connector->base.dpms = DRM_MODE_DPMS_ON;
 
 			encoder = connector->encoder;
 			connector->base.encoder = &encoder->base;
 
-			if (encoder->base.crtc &&
-			    encoder->base.crtc->state->active) {
+			crtc = to_intel_crtc(encoder->base.crtc);
+			crtc_state = crtc ? to_intel_crtc_state(crtc->base.state) : NULL;
+
+			if (crtc_state && crtc_state->base.active) {
 				/*
 				 * This has to be done during hardware readout
 				 * because anything calling .crtc_disable may
 				 * rely on the connector_mask being accurate.
 				 */
-				encoder->base.crtc->state->connector_mask |=
+				crtc_state->base.connector_mask |=
 					drm_connector_mask(&connector->base);
-				encoder->base.crtc->state->encoder_mask |=
+				crtc_state->base.encoder_mask |=
 					drm_encoder_mask(&encoder->base);
 			}
-
 		} else {
 			connector->base.dpms = DRM_MODE_DPMS_OFF;
 			connector->base.encoder = NULL;
-- 
cgit v1.2.3


From 3abe897787c2445fb1aa955ac229bdfe2ac786c2 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 27 Sep 2019 16:14:30 +0300
Subject: drm/i915: Prepare the mode readout for hw vs. uapi state split
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prepare the mode readout for the uapi vs. hw state split.
We'll want to do all readout into the hw state.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190927131432.15978-4-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index c72c9a4bb973..2309b349f4b5 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -16803,7 +16803,7 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			crtc->base.mode.hdisplay = crtc_state->pipe_src_w;
 			crtc->base.mode.vdisplay = crtc_state->pipe_src_h;
 			intel_mode_from_pipe_config(&crtc_state->base.adjusted_mode, crtc_state);
-			WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode));
+			WARN_ON(drm_atomic_set_mode_for_crtc(&crtc_state->base, &crtc->base.mode));
 
 			/*
 			 * The initial mode needs to be set in order to keep
-- 
cgit v1.2.3


From fcb9bba47fb5ff39912f8f3b7b6d32992e461368 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Tue, 15 Oct 2019 09:11:31 -0700
Subject: drm/i915/ehl: Don't forget to set TC long detect function

Since EHL's MCC PCH reuses one of the TC pins we need to supply a TC
long detect function when handling the interrupts.

Fixes: 53448aed7b80 ("drm/i915/ehl: Port C's hotplug interrupt is associated with TC1 bits")
Reported-by: kbuild test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Vivek Kasireddy <vivek.kasireddy@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015161131.21239-1-matthew.d.roper@intel.com
Reviewed-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index a7c968b01af3..af7426cd8de9 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2251,6 +2251,7 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 	} else if (HAS_PCH_MCC(dev_priv)) {
 		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP;
 		tc_hotplug_trigger = pch_iir & SDE_TC_HOTPLUG_ICP(PORT_TC1);
+		tc_port_hotplug_long_detect = icp_tc_port_hotplug_long_detect;
 		pins = hpd_icp;
 	} else {
 		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP;
-- 
cgit v1.2.3


From 943682e3bd19385511171d730499120ab7245566 Mon Sep 17 00:00:00 2001
From: Matt Roper <matthew.d.roper@intel.com>
Date: Tue, 15 Oct 2019 09:28:54 -0700
Subject: drm/i915: Introduce Jasper Lake PCH
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Jasper Lake PCH follows ICP/TGP's south display behavior and is
identical to MCC graphics-wise except that it does not use the unusual
(port C -> TC1) pin mapping that MCC does.

Also, it turns out the extra PCH ID that we had previously thought was a
form of MCC is actually a second ID for JSP (i.e., port C uses the port
C pins instead of the TC1 pins).

v2:
 - Also update the port masks (not just the pin table) in
   mcc_hpd_irq_setup.  (Vivek)

v3:
 - Break jsp_hpd_irq_setup out into its own function for clarity.
   (Vivek)

Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: James Ausmus <james.ausmus@intel.com>
Cc: Vivek Kasireddy <vivek.kasireddy@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015162854.30546-1-matthew.d.roper@intel.com
---
 drivers/gpu/drm/i915/i915_irq.c  | 24 +++++++++++++++++++++++-
 drivers/gpu/drm/i915/intel_pch.c |  6 +++++-
 drivers/gpu/drm/i915/intel_pch.h |  5 ++++-
 3 files changed, 32 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index af7426cd8de9..ef09fbb36f37 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2248,12 +2248,19 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		tc_hotplug_trigger = pch_iir & SDE_TC_MASK_TGP;
 		tc_port_hotplug_long_detect = tgp_tc_port_hotplug_long_detect;
 		pins = hpd_tgp;
+	} else if (HAS_PCH_JSP(dev_priv)) {
+		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_TGP;
+		tc_hotplug_trigger = 0;
+		pins = hpd_tgp;
 	} else if (HAS_PCH_MCC(dev_priv)) {
 		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP;
 		tc_hotplug_trigger = pch_iir & SDE_TC_HOTPLUG_ICP(PORT_TC1);
 		tc_port_hotplug_long_detect = icp_tc_port_hotplug_long_detect;
 		pins = hpd_icp;
 	} else {
+		WARN(!HAS_PCH_ICP(dev_priv),
+		     "Unrecognized PCH type 0x%x\n", INTEL_PCH_TYPE(dev_priv));
+
 		ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP;
 		tc_hotplug_trigger = pch_iir & SDE_TC_MASK_ICP;
 		tc_port_hotplug_long_detect = icp_tc_port_hotplug_long_detect;
@@ -3383,6 +3390,19 @@ static void mcc_hpd_irq_setup(struct drm_i915_private *dev_priv)
 			  hpd_icp);
 }
 
+/*
+ * JSP behaves exactly the same as MCC above except that port C is mapped to
+ * the DDI-C pins instead of the TC1 pins.  This means we should follow TGP's
+ * masks & tables rather than ICP's masks & tables.
+ */
+static void jsp_hpd_irq_setup(struct drm_i915_private *dev_priv)
+{
+	icp_hpd_irq_setup(dev_priv,
+			  SDE_DDI_MASK_TGP, 0,
+			  TGP_DDI_HPD_ENABLE_MASK, 0,
+			  hpd_tgp);
+}
+
 static void gen11_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
 	u32 hotplug;
@@ -4314,7 +4334,9 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 		if (I915_HAS_HOTPLUG(dev_priv))
 			dev_priv->display.hpd_irq_setup = i915_hpd_irq_setup;
 	} else {
-		if (HAS_PCH_MCC(dev_priv))
+		if (HAS_PCH_JSP(dev_priv))
+			dev_priv->display.hpd_irq_setup = jsp_hpd_irq_setup;
+		else if (HAS_PCH_MCC(dev_priv))
 			dev_priv->display.hpd_irq_setup = mcc_hpd_irq_setup;
 		else if (INTEL_GEN(dev_priv) >= 11)
 			dev_priv->display.hpd_irq_setup = gen11_hpd_irq_setup;
diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c
index 15f8bff141f9..1035d3d46fd8 100644
--- a/drivers/gpu/drm/i915/intel_pch.c
+++ b/drivers/gpu/drm/i915/intel_pch.c
@@ -79,7 +79,6 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 		WARN_ON(!IS_ICELAKE(dev_priv));
 		return PCH_ICP;
 	case INTEL_PCH_MCC_DEVICE_ID_TYPE:
-	case INTEL_PCH_MCC2_DEVICE_ID_TYPE:
 		DRM_DEBUG_KMS("Found Mule Creek Canyon PCH\n");
 		WARN_ON(!IS_ELKHARTLAKE(dev_priv));
 		return PCH_MCC;
@@ -87,6 +86,11 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 		DRM_DEBUG_KMS("Found Tiger Lake LP PCH\n");
 		WARN_ON(!IS_TIGERLAKE(dev_priv));
 		return PCH_TGP;
+	case INTEL_PCH_JSP_DEVICE_ID_TYPE:
+	case INTEL_PCH_JSP2_DEVICE_ID_TYPE:
+		DRM_DEBUG_KMS("Found Jasper Lake PCH\n");
+		WARN_ON(!IS_ELKHARTLAKE(dev_priv));
+		return PCH_JSP;
 	default:
 		return PCH_NONE;
 	}
diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h
index c29c81ec7971..f4dc18c34291 100644
--- a/drivers/gpu/drm/i915/intel_pch.h
+++ b/drivers/gpu/drm/i915/intel_pch.h
@@ -23,6 +23,7 @@ enum intel_pch {
 	PCH_SPT,        /* Sunrisepoint/Kaby Lake PCH */
 	PCH_CNP,        /* Cannon/Comet Lake PCH */
 	PCH_ICP,	/* Ice Lake PCH */
+	PCH_JSP,	/* Jasper Lake PCH */
 	PCH_MCC,        /* Mule Creek Canyon PCH */
 	PCH_TGP,	/* Tiger Lake PCH */
 };
@@ -44,14 +45,16 @@ enum intel_pch {
 #define INTEL_PCH_CMP2_DEVICE_ID_TYPE		0x0680
 #define INTEL_PCH_ICP_DEVICE_ID_TYPE		0x3480
 #define INTEL_PCH_MCC_DEVICE_ID_TYPE		0x4B00
-#define INTEL_PCH_MCC2_DEVICE_ID_TYPE		0x3880
 #define INTEL_PCH_TGP_DEVICE_ID_TYPE		0xA080
+#define INTEL_PCH_JSP_DEVICE_ID_TYPE		0x4D80
+#define INTEL_PCH_JSP2_DEVICE_ID_TYPE		0x3880
 #define INTEL_PCH_P2X_DEVICE_ID_TYPE		0x7100
 #define INTEL_PCH_P3X_DEVICE_ID_TYPE		0x7000
 #define INTEL_PCH_QEMU_DEVICE_ID_TYPE		0x2900 /* qemu q35 has 2918 */
 
 #define INTEL_PCH_TYPE(dev_priv)		((dev_priv)->pch_type)
 #define INTEL_PCH_ID(dev_priv)			((dev_priv)->pch_id)
+#define HAS_PCH_JSP(dev_priv)			(INTEL_PCH_TYPE(dev_priv) == PCH_JSP)
 #define HAS_PCH_MCC(dev_priv)			(INTEL_PCH_TYPE(dev_priv) == PCH_MCC)
 #define HAS_PCH_TGP(dev_priv)			(INTEL_PCH_TYPE(dev_priv) == PCH_TGP)
 #define HAS_PCH_ICP(dev_priv)			(INTEL_PCH_TYPE(dev_priv) == PCH_ICP)
-- 
cgit v1.2.3


From bc88f85c6c09306bd21917e1ae28205e9cd775a7 Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Wed, 16 Oct 2019 12:24:58 +0100
Subject: kthread: make __kthread_queue_delayed_work static

The __kthread_queue_delayed_work is not exported so
make it static, to avoid the following sparse warning:

  kernel/kthread.c:869:6: warning: symbol '__kthread_queue_delayed_work' was not declared. Should it be static?

Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/kthread.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/kthread.c b/kernel/kthread.c
index 621467c33fef..b262f47046ca 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -866,9 +866,9 @@ void kthread_delayed_work_timer_fn(struct timer_list *t)
 }
 EXPORT_SYMBOL(kthread_delayed_work_timer_fn);
 
-void __kthread_queue_delayed_work(struct kthread_worker *worker,
-				  struct kthread_delayed_work *dwork,
-				  unsigned long delay)
+static void __kthread_queue_delayed_work(struct kthread_worker *worker,
+					 struct kthread_delayed_work *dwork,
+					 unsigned long delay)
 {
 	struct timer_list *timer = &dwork->timer;
 	struct kthread_work *work = &dwork->work;
-- 
cgit v1.2.3


From 3874d73e06c9b9dc15de0b7382fc223986d75571 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Mon, 14 Oct 2019 16:58:35 -0700
Subject: md/raid0: fix warning message for parameter default_layout

The message should match the parameter, i.e. raid0.default_layout.

Fixes: c84a1372df92 ("md/raid0: avoid RAID0 data corruption due to layout confusion.")
Cc: NeilBrown <neilb@suse.de>
Reported-by: Ivan Topolsky <doktor.yak@gmail.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
---
 drivers/md/raid0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index f61693e59684..1e772287b1c8 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -154,7 +154,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	} else {
 		pr_err("md/raid0:%s: cannot assemble multi-zone RAID0 with default_layout setting\n",
 		       mdname(mddev));
-		pr_err("md/raid0: please set raid.default_layout to 1 or 2\n");
+		pr_err("md/raid0: please set raid0.default_layout to 1 or 2\n");
 		err = -ENOTSUPP;
 		goto abort;
 	}
-- 
cgit v1.2.3


From 19c95f261c6558d4c2cbbfacd2d8bb6501384601 Mon Sep 17 00:00:00 2001
From: Julien Thierry <julien.thierry@arm.com>
Date: Tue, 15 Oct 2019 18:25:44 +0100
Subject: arm64: entry.S: Do not preempt from IRQ before all cpufeatures are
 enabled

Preempting from IRQ-return means that the task has its PSTATE saved
on the stack, which will get restored when the task is resumed and does
the actual IRQ return.

However, enabling some CPU features requires modifying the PSTATE. This
means that, if a task was scheduled out during an IRQ-return before all
CPU features are enabled, the task might restore a PSTATE that does not
include the feature enablement changes once scheduled back in.

* Task 1:

PAN == 0 ---|                          |---------------
            |                          |<- return from IRQ, PSTATE.PAN = 0
            | <- IRQ                   |
            +--------+ <- preempt()  +--
                                     ^
                                     |
                                     reschedule Task 1, PSTATE.PAN == 1
* Init:
        --------------------+------------------------
                            ^
                            |
                            enable_cpu_features
                            set PSTATE.PAN on all CPUs

Worse than this, since PSTATE is untouched when task switching is done,
a task missing the new bits in PSTATE might affect another task, if both
do direct calls to schedule() (outside of IRQ/exception contexts).

Fix this by preventing preemption on IRQ-return until features are
enabled on all CPUs.

This way the only PSTATE values that are saved on the stack are from
synchronous exceptions. These are expected to be fatal this early, the
exception is BRK for WARN_ON(), but as this uses do_debug_exception()
which keeps IRQs masked, it shouldn't call schedule().

Signed-off-by: Julien Thierry <julien.thierry@arm.com>
[james: Replaced a really cool hack, with an even simpler static key in C.
 expanded commit message with Julien's cover-letter ascii art]
Signed-off-by: James Morse <james.morse@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kernel/entry.S   |  2 +-
 arch/arm64/kernel/process.c | 18 ++++++++++++++++++
 include/linux/sched.h       |  1 +
 3 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index e304fe04b098..e1859e010c5f 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -680,7 +680,7 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	orr	x24, x24, x0
 alternative_else_nop_endif
 	cbnz	x24, 1f				// preempt count != 0 || NMI return path
-	bl	preempt_schedule_irq		// irq en/disable is done inside
+	bl	arm64_preempt_schedule_irq	// irq en/disable is done inside
 1:
 #endif
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 1fb2819fc048..71f788cd2b18 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -17,6 +17,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/kernel.h>
+#include <linux/lockdep.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/sysctl.h>
@@ -44,6 +45,7 @@
 #include <asm/alternative.h>
 #include <asm/arch_gicv3.h>
 #include <asm/compat.h>
+#include <asm/cpufeature.h>
 #include <asm/cacheflush.h>
 #include <asm/exec.h>
 #include <asm/fpsimd.h>
@@ -631,3 +633,19 @@ static int __init tagged_addr_init(void)
 
 core_initcall(tagged_addr_init);
 #endif	/* CONFIG_ARM64_TAGGED_ADDR_ABI */
+
+asmlinkage void __sched arm64_preempt_schedule_irq(void)
+{
+	lockdep_assert_irqs_disabled();
+
+	/*
+	 * Preempting a task from an IRQ means we leave copies of PSTATE
+	 * on the stack. cpufeature's enable calls may modify PSTATE, but
+	 * resuming one of these preempted tasks would undo those changes.
+	 *
+	 * Only allow a task to be preempted once cpufeatures have been
+	 * enabled.
+	 */
+	if (static_branch_likely(&arm64_const_caps_ready))
+		preempt_schedule_irq();
+}
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2c2e56bd8913..67a1d86981a9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -223,6 +223,7 @@ extern long schedule_timeout_uninterruptible(long timeout);
 extern long schedule_timeout_idle(long timeout);
 asmlinkage void schedule(void);
 extern void schedule_preempt_disabled(void);
+asmlinkage void preempt_schedule_irq(void);
 
 extern int __must_check io_schedule_prepare(void);
 extern void io_schedule_finish(int token);
-- 
cgit v1.2.3


From 29a0f5ad87e6f45c984ffffa57b7142d178ff422 Mon Sep 17 00:00:00 2001
From: Yang Yingliang <yangyingliang@huawei.com>
Date: Wed, 16 Oct 2019 11:42:57 +0800
Subject: arm64: sysreg: fix incorrect definition of SYS_PAR_EL1_F

The 'F' field of the PAR_EL1 register lives in bit 0, not bit 1.
Fix the broken definition in 'sysreg.h'.

Fixes: e8620cff9994 ("arm64: sysreg: Add some field definitions for PAR_EL1")
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/sysreg.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 972d196c7714..6e919fafb43d 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -212,7 +212,7 @@
 #define SYS_FAR_EL1			sys_reg(3, 0, 6, 0, 0)
 #define SYS_PAR_EL1			sys_reg(3, 0, 7, 4, 0)
 
-#define SYS_PAR_EL1_F			BIT(1)
+#define SYS_PAR_EL1_F			BIT(0)
 #define SYS_PAR_EL1_FST			GENMASK(6, 1)
 
 /*** Statistical Profiling Extension ***/
-- 
cgit v1.2.3


From 3813733595c0c7c0674d106309b04e871d54dc1c Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 16 Oct 2019 12:03:04 +0100
Subject: arm64: mm: fix inverted PAR_EL1.F check

When detecting a spurious EL1 translation fault, we have the CPU retry
the translation using an AT S1E1R instruction, and inspect PAR_EL1 to
determine if the fault was spurious.

When PAR_EL1.F == 0, the AT instruction successfully translated the
address without a fault, which implies the original fault was spurious.
However, in this case we return false and treat the original fault as if
it was not spurious.

Invert the return value so that we treat such a case as spurious.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Fixes: 42f91093b043 ("arm64: mm: Ignore spurious translation faults taken from the kernel")
Tested-by: James Morse <james.morse@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/fault.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 855f2a7954e6..9fc6db0bcbad 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -268,8 +268,12 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr,
 	par = read_sysreg(par_el1);
 	local_irq_restore(flags);
 
+	/*
+	 * If we now have a valid translation, treat the translation fault as
+	 * spurious.
+	 */
 	if (!(par & SYS_PAR_EL1_F))
-		return false;
+		return true;
 
 	/*
 	 * If we got a different type of fault from the AT instruction,
-- 
cgit v1.2.3


From 597399d0cb91d049fcb78fb45c7694771b583bb7 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Tue, 15 Oct 2019 21:04:18 -0700
Subject: arm64: tags: Preserve tags for addresses translated via TTBR1

Sign-extending TTBR1 addresses when converting to an untagged address
breaks the documented POSIX semantics for mlock() in some obscure error
cases where we end up returning -EINVAL instead of -ENOMEM as a direct
result of rewriting the upper address bits.

Rework the untagged_addr() macro to preserve the upper address bits for
TTBR1 addresses and only clear the tag bits for user addresses. This
matches the behaviour of the 'clear_address_tag' assembly macro, so
rename that and align the implementations at the same time so that they
use the same instruction sequences for the tag manipulation.

Link: https://lore.kernel.org/stable/20191014162651.GF19200@arrakis.emea.arm.com/
Reported-by: Jan Stancek <jstancek@redhat.com>
Tested-by: Jan Stancek <jstancek@redhat.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Tested-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Reviewed-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/asm-uaccess.h |  7 +++----
 arch/arm64/include/asm/memory.h      | 10 ++++++++--
 arch/arm64/kernel/entry.S            |  4 ++--
 3 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
index f74909ba29bd..5bf963830b17 100644
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -78,10 +78,9 @@ alternative_else_nop_endif
 /*
  * Remove the address tag from a virtual address, if present.
  */
-	.macro	clear_address_tag, dst, addr
-	tst	\addr, #(1 << 55)
-	bic	\dst, \addr, #(0xff << 56)
-	csel	\dst, \dst, \addr, eq
+	.macro	untagged_addr, dst, addr
+	sbfx	\dst, \addr, #0, #56
+	and	\dst, \dst, \addr
 	.endm
 
 #endif
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index b61b50bf68b1..c23c47360664 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -215,12 +215,18 @@ static inline unsigned long kaslr_offset(void)
  * up with a tagged userland pointer. Clear the tag to get a sane pointer to
  * pass on to access_ok(), for instance.
  */
-#define untagged_addr(addr)	\
+#define __untagged_addr(addr)	\
 	((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55))
 
+#define untagged_addr(addr)	({					\
+	u64 __addr = (__force u64)addr;					\
+	__addr &= __untagged_addr(__addr);				\
+	(__force __typeof__(addr))__addr;				\
+})
+
 #ifdef CONFIG_KASAN_SW_TAGS
 #define __tag_shifted(tag)	((u64)(tag) << 56)
-#define __tag_reset(addr)	untagged_addr(addr)
+#define __tag_reset(addr)	__untagged_addr(addr)
 #define __tag_get(addr)		(__u8)((u64)(addr) >> 56)
 #else
 #define __tag_shifted(tag)	0UL
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index e1859e010c5f..a3a63092eba9 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -604,7 +604,7 @@ el1_da:
 	 */
 	mrs	x3, far_el1
 	inherit_daif	pstate=x23, tmp=x2
-	clear_address_tag x0, x3
+	untagged_addr	x0, x3
 	mov	x2, sp				// struct pt_regs
 	bl	do_mem_abort
 
@@ -808,7 +808,7 @@ el0_da:
 	mrs	x26, far_el1
 	ct_user_exit_irqoff
 	enable_daif
-	clear_address_tag x0, x26
+	untagged_addr	x0, x26
 	mov	x1, x25
 	mov	x2, sp
 	bl	do_mem_abort
-- 
cgit v1.2.3


From 1357fa8136ea0309890b0a8e5f7311e4f01f2b6a Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 Oct 2019 13:02:49 +0100
Subject: drm/i915/selftests: Teach execlists to take intel_gt as its argument

The execlists selftests are hardware centric and so want to use the gt
as its target.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016120249.22714-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/selftest_lrc.c | 290 ++++++++++++++++-----------------
 1 file changed, 143 insertions(+), 147 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 9c1f34fb5882..2868371c609e 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -51,20 +51,20 @@ static struct i915_vma *create_scratch(struct intel_gt *gt)
 
 static int live_sanitycheck(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct i915_gem_engines_iter it;
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
 	struct igt_spinner spin;
 	int err = -ENOMEM;
 
-	if (!HAS_LOGICAL_RING_CONTEXTS(i915))
+	if (!HAS_LOGICAL_RING_CONTEXTS(gt->i915))
 		return 0;
 
-	if (igt_spinner_init(&spin, &i915->gt))
+	if (igt_spinner_init(&spin, gt))
 		return -ENOMEM;
 
-	ctx = kernel_context(i915);
+	ctx = kernel_context(gt->i915);
 	if (!ctx)
 		goto err_spin;
 
@@ -81,13 +81,13 @@ static int live_sanitycheck(void *arg)
 		if (!igt_wait_for_spinner(&spin, rq)) {
 			GEM_TRACE("spinner failed to start\n");
 			GEM_TRACE_DUMP();
-			intel_gt_set_wedged(&i915->gt);
+			intel_gt_set_wedged(gt);
 			err = -EIO;
 			goto err_ctx;
 		}
 
 		igt_spinner_end(&spin);
-		if (igt_flush_test(i915)) {
+		if (igt_flush_test(gt->i915)) {
 			err = -EIO;
 			goto err_ctx;
 		}
@@ -102,7 +102,7 @@ err_spin:
 	return err;
 }
 
-static int live_unlite_restore(struct drm_i915_private *i915, int prio)
+static int live_unlite_restore(struct intel_gt *gt, int prio)
 {
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx;
@@ -115,15 +115,15 @@ static int live_unlite_restore(struct drm_i915_private *i915, int prio)
 	 * on the same engine from the same parent context.
 	 */
 
-	if (igt_spinner_init(&spin, &i915->gt))
+	if (igt_spinner_init(&spin, gt))
 		return err;
 
-	ctx = kernel_context(i915);
+	ctx = kernel_context(gt->i915);
 	if (!ctx)
 		goto err_spin;
 
 	err = 0;
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		struct intel_context *ce[2] = {};
 		struct i915_request *rq[2];
 		struct igt_live_test t;
@@ -135,7 +135,7 @@ static int live_unlite_restore(struct drm_i915_private *i915, int prio)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		if (igt_live_test_begin(&t, i915, __func__, engine->name)) {
+		if (igt_live_test_begin(&t, gt->i915, __func__, engine->name)) {
 			err = -EIO;
 			break;
 		}
@@ -416,7 +416,7 @@ out:
 
 static int live_timeslice_preempt(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 	void *vaddr;
@@ -432,11 +432,11 @@ static int live_timeslice_preempt(void *arg)
 	 * ready task.
 	 */
 
-	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
-	vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
+	vma = i915_vma_instance(obj, &gt->ggtt->vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err_obj;
@@ -456,7 +456,7 @@ static int live_timeslice_preempt(void *arg)
 		struct intel_engine_cs *engine;
 		enum intel_engine_id id;
 
-		for_each_engine(engine, i915, id) {
+		for_each_engine(engine, gt->i915, id) {
 			if (!intel_engine_has_preemption(engine))
 				continue;
 
@@ -466,7 +466,7 @@ static int live_timeslice_preempt(void *arg)
 			if (err)
 				goto err_pin;
 
-			if (igt_flush_test(i915)) {
+			if (igt_flush_test(gt->i915)) {
 				err = -EIO;
 				goto err_pin;
 			}
@@ -484,7 +484,7 @@ err_obj:
 
 static int live_busywait_preempt(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct i915_gem_context *ctx_hi, *ctx_lo;
 	struct intel_engine_cs *engine;
 	struct drm_i915_gem_object *obj;
@@ -498,19 +498,19 @@ static int live_busywait_preempt(void *arg)
 	 * preempt the busywaits used to synchronise between rings.
 	 */
 
-	ctx_hi = kernel_context(i915);
+	ctx_hi = kernel_context(gt->i915);
 	if (!ctx_hi)
 		return -ENOMEM;
 	ctx_hi->sched.priority =
 		I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
 
-	ctx_lo = kernel_context(i915);
+	ctx_lo = kernel_context(gt->i915);
 	if (!ctx_lo)
 		goto err_ctx_hi;
 	ctx_lo->sched.priority =
 		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
 
-	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
 		goto err_ctx_lo;
@@ -522,7 +522,7 @@ static int live_busywait_preempt(void *arg)
 		goto err_obj;
 	}
 
-	vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
+	vma = i915_vma_instance(obj, &gt->ggtt->vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err_map;
@@ -532,7 +532,7 @@ static int live_busywait_preempt(void *arg)
 	if (err)
 		goto err_map;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		struct i915_request *lo, *hi;
 		struct igt_live_test t;
 		u32 *cs;
@@ -543,7 +543,7 @@ static int live_busywait_preempt(void *arg)
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
-		if (igt_live_test_begin(&t, i915, __func__, engine->name)) {
+		if (igt_live_test_begin(&t, gt->i915, __func__, engine->name)) {
 			err = -EIO;
 			goto err_vma;
 		}
@@ -623,7 +623,7 @@ static int live_busywait_preempt(void *arg)
 		i915_request_add(hi);
 
 		if (i915_request_wait(lo, 0, HZ / 5) < 0) {
-			struct drm_printer p = drm_info_printer(i915->drm.dev);
+			struct drm_printer p = drm_info_printer(gt->i915->drm.dev);
 
 			pr_err("%s: Failed to preempt semaphore busywait!\n",
 			       engine->name);
@@ -631,7 +631,7 @@ static int live_busywait_preempt(void *arg)
 			intel_engine_dump(engine, &p, "%s\n", engine->name);
 			GEM_TRACE_DUMP();
 
-			intel_gt_set_wedged(&i915->gt);
+			intel_gt_set_wedged(gt);
 			err = -EIO;
 			goto err_vma;
 		}
@@ -677,45 +677,45 @@ spinner_create_request(struct igt_spinner *spin,
 
 static int live_preempt(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct i915_gem_context *ctx_hi, *ctx_lo;
 	struct igt_spinner spin_hi, spin_lo;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	int err = -ENOMEM;
 
-	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+	if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
 		return 0;
 
-	if (!(i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
+	if (!(gt->i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
 		pr_err("Logical preemption supported, but not exposed\n");
 
-	if (igt_spinner_init(&spin_hi, &i915->gt))
+	if (igt_spinner_init(&spin_hi, gt))
 		return -ENOMEM;
 
-	if (igt_spinner_init(&spin_lo, &i915->gt))
+	if (igt_spinner_init(&spin_lo, gt))
 		goto err_spin_hi;
 
-	ctx_hi = kernel_context(i915);
+	ctx_hi = kernel_context(gt->i915);
 	if (!ctx_hi)
 		goto err_spin_lo;
 	ctx_hi->sched.priority =
 		I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
 
-	ctx_lo = kernel_context(i915);
+	ctx_lo = kernel_context(gt->i915);
 	if (!ctx_lo)
 		goto err_ctx_hi;
 	ctx_lo->sched.priority =
 		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		struct igt_live_test t;
 		struct i915_request *rq;
 
 		if (!intel_engine_has_preemption(engine))
 			continue;
 
-		if (igt_live_test_begin(&t, i915, __func__, engine->name)) {
+		if (igt_live_test_begin(&t, gt->i915, __func__, engine->name)) {
 			err = -EIO;
 			goto err_ctx_lo;
 		}
@@ -731,7 +731,7 @@ static int live_preempt(void *arg)
 		if (!igt_wait_for_spinner(&spin_lo, rq)) {
 			GEM_TRACE("lo spinner failed to start\n");
 			GEM_TRACE_DUMP();
-			intel_gt_set_wedged(&i915->gt);
+			intel_gt_set_wedged(gt);
 			err = -EIO;
 			goto err_ctx_lo;
 		}
@@ -748,7 +748,7 @@ static int live_preempt(void *arg)
 		if (!igt_wait_for_spinner(&spin_hi, rq)) {
 			GEM_TRACE("hi spinner failed to start\n");
 			GEM_TRACE_DUMP();
-			intel_gt_set_wedged(&i915->gt);
+			intel_gt_set_wedged(gt);
 			err = -EIO;
 			goto err_ctx_lo;
 		}
@@ -776,7 +776,7 @@ err_spin_hi:
 
 static int live_late_preempt(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct i915_gem_context *ctx_hi, *ctx_lo;
 	struct igt_spinner spin_hi, spin_lo;
 	struct intel_engine_cs *engine;
@@ -784,34 +784,34 @@ static int live_late_preempt(void *arg)
 	enum intel_engine_id id;
 	int err = -ENOMEM;
 
-	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+	if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
 		return 0;
 
-	if (igt_spinner_init(&spin_hi, &i915->gt))
+	if (igt_spinner_init(&spin_hi, gt))
 		return -ENOMEM;
 
-	if (igt_spinner_init(&spin_lo, &i915->gt))
+	if (igt_spinner_init(&spin_lo, gt))
 		goto err_spin_hi;
 
-	ctx_hi = kernel_context(i915);
+	ctx_hi = kernel_context(gt->i915);
 	if (!ctx_hi)
 		goto err_spin_lo;
 
-	ctx_lo = kernel_context(i915);
+	ctx_lo = kernel_context(gt->i915);
 	if (!ctx_lo)
 		goto err_ctx_hi;
 
 	/* Make sure ctx_lo stays before ctx_hi until we trigger preemption. */
 	ctx_lo->sched.priority = I915_USER_PRIORITY(1);
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		struct igt_live_test t;
 		struct i915_request *rq;
 
 		if (!intel_engine_has_preemption(engine))
 			continue;
 
-		if (igt_live_test_begin(&t, i915, __func__, engine->name)) {
+		if (igt_live_test_begin(&t, gt->i915, __func__, engine->name)) {
 			err = -EIO;
 			goto err_ctx_lo;
 		}
@@ -875,7 +875,7 @@ err_spin_hi:
 err_wedged:
 	igt_spinner_end(&spin_hi);
 	igt_spinner_end(&spin_lo);
-	intel_gt_set_wedged(&i915->gt);
+	intel_gt_set_wedged(gt);
 	err = -EIO;
 	goto err_ctx_lo;
 }
@@ -885,14 +885,13 @@ struct preempt_client {
 	struct i915_gem_context *ctx;
 };
 
-static int preempt_client_init(struct drm_i915_private *i915,
-			       struct preempt_client *c)
+static int preempt_client_init(struct intel_gt *gt, struct preempt_client *c)
 {
-	c->ctx = kernel_context(i915);
+	c->ctx = kernel_context(gt->i915);
 	if (!c->ctx)
 		return -ENOMEM;
 
-	if (igt_spinner_init(&c->spin, &i915->gt))
+	if (igt_spinner_init(&c->spin, gt))
 		goto err_ctx;
 
 	return 0;
@@ -910,7 +909,7 @@ static void preempt_client_fini(struct preempt_client *c)
 
 static int live_nopreempt(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
 	struct preempt_client a, b;
 	enum intel_engine_id id;
@@ -921,16 +920,16 @@ static int live_nopreempt(void *arg)
 	 * that may be being observed and not want to be interrupted.
 	 */
 
-	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+	if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
 		return 0;
 
-	if (preempt_client_init(i915, &a))
+	if (preempt_client_init(gt, &a))
 		return -ENOMEM;
-	if (preempt_client_init(i915, &b))
+	if (preempt_client_init(gt, &b))
 		goto err_client_a;
 	b.ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX);
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		struct i915_request *rq_a, *rq_b;
 
 		if (!intel_engine_has_preemption(engine))
@@ -990,7 +989,7 @@ static int live_nopreempt(void *arg)
 			goto err_wedged;
 		}
 
-		if (igt_flush_test(i915))
+		if (igt_flush_test(gt->i915))
 			goto err_wedged;
 	}
 
@@ -1004,14 +1003,14 @@ err_client_a:
 err_wedged:
 	igt_spinner_end(&b.spin);
 	igt_spinner_end(&a.spin);
-	intel_gt_set_wedged(&i915->gt);
+	intel_gt_set_wedged(gt);
 	err = -EIO;
 	goto err_client_b;
 }
 
 static int live_suppress_self_preempt(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
 	struct i915_sched_attr attr = {
 		.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX)
@@ -1027,28 +1026,28 @@ static int live_suppress_self_preempt(void *arg)
 	 * completion event.
 	 */
 
-	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+	if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
 		return 0;
 
-	if (USES_GUC_SUBMISSION(i915))
+	if (USES_GUC_SUBMISSION(gt->i915))
 		return 0; /* presume black blox */
 
-	if (intel_vgpu_active(i915))
+	if (intel_vgpu_active(gt->i915))
 		return 0; /* GVT forces single port & request submission */
 
-	if (preempt_client_init(i915, &a))
+	if (preempt_client_init(gt, &a))
 		return -ENOMEM;
-	if (preempt_client_init(i915, &b))
+	if (preempt_client_init(gt, &b))
 		goto err_client_a;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		struct i915_request *rq_a, *rq_b;
 		int depth;
 
 		if (!intel_engine_has_preemption(engine))
 			continue;
 
-		if (igt_flush_test(i915))
+		if (igt_flush_test(gt->i915))
 			goto err_wedged;
 
 		intel_engine_pm_get(engine);
@@ -1109,7 +1108,7 @@ static int live_suppress_self_preempt(void *arg)
 		}
 
 		intel_engine_pm_put(engine);
-		if (igt_flush_test(i915))
+		if (igt_flush_test(gt->i915))
 			goto err_wedged;
 	}
 
@@ -1123,7 +1122,7 @@ err_client_a:
 err_wedged:
 	igt_spinner_end(&b.spin);
 	igt_spinner_end(&a.spin);
-	intel_gt_set_wedged(&i915->gt);
+	intel_gt_set_wedged(gt);
 	err = -EIO;
 	goto err_client_b;
 }
@@ -1183,7 +1182,7 @@ static void dummy_request_free(struct i915_request *dummy)
 
 static int live_suppress_wait_preempt(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct preempt_client client[4];
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -1196,19 +1195,19 @@ static int live_suppress_wait_preempt(void *arg)
 	 * not needlessly generate preempt-to-idle cycles.
 	 */
 
-	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+	if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
 		return 0;
 
-	if (preempt_client_init(i915, &client[0])) /* ELSP[0] */
+	if (preempt_client_init(gt, &client[0])) /* ELSP[0] */
 		return -ENOMEM;
-	if (preempt_client_init(i915, &client[1])) /* ELSP[1] */
+	if (preempt_client_init(gt, &client[1])) /* ELSP[1] */
 		goto err_client_0;
-	if (preempt_client_init(i915, &client[2])) /* head of queue */
+	if (preempt_client_init(gt, &client[2])) /* head of queue */
 		goto err_client_1;
-	if (preempt_client_init(i915, &client[3])) /* bystander */
+	if (preempt_client_init(gt, &client[3])) /* bystander */
 		goto err_client_2;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		int depth;
 
 		if (!intel_engine_has_preemption(engine))
@@ -1263,7 +1262,7 @@ static int live_suppress_wait_preempt(void *arg)
 			for (i = 0; i < ARRAY_SIZE(client); i++)
 				igt_spinner_end(&client[i].spin);
 
-			if (igt_flush_test(i915))
+			if (igt_flush_test(gt->i915))
 				goto err_wedged;
 
 			if (engine->execlists.preempt_hang.count) {
@@ -1291,14 +1290,14 @@ err_client_0:
 err_wedged:
 	for (i = 0; i < ARRAY_SIZE(client); i++)
 		igt_spinner_end(&client[i].spin);
-	intel_gt_set_wedged(&i915->gt);
+	intel_gt_set_wedged(gt);
 	err = -EIO;
 	goto err_client_3;
 }
 
 static int live_chain_preempt(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
 	struct preempt_client hi, lo;
 	enum intel_engine_id id;
@@ -1310,16 +1309,16 @@ static int live_chain_preempt(void *arg)
 	 * the previously submitted spinner in B.
 	 */
 
-	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+	if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
 		return 0;
 
-	if (preempt_client_init(i915, &hi))
+	if (preempt_client_init(gt, &hi))
 		return -ENOMEM;
 
-	if (preempt_client_init(i915, &lo))
+	if (preempt_client_init(gt, &lo))
 		goto err_client_hi;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		struct i915_sched_attr attr = {
 			.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX),
 		};
@@ -1350,7 +1349,7 @@ static int live_chain_preempt(void *arg)
 			goto err_wedged;
 		}
 
-		if (igt_live_test_begin(&t, i915, __func__, engine->name)) {
+		if (igt_live_test_begin(&t, gt->i915, __func__, engine->name)) {
 			err = -EIO;
 			goto err_wedged;
 		}
@@ -1388,7 +1387,7 @@ static int live_chain_preempt(void *arg)
 			igt_spinner_end(&hi.spin);
 			if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 				struct drm_printer p =
-					drm_info_printer(i915->drm.dev);
+					drm_info_printer(gt->i915->drm.dev);
 
 				pr_err("Failed to preempt over chain of %d\n",
 				       count);
@@ -1404,7 +1403,7 @@ static int live_chain_preempt(void *arg)
 			i915_request_add(rq);
 			if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 				struct drm_printer p =
-					drm_info_printer(i915->drm.dev);
+					drm_info_printer(gt->i915->drm.dev);
 
 				pr_err("Failed to flush low priority chain of %d requests\n",
 				       count);
@@ -1430,45 +1429,45 @@ err_client_hi:
 err_wedged:
 	igt_spinner_end(&hi.spin);
 	igt_spinner_end(&lo.spin);
-	intel_gt_set_wedged(&i915->gt);
+	intel_gt_set_wedged(gt);
 	err = -EIO;
 	goto err_client_lo;
 }
 
 static int live_preempt_hang(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct i915_gem_context *ctx_hi, *ctx_lo;
 	struct igt_spinner spin_hi, spin_lo;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	int err = -ENOMEM;
 
-	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+	if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
 		return 0;
 
-	if (!intel_has_reset_engine(&i915->gt))
+	if (!intel_has_reset_engine(gt))
 		return 0;
 
-	if (igt_spinner_init(&spin_hi, &i915->gt))
+	if (igt_spinner_init(&spin_hi, gt))
 		return -ENOMEM;
 
-	if (igt_spinner_init(&spin_lo, &i915->gt))
+	if (igt_spinner_init(&spin_lo, gt))
 		goto err_spin_hi;
 
-	ctx_hi = kernel_context(i915);
+	ctx_hi = kernel_context(gt->i915);
 	if (!ctx_hi)
 		goto err_spin_lo;
 	ctx_hi->sched.priority =
 		I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
 
-	ctx_lo = kernel_context(i915);
+	ctx_lo = kernel_context(gt->i915);
 	if (!ctx_lo)
 		goto err_ctx_hi;
 	ctx_lo->sched.priority =
 		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		struct i915_request *rq;
 
 		if (!intel_engine_has_preemption(engine))
@@ -1485,7 +1484,7 @@ static int live_preempt_hang(void *arg)
 		if (!igt_wait_for_spinner(&spin_lo, rq)) {
 			GEM_TRACE("lo spinner failed to start\n");
 			GEM_TRACE_DUMP();
-			intel_gt_set_wedged(&i915->gt);
+			intel_gt_set_wedged(gt);
 			err = -EIO;
 			goto err_ctx_lo;
 		}
@@ -1507,28 +1506,28 @@ static int live_preempt_hang(void *arg)
 						 HZ / 10)) {
 			pr_err("Preemption did not occur within timeout!");
 			GEM_TRACE_DUMP();
-			intel_gt_set_wedged(&i915->gt);
+			intel_gt_set_wedged(gt);
 			err = -EIO;
 			goto err_ctx_lo;
 		}
 
-		set_bit(I915_RESET_ENGINE + id, &i915->gt.reset.flags);
+		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		intel_engine_reset(engine, NULL);
-		clear_bit(I915_RESET_ENGINE + id, &i915->gt.reset.flags);
+		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 
 		engine->execlists.preempt_hang.inject_hang = false;
 
 		if (!igt_wait_for_spinner(&spin_hi, rq)) {
 			GEM_TRACE("hi spinner failed to start\n");
 			GEM_TRACE_DUMP();
-			intel_gt_set_wedged(&i915->gt);
+			intel_gt_set_wedged(gt);
 			err = -EIO;
 			goto err_ctx_lo;
 		}
 
 		igt_spinner_end(&spin_hi);
 		igt_spinner_end(&spin_lo);
-		if (igt_flush_test(i915)) {
+		if (igt_flush_test(gt->i915)) {
 			err = -EIO;
 			goto err_ctx_lo;
 		}
@@ -1557,7 +1556,7 @@ static int random_priority(struct rnd_state *rnd)
 }
 
 struct preempt_smoke {
-	struct drm_i915_private *i915;
+	struct intel_gt *gt;
 	struct i915_gem_context **contexts;
 	struct intel_engine_cs *engine;
 	struct drm_i915_gem_object *batch;
@@ -1657,7 +1656,7 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 	unsigned long count;
 	int err = 0;
 
-	for_each_engine(engine, smoke->i915, id) {
+	for_each_engine(engine, smoke->gt->i915, id) {
 		arg[id] = *smoke;
 		arg[id].engine = engine;
 		if (!(flags & BATCH))
@@ -1674,7 +1673,7 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 	}
 
 	count = 0;
-	for_each_engine(engine, smoke->i915, id) {
+	for_each_engine(engine, smoke->gt->i915, id) {
 		int status;
 
 		if (IS_ERR_OR_NULL(tsk[id]))
@@ -1691,7 +1690,7 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 
 	pr_info("Submitted %lu crescendo:%x requests across %d engines and %d contexts\n",
 		count, flags,
-		RUNTIME_INFO(smoke->i915)->num_engines, smoke->ncontext);
+		RUNTIME_INFO(smoke->gt->i915)->num_engines, smoke->ncontext);
 	return 0;
 }
 
@@ -1703,7 +1702,7 @@ static int smoke_random(struct preempt_smoke *smoke, unsigned int flags)
 
 	count = 0;
 	do {
-		for_each_engine(smoke->engine, smoke->i915, id) {
+		for_each_engine(smoke->engine, smoke->gt->i915, id) {
 			struct i915_gem_context *ctx = smoke_context(smoke);
 			int err;
 
@@ -1719,14 +1718,14 @@ static int smoke_random(struct preempt_smoke *smoke, unsigned int flags)
 
 	pr_info("Submitted %lu random:%x requests across %d engines and %d contexts\n",
 		count, flags,
-		RUNTIME_INFO(smoke->i915)->num_engines, smoke->ncontext);
+		RUNTIME_INFO(smoke->gt->i915)->num_engines, smoke->ncontext);
 	return 0;
 }
 
 static int live_preempt_smoke(void *arg)
 {
 	struct preempt_smoke smoke = {
-		.i915 = arg,
+		.gt = arg,
 		.prng = I915_RND_STATE_INITIALIZER(i915_selftest.random_seed),
 		.ncontext = 1024,
 	};
@@ -1736,7 +1735,7 @@ static int live_preempt_smoke(void *arg)
 	u32 *cs;
 	int n;
 
-	if (!HAS_LOGICAL_RING_PREEMPTION(smoke.i915))
+	if (!HAS_LOGICAL_RING_PREEMPTION(smoke.gt->i915))
 		return 0;
 
 	smoke.contexts = kmalloc_array(smoke.ncontext,
@@ -1745,7 +1744,8 @@ static int live_preempt_smoke(void *arg)
 	if (!smoke.contexts)
 		return -ENOMEM;
 
-	smoke.batch = i915_gem_object_create_internal(smoke.i915, PAGE_SIZE);
+	smoke.batch =
+		i915_gem_object_create_internal(smoke.gt->i915, PAGE_SIZE);
 	if (IS_ERR(smoke.batch)) {
 		err = PTR_ERR(smoke.batch);
 		goto err_free;
@@ -1762,13 +1762,13 @@ static int live_preempt_smoke(void *arg)
 	i915_gem_object_flush_map(smoke.batch);
 	i915_gem_object_unpin_map(smoke.batch);
 
-	if (igt_live_test_begin(&t, smoke.i915, __func__, "all")) {
+	if (igt_live_test_begin(&t, smoke.gt->i915, __func__, "all")) {
 		err = -EIO;
 		goto err_batch;
 	}
 
 	for (n = 0; n < smoke.ncontext; n++) {
-		smoke.contexts[n] = kernel_context(smoke.i915);
+		smoke.contexts[n] = kernel_context(smoke.gt->i915);
 		if (!smoke.contexts[n])
 			goto err_ctx;
 	}
@@ -1801,7 +1801,7 @@ err_free:
 	return err;
 }
 
-static int nop_virtual_engine(struct drm_i915_private *i915,
+static int nop_virtual_engine(struct intel_gt *gt,
 			      struct intel_engine_cs **siblings,
 			      unsigned int nsibling,
 			      unsigned int nctx,
@@ -1820,7 +1820,7 @@ static int nop_virtual_engine(struct drm_i915_private *i915,
 	GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ctx));
 
 	for (n = 0; n < nctx; n++) {
-		ctx[n] = kernel_context(i915);
+		ctx[n] = kernel_context(gt->i915);
 		if (!ctx[n]) {
 			err = -ENOMEM;
 			nctx = n;
@@ -1845,7 +1845,7 @@ static int nop_virtual_engine(struct drm_i915_private *i915,
 		}
 	}
 
-	err = igt_live_test_begin(&t, i915, __func__, ve[0]->engine->name);
+	err = igt_live_test_begin(&t, gt->i915, __func__, ve[0]->engine->name);
 	if (err)
 		goto out;
 
@@ -1892,7 +1892,7 @@ static int nop_virtual_engine(struct drm_i915_private *i915,
 					  request[nc]->fence.context,
 					  request[nc]->fence.seqno);
 				GEM_TRACE_DUMP();
-				intel_gt_set_wedged(&i915->gt);
+				intel_gt_set_wedged(gt);
 				break;
 			}
 		}
@@ -1914,7 +1914,7 @@ static int nop_virtual_engine(struct drm_i915_private *i915,
 		prime, div64_u64(ktime_to_ns(times[1]), prime));
 
 out:
-	if (igt_flush_test(i915))
+	if (igt_flush_test(gt->i915))
 		err = -EIO;
 
 	for (nc = 0; nc < nctx; nc++) {
@@ -1927,19 +1927,18 @@ out:
 
 static int live_virtual_engine(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct intel_engine_cs *siblings[MAX_ENGINE_INSTANCE + 1];
 	struct intel_engine_cs *engine;
-	struct intel_gt *gt = &i915->gt;
 	enum intel_engine_id id;
 	unsigned int class, inst;
 	int err;
 
-	if (USES_GUC_SUBMISSION(i915))
+	if (USES_GUC_SUBMISSION(gt->i915))
 		return 0;
 
-	for_each_engine(engine, i915, id) {
-		err = nop_virtual_engine(i915, &engine, 1, 1, 0);
+	for_each_engine(engine, gt->i915, id) {
+		err = nop_virtual_engine(gt, &engine, 1, 1, 0);
 		if (err) {
 			pr_err("Failed to wrap engine %s: err=%d\n",
 			       engine->name, err);
@@ -1961,13 +1960,13 @@ static int live_virtual_engine(void *arg)
 			continue;
 
 		for (n = 1; n <= nsibling + 1; n++) {
-			err = nop_virtual_engine(i915, siblings, nsibling,
+			err = nop_virtual_engine(gt, siblings, nsibling,
 						 n, 0);
 			if (err)
 				return err;
 		}
 
-		err = nop_virtual_engine(i915, siblings, nsibling, n, CHAIN);
+		err = nop_virtual_engine(gt, siblings, nsibling, n, CHAIN);
 		if (err)
 			return err;
 	}
@@ -1975,7 +1974,7 @@ static int live_virtual_engine(void *arg)
 	return 0;
 }
 
-static int mask_virtual_engine(struct drm_i915_private *i915,
+static int mask_virtual_engine(struct intel_gt *gt,
 			       struct intel_engine_cs **siblings,
 			       unsigned int nsibling)
 {
@@ -1991,7 +1990,7 @@ static int mask_virtual_engine(struct drm_i915_private *i915,
 	 * restrict it to our desired engine within the virtual engine.
 	 */
 
-	ctx = kernel_context(i915);
+	ctx = kernel_context(gt->i915);
 	if (!ctx)
 		return -ENOMEM;
 
@@ -2005,7 +2004,7 @@ static int mask_virtual_engine(struct drm_i915_private *i915,
 	if (err)
 		goto out_put;
 
-	err = igt_live_test_begin(&t, i915, __func__, ve->engine->name);
+	err = igt_live_test_begin(&t, gt->i915, __func__, ve->engine->name);
 	if (err)
 		goto out_unpin;
 
@@ -2036,7 +2035,7 @@ static int mask_virtual_engine(struct drm_i915_private *i915,
 				  request[n]->fence.context,
 				  request[n]->fence.seqno);
 			GEM_TRACE_DUMP();
-			intel_gt_set_wedged(&i915->gt);
+			intel_gt_set_wedged(gt);
 			err = -EIO;
 			goto out;
 		}
@@ -2052,7 +2051,7 @@ static int mask_virtual_engine(struct drm_i915_private *i915,
 
 	err = igt_live_test_end(&t);
 out:
-	if (igt_flush_test(i915))
+	if (igt_flush_test(gt->i915))
 		err = -EIO;
 
 	for (n = 0; n < nsibling; n++)
@@ -2069,13 +2068,12 @@ out_close:
 
 static int live_virtual_mask(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct intel_engine_cs *siblings[MAX_ENGINE_INSTANCE + 1];
-	struct intel_gt *gt = &i915->gt;
 	unsigned int class, inst;
 	int err;
 
-	if (USES_GUC_SUBMISSION(i915))
+	if (USES_GUC_SUBMISSION(gt->i915))
 		return 0;
 
 	for (class = 0; class <= MAX_ENGINE_CLASS; class++) {
@@ -2091,7 +2089,7 @@ static int live_virtual_mask(void *arg)
 		if (nsibling < 2)
 			continue;
 
-		err = mask_virtual_engine(i915, siblings, nsibling);
+		err = mask_virtual_engine(gt, siblings, nsibling);
 		if (err)
 			return err;
 	}
@@ -2099,7 +2097,7 @@ static int live_virtual_mask(void *arg)
 	return 0;
 }
 
-static int preserved_virtual_engine(struct drm_i915_private *i915,
+static int preserved_virtual_engine(struct intel_gt *gt,
 				    struct intel_engine_cs **siblings,
 				    unsigned int nsibling)
 {
@@ -2112,7 +2110,7 @@ static int preserved_virtual_engine(struct drm_i915_private *i915,
 	int err = 0;
 	u32 *cs;
 
-	ctx = kernel_context(i915);
+	ctx = kernel_context(gt->i915);
 	if (!ctx)
 		return -ENOMEM;
 
@@ -2132,7 +2130,7 @@ static int preserved_virtual_engine(struct drm_i915_private *i915,
 	if (err)
 		goto out_put;
 
-	err = igt_live_test_begin(&t, i915, __func__, ve->engine->name);
+	err = igt_live_test_begin(&t, gt->i915, __func__, ve->engine->name);
 	if (err)
 		goto out_unpin;
 
@@ -2212,9 +2210,8 @@ out_close:
 
 static int live_virtual_preserved(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct intel_engine_cs *siblings[MAX_ENGINE_INSTANCE + 1];
-	struct intel_gt *gt = &i915->gt;
 	unsigned int class, inst;
 
 	/*
@@ -2223,11 +2220,11 @@ static int live_virtual_preserved(void *arg)
 	 * are preserved.
 	 */
 
-	if (USES_GUC_SUBMISSION(i915))
+	if (USES_GUC_SUBMISSION(gt->i915))
 		return 0;
 
 	/* As we use CS_GPR we cannot run before they existed on all engines. */
-	if (INTEL_GEN(i915) < 9)
+	if (INTEL_GEN(gt->i915) < 9)
 		return 0;
 
 	for (class = 0; class <= MAX_ENGINE_CLASS; class++) {
@@ -2243,7 +2240,7 @@ static int live_virtual_preserved(void *arg)
 		if (nsibling < 2)
 			continue;
 
-		err = preserved_virtual_engine(i915, siblings, nsibling);
+		err = preserved_virtual_engine(gt, siblings, nsibling);
 		if (err)
 			return err;
 	}
@@ -2251,7 +2248,7 @@ static int live_virtual_preserved(void *arg)
 	return 0;
 }
 
-static int bond_virtual_engine(struct drm_i915_private *i915,
+static int bond_virtual_engine(struct intel_gt *gt,
 			       unsigned int class,
 			       struct intel_engine_cs **siblings,
 			       unsigned int nsibling,
@@ -2267,13 +2264,13 @@ static int bond_virtual_engine(struct drm_i915_private *i915,
 
 	GEM_BUG_ON(nsibling >= ARRAY_SIZE(rq) - 1);
 
-	ctx = kernel_context(i915);
+	ctx = kernel_context(gt->i915);
 	if (!ctx)
 		return -ENOMEM;
 
 	err = 0;
 	rq[0] = ERR_PTR(-ENOMEM);
-	for_each_engine(master, i915, id) {
+	for_each_engine(master, gt->i915, id) {
 		struct i915_sw_fence fence = {};
 
 		if (master->class == class)
@@ -2378,7 +2375,7 @@ static int bond_virtual_engine(struct drm_i915_private *i915,
 out:
 	for (n = 0; !IS_ERR(rq[n]); n++)
 		i915_request_put(rq[n]);
-	if (igt_flush_test(i915))
+	if (igt_flush_test(gt->i915))
 		err = -EIO;
 
 	kernel_context_close(ctx);
@@ -2395,13 +2392,12 @@ static int live_virtual_bond(void *arg)
 		{ "schedule", BOND_SCHEDULE },
 		{ },
 	};
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct intel_engine_cs *siblings[MAX_ENGINE_INSTANCE + 1];
-	struct intel_gt *gt = &i915->gt;
 	unsigned int class, inst;
 	int err;
 
-	if (USES_GUC_SUBMISSION(i915))
+	if (USES_GUC_SUBMISSION(gt->i915))
 		return 0;
 
 	for (class = 0; class <= MAX_ENGINE_CLASS; class++) {
@@ -2420,7 +2416,7 @@ static int live_virtual_bond(void *arg)
 			continue;
 
 		for (p = phases; p->name; p++) {
-			err = bond_virtual_engine(i915,
+			err = bond_virtual_engine(gt,
 						  class, siblings, nsibling,
 						  p->flags);
 			if (err) {
@@ -2462,7 +2458,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
-	return i915_live_subtests(tests, i915);
+	return intel_gt_live_subtests(tests, &i915->gt);
 }
 
 static void hexdump(const void *buf, size_t len)
-- 
cgit v1.2.3


From 3b05c4f832fa9beeb8da4bafb3c2d115b77a8d5b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 Oct 2019 12:53:11 +0100
Subject: drm/i915/selftests: Teach guc to take intel_gt as its argument

The guc selftests are hardware^W firmare centric and so want to use the
gt as its target.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016115311.12894-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/uc/selftest_guc.c | 42 +++++++++++--------------------
 1 file changed, 14 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
index f927f851aadf..d8a80388bd31 100644
--- a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c
@@ -108,22 +108,15 @@ static bool client_doorbell_in_sync(struct intel_guc_client *client)
  * validating that the doorbells status expected by the driver matches what the
  * GuC/HW have.
  */
-static int igt_guc_clients(void *args)
+static int igt_guc_clients(void *arg)
 {
-	struct drm_i915_private *dev_priv = args;
+	struct intel_gt *gt = arg;
+	struct intel_guc *guc = &gt->uc.guc;
 	intel_wakeref_t wakeref;
-	struct intel_guc *guc;
 	int err = 0;
 
-	GEM_BUG_ON(!HAS_GT_UC(dev_priv));
-	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
-
-	guc = &dev_priv->gt.uc.guc;
-	if (!guc) {
-		pr_err("No guc object!\n");
-		err = -EINVAL;
-		goto unlock;
-	}
+	GEM_BUG_ON(!HAS_GT_UC(gt->i915));
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 
 	err = check_all_doorbells(guc);
 	if (err)
@@ -188,7 +181,7 @@ out:
 	guc_clients_create(guc);
 	guc_clients_enable(guc);
 unlock:
-	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 	return err;
 }
 
@@ -199,21 +192,14 @@ unlock:
  */
 static int igt_guc_doorbells(void *arg)
 {
-	struct drm_i915_private *dev_priv = arg;
+	struct intel_gt *gt = arg;
+	struct intel_guc *guc = &gt->uc.guc;
 	intel_wakeref_t wakeref;
-	struct intel_guc *guc;
 	int i, err = 0;
 	u16 db_id;
 
-	GEM_BUG_ON(!HAS_GT_UC(dev_priv));
-	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
-
-	guc = &dev_priv->gt.uc.guc;
-	if (!guc) {
-		pr_err("No guc object!\n");
-		err = -EINVAL;
-		goto unlock;
-	}
+	GEM_BUG_ON(!HAS_GT_UC(gt->i915));
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 
 	err = check_all_doorbells(guc);
 	if (err)
@@ -295,19 +281,19 @@ out:
 			guc_client_free(clients[i]);
 		}
 unlock:
-	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 	return err;
 }
 
-int intel_guc_live_selftest(struct drm_i915_private *dev_priv)
+int intel_guc_live_selftest(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_guc_clients),
 		SUBTEST(igt_guc_doorbells),
 	};
 
-	if (!USES_GUC_SUBMISSION(dev_priv))
+	if (!USES_GUC_SUBMISSION(i915))
 		return 0;
 
-	return i915_subtests(tests, dev_priv);
+	return intel_gt_live_subtests(tests, &i915->gt);
 }
-- 
cgit v1.2.3


From bb3d4c9d636b3304da95facd172323f9e86e1262 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 Oct 2019 12:49:02 +0100
Subject: drm/i915/selftests: Teach workarounds to take intel_gt as its
 argument

The workarounds selftests are hardware centric and so want to use the gt
as its target.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016114902.24388-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/selftest_workarounds.c | 128 +++++++++++++------------
 1 file changed, 65 insertions(+), 63 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index dc11f7ad50a2..8856c6c46cc4 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -58,7 +58,7 @@ static int request_add_spin(struct i915_request *rq, struct igt_spinner *spin)
 }
 
 static void
-reference_lists_init(struct drm_i915_private *i915, struct wa_lists *lists)
+reference_lists_init(struct intel_gt *gt, struct wa_lists *lists)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -66,10 +66,10 @@ reference_lists_init(struct drm_i915_private *i915, struct wa_lists *lists)
 	memset(lists, 0, sizeof(*lists));
 
 	wa_init_start(&lists->gt_wa_list, "GT_REF", "global");
-	gt_init_workarounds(i915, &lists->gt_wa_list);
+	gt_init_workarounds(gt->i915, &lists->gt_wa_list);
 	wa_init_finish(&lists->gt_wa_list);
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		struct i915_wa_list *wal = &lists->engine[id].wa_list;
 
 		wa_init_start(wal, "REF", engine->name);
@@ -83,12 +83,12 @@ reference_lists_init(struct drm_i915_private *i915, struct wa_lists *lists)
 }
 
 static void
-reference_lists_fini(struct drm_i915_private *i915, struct wa_lists *lists)
+reference_lists_fini(struct intel_gt *gt, struct wa_lists *lists)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, i915, id)
+	for_each_engine(engine, gt->i915, id)
 		intel_wa_list_free(&lists->engine[id].wa_list);
 
 	intel_wa_list_free(&lists->gt_wa_list);
@@ -215,10 +215,10 @@ static int check_whitelist(struct i915_gem_context *ctx,
 
 	err = 0;
 	i915_gem_object_lock(results);
-	intel_wedge_on_timeout(&wedge, &ctx->i915->gt, HZ / 5) /* safety net! */
+	intel_wedge_on_timeout(&wedge, engine->gt, HZ / 5) /* safety net! */
 		err = i915_gem_object_set_to_cpu_domain(results, false);
 	i915_gem_object_unlock(results);
-	if (intel_gt_is_wedged(&ctx->i915->gt))
+	if (intel_gt_is_wedged(engine->gt))
 		err = -EIO;
 	if (err)
 		goto out_put;
@@ -605,7 +605,7 @@ err_request:
 		if (err) {
 			pr_err("%s: Futzing %x timedout; cancelling test\n",
 			       engine->name, reg);
-			intel_gt_set_wedged(&ctx->i915->gt);
+			intel_gt_set_wedged(engine->gt);
 			goto out_batch;
 		}
 
@@ -704,7 +704,7 @@ out_scratch:
 
 static int live_dirty_whitelist(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx;
 	enum intel_engine_id id;
@@ -713,20 +713,20 @@ static int live_dirty_whitelist(void *arg)
 
 	/* Can the user write to the whitelisted registers? */
 
-	if (INTEL_GEN(i915) < 7) /* minimum requirement for LRI, SRM, LRM */
+	if (INTEL_GEN(gt->i915) < 7) /* minimum requirement for LRI, SRM, LRM */
 		return 0;
 
-	file = mock_file(i915);
+	file = mock_file(gt->i915);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ctx = live_context(i915, file);
+	ctx = live_context(gt->i915, file);
 	if (IS_ERR(ctx)) {
 		err = PTR_ERR(ctx);
 		goto out_file;
 	}
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		if (engine->whitelist.count == 0)
 			continue;
 
@@ -736,41 +736,43 @@ static int live_dirty_whitelist(void *arg)
 	}
 
 out_file:
-	mock_file_free(i915, file);
+	mock_file_free(gt->i915, file);
 	return err;
 }
 
 static int live_reset_whitelist(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
-	struct intel_engine_cs *engine = i915->engine[RCS0];
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int err = 0;
 
 	/* If we reset the gpu, we should not lose the RING_NONPRIV */
+	igt_global_reset_lock(gt);
 
-	if (!engine || engine->whitelist.count == 0)
-		return 0;
-
-	igt_global_reset_lock(&i915->gt);
+	for_each_engine(engine, gt->i915, id) {
+		if (engine->whitelist.count == 0)
+			continue;
 
-	if (intel_has_reset_engine(&i915->gt)) {
-		err = check_whitelist_across_reset(engine,
-						   do_engine_reset,
-						   "engine");
-		if (err)
-			goto out;
-	}
+		if (intel_has_reset_engine(gt)) {
+			err = check_whitelist_across_reset(engine,
+							   do_engine_reset,
+							   "engine");
+			if (err)
+				goto out;
+		}
 
-	if (intel_has_gpu_reset(&i915->gt)) {
-		err = check_whitelist_across_reset(engine,
-						   do_device_reset,
-						   "device");
-		if (err)
-			goto out;
+		if (intel_has_gpu_reset(gt)) {
+			err = check_whitelist_across_reset(engine,
+							   do_device_reset,
+							   "device");
+			if (err)
+				goto out;
+		}
 	}
 
 out:
-	igt_global_reset_unlock(&i915->gt);
+	igt_global_reset_unlock(gt);
 	return err;
 }
 
@@ -996,7 +998,7 @@ err_a:
 
 static int live_isolated_whitelist(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct {
 		struct i915_gem_context *ctx;
 		struct i915_vma *scratch[2];
@@ -1010,17 +1012,14 @@ static int live_isolated_whitelist(void *arg)
 	 * invisible to a second context.
 	 */
 
-	if (!intel_engines_has_context_isolation(i915))
-		return 0;
-
-	if (!i915->kernel_context->vm)
+	if (!intel_engines_has_context_isolation(gt->i915))
 		return 0;
 
 	for (i = 0; i < ARRAY_SIZE(client); i++) {
 		struct i915_address_space *vm;
 		struct i915_gem_context *c;
 
-		c = kernel_context(i915);
+		c = kernel_context(gt->i915);
 		if (IS_ERR(c)) {
 			err = PTR_ERR(c);
 			goto err;
@@ -1049,7 +1048,10 @@ static int live_isolated_whitelist(void *arg)
 		i915_vm_put(vm);
 	}
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
+		if (!engine->kernel_context->vm)
+			continue;
+
 		if (!whitelist_writable_count(engine))
 			continue;
 
@@ -1103,7 +1105,7 @@ err:
 		kernel_context_close(client[i].ctx);
 	}
 
-	if (igt_flush_test(i915))
+	if (igt_flush_test(gt->i915))
 		err = -EIO;
 
 	return err;
@@ -1138,16 +1140,16 @@ verify_wa_lists(struct i915_gem_context *ctx, struct wa_lists *lists,
 static int
 live_gpu_reset_workarounds(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct i915_gem_context *ctx;
 	intel_wakeref_t wakeref;
 	struct wa_lists lists;
 	bool ok;
 
-	if (!intel_has_gpu_reset(&i915->gt))
+	if (!intel_has_gpu_reset(gt))
 		return 0;
 
-	ctx = kernel_context(i915);
+	ctx = kernel_context(gt->i915);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
@@ -1155,25 +1157,25 @@ live_gpu_reset_workarounds(void *arg)
 
 	pr_info("Verifying after GPU reset...\n");
 
-	igt_global_reset_lock(&i915->gt);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
+	igt_global_reset_lock(gt);
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 
-	reference_lists_init(i915, &lists);
+	reference_lists_init(gt, &lists);
 
 	ok = verify_wa_lists(ctx, &lists, "before reset");
 	if (!ok)
 		goto out;
 
-	intel_gt_reset(&i915->gt, ALL_ENGINES, "live_workarounds");
+	intel_gt_reset(gt, ALL_ENGINES, "live_workarounds");
 
 	ok = verify_wa_lists(ctx, &lists, "after reset");
 
 out:
 	i915_gem_context_unlock_engines(ctx);
 	kernel_context_close(ctx);
-	reference_lists_fini(i915, &lists);
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	igt_global_reset_unlock(&i915->gt);
+	reference_lists_fini(gt, &lists);
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
+	igt_global_reset_unlock(gt);
 
 	return ok ? 0 : -ESRCH;
 }
@@ -1181,7 +1183,7 @@ out:
 static int
 live_engine_reset_workarounds(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct i915_gem_engines_iter it;
 	struct i915_gem_context *ctx;
 	struct intel_context *ce;
@@ -1191,17 +1193,17 @@ live_engine_reset_workarounds(void *arg)
 	struct wa_lists lists;
 	int ret = 0;
 
-	if (!intel_has_reset_engine(&i915->gt))
+	if (!intel_has_reset_engine(gt))
 		return 0;
 
-	ctx = kernel_context(i915);
+	ctx = kernel_context(gt->i915);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	igt_global_reset_lock(&i915->gt);
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
+	igt_global_reset_lock(gt);
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
 
-	reference_lists_init(i915, &lists);
+	reference_lists_init(gt, &lists);
 
 	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
 		struct intel_engine_cs *engine = ce->engine;
@@ -1254,12 +1256,12 @@ live_engine_reset_workarounds(void *arg)
 	}
 err:
 	i915_gem_context_unlock_engines(ctx);
-	reference_lists_fini(i915, &lists);
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-	igt_global_reset_unlock(&i915->gt);
+	reference_lists_fini(gt, &lists);
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
+	igt_global_reset_unlock(gt);
 	kernel_context_close(ctx);
 
-	igt_flush_test(i915);
+	igt_flush_test(gt->i915);
 
 	return ret;
 }
@@ -1277,5 +1279,5 @@ int intel_workarounds_live_selftests(struct drm_i915_private *i915)
 	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
-	return i915_subtests(tests, i915);
+	return intel_gt_live_subtests(tests, &i915->gt);
 }
-- 
cgit v1.2.3


From 5f65d5a6e4bddd8212a101fd566e1554cfd5e355 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 Oct 2019 12:38:40 +0100
Subject: drm/i915/selftests: Teach timelines to take intel_gt as its argument

The timelines selftests are [mostly] hardware centric and so want to use
the gt as its target.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016113840.1106-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/selftest_timeline.c | 48 +++++++++++++++--------------
 1 file changed, 25 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index d6df40cdc8a6..473a56b0ae46 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -35,7 +35,7 @@ static unsigned long hwsp_cacheline(struct intel_timeline *tl)
 #define CACHELINES_PER_PAGE (PAGE_SIZE / CACHELINE_BYTES)
 
 struct mock_hwsp_freelist {
-	struct drm_i915_private *i915;
+	struct intel_gt *gt;
 	struct radix_tree_root cachelines;
 	struct intel_timeline **history;
 	unsigned long count, max;
@@ -68,7 +68,7 @@ static int __mock_hwsp_timeline(struct mock_hwsp_freelist *state,
 		unsigned long cacheline;
 		int err;
 
-		tl = intel_timeline_create(&state->i915->gt, NULL);
+		tl = intel_timeline_create(state->gt, NULL);
 		if (IS_ERR(tl))
 			return PTR_ERR(tl);
 
@@ -106,6 +106,7 @@ static int __mock_hwsp_timeline(struct mock_hwsp_freelist *state,
 static int mock_hwsp_freelist(void *arg)
 {
 	struct mock_hwsp_freelist state;
+	struct drm_i915_private *i915;
 	const struct {
 		const char *name;
 		unsigned int flags;
@@ -117,12 +118,14 @@ static int mock_hwsp_freelist(void *arg)
 	unsigned int na;
 	int err = 0;
 
+	i915 = mock_gem_device();
+	if (!i915)
+		return -ENOMEM;
+
 	INIT_RADIX_TREE(&state.cachelines, GFP_KERNEL);
 	state.prng = I915_RND_STATE_INITIALIZER(i915_selftest.random_seed);
 
-	state.i915 = mock_gem_device();
-	if (!state.i915)
-		return -ENOMEM;
+	state.gt = &i915->gt;
 
 	/*
 	 * Create a bunch of timelines and check that their HWSP do not overlap.
@@ -151,7 +154,7 @@ out:
 		__mock_hwsp_record(&state, na, NULL);
 	kfree(state.history);
 err_put:
-	drm_dev_put(&state.i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
@@ -476,11 +479,11 @@ out:
 }
 
 static struct intel_timeline *
-checked_intel_timeline_create(struct drm_i915_private *i915)
+checked_intel_timeline_create(struct intel_gt *gt)
 {
 	struct intel_timeline *tl;
 
-	tl = intel_timeline_create(&i915->gt, NULL);
+	tl = intel_timeline_create(gt, NULL);
 	if (IS_ERR(tl))
 		return tl;
 
@@ -497,7 +500,7 @@ checked_intel_timeline_create(struct drm_i915_private *i915)
 static int live_hwsp_engine(void *arg)
 {
 #define NUM_TIMELINES 4096
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct intel_timeline **timelines;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -516,7 +519,7 @@ static int live_hwsp_engine(void *arg)
 		return -ENOMEM;
 
 	count = 0;
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
@@ -526,7 +529,7 @@ static int live_hwsp_engine(void *arg)
 			struct intel_timeline *tl;
 			struct i915_request *rq;
 
-			tl = checked_intel_timeline_create(i915);
+			tl = checked_intel_timeline_create(gt);
 			if (IS_ERR(tl)) {
 				err = PTR_ERR(tl);
 				break;
@@ -548,7 +551,7 @@ static int live_hwsp_engine(void *arg)
 			break;
 	}
 
-	if (igt_flush_test(i915))
+	if (igt_flush_test(gt->i915))
 		err = -EIO;
 
 	for (n = 0; n < count; n++) {
@@ -570,7 +573,7 @@ static int live_hwsp_engine(void *arg)
 static int live_hwsp_alternate(void *arg)
 {
 #define NUM_TIMELINES 4096
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct intel_timeline **timelines;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -591,14 +594,14 @@ static int live_hwsp_alternate(void *arg)
 
 	count = 0;
 	for (n = 0; n < NUM_TIMELINES; n++) {
-		for_each_engine(engine, i915, id) {
+		for_each_engine(engine, gt->i915, id) {
 			struct intel_timeline *tl;
 			struct i915_request *rq;
 
 			if (!intel_engine_can_store_dword(engine))
 				continue;
 
-			tl = checked_intel_timeline_create(i915);
+			tl = checked_intel_timeline_create(gt);
 			if (IS_ERR(tl)) {
 				intel_engine_pm_put(engine);
 				err = PTR_ERR(tl);
@@ -620,7 +623,7 @@ static int live_hwsp_alternate(void *arg)
 	}
 
 out:
-	if (igt_flush_test(i915))
+	if (igt_flush_test(gt->i915))
 		err = -EIO;
 
 	for (n = 0; n < count; n++) {
@@ -641,8 +644,7 @@ out:
 
 static int live_hwsp_wrap(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
-	struct intel_gt *gt = &i915->gt;
+	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
 	struct intel_timeline *tl;
 	enum intel_engine_id id;
@@ -740,7 +742,7 @@ static int live_hwsp_wrap(void *arg)
 	}
 
 out:
-	if (igt_flush_test(i915))
+	if (igt_flush_test(gt->i915))
 		err = -EIO;
 
 	intel_timeline_unpin(tl);
@@ -751,7 +753,7 @@ out_free:
 
 static int live_hwsp_recycle(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	unsigned long count;
@@ -764,7 +766,7 @@ static int live_hwsp_recycle(void *arg)
 	 */
 
 	count = 0;
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt->i915, id) {
 		IGT_TIMEOUT(end_time);
 
 		if (!intel_engine_can_store_dword(engine))
@@ -776,7 +778,7 @@ static int live_hwsp_recycle(void *arg)
 			struct intel_timeline *tl;
 			struct i915_request *rq;
 
-			tl = checked_intel_timeline_create(i915);
+			tl = checked_intel_timeline_create(gt);
 			if (IS_ERR(tl)) {
 				err = PTR_ERR(tl);
 				break;
@@ -831,5 +833,5 @@ int intel_timeline_live_selftests(struct drm_i915_private *i915)
 	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
-	return i915_live_subtests(tests, i915);
+	return intel_gt_live_subtests(tests, &i915->gt);
 }
-- 
cgit v1.2.3


From bd74708cd979f4934f0744055ce3b47da68733ce Mon Sep 17 00:00:00 2001
From: Mahesh Bandewar <maheshb@google.com>
Date: Wed, 16 Oct 2019 00:04:38 -0700
Subject: Revert "blackhole_netdev: fix syzkaller reported issue"

This reverts commit b0818f80c8c1bc215bba276bd61c216014fab23b.

Started seeing weird behavior after this patch especially in
the IPv6 code path. Haven't root caused it, but since this was
applied to net branch, taking a precautionary measure to revert
it and look / analyze those failures

Revert this now and I'll send a better fix after analysing / fixing
the weirdness observed.

CC: Eric Dumazet <edumazet@google.com>
CC: Wei Wang <weiwan@google.com>
CC: David S. Miller <davem@davemloft.net>
Signed-off-by: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c |  7 +------
 net/ipv6/route.c    | 15 +++++++++------
 2 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4c87594d1389..34ccef18b40e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6996,7 +6996,7 @@ static struct rtnl_af_ops inet6_ops __read_mostly = {
 
 int __init addrconf_init(void)
 {
-	struct inet6_dev *idev, *bdev;
+	struct inet6_dev *idev;
 	int i, err;
 
 	err = ipv6_addr_label_init();
@@ -7036,14 +7036,10 @@ int __init addrconf_init(void)
 	 */
 	rtnl_lock();
 	idev = ipv6_add_dev(init_net.loopback_dev);
-	bdev = ipv6_add_dev(blackhole_netdev);
 	rtnl_unlock();
 	if (IS_ERR(idev)) {
 		err = PTR_ERR(idev);
 		goto errlo;
-	} else if (IS_ERR(bdev)) {
-		err = PTR_ERR(bdev);
-		goto errlo;
 	}
 
 	ip6_route_init_special_entries();
@@ -7128,7 +7124,6 @@ void addrconf_cleanup(void)
 		addrconf_ifdown(dev, 1);
 	}
 	addrconf_ifdown(init_net.loopback_dev, 2);
-	addrconf_ifdown(blackhole_netdev, 2);
 
 	/*
 	 *	Check hash table.
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 742120728869..a63ff85fe141 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -155,9 +155,10 @@ void rt6_uncached_list_del(struct rt6_info *rt)
 
 static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
 {
+	struct net_device *loopback_dev = net->loopback_dev;
 	int cpu;
 
-	if (dev == net->loopback_dev)
+	if (dev == loopback_dev)
 		return;
 
 	for_each_possible_cpu(cpu) {
@@ -170,7 +171,7 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
 			struct net_device *rt_dev = rt->dst.dev;
 
 			if (rt_idev->dev == dev) {
-				rt->rt6i_idev = in6_dev_get(blackhole_netdev);
+				rt->rt6i_idev = in6_dev_get(loopback_dev);
 				in6_dev_put(rt_idev);
 			}
 
@@ -385,11 +386,13 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 {
 	struct rt6_info *rt = (struct rt6_info *)dst;
 	struct inet6_dev *idev = rt->rt6i_idev;
+	struct net_device *loopback_dev =
+		dev_net(dev)->loopback_dev;
 
-	if (idev && idev->dev != dev_net(dev)->loopback_dev) {
-		struct inet6_dev *ibdev = in6_dev_get(blackhole_netdev);
-		if (ibdev) {
-			rt->rt6i_idev = ibdev;
+	if (idev && idev->dev != loopback_dev) {
+		struct inet6_dev *loopback_idev = in6_dev_get(loopback_dev);
+		if (loopback_idev) {
+			rt->rt6i_idev = loopback_idev;
 			in6_dev_put(idev);
 		}
 	}
-- 
cgit v1.2.3


From 128260a41eeba4dd8d4433eab96aeeb7192392a4 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 12:00:56 +0100
Subject: drm/i915/execlists: Refactor -EIO markup of hung requests

Pull setting -EIO on the hung requests into its own utility function.
Having allowed ourselves to short-circuit submission of completed
requests, we can now do the mark_eio() prior to submission and avoid
some redundant operations.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923110056.15176-4-chris@chris-wilson.co.uk
(cherry picked from commit 0d7cf7bc15e75bf79f2f65d61d19f896609f816a)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 31 +++++++++++++++++--------------
 1 file changed, 17 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index bdfcc7bdadbf..46005986e95f 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -234,6 +234,13 @@ static void execlists_init_reg_state(u32 *reg_state,
 				     struct intel_engine_cs *engine,
 				     struct intel_ring *ring);
 
+static void mark_eio(struct i915_request *rq)
+{
+	if (!i915_request_signaled(rq))
+		dma_fence_set_error(&rq->fence, -EIO);
+	i915_request_mark_complete(rq);
+}
+
 static inline u32 intel_hws_preempt_address(struct intel_engine_cs *engine)
 {
 	return (i915_ggtt_offset(engine->status_page.vma) +
@@ -2574,12 +2581,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	__execlists_reset(engine, true);
 
 	/* Mark all executing requests as skipped. */
-	list_for_each_entry(rq, &engine->active.requests, sched.link) {
-		if (!i915_request_signaled(rq))
-			dma_fence_set_error(&rq->fence, -EIO);
-
-		i915_request_mark_complete(rq);
-	}
+	list_for_each_entry(rq, &engine->active.requests, sched.link)
+		mark_eio(rq);
 
 	/* Flush the queued requests to the timeline list (for retiring). */
 	while ((rb = rb_first_cached(&execlists->queue))) {
@@ -2587,9 +2590,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 		int i;
 
 		priolist_for_each_request_consume(rq, rn, p, i) {
+			mark_eio(rq);
 			__i915_request_submit(rq);
-			dma_fence_set_error(&rq->fence, -EIO);
-			i915_request_mark_complete(rq);
 		}
 
 		rb_erase_cached(&p->node, &execlists->queue);
@@ -2605,13 +2607,14 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 		RB_CLEAR_NODE(rb);
 
 		spin_lock(&ve->base.active.lock);
-		if (ve->request) {
-			ve->request->engine = engine;
-			__i915_request_submit(ve->request);
-			dma_fence_set_error(&ve->request->fence, -EIO);
-			i915_request_mark_complete(ve->request);
+		rq = fetch_and_zero(&ve->request);
+		if (rq) {
+			mark_eio(rq);
+
+			rq->engine = engine;
+			__i915_request_submit(rq);
+
 			ve->base.execlists.queue_priority_hint = INT_MIN;
-			ve->request = NULL;
 		}
 		spin_unlock(&ve->base.active.lock);
 	}
-- 
cgit v1.2.3


From 0336ab580878f4c5663dfa2b66095821fdc3e588 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 11 Oct 2019 23:20:30 +0300
Subject: drm/i915: Favor last VBT child device with conflicting AUX ch/DDC pin
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The first come first served apporoach to handling the VBT
child device AUX ch conflicts has backfired. We have machines
in the wild where the VBT specifies both port A eDP and
port E DP (in that order) with port E being the real one.

So let's try to flip the preference around and let the last
child device win once again.

Cc: stable@vger.kernel.org
Cc: Jani Nikula <jani.nikula@intel.com>
Tested-by: Masami Ichikawa <masami256@gmail.com>
Tested-by: Torsten <freedesktop201910@liggy.de>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111966
Fixes: 36a0f92020dc ("drm/i915/bios: make child device order the priority order")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011202030.8829-1-ville.syrjala@linux.intel.com
Acked-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit 41e35ffb380bde1379e4030bb5b2ac824d5139cf)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_bios.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index efb39f350b19..3250c1b8dcca 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1270,7 +1270,7 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("port %c trying to use the same DDC pin (0x%x) as port %c, "
 			      "disabling port %c DVI/HDMI support\n",
 			      port_name(port), info->alternate_ddc_pin,
-			      port_name(p), port_name(port));
+			      port_name(p), port_name(p));
 
 		/*
 		 * If we have multiple ports supposedly sharing the
@@ -1278,9 +1278,14 @@ static void sanitize_ddc_pin(struct drm_i915_private *dev_priv,
 		 * port. Otherwise they share the same ddc bin and
 		 * system couldn't communicate with them separately.
 		 *
-		 * Give child device order the priority, first come first
-		 * served.
+		 * Give inverse child device order the priority,
+		 * last one wins. Yes, there are real machines
+		 * (eg. Asrock B250M-HDV) where VBT has both
+		 * port A and port E with the same AUX ch and
+		 * we must pick port E :(
 		 */
+		info = &dev_priv->vbt.ddi_port_info[p];
+
 		info->supports_dvi = false;
 		info->supports_hdmi = false;
 		info->alternate_ddc_pin = 0;
@@ -1316,7 +1321,7 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
 		DRM_DEBUG_KMS("port %c trying to use the same AUX CH (0x%x) as port %c, "
 			      "disabling port %c DP support\n",
 			      port_name(port), info->alternate_aux_channel,
-			      port_name(p), port_name(port));
+			      port_name(p), port_name(p));
 
 		/*
 		 * If we have multiple ports supposedlt sharing the
@@ -1324,9 +1329,14 @@ static void sanitize_aux_ch(struct drm_i915_private *dev_priv,
 		 * port. Otherwise they share the same aux channel
 		 * and system couldn't communicate with them separately.
 		 *
-		 * Give child device order the priority, first come first
-		 * served.
+		 * Give inverse child device order the priority,
+		 * last one wins. Yes, there are real machines
+		 * (eg. Asrock B250M-HDV) where VBT has both
+		 * port A and port E with the same AUX ch and
+		 * we must pick port E :(
 		 */
+		info = &dev_priv->vbt.ddi_port_info[p];
+
 		info->supports_dp = false;
 		info->alternate_aux_channel = 0;
 	}
-- 
cgit v1.2.3


From 4f2a572eda67aecb1e7e4fc26cc985fb8158f6e8 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 28 Sep 2019 09:25:46 +0100
Subject: drm/i915/userptr: Never allow userptr into the mappable GGTT

Daniel Vetter uncovered a nasty cycle in using the mmu-notifiers to
invalidate userptr objects which also happen to be pulled into GGTT
mmaps. That is when we unbind the userptr object (on mmu invalidation),
we revoke all CPU mmaps, which may then recurse into mmu invalidation.

We looked for ways of breaking the cycle, but the revocation on
invalidation is required and cannot be avoided. The only solution we
could see was to not allow such GGTT bindings of userptr objects in the
first place. In practice, no one really wants to use a GGTT mmapping of
a CPU pointer...

Just before Daniel's explosive lockdep patches land in v5.4-rc1, we got
a genuine blip from CI:

<4>[  246.793958] ======================================================
<4>[  246.793972] WARNING: possible circular locking dependency detected
<4>[  246.793989] 5.3.0-gbd6c56f50d15-drmtip_372+ #1 Tainted: G     U
<4>[  246.794003] ------------------------------------------------------
<4>[  246.794017] kswapd0/145 is trying to acquire lock:
<4>[  246.794030] 000000003f565be6 (&dev->struct_mutex/1){+.+.}, at: userptr_mn_invalidate_range_start+0x18f/0x220 [i915]
<4>[  246.794250]
                  but task is already holding lock:
<4>[  246.794263] 000000001799cef9 (&anon_vma->rwsem){++++}, at: page_lock_anon_vma_read+0xe6/0x2a0
<4>[  246.794291]
                  which lock already depends on the new lock.

<4>[  246.794307]
                  the existing dependency chain (in reverse order) is:
<4>[  246.794322]
                  -> #3 (&anon_vma->rwsem){++++}:
<4>[  246.794344]        down_write+0x33/0x70
<4>[  246.794357]        __vma_adjust+0x3d9/0x7b0
<4>[  246.794370]        __split_vma+0x16a/0x180
<4>[  246.794385]        mprotect_fixup+0x2a5/0x320
<4>[  246.794399]        do_mprotect_pkey+0x208/0x2e0
<4>[  246.794413]        __x64_sys_mprotect+0x16/0x20
<4>[  246.794429]        do_syscall_64+0x55/0x1c0
<4>[  246.794443]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  246.794456]
                  -> #2 (&mapping->i_mmap_rwsem){++++}:
<4>[  246.794478]        down_write+0x33/0x70
<4>[  246.794493]        unmap_mapping_pages+0x48/0x130
<4>[  246.794519]        i915_vma_revoke_mmap+0x81/0x1b0 [i915]
<4>[  246.794519]        i915_vma_unbind+0x11d/0x4a0 [i915]
<4>[  246.794519]        i915_vma_destroy+0x31/0x300 [i915]
<4>[  246.794519]        __i915_gem_free_objects+0xb8/0x4b0 [i915]
<4>[  246.794519]        drm_file_free.part.0+0x1e6/0x290
<4>[  246.794519]        drm_release+0xa6/0xe0
<4>[  246.794519]        __fput+0xc2/0x250
<4>[  246.794519]        task_work_run+0x82/0xb0
<4>[  246.794519]        do_exit+0x35b/0xdb0
<4>[  246.794519]        do_group_exit+0x34/0xb0
<4>[  246.794519]        __x64_sys_exit_group+0xf/0x10
<4>[  246.794519]        do_syscall_64+0x55/0x1c0
<4>[  246.794519]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  246.794519]
                  -> #1 (&vm->mutex){+.+.}:
<4>[  246.794519]        i915_gem_shrinker_taints_mutex+0x6d/0xe0 [i915]
<4>[  246.794519]        i915_address_space_init+0x9f/0x160 [i915]
<4>[  246.794519]        i915_ggtt_init_hw+0x55/0x170 [i915]
<4>[  246.794519]        i915_driver_probe+0xc9f/0x1620 [i915]
<4>[  246.794519]        i915_pci_probe+0x43/0x1b0 [i915]
<4>[  246.794519]        pci_device_probe+0x9e/0x120
<4>[  246.794519]        really_probe+0xea/0x3d0
<4>[  246.794519]        driver_probe_device+0x10b/0x120
<4>[  246.794519]        device_driver_attach+0x4a/0x50
<4>[  246.794519]        __driver_attach+0x97/0x130
<4>[  246.794519]        bus_for_each_dev+0x74/0xc0
<4>[  246.794519]        bus_add_driver+0x13f/0x210
<4>[  246.794519]        driver_register+0x56/0xe0
<4>[  246.794519]        do_one_initcall+0x58/0x300
<4>[  246.794519]        do_init_module+0x56/0x1f6
<4>[  246.794519]        load_module+0x25bd/0x2a40
<4>[  246.794519]        __se_sys_finit_module+0xd3/0xf0
<4>[  246.794519]        do_syscall_64+0x55/0x1c0
<4>[  246.794519]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  246.794519]
                  -> #0 (&dev->struct_mutex/1){+.+.}:
<4>[  246.794519]        __lock_acquire+0x15d8/0x1e90
<4>[  246.794519]        lock_acquire+0xa6/0x1c0
<4>[  246.794519]        __mutex_lock+0x9d/0x9b0
<4>[  246.794519]        userptr_mn_invalidate_range_start+0x18f/0x220 [i915]
<4>[  246.794519]        __mmu_notifier_invalidate_range_start+0x85/0x110
<4>[  246.794519]        try_to_unmap_one+0x76b/0x860
<4>[  246.794519]        rmap_walk_anon+0x104/0x280
<4>[  246.794519]        try_to_unmap+0xc0/0xf0
<4>[  246.794519]        shrink_page_list+0x561/0xc10
<4>[  246.794519]        shrink_inactive_list+0x220/0x440
<4>[  246.794519]        shrink_node_memcg+0x36e/0x740
<4>[  246.794519]        shrink_node+0xcb/0x490
<4>[  246.794519]        balance_pgdat+0x241/0x580
<4>[  246.794519]        kswapd+0x16c/0x530
<4>[  246.794519]        kthread+0x119/0x130
<4>[  246.794519]        ret_from_fork+0x24/0x50
<4>[  246.794519]
                  other info that might help us debug this:

<4>[  246.794519] Chain exists of:
                    &dev->struct_mutex/1 --> &mapping->i_mmap_rwsem --> &anon_vma->rwsem

<4>[  246.794519]  Possible unsafe locking scenario:

<4>[  246.794519]        CPU0                    CPU1
<4>[  246.794519]        ----                    ----
<4>[  246.794519]   lock(&anon_vma->rwsem);
<4>[  246.794519]                                lock(&mapping->i_mmap_rwsem);
<4>[  246.794519]                                lock(&anon_vma->rwsem);
<4>[  246.794519]   lock(&dev->struct_mutex/1);
<4>[  246.794519]
                   *** DEADLOCK ***

v2: Say no to mmap_ioctl

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111744
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111870
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: stable@vger.kernel.org
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190928082546.3473-1-chris@chris-wilson.co.uk
(cherry picked from commit a4311745bba9763e3c965643d4531bd5765b0513)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_mman.c         | 7 +++++++
 drivers/gpu/drm/i915/gem/i915_gem_object.h       | 6 ++++++
 drivers/gpu/drm/i915/gem/i915_gem_object_types.h | 3 ++-
 drivers/gpu/drm/i915/gem/i915_gem_userptr.c      | 1 +
 drivers/gpu/drm/i915/i915_gem.c                  | 3 +++
 5 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 91051e178021..05289edbafe3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -364,6 +364,7 @@ err:
 		return VM_FAULT_OOM;
 	case -ENOSPC:
 	case -EFAULT:
+	case -ENODEV: /* bad object, how did you get here! */
 		return VM_FAULT_SIGBUS;
 	default:
 		WARN_ONCE(ret, "unhandled error in %s: %i\n", __func__, ret);
@@ -475,10 +476,16 @@ i915_gem_mmap_gtt(struct drm_file *file,
 	if (!obj)
 		return -ENOENT;
 
+	if (i915_gem_object_never_bind_ggtt(obj)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
 	ret = create_mmap_offset(obj);
 	if (ret == 0)
 		*offset = drm_vma_node_offset_addr(&obj->base.vma_node);
 
+out:
 	i915_gem_object_put(obj);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 5efb9936e05b..ddf3605bea8e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -152,6 +152,12 @@ i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj)
 	return obj->ops->flags & I915_GEM_OBJECT_IS_PROXY;
 }
 
+static inline bool
+i915_gem_object_never_bind_ggtt(const struct drm_i915_gem_object *obj)
+{
+	return obj->ops->flags & I915_GEM_OBJECT_NO_GGTT;
+}
+
 static inline bool
 i915_gem_object_needs_async_cancel(const struct drm_i915_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index ede0eb4218a8..646859fea224 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -32,7 +32,8 @@ struct drm_i915_gem_object_ops {
 #define I915_GEM_OBJECT_HAS_STRUCT_PAGE	BIT(0)
 #define I915_GEM_OBJECT_IS_SHRINKABLE	BIT(1)
 #define I915_GEM_OBJECT_IS_PROXY	BIT(2)
-#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(3)
+#define I915_GEM_OBJECT_NO_GGTT		BIT(3)
+#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(4)
 
 	/* Interface between the GEM object and its backing storage.
 	 * get_pages() is called once prior to the use of the associated set
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 11b231c187c5..6b3b50f0f6d9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -702,6 +702,7 @@ i915_gem_userptr_dmabuf_export(struct drm_i915_gem_object *obj)
 static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = {
 	.flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE |
 		 I915_GEM_OBJECT_IS_SHRINKABLE |
+		 I915_GEM_OBJECT_NO_GGTT |
 		 I915_GEM_OBJECT_ASYNC_CANCEL,
 	.get_pages = i915_gem_userptr_get_pages,
 	.put_pages = i915_gem_userptr_put_pages,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 95e7c52cf8ed..d0f94f239919 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -969,6 +969,9 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 
 	lockdep_assert_held(&obj->base.dev->struct_mutex);
 
+	if (i915_gem_object_never_bind_ggtt(obj))
+		return ERR_PTR(-ENODEV);
+
 	if (flags & PIN_MAPPABLE &&
 	    (!view || view->type == I915_GGTT_VIEW_NORMAL)) {
 		/* If the required space is larger than the available
-- 
cgit v1.2.3


From 0a544a2a728e2e33bb7fc38dd542ecb90ee393eb Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 23 Sep 2019 16:28:42 +0100
Subject: drm/i915: Fixup preempt-to-busy vs resubmission of a virtual request

As preempt-to-busy leaves the request on the HW as the resubmission is
processed, that request may complete in the background and even cause a
second virtual request to enter queue. This second virtual request
breaks our "single request in the virtual pipeline" assumptions.
Furthermore, as the virtual request may be completed and retired, we
lose the reference the virtual engine assumes is held. Normally, just
removing the request from the scheduler queue removes it from the
engine, but the virtual engine keeps track of its singleton request via
its ve->request. This pointer needs protecting with a reference.

v2: Drop unnecessary motion of rq->engine = owner

Fixes: 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190923152844.8914-1-chris@chris-wilson.co.uk
(cherry picked from commit b647c7df01b75761b4c0b1cb6f4841088c0b1121)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_lrc.c | 32 ++++++++++++++++++++++++++------
 1 file changed, 26 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 46005986e95f..06a506c29463 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1243,6 +1243,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				submit = true;
 				last = rq;
 			}
+			i915_request_put(rq);
 
 			/*
 			 * Hmm, we have a bunch of virtual engine requests,
@@ -2613,6 +2614,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 
 			rq->engine = engine;
 			__i915_request_submit(rq);
+			i915_request_put(rq);
 
 			ve->base.execlists.queue_priority_hint = INT_MIN;
 		}
@@ -3618,6 +3620,8 @@ submit_engine:
 static void virtual_submit_request(struct i915_request *rq)
 {
 	struct virtual_engine *ve = to_virtual_engine(rq->engine);
+	struct i915_request *old;
+	unsigned long flags;
 
 	GEM_TRACE("%s: rq=%llx:%lld\n",
 		  ve->base.name,
@@ -3626,15 +3630,31 @@ static void virtual_submit_request(struct i915_request *rq)
 
 	GEM_BUG_ON(ve->base.submit_request != virtual_submit_request);
 
-	GEM_BUG_ON(ve->request);
-	GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+	spin_lock_irqsave(&ve->base.active.lock, flags);
+
+	old = ve->request;
+	if (old) { /* background completion event from preempt-to-busy */
+		GEM_BUG_ON(!i915_request_completed(old));
+		__i915_request_submit(old);
+		i915_request_put(old);
+	}
 
-	ve->base.execlists.queue_priority_hint = rq_prio(rq);
-	WRITE_ONCE(ve->request, rq);
+	if (i915_request_completed(rq)) {
+		__i915_request_submit(rq);
 
-	list_move_tail(&rq->sched.link, virtual_queue(ve));
+		ve->base.execlists.queue_priority_hint = INT_MIN;
+		ve->request = NULL;
+	} else {
+		ve->base.execlists.queue_priority_hint = rq_prio(rq);
+		ve->request = i915_request_get(rq);
+
+		GEM_BUG_ON(!list_empty(virtual_queue(ve)));
+		list_move_tail(&rq->sched.link, virtual_queue(ve));
+
+		tasklet_schedule(&ve->base.execlists.tasklet);
+	}
 
-	tasklet_schedule(&ve->base.execlists.tasklet);
+	spin_unlock_irqrestore(&ve->base.active.lock, flags);
 }
 
 static struct ve_bond *
-- 
cgit v1.2.3


From eca0b72089695d5b19c8c2b287ac3f6fbe79197e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 Oct 2019 10:07:49 +0100
Subject: drm/i915: Do initial mocs configuration directly

Now that we record the default "goldenstate" context, we do not need to
emit the mocs registers at the start of each context and can simply do
mmio before the first context and capture the registers as part of its
default image. As a consequence, this means that we repeat the mmio
after each engine reset, fixing up any platform and registers that were
zapped by the reset (for those platforms with global not context-saved
settings).

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111723
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111645
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Prathap Kumar Valsan <prathap.kumar.valsan@intel.com>
Reviewed-by: Prathap Kumar Valsan <prathap.kumar.valsan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016090749.7092-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_mocs.c | 274 +++++++++--------------------------
 drivers/gpu/drm/i915/gt/intel_mocs.h |   3 -
 drivers/gpu/drm/i915/i915_gem.c      |   9 --
 3 files changed, 66 insertions(+), 220 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index 728704bbbe18..5bac3966906b 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -287,10 +287,9 @@ static const struct drm_i915_mocs_entry icelake_mocs_table[] = {
 	GEN11_MOCS_ENTRIES
 };
 
-static bool get_mocs_settings(struct intel_gt *gt,
+static bool get_mocs_settings(const struct drm_i915_private *i915,
 			      struct drm_i915_mocs_table *table)
 {
-	struct drm_i915_private *i915 = gt->i915;
 	bool result = false;
 
 	if (INTEL_GEN(i915) >= 12) {
@@ -331,9 +330,9 @@ static bool get_mocs_settings(struct intel_gt *gt,
 	return result;
 }
 
-static i915_reg_t mocs_register(enum intel_engine_id engine_id, int index)
+static i915_reg_t mocs_register(const struct intel_engine_cs *engine, int index)
 {
-	switch (engine_id) {
+	switch (engine->id) {
 	case RCS0:
 		return GEN9_GFX_MOCS(index);
 	case VCS0:
@@ -347,7 +346,7 @@ static i915_reg_t mocs_register(enum intel_engine_id engine_id, int index)
 	case VCS2:
 		return GEN11_MFX2_MOCS(index);
 	default:
-		MISSING_CASE(engine_id);
+		MISSING_CASE(engine->id);
 		return INVALID_MMIO_REG;
 	}
 }
@@ -365,118 +364,25 @@ static u32 get_entry_control(const struct drm_i915_mocs_table *table,
 	return table->table[I915_MOCS_PTE].control_value;
 }
 
-/**
- * intel_mocs_init_engine() - emit the mocs control table
- * @engine:	The engine for whom to emit the registers.
- *
- * This function simply emits a MI_LOAD_REGISTER_IMM command for the
- * given table starting at the given address.
- */
-void intel_mocs_init_engine(struct intel_engine_cs *engine)
+static void init_mocs_table(struct intel_engine_cs *engine,
+			    const struct drm_i915_mocs_table *table)
 {
-	struct intel_gt *gt = engine->gt;
-	struct intel_uncore *uncore = gt->uncore;
-	struct drm_i915_mocs_table table;
-	unsigned int index;
-	u32 unused_value;
-
-	/* Platforms with global MOCS do not need per-engine initialization. */
-	if (HAS_GLOBAL_MOCS_REGISTERS(gt->i915))
-		return;
-
-	/* Called under a blanket forcewake */
-	assert_forcewakes_active(uncore, FORCEWAKE_ALL);
-
-	if (!get_mocs_settings(gt, &table))
-		return;
-
-	/* Set unused values to PTE */
-	unused_value = table.table[I915_MOCS_PTE].control_value;
-
-	for (index = 0; index < table.size; index++) {
-		u32 value = get_entry_control(&table, index);
+	struct intel_uncore *uncore = engine->uncore;
+	u32 unused_value = table->table[I915_MOCS_PTE].control_value;
+	unsigned int i;
 
+	for (i = 0; i < table->size; i++)
 		intel_uncore_write_fw(uncore,
-				      mocs_register(engine->id, index),
-				      value);
-	}
+				      mocs_register(engine, i),
+				      get_entry_control(table, i));
 
-	/* All remaining entries are also unused */
-	for (; index < table.n_entries; index++)
+	/* All remaining entries are unused */
+	for (; i < table->n_entries; i++)
 		intel_uncore_write_fw(uncore,
-				      mocs_register(engine->id, index),
+				      mocs_register(engine, i),
 				      unused_value);
 }
 
-static void intel_mocs_init_global(struct intel_gt *gt)
-{
-	struct intel_uncore *uncore = gt->uncore;
-	struct drm_i915_mocs_table table;
-	unsigned int index;
-
-	GEM_BUG_ON(!HAS_GLOBAL_MOCS_REGISTERS(gt->i915));
-
-	if (!get_mocs_settings(gt, &table))
-		return;
-
-	if (GEM_DEBUG_WARN_ON(table.size > table.n_entries))
-		return;
-
-	for (index = 0; index < table.size; index++)
-		intel_uncore_write(uncore,
-				   GEN12_GLOBAL_MOCS(index),
-				   table.table[index].control_value);
-
-	/*
-	 * Ok, now set the unused entries to the invalid entry (index 0). These
-	 * entries are officially undefined and no contract for the contents and
-	 * settings is given for these entries.
-	 */
-	for (; index < table.n_entries; index++)
-		intel_uncore_write(uncore,
-				   GEN12_GLOBAL_MOCS(index),
-				   table.table[0].control_value);
-}
-
-static int emit_mocs_control_table(struct i915_request *rq,
-				   const struct drm_i915_mocs_table *table)
-{
-	enum intel_engine_id engine = rq->engine->id;
-	unsigned int index;
-	u32 unused_value;
-	u32 *cs;
-
-	if (GEM_WARN_ON(table->size > table->n_entries))
-		return -ENODEV;
-
-	/* Set unused values to PTE */
-	unused_value = table->table[I915_MOCS_PTE].control_value;
-
-	cs = intel_ring_begin(rq, 2 + 2 * table->n_entries);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	*cs++ = MI_LOAD_REGISTER_IMM(table->n_entries);
-
-	for (index = 0; index < table->size; index++) {
-		u32 value = get_entry_control(table, index);
-
-		*cs++ = i915_mmio_reg_offset(mocs_register(engine, index));
-		*cs++ = value;
-	}
-
-	/* All remaining entries are also unused */
-	for (; index < table->n_entries; index++) {
-		*cs++ = i915_mmio_reg_offset(mocs_register(engine, index));
-		*cs++ = unused_value;
-	}
-
-	*cs++ = MI_NOOP;
-	intel_ring_advance(rq, cs);
-
-	return 0;
-}
-
 /*
  * Get l3cc_value from MOCS entry taking into account when it's not used:
  * I915_MOCS_PTE's value is returned in this case.
@@ -494,141 +400,93 @@ static inline u32 l3cc_combine(const struct drm_i915_mocs_table *table,
 			       u16 low,
 			       u16 high)
 {
-	return low | high << 16;
+	return low | (u32)high << 16;
 }
 
-static int emit_mocs_l3cc_table(struct i915_request *rq,
-				const struct drm_i915_mocs_table *table)
+static void init_l3cc_table(struct intel_engine_cs *engine,
+			    const struct drm_i915_mocs_table *table)
 {
-	u16 unused_value;
+	struct intel_uncore *uncore = engine->uncore;
+	u16 unused_value = table->table[I915_MOCS_PTE].l3cc_value;
 	unsigned int i;
-	u32 *cs;
-
-	if (GEM_WARN_ON(table->size > table->n_entries))
-		return -ENODEV;
-
-	/* Set unused values to PTE */
-	unused_value = table->table[I915_MOCS_PTE].l3cc_value;
-
-	cs = intel_ring_begin(rq, 2 + table->n_entries);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	*cs++ = MI_LOAD_REGISTER_IMM(table->n_entries / 2);
 
 	for (i = 0; i < table->size / 2; i++) {
 		u16 low = get_entry_l3cc(table, 2 * i);
 		u16 high = get_entry_l3cc(table, 2 * i + 1);
 
-		*cs++ = i915_mmio_reg_offset(GEN9_LNCFCMOCS(i));
-		*cs++ = l3cc_combine(table, low, high);
+		intel_uncore_write(uncore,
+				   GEN9_LNCFCMOCS(i),
+				   l3cc_combine(table, low, high));
 	}
 
 	/* Odd table size - 1 left over */
-	if (table->size & 0x01) {
+	if (table->size & 1) {
 		u16 low = get_entry_l3cc(table, 2 * i);
 
-		*cs++ = i915_mmio_reg_offset(GEN9_LNCFCMOCS(i));
-		*cs++ = l3cc_combine(table, low, unused_value);
+		intel_uncore_write(uncore,
+				   GEN9_LNCFCMOCS(i),
+				   l3cc_combine(table, low, unused_value));
 		i++;
 	}
 
 	/* All remaining entries are also unused */
-	for (; i < table->n_entries / 2; i++) {
-		*cs++ = i915_mmio_reg_offset(GEN9_LNCFCMOCS(i));
-		*cs++ = l3cc_combine(table, unused_value, unused_value);
-	}
-
-	*cs++ = MI_NOOP;
-	intel_ring_advance(rq, cs);
-
-	return 0;
+	for (; i < table->n_entries / 2; i++)
+		intel_uncore_write(uncore,
+				   GEN9_LNCFCMOCS(i),
+				   l3cc_combine(table, unused_value,
+						unused_value));
 }
 
-static void intel_mocs_init_l3cc_table(struct intel_gt *gt)
+void intel_mocs_init_engine(struct intel_engine_cs *engine)
 {
-	struct intel_uncore *uncore = gt->uncore;
 	struct drm_i915_mocs_table table;
-	unsigned int i;
-	u16 unused_value;
 
-	if (!get_mocs_settings(gt, &table))
+	/* Called under a blanket forcewake */
+	assert_forcewakes_active(engine->uncore, FORCEWAKE_ALL);
+
+	if (!get_mocs_settings(engine->i915, &table))
 		return;
 
-	/* Set unused values to PTE */
-	unused_value = table.table[I915_MOCS_PTE].l3cc_value;
+	/* Platforms with global MOCS do not need per-engine initialization. */
+	if (!HAS_GLOBAL_MOCS_REGISTERS(engine->i915))
+		init_mocs_table(engine, &table);
 
-	for (i = 0; i < table.size / 2; i++) {
-		u16 low = get_entry_l3cc(&table, 2 * i);
-		u16 high = get_entry_l3cc(&table, 2 * i + 1);
+	if (engine->class == RENDER_CLASS)
+		init_l3cc_table(engine, &table);
+}
 
-		intel_uncore_write(uncore,
-				   GEN9_LNCFCMOCS(i),
-				   l3cc_combine(&table, low, high));
-	}
+static void intel_mocs_init_global(struct intel_gt *gt)
+{
+	struct intel_uncore *uncore = gt->uncore;
+	struct drm_i915_mocs_table table;
+	unsigned int index;
 
-	/* Odd table size - 1 left over */
-	if (table.size & 0x01) {
-		u16 low = get_entry_l3cc(&table, 2 * i);
+	GEM_BUG_ON(!HAS_GLOBAL_MOCS_REGISTERS(gt->i915));
 
-		intel_uncore_write(uncore,
-				   GEN9_LNCFCMOCS(i),
-				   l3cc_combine(&table, low, unused_value));
-		i++;
-	}
+	if (!get_mocs_settings(gt->i915, &table))
+		return;
 
-	/* All remaining entries are also unused */
-	for (; i < table.n_entries / 2; i++)
-		intel_uncore_write(uncore,
-				   GEN9_LNCFCMOCS(i),
-				   l3cc_combine(&table, unused_value,
-						unused_value));
-}
+	if (GEM_DEBUG_WARN_ON(table.size > table.n_entries))
+		return;
 
-/**
- * intel_mocs_emit() - program the MOCS register.
- * @rq:	Request to use to set up the MOCS tables.
- *
- * This function will emit a batch buffer with the values required for
- * programming the MOCS register values for all the currently supported
- * rings.
- *
- * These registers are partially stored in the RCS context, so they are
- * emitted at the same time so that when a context is created these registers
- * are set up. These registers have to be emitted into the start of the
- * context as setting the ELSP will re-init some of these registers back
- * to the hw values.
- *
- * Return: 0 on success, otherwise the error status.
- */
-int intel_mocs_emit(struct i915_request *rq)
-{
-	struct drm_i915_mocs_table t;
-	int ret;
-
-	if (HAS_GLOBAL_MOCS_REGISTERS(rq->i915) ||
-	    rq->engine->class != RENDER_CLASS)
-		return 0;
-
-	if (get_mocs_settings(rq->engine->gt, &t)) {
-		/* Program the RCS control registers */
-		ret = emit_mocs_control_table(rq, &t);
-		if (ret)
-			return ret;
-
-		/* Now program the l3cc registers */
-		ret = emit_mocs_l3cc_table(rq, &t);
-		if (ret)
-			return ret;
-	}
+	for (index = 0; index < table.size; index++)
+		intel_uncore_write(uncore,
+				   GEN12_GLOBAL_MOCS(index),
+				   table.table[index].control_value);
 
-	return 0;
+	/*
+	 * Ok, now set the unused entries to the invalid entry (index 0). These
+	 * entries are officially undefined and no contract for the contents and
+	 * settings is given for these entries.
+	 */
+	for (; index < table.n_entries; index++)
+		intel_uncore_write(uncore,
+				   GEN12_GLOBAL_MOCS(index),
+				   table.table[0].control_value);
 }
 
 void intel_mocs_init(struct intel_gt *gt)
 {
-	intel_mocs_init_l3cc_table(gt);
-
 	if (HAS_GLOBAL_MOCS_REGISTERS(gt->i915))
 		intel_mocs_init_global(gt);
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.h b/drivers/gpu/drm/i915/gt/intel_mocs.h
index 2ae816b7ca19..83371f3e6ba1 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.h
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.h
@@ -49,13 +49,10 @@
  * context handling keep the MOCS in step.
  */
 
-struct i915_request;
 struct intel_engine_cs;
 struct intel_gt;
 
 void intel_mocs_init(struct intel_gt *gt);
 void intel_mocs_init_engine(struct intel_engine_cs *engine);
 
-int intel_mocs_emit(struct i915_request *rq);
-
 #endif
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0ddbd3a5fb8d..3694c7ff6d23 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1111,15 +1111,6 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 		if (err)
 			goto err_rq;
 
-		/*
-		 * Failing to program the MOCS is non-fatal.The system will not
-		 * run at peak performance. So warn the user and carry on.
-		 */
-		err = intel_mocs_emit(rq);
-		if (err)
-			dev_notice(i915->drm.dev,
-				   "Failed to program MOCS registers; expect performance issues.\n");
-
 		err = intel_renderstate_emit(rq);
 		if (err)
 			goto err_rq;
-- 
cgit v1.2.3


From e9d4c9245f54cd50b9bdbdf216a9c0d6404ced7b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 Oct 2019 15:32:33 +0100
Subject: drm/i915: Store i915_ggtt as the backpointer on fence registers

Now that i915_ggtt knows everything about its own paths to perform mmio,
we can use that as our primary backpointer for individual fence
registers. This reduces the amount of pointer dancing we have to perform
on the common paths, but more importantly finishes our fence register
encapsulation.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016143234.4075-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_reset.c     |  2 +-
 drivers/gpu/drm/i915/gvt/aperture_gm.c    |  2 +-
 drivers/gpu/drm/i915/i915_drv.c           |  6 +--
 drivers/gpu/drm/i915/i915_gem.c           |  2 +-
 drivers/gpu/drm/i915/i915_gem_fence_reg.c | 74 ++++++++++++++++++-------------
 drivers/gpu/drm/i915/i915_gem_fence_reg.h |  7 ++-
 drivers/gpu/drm/i915/selftests/i915_gem.c |  2 +-
 7 files changed, 54 insertions(+), 41 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 77445d100ca8..477bfafdb103 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -715,7 +715,7 @@ static int gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask)
 	for_each_engine(engine, gt->i915, id)
 		__intel_engine_reset(engine, stalled_mask & engine->mask);
 
-	i915_gem_restore_fences(gt->i915);
+	i915_gem_restore_fences(gt->ggtt);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c
index d996bbc7ea59..771420453f82 100644
--- a/drivers/gpu/drm/i915/gvt/aperture_gm.c
+++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c
@@ -198,7 +198,7 @@ static int alloc_vgpu_fence(struct intel_vgpu *vgpu)
 	mutex_lock(&dev_priv->ggtt.vm.mutex);
 
 	for (i = 0; i < vgpu_fence_sz(vgpu); i++) {
-		reg = i915_reserve_fence(dev_priv);
+		reg = i915_reserve_fence(&dev_priv->ggtt);
 		if (IS_ERR(reg))
 			goto out_free_fence;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 9354924576c4..fd532b8cfdb8 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1804,7 +1804,7 @@ static int i915_drm_resume(struct drm_device *dev)
 		DRM_ERROR("failed to re-enable GGTT\n");
 
 	i915_gem_restore_gtt_mappings(dev_priv);
-	i915_gem_restore_fences(dev_priv);
+	i915_gem_restore_fences(&dev_priv->ggtt);
 
 	intel_csr_ucode_resume(dev_priv);
 
@@ -2502,7 +2502,7 @@ static int intel_runtime_suspend(struct device *kdev)
 
 		intel_gt_runtime_resume(&dev_priv->gt);
 
-		i915_gem_restore_fences(dev_priv);
+		i915_gem_restore_fences(&dev_priv->ggtt);
 
 		enable_rpm_wakeref_asserts(rpm);
 
@@ -2582,7 +2582,7 @@ static int intel_runtime_resume(struct device *kdev)
 	 * we can do is to hope that things will still work (and disable RPM).
 	 */
 	intel_gt_runtime_resume(&dev_priv->gt);
-	i915_gem_restore_fences(dev_priv);
+	i915_gem_restore_fences(&dev_priv->ggtt);
 
 	/*
 	 * On VLV/CHV display interrupts are part of the display
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 3694c7ff6d23..aef5cf2227dd 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1360,7 +1360,7 @@ err_unlock:
 		/* Minimal basic recovery for KMS */
 		ret = i915_ggtt_enable_hw(dev_priv);
 		i915_gem_restore_gtt_mappings(dev_priv);
-		i915_gem_restore_fences(dev_priv);
+		i915_gem_restore_fences(&dev_priv->ggtt);
 		intel_init_clock_gating(dev_priv);
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
index 487b7261f7ed..83b450d9ce84 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
@@ -59,6 +59,16 @@
 
 #define pipelined 0
 
+static struct drm_i915_private *fence_to_i915(struct i915_fence_reg *fence)
+{
+	return fence->ggtt->vm.i915;
+}
+
+static struct intel_uncore *fence_to_uncore(struct i915_fence_reg *fence)
+{
+	return fence->ggtt->vm.gt->uncore;
+}
+
 static void i965_write_fence_reg(struct i915_fence_reg *fence,
 				 struct i915_vma *vma)
 {
@@ -66,7 +76,7 @@ static void i965_write_fence_reg(struct i915_fence_reg *fence,
 	int fence_pitch_shift;
 	u64 val;
 
-	if (INTEL_GEN(fence->i915) >= 6) {
+	if (INTEL_GEN(fence_to_i915(fence)) >= 6) {
 		fence_reg_lo = FENCE_REG_GEN6_LO(fence->id);
 		fence_reg_hi = FENCE_REG_GEN6_HI(fence->id);
 		fence_pitch_shift = GEN6_FENCE_PITCH_SHIFT;
@@ -95,7 +105,7 @@ static void i965_write_fence_reg(struct i915_fence_reg *fence,
 	}
 
 	if (!pipelined) {
-		struct intel_uncore *uncore = &fence->i915->uncore;
+		struct intel_uncore *uncore = fence_to_uncore(fence);
 
 		/*
 		 * To w/a incoherency with non-atomic 64-bit register updates,
@@ -132,7 +142,7 @@ static void i915_write_fence_reg(struct i915_fence_reg *fence,
 		GEM_BUG_ON(!is_power_of_2(vma->fence_size));
 		GEM_BUG_ON(!IS_ALIGNED(vma->node.start, vma->fence_size));
 
-		if (is_y_tiled && HAS_128_BYTE_Y_TILING(fence->i915))
+		if (is_y_tiled && HAS_128_BYTE_Y_TILING(fence_to_i915(fence)))
 			stride /= 128;
 		else
 			stride /= 512;
@@ -148,7 +158,7 @@ static void i915_write_fence_reg(struct i915_fence_reg *fence,
 	}
 
 	if (!pipelined) {
-		struct intel_uncore *uncore = &fence->i915->uncore;
+		struct intel_uncore *uncore = fence_to_uncore(fence);
 		i915_reg_t reg = FENCE_REG(fence->id);
 
 		intel_uncore_write_fw(uncore, reg, val);
@@ -180,7 +190,7 @@ static void i830_write_fence_reg(struct i915_fence_reg *fence,
 	}
 
 	if (!pipelined) {
-		struct intel_uncore *uncore = &fence->i915->uncore;
+		struct intel_uncore *uncore = fence_to_uncore(fence);
 		i915_reg_t reg = FENCE_REG(fence->id);
 
 		intel_uncore_write_fw(uncore, reg, val);
@@ -191,15 +201,17 @@ static void i830_write_fence_reg(struct i915_fence_reg *fence,
 static void fence_write(struct i915_fence_reg *fence,
 			struct i915_vma *vma)
 {
+	struct drm_i915_private *i915 = fence_to_i915(fence);
+
 	/*
 	 * Previous access through the fence register is marshalled by
 	 * the mb() inside the fault handlers (i915_gem_release_mmaps)
 	 * and explicitly managed for internal users.
 	 */
 
-	if (IS_GEN(fence->i915, 2))
+	if (IS_GEN(i915, 2))
 		i830_write_fence_reg(fence, vma);
-	else if (IS_GEN(fence->i915, 3))
+	else if (IS_GEN(i915, 3))
 		i915_write_fence_reg(fence, vma);
 	else
 		i965_write_fence_reg(fence, vma);
@@ -215,6 +227,8 @@ static void fence_write(struct i915_fence_reg *fence,
 static int fence_update(struct i915_fence_reg *fence,
 			struct i915_vma *vma)
 {
+	struct i915_ggtt *ggtt = fence->ggtt;
+	struct intel_uncore *uncore = fence_to_uncore(fence);
 	intel_wakeref_t wakeref;
 	struct i915_vma *old;
 	int ret;
@@ -256,7 +270,7 @@ static int fence_update(struct i915_fence_reg *fence,
 			old->fence = NULL;
 		}
 
-		list_move(&fence->link, &fence->i915->ggtt.fence_list);
+		list_move(&fence->link, &ggtt->fence_list);
 	}
 
 	/*
@@ -269,7 +283,7 @@ static int fence_update(struct i915_fence_reg *fence,
 	 * be cleared before we can use any other fences to ensure that
 	 * the new fences do not overlap the elided clears, confusing HW.
 	 */
-	wakeref = intel_runtime_pm_get_if_in_use(&fence->i915->runtime_pm);
+	wakeref = intel_runtime_pm_get_if_in_use(uncore->rpm);
 	if (!wakeref) {
 		GEM_BUG_ON(vma);
 		return 0;
@@ -280,10 +294,10 @@ static int fence_update(struct i915_fence_reg *fence,
 
 	if (vma) {
 		vma->fence = fence;
-		list_move_tail(&fence->link, &fence->i915->ggtt.fence_list);
+		list_move_tail(&fence->link, &ggtt->fence_list);
 	}
 
-	intel_runtime_pm_put(&fence->i915->runtime_pm, wakeref);
+	intel_runtime_pm_put(uncore->rpm, wakeref);
 	return 0;
 }
 
@@ -312,11 +326,11 @@ int i915_vma_revoke_fence(struct i915_vma *vma)
 	return fence_update(fence, NULL);
 }
 
-static struct i915_fence_reg *fence_find(struct drm_i915_private *i915)
+static struct i915_fence_reg *fence_find(struct i915_ggtt *ggtt)
 {
 	struct i915_fence_reg *fence;
 
-	list_for_each_entry(fence, &i915->ggtt.fence_list, link) {
+	list_for_each_entry(fence, &ggtt->fence_list, link) {
 		GEM_BUG_ON(fence->vma && fence->vma->fence != fence);
 
 		if (atomic_read(&fence->pin_count))
@@ -326,7 +340,7 @@ static struct i915_fence_reg *fence_find(struct drm_i915_private *i915)
 	}
 
 	/* Wait for completion of pending flips which consume fences */
-	if (intel_has_pending_fb_unpin(i915))
+	if (intel_has_pending_fb_unpin(ggtt->vm.i915))
 		return ERR_PTR(-EAGAIN);
 
 	return ERR_PTR(-EDEADLK);
@@ -351,7 +365,7 @@ int __i915_vma_pin_fence(struct i915_vma *vma)
 			return 0;
 		}
 	} else if (set) {
-		fence = fence_find(vma->vm->i915);
+		fence = fence_find(ggtt);
 		if (IS_ERR(fence))
 			return PTR_ERR(fence);
 
@@ -402,7 +416,7 @@ int i915_vma_pin_fence(struct i915_vma *vma)
 	 * Note that we revoke fences on runtime suspend. Therefore the user
 	 * must keep the device awake whilst using the fence.
 	 */
-	assert_rpm_wakelock_held(&vma->vm->i915->runtime_pm);
+	assert_rpm_wakelock_held(vma->vm->gt->uncore->rpm);
 	GEM_BUG_ON(!i915_vma_is_pinned(vma));
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
 
@@ -418,14 +432,13 @@ int i915_vma_pin_fence(struct i915_vma *vma)
 
 /**
  * i915_reserve_fence - Reserve a fence for vGPU
- * @i915: i915 device private
+ * @ggtt: Global GTT
  *
  * This function walks the fence regs looking for a free one and remove
  * it from the fence_list. It is used to reserve fence for vGPU to use.
  */
-struct i915_fence_reg *i915_reserve_fence(struct drm_i915_private *i915)
+struct i915_fence_reg *i915_reserve_fence(struct i915_ggtt *ggtt)
 {
-	struct i915_ggtt *ggtt = &i915->ggtt;
 	struct i915_fence_reg *fence;
 	int count;
 	int ret;
@@ -439,7 +452,7 @@ struct i915_fence_reg *i915_reserve_fence(struct drm_i915_private *i915)
 	if (count <= 1)
 		return ERR_PTR(-ENOSPC);
 
-	fence = fence_find(i915);
+	fence = fence_find(ggtt);
 	if (IS_ERR(fence))
 		return fence;
 
@@ -463,7 +476,7 @@ struct i915_fence_reg *i915_reserve_fence(struct drm_i915_private *i915)
  */
 void i915_unreserve_fence(struct i915_fence_reg *fence)
 {
-	struct i915_ggtt *ggtt = &fence->i915->ggtt;
+	struct i915_ggtt *ggtt = fence->ggtt;
 
 	lockdep_assert_held(&ggtt->vm.mutex);
 
@@ -472,19 +485,19 @@ void i915_unreserve_fence(struct i915_fence_reg *fence)
 
 /**
  * i915_gem_restore_fences - restore fence state
- * @i915: i915 device private
+ * @ggtt: Global GTT
  *
  * Restore the hw fence state to match the software tracking again, to be called
  * after a gpu reset and on resume. Note that on runtime suspend we only cancel
  * the fences, to be reacquired by the user later.
  */
-void i915_gem_restore_fences(struct drm_i915_private *i915)
+void i915_gem_restore_fences(struct i915_ggtt *ggtt)
 {
 	int i;
 
 	rcu_read_lock(); /* keep obj alive as we dereference */
-	for (i = 0; i < i915->ggtt.num_fences; i++) {
-		struct i915_fence_reg *reg = &i915->ggtt.fence_regs[i];
+	for (i = 0; i < ggtt->num_fences; i++) {
+		struct i915_fence_reg *reg = &ggtt->fence_regs[i];
 		struct i915_vma *vma = READ_ONCE(reg->vma);
 
 		GEM_BUG_ON(vma && vma->fence != reg);
@@ -550,7 +563,7 @@ void i915_gem_restore_fences(struct drm_i915_private *i915)
  */
 
 /**
- * i915_gem_detect_bit_6_swizzle - detect bit 6 swizzling pattern
+ * detect_bit_6_swizzle - detect bit 6 swizzling pattern
  * @i915: i915 device private
  *
  * Detects bit 6 swizzling of address lookup between IGD access and CPU
@@ -822,12 +835,13 @@ i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj,
 void i915_ggtt_init_fences(struct i915_ggtt *ggtt)
 {
 	struct drm_i915_private *i915 = ggtt->vm.i915;
+	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
 	int num_fences;
 	int i;
 
 	INIT_LIST_HEAD(&ggtt->fence_list);
 	INIT_LIST_HEAD(&ggtt->userfault_list);
-	intel_wakeref_auto_init(&ggtt->userfault_wakeref, &i915->runtime_pm);
+	intel_wakeref_auto_init(&ggtt->userfault_wakeref, uncore->rpm);
 
 	detect_bit_6_swizzle(i915);
 
@@ -842,20 +856,20 @@ void i915_ggtt_init_fences(struct i915_ggtt *ggtt)
 		num_fences = 8;
 
 	if (intel_vgpu_active(i915))
-		num_fences = intel_uncore_read(&i915->uncore,
+		num_fences = intel_uncore_read(uncore,
 					       vgtif_reg(avail_rs.fence_num));
 
 	/* Initialize fence registers to zero */
 	for (i = 0; i < num_fences; i++) {
 		struct i915_fence_reg *fence = &ggtt->fence_regs[i];
 
-		fence->i915 = i915;
+		fence->ggtt = ggtt;
 		fence->id = i;
 		list_add_tail(&fence->link, &ggtt->fence_list);
 	}
 	ggtt->num_fences = num_fences;
 
-	i915_gem_restore_fences(i915);
+	i915_gem_restore_fences(ggtt);
 }
 
 void intel_gt_init_swizzling(struct intel_gt *gt)
diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.h b/drivers/gpu/drm/i915/i915_gem_fence_reg.h
index 99866fb9d94f..7bd521cd7cd7 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.h
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.h
@@ -29,7 +29,6 @@
 #include <linux/types.h>
 
 struct drm_i915_gem_object;
-struct drm_i915_private;
 struct i915_ggtt;
 struct i915_vma;
 struct intel_gt;
@@ -39,7 +38,7 @@ struct sg_table;
 
 struct i915_fence_reg {
 	struct list_head link;
-	struct drm_i915_private *i915;
+	struct i915_ggtt *ggtt;
 	struct i915_vma *vma;
 	atomic_t pin_count;
 	int id;
@@ -55,10 +54,10 @@ struct i915_fence_reg {
 };
 
 /* i915_gem_fence_reg.c */
-struct i915_fence_reg *i915_reserve_fence(struct drm_i915_private *i915);
+struct i915_fence_reg *i915_reserve_fence(struct i915_ggtt *ggtt);
 void i915_unreserve_fence(struct i915_fence_reg *fence);
 
-void i915_gem_restore_fences(struct drm_i915_private *i915);
+void i915_gem_restore_fences(struct i915_ggtt *ggtt);
 
 void i915_gem_object_do_bit_17_swizzle(struct drm_i915_gem_object *obj,
 				       struct sg_table *pages);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index bfa40a5b6d98..97f89f744ee2 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -120,7 +120,7 @@ static void pm_resume(struct drm_i915_private *i915)
 		i915_gem_sanitize(i915);
 
 		i915_gem_restore_gtt_mappings(i915);
-		i915_gem_restore_fences(i915);
+		i915_gem_restore_fences(&i915->ggtt);
 
 		i915_gem_resume(i915);
 	}
-- 
cgit v1.2.3


From 972c646f1cfed31ec9661ee7abc161b3ccf21fdd Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 Oct 2019 15:32:34 +0100
Subject: drm/i915: Move swizzle_bit under i915_ggtt

The HW performs swizzling as part of its fence tiling inside the Global
GTT. We already do the probing of the HW settings from the GGTT setup,
complete the picture by storing the information as part of the GGTT. The
primary benefit is the consistency of our probe routines do not break
the i915_ggtt encapsulation.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016143234.4075-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gem/i915_gem_tiling.c         |  8 ++++----
 drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c |  8 ++++----
 drivers/gpu/drm/i915/i915_debugfs.c                |  4 ++--
 drivers/gpu/drm/i915/i915_drv.h                    |  9 ++-------
 drivers/gpu/drm/i915/i915_gem_fence_reg.c          | 15 ++++++++-------
 drivers/gpu/drm/i915/i915_gem_gtt.h                |  5 +++++
 6 files changed, 25 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
index dc2a83ce44d5..1fa592d82af5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c
@@ -348,9 +348,9 @@ i915_gem_set_tiling_ioctl(struct drm_device *dev, void *data,
 		args->stride = 0;
 	} else {
 		if (args->tiling_mode == I915_TILING_X)
-			args->swizzle_mode = to_i915(dev)->mm.bit_6_swizzle_x;
+			args->swizzle_mode = to_i915(dev)->ggtt.bit_6_swizzle_x;
 		else
-			args->swizzle_mode = to_i915(dev)->mm.bit_6_swizzle_y;
+			args->swizzle_mode = to_i915(dev)->ggtt.bit_6_swizzle_y;
 
 		/* Hide bit 17 swizzling from the user.  This prevents old Mesa
 		 * from aborting the application on sw fallbacks to bit 17,
@@ -421,10 +421,10 @@ i915_gem_get_tiling_ioctl(struct drm_device *dev, void *data,
 
 	switch (args->tiling_mode) {
 	case I915_TILING_X:
-		args->swizzle_mode = dev_priv->mm.bit_6_swizzle_x;
+		args->swizzle_mode = dev_priv->ggtt.bit_6_swizzle_x;
 		break;
 	case I915_TILING_Y:
-		args->swizzle_mode = dev_priv->mm.bit_6_swizzle_y;
+		args->swizzle_mode = dev_priv->ggtt.bit_6_swizzle_y;
 		break;
 	default:
 	case I915_TILING_NONE:
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index cfa52c525691..65d4dbf91999 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -357,10 +357,10 @@ static int igt_partial_tiling(void *arg)
 		tile.tiling = tiling;
 		switch (tiling) {
 		case I915_TILING_X:
-			tile.swizzle = i915->mm.bit_6_swizzle_x;
+			tile.swizzle = i915->ggtt.bit_6_swizzle_x;
 			break;
 		case I915_TILING_Y:
-			tile.swizzle = i915->mm.bit_6_swizzle_y;
+			tile.swizzle = i915->ggtt.bit_6_swizzle_y;
 			break;
 		}
 
@@ -474,10 +474,10 @@ static int igt_smoke_tiling(void *arg)
 			break;
 
 		case I915_TILING_X:
-			tile.swizzle = i915->mm.bit_6_swizzle_x;
+			tile.swizzle = i915->ggtt.bit_6_swizzle_x;
 			break;
 		case I915_TILING_Y:
-			tile.swizzle = i915->mm.bit_6_swizzle_y;
+			tile.swizzle = i915->ggtt.bit_6_swizzle_y;
 			break;
 		}
 
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index a541b6ae534f..ada57eee914a 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1660,9 +1660,9 @@ static int i915_swizzle_info(struct seq_file *m, void *data)
 	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
 
 	seq_printf(m, "bit6 swizzle for X-tiling = %s\n",
-		   swizzle_string(dev_priv->mm.bit_6_swizzle_x));
+		   swizzle_string(dev_priv->ggtt.bit_6_swizzle_x));
 	seq_printf(m, "bit6 swizzle for Y-tiling = %s\n",
-		   swizzle_string(dev_priv->mm.bit_6_swizzle_y));
+		   swizzle_string(dev_priv->ggtt.bit_6_swizzle_y));
 
 	if (IS_GEN_RANGE(dev_priv, 3, 4)) {
 		seq_printf(m, "DDC = 0x%08x\n",
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f6aee1e01a7f..88956f37d96c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -695,11 +695,6 @@ struct i915_gem_mm {
 	 */
 	struct workqueue_struct *userptr_wq;
 
-	/** Bit 6 swizzling required for X tiling */
-	u32 bit_6_swizzle_x;
-	/** Bit 6 swizzling required for Y tiling */
-	u32 bit_6_swizzle_y;
-
 	/* shrinker accounting, also useful for userland debugging */
 	u64 shrink_memory;
 	u32 shrink_count;
@@ -2014,9 +2009,9 @@ i915_gem_object_create_internal(struct drm_i915_private *dev_priv,
 /* i915_gem_tiling.c */
 static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
 {
-	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 
-	return dev_priv->mm.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_9_10_17 &&
+	return i915->ggtt.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_9_10_17 &&
 		i915_gem_object_is_tiled(obj);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
index 83b450d9ce84..321189e1b0f2 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
@@ -564,14 +564,15 @@ void i915_gem_restore_fences(struct i915_ggtt *ggtt)
 
 /**
  * detect_bit_6_swizzle - detect bit 6 swizzling pattern
- * @i915: i915 device private
+ * @ggtt: Global GGTT
  *
  * Detects bit 6 swizzling of address lookup between IGD access and CPU
  * access through main memory.
  */
-static void detect_bit_6_swizzle(struct drm_i915_private *i915)
+static void detect_bit_6_swizzle(struct i915_ggtt *ggtt)
 {
-	struct intel_uncore *uncore = &i915->uncore;
+	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
+	struct drm_i915_private *i915 = ggtt->vm.i915;
 	u32 swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
 	u32 swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
 
@@ -733,8 +734,8 @@ static void detect_bit_6_swizzle(struct drm_i915_private *i915)
 		swizzle_y = I915_BIT_6_SWIZZLE_NONE;
 	}
 
-	i915->mm.bit_6_swizzle_x = swizzle_x;
-	i915->mm.bit_6_swizzle_y = swizzle_y;
+	i915->ggtt.bit_6_swizzle_x = swizzle_x;
+	i915->ggtt.bit_6_swizzle_y = swizzle_y;
 }
 
 /*
@@ -843,7 +844,7 @@ void i915_ggtt_init_fences(struct i915_ggtt *ggtt)
 	INIT_LIST_HEAD(&ggtt->userfault_list);
 	intel_wakeref_auto_init(&ggtt->userfault_wakeref, uncore->rpm);
 
-	detect_bit_6_swizzle(i915);
+	detect_bit_6_swizzle(ggtt);
 
 	if (INTEL_GEN(i915) >= 7 &&
 	    !(IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)))
@@ -878,7 +879,7 @@ void intel_gt_init_swizzling(struct intel_gt *gt)
 	struct intel_uncore *uncore = gt->uncore;
 
 	if (INTEL_GEN(i915) < 5 ||
-	    i915->mm.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_NONE)
+	    i915->ggtt.bit_6_swizzle_x == I915_BIT_6_SWIZZLE_NONE)
 		return;
 
 	intel_uncore_rmw(uncore, DISP_ARB_CTL, 0, DISP_TILE_SURFACE_SWIZZLING);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 0a18fdfe63ff..f074f1de66e8 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -411,6 +411,11 @@ struct i915_ggtt {
 
 	int mtrr;
 
+	/** Bit 6 swizzling required for X tiling */
+	u32 bit_6_swizzle_x;
+	/** Bit 6 swizzling required for Y tiling */
+	u32 bit_6_swizzle_y;
+
 	u32 pin_bias;
 
 	unsigned int num_fences;
-- 
cgit v1.2.3


From 2ca4f6ca4562594ef161e4140c2a5e0e5282967b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 14 Oct 2019 06:04:38 -0700
Subject: rxrpc: use rcu protection while reading sk->sk_user_data

We need to extend the rcu_read_lock() section in rxrpc_error_report()
and use rcu_dereference_sk_user_data() instead of plain access
to sk->sk_user_data to make sure all rules are respected.

The compiler wont reload sk->sk_user_data at will, and RCU rules
prevent memory beeing freed too soon.

Fixes: f0308fb07080 ("rxrpc: Fix possible NULL pointer access in ICMP handling")
Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/peer_event.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 61451281d74a..48f67a9b1037 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -147,13 +147,16 @@ void rxrpc_error_report(struct sock *sk)
 {
 	struct sock_exterr_skb *serr;
 	struct sockaddr_rxrpc srx;
-	struct rxrpc_local *local = sk->sk_user_data;
+	struct rxrpc_local *local;
 	struct rxrpc_peer *peer;
 	struct sk_buff *skb;
 
-	if (unlikely(!local))
+	rcu_read_lock();
+	local = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!local)) {
+		rcu_read_unlock();
 		return;
-
+	}
 	_enter("%p{%d}", sk, local->debug_id);
 
 	/* Clear the outstanding error value on the socket so that it doesn't
@@ -163,6 +166,7 @@ void rxrpc_error_report(struct sock *sk)
 
 	skb = sock_dequeue_err_skb(sk);
 	if (!skb) {
+		rcu_read_unlock();
 		_leave("UDP socket errqueue empty");
 		return;
 	}
@@ -170,11 +174,11 @@ void rxrpc_error_report(struct sock *sk)
 	serr = SKB_EXT_ERR(skb);
 	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
 		_leave("UDP empty message");
+		rcu_read_unlock();
 		rxrpc_free_skb(skb, rxrpc_skb_freed);
 		return;
 	}
 
-	rcu_read_lock();
 	peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
 	if (peer && !rxrpc_get_peer_maybe(peer))
 		peer = NULL;
-- 
cgit v1.2.3


From 3de5ae54712c75cf3c517a288e0a704784ec6cf5 Mon Sep 17 00:00:00 2001
From: Yonglong Liu <liuyonglong@huawei.com>
Date: Wed, 16 Oct 2019 10:30:39 +0800
Subject: net: phy: Fix "link partner" information disappear issue

Some drivers just call phy_ethtool_ksettings_set() to set the
links, for those phy drivers that use genphy_read_status(), if
autoneg is on, and the link is up, than execute "ethtool -s
ethx autoneg on" will cause "link partner" information disappear.

The call trace is phy_ethtool_ksettings_set()->phy_start_aneg()
->linkmode_zero(phydev->lp_advertising)->genphy_read_status(),
the link didn't change, so genphy_read_status() just return, and
phydev->lp_advertising is zero now.

This patch moves the clear operation of lp_advertising from
phy_start_aneg() to genphy_read_lpa()/genphy_c45_read_lpa(), and
if autoneg on and autoneg not complete, just clear what the
generic functions care about.

Fixes: 88d6272acaaa ("net: phy: avoid unneeded MDIO reads in genphy_read_status")
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy-c45.c    |  2 ++
 drivers/net/phy/phy.c        |  3 ---
 drivers/net/phy/phy_device.c | 11 ++++++++++-
 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 7935593debb1..a1caeee12236 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -323,6 +323,8 @@ int genphy_c45_read_pma(struct phy_device *phydev)
 {
 	int val;
 
+	linkmode_zero(phydev->lp_advertising);
+
 	val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_CTRL1);
 	if (val < 0)
 		return val;
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 119e6f466056..105d389b58e7 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -572,9 +572,6 @@ int phy_start_aneg(struct phy_device *phydev)
 	if (AUTONEG_DISABLE == phydev->autoneg)
 		phy_sanitize_settings(phydev);
 
-	/* Invalidate LP advertising flags */
-	linkmode_zero(phydev->lp_advertising);
-
 	err = phy_config_aneg(phydev);
 	if (err < 0)
 		goto out_unlock;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 9d2bbb13293e..adb66a2fae18 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1787,7 +1787,14 @@ int genphy_read_lpa(struct phy_device *phydev)
 {
 	int lpa, lpagb;
 
-	if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) {
+	if (phydev->autoneg == AUTONEG_ENABLE) {
+		if (!phydev->autoneg_complete) {
+			mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising,
+							0);
+			mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, 0);
+			return 0;
+		}
+
 		if (phydev->is_gigabit_capable) {
 			lpagb = phy_read(phydev, MII_STAT1000);
 			if (lpagb < 0)
@@ -1815,6 +1822,8 @@ int genphy_read_lpa(struct phy_device *phydev)
 			return lpa;
 
 		mii_lpa_mod_linkmode_lpa_t(phydev->lp_advertising, lpa);
+	} else {
+		linkmode_zero(phydev->lp_advertising);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From e497c20e203680aba9ccf7bb475959595908ca7e Mon Sep 17 00:00:00 2001
From: Biao Huang <biao.huang@mediatek.com>
Date: Tue, 15 Oct 2019 11:24:44 +0800
Subject: net: stmmac: disable/enable ptp_ref_clk in suspend/resume flow

disable ptp_ref_clk in suspend flow, and enable it in resume flow.

Fixes: f573c0b9c4e0 ("stmmac: move stmmac_clk, pclk, clk_ptp_ref and stmmac_rst to platform structure")
Signed-off-by: Biao Huang <biao.huang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c76a1336a451..8fa13d43b5bc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4742,8 +4742,10 @@ int stmmac_suspend(struct device *dev)
 		stmmac_mac_set(priv, priv->ioaddr, false);
 		pinctrl_pm_select_sleep_state(priv->device);
 		/* Disable clock in case of PWM is off */
-		clk_disable(priv->plat->pclk);
-		clk_disable(priv->plat->stmmac_clk);
+		if (priv->plat->clk_ptp_ref)
+			clk_disable_unprepare(priv->plat->clk_ptp_ref);
+		clk_disable_unprepare(priv->plat->pclk);
+		clk_disable_unprepare(priv->plat->stmmac_clk);
 	}
 	mutex_unlock(&priv->lock);
 
@@ -4806,8 +4808,10 @@ int stmmac_resume(struct device *dev)
 	} else {
 		pinctrl_pm_select_default_state(priv->device);
 		/* enable the clk previously disabled */
-		clk_enable(priv->plat->stmmac_clk);
-		clk_enable(priv->plat->pclk);
+		clk_prepare_enable(priv->plat->stmmac_clk);
+		clk_prepare_enable(priv->plat->pclk);
+		if (priv->plat->clk_ptp_ref)
+			clk_prepare_enable(priv->plat->clk_ptp_ref);
 		/* reset the phy so that it's ready */
 		if (priv->mii)
 			stmmac_mdio_reset(priv->mii);
-- 
cgit v1.2.3


From eb8de23c955bd4dae47bfdac61179010d3e451d8 Mon Sep 17 00:00:00 2001
From: Khaled Almahallawy <khaled.almahallawy@intel.com>
Date: Tue, 8 Oct 2019 15:09:05 -0700
Subject: drm/i915/tgl: Enable DDI/Port G

In TGL there we are missing the initialization of port G.
Do the same as for other ports.

Signed-off-by: Khaled Almahallawy <khaled.almahallawy@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191008220905.18278-1-khaled.almahallawy@intel.com
---
 drivers/gpu/drm/i915/display/intel_bios.c     | 4 ++++
 drivers/gpu/drm/i915/display/intel_display.c  | 6 ++++++
 drivers/gpu/drm/i915/display/intel_display.h  | 1 +
 drivers/gpu/drm/i915/display/intel_dp.c       | 2 ++
 drivers/gpu/drm/i915/display/intel_vbt_defs.h | 3 +++
 5 files changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index f0307b04cc13..63c1bd4c2954 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -1399,6 +1399,7 @@ static enum port dvo_port_to_port(u8 dvo_port)
 		[PORT_D] = { DVO_PORT_HDMID, DVO_PORT_DPD, -1},
 		[PORT_E] = { DVO_PORT_CRT, DVO_PORT_HDMIE, DVO_PORT_DPE},
 		[PORT_F] = { DVO_PORT_HDMIF, DVO_PORT_DPF, -1},
+		[PORT_G] = { DVO_PORT_HDMIG, DVO_PORT_DPG, -1},
 	};
 	enum port port;
 	int i;
@@ -2258,6 +2259,9 @@ enum aux_ch intel_bios_port_aux_ch(struct drm_i915_private *dev_priv,
 	case DP_AUX_F:
 		aux_ch = AUX_CH_F;
 		break;
+	case DP_AUX_G:
+		aux_ch = AUX_CH_G;
+		break;
 	default:
 		MISSING_CASE(info->alternate_aux_channel);
 		aux_ch = AUX_CH_A;
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 2309b349f4b5..164ded862148 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -6689,6 +6689,8 @@ enum intel_display_power_domain intel_port_to_power_domain(enum port port)
 		return POWER_DOMAIN_PORT_DDI_E_LANES;
 	case PORT_F:
 		return POWER_DOMAIN_PORT_DDI_F_LANES;
+	case PORT_G:
+		return POWER_DOMAIN_PORT_DDI_G_LANES;
 	default:
 		MISSING_CASE(port);
 		return POWER_DOMAIN_PORT_OTHER;
@@ -6712,6 +6714,8 @@ intel_aux_power_domain(struct intel_digital_port *dig_port)
 			return POWER_DOMAIN_AUX_E_TBT;
 		case AUX_CH_F:
 			return POWER_DOMAIN_AUX_F_TBT;
+		case AUX_CH_G:
+			return POWER_DOMAIN_AUX_G_TBT;
 		default:
 			MISSING_CASE(dig_port->aux_ch);
 			return POWER_DOMAIN_AUX_C_TBT;
@@ -6731,6 +6735,8 @@ intel_aux_power_domain(struct intel_digital_port *dig_port)
 		return POWER_DOMAIN_AUX_E;
 	case AUX_CH_F:
 		return POWER_DOMAIN_AUX_F;
+	case AUX_CH_G:
+		return POWER_DOMAIN_AUX_G;
 	default:
 		MISSING_CASE(dig_port->aux_ch);
 		return POWER_DOMAIN_AUX_A;
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index bed203ec1df8..90807603987c 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -271,6 +271,7 @@ enum aux_ch {
 	AUX_CH_D,
 	AUX_CH_E, /* ICL+ */
 	AUX_CH_F,
+	AUX_CH_G,
 };
 
 #define aux_ch_name(a) ((a) + 'A')
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index dd5dc1e38495..c4c081c79dd9 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1644,6 +1644,7 @@ static i915_reg_t skl_aux_ctl_reg(struct intel_dp *intel_dp)
 	case AUX_CH_D:
 	case AUX_CH_E:
 	case AUX_CH_F:
+	case AUX_CH_G:
 		return DP_AUX_CH_CTL(aux_ch);
 	default:
 		MISSING_CASE(aux_ch);
@@ -1664,6 +1665,7 @@ static i915_reg_t skl_aux_data_reg(struct intel_dp *intel_dp, int index)
 	case AUX_CH_D:
 	case AUX_CH_E:
 	case AUX_CH_F:
+	case AUX_CH_G:
 		return DP_AUX_CH_DATA(aux_ch, index);
 	default:
 		MISSING_CASE(aux_ch);
diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
index dfcd156b5094..e3045ced4bfe 100644
--- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
@@ -291,6 +291,8 @@ struct bdb_general_features {
 #define DVO_PORT_HDMIE		12				/* 193 */
 #define DVO_PORT_DPF		13				/* N/A */
 #define DVO_PORT_HDMIF		14				/* N/A */
+#define DVO_PORT_DPG		15
+#define DVO_PORT_HDMIG		16
 #define DVO_PORT_MIPIA		21				/* 171 */
 #define DVO_PORT_MIPIB		22				/* 171 */
 #define DVO_PORT_MIPIC		23				/* 171 */
@@ -325,6 +327,7 @@ enum vbt_gmbus_ddi {
 #define DP_AUX_D 0x30
 #define DP_AUX_E 0x50
 #define DP_AUX_F 0x60
+#define DP_AUX_G 0x70
 
 #define VBT_DP_MAX_LINK_RATE_HBR3	0
 #define VBT_DP_MAX_LINK_RATE_HBR2	1
-- 
cgit v1.2.3


From 700dea5a0bea9f64eba89fae7cb2540326fdfdc1 Mon Sep 17 00:00:00 2001
From: Dmitry Goldin <dgoldin+lkml@protonmail.ch>
Date: Wed, 9 Oct 2019 13:42:14 +0000
Subject: kheaders: substituting --sort in archive creation

The option --sort=ORDER was only introduced in tar 1.28 (2014), which
is rather new and might not be available in some setups.

This patch tries to replicate the previous behaviour as closely as
possible to fix the kheaders build for older environments. It does
not produce identical archives compared to the previous version due
to minor sorting differences but produces reproducible results itself
in my tests.

Reported-by: Andreas Schwab <schwab@suse.de>
Signed-off-by: Dmitry Goldin <dgoldin+lkml@protonmail.ch>
Tested-by: Andreas Schwab <schwab@suse.de>
Tested-by: Quentin Perret <qperret@google.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 kernel/gen_kheaders.sh | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh
index aff79e461fc9..5a0fc0b0403a 100755
--- a/kernel/gen_kheaders.sh
+++ b/kernel/gen_kheaders.sh
@@ -71,10 +71,13 @@ done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1
 find $cpio_dir -type f -print0 |
 	xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;'
 
-# Create archive and try to normalize metadata for reproducibility
-tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \
-    --owner=0 --group=0 --sort=name --numeric-owner \
-    -Jcf $tarfile -C $cpio_dir/ . > /dev/null
+# Create archive and try to normalize metadata for reproducibility.
+# For compatibility with older versions of tar, files are fed to tar
+# pre-sorted, as --sort=name might not be available.
+find $cpio_dir -printf "./%P\n" | LC_ALL=C sort | \
+    tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \
+    --owner=0 --group=0 --numeric-owner --no-recursion \
+    -Jcf $tarfile -C $cpio_dir/ -T - > /dev/null
 
 echo "$src_files_md5" >  kernel/kheaders.md5
 echo "$obj_files_md5" >> kernel/kheaders.md5
-- 
cgit v1.2.3


From 7571b6a17fcc5e4f6903f065a82d0e38011346ed Mon Sep 17 00:00:00 2001
From: Szabolcs Szőke <szszoke.code@gmail.com>
Date: Fri, 11 Oct 2019 19:19:36 +0200
Subject: ALSA: usb-audio: Disable quirks for BOSS Katana amplifiers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

BOSS Katana amplifiers cannot be used for recording or playback if quirks
are applied

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=195223
Signed-off-by: Szabolcs Szőke <szszoke.code@gmail.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20191011171937.8013-1-szszoke.code@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/pcm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 33cd26763c0e..ff5ab24f3bd1 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -348,6 +348,9 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs,
 		ep = 0x84;
 		ifnum = 0;
 		goto add_sync_ep_from_ifnum;
+	case USB_ID(0x0582, 0x01d8): /* BOSS Katana */
+		/* BOSS Katana amplifiers do not need quirks */
+		return 0;
 	}
 
 	if (attr == USB_ENDPOINT_SYNC_ASYNC &&
-- 
cgit v1.2.3


From 8c8967a7dc01a25f57a0757fdca10987773cd1f2 Mon Sep 17 00:00:00 2001
From: Daniel Drake <drake@endlessm.com>
Date: Thu, 17 Oct 2019 16:15:01 +0800
Subject: ALSA: hda/realtek - Enable headset mic on Asus MJ401TA

On Asus MJ401TA (with Realtek ALC256), the headset mic is connected to
pin 0x19, with default configuration value 0x411111f0 (indicating no
physical connection).

Enable this by quirking the pin. Mic jack detection was also tested and
found to be working.

This enables use of the headset mic on this product.

Signed-off-by: Daniel Drake <drake@endlessm.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20191017081501.17135-1-drake@endlessm.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index b5c225a56b98..ce4f11659765 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5881,6 +5881,7 @@ enum {
 	ALC225_FIXUP_WYSE_AUTO_MUTE,
 	ALC225_FIXUP_WYSE_DISABLE_MIC_VREF,
 	ALC286_FIXUP_ACER_AIO_HEADSET_MIC,
+	ALC256_FIXUP_ASUS_HEADSET_MIC,
 	ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
 	ALC299_FIXUP_PREDATOR_SPK,
 	ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC,
@@ -6930,6 +6931,15 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE
 	},
+	[ALC256_FIXUP_ASUS_HEADSET_MIC] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x03a11020 }, /* headset mic with jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE
+	},
 	[ALC256_FIXUP_ASUS_MIC_NO_PRESENCE] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -7126,6 +7136,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
 	SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
 	SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC),
-- 
cgit v1.2.3


From 05488673a4d41383f9dd537f298e525e6b00fb93 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Wed, 16 Oct 2019 10:38:02 +0100
Subject: drm/i915/pmu: Support multiple GPUs

With discrete graphics system can have both integrated and discrete GPU
handled by i915.

Currently we use a fixed name ("i915") when registering as the uncore PMU
provider which stops working in this case.

To fix this we add the PCI device name string to non-integrated devices
handled by us. Integrated devices keep the legacy name preserving
backward compatibility.

v2:
 * Detect IGP and keep legacy name. (Michal)
 * Use PCI device name as suffix. (Michal, Chris)

v3:
 * Constify the name. (Chris)
 * Use pci_domain_nr. (Chris)

v4:
 * Fix kfree_const usage. (Chris)

v5:
 * kfree_const does not work for modules. (Chris)
 * Changed is_igp helper to take i915.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016093802.12483-1-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/i915_pmu.c | 29 +++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_pmu.h |  4 ++++
 2 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index d0508719492e..00fe401868c4 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -1080,6 +1080,17 @@ static void i915_pmu_unregister_cpuhp_state(struct i915_pmu *pmu)
 	cpuhp_remove_multi_state(cpuhp_slot);
 }
 
+static bool is_igp(struct drm_i915_private *i915)
+{
+	struct pci_dev *pdev = i915->drm.pdev;
+
+	/* IGP is 0000:00:02.0 */
+	return pci_domain_nr(pdev->bus) == 0 &&
+	       pdev->bus->number == 0 &&
+	       PCI_SLOT(pdev->devfn) == 2 &&
+	       PCI_FUNC(pdev->devfn) == 0;
+}
+
 void i915_pmu_register(struct drm_i915_private *i915)
 {
 	struct i915_pmu *pmu = &i915->pmu;
@@ -1110,10 +1121,19 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	pmu->timer.function = i915_sample;
 
-	ret = perf_pmu_register(&pmu->base, "i915", -1);
-	if (ret)
+	if (!is_igp(i915))
+		pmu->name = kasprintf(GFP_KERNEL,
+				      "i915-%s",
+				      dev_name(i915->drm.dev));
+	else
+		pmu->name = "i915";
+	if (!pmu->name)
 		goto err;
 
+	ret = perf_pmu_register(&pmu->base, pmu->name, -1);
+	if (ret)
+		goto err_name;
+
 	ret = i915_pmu_register_cpuhp_state(pmu);
 	if (ret)
 		goto err_unreg;
@@ -1122,6 +1142,9 @@ void i915_pmu_register(struct drm_i915_private *i915)
 
 err_unreg:
 	perf_pmu_unregister(&pmu->base);
+err_name:
+	if (!is_igp(i915))
+		kfree(pmu->name);
 err:
 	pmu->base.event_init = NULL;
 	free_event_attributes(pmu);
@@ -1143,5 +1166,7 @@ void i915_pmu_unregister(struct drm_i915_private *i915)
 
 	perf_pmu_unregister(&pmu->base);
 	pmu->base.event_init = NULL;
+	if (!is_igp(i915))
+		kfree(pmu->name);
 	free_event_attributes(pmu);
 }
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index 067dbbf3bdff..bf52e3983631 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -46,6 +46,10 @@ struct i915_pmu {
 	 * @base: PMU base.
 	 */
 	struct pmu base;
+	/**
+	 * @name: Name as registered with perf core.
+	 */
+	const char *name;
 	/**
 	 * @lock: Lock protecting enable mask and ref count handling.
 	 */
-- 
cgit v1.2.3


From b1fc5833357524d5d342737913dbe32ff3557bc5 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 7 Oct 2019 11:45:36 +0100
Subject: stop_machine: Avoid potential race behaviour

Both multi_cpu_stop() and set_state() access multi_stop_data::state
racily using plain accesses. These are subject to compiler
transformations which could break the intended behaviour of the code,
and this situation is detected by KCSAN on both arm64 and x86 (splats
below).

Improve matters by using READ_ONCE() and WRITE_ONCE() to ensure that the
compiler cannot elide, replay, or tear loads and stores.

In multi_cpu_stop() the two loads of multi_stop_data::state are expected to
be a consistent value, so snapshot the value into a temporary variable to
ensure this.

The state transitions are serialized by atomic manipulation of
multi_stop_data::num_threads, and other fields in multi_stop_data are not
modified while subject to concurrent reads.

KCSAN splat on arm64:

| BUG: KCSAN: data-race in multi_cpu_stop+0xa8/0x198 and set_state+0x80/0xb0
|
| write to 0xffff00001003bd00 of 4 bytes by task 24 on cpu 3:
|  set_state+0x80/0xb0
|  multi_cpu_stop+0x16c/0x198
|  cpu_stopper_thread+0x170/0x298
|  smpboot_thread_fn+0x40c/0x560
|  kthread+0x1a8/0x1b0
|  ret_from_fork+0x10/0x18
|
| read to 0xffff00001003bd00 of 4 bytes by task 14 on cpu 1:
|  multi_cpu_stop+0xa8/0x198
|  cpu_stopper_thread+0x170/0x298
|  smpboot_thread_fn+0x40c/0x560
|  kthread+0x1a8/0x1b0
|  ret_from_fork+0x10/0x18
|
| Reported by Kernel Concurrency Sanitizer on:
| CPU: 1 PID: 14 Comm: migration/1 Not tainted 5.3.0-00007-g67ab35a199f4-dirty #3
| Hardware name: linux,dummy-virt (DT)

KCSAN splat on x86:

| write to 0xffffb0bac0013e18 of 4 bytes by task 19 on cpu 2:
|  set_state kernel/stop_machine.c:170 [inline]
|  ack_state kernel/stop_machine.c:177 [inline]
|  multi_cpu_stop+0x1a4/0x220 kernel/stop_machine.c:227
|  cpu_stopper_thread+0x19e/0x280 kernel/stop_machine.c:516
|  smpboot_thread_fn+0x1a8/0x300 kernel/smpboot.c:165
|  kthread+0x1b5/0x200 kernel/kthread.c:255
|  ret_from_fork+0x35/0x40 arch/x86/entry/entry_64.S:352
|
| read to 0xffffb0bac0013e18 of 4 bytes by task 44 on cpu 7:
|  multi_cpu_stop+0xb4/0x220 kernel/stop_machine.c:213
|  cpu_stopper_thread+0x19e/0x280 kernel/stop_machine.c:516
|  smpboot_thread_fn+0x1a8/0x300 kernel/smpboot.c:165
|  kthread+0x1b5/0x200 kernel/kthread.c:255
|  ret_from_fork+0x35/0x40 arch/x86/entry/entry_64.S:352
|
| Reported by Kernel Concurrency Sanitizer on:
| CPU: 7 PID: 44 Comm: migration/7 Not tainted 5.3.0+ #1
| Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Marco Elver <elver@google.com>
Link: https://lkml.kernel.org/r/20191007104536.27276-1-mark.rutland@arm.com
---
 kernel/stop_machine.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index c7031a22aa7b..998d50ee2d9b 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2010		SUSE Linux Products GmbH
  * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
  */
+#include <linux/compiler.h>
 #include <linux/completion.h>
 #include <linux/cpu.h>
 #include <linux/init.h>
@@ -167,7 +168,7 @@ static void set_state(struct multi_stop_data *msdata,
 	/* Reset ack counter. */
 	atomic_set(&msdata->thread_ack, msdata->num_threads);
 	smp_wmb();
-	msdata->state = newstate;
+	WRITE_ONCE(msdata->state, newstate);
 }
 
 /* Last one to ack a state moves to the next state. */
@@ -186,7 +187,7 @@ void __weak stop_machine_yield(const struct cpumask *cpumask)
 static int multi_cpu_stop(void *data)
 {
 	struct multi_stop_data *msdata = data;
-	enum multi_stop_state curstate = MULTI_STOP_NONE;
+	enum multi_stop_state newstate, curstate = MULTI_STOP_NONE;
 	int cpu = smp_processor_id(), err = 0;
 	const struct cpumask *cpumask;
 	unsigned long flags;
@@ -210,8 +211,9 @@ static int multi_cpu_stop(void *data)
 	do {
 		/* Chill out and ensure we re-read multi_stop_state. */
 		stop_machine_yield(cpumask);
-		if (msdata->state != curstate) {
-			curstate = msdata->state;
+		newstate = READ_ONCE(msdata->state);
+		if (newstate != curstate) {
+			curstate = newstate;
 			switch (curstate) {
 			case MULTI_STOP_DISABLE_IRQ:
 				local_irq_disable();
-- 
cgit v1.2.3


From d4a415dcda35d298b0048eb9c1a9bc04a5007fe0 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 15 Oct 2019 22:05:38 +0300
Subject: drm/i915: Fix MST oops due to MSA changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The MSA MISC computation now depends on the connector state, and
we do it from the DDI .pre_enable() hook. All that is fine for
DP SST but with MST we don't actually pass the connector state
to the dig port's .pre_enable() hook which leads to an oops.

Need to think more how to solve this in a cleaner fashion, but
for now let's just add a NULL check to stop the oopsing.

Cc: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
Cc: Uma Shankar <uma.shankar@intel.com>
Fixes: 0c06fa156006 ("drm/i915/dp: Add support of BT.2020 Colorimetry to DP MSA")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015190538.27539-1-ville.syrjala@linux.intel.com
Reviewed-by: Uma Shankar <uma.shankar@intel.com>
Reviewed-by: Gwan-gyeong Mun <gwan-gyeong.mun@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 80f8e2698be0..4c81449ec144 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -1794,8 +1794,10 @@ void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
 	 * of Color Encoding Format and Content Color Gamut] while sending
 	 * YCBCR 420, HDR BT.2020 signals we should program MSA MISC1 fields
 	 * which indicate VSC SDP for the Pixel Encoding/Colorimetry Format.
+	 *
+	 * FIXME MST doesn't pass in the conn_state
 	 */
-	if (intel_dp_needs_vsc_sdp(crtc_state, conn_state))
+	if (conn_state && intel_dp_needs_vsc_sdp(crtc_state, conn_state))
 		temp |= DP_MSA_MISC_COLOR_VSC_SDP;
 
 	I915_WRITE(TRANS_MSA_MISC(cpu_transcoder), temp);
-- 
cgit v1.2.3


From 13bd677a472d534bf100bab2713efc3f9e3f5978 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Wed, 16 Oct 2019 09:21:50 -0400
Subject: dm cache: fix bugs when a GFP_NOWAIT allocation fails

GFP_NOWAIT allocation can fail anytime - it doesn't wait for memory being
available and it fails if the mempool is exhausted and there is not enough
memory.

If we go down this path:
  map_bio -> mg_start -> alloc_migration -> mempool_alloc(GFP_NOWAIT)
we can see that map_bio() doesn't check the return value of mg_start(),
and the bio is leaked.

If we go down this path:
  map_bio -> mg_start -> mg_lock_writes -> alloc_prison_cell ->
  dm_bio_prison_alloc_cell_v2 -> mempool_alloc(GFP_NOWAIT) ->
  mg_lock_writes -> mg_complete
the bio is ended with an error - it is unacceptable because it could
cause filesystem corruption if the machine ran out of memory
temporarily.

Change GFP_NOWAIT to GFP_NOIO, so that the mempool code will properly
wait until memory becomes available. mempool_alloc with GFP_NOIO can't
fail, so remove the code paths that deal with allocation failure.

Cc: stable@vger.kernel.org
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm-cache-target.c | 28 ++--------------------------
 1 file changed, 2 insertions(+), 26 deletions(-)

diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index d249cf8ac277..8346e6d1816c 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -542,7 +542,7 @@ static void wake_migration_worker(struct cache *cache)
 
 static struct dm_bio_prison_cell_v2 *alloc_prison_cell(struct cache *cache)
 {
-	return dm_bio_prison_alloc_cell_v2(cache->prison, GFP_NOWAIT);
+	return dm_bio_prison_alloc_cell_v2(cache->prison, GFP_NOIO);
 }
 
 static void free_prison_cell(struct cache *cache, struct dm_bio_prison_cell_v2 *cell)
@@ -554,9 +554,7 @@ static struct dm_cache_migration *alloc_migration(struct cache *cache)
 {
 	struct dm_cache_migration *mg;
 
-	mg = mempool_alloc(&cache->migration_pool, GFP_NOWAIT);
-	if (!mg)
-		return NULL;
+	mg = mempool_alloc(&cache->migration_pool, GFP_NOIO);
 
 	memset(mg, 0, sizeof(*mg));
 
@@ -664,10 +662,6 @@ static bool bio_detain_shared(struct cache *cache, dm_oblock_t oblock, struct bi
 	struct dm_bio_prison_cell_v2 *cell_prealloc, *cell;
 
 	cell_prealloc = alloc_prison_cell(cache); /* FIXME: allow wait if calling from worker */
-	if (!cell_prealloc) {
-		defer_bio(cache, bio);
-		return false;
-	}
 
 	build_key(oblock, end, &key);
 	r = dm_cell_get_v2(cache->prison, &key, lock_level(bio), bio, cell_prealloc, &cell);
@@ -1493,11 +1487,6 @@ static int mg_lock_writes(struct dm_cache_migration *mg)
 	struct dm_bio_prison_cell_v2 *prealloc;
 
 	prealloc = alloc_prison_cell(cache);
-	if (!prealloc) {
-		DMERR_LIMIT("%s: alloc_prison_cell failed", cache_device_name(cache));
-		mg_complete(mg, false);
-		return -ENOMEM;
-	}
 
 	/*
 	 * Prevent writes to the block, but allow reads to continue.
@@ -1535,11 +1524,6 @@ static int mg_start(struct cache *cache, struct policy_work *op, struct bio *bio
 	}
 
 	mg = alloc_migration(cache);
-	if (!mg) {
-		policy_complete_background_work(cache->policy, op, false);
-		background_work_end(cache);
-		return -ENOMEM;
-	}
 
 	mg->op = op;
 	mg->overwrite_bio = bio;
@@ -1628,10 +1612,6 @@ static int invalidate_lock(struct dm_cache_migration *mg)
 	struct dm_bio_prison_cell_v2 *prealloc;
 
 	prealloc = alloc_prison_cell(cache);
-	if (!prealloc) {
-		invalidate_complete(mg, false);
-		return -ENOMEM;
-	}
 
 	build_key(mg->invalidate_oblock, oblock_succ(mg->invalidate_oblock), &key);
 	r = dm_cell_lock_v2(cache->prison, &key,
@@ -1669,10 +1649,6 @@ static int invalidate_start(struct cache *cache, dm_cblock_t cblock,
 		return -EPERM;
 
 	mg = alloc_migration(cache);
-	if (!mg) {
-		background_work_end(cache);
-		return -ENOMEM;
-	}
 
 	mg->overwrite_bio = bio;
 	mg->invalidate_cblock = cblock;
-- 
cgit v1.2.3


From 94989e318b2f11e217e86bee058088064fa9a2e9 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 17 Oct 2019 17:04:11 +0200
Subject: ALSA: hda - Force runtime PM on Nvidia HDMI codecs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Przemysław Kopa reports that since commit b516ea586d71 ("PCI: Enable
NVIDIA HDA controllers"), the discrete GPU Nvidia GeForce GT 540M on his
2011 Samsung laptop refuses to runtime suspend, resulting in a power
regression and excessive heat.

Rivera Valdez witnesses the same issue with a GeForce GT 525M (GF108M)
of the same era, as does another Arch Linux user named "R0AR" with a
more recent GeForce GTX 1050 Ti (GP107M).

The commit exposes the discrete GPU's HDA controller and all four codecs
on the controller do not set the CLKSTOP and EPSS bits in the Supported
Power States Response.  They also do not set the PS-ClkStopOk bit in the
Get Power State Response.  hda_codec_runtime_suspend() therefore does
not call snd_hdac_codec_link_down(), which prevents each codec and the
PCI device from runtime suspending.

The same issue is present on some AMD discrete GPUs and we addressed it
by forcing runtime PM despite the bits not being set, see commit
57cb54e53bdd ("ALSA: hda - Force to link down at runtime suspend on
ATI/AMD HDMI").

Do the same for Nvidia HDMI codecs.

Fixes: b516ea586d71 ("PCI: Enable NVIDIA HDA controllers")
Link: https://bbs.archlinux.org/viewtopic.php?pid=1865512
Link: https://bugs.freedesktop.org/show_bug.cgi?id=75985#c81
Reported-by: Przemysław Kopa <prymoo@gmail.com>
Reported-by: Rivera Valdez <riveravaldez@ysinembargo.com>
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Cc: Daniel Drake <dan@reactivated.net>
Cc: stable@vger.kernel.org # v5.3+
Link: https://lore.kernel.org/r/3086bc75135c1e3567c5bc4f3cc4ff5cbf7a56c2.1571324194.git.lukas@wunner.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_hdmi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index bca5de78e9ad..795cbda32cbb 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -3474,6 +3474,8 @@ static int patch_nvhdmi(struct hda_codec *codec)
 		nvhdmi_chmap_cea_alloc_validate_get_type;
 	spec->chmap.ops.chmap_validate = nvhdmi_chmap_validate;
 
+	codec->link_down_at_suspend = 1;
+
 	generic_acomp_init(codec, &nvhdmi_audio_ops, nvhdmi_port2pin);
 
 	return 0;
-- 
cgit v1.2.3


From 283ea345934d277e30c841c577e0e2142b4bfcae Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Thu, 17 Oct 2019 16:22:37 +0200
Subject: coccinelle: api/devm_platform_ioremap_resource: remove useless script

While it is useful for new drivers to use devm_platform_ioremap_resource,
this script is currently used to spam maintainers, often updating very
old drivers.  The net benefit is the removal of 2 lines of code in the
driver but the review load for the maintainers is huge.  As of now, more
that 560 patches have been sent, some of them obviously broken, as in:

 https://lore.kernel.org/lkml/9bbcce19c777583815c92ce3c2ff2586@www.loen.fr/

Remove the script to reduce the spam.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Acked-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 .../api/devm_platform_ioremap_resource.cocci       | 60 ----------------------
 1 file changed, 60 deletions(-)
 delete mode 100644 scripts/coccinelle/api/devm_platform_ioremap_resource.cocci

diff --git a/scripts/coccinelle/api/devm_platform_ioremap_resource.cocci b/scripts/coccinelle/api/devm_platform_ioremap_resource.cocci
deleted file mode 100644
index 56a2e261d61d..000000000000
--- a/scripts/coccinelle/api/devm_platform_ioremap_resource.cocci
+++ /dev/null
@@ -1,60 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/// Use devm_platform_ioremap_resource helper which wraps
-/// platform_get_resource() and devm_ioremap_resource() together.
-///
-// Confidence: High
-// Copyright: (C) 2019 Himanshu Jha GPLv2.
-// Copyright: (C) 2019 Julia Lawall, Inria/LIP6. GPLv2.
-// Keywords: platform_get_resource, devm_ioremap_resource,
-// Keywords: devm_platform_ioremap_resource
-
-virtual patch
-virtual report
-
-@r depends on patch && !report@
-expression e1, e2, arg1, arg2, arg3;
-identifier id;
-@@
-
-(
-- id = platform_get_resource(arg1, IORESOURCE_MEM, arg2);
-|
-- struct resource *id = platform_get_resource(arg1, IORESOURCE_MEM, arg2);
-)
-  ... when != id
-- e1 = devm_ioremap_resource(arg3, id);
-+ e1 = devm_platform_ioremap_resource(arg1, arg2);
-  ... when != id
-? id = e2
-
-@r1 depends on patch && !report@
-identifier r.id;
-type T;
-@@
-
-- T *id;
-  ...when != id
-
-@r2 depends on report && !patch@
-identifier id;
-expression e1, e2, arg1, arg2, arg3;
-position j0;
-@@
-
-(
-  id = platform_get_resource(arg1, IORESOURCE_MEM, arg2);
-|
-  struct resource *id = platform_get_resource(arg1, IORESOURCE_MEM, arg2);
-)
-  ... when != id
-  e1@j0 = devm_ioremap_resource(arg3, id);
-  ... when != id
-? id = e2
-
-@script:python depends on report && !patch@
-e1 << r2.e1;
-j0 << r2.j0;
-@@
-
-msg = "WARNING: Use devm_platform_ioremap_resource for %s" % (e1)
-coccilib.report.print_report(j0[0], msg)
-- 
cgit v1.2.3


From 493065e24eb13cf1e974ef9fc0185d6266d16067 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Mon, 14 Oct 2019 11:36:00 -0700
Subject: drm/i915: Add microcontrollers documentation section

To better organize the information, add a microcontrollers section and
move/link the GuC, HuC and DMC documentation under it. Also add a small
intro.

Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Acked-by: Anna Karas <anna.karas@intel.com>
Reviewed-by: Martin Peres <martin.peres@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191014183602.3643-1-daniele.ceraolospurio@intel.com
---
 Documentation/gpu/i915.rst | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 465779670fd4..f1bae7867045 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -415,6 +415,15 @@ Object Tiling IOCTLs
 .. kernel-doc:: drivers/gpu/drm/i915/gem/i915_gem_tiling.c
    :doc: buffer object tiling
 
+Microcontrollers
+================
+
+Starting from gen9, three microcontrollers are available on the HW: the
+graphics microcontroller (GuC), the HEVC/H.265 microcontroller (HuC) and the
+display microcontroller (DMC). The driver is responsible for loading the
+firmwares on the microcontrollers; the GuC and HuC firmwares are transferred
+to WOPCM using the DMA engine, while the DMC firmware is written through MMIO.
+
 WOPCM
 -----
 
@@ -454,6 +463,15 @@ GuC Address Space
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.c
    :doc: GuC Address Space
 
+HuC
+---
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
+   :doc: HuC Firmware
+
+DMC
+---
+See `CSR firmware support for DMC`_
+
 Tracing
 =======
 
-- 
cgit v1.2.3


From 218151e997449717cbb70f304b7b8f9918ba6af4 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Mon, 14 Oct 2019 11:36:01 -0700
Subject: drm/i915/guc: improve documentation

Add a short description of what we expect from GuC and some minor
improvements to existing documentation. Also remove a comment about a
difference between GuC and HuC that is not true anymore.

v2: add that the GuC is not mandatory (Martin)
v3: add extra newline for better text organization (Martin)

Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Martin Peres <martin.peres@linux.intel.com>
Acked-by: Anna Karas <anna.karas@intel.com>
Reviewed-by: Martin Peres <martin.peres@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191014183602.3643-2-daniele.ceraolospurio@intel.com
---
 Documentation/gpu/i915.rst                        | 22 ++++++++++------
 drivers/gpu/drm/i915/gt/uc/intel_guc.c            | 31 +++++++++++++++++++++--
 drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c |  6 +++++
 drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h      |  3 ---
 4 files changed, 49 insertions(+), 13 deletions(-)

diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index f1bae7867045..357e9dfa7de1 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -436,12 +436,24 @@ WOPCM Layout
 GuC
 ---
 
-Firmware Layout
-~~~~~~~~~~~~~~~
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.c
+   :doc: GuC
+
+GuC Firmware Layout
+~~~~~~~~~~~~~~~~~~~
 
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h
    :doc: Firmware Layout
 
+GuC Memory Management
+~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.c
+   :doc: GuC Memory Management
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.c
+   :functions: intel_guc_allocate_vma
+
+
 GuC-specific firmware loader
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
@@ -457,12 +469,6 @@ GuC-based command submission
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
    :internal:
 
-GuC Address Space
-~~~~~~~~~~~~~~~~~
-
-.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_guc.c
-   :doc: GuC Address Space
-
 HuC
 ---
 .. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 249c747e9756..37f7bcbf7dac 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -9,6 +9,27 @@
 #include "intel_guc_submission.h"
 #include "i915_drv.h"
 
+/**
+ * DOC: GuC
+ *
+ * The GuC is a microcontroller inside the GT HW, introduced in gen9. The GuC is
+ * designed to offload some of the functionality usually performed by the host
+ * driver; currently the main operations it can take care of are:
+ *
+ * - Authentication of the HuC, which is required to fully enable HuC usage.
+ * - Low latency graphics context scheduling (a.k.a. GuC submission).
+ * - GT Power management.
+ *
+ * The enable_guc module parameter can be used to select which of those
+ * operations to enable within GuC. Note that not all the operations are
+ * supported on all gen9+ platforms.
+ *
+ * Enabling the GuC is not mandatory and therefore the firmware is only loaded
+ * if at least one of the operations is selected. However, not loading the GuC
+ * might result in the loss of some features that do require the GuC (currently
+ * just the HuC, but more are expected to land in the future).
+ */
+
 static void gen8_guc_raise_irq(struct intel_guc *guc)
 {
 	struct intel_gt *gt = guc_to_gt(guc);
@@ -548,9 +569,15 @@ int intel_guc_resume(struct intel_guc *guc)
 }
 
 /**
- * DOC: GuC Address Space
+ * DOC: GuC Memory Management
  *
- * The layout of GuC address space is shown below:
+ * GuC can't allocate any memory for its own usage, so all the allocations must
+ * be handled by the host driver. GuC accesses the memory via the GGTT, with the
+ * exception of the top and bottom parts of the 4GB address space, which are
+ * instead re-mapped by the GuC HW to memory location of the FW itself (WOPCM)
+ * or other parts of the HW. The driver must take care not to place objects that
+ * the GuC is going to access in these reserved ranges. The layout of the GuC
+ * address space is shown below:
  *
  * ::
  *
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index f325d3dd564f..849a44add424 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -29,6 +29,12 @@ enum {
 /**
  * DOC: GuC-based command submission
  *
+ * IMPORTANT NOTE: GuC submission is currently not supported in i915. The GuC
+ * firmware is moving to an updated submission interface and we plan to
+ * turn submission back on when that lands. The below documentation (and related
+ * code) matches the old submission model and will be updated as part of the
+ * upgrade to the new flow.
+ *
  * GuC client:
  * A intel_guc_client refers to a submission path through GuC. Currently, there
  * is only one client, which is charged with all submissions to the GuC. This
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h
index f8f6c91a0df6..029214cdedd5 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw_abi.h
@@ -39,9 +39,6 @@
  * 3. Length info of each component can be found in header, in dwords.
  * 4. Modulus and exponent key are not required by driver. They may not appear
  *    in fw. So driver will load a truncated firmware in this case.
- *
- * The only difference between GuC and HuC firmwares is how the version
- * information is saved.
  */
 
 struct uc_css_header {
-- 
cgit v1.2.3


From 0b23e2a6ed5cb1196dae7d34c5910193d86244a9 Mon Sep 17 00:00:00 2001
From: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Date: Mon, 14 Oct 2019 11:36:02 -0700
Subject: drm/i915/huc: improve documentation

Better explain the usage of the microcontroller and what i915 is
responsible of. While at it, fix the documentation for the auth
function, which doesn't do any pinning anymore.

v2: add a comment on HuC being optional and descrive how HuC accesses
    memory (Martin)
v3: add extra newline for better text organization (Martin)

Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Martin Peres <martin.peres@linux.intel.com>
Acked-by: Anna Karas <anna.karas@intel.com>
Reviewed-by: Martin Peres <martin.peres@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191014183602.3643-3-daniele.ceraolospurio@intel.com
---
 Documentation/gpu/i915.rst                | 16 ++++++++++++--
 drivers/gpu/drm/i915/gt/uc/intel_huc.c    | 35 +++++++++++++++++++++++++++----
 drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c | 15 -------------
 3 files changed, 45 insertions(+), 21 deletions(-)

diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 357e9dfa7de1..60bd6e6403da 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -471,8 +471,20 @@ GuC-based command submission
 
 HuC
 ---
-.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
-   :doc: HuC Firmware
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_huc.c
+   :doc: HuC
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_huc.c
+   :functions: intel_huc_auth
+
+HuC Memory Management
+~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/i915/gt/uc/intel_huc.c
+   :doc: HuC Memory Management
+
+HuC Firmware Layout
+~~~~~~~~~~~~~~~~~~~
+The HuC FW layout is the same as the GuC one, see `GuC Firmware Layout`_
 
 DMC
 ---
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index 33608a114d4e..8be515c8d0f0 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -9,6 +9,34 @@
 #include "intel_huc.h"
 #include "i915_drv.h"
 
+/**
+ * DOC: HuC
+ *
+ * The HuC is a dedicated microcontroller for usage in media HEVC (High
+ * Efficiency Video Coding) operations. Userspace can directly use the firmware
+ * capabilities by adding HuC specific commands to batch buffers.
+ *
+ * The kernel driver is only responsible for loading the HuC firmware and
+ * triggering its security authentication, which is performed by the GuC. For
+ * The GuC to correctly perform the authentication, the HuC binary must be
+ * loaded before the GuC one. Loading the HuC is optional; however, not using
+ * the HuC might negatively impact power usage and/or performance of media
+ * workloads, depending on the use-cases.
+ *
+ * See https://github.com/intel/media-driver for the latest details on HuC
+ * functionality.
+ */
+
+/**
+ * DOC: HuC Memory Management
+ *
+ * Similarly to the GuC, the HuC can't do any memory allocations on its own,
+ * with the difference being that the allocations for HuC usage are handled by
+ * the userspace driver instead of the kernel one. The HuC accesses the memory
+ * via the PPGTT belonging to the context loaded on the VCS executing the
+ * HuC-specific commands.
+ */
+
 void intel_huc_init_early(struct intel_huc *huc)
 {
 	struct drm_i915_private *i915 = huc_to_gt(huc)->i915;
@@ -118,10 +146,9 @@ void intel_huc_fini(struct intel_huc *huc)
  *
  * Called after HuC and GuC firmware loading during intel_uc_init_hw().
  *
- * This function pins HuC firmware image object into GGTT.
- * Then it invokes GuC action to authenticate passing the offset to RSA
- * signature through intel_guc_auth_huc(). It then waits for 50ms for
- * firmware verification ACK and unpins the object.
+ * This function invokes the GuC action to authenticate the HuC firmware,
+ * passing the offset of the RSA signature to intel_guc_auth_huc(). It then
+ * waits for up to 50ms for firmware verification ACK.
  */
 int intel_huc_auth(struct intel_huc *huc)
 {
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
index 74602487ed67..d654340d4d03 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc_fw.c
@@ -7,21 +7,6 @@
 #include "intel_huc_fw.h"
 #include "i915_drv.h"
 
-/**
- * DOC: HuC Firmware
- *
- * Motivation:
- * GEN9 introduces a new dedicated firmware for usage in media HEVC (High
- * Efficiency Video Coding) operations. Userspace can use the firmware
- * capabilities by adding HuC specific commands to batch buffers.
- *
- * Implementation:
- * The same firmware loader is used as the GuC. However, the actual
- * loading to HW is deferred until GEM initialization is done.
- *
- * Note that HuC firmware loading must be done before GuC loading.
- */
-
 /**
  * intel_huc_fw_init_early() - initializes HuC firmware struct
  * @huc: intel_huc struct
-- 
cgit v1.2.3


From af0de1303c4e8f44fadd7b4c593f09f22324b04f Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 17 Oct 2019 15:25:47 +0200
Subject: usb: hso: obey DMA rules in tiocmget

The serial state information must not be embedded into another
data structure, as this interferes with cache handling for DMA
on architectures without cache coherence..
That would result in data corruption on some architectures
Allocating it separately.

v2: fix syntax error

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/hso.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index a505b2ab88b8..74849da031fa 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -186,7 +186,7 @@ struct hso_tiocmget {
 	int    intr_completed;
 	struct usb_endpoint_descriptor *endp;
 	struct urb *urb;
-	struct hso_serial_state_notification serial_state_notification;
+	struct hso_serial_state_notification *serial_state_notification;
 	u16    prev_UART_state_bitmap;
 	struct uart_icount icount;
 };
@@ -1432,7 +1432,7 @@ static int tiocmget_submit_urb(struct hso_serial *serial,
 			 usb_rcvintpipe(usb,
 					tiocmget->endp->
 					bEndpointAddress & 0x7F),
-			 &tiocmget->serial_state_notification,
+			 tiocmget->serial_state_notification,
 			 sizeof(struct hso_serial_state_notification),
 			 tiocmget_intr_callback, serial,
 			 tiocmget->endp->bInterval);
@@ -1479,7 +1479,7 @@ static void tiocmget_intr_callback(struct urb *urb)
 	/* wIndex should be the USB interface number of the port to which the
 	 * notification applies, which should always be the Modem port.
 	 */
-	serial_state_notification = &tiocmget->serial_state_notification;
+	serial_state_notification = tiocmget->serial_state_notification;
 	if (serial_state_notification->bmRequestType != BM_REQUEST_TYPE ||
 	    serial_state_notification->bNotification != B_NOTIFICATION ||
 	    le16_to_cpu(serial_state_notification->wValue) != W_VALUE ||
@@ -2565,6 +2565,8 @@ static void hso_free_tiomget(struct hso_serial *serial)
 		usb_free_urb(tiocmget->urb);
 		tiocmget->urb = NULL;
 		serial->tiocmget = NULL;
+		kfree(tiocmget->serial_state_notification);
+		tiocmget->serial_state_notification = NULL;
 		kfree(tiocmget);
 	}
 }
@@ -2615,10 +2617,13 @@ static struct hso_device *hso_create_bulk_serial_device(
 		num_urbs = 2;
 		serial->tiocmget = kzalloc(sizeof(struct hso_tiocmget),
 					   GFP_KERNEL);
+		serial->tiocmget->serial_state_notification
+			= kzalloc(sizeof(struct hso_serial_state_notification),
+					   GFP_KERNEL);
 		/* it isn't going to break our heart if serial->tiocmget
 		 *  allocation fails don't bother checking this.
 		 */
-		if (serial->tiocmget) {
+		if (serial->tiocmget && serial->tiocmget->serial_state_notification) {
 			tiocmget = serial->tiocmget;
 			tiocmget->endp = hso_get_ep(interface,
 						    USB_ENDPOINT_XFER_INT,
-- 
cgit v1.2.3


From 8398b375a9e3f5e4bba9bcdfed152a8a247dee01 Mon Sep 17 00:00:00 2001
From: Florin Chiculita <florinlaurentiu.chiculita@nxp.com>
Date: Wed, 16 Oct 2019 10:36:22 +0300
Subject: dpaa2-eth: add irq for the dpmac connect/disconnect event

Add IRQ for the DPNI endpoint change event, resolving the issue
when a dynamically created DPNI gets a randomly generated hw address
when the endpoint is a DPMAC object.

Signed-off-by: Florin Chiculita <florinlaurentiu.chiculita@nxp.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 6 +++++-
 drivers/net/ethernet/freescale/dpaa2/dpni.h      | 5 ++++-
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 162d7d8fb295..5acd734a216b 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -3306,6 +3306,9 @@ static irqreturn_t dpni_irq0_handler_thread(int irq_num, void *arg)
 	if (status & DPNI_IRQ_EVENT_LINK_CHANGED)
 		link_state_update(netdev_priv(net_dev));
 
+	if (status & DPNI_IRQ_EVENT_ENDPOINT_CHANGED)
+		set_mac_addr(netdev_priv(net_dev));
+
 	return IRQ_HANDLED;
 }
 
@@ -3331,7 +3334,8 @@ static int setup_irqs(struct fsl_mc_device *ls_dev)
 	}
 
 	err = dpni_set_irq_mask(ls_dev->mc_io, 0, ls_dev->mc_handle,
-				DPNI_IRQ_INDEX, DPNI_IRQ_EVENT_LINK_CHANGED);
+				DPNI_IRQ_INDEX, DPNI_IRQ_EVENT_LINK_CHANGED |
+				DPNI_IRQ_EVENT_ENDPOINT_CHANGED);
 	if (err < 0) {
 		dev_err(&ls_dev->dev, "dpni_set_irq_mask(): %d\n", err);
 		goto free_irq;
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h
index fd583911b6c0..ee0711d06b3a 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpni.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h
@@ -133,9 +133,12 @@ int dpni_reset(struct fsl_mc_io	*mc_io,
  */
 #define DPNI_IRQ_INDEX				0
 /**
- * IRQ event - indicates a change in link state
+ * IRQ events:
+ *       indicates a change in link state
+ *       indicates a change in endpoint
  */
 #define DPNI_IRQ_EVENT_LINK_CHANGED		0x00000001
+#define DPNI_IRQ_EVENT_ENDPOINT_CHANGED		0x00000002
 
 int dpni_set_irq_enable(struct fsl_mc_io	*mc_io,
 			u32			cmd_flags,
-- 
cgit v1.2.3


From a690af4f16f9bd1f976a4257e1529b6323a8d0e1 Mon Sep 17 00:00:00 2001
From: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Date: Wed, 16 Oct 2019 10:36:23 +0300
Subject: dpaa2-eth: Fix TX FQID values

Depending on when MC connects the DPNI to a MAC, Tx FQIDs may
not be available during probe time.

Read the FQIDs each time the link goes up to avoid using invalid
values. In case an error occurs or an invalid value is retrieved,
fall back to QDID-based enqueueing.

Fixes: 1fa0f68c9255 ("dpaa2-eth: Use FQ-based DPIO enqueue API")
Signed-off-by: Ioana Radulescu <ruxandra.radulescu@nxp.com>
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 44 ++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 5acd734a216b..19379bae0144 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1235,6 +1235,8 @@ static void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv, bool enable)
 	priv->rx_td_enabled = enable;
 }
 
+static void update_tx_fqids(struct dpaa2_eth_priv *priv);
+
 static int link_state_update(struct dpaa2_eth_priv *priv)
 {
 	struct dpni_link_state state = {0};
@@ -1261,6 +1263,7 @@ static int link_state_update(struct dpaa2_eth_priv *priv)
 		goto out;
 
 	if (state.up) {
+		update_tx_fqids(priv);
 		netif_carrier_on(priv->net_dev);
 		netif_tx_start_all_queues(priv->net_dev);
 	} else {
@@ -2533,6 +2536,47 @@ static int set_pause(struct dpaa2_eth_priv *priv)
 	return 0;
 }
 
+static void update_tx_fqids(struct dpaa2_eth_priv *priv)
+{
+	struct dpni_queue_id qid = {0};
+	struct dpaa2_eth_fq *fq;
+	struct dpni_queue queue;
+	int i, j, err;
+
+	/* We only use Tx FQIDs for FQID-based enqueue, so check
+	 * if DPNI version supports it before updating FQIDs
+	 */
+	if (dpaa2_eth_cmp_dpni_ver(priv, DPNI_ENQUEUE_FQID_VER_MAJOR,
+				   DPNI_ENQUEUE_FQID_VER_MINOR) < 0)
+		return;
+
+	for (i = 0; i < priv->num_fqs; i++) {
+		fq = &priv->fq[i];
+		if (fq->type != DPAA2_TX_CONF_FQ)
+			continue;
+		for (j = 0; j < dpaa2_eth_tc_count(priv); j++) {
+			err = dpni_get_queue(priv->mc_io, 0, priv->mc_token,
+					     DPNI_QUEUE_TX, j, fq->flowid,
+					     &queue, &qid);
+			if (err)
+				goto out_err;
+
+			fq->tx_fqid[j] = qid.fqid;
+			if (fq->tx_fqid[j] == 0)
+				goto out_err;
+		}
+	}
+
+	priv->enqueue = dpaa2_eth_enqueue_fq;
+
+	return;
+
+out_err:
+	netdev_info(priv->net_dev,
+		    "Error reading Tx FQID, fallback to QDID-based enqueue\n");
+	priv->enqueue = dpaa2_eth_enqueue_qd;
+}
+
 /* Configure the DPNI object this interface is associated with */
 static int setup_dpni(struct fsl_mc_device *ls_dev)
 {
-- 
cgit v1.2.3


From c9ad4c1049f7e0e8d59e975963dda002af47d93e Mon Sep 17 00:00:00 2001
From: "Ben Dooks (Codethink)" <ben.dooks@codethink.co.uk>
Date: Wed, 16 Oct 2019 09:22:05 +0100
Subject: net: stmmac: fix argument to stmmac_pcs_ctrl_ane()

The stmmac_pcs_ctrl_ane() expects a register address as
argument 1, but for some reason the mac_device_info is
being passed.

Fix the warning (and possible bug) from sparse:

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c:2613:17: warning: incorrect type in argument 1 (different address spaces)
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c:2613:17:    expected void [noderef] <asn:2> *ioaddr
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c:2613:17:    got struct mac_device_info *hw

Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 8fa13d43b5bc..3dfd04e0506a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2610,7 +2610,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	}
 
 	if (priv->hw->pcs)
-		stmmac_pcs_ctrl_ane(priv, priv->hw, 1, priv->hw->ps, 0);
+		stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 1, priv->hw->ps, 0);
 
 	/* set TX and RX rings length */
 	stmmac_set_rings_length(priv);
-- 
cgit v1.2.3


From 7f238ca984b9c6a89e2339c661440c775d617386 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Wed, 16 Oct 2019 15:33:23 +0200
Subject: net: dsa: microchip: Do not reinit mutexes on KSZ87xx

The KSZ87xx driver calls mutex_init() on mutexes already inited in
ksz_common.c ksz_switch_register(). Do not do it twice, drop the
reinitialization.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: David S. Miller <davem@davemloft.net>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: George McCollister <george.mccollister@gmail.com>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz8795.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c
index a23d3ffdf0c4..24a5e99f7fd5 100644
--- a/drivers/net/dsa/microchip/ksz8795.c
+++ b/drivers/net/dsa/microchip/ksz8795.c
@@ -1224,10 +1224,6 @@ static int ksz8795_switch_init(struct ksz_device *dev)
 {
 	int i;
 
-	mutex_init(&dev->stats_mutex);
-	mutex_init(&dev->alu_mutex);
-	mutex_init(&dev->vlan_mutex);
-
 	dev->ds->ops = &ksz8795_switch_ops;
 
 	for (i = 0; i < ARRAY_SIZE(ksz8795_switch_chips); i++) {
-- 
cgit v1.2.3


From 013572a236ef53cbd1e315e0acf2ee632cc816d4 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Wed, 16 Oct 2019 15:33:24 +0200
Subject: net: dsa: microchip: Add shared regmap mutex

The KSZ driver uses one regmap per register width (8/16/32), each with
it's own lock, but accessing the same set of registers. In theory, it
is possible to create a race condition between these regmaps, although
the underlying bus (SPI or I2C) locking should assure nothing bad will
really happen and the accesses would be correct.

To make the driver do the right thing, add one single shared mutex for
all the regmaps used by the driver instead. This assures that even if
some future hardware is on a bus which does not serialize the accesses
the same way SPI or I2C does, nothing bad will happen.

Note that the status_mutex was unused and only initied, hence it was
renamed and repurposed as the regmap mutex.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: David S. Miller <davem@davemloft.net>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: George McCollister <george.mccollister@gmail.com>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/microchip/ksz8795_spi.c |  7 ++++---
 drivers/net/dsa/microchip/ksz9477_i2c.c |  6 ++++--
 drivers/net/dsa/microchip/ksz9477_spi.c |  6 ++++--
 drivers/net/dsa/microchip/ksz_common.c  |  2 +-
 drivers/net/dsa/microchip/ksz_common.h  | 16 +++++++++++++++-
 5 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz8795_spi.c b/drivers/net/dsa/microchip/ksz8795_spi.c
index d0f8153e86b7..8b00f8e6c02f 100644
--- a/drivers/net/dsa/microchip/ksz8795_spi.c
+++ b/drivers/net/dsa/microchip/ksz8795_spi.c
@@ -25,6 +25,7 @@ KSZ_REGMAP_TABLE(ksz8795, 16, SPI_ADDR_SHIFT,
 
 static int ksz8795_spi_probe(struct spi_device *spi)
 {
+	struct regmap_config rc;
 	struct ksz_device *dev;
 	int i, ret;
 
@@ -33,9 +34,9 @@ static int ksz8795_spi_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	for (i = 0; i < ARRAY_SIZE(ksz8795_regmap_config); i++) {
-		dev->regmap[i] = devm_regmap_init_spi(spi,
-						      &ksz8795_regmap_config
-						      [i]);
+		rc = ksz8795_regmap_config[i];
+		rc.lock_arg = &dev->regmap_mutex;
+		dev->regmap[i] = devm_regmap_init_spi(spi, &rc);
 		if (IS_ERR(dev->regmap[i])) {
 			ret = PTR_ERR(dev->regmap[i]);
 			dev_err(&spi->dev,
diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c
index 0b1e01f0873d..fdffd9e0c518 100644
--- a/drivers/net/dsa/microchip/ksz9477_i2c.c
+++ b/drivers/net/dsa/microchip/ksz9477_i2c.c
@@ -17,6 +17,7 @@ KSZ_REGMAP_TABLE(ksz9477, not_used, 16, 0, 0);
 static int ksz9477_i2c_probe(struct i2c_client *i2c,
 			     const struct i2c_device_id *i2c_id)
 {
+	struct regmap_config rc;
 	struct ksz_device *dev;
 	int i, ret;
 
@@ -25,8 +26,9 @@ static int ksz9477_i2c_probe(struct i2c_client *i2c,
 		return -ENOMEM;
 
 	for (i = 0; i < ARRAY_SIZE(ksz9477_regmap_config); i++) {
-		dev->regmap[i] = devm_regmap_init_i2c(i2c,
-					&ksz9477_regmap_config[i]);
+		rc = ksz9477_regmap_config[i];
+		rc.lock_arg = &dev->regmap_mutex;
+		dev->regmap[i] = devm_regmap_init_i2c(i2c, &rc);
 		if (IS_ERR(dev->regmap[i])) {
 			ret = PTR_ERR(dev->regmap[i]);
 			dev_err(&i2c->dev,
diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c
index f4198d6f72be..c5f64959a184 100644
--- a/drivers/net/dsa/microchip/ksz9477_spi.c
+++ b/drivers/net/dsa/microchip/ksz9477_spi.c
@@ -24,6 +24,7 @@ KSZ_REGMAP_TABLE(ksz9477, 32, SPI_ADDR_SHIFT,
 
 static int ksz9477_spi_probe(struct spi_device *spi)
 {
+	struct regmap_config rc;
 	struct ksz_device *dev;
 	int i, ret;
 
@@ -32,8 +33,9 @@ static int ksz9477_spi_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	for (i = 0; i < ARRAY_SIZE(ksz9477_regmap_config); i++) {
-		dev->regmap[i] = devm_regmap_init_spi(spi,
-					&ksz9477_regmap_config[i]);
+		rc = ksz9477_regmap_config[i];
+		rc.lock_arg = &dev->regmap_mutex;
+		dev->regmap[i] = devm_regmap_init_spi(spi, &rc);
 		if (IS_ERR(dev->regmap[i])) {
 			ret = PTR_ERR(dev->regmap[i]);
 			dev_err(&spi->dev,
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index b0b870f0c252..fe47180c908b 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -436,7 +436,7 @@ int ksz_switch_register(struct ksz_device *dev,
 	}
 
 	mutex_init(&dev->dev_mutex);
-	mutex_init(&dev->stats_mutex);
+	mutex_init(&dev->regmap_mutex);
 	mutex_init(&dev->alu_mutex);
 	mutex_init(&dev->vlan_mutex);
 
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index 64c2677693d2..a20ebb749377 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -47,7 +47,7 @@ struct ksz_device {
 	const char *name;
 
 	struct mutex dev_mutex;		/* device access */
-	struct mutex stats_mutex;	/* status access */
+	struct mutex regmap_mutex;	/* regmap access */
 	struct mutex alu_mutex;		/* ALU access */
 	struct mutex vlan_mutex;	/* vlan access */
 	const struct ksz_dev_ops *dev_ops;
@@ -290,6 +290,18 @@ static inline void ksz_pwrite32(struct ksz_device *dev, int port, int offset,
 	ksz_write32(dev, dev->dev_ops->get_port_addr(port, offset), data);
 }
 
+static inline void ksz_regmap_lock(void *__mtx)
+{
+	struct mutex *mtx = __mtx;
+	mutex_lock(mtx);
+}
+
+static inline void ksz_regmap_unlock(void *__mtx)
+{
+	struct mutex *mtx = __mtx;
+	mutex_unlock(mtx);
+}
+
 /* Regmap tables generation */
 #define KSZ_SPI_OP_RD		3
 #define KSZ_SPI_OP_WR		2
@@ -314,6 +326,8 @@ static inline void ksz_pwrite32(struct ksz_device *dev, int port, int offset,
 		.write_flag_mask =					\
 			KSZ_SPI_OP_FLAG_MASK(KSZ_SPI_OP_WR, swp,	\
 					     regbits, regpad),		\
+		.lock = ksz_regmap_lock,				\
+		.unlock = ksz_regmap_unlock,				\
 		.reg_format_endian = REGMAP_ENDIAN_BIG,			\
 		.val_format_endian = REGMAP_ENDIAN_BIG			\
 	}
-- 
cgit v1.2.3


From e9768bfe875f1c54d70d5a512e734993996513a5 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 Oct 2019 13:52:36 +0100
Subject: drm/i915/selftests: Teach requests to use all available engines

The request selftests straddle the boundary between checking the driver
and the hardware. They are subject to the quirks of the underlying HW,
but operate on top of the backend abstractions. The tests focus on the
scheduler elements and so should check for interactions of the scheduler
across all exposed engines.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016125236.17960-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_request.c | 287 ++++++++++++++++----------
 1 file changed, 175 insertions(+), 112 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 0897a7b04944..30ae34f62176 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -37,6 +37,18 @@
 #include "mock_drm.h"
 #include "mock_gem_device.h"
 
+static unsigned int num_uabi_engines(struct drm_i915_private *i915)
+{
+	struct intel_engine_cs *engine;
+	unsigned int count;
+
+	count = 0;
+	for_each_uabi_engine(engine, i915)
+		count++;
+
+	return count;
+}
+
 static int igt_add_request(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
@@ -281,7 +293,7 @@ static int __igt_breadcrumbs_smoketest(void *arg)
 	 * that the fences were marked as signaled.
 	 */
 
-	requests = kmalloc_array(total, sizeof(*requests), GFP_KERNEL);
+	requests = kcalloc(total, sizeof(*requests), GFP_KERNEL);
 	if (!requests)
 		return -ENOMEM;
 
@@ -422,12 +434,11 @@ static int mock_breadcrumbs_smoketest(void *arg)
 	 * See __igt_breadcrumbs_smoketest();
 	 */
 
-	threads = kmalloc_array(ncpus, sizeof(*threads), GFP_KERNEL);
+	threads = kcalloc(ncpus, sizeof(*threads), GFP_KERNEL);
 	if (!threads)
 		return -ENOMEM;
 
-	t.contexts =
-		kmalloc_array(t.ncontexts, sizeof(*t.contexts), GFP_KERNEL);
+	t.contexts = kcalloc(t.ncontexts, sizeof(*t.contexts), GFP_KERNEL);
 	if (!t.contexts) {
 		ret = -ENOMEM;
 		goto out_threads;
@@ -511,15 +522,15 @@ static int live_nop_request(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct intel_engine_cs *engine;
 	struct igt_live_test t;
-	unsigned int id;
 	int err = -ENODEV;
 
-	/* Submit various sized batches of empty requests, to each engine
+	/*
+	 * Submit various sized batches of empty requests, to each engine
 	 * (individually), and wait for the batch to complete. We can check
 	 * the overhead of submitting requests to the hardware.
 	 */
 
-	for_each_engine(engine, i915, id) {
+	for_each_uabi_engine(engine, i915) {
 		unsigned long n, prime;
 		IGT_TIMEOUT(end_time);
 		ktime_t times[2] = {};
@@ -539,7 +550,8 @@ static int live_nop_request(void *arg)
 				if (IS_ERR(request))
 					return PTR_ERR(request);
 
-				/* This space is left intentionally blank.
+				/*
+				 * This space is left intentionally blank.
 				 *
 				 * We do not actually want to perform any
 				 * action with this request, we just want
@@ -657,10 +669,10 @@ static int live_empty_request(void *arg)
 	struct intel_engine_cs *engine;
 	struct igt_live_test t;
 	struct i915_vma *batch;
-	unsigned int id;
 	int err = 0;
 
-	/* Submit various sized batches of empty requests, to each engine
+	/*
+	 * Submit various sized batches of empty requests, to each engine
 	 * (individually), and wait for the batch to complete. We can check
 	 * the overhead of submitting requests to the hardware.
 	 */
@@ -669,7 +681,7 @@ static int live_empty_request(void *arg)
 	if (IS_ERR(batch))
 		return PTR_ERR(batch);
 
-	for_each_engine(engine, i915, id) {
+	for_each_uabi_engine(engine, i915) {
 		IGT_TIMEOUT(end_time);
 		struct i915_request *request;
 		unsigned long n, prime;
@@ -801,63 +813,73 @@ static int recursive_batch_resolve(struct i915_vma *batch)
 static int live_all_engines(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
+	const unsigned int nengines = num_uabi_engines(i915);
 	struct intel_engine_cs *engine;
-	struct i915_request *request[I915_NUM_ENGINES];
+	struct i915_request **request;
 	struct igt_live_test t;
 	struct i915_vma *batch;
-	unsigned int id;
+	unsigned int idx;
 	int err;
 
-	/* Check we can submit requests to all engines simultaneously. We
+	/*
+	 * Check we can submit requests to all engines simultaneously. We
 	 * send a recursive batch to each engine - checking that we don't
 	 * block doing so, and that they don't complete too soon.
 	 */
 
+	request = kcalloc(nengines, sizeof(*request), GFP_KERNEL);
+	if (!request)
+		return -ENOMEM;
+
 	err = igt_live_test_begin(&t, i915, __func__, "");
 	if (err)
-		return err;
+		goto out_free;
 
 	batch = recursive_batch(i915);
 	if (IS_ERR(batch)) {
 		err = PTR_ERR(batch);
 		pr_err("%s: Unable to create batch, err=%d\n", __func__, err);
-		return err;
+		goto out_free;
 	}
 
-	for_each_engine(engine, i915, id) {
-		request[id] = i915_request_create(engine->kernel_context);
-		if (IS_ERR(request[id])) {
-			err = PTR_ERR(request[id]);
+	idx = 0;
+	for_each_uabi_engine(engine, i915) {
+		request[idx] = i915_request_create(engine->kernel_context);
+		if (IS_ERR(request[idx])) {
+			err = PTR_ERR(request[idx]);
 			pr_err("%s: Request allocation failed with err=%d\n",
 			       __func__, err);
 			goto out_request;
 		}
 
-		err = engine->emit_bb_start(request[id],
+		err = engine->emit_bb_start(request[idx],
 					    batch->node.start,
 					    batch->node.size,
 					    0);
 		GEM_BUG_ON(err);
-		request[id]->batch = batch;
+		request[idx]->batch = batch;
 
 		i915_vma_lock(batch);
-		err = i915_request_await_object(request[id], batch->obj, 0);
+		err = i915_request_await_object(request[idx], batch->obj, 0);
 		if (err == 0)
-			err = i915_vma_move_to_active(batch, request[id], 0);
+			err = i915_vma_move_to_active(batch, request[idx], 0);
 		i915_vma_unlock(batch);
 		GEM_BUG_ON(err);
 
-		i915_request_get(request[id]);
-		i915_request_add(request[id]);
+		i915_request_get(request[idx]);
+		i915_request_add(request[idx]);
+		idx++;
 	}
 
-	for_each_engine(engine, i915, id) {
-		if (i915_request_completed(request[id])) {
+	idx = 0;
+	for_each_uabi_engine(engine, i915) {
+		if (i915_request_completed(request[idx])) {
 			pr_err("%s(%s): request completed too early!\n",
 			       __func__, engine->name);
 			err = -EINVAL;
 			goto out_request;
 		}
+		idx++;
 	}
 
 	err = recursive_batch_resolve(batch);
@@ -866,10 +888,11 @@ static int live_all_engines(void *arg)
 		goto out_request;
 	}
 
-	for_each_engine(engine, i915, id) {
+	idx = 0;
+	for_each_uabi_engine(engine, i915) {
 		long timeout;
 
-		timeout = i915_request_wait(request[id], 0,
+		timeout = i915_request_wait(request[idx], 0,
 					    MAX_SCHEDULE_TIMEOUT);
 		if (timeout < 0) {
 			err = timeout;
@@ -878,43 +901,56 @@ static int live_all_engines(void *arg)
 			goto out_request;
 		}
 
-		GEM_BUG_ON(!i915_request_completed(request[id]));
-		i915_request_put(request[id]);
-		request[id] = NULL;
+		GEM_BUG_ON(!i915_request_completed(request[idx]));
+		i915_request_put(request[idx]);
+		request[idx] = NULL;
+		idx++;
 	}
 
 	err = igt_live_test_end(&t);
 
 out_request:
-	for_each_engine(engine, i915, id)
-		if (request[id])
-			i915_request_put(request[id]);
+	idx = 0;
+	for_each_uabi_engine(engine, i915) {
+		if (request[idx])
+			i915_request_put(request[idx]);
+		idx++;
+	}
 	i915_vma_unpin(batch);
 	i915_vma_put(batch);
+out_free:
+	kfree(request);
 	return err;
 }
 
 static int live_sequential_engines(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct i915_request *request[I915_NUM_ENGINES] = {};
+	const unsigned int nengines = num_uabi_engines(i915);
+	struct i915_request **request;
 	struct i915_request *prev = NULL;
 	struct intel_engine_cs *engine;
 	struct igt_live_test t;
-	unsigned int id;
+	unsigned int idx;
 	int err;
 
-	/* Check we can submit requests to all engines sequentially, such
+	/*
+	 * Check we can submit requests to all engines sequentially, such
 	 * that each successive request waits for the earlier ones. This
 	 * tests that we don't execute requests out of order, even though
 	 * they are running on independent engines.
 	 */
 
+	request = kcalloc(nengines, sizeof(*request), GFP_KERNEL);
+	if (!request)
+		return -ENOMEM;
+
 	err = igt_live_test_begin(&t, i915, __func__, "");
 	if (err)
-		return err;
+		goto out_free;
 
-	for_each_engine(engine, i915, id) {
+	idx = 0;
+	for_each_uabi_engine(engine, i915) {
 		struct i915_vma *batch;
 
 		batch = recursive_batch(i915);
@@ -922,66 +958,69 @@ static int live_sequential_engines(void *arg)
 			err = PTR_ERR(batch);
 			pr_err("%s: Unable to create batch for %s, err=%d\n",
 			       __func__, engine->name, err);
-			return err;
+			goto out_free;
 		}
 
-		request[id] = i915_request_create(engine->kernel_context);
-		if (IS_ERR(request[id])) {
-			err = PTR_ERR(request[id]);
+		request[idx] = i915_request_create(engine->kernel_context);
+		if (IS_ERR(request[idx])) {
+			err = PTR_ERR(request[idx]);
 			pr_err("%s: Request allocation failed for %s with err=%d\n",
 			       __func__, engine->name, err);
 			goto out_request;
 		}
 
 		if (prev) {
-			err = i915_request_await_dma_fence(request[id],
+			err = i915_request_await_dma_fence(request[idx],
 							   &prev->fence);
 			if (err) {
-				i915_request_add(request[id]);
+				i915_request_add(request[idx]);
 				pr_err("%s: Request await failed for %s with err=%d\n",
 				       __func__, engine->name, err);
 				goto out_request;
 			}
 		}
 
-		err = engine->emit_bb_start(request[id],
+		err = engine->emit_bb_start(request[idx],
 					    batch->node.start,
 					    batch->node.size,
 					    0);
 		GEM_BUG_ON(err);
-		request[id]->batch = batch;
+		request[idx]->batch = batch;
 
 		i915_vma_lock(batch);
-		err = i915_request_await_object(request[id], batch->obj, false);
+		err = i915_request_await_object(request[idx],
+						batch->obj, false);
 		if (err == 0)
-			err = i915_vma_move_to_active(batch, request[id], 0);
+			err = i915_vma_move_to_active(batch, request[idx], 0);
 		i915_vma_unlock(batch);
 		GEM_BUG_ON(err);
 
-		i915_request_get(request[id]);
-		i915_request_add(request[id]);
+		i915_request_get(request[idx]);
+		i915_request_add(request[idx]);
 
-		prev = request[id];
+		prev = request[idx];
+		idx++;
 	}
 
-	for_each_engine(engine, i915, id) {
+	idx = 0;
+	for_each_uabi_engine(engine, i915) {
 		long timeout;
 
-		if (i915_request_completed(request[id])) {
+		if (i915_request_completed(request[idx])) {
 			pr_err("%s(%s): request completed too early!\n",
 			       __func__, engine->name);
 			err = -EINVAL;
 			goto out_request;
 		}
 
-		err = recursive_batch_resolve(request[id]->batch);
+		err = recursive_batch_resolve(request[idx]->batch);
 		if (err) {
 			pr_err("%s: failed to resolve batch, err=%d\n",
 			       __func__, err);
 			goto out_request;
 		}
 
-		timeout = i915_request_wait(request[id], 0,
+		timeout = i915_request_wait(request[idx], 0,
 					    MAX_SCHEDULE_TIMEOUT);
 		if (timeout < 0) {
 			err = timeout;
@@ -990,30 +1029,35 @@ static int live_sequential_engines(void *arg)
 			goto out_request;
 		}
 
-		GEM_BUG_ON(!i915_request_completed(request[id]));
+		GEM_BUG_ON(!i915_request_completed(request[idx]));
+		idx++;
 	}
 
 	err = igt_live_test_end(&t);
 
 out_request:
-	for_each_engine(engine, i915, id) {
+	idx = 0;
+	for_each_uabi_engine(engine, i915) {
 		u32 *cmd;
 
-		if (!request[id])
+		if (!request[idx])
 			break;
 
-		cmd = i915_gem_object_pin_map(request[id]->batch->obj,
+		cmd = i915_gem_object_pin_map(request[idx]->batch->obj,
 					      I915_MAP_WC);
 		if (!IS_ERR(cmd)) {
 			*cmd = MI_BATCH_BUFFER_END;
 			intel_gt_chipset_flush(engine->gt);
 
-			i915_gem_object_unpin_map(request[id]->batch->obj);
+			i915_gem_object_unpin_map(request[idx]->batch->obj);
 		}
 
-		i915_vma_put(request[id]->batch);
-		i915_request_put(request[id]);
+		i915_vma_put(request[idx]->batch);
+		i915_request_put(request[idx]);
+		idx++;
 	}
+out_free:
+	kfree(request);
 	return err;
 }
 
@@ -1079,9 +1123,10 @@ static int live_parallel_engines(void *arg)
 		__live_parallel_engineN,
 		NULL,
 	};
+	const unsigned int nengines = num_uabi_engines(i915);
 	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
 	int (* const *fn)(void *arg);
+	struct task_struct **tsk;
 	int err = 0;
 
 	/*
@@ -1089,42 +1134,49 @@ static int live_parallel_engines(void *arg)
 	 * tests that we load up the system maximally.
 	 */
 
+	tsk = kcalloc(nengines, sizeof(*tsk), GFP_KERNEL);
+	if (!tsk)
+		return -ENOMEM;
+
 	for (fn = func; !err && *fn; fn++) {
-		struct task_struct *tsk[I915_NUM_ENGINES] = {};
 		struct igt_live_test t;
+		unsigned int idx;
 
 		err = igt_live_test_begin(&t, i915, __func__, "");
 		if (err)
 			break;
 
-		for_each_engine(engine, i915, id) {
-			tsk[id] = kthread_run(*fn, engine,
-					      "igt/parallel:%s",
-					      engine->name);
-			if (IS_ERR(tsk[id])) {
-				err = PTR_ERR(tsk[id]);
+		idx = 0;
+		for_each_uabi_engine(engine, i915) {
+			tsk[idx] = kthread_run(*fn, engine,
+					       "igt/parallel:%s",
+					       engine->name);
+			if (IS_ERR(tsk[idx])) {
+				err = PTR_ERR(tsk[idx]);
 				break;
 			}
-			get_task_struct(tsk[id]);
+			get_task_struct(tsk[idx++]);
 		}
 
-		for_each_engine(engine, i915, id) {
+		idx = 0;
+		for_each_uabi_engine(engine, i915) {
 			int status;
 
-			if (IS_ERR_OR_NULL(tsk[id]))
-				continue;
+			if (IS_ERR(tsk[idx]))
+				break;
 
-			status = kthread_stop(tsk[id]);
+			status = kthread_stop(tsk[idx]);
 			if (status && !err)
 				err = status;
 
-			put_task_struct(tsk[id]);
+			put_task_struct(tsk[idx++]);
 		}
 
 		if (igt_live_test_end(&t))
 			err = -EIO;
 	}
 
+	kfree(tsk);
 	return err;
 }
 
@@ -1168,16 +1220,16 @@ max_batches(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 static int live_breadcrumbs_smoketest(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct smoketest t[I915_NUM_ENGINES];
-	unsigned int ncpus = num_online_cpus();
+	const unsigned int nengines = num_uabi_engines(i915);
+	const unsigned int ncpus = num_online_cpus();
 	unsigned long num_waits, num_fences;
 	struct intel_engine_cs *engine;
 	struct task_struct **threads;
 	struct igt_live_test live;
-	enum intel_engine_id id;
 	intel_wakeref_t wakeref;
 	struct drm_file *file;
-	unsigned int n;
+	struct smoketest *smoke;
+	unsigned int n, idx;
 	int ret = 0;
 
 	/*
@@ -1196,28 +1248,31 @@ static int live_breadcrumbs_smoketest(void *arg)
 		goto out_rpm;
 	}
 
-	threads = kcalloc(ncpus * I915_NUM_ENGINES,
-			  sizeof(*threads),
-			  GFP_KERNEL);
-	if (!threads) {
+	smoke = kcalloc(nengines, sizeof(*smoke), GFP_KERNEL);
+	if (!smoke) {
 		ret = -ENOMEM;
 		goto out_file;
 	}
 
-	memset(&t[0], 0, sizeof(t[0]));
-	t[0].request_alloc = __live_request_alloc;
-	t[0].ncontexts = 64;
-	t[0].contexts = kmalloc_array(t[0].ncontexts,
-				      sizeof(*t[0].contexts),
-				      GFP_KERNEL);
-	if (!t[0].contexts) {
+	threads = kcalloc(ncpus * nengines, sizeof(*threads), GFP_KERNEL);
+	if (!threads) {
+		ret = -ENOMEM;
+		goto out_smoke;
+	}
+
+	smoke[0].request_alloc = __live_request_alloc;
+	smoke[0].ncontexts = 64;
+	smoke[0].contexts = kcalloc(smoke[0].ncontexts,
+				    sizeof(*smoke[0].contexts),
+				    GFP_KERNEL);
+	if (!smoke[0].contexts) {
 		ret = -ENOMEM;
 		goto out_threads;
 	}
 
-	for (n = 0; n < t[0].ncontexts; n++) {
-		t[0].contexts[n] = live_context(i915, file);
-		if (!t[0].contexts[n]) {
+	for (n = 0; n < smoke[0].ncontexts; n++) {
+		smoke[0].contexts[n] = live_context(i915, file);
+		if (!smoke[0].contexts[n]) {
 			ret = -ENOMEM;
 			goto out_contexts;
 		}
@@ -1227,42 +1282,47 @@ static int live_breadcrumbs_smoketest(void *arg)
 	if (ret)
 		goto out_contexts;
 
-	for_each_engine(engine, i915, id) {
-		t[id] = t[0];
-		t[id].engine = engine;
-		t[id].max_batch = max_batches(t[0].contexts[0], engine);
-		if (t[id].max_batch < 0) {
-			ret = t[id].max_batch;
+	idx = 0;
+	for_each_uabi_engine(engine, i915) {
+		smoke[idx] = smoke[0];
+		smoke[idx].engine = engine;
+		smoke[idx].max_batch =
+			max_batches(smoke[0].contexts[0], engine);
+		if (smoke[idx].max_batch < 0) {
+			ret = smoke[idx].max_batch;
 			goto out_flush;
 		}
 		/* One ring interleaved between requests from all cpus */
-		t[id].max_batch /= num_online_cpus() + 1;
+		smoke[idx].max_batch /= num_online_cpus() + 1;
 		pr_debug("Limiting batches to %d requests on %s\n",
-			 t[id].max_batch, engine->name);
+			 smoke[idx].max_batch, engine->name);
 
 		for (n = 0; n < ncpus; n++) {
 			struct task_struct *tsk;
 
 			tsk = kthread_run(__igt_breadcrumbs_smoketest,
-					  &t[id], "igt/%d.%d", id, n);
+					  &smoke[idx], "igt/%d.%d", idx, n);
 			if (IS_ERR(tsk)) {
 				ret = PTR_ERR(tsk);
 				goto out_flush;
 			}
 
 			get_task_struct(tsk);
-			threads[id * ncpus + n] = tsk;
+			threads[idx * ncpus + n] = tsk;
 		}
+
+		idx++;
 	}
 
 	msleep(jiffies_to_msecs(i915_selftest.timeout_jiffies));
 
 out_flush:
+	idx = 0;
 	num_waits = 0;
 	num_fences = 0;
-	for_each_engine(engine, i915, id) {
+	for_each_uabi_engine(engine, i915) {
 		for (n = 0; n < ncpus; n++) {
-			struct task_struct *tsk = threads[id * ncpus + n];
+			struct task_struct *tsk = threads[idx * ncpus + n];
 			int err;
 
 			if (!tsk)
@@ -1275,17 +1335,20 @@ out_flush:
 			put_task_struct(tsk);
 		}
 
-		num_waits += atomic_long_read(&t[id].num_waits);
-		num_fences += atomic_long_read(&t[id].num_fences);
+		num_waits += atomic_long_read(&smoke[idx].num_waits);
+		num_fences += atomic_long_read(&smoke[idx].num_fences);
+		idx++;
 	}
 	pr_info("Completed %lu waits for %lu fences across %d engines and %d cpus\n",
 		num_waits, num_fences, RUNTIME_INFO(i915)->num_engines, ncpus);
 
 	ret = igt_live_test_end(&live) ?: ret;
 out_contexts:
-	kfree(t[0].contexts);
+	kfree(smoke[0].contexts);
 out_threads:
 	kfree(threads);
+out_smoke:
+	kfree(smoke);
 out_file:
 	mock_file_free(i915, file);
 out_rpm:
-- 
cgit v1.2.3


From 1dfffa0051eae890ce36924651ecff60df5d779e Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 17 Oct 2019 18:13:52 +0200
Subject: drm/i915: Don't disable interrupts independently of the lock

The locks (active.lock and rq->lock) need to be taken with disabled
interrupts. This is done in i915_request_retire() by disabling the
interrupts independently of the locks itself.
While local_irq_disable()+spin_lock() equals spin_lock_irq() on vanilla
it does not on PREEMPT_RT.
Chris Wilson confirmed that local_irq_disable() was just introduced as
an optimisation to avoid enabling/disabling interrupts during
lock/unlock combo.

Enable/disable interrupts as part of the locking instruction.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191017161352.e5z3ugse7gxl5ari@linutronix.de
---
 drivers/gpu/drm/i915/i915_request.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index f1cadad4e81c..4575f368455d 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -206,14 +206,14 @@ static void remove_from_engine(struct i915_request *rq)
 	 * check that the rq still belongs to the newly locked engine.
 	 */
 	locked = READ_ONCE(rq->engine);
-	spin_lock(&locked->active.lock);
+	spin_lock_irq(&locked->active.lock);
 	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
 		spin_unlock(&locked->active.lock);
 		spin_lock(&engine->active.lock);
 		locked = engine;
 	}
 	list_del(&rq->sched.link);
-	spin_unlock(&locked->active.lock);
+	spin_unlock_irq(&locked->active.lock);
 }
 
 bool i915_request_retire(struct i915_request *rq)
@@ -242,8 +242,6 @@ bool i915_request_retire(struct i915_request *rq)
 				  &i915_request_timeline(rq)->requests));
 	rq->ring->head = rq->postfix;
 
-	local_irq_disable();
-
 	/*
 	 * We only loosely track inflight requests across preemption,
 	 * and so we may find ourselves attempting to retire a _completed_
@@ -252,7 +250,7 @@ bool i915_request_retire(struct i915_request *rq)
 	 */
 	remove_from_engine(rq);
 
-	spin_lock(&rq->lock);
+	spin_lock_irq(&rq->lock);
 	i915_request_mark_complete(rq);
 	if (!i915_request_signaled(rq))
 		dma_fence_signal_locked(&rq->fence);
@@ -267,9 +265,7 @@ bool i915_request_retire(struct i915_request *rq)
 		__notify_execute_cb(rq);
 	}
 	GEM_BUG_ON(!list_empty(&rq->execute_cb));
-	spin_unlock(&rq->lock);
-
-	local_irq_enable();
+	spin_unlock_irq(&rq->lock);
 
 	remove_from_client(rq);
 	list_del(&rq->link);
-- 
cgit v1.2.3


From 491381ce07ca57f68c49c79a8a43da5b60749e32 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 17 Oct 2019 09:20:46 -0600
Subject: io_uring: fix up O_NONBLOCK handling for sockets

We've got two issues with the non-regular file handling for non-blocking
IO:

1) We don't want to re-do a short read in full for a non-regular file,
   as we can't just read the data again.
2) For non-regular files that don't support non-blocking IO attempts,
   we need to punt to async context even if the file is opened as
   non-blocking. Otherwise the caller always gets -EAGAIN.

Add two new request flags to handle these cases. One is just a cache
of the inode S_ISREG() status, the other tells io_uring that we always
need to punt this request to async context, even if REQ_F_NOWAIT is set.

Cc: stable@vger.kernel.org
Reported-by: Hrvoje Zeba <zeba.hrvoje@gmail.com>
Tested-by: Hrvoje Zeba <zeba.hrvoje@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 57 +++++++++++++++++++++++++++++++++++++++------------------
 1 file changed, 39 insertions(+), 18 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index d2cb277da2f4..b7d4085d6ffd 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -322,6 +322,8 @@ struct io_kiocb {
 #define REQ_F_FAIL_LINK		256	/* fail rest of links */
 #define REQ_F_SHADOW_DRAIN	512	/* link-drain shadow req */
 #define REQ_F_TIMEOUT		1024	/* timeout request */
+#define REQ_F_ISREG		2048	/* regular file */
+#define REQ_F_MUST_PUNT		4096	/* must be punted even for NONBLOCK */
 	u64			user_data;
 	u32			result;
 	u32			sequence;
@@ -914,26 +916,26 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
 	return ret;
 }
 
-static void kiocb_end_write(struct kiocb *kiocb)
+static void kiocb_end_write(struct io_kiocb *req)
 {
-	if (kiocb->ki_flags & IOCB_WRITE) {
-		struct inode *inode = file_inode(kiocb->ki_filp);
+	/*
+	 * Tell lockdep we inherited freeze protection from submission
+	 * thread.
+	 */
+	if (req->flags & REQ_F_ISREG) {
+		struct inode *inode = file_inode(req->file);
 
-		/*
-		 * Tell lockdep we inherited freeze protection from submission
-		 * thread.
-		 */
-		if (S_ISREG(inode->i_mode))
-			__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
-		file_end_write(kiocb->ki_filp);
+		__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
 	}
+	file_end_write(req->file);
 }
 
 static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
 
-	kiocb_end_write(kiocb);
+	if (kiocb->ki_flags & IOCB_WRITE)
+		kiocb_end_write(req);
 
 	if ((req->flags & REQ_F_LINK) && res != req->result)
 		req->flags |= REQ_F_FAIL_LINK;
@@ -945,7 +947,8 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
 {
 	struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
 
-	kiocb_end_write(kiocb);
+	if (kiocb->ki_flags & IOCB_WRITE)
+		kiocb_end_write(req);
 
 	if ((req->flags & REQ_F_LINK) && res != req->result)
 		req->flags |= REQ_F_FAIL_LINK;
@@ -1059,8 +1062,17 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
 	if (!req->file)
 		return -EBADF;
 
-	if (force_nonblock && !io_file_supports_async(req->file))
-		force_nonblock = false;
+	if (S_ISREG(file_inode(req->file)->i_mode))
+		req->flags |= REQ_F_ISREG;
+
+	/*
+	 * If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
+	 * we know to async punt it even if it was opened O_NONBLOCK
+	 */
+	if (force_nonblock && !io_file_supports_async(req->file)) {
+		req->flags |= REQ_F_MUST_PUNT;
+		return -EAGAIN;
+	}
 
 	kiocb->ki_pos = READ_ONCE(sqe->off);
 	kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
@@ -1081,7 +1093,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
 		return ret;
 
 	/* don't allow async punt if RWF_NOWAIT was requested */
-	if (kiocb->ki_flags & IOCB_NOWAIT)
+	if ((kiocb->ki_flags & IOCB_NOWAIT) ||
+	    (req->file->f_flags & O_NONBLOCK))
 		req->flags |= REQ_F_NOWAIT;
 
 	if (force_nonblock)
@@ -1382,7 +1395,9 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 		 * need async punt anyway, so it's more efficient to do it
 		 * here.
 		 */
-		if (force_nonblock && ret2 > 0 && ret2 < read_size)
+		if (force_nonblock && !(req->flags & REQ_F_NOWAIT) &&
+		    (req->flags & REQ_F_ISREG) &&
+		    ret2 > 0 && ret2 < read_size)
 			ret2 = -EAGAIN;
 		/* Catch -EAGAIN return for forced non-blocking submission */
 		if (!force_nonblock || ret2 != -EAGAIN) {
@@ -1447,7 +1462,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 		 * released so that it doesn't complain about the held lock when
 		 * we return to userspace.
 		 */
-		if (S_ISREG(file_inode(file)->i_mode)) {
+		if (req->flags & REQ_F_ISREG) {
 			__sb_start_write(file_inode(file)->i_sb,
 						SB_FREEZE_WRITE, true);
 			__sb_writers_release(file_inode(file)->i_sb,
@@ -2282,7 +2297,13 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	int ret;
 
 	ret = __io_submit_sqe(ctx, req, s, force_nonblock);
-	if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
+
+	/*
+	 * We async punt it if the file wasn't marked NOWAIT, or if the file
+	 * doesn't support non-blocking read/write attempts
+	 */
+	if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) ||
+	    (req->flags & REQ_F_MUST_PUNT))) {
 		struct io_uring_sqe *sqe_copy;
 
 		sqe_copy = kmemdup(s->sqe, sizeof(*sqe_copy), GFP_KERNEL);
-- 
cgit v1.2.3


From 8b07a65ad30e5612d9590fb50468ff4fa314cfc7 Mon Sep 17 00:00:00 2001
From: yangerkun <yangerkun@huawei.com>
Date: Thu, 17 Oct 2019 12:12:35 +0800
Subject: io_uring: fix logic error in io_timeout

If ctx->cached_sq_head < nxt_sq_head, we should add UINT_MAX to tmp, not
tmp_nxt.

Fixes: 5da0fb1ab34c ("io_uring: consider the overflow of sequence for timeout req")
Signed-off-by: yangerkun <yangerkun@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index b7d4085d6ffd..1d03afd74368 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1949,7 +1949,7 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		 * once there is some timeout req still be valid.
 		 */
 		if (ctx->cached_sq_head < nxt_sq_head)
-			tmp_nxt += UINT_MAX;
+			tmp += UINT_MAX;
 
 		if (tmp >= tmp_nxt)
 			break;
-- 
cgit v1.2.3


From a50134b1983b8860e0e74e41579cbb19a7304ca7 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Thu, 17 Oct 2019 17:18:52 +0100
Subject: drm/i915: Make for_each_engine_masked work on intel_gt

Medium term goal is to eliminate the i915->engine[] array and to get there
we have recently introduced equivalent array in intel_gt. Now we need to
migrate the code further towards this state.

This next step is to eliminate usage of i915->engines[] from the
for_each_engine_masked iterator.

For this to work we also need to use engine->id as index when populating
the gt->engine[] array and adjust the default engine set indexing to use
engine->legacy_idx instead of assuming gt->engines[] indexing.

v2:
  * Populate gt->engine[] earlier.
  * Check that we don't duplicate engine->legacy_idx

v3:
  * Work around the initialization order issue between default_engines()
    and intel_engines_driver_register() which sets engine->legacy_idx for
    now. It will be fixed properly later.

v4:
  * Merge with forgotten v2.5.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191017161852.8836-1-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c  | 13 ++++++++++---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c    |  5 +++++
 drivers/gpu/drm/i915/gt/intel_engine_types.h |  1 +
 drivers/gpu/drm/i915/gt/intel_engine_user.c  | 18 +++++-------------
 drivers/gpu/drm/i915/gt/intel_gt.c           |  2 +-
 drivers/gpu/drm/i915/gt/intel_hangcheck.c    |  2 +-
 drivers/gpu/drm/i915/gt/intel_reset.c        | 12 ++++++------
 drivers/gpu/drm/i915/gvt/execlist.c          |  4 ++--
 drivers/gpu/drm/i915/gvt/scheduler.c         |  2 +-
 drivers/gpu/drm/i915/i915_active.c           |  4 ++--
 drivers/gpu/drm/i915/i915_drv.h              |  6 +++---
 11 files changed, 37 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 5d8221c7ba83..7b01f4605f21 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -203,15 +203,22 @@ static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx)
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
 
+		if (engine->legacy_idx == INVALID_ENGINE)
+			continue;
+
+		GEM_BUG_ON(engine->legacy_idx >= I915_NUM_ENGINES);
+		GEM_BUG_ON(e->engines[engine->legacy_idx]);
+
 		ce = intel_context_create(ctx, engine);
 		if (IS_ERR(ce)) {
-			__free_engines(e, id);
+			__free_engines(e, e->num_engines + 1);
 			return ERR_CAST(ce);
 		}
 
-		e->engines[id] = ce;
-		e->num_engines = id + 1;
+		e->engines[engine->legacy_idx] = ce;
+		e->num_engines = max(e->num_engines, engine->legacy_idx);
 	}
+	e->num_engines++;
 
 	return e;
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 5051a1fd2565..e514c68b0713 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -277,6 +277,9 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	BUILD_BUG_ON(MAX_ENGINE_CLASS >= BIT(GEN11_ENGINE_CLASS_WIDTH));
 	BUILD_BUG_ON(MAX_ENGINE_INSTANCE >= BIT(GEN11_ENGINE_INSTANCE_WIDTH));
 
+	if (GEM_DEBUG_WARN_ON(id >= ARRAY_SIZE(gt->engine)))
+		return -EINVAL;
+
 	if (GEM_DEBUG_WARN_ON(info->class > MAX_ENGINE_CLASS))
 		return -EINVAL;
 
@@ -293,6 +296,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	BUILD_BUG_ON(BITS_PER_TYPE(engine->mask) < I915_NUM_ENGINES);
 
 	engine->id = id;
+	engine->legacy_idx = INVALID_ENGINE;
 	engine->mask = BIT(id);
 	engine->i915 = gt->i915;
 	engine->gt = gt;
@@ -328,6 +332,7 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	intel_engine_sanitize_mmio(engine);
 
 	gt->engine_class[info->class][info->instance] = engine;
+	gt->engine[id] = engine;
 
 	intel_engine_add_user(engine);
 	gt->i915->engine[id] = engine;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 6199064f332b..3451be034caf 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -148,6 +148,7 @@ enum intel_engine_id {
 	VECS1,
 #define _VECS(n) (VECS0 + (n))
 	I915_NUM_ENGINES
+#define INVALID_ENGINE ((enum intel_engine_id)-1)
 };
 
 struct st_preempt_hang {
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c
index 77cd5de83930..7f7150a733f4 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_user.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c
@@ -160,10 +160,10 @@ static int legacy_ring_idx(const struct legacy_ring *ring)
 	};
 
 	if (GEM_DEBUG_WARN_ON(ring->class >= ARRAY_SIZE(map)))
-		return -1;
+		return INVALID_ENGINE;
 
 	if (GEM_DEBUG_WARN_ON(ring->instance >= map[ring->class].max))
-		return -1;
+		return INVALID_ENGINE;
 
 	return map[ring->class].base + ring->instance;
 }
@@ -171,23 +171,15 @@ static int legacy_ring_idx(const struct legacy_ring *ring)
 static void add_legacy_ring(struct legacy_ring *ring,
 			    struct intel_engine_cs *engine)
 {
-	int idx;
-
 	if (engine->gt != ring->gt || engine->class != ring->class) {
 		ring->gt = engine->gt;
 		ring->class = engine->class;
 		ring->instance = 0;
 	}
 
-	idx = legacy_ring_idx(ring);
-	if (unlikely(idx == -1))
-		return;
-
-	GEM_BUG_ON(idx >= ARRAY_SIZE(ring->gt->engine));
-	ring->gt->engine[idx] = engine;
-	ring->instance++;
-
-	engine->legacy_idx = idx;
+	engine->legacy_idx = legacy_ring_idx(ring);
+	if (engine->legacy_idx != INVALID_ENGINE)
+		ring->instance++;
 }
 
 void intel_engines_driver_register(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index b3619a2a5d0e..c99b6b2f38c2 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -186,7 +186,7 @@ intel_gt_clear_error_registers(struct intel_gt *gt,
 		struct intel_engine_cs *engine;
 		enum intel_engine_id id;
 
-		for_each_engine_masked(engine, i915, engine_mask, id)
+		for_each_engine_masked(engine, gt, engine_mask, id)
 			gen8_clear_engine_error_register(engine);
 	}
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_hangcheck.c b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
index c14dbeb3ccc3..b2af73984f93 100644
--- a/drivers/gpu/drm/i915/gt/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
@@ -237,7 +237,7 @@ static void hangcheck_declare_hang(struct intel_gt *gt,
 		hung &= ~stuck;
 	len = scnprintf(msg, sizeof(msg),
 			"%s on ", stuck == hung ? "no progress" : "hang");
-	for_each_engine_masked(engine, gt->i915, hung, tmp)
+	for_each_engine_masked(engine, gt, hung, tmp)
 		len += scnprintf(msg + len, sizeof(msg) - len,
 				 "%s, ", engine->name);
 	msg[len-2] = '\0';
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 477bfafdb103..b191b0745703 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -298,7 +298,7 @@ static int gen6_reset_engines(struct intel_gt *gt,
 		intel_engine_mask_t tmp;
 
 		hw_mask = 0;
-		for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
+		for_each_engine_masked(engine, gt, engine_mask, tmp) {
 			GEM_BUG_ON(engine->id >= ARRAY_SIZE(hw_engine_mask));
 			hw_mask |= hw_engine_mask[engine->id];
 		}
@@ -432,7 +432,7 @@ static int gen11_reset_engines(struct intel_gt *gt,
 		hw_mask = GEN11_GRDOM_FULL;
 	} else {
 		hw_mask = 0;
-		for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
+		for_each_engine_masked(engine, gt, engine_mask, tmp) {
 			GEM_BUG_ON(engine->id >= ARRAY_SIZE(hw_engine_mask));
 			hw_mask |= hw_engine_mask[engine->id];
 			ret = gen11_lock_sfc(engine, &hw_mask);
@@ -451,7 +451,7 @@ sfc_unlock:
 	 * expiration).
 	 */
 	if (engine_mask != ALL_ENGINES)
-		for_each_engine_masked(engine, gt->i915, engine_mask, tmp)
+		for_each_engine_masked(engine, gt, engine_mask, tmp)
 			gen11_unlock_sfc(engine);
 
 	return ret;
@@ -510,7 +510,7 @@ static int gen8_reset_engines(struct intel_gt *gt,
 	intel_engine_mask_t tmp;
 	int ret;
 
-	for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
+	for_each_engine_masked(engine, gt, engine_mask, tmp) {
 		ret = gen8_engine_reset_prepare(engine);
 		if (ret && !reset_non_ready)
 			goto skip_reset;
@@ -536,7 +536,7 @@ static int gen8_reset_engines(struct intel_gt *gt,
 		ret = gen6_reset_engines(gt, engine_mask, retry);
 
 skip_reset:
-	for_each_engine_masked(engine, gt->i915, engine_mask, tmp)
+	for_each_engine_masked(engine, gt, engine_mask, tmp)
 		gen8_engine_reset_cancel(engine);
 
 	return ret;
@@ -1206,7 +1206,7 @@ void intel_gt_handle_error(struct intel_gt *gt,
 	 * single reset fails.
 	 */
 	if (intel_has_reset_engine(gt) && !intel_gt_is_wedged(gt)) {
-		for_each_engine_masked(engine, gt->i915, engine_mask, tmp) {
+		for_each_engine_masked(engine, gt, engine_mask, tmp) {
 			BUILD_BUG_ON(I915_RESET_MODESET >= I915_RESET_ENGINE);
 			if (test_and_set_bit(I915_RESET_ENGINE + engine->id,
 					     &gt->reset.flags))
diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
index f21b8fb5b37e..d6e7a1189bad 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.c
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -534,7 +534,7 @@ static void clean_execlist(struct intel_vgpu *vgpu,
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	intel_engine_mask_t tmp;
 
-	for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
+	for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp) {
 		kfree(s->ring_scan_buffer[engine->id]);
 		s->ring_scan_buffer[engine->id] = NULL;
 		s->ring_scan_buffer_size[engine->id] = 0;
@@ -548,7 +548,7 @@ static void reset_execlist(struct intel_vgpu *vgpu,
 	struct intel_engine_cs *engine;
 	intel_engine_mask_t tmp;
 
-	for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
+	for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp)
 		init_vgpu_execlist(vgpu, engine->id);
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 6850f1f40241..9ebb2534558b 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -887,7 +887,7 @@ void intel_vgpu_clean_workloads(struct intel_vgpu *vgpu,
 	intel_engine_mask_t tmp;
 
 	/* free the unsubmited workloads in the queues. */
-	for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
+	for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp) {
 		list_for_each_entry_safe(pos, n,
 			&s->workload_q_head[engine->id], list) {
 			list_del_init(&pos->list);
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index aa37c07004b9..7927b1a0c7a6 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -590,8 +590,8 @@ match:
 int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 					    struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *i915 = engine->i915;
 	intel_engine_mask_t tmp, mask = engine->mask;
+	struct intel_gt *gt = engine->gt;
 	struct llist_node *pos, *next;
 	int err;
 
@@ -603,7 +603,7 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 	 * We can then use the preallocated nodes in
 	 * i915_active_acquire_barrier()
 	 */
-	for_each_engine_masked(engine, i915, mask, tmp) {
+	for_each_engine_masked(engine, gt, mask, tmp) {
 		u64 idx = engine->kernel_context->timeline->fence_context;
 		struct active_node *node;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 88956f37d96c..40e923b0c2c8 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1415,10 +1415,10 @@ static inline struct drm_i915_private *pdev_to_i915(struct pci_dev *pdev)
 		for_each_if ((engine__) = (dev_priv__)->engine[(id__)])
 
 /* Iterator over subset of engines selected by mask */
-#define for_each_engine_masked(engine__, dev_priv__, mask__, tmp__) \
-	for ((tmp__) = (mask__) & INTEL_INFO(dev_priv__)->engine_mask; \
+#define for_each_engine_masked(engine__, gt__, mask__, tmp__) \
+	for ((tmp__) = (mask__) & INTEL_INFO((gt__)->i915)->engine_mask; \
 	     (tmp__) ? \
-	     ((engine__) = (dev_priv__)->engine[__mask_next_bit(tmp__)]), 1 : \
+	     ((engine__) = (gt__)->engine[__mask_next_bit(tmp__)]), 1 : \
 	     0;)
 
 #define rb_to_uabi_engine(rb) \
-- 
cgit v1.2.3


From 5d904e3c5d40c3939d53659e9c473500c3c24039 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Thu, 17 Oct 2019 10:45:00 +0100
Subject: drm/i915: Pass in intel_gt at some for_each_engine sites

Where the function, or code segment, operates on intel_gt, we need to
start passing it instead of i915 to for_each_engine(_masked).

This is another partial step in migration of i915->engines[] to
gt->engines[].

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191017094500.21831-2-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/gt/intel_engine_cs.c         |  4 +--
 drivers/gpu/drm/i915/gt/intel_gt.c                |  2 +-
 drivers/gpu/drm/i915/gt/intel_gt_pm.c             |  8 ++---
 drivers/gpu/drm/i915/gt/intel_gt_requests.c       |  2 +-
 drivers/gpu/drm/i915/gt/intel_hangcheck.c         |  4 +--
 drivers/gpu/drm/i915/gt/intel_reset.c             | 18 +++++------
 drivers/gpu/drm/i915/gt/selftest_context.c        |  6 ++--
 drivers/gpu/drm/i915/gt/selftest_engine_pm.c      |  2 +-
 drivers/gpu/drm/i915/gt/selftest_hangcheck.c      | 20 ++++++------
 drivers/gpu/drm/i915/gt/selftest_lrc.c            | 38 +++++++++++------------
 drivers/gpu/drm/i915/gt/selftest_reset.c          |  2 +-
 drivers/gpu/drm/i915/gt/selftest_timeline.c       |  8 ++---
 drivers/gpu/drm/i915/gt/selftest_workarounds.c    | 10 +++---
 drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c |  6 ++--
 drivers/gpu/drm/i915/selftests/igt_reset.c        |  4 +--
 15 files changed, 67 insertions(+), 67 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index e514c68b0713..051734c9b733 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1123,7 +1123,7 @@ bool intel_engines_are_idle(struct intel_gt *gt)
 	if (!READ_ONCE(gt->awake))
 		return true;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		if (!intel_engine_is_idle(engine))
 			return false;
 	}
@@ -1136,7 +1136,7 @@ void intel_engines_reset_default_submission(struct intel_gt *gt)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, gt->i915, id)
+	for_each_engine(engine, gt, id)
 		engine->set_default_submission(engine);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index c99b6b2f38c2..1c4b6c9642ad 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -197,7 +197,7 @@ static void gen6_check_faults(struct intel_gt *gt)
 	enum intel_engine_id id;
 	u32 fault;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		fault = GEN6_RING_FAULT_REG_READ(engine);
 		if (fault & RING_FAULT_VALID) {
 			DRM_DEBUG_DRIVER("Unexpected fault\n"
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index bd1bd3e00a94..b866d5b1eee0 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -136,16 +136,16 @@ void intel_gt_sanitize(struct intel_gt *gt, bool force)
 
 	intel_uc_sanitize(&gt->uc);
 
-	for_each_engine(engine, gt->i915, id)
+	for_each_engine(engine, gt, id)
 		if (engine->reset.prepare)
 			engine->reset.prepare(engine);
 
 	if (reset_engines(gt) || force) {
-		for_each_engine(engine, gt->i915, id)
+		for_each_engine(engine, gt, id)
 			__intel_engine_reset(engine, false);
 	}
 
-	for_each_engine(engine, gt->i915, id)
+	for_each_engine(engine, gt, id)
 		if (engine->reset.finish)
 			engine->reset.finish(engine);
 }
@@ -177,7 +177,7 @@ int intel_gt_resume(struct intel_gt *gt)
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 	intel_rc6_sanitize(&gt->rc6);
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
 
 		intel_engine_pm_get(engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index cbb4069b11e1..b73229a84d85 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -25,7 +25,7 @@ static void flush_submission(struct intel_gt *gt)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, gt->i915, id)
+	for_each_engine(engine, gt, id)
 		intel_engine_flush_submission(engine);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_hangcheck.c b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
index b2af73984f93..0fdef00af9e4 100644
--- a/drivers/gpu/drm/i915/gt/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
@@ -281,7 +281,7 @@ static void hangcheck_elapsed(struct work_struct *work)
 	 */
 	intel_uncore_arm_unclaimed_mmio_detection(gt->uncore);
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct hangcheck hc;
 
 		intel_engine_breadcrumbs_irq(engine);
@@ -303,7 +303,7 @@ static void hangcheck_elapsed(struct work_struct *work)
 	if (GEM_SHOW_DEBUG() && (hung | stuck)) {
 		struct drm_printer p = drm_debug_printer("hangcheck");
 
-		for_each_engine(engine, gt->i915, id) {
+		for_each_engine(engine, gt, id) {
 			if (intel_engine_is_idle(engine))
 				continue;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index b191b0745703..bf8d1ed4b1d8 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -682,7 +682,7 @@ static intel_engine_mask_t reset_prepare(struct intel_gt *gt)
 	intel_engine_mask_t awake = 0;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		if (intel_engine_pm_get_if_awake(engine))
 			awake |= engine->mask;
 		reset_prepare_engine(engine);
@@ -712,7 +712,7 @@ static int gt_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask)
 	if (err)
 		return err;
 
-	for_each_engine(engine, gt->i915, id)
+	for_each_engine(engine, gt, id)
 		__intel_engine_reset(engine, stalled_mask & engine->mask);
 
 	i915_gem_restore_fences(gt->ggtt);
@@ -733,7 +733,7 @@ static void reset_finish(struct intel_gt *gt, intel_engine_mask_t awake)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		reset_finish_engine(engine);
 		if (awake & engine->mask)
 			intel_engine_pm_put(engine);
@@ -769,7 +769,7 @@ static void __intel_gt_set_wedged(struct intel_gt *gt)
 	if (GEM_SHOW_DEBUG() && !intel_engines_are_idle(gt)) {
 		struct drm_printer p = drm_debug_printer(__func__);
 
-		for_each_engine(engine, gt->i915, id)
+		for_each_engine(engine, gt, id)
 			intel_engine_dump(engine, &p, "%s\n", engine->name);
 	}
 
@@ -786,7 +786,7 @@ static void __intel_gt_set_wedged(struct intel_gt *gt)
 	if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display)
 		__intel_gt_reset(gt, ALL_ENGINES);
 
-	for_each_engine(engine, gt->i915, id)
+	for_each_engine(engine, gt, id)
 		engine->submit_request = nop_submit_request;
 
 	/*
@@ -798,7 +798,7 @@ static void __intel_gt_set_wedged(struct intel_gt *gt)
 	set_bit(I915_WEDGED, &gt->reset.flags);
 
 	/* Mark all executing requests as skipped */
-	for_each_engine(engine, gt->i915, id)
+	for_each_engine(engine, gt, id)
 		engine->cancel_requests(engine);
 
 	reset_finish(gt, awake);
@@ -934,7 +934,7 @@ static int resume(struct intel_gt *gt)
 	enum intel_engine_id id;
 	int ret;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		ret = engine->resume(engine);
 		if (ret)
 			return ret;
@@ -1234,7 +1234,7 @@ void intel_gt_handle_error(struct intel_gt *gt,
 	synchronize_rcu_expedited();
 
 	/* Prevent any other reset-engine attempt. */
-	for_each_engine(engine, gt->i915, tmp) {
+	for_each_engine(engine, gt, tmp) {
 		while (test_and_set_bit(I915_RESET_ENGINE + engine->id,
 					&gt->reset.flags))
 			wait_on_bit(&gt->reset.flags,
@@ -1244,7 +1244,7 @@ void intel_gt_handle_error(struct intel_gt *gt,
 
 	intel_gt_reset_global(gt, engine_mask, msg);
 
-	for_each_engine(engine, gt->i915, tmp)
+	for_each_engine(engine, gt, tmp)
 		clear_bit_unlock(I915_RESET_ENGINE + engine->id,
 				 &gt->reset.flags);
 	clear_bit_unlock(I915_RESET_BACKOFF, &gt->reset.flags);
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index 7c838a57e174..f63a26a3e620 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -159,7 +159,7 @@ static int live_context_size(void *arg)
 	if (IS_ERR(fixme))
 		return PTR_ERR(fixme);
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct {
 			struct drm_i915_gem_object *state;
 			void *pinned;
@@ -305,7 +305,7 @@ static int live_active_context(void *arg)
 		goto out_file;
 	}
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		err = __live_active_context(engine, fixme);
 		if (err)
 			break;
@@ -415,7 +415,7 @@ static int live_remote_context(void *arg)
 		goto out_file;
 	}
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		err = __live_remote_context(engine, fixme);
 		if (err)
 			break;
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
index 3a1419376912..20b9c83f43ad 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
@@ -25,7 +25,7 @@ static int live_engine_pm(void *arg)
 	}
 
 	GEM_BUG_ON(intel_gt_pm_is_awake(gt));
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		const typeof(*igt_atomic_phases) *p;
 
 		for (p = igt_atomic_phases; p->name; p++) {
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 569a4105d49e..8e0016464325 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -323,7 +323,7 @@ static int igt_hang_sanitycheck(void *arg)
 	if (err)
 		return err;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct intel_wedge_me w;
 		long timeout;
 
@@ -400,7 +400,7 @@ static int igt_reset_nop(void *arg)
 	reset_count = i915_reset_count(global);
 	count = 0;
 	do {
-		for_each_engine(engine, gt->i915, id) {
+		for_each_engine(engine, gt, id) {
 			int i;
 
 			for (i = 0; i < 16; i++) {
@@ -471,7 +471,7 @@ static int igt_reset_nop_engine(void *arg)
 	}
 
 	i915_gem_context_clear_bannable(ctx);
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		unsigned int reset_count, reset_engine_count;
 		unsigned int count;
 		IGT_TIMEOUT(end_time);
@@ -560,7 +560,7 @@ static int __igt_reset_engine(struct intel_gt *gt, bool active)
 			return err;
 	}
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		unsigned int reset_count, reset_engine_count;
 		IGT_TIMEOUT(end_time);
 
@@ -782,7 +782,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 			h.ctx->sched.priority = 1024;
 	}
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct active_engine threads[I915_NUM_ENGINES] = {};
 		unsigned long device = i915_reset_count(global);
 		unsigned long count = 0, reported;
@@ -800,7 +800,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 		}
 
 		memset(threads, 0, sizeof(threads));
-		for_each_engine(other, gt->i915, tmp) {
+		for_each_engine(other, gt, tmp) {
 			struct task_struct *tsk;
 
 			threads[tmp].resets =
@@ -914,7 +914,7 @@ static int __igt_reset_engines(struct intel_gt *gt,
 		}
 
 unwind:
-		for_each_engine(other, gt->i915, tmp) {
+		for_each_engine(other, gt, tmp) {
 			int ret;
 
 			if (!threads[tmp].task)
@@ -1335,7 +1335,7 @@ static int wait_for_others(struct intel_gt *gt,
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		if (engine == exclude)
 			continue;
 
@@ -1363,7 +1363,7 @@ static int igt_reset_queue(void *arg)
 	if (err)
 		goto unlock;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct i915_request *prev;
 		IGT_TIMEOUT(end_time);
 		unsigned int count;
@@ -1651,7 +1651,7 @@ static int igt_reset_engines_atomic(void *arg)
 		struct intel_engine_cs *engine;
 		enum intel_engine_id id;
 
-		for_each_engine(engine, gt->i915, id) {
+		for_each_engine(engine, gt, id) {
 			err = igt_atomic_reset_engine(engine, p);
 			if (err)
 				goto out;
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 2868371c609e..007d6203fe0e 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -123,7 +123,7 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 		goto err_spin;
 
 	err = 0;
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct intel_context *ce[2] = {};
 		struct i915_request *rq[2];
 		struct igt_live_test t;
@@ -384,7 +384,7 @@ slice_semaphore_queue(struct intel_engine_cs *outer,
 		return PTR_ERR(head);
 
 	i915_request_get(head);
-	for_each_engine(engine, outer->i915, id) {
+	for_each_engine(engine, outer->gt, id) {
 		for (i = 0; i < count; i++) {
 			struct i915_request *rq;
 
@@ -456,7 +456,7 @@ static int live_timeslice_preempt(void *arg)
 		struct intel_engine_cs *engine;
 		enum intel_engine_id id;
 
-		for_each_engine(engine, gt->i915, id) {
+		for_each_engine(engine, gt, id) {
 			if (!intel_engine_has_preemption(engine))
 				continue;
 
@@ -532,7 +532,7 @@ static int live_busywait_preempt(void *arg)
 	if (err)
 		goto err_map;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct i915_request *lo, *hi;
 		struct igt_live_test t;
 		u32 *cs;
@@ -708,7 +708,7 @@ static int live_preempt(void *arg)
 	ctx_lo->sched.priority =
 		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct igt_live_test t;
 		struct i915_request *rq;
 
@@ -804,7 +804,7 @@ static int live_late_preempt(void *arg)
 	/* Make sure ctx_lo stays before ctx_hi until we trigger preemption. */
 	ctx_lo->sched.priority = I915_USER_PRIORITY(1);
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct igt_live_test t;
 		struct i915_request *rq;
 
@@ -929,7 +929,7 @@ static int live_nopreempt(void *arg)
 		goto err_client_a;
 	b.ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX);
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct i915_request *rq_a, *rq_b;
 
 		if (!intel_engine_has_preemption(engine))
@@ -1040,7 +1040,7 @@ static int live_suppress_self_preempt(void *arg)
 	if (preempt_client_init(gt, &b))
 		goto err_client_a;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct i915_request *rq_a, *rq_b;
 		int depth;
 
@@ -1207,7 +1207,7 @@ static int live_suppress_wait_preempt(void *arg)
 	if (preempt_client_init(gt, &client[3])) /* bystander */
 		goto err_client_2;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		int depth;
 
 		if (!intel_engine_has_preemption(engine))
@@ -1318,7 +1318,7 @@ static int live_chain_preempt(void *arg)
 	if (preempt_client_init(gt, &lo))
 		goto err_client_hi;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct i915_sched_attr attr = {
 			.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX),
 		};
@@ -1467,7 +1467,7 @@ static int live_preempt_hang(void *arg)
 	ctx_lo->sched.priority =
 		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct i915_request *rq;
 
 		if (!intel_engine_has_preemption(engine))
@@ -1656,7 +1656,7 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 	unsigned long count;
 	int err = 0;
 
-	for_each_engine(engine, smoke->gt->i915, id) {
+	for_each_engine(engine, smoke->gt, id) {
 		arg[id] = *smoke;
 		arg[id].engine = engine;
 		if (!(flags & BATCH))
@@ -1673,7 +1673,7 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 	}
 
 	count = 0;
-	for_each_engine(engine, smoke->gt->i915, id) {
+	for_each_engine(engine, smoke->gt, id) {
 		int status;
 
 		if (IS_ERR_OR_NULL(tsk[id]))
@@ -1702,7 +1702,7 @@ static int smoke_random(struct preempt_smoke *smoke, unsigned int flags)
 
 	count = 0;
 	do {
-		for_each_engine(smoke->engine, smoke->gt->i915, id) {
+		for_each_engine(smoke->engine, smoke->gt, id) {
 			struct i915_gem_context *ctx = smoke_context(smoke);
 			int err;
 
@@ -1937,7 +1937,7 @@ static int live_virtual_engine(void *arg)
 	if (USES_GUC_SUBMISSION(gt->i915))
 		return 0;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		err = nop_virtual_engine(gt, &engine, 1, 1, 0);
 		if (err) {
 			pr_err("Failed to wrap engine %s: err=%d\n",
@@ -2270,7 +2270,7 @@ static int bond_virtual_engine(struct intel_gt *gt,
 
 	err = 0;
 	rq[0] = ERR_PTR(-ENOMEM);
-	for_each_engine(master, gt->i915, id) {
+	for_each_engine(master, gt, id) {
 		struct i915_sw_fence fence = {};
 
 		if (master->class == class)
@@ -2508,7 +2508,7 @@ static int live_lrc_layout(void *arg)
 		return -ENOMEM;
 
 	err = 0;
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		u32 *hw, *lrc;
 		int dw;
 
@@ -2701,7 +2701,7 @@ static int live_lrc_state(void *arg)
 		goto out_close;
 	}
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		err = __live_lrc_state(fixme, engine, scratch);
 		if (err)
 			break;
@@ -2844,7 +2844,7 @@ static int live_gpr_clear(void *arg)
 		goto out_close;
 	}
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		err = __live_gpr_clear(fixme, engine, scratch);
 		if (err)
 			break;
diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c
index 419b38fa7828..6efb9221b7fa 100644
--- a/drivers/gpu/drm/i915/gt/selftest_reset.c
+++ b/drivers/gpu/drm/i915/gt/selftest_reset.c
@@ -125,7 +125,7 @@ static int igt_atomic_engine_reset(void *arg)
 	if (!igt_force_reset(gt))
 		goto out_unlock;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		tasklet_disable_nosync(&engine->execlists.tasklet);
 		intel_engine_pm_get(engine);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index 473a56b0ae46..dac86f699a4c 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -519,7 +519,7 @@ static int live_hwsp_engine(void *arg)
 		return -ENOMEM;
 
 	count = 0;
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		if (!intel_engine_can_store_dword(engine))
 			continue;
 
@@ -594,7 +594,7 @@ static int live_hwsp_alternate(void *arg)
 
 	count = 0;
 	for (n = 0; n < NUM_TIMELINES; n++) {
-		for_each_engine(engine, gt->i915, id) {
+		for_each_engine(engine, gt, id) {
 			struct intel_timeline *tl;
 			struct i915_request *rq;
 
@@ -666,7 +666,7 @@ static int live_hwsp_wrap(void *arg)
 	if (err)
 		goto out_free;
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		const u32 *hwsp_seqno[2];
 		struct i915_request *rq;
 		u32 seqno[2];
@@ -766,7 +766,7 @@ static int live_hwsp_recycle(void *arg)
 	 */
 
 	count = 0;
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		IGT_TIMEOUT(end_time);
 
 		if (!intel_engine_can_store_dword(engine))
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index 8856c6c46cc4..ef02920cec29 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -69,7 +69,7 @@ reference_lists_init(struct intel_gt *gt, struct wa_lists *lists)
 	gt_init_workarounds(gt->i915, &lists->gt_wa_list);
 	wa_init_finish(&lists->gt_wa_list);
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct i915_wa_list *wal = &lists->engine[id].wa_list;
 
 		wa_init_start(wal, "REF", engine->name);
@@ -88,7 +88,7 @@ reference_lists_fini(struct intel_gt *gt, struct wa_lists *lists)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, gt->i915, id)
+	for_each_engine(engine, gt, id)
 		intel_wa_list_free(&lists->engine[id].wa_list);
 
 	intel_wa_list_free(&lists->gt_wa_list);
@@ -726,7 +726,7 @@ static int live_dirty_whitelist(void *arg)
 		goto out_file;
 	}
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		if (engine->whitelist.count == 0)
 			continue;
 
@@ -750,7 +750,7 @@ static int live_reset_whitelist(void *arg)
 	/* If we reset the gpu, we should not lose the RING_NONPRIV */
 	igt_global_reset_lock(gt);
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		if (engine->whitelist.count == 0)
 			continue;
 
@@ -1048,7 +1048,7 @@ static int live_isolated_whitelist(void *arg)
 		i915_vm_put(vm);
 	}
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		if (!engine->kernel_context->vm)
 			continue;
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 849a44add424..009e54a3764f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1020,7 +1020,7 @@ static void guc_interrupts_capture(struct intel_gt *gt)
 	 * to GuC
 	 */
 	irqs = _MASKED_BIT_ENABLE(GFX_INTERRUPT_STEERING);
-	for_each_engine(engine, gt->i915, id)
+	for_each_engine(engine, gt, id)
 		ENGINE_WRITE(engine, RING_MODE_GEN7, irqs);
 
 	/* route USER_INTERRUPT to Host, all others are sent to GuC. */
@@ -1068,7 +1068,7 @@ static void guc_interrupts_release(struct intel_gt *gt)
 	 */
 	irqs = _MASKED_FIELD(GFX_FORWARD_VBLANK_MASK, GFX_FORWARD_VBLANK_NEVER);
 	irqs |= _MASKED_BIT_DISABLE(GFX_INTERRUPT_STEERING);
-	for_each_engine(engine, gt->i915, id)
+	for_each_engine(engine, gt, id)
 		ENGINE_WRITE(engine, RING_MODE_GEN7, irqs);
 
 	/* route all GT interrupts to the host */
@@ -1151,7 +1151,7 @@ int intel_guc_submission_enable(struct intel_guc *guc)
 	/* Take over from manual control of ELSP (execlists) */
 	guc_interrupts_capture(gt);
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		engine->set_default_submission = guc_set_default_submission;
 		engine->set_default_submission(engine);
 	}
diff --git a/drivers/gpu/drm/i915/selftests/igt_reset.c b/drivers/gpu/drm/i915/selftests/igt_reset.c
index 7ec8f8b049c6..9f8590b868a9 100644
--- a/drivers/gpu/drm/i915/selftests/igt_reset.c
+++ b/drivers/gpu/drm/i915/selftests/igt_reset.c
@@ -22,7 +22,7 @@ void igt_global_reset_lock(struct intel_gt *gt)
 		wait_event(gt->reset.queue,
 			   !test_bit(I915_RESET_BACKOFF, &gt->reset.flags));
 
-	for_each_engine(engine, gt->i915, id) {
+	for_each_engine(engine, gt, id) {
 		while (test_and_set_bit(I915_RESET_ENGINE + id,
 					&gt->reset.flags))
 			wait_on_bit(&gt->reset.flags, I915_RESET_ENGINE + id,
@@ -35,7 +35,7 @@ void igt_global_reset_unlock(struct intel_gt *gt)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, gt->i915, id)
+	for_each_engine(engine, gt, id)
 		clear_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 
 	clear_bit(I915_RESET_BACKOFF, &gt->reset.flags);
-- 
cgit v1.2.3


From 8b95599c55ed24b36cf44a4720067cfe67edbcb4 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Wed, 16 Oct 2019 15:35:06 +0200
Subject: net: phy: micrel: Discern KSZ8051 and KSZ8795 PHYs

The KSZ8051 PHY and the KSZ8794/KSZ8795/KSZ8765 switch share exactly the
same PHY ID. Since KSZ8051 is higher in the ksphy_driver[] list of PHYs
in the micrel PHY driver, it is used even with the KSZ87xx switch. This
is wrong, since the KSZ8051 configures registers of the PHY which are
not present on the simplified KSZ87xx switch PHYs and misconfigures
other registers of the KSZ87xx switch PHYs.

Fortunatelly, it is possible to tell apart the KSZ8051 PHY from the
KSZ87xx switch by checking the Basic Status register Bit 0, which is
read-only and indicates presence of the Extended Capability Registers.
The KSZ8051 PHY has those registers while the KSZ87xx switch does not.

This patch implements simple check for the presence of this bit for
both the KSZ8051 PHY and KSZ87xx switch, to let both use the correct
PHY driver instance.

Fixes: 9d162ed69f51 ("net: phy: micrel: add support for KSZ8795")
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: David S. Miller <davem@davemloft.net>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: George McCollister <george.mccollister@gmail.com>
Cc: Heiner Kallweit <hkallweit1@gmail.com>
Cc: Sean Nyekjaer <sean.nyekjaer@prevas.dk>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c | 40 ++++++++++++++++++++++++++++++++++++----
 1 file changed, 36 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 2fea5541c35a..a0444e28c6e7 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -341,6 +341,35 @@ static int ksz8041_config_aneg(struct phy_device *phydev)
 	return genphy_config_aneg(phydev);
 }
 
+static int ksz8051_ksz8795_match_phy_device(struct phy_device *phydev,
+					    const u32 ksz_phy_id)
+{
+	int ret;
+
+	if ((phydev->phy_id & MICREL_PHY_ID_MASK) != ksz_phy_id)
+		return 0;
+
+	ret = phy_read(phydev, MII_BMSR);
+	if (ret < 0)
+		return ret;
+
+	/* KSZ8051 PHY and KSZ8794/KSZ8795/KSZ8765 switch share the same
+	 * exact PHY ID. However, they can be told apart by the extended
+	 * capability registers presence. The KSZ8051 PHY has them while
+	 * the switch does not.
+	 */
+	ret &= BMSR_ERCAP;
+	if (ksz_phy_id == PHY_ID_KSZ8051)
+		return ret;
+	else
+		return !ret;
+}
+
+static int ksz8051_match_phy_device(struct phy_device *phydev)
+{
+	return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ8051);
+}
+
 static int ksz8081_config_init(struct phy_device *phydev)
 {
 	/* KSZPHY_OMSO_FACTORY_TEST is set at de-assertion of the reset line
@@ -364,6 +393,11 @@ static int ksz8061_config_init(struct phy_device *phydev)
 	return kszphy_config_init(phydev);
 }
 
+static int ksz8795_match_phy_device(struct phy_device *phydev)
+{
+	return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ8795);
+}
+
 static int ksz9021_load_values_from_of(struct phy_device *phydev,
 				       const struct device_node *of_node,
 				       u16 reg,
@@ -1017,8 +1051,6 @@ static struct phy_driver ksphy_driver[] = {
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
-	.phy_id		= PHY_ID_KSZ8051,
-	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ8051",
 	/* PHY_BASIC_FEATURES */
 	.driver_data	= &ksz8051_type,
@@ -1029,6 +1061,7 @@ static struct phy_driver ksphy_driver[] = {
 	.get_sset_count = kszphy_get_sset_count,
 	.get_strings	= kszphy_get_strings,
 	.get_stats	= kszphy_get_stats,
+	.match_phy_device = ksz8051_match_phy_device,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
@@ -1141,13 +1174,12 @@ static struct phy_driver ksphy_driver[] = {
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
-	.phy_id		= PHY_ID_KSZ8795,
-	.phy_id_mask	= MICREL_PHY_ID_MASK,
 	.name		= "Micrel KSZ8795",
 	/* PHY_BASIC_FEATURES */
 	.config_init	= kszphy_config_init,
 	.config_aneg	= ksz8873mll_config_aneg,
 	.read_status	= ksz8873mll_read_status,
+	.match_phy_device = ksz8795_match_phy_device,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
-- 
cgit v1.2.3


From 1d951ba3da67bbc7a9b0e05987e09552c2060e18 Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Wed, 16 Oct 2019 15:35:07 +0200
Subject: net: phy: micrel: Update KSZ87xx PHY name

The KSZ8795 PHY ID is in fact used by KSZ8794/KSZ8795/KSZ8765 switches.
Update the PHY ID and name to reflect that, as this family of switches
is commonly refered to as KSZ87xx

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: David S. Miller <davem@davemloft.net>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: George McCollister <george.mccollister@gmail.com>
Cc: Heiner Kallweit <hkallweit1@gmail.com>
Cc: Sean Nyekjaer <sean.nyekjaer@prevas.dk>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <woojung.huh@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/micrel.c   | 4 ++--
 include/linux/micrel_phy.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index a0444e28c6e7..63dedec0433d 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -395,7 +395,7 @@ static int ksz8061_config_init(struct phy_device *phydev)
 
 static int ksz8795_match_phy_device(struct phy_device *phydev)
 {
-	return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ8795);
+	return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ87XX);
 }
 
 static int ksz9021_load_values_from_of(struct phy_device *phydev,
@@ -1174,7 +1174,7 @@ static struct phy_driver ksphy_driver[] = {
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 }, {
-	.name		= "Micrel KSZ8795",
+	.name		= "Micrel KSZ87XX Switch",
 	/* PHY_BASIC_FEATURES */
 	.config_init	= kszphy_config_init,
 	.config_aneg	= ksz8873mll_config_aneg,
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index ad24554f11f9..75f880c25bb8 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -31,7 +31,7 @@
 #define PHY_ID_KSZ886X		0x00221430
 #define PHY_ID_KSZ8863		0x00221435
 
-#define PHY_ID_KSZ8795		0x00221550
+#define PHY_ID_KSZ87XX		0x00221550
 
 #define	PHY_ID_KSZ9477		0x00221631
 
-- 
cgit v1.2.3


From 595e0651d0296bad2491a4a29a7a43eae6328b02 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Wed, 16 Oct 2019 20:52:09 +0200
Subject: ipv4: Return -ENETUNREACH if we can't create route but saddr is valid

...instead of -EINVAL. An issue was found with older kernel versions
while unplugging a NFS client with pending RPCs, and the wrong error
code here prevented it from recovering once link is back up with a
configured address.

Incidentally, this is not an issue anymore since commit 4f8943f80883
("SUNRPC: Replace direct task wakeups from softirq context"), included
in 5.2-rc7, had the effect of decoupling the forwarding of this error
by using SO_ERROR in xs_wake_error(), as pointed out by Benjamin
Coddington.

To the best of my knowledge, this isn't currently causing any further
issue, but the error code doesn't look appropriate anyway, and we
might hit this in other paths as well.

In detail, as analysed by Gonzalo Siero, once the route is deleted
because the interface is down, and can't be resolved and we return
-EINVAL here, this ends up, courtesy of inet_sk_rebuild_header(),
as the socket error seen by tcp_write_err(), called by
tcp_retransmit_timer().

In turn, tcp_write_err() indirectly calls xs_error_report(), which
wakes up the RPC pending tasks with a status of -EINVAL. This is then
seen by call_status() in the SUN RPC implementation, which aborts the
RPC call calling rpc_exit(), instead of handling this as a
potentially temporary condition, i.e. as a timeout.

Return -EINVAL only if the input parameters passed to
ip_route_output_key_hash_rcu() are actually invalid (this is the case
if the specified source address is multicast, limited broadcast or
all zeroes), but return -ENETUNREACH in all cases where, at the given
moment, the given source address doesn't allow resolving the route.

While at it, drop the initialisation of err to -ENETUNREACH, which
was added to __ip_route_output_key() back then by commit
0315e3827048 ("net: Fix behaviour of unreachable, blackhole and
prohibit routes"), but actually had no effect, as it was, and is,
overwritten by the fib_lookup() return code assignment, and anyway
ignored in all other branches, including the if (fl4->saddr) one:
I find this rather confusing, as it would look like -ENETUNREACH is
the "default" error, while that statement has no effect.

Also note that after commit fc75fc8339e7 ("ipv4: dont create routes
on down devices"), we would get -ENETUNREACH if the device is down,
but -EINVAL if the source address is specified and we can't resolve
the route, and this appears to be rather inconsistent.

Reported-by: Stefan Walter <walteste@inf.ethz.ch>
Analysed-by: Benjamin Coddington <bcodding@redhat.com>
Analysed-by: Gonzalo Siero <gsierohu@redhat.com>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 14654876127e..5bc172abd143 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2470,14 +2470,17 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
 	int orig_oif = fl4->flowi4_oif;
 	unsigned int flags = 0;
 	struct rtable *rth;
-	int err = -ENETUNREACH;
+	int err;
 
 	if (fl4->saddr) {
-		rth = ERR_PTR(-EINVAL);
 		if (ipv4_is_multicast(fl4->saddr) ||
 		    ipv4_is_lbcast(fl4->saddr) ||
-		    ipv4_is_zeronet(fl4->saddr))
+		    ipv4_is_zeronet(fl4->saddr)) {
+			rth = ERR_PTR(-EINVAL);
 			goto out;
+		}
+
+		rth = ERR_PTR(-ENETUNREACH);
 
 		/* I removed check for oif == dev_out->oif here.
 		   It was wrong for two reasons:
-- 
cgit v1.2.3


From 5018c59607a511cdee743b629c76206d9c9e6d7b Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Wed, 16 Oct 2019 12:03:15 -0700
Subject: ipv4: fix race condition between route lookup and invalidation

Jesse and Ido reported the following race condition:
<CPU A, t0> - Received packet A is forwarded and cached dst entry is
taken from the nexthop ('nhc->nhc_rth_input'). Calls skb_dst_set()

<t1> - Given Jesse has busy routers ("ingesting full BGP routing tables
from multiple ISPs"), route is added / deleted and rt_cache_flush() is
called

<CPU B, t2> - Received packet B tries to use the same cached dst entry
from t0, but rt_cache_valid() is no longer true and it is replaced in
rt_cache_route() by the newer one. This calls dst_dev_put() on the
original dst entry which assigns the blackhole netdev to 'dst->dev'

<CPU A, t3> - dst_input(skb) is called on packet A and it is dropped due
to 'dst->dev' being the blackhole netdev

There are 2 issues in the v4 routing code:
1. A per-netns counter is used to do the validation of the route. That
means whenever a route is changed in the netns, users of all routes in
the netns needs to redo lookup. v6 has an implementation of only
updating fn_sernum for routes that are affected.
2. When rt_cache_valid() returns false, rt_cache_route() is called to
throw away the current cache, and create a new one. This seems
unnecessary because as long as this route does not change, the route
cache does not need to be recreated.

To fully solve the above 2 issues, it probably needs quite some code
changes and requires careful testing, and does not suite for net branch.

So this patch only tries to add the deleted cached rt into the uncached
list, so user could still be able to use it to receive packets until
it's done.

Fixes: 95c47f9cf5e0 ("ipv4: call dst_dev_put() properly")
Signed-off-by: Wei Wang <weiwan@google.com>
Reported-by: Ido Schimmel <idosch@idosch.org>
Reported-by: Jesse Hathaway <jesse@mbuki-mvuki.org>
Tested-by: Jesse Hathaway <jesse@mbuki-mvuki.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Cc: David Ahern <dsahern@gmail.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/route.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 5bc172abd143..621f83434b24 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1482,7 +1482,7 @@ static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt)
 	prev = cmpxchg(p, orig, rt);
 	if (prev == orig) {
 		if (orig) {
-			dst_dev_put(&orig->dst);
+			rt_add_uncached_list(orig);
 			dst_release(&orig->dst);
 		}
 	} else {
-- 
cgit v1.2.3


From 0cc76d2b14ffcd00a99d6ec3b9ebad39c659701a Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Thu, 17 Oct 2019 05:14:08 +0800
Subject: net: Update address for MediaTek ethernet driver in MAINTAINERS

Update maintainers for MediaTek ethernet driver with Mark Lee.
He is familiar with MediaTek mt762x series ethernet devices and
will keep following maintenance from the vendor side.

Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Mark Lee <Mark-MC.Lee@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 49e4b004917b..60c8b337eb88 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10258,7 +10258,7 @@ MEDIATEK ETHERNET DRIVER
 M:	Felix Fietkau <nbd@openwrt.org>
 M:	John Crispin <john@phrozen.org>
 M:	Sean Wang <sean.wang@mediatek.com>
-M:	Nelson Chang <nelson.chang@mediatek.com>
+M:	Mark Lee <Mark-MC.Lee@mediatek.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/mediatek/
-- 
cgit v1.2.3


From 56a0b978d42f58c7e3ba715cf65af487d427524d Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Tue, 15 Oct 2019 22:07:31 +0800
Subject: ACPI: CPPC: Set pcc_data[pcc_ss_id] to NULL in
 acpi_cppc_processor_exit()

When enabling KASAN and DEBUG_TEST_DRIVER_REMOVE, I find this KASAN
warning:

[   20.872057] BUG: KASAN: use-after-free in pcc_data_alloc+0x40/0xb8
[   20.878226] Read of size 4 at addr ffff00236cdeb684 by task swapper/0/1
[   20.884826]
[   20.886309] CPU: 19 PID: 1 Comm: swapper/0 Not tainted 5.4.0-rc1-00009-ge7f7df3db5bf-dirty #289
[   20.894994] Hardware name: Huawei D06 /D06, BIOS Hisilicon D06 UEFI RC0 - V1.16.01 03/15/2019
[   20.903505] Call trace:
[   20.905942]  dump_backtrace+0x0/0x200
[   20.909593]  show_stack+0x14/0x20
[   20.912899]  dump_stack+0xd4/0x130
[   20.916291]  print_address_description.isra.9+0x6c/0x3b8
[   20.921592]  __kasan_report+0x12c/0x23c
[   20.925417]  kasan_report+0xc/0x18
[   20.928808]  __asan_load4+0x94/0xb8
[   20.932286]  pcc_data_alloc+0x40/0xb8
[   20.935938]  acpi_cppc_processor_probe+0x4e8/0xb08
[   20.940717]  __acpi_processor_start+0x48/0xb0
[   20.945062]  acpi_processor_start+0x40/0x60
[   20.949235]  really_probe+0x118/0x548
[   20.952887]  driver_probe_device+0x7c/0x148
[   20.957059]  device_driver_attach+0x94/0xa0
[   20.961231]  __driver_attach+0xa4/0x110
[   20.965055]  bus_for_each_dev+0xe8/0x158
[   20.968966]  driver_attach+0x30/0x40
[   20.972531]  bus_add_driver+0x234/0x2f0
[   20.976356]  driver_register+0xbc/0x1d0
[   20.980182]  acpi_processor_driver_init+0x40/0xe4
[   20.984875]  do_one_initcall+0xb4/0x254
[   20.988700]  kernel_init_freeable+0x24c/0x2f8
[   20.993047]  kernel_init+0x10/0x118
[   20.996524]  ret_from_fork+0x10/0x18
[   21.000087]
[   21.001567] Allocated by task 1:
[   21.004785]  save_stack+0x28/0xc8
[   21.008089]  __kasan_kmalloc.isra.9+0xbc/0xd8
[   21.012435]  kasan_kmalloc+0xc/0x18
[   21.015913]  pcc_data_alloc+0x94/0xb8
[   21.019564]  acpi_cppc_processor_probe+0x4e8/0xb08
[   21.024343]  __acpi_processor_start+0x48/0xb0
[   21.028689]  acpi_processor_start+0x40/0x60
[   21.032860]  really_probe+0x118/0x548
[   21.036512]  driver_probe_device+0x7c/0x148
[   21.040684]  device_driver_attach+0x94/0xa0
[   21.044855]  __driver_attach+0xa4/0x110
[   21.048680]  bus_for_each_dev+0xe8/0x158
[   21.052591]  driver_attach+0x30/0x40
[   21.056155]  bus_add_driver+0x234/0x2f0
[   21.059980]  driver_register+0xbc/0x1d0
[   21.063805]  acpi_processor_driver_init+0x40/0xe4
[   21.068497]  do_one_initcall+0xb4/0x254
[   21.072322]  kernel_init_freeable+0x24c/0x2f8
[   21.076667]  kernel_init+0x10/0x118
[   21.080144]  ret_from_fork+0x10/0x18
[   21.083707]
[   21.085186] Freed by task 1:
[   21.088056]  save_stack+0x28/0xc8
[   21.091360]  __kasan_slab_free+0x118/0x180
[   21.095445]  kasan_slab_free+0x10/0x18
[   21.099183]  kfree+0x80/0x268
[   21.102139]  acpi_cppc_processor_exit+0x1a8/0x1b8
[   21.106832]  acpi_processor_stop+0x70/0x80
[   21.110917]  really_probe+0x174/0x548
[   21.114568]  driver_probe_device+0x7c/0x148
[   21.118740]  device_driver_attach+0x94/0xa0
[   21.122912]  __driver_attach+0xa4/0x110
[   21.126736]  bus_for_each_dev+0xe8/0x158
[   21.130648]  driver_attach+0x30/0x40
[   21.134212]  bus_add_driver+0x234/0x2f0
[   21.0x10/0x18
[   21.161764]
[   21.163244] The buggy address belongs to the object at ffff00236cdeb600
[   21.163244]  which belongs to the cache kmalloc-256 of size 256
[   21.175750] The buggy address is located 132 bytes inside of
[   21.175750]  256-byte region [ffff00236cdeb600, ffff00236cdeb700)
[   21.187473] The buggy address belongs to the page:
[   21.192254] page:fffffe008d937a00 refcount:1 mapcount:0 mapping:ffff002370c0fa00 index:0x0 compound_mapcount: 0
[   21.202331] flags: 0x1ffff00000010200(slab|head)
[   21.206940] raw: 1ffff00000010200 dead000000000100 dead000000000122 ffff002370c0fa00
[   21.214671] raw: 0000000000000000 00000000802a002a 00000001ffffffff 0000000000000000
[   21.222400] page dumped because: kasan: bad access detected
[   21.227959]
[   21.229438] Memory state around the buggy address:
[   21.234218]  ffff00236cdeb580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[   21.241427]  ffff00236cdeb600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[   21.248637] >ffff00236cdeb680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[   21.255845]                    ^
[   21.259062]  ffff00236cdeb700: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[   21.266272]  ffff00236cdeb780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[   21.273480] ==================================================================

It seems that global pcc_data[pcc_ss_id] can be freed in
acpi_cppc_processor_exit(), but we may later reference this value, so
NULLify it when freed.

Also remove the useless setting of data "pcc_channel_acquired", which
we're about to free.

Fixes: 85b1407bf6d2 ("ACPI / CPPC: Make CPPC ACPI driver aware of PCC subspace IDs")
Signed-off-by: John Garry <john.garry@huawei.com>
Cc: 4.15+ <stable@vger.kernel.org> # 4.15+
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/cppc_acpi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 3b2525908dd8..a1a858ad4d18 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -905,8 +905,8 @@ void acpi_cppc_processor_exit(struct acpi_processor *pr)
 			pcc_data[pcc_ss_id]->refcount--;
 			if (!pcc_data[pcc_ss_id]->refcount) {
 				pcc_mbox_free_channel(pcc_data[pcc_ss_id]->pcc_channel);
-				pcc_data[pcc_ss_id]->pcc_channel_acquired = 0;
 				kfree(pcc_data[pcc_ss_id]);
+				pcc_data[pcc_ss_id] = NULL;
 			}
 		}
 	}
-- 
cgit v1.2.3


From fb26eee0600dbd6b2eb20356b7d425cb71413ea2 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Fri, 18 Oct 2019 10:05:14 +0100
Subject: drm/i915/pmu: Fix uninitialized variable on error path

If name allocation failed the log message will contain an uninitialized
error code which can be confusing.

Fixes: 05488673a4d4 ("drm/i915/pmu: Support multiple GPUs")
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018090514.1818-1-tvrtko.ursulin@linux.intel.com
[tursulin: Commit message spelling fix.]
---
 drivers/gpu/drm/i915/i915_pmu.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 00fe401868c4..144c32eed045 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -1094,7 +1094,7 @@ static bool is_igp(struct drm_i915_private *i915)
 void i915_pmu_register(struct drm_i915_private *i915)
 {
 	struct i915_pmu *pmu = &i915->pmu;
-	int ret;
+	int ret = -ENOMEM;
 
 	if (INTEL_GEN(i915) <= 2) {
 		dev_info(i915->drm.dev, "PMU not supported for this GPU.");
@@ -1102,10 +1102,8 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	}
 
 	i915_pmu_events_attr_group.attrs = create_event_attributes(pmu);
-	if (!i915_pmu_events_attr_group.attrs) {
-		ret = -ENOMEM;
+	if (!i915_pmu_events_attr_group.attrs)
 		goto err;
-	}
 
 	pmu->base.attr_groups	= i915_pmu_attr_groups;
 	pmu->base.task_ctx_nr	= perf_invalid_context;
-- 
cgit v1.2.3


From 253a774bb08b549488047c3fb4afc0faf6f194ae Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 18 Oct 2019 08:20:27 +0100
Subject: drm/i915/execlists: Don't merely skip submission if maybe timeslicing

Normally, we try and skip submission if ELSP[1] is filled. However, we
may desire to enable timeslicing due to the queue priority, even if
ELSP[1] itself does not require timeslicing. That is the queue is equal
priority to ELSP[0] and higher priority then ELSP[1]. Previously, we
would wait until the context switch to preempt the current ELSP[1], but
with timeslicing, we want to preempt ELSP[0] and replace it with the
queue.

In writing the test case, it become quickly apparent that we were also
suppressing the tasklet during promotion and so failing to notice when
the queue started requiring timeslicing.

Fixes: 2229adc81380 ("drm/i915/execlist: Trim immediate timeslice expiry")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018072027.31948-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_lrc.c    |  22 ++++-
 drivers/gpu/drm/i915/gt/selftest_lrc.c | 168 ++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/i915_scheduler.c  |  17 +++-
 drivers/gpu/drm/i915/i915_scheduler.h  |  18 ----
 4 files changed, 196 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index e9fe9f79cedd..d0088d020220 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -352,10 +352,15 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
 	 * However, the priority hint is a mere hint that we may need to
 	 * preempt. If that hint is stale or we may be trying to preempt
 	 * ourselves, ignore the request.
+	 *
+	 * More naturally we would write
+	 *      prio >= max(0, last);
+	 * except that we wish to prevent triggering preemption at the same
+	 * priority level: the task that is running should remain running
+	 * to preserve FIFO ordering of dependencies.
 	 */
-	last_prio = effective_prio(rq);
-	if (!i915_scheduler_need_preempt(engine->execlists.queue_priority_hint,
-					 last_prio))
+	last_prio = max(effective_prio(rq), I915_PRIORITY_NORMAL - 1);
+	if (engine->execlists.queue_priority_hint <= last_prio)
 		return false;
 
 	/*
@@ -1509,8 +1514,17 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			 * submission.
 			 */
 			if (!list_is_last(&last->sched.link,
-					  &engine->active.requests))
+					  &engine->active.requests)) {
+				/*
+				 * Even if ELSP[1] is occupied and not worthy
+				 * of timeslices, our queue might be.
+				 */
+				if (!execlists->timer.expires &&
+				    need_timeslice(engine, last))
+					mod_timer(&execlists->timer,
+						  jiffies + 1);
 				return;
+			}
 
 			/*
 			 * WaIdleLiteRestore:bdw,skl
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 007d6203fe0e..5dc679781a08 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -325,7 +325,13 @@ semaphore_queue(struct intel_engine_cs *engine, struct i915_vma *vma, int idx)
 	if (IS_ERR(rq))
 		goto out_ctx;
 
-	err = emit_semaphore_chain(rq, vma, idx);
+	err = 0;
+	if (rq->engine->emit_init_breadcrumb)
+		err = rq->engine->emit_init_breadcrumb(rq);
+	if (err == 0)
+		err = emit_semaphore_chain(rq, vma, idx);
+	if (err == 0)
+		i915_request_get(rq);
 	i915_request_add(rq);
 	if (err)
 		rq = ERR_PTR(err);
@@ -338,10 +344,10 @@ out_ctx:
 static int
 release_queue(struct intel_engine_cs *engine,
 	      struct i915_vma *vma,
-	      int idx)
+	      int idx, int prio)
 {
 	struct i915_sched_attr attr = {
-		.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX),
+		.priority = prio,
 	};
 	struct i915_request *rq;
 	u32 *cs;
@@ -362,9 +368,15 @@ release_queue(struct intel_engine_cs *engine,
 	*cs++ = 1;
 
 	intel_ring_advance(rq, cs);
+
+	i915_request_get(rq);
 	i915_request_add(rq);
 
+	local_bh_disable();
 	engine->schedule(rq, &attr);
+	local_bh_enable(); /* kick tasklet */
+
+	i915_request_put(rq);
 
 	return 0;
 }
@@ -383,7 +395,6 @@ slice_semaphore_queue(struct intel_engine_cs *outer,
 	if (IS_ERR(head))
 		return PTR_ERR(head);
 
-	i915_request_get(head);
 	for_each_engine(engine, outer->gt, id) {
 		for (i = 0; i < count; i++) {
 			struct i915_request *rq;
@@ -393,10 +404,12 @@ slice_semaphore_queue(struct intel_engine_cs *outer,
 				err = PTR_ERR(rq);
 				goto out;
 			}
+
+			i915_request_put(rq);
 		}
 	}
 
-	err = release_queue(outer, vma, n);
+	err = release_queue(outer, vma, n, INT_MAX);
 	if (err)
 		goto out;
 
@@ -482,6 +495,150 @@ err_obj:
 	return err;
 }
 
+static struct i915_request *nop_request(struct intel_engine_cs *engine)
+{
+	struct i915_request *rq;
+
+	rq = i915_request_create(engine->kernel_context);
+	if (IS_ERR(rq))
+		return rq;
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+
+	return rq;
+}
+
+static void wait_for_submit(struct intel_engine_cs *engine,
+			    struct i915_request *rq)
+{
+	do {
+		cond_resched();
+		intel_engine_flush_submission(engine);
+	} while (!i915_request_is_active(rq));
+}
+
+static int live_timeslice_queue(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct drm_i915_gem_object *obj;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	struct i915_vma *vma;
+	void *vaddr;
+	int err = 0;
+
+	/*
+	 * Make sure that even if ELSP[0] and ELSP[1] are filled with
+	 * timeslicing between them disabled, we *do* enable timeslicing
+	 * if the queue demands it. (Normally, we do not submit if
+	 * ELSP[1] is already occupied, so must rely on timeslicing to
+	 * eject ELSP[0] in favour of the queue.)
+	 */
+
+	obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	vma = i915_vma_instance(obj, &gt->ggtt->vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto err_obj;
+	}
+
+	vaddr = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(vaddr)) {
+		err = PTR_ERR(vaddr);
+		goto err_obj;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL);
+	if (err)
+		goto err_map;
+
+	for_each_engine(engine, gt, id) {
+		struct i915_sched_attr attr = {
+			.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX),
+		};
+		struct i915_request *rq, *nop;
+
+		if (!intel_engine_has_preemption(engine))
+			continue;
+
+		memset(vaddr, 0, PAGE_SIZE);
+
+		/* ELSP[0]: semaphore wait */
+		rq = semaphore_queue(engine, vma, 0);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto err_pin;
+		}
+		engine->schedule(rq, &attr);
+		wait_for_submit(engine, rq);
+
+		/* ELSP[1]: nop request */
+		nop = nop_request(engine);
+		if (IS_ERR(nop)) {
+			err = PTR_ERR(nop);
+			i915_request_put(rq);
+			goto err_pin;
+		}
+		wait_for_submit(engine, nop);
+		i915_request_put(nop);
+
+		GEM_BUG_ON(i915_request_completed(rq));
+		GEM_BUG_ON(execlists_active(&engine->execlists) != rq);
+
+		/* Queue: semaphore signal, matching priority as semaphore */
+		err = release_queue(engine, vma, 1, effective_prio(rq));
+		if (err) {
+			i915_request_put(rq);
+			goto err_pin;
+		}
+
+		intel_engine_flush_submission(engine);
+		if (!READ_ONCE(engine->execlists.timer.expires) &&
+		    !i915_request_completed(rq)) {
+			struct drm_printer p =
+				drm_info_printer(gt->i915->drm.dev);
+
+			GEM_TRACE_ERR("%s: Failed to enable timeslicing!\n",
+				      engine->name);
+			intel_engine_dump(engine, &p,
+					  "%s\n", engine->name);
+			GEM_TRACE_DUMP();
+
+			memset(vaddr, 0xff, PAGE_SIZE);
+			err = -EINVAL;
+		}
+
+		/* Timeslice every jiffie, so within 2 we should signal */
+		if (i915_request_wait(rq, 0, 3) < 0) {
+			struct drm_printer p =
+				drm_info_printer(gt->i915->drm.dev);
+
+			pr_err("%s: Failed to timeslice into queue\n",
+			       engine->name);
+			intel_engine_dump(engine, &p,
+					  "%s\n", engine->name);
+
+			memset(vaddr, 0xff, PAGE_SIZE);
+			err = -EIO;
+		}
+		i915_request_put(rq);
+		if (err)
+			break;
+	}
+
+err_pin:
+	i915_vma_unpin(vma);
+err_map:
+	i915_gem_object_unpin_map(obj);
+err_obj:
+	i915_gem_object_put(obj);
+	return err;
+}
+
 static int live_busywait_preempt(void *arg)
 {
 	struct intel_gt *gt = arg;
@@ -2437,6 +2594,7 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_unlite_switch),
 		SUBTEST(live_unlite_preempt),
 		SUBTEST(live_timeslice_preempt),
+		SUBTEST(live_timeslice_queue),
 		SUBTEST(live_busywait_preempt),
 		SUBTEST(live_preempt),
 		SUBTEST(live_late_preempt),
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 7b84ebca2901..0ca40f6bf08c 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -177,9 +177,22 @@ static inline int rq_prio(const struct i915_request *rq)
 	return rq->sched.attr.priority | __NO_PREEMPTION;
 }
 
+static inline bool need_preempt(int prio, int active)
+{
+	/*
+	 * Allow preemption of low -> normal -> high, but we do
+	 * not allow low priority tasks to preempt other low priority
+	 * tasks under the impression that latency for low priority
+	 * tasks does not matter (as much as background throughput),
+	 * so kiss.
+	 */
+	return prio >= max(I915_PRIORITY_NORMAL, active);
+}
+
 static void kick_submission(struct intel_engine_cs *engine, int prio)
 {
-	const struct i915_request *inflight = *engine->execlists.active;
+	const struct i915_request *inflight =
+		execlists_active(&engine->execlists);
 
 	/*
 	 * If we are already the currently executing context, don't
@@ -188,7 +201,7 @@ static void kick_submission(struct intel_engine_cs *engine, int prio)
 	 * tasklet, i.e. we have not change the priority queue
 	 * sufficiently to oust the running context.
 	 */
-	if (!inflight || !i915_scheduler_need_preempt(prio, rq_prio(inflight)))
+	if (!inflight || !need_preempt(prio, rq_prio(inflight)))
 		return;
 
 	tasklet_hi_schedule(&engine->execlists.tasklet);
diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h
index 7eefccff39bf..07d243acf553 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.h
+++ b/drivers/gpu/drm/i915/i915_scheduler.h
@@ -52,22 +52,4 @@ static inline void i915_priolist_free(struct i915_priolist *p)
 		__i915_priolist_free(p);
 }
 
-static inline bool i915_scheduler_need_preempt(int prio, int active)
-{
-	/*
-	 * Allow preemption of low -> normal -> high, but we do
-	 * not allow low priority tasks to preempt other low priority
-	 * tasks under the impression that latency for low priority
-	 * tasks does not matter (as much as background throughput),
-	 * so kiss.
-	 *
-	 * More naturally we would write
-	 *	prio >= max(0, last);
-	 * except that we wish to prevent triggering preemption at the same
-	 * priority level: the task that is running should remain running
-	 * to preserve FIFO ordering of dependencies.
-	 */
-	return prio > max(I915_PRIORITY_NORMAL - 1, active);
-}
-
 #endif /* _I915_SCHEDULER_H_ */
-- 
cgit v1.2.3


From f7c0f50f1857c1cf013466fcea4dc98d116bf456 Mon Sep 17 00:00:00 2001
From: Andrea Parri <parri.andrea@gmail.com>
Date: Tue, 15 Oct 2019 12:35:02 +0200
Subject: x86/hyperv: Set pv_info.name to "Hyper-V"

Michael reported that the x86/hyperv initialization code prints the
following dmesg when running in a VM on Hyper-V:

  [    0.000738] Booting paravirtualized kernel on bare hardware

Let the x86/hyperv initialization code set pv_info.name to "Hyper-V" so
dmesg reports correctly:

  [    0.000172] Booting paravirtualized kernel on Hyper-V

[ tglx: Folded build fix provided by Yue ]

Reported-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Andrea Parri <parri.andrea@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Wei Liu <wei.liu@kernel.org>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Cc: YueHaibing <yuehaibing@huawei.com>
Link: https://lkml.kernel.org/r/20191015103502.13156-1-parri.andrea@gmail.com
---
 arch/x86/kernel/cpu/mshyperv.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 267daad8c036..c656d92cd708 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -216,6 +216,10 @@ static void __init ms_hyperv_init_platform(void)
 	int hv_host_info_ecx;
 	int hv_host_info_edx;
 
+#ifdef CONFIG_PARAVIRT
+	pv_info.name = "Hyper-V";
+#endif
+
 	/*
 	 * Extract the features and hints
 	 */
-- 
cgit v1.2.3


From 228d120051a2234356690924c1f42e07e54e1eaf Mon Sep 17 00:00:00 2001
From: Zhenzhong Duan <zhenzhong.duan@oracle.com>
Date: Sun, 29 Sep 2019 09:13:52 +0800
Subject: x86/boot/acpi: Move get_cmdline_acpi_rsdp() under #ifdef guard

When building with "EXTRA_CFLAGS=-Wall" gcc warns:

arch/x86/boot/compressed/acpi.c:29:30: warning: get_cmdline_acpi_rsdp defined but not used [-Wunused-function]

get_cmdline_acpi_rsdp() is only used when CONFIG_RANDOMIZE_BASE and
CONFIG_MEMORY_HOTREMOVE are both enabled, so any build where one of these
config options is disabled has this issue.

Move the function under the same ifdef guard as the call site.

[ tglx: Add context to the changelog so it becomes useful ]

Fixes: 41fa1ee9c6d6 ("acpi: Ignore acpi_rsdp kernel param when the kernel has been locked down")
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/1569719633-32164-1-git-send-email-zhenzhong.duan@oracle.com
---
 arch/x86/boot/compressed/acpi.c | 48 ++++++++++++++++++++---------------------
 1 file changed, 24 insertions(+), 24 deletions(-)

diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index 149795c369f2..25019d42ae93 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -20,30 +20,6 @@
  */
 struct mem_vector immovable_mem[MAX_NUMNODES*2];
 
-/*
- * Max length of 64-bit hex address string is 19, prefix "0x" + 16 hex
- * digits, and '\0' for termination.
- */
-#define MAX_ADDR_LEN 19
-
-static acpi_physical_address get_cmdline_acpi_rsdp(void)
-{
-	acpi_physical_address addr = 0;
-
-#ifdef CONFIG_KEXEC
-	char val[MAX_ADDR_LEN] = { };
-	int ret;
-
-	ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN);
-	if (ret < 0)
-		return 0;
-
-	if (kstrtoull(val, 16, &addr))
-		return 0;
-#endif
-	return addr;
-}
-
 /*
  * Search EFI system tables for RSDP.  If both ACPI_20_TABLE_GUID and
  * ACPI_TABLE_GUID are found, take the former, which has more features.
@@ -298,6 +274,30 @@ acpi_physical_address get_rsdp_addr(void)
 }
 
 #if defined(CONFIG_RANDOMIZE_BASE) && defined(CONFIG_MEMORY_HOTREMOVE)
+/*
+ * Max length of 64-bit hex address string is 19, prefix "0x" + 16 hex
+ * digits, and '\0' for termination.
+ */
+#define MAX_ADDR_LEN 19
+
+static acpi_physical_address get_cmdline_acpi_rsdp(void)
+{
+	acpi_physical_address addr = 0;
+
+#ifdef CONFIG_KEXEC
+	char val[MAX_ADDR_LEN] = { };
+	int ret;
+
+	ret = cmdline_find_option("acpi_rsdp", val, MAX_ADDR_LEN);
+	if (ret < 0)
+		return 0;
+
+	if (kstrtoull(val, 16, &addr))
+		return 0;
+#endif
+	return addr;
+}
+
 /* Compute SRAT address from RSDP. */
 static unsigned long get_acpi_srat_table(void)
 {
-- 
cgit v1.2.3


From 3aae9d08532c8e542ad2787b3f1c6b4ee14db32b Mon Sep 17 00:00:00 2001
From: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
Date: Fri, 18 Oct 2019 10:07:49 +0100
Subject: drm/i915: enumerate and init each supported region

Nothing to enumerate yet...

Signed-off-by: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018090751.28295-1-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h                  |  7 +++
 drivers/gpu/drm/i915/i915_gem_gtt.c              | 56 +++++++++++++++++++++---
 drivers/gpu/drm/i915/intel_device_info.h         |  2 +
 drivers/gpu/drm/i915/intel_memory_region.h       |  4 ++
 drivers/gpu/drm/i915/selftests/mock_gem_device.c |  6 +++
 5 files changed, 68 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 40e923b0c2c8..faf645802710 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -684,6 +684,8 @@ struct i915_gem_mm {
 	 */
 	struct vfsmount *gemfs;
 
+	struct intel_memory_region *regions[INTEL_REGION_UNKNOWN];
+
 	struct notifier_block oom_notifier;
 	struct notifier_block vmap_notifier;
 	struct shrinker shrinker;
@@ -1783,6 +1785,8 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 
 #define HAS_IPC(dev_priv)		 (INTEL_INFO(dev_priv)->display.has_ipc)
 
+#define HAS_REGION(i915, i) (INTEL_INFO(i915)->memory_regions & (i))
+
 #define HAS_GT_UC(dev_priv)	(INTEL_INFO(dev_priv)->has_gt_uc)
 
 /* Having GuC is not the same as using GuC */
@@ -2001,6 +2005,9 @@ int __must_check i915_gem_evict_for_node(struct i915_address_space *vm,
 					 unsigned int flags);
 int i915_gem_evict_vm(struct i915_address_space *vm);
 
+void i915_gem_cleanup_memory_regions(struct drm_i915_private *i915);
+int i915_gem_init_memory_regions(struct drm_i915_private *i915);
+
 /* i915_gem_internal.c */
 struct drm_i915_gem_object *
 i915_gem_object_create_internal(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 7b15bb891970..7b8e30c72f86 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2744,6 +2744,52 @@ int i915_init_ggtt(struct drm_i915_private *i915)
 	return 0;
 }
 
+void i915_gem_cleanup_memory_regions(struct drm_i915_private *i915)
+{
+	int i;
+
+	i915_gem_cleanup_stolen(i915);
+
+	for (i = 0; i < INTEL_REGION_UNKNOWN; i++) {
+		struct intel_memory_region *region = i915->mm.regions[i];
+
+		if (region)
+			intel_memory_region_put(region);
+	}
+}
+
+int i915_gem_init_memory_regions(struct drm_i915_private *i915)
+{
+	int err, i;
+
+	/*
+	 * Initialise stolen early so that we may reserve preallocated
+	 * objects for the BIOS to KMS transition.
+	 */
+	/* XXX: stolen will become a region at some point */
+	err = i915_gem_init_stolen(i915);
+	if (err)
+		return err;
+
+	for (i = 0; i < INTEL_REGION_UNKNOWN; i++) {
+		struct intel_memory_region *mem = ERR_PTR(-ENODEV);
+
+		if (!HAS_REGION(i915, BIT(i)))
+			continue;
+
+		if (IS_ERR(mem)) {
+			err = PTR_ERR(mem);
+			goto out_cleanup;
+		}
+	}
+
+	return 0;
+
+out_cleanup:
+	i915_gem_cleanup_memory_regions(i915);
+	return err;
+}
+
 static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
 {
 	struct i915_vma *vma, *vn;
@@ -2781,6 +2827,8 @@ void i915_ggtt_driver_release(struct drm_i915_private *i915)
 {
 	struct pagevec *pvec;
 
+	i915_gem_cleanup_memory_regions(i915);
+
 	fini_aliasing_ppgtt(&i915->ggtt);
 
 	ggtt_cleanup_hw(&i915->ggtt);
@@ -2790,8 +2838,6 @@ void i915_ggtt_driver_release(struct drm_i915_private *i915)
 		set_pages_array_wb(pvec->pages, pvec->nr);
 		__pagevec_release(pvec);
 	}
-
-	i915_gem_cleanup_stolen(i915);
 }
 
 static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
@@ -3240,11 +3286,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	if (ret)
 		return ret;
 
-	/*
-	 * Initialise stolen early so that we may reserve preallocated
-	 * objects for the BIOS to KMS transition.
-	 */
-	ret = i915_gem_init_stolen(dev_priv);
+	ret = i915_gem_init_memory_regions(dev_priv);
 	if (ret)
 		goto out_gtt_cleanup;
 
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 0cdc2465534b..e9940f932d26 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -160,6 +160,8 @@ struct intel_device_info {
 
 	unsigned int page_sizes; /* page sizes supported by the HW */
 
+	u32 memory_regions; /* regions supported by the HW */
+
 	u32 display_mmio_offset;
 
 	u8 pipe_mask;
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index 52c141b6108c..2c165a7a5ab4 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -18,6 +18,10 @@ struct drm_i915_gem_object;
 struct intel_memory_region;
 struct sg_table;
 
+enum intel_region_id {
+	INTEL_REGION_UNKNOWN = 0, /* Should be last */
+};
+
 #define I915_ALLOC_MIN_PAGE_SIZE  BIT(0)
 #define I915_ALLOC_CONTIGUOUS     BIT(1)
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 9c22d41b30cd..bc5e3c67409f 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -74,6 +74,8 @@ static void mock_device_release(struct drm_device *dev)
 
 	i915_gemfs_fini(i915);
 
+	i915_gem_cleanup_memory_regions(i915);
+
 	drm_mode_config_cleanup(&i915->drm);
 
 	drm_dev_fini(&i915->drm);
@@ -196,6 +198,10 @@ struct drm_i915_private *mock_gem_device(void)
 
 	WARN_ON(i915_gemfs_init(i915));
 
+	err = i915_gem_init_memory_regions(i915);
+	if (err)
+		goto err_context;
+
 	return i915;
 
 err_context:
-- 
cgit v1.2.3


From da1184cd41d4c6b316a937ac1da5825807e8f6fb Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 18 Oct 2019 10:07:50 +0100
Subject: drm/i915: treat shmem as a region

Convert shmem to an intel_memory_region.

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018090751.28295-2-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/gem/i915_gem_object.h       |  5 +-
 drivers/gpu/drm/i915/gem/i915_gem_phys.c         |  5 +-
 drivers/gpu/drm/i915/gem/i915_gem_region.c       |  7 ++-
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c        | 79 +++++++++++++++++-------
 drivers/gpu/drm/i915/i915_drv.h                  |  2 +
 drivers/gpu/drm/i915/i915_gem.c                  |  9 ---
 drivers/gpu/drm/i915/i915_gem_gtt.c              | 15 +++++
 drivers/gpu/drm/i915/i915_pci.c                  | 29 ++++++---
 drivers/gpu/drm/i915/intel_memory_region.c       | 10 +++
 drivers/gpu/drm/i915/intel_memory_region.h       | 28 ++++++++-
 drivers/gpu/drm/i915/selftests/mock_gem_device.c |  7 +--
 11 files changed, 149 insertions(+), 47 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index c5e14c9c805c..85921796851f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -25,10 +25,11 @@ void i915_gem_object_free(struct drm_i915_gem_object *obj);
 void i915_gem_object_init(struct drm_i915_gem_object *obj,
 			  const struct drm_i915_gem_object_ops *ops);
 struct drm_i915_gem_object *
-i915_gem_object_create_shmem(struct drm_i915_private *i915, u64 size);
+i915_gem_object_create_shmem(struct drm_i915_private *i915,
+			     resource_size_t size);
 struct drm_i915_gem_object *
 i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915,
-				       const void *data, size_t size);
+				       const void *data, resource_size_t size);
 
 extern const struct drm_i915_gem_object_ops i915_gem_shmem_ops;
 void __i915_gem_object_release_shmem(struct drm_i915_gem_object *obj,
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
index 768356908160..8043ff63d73f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c
@@ -16,6 +16,7 @@
 #include "gt/intel_gt.h"
 #include "i915_drv.h"
 #include "i915_gem_object.h"
+#include "i915_gem_region.h"
 #include "i915_scatterlist.h"
 
 static int i915_gem_object_get_pages_phys(struct drm_i915_gem_object *obj)
@@ -191,8 +192,10 @@ int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align)
 	/* Perma-pin (until release) the physical set of pages */
 	__i915_gem_object_pin_pages(obj);
 
-	if (!IS_ERR_OR_NULL(pages))
+	if (!IS_ERR_OR_NULL(pages)) {
 		i915_gem_shmem_ops.put_pages(obj, pages);
+		i915_gem_object_release_memory_region(obj);
+	}
 	mutex_unlock(&obj->mm.lock);
 	return 0;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c
index d3f7733bc7ed..2f7bcfb9c964 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_region.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c
@@ -6,6 +6,7 @@
 #include "intel_memory_region.h"
 #include "i915_gem_region.h"
 #include "i915_drv.h"
+#include "i915_trace.h"
 
 void
 i915_gem_object_put_pages_buddy(struct drm_i915_gem_object *obj,
@@ -165,5 +166,9 @@ i915_gem_object_create_region(struct intel_memory_region *mem,
 	if (overflows_type(size, obj->base.size))
 		return ERR_PTR(-E2BIG);
 
-	return mem->ops->create_object(mem, size, flags);
+	obj = mem->ops->create_object(mem, size, flags);
+	if (!IS_ERR(obj))
+		trace_i915_gem_object_create(obj);
+
+	return obj;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 4c4954e8ce0a..be68b76e13b3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -7,7 +7,9 @@
 #include <linux/pagevec.h>
 #include <linux/swap.h>
 
+#include "gem/i915_gem_region.h"
 #include "i915_drv.h"
+#include "i915_gemfs.h"
 #include "i915_gem_object.h"
 #include "i915_scatterlist.h"
 #include "i915_trace.h"
@@ -26,6 +28,7 @@ static void check_release_pagevec(struct pagevec *pvec)
 static int shmem_get_pages(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct intel_memory_region *mem = obj->mm.region;
 	const unsigned long page_count = obj->base.size / PAGE_SIZE;
 	unsigned long i;
 	struct address_space *mapping;
@@ -52,7 +55,7 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj)
 	 * If there's no chance of allocating enough pages for the whole
 	 * object, bail early.
 	 */
-	if (page_count > totalram_pages())
+	if (obj->base.size > resource_size(&mem->region))
 		return -ENOMEM;
 
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
@@ -417,6 +420,8 @@ shmem_pwrite(struct drm_i915_gem_object *obj,
 
 static void shmem_release(struct drm_i915_gem_object *obj)
 {
+	i915_gem_object_release_memory_region(obj);
+
 	fput(obj->base.filp);
 }
 
@@ -434,9 +439,9 @@ const struct drm_i915_gem_object_ops i915_gem_shmem_ops = {
 	.release = shmem_release,
 };
 
-static int create_shmem(struct drm_i915_private *i915,
-			struct drm_gem_object *obj,
-			size_t size)
+static int __create_shmem(struct drm_i915_private *i915,
+			  struct drm_gem_object *obj,
+			  resource_size_t size)
 {
 	unsigned long flags = VM_NORESERVE;
 	struct file *filp;
@@ -455,31 +460,23 @@ static int create_shmem(struct drm_i915_private *i915,
 	return 0;
 }
 
-struct drm_i915_gem_object *
-i915_gem_object_create_shmem(struct drm_i915_private *i915, u64 size)
+static struct drm_i915_gem_object *
+create_shmem(struct intel_memory_region *mem,
+	     resource_size_t size,
+	     unsigned int flags)
 {
+	struct drm_i915_private *i915 = mem->i915;
 	struct drm_i915_gem_object *obj;
 	struct address_space *mapping;
 	unsigned int cache_level;
 	gfp_t mask;
 	int ret;
 
-	/* There is a prevalence of the assumption that we fit the object's
-	 * page count inside a 32bit _signed_ variable. Let's document this and
-	 * catch if we ever need to fix it. In the meantime, if you do spot
-	 * such a local variable, please consider fixing!
-	 */
-	if (size >> PAGE_SHIFT > INT_MAX)
-		return ERR_PTR(-E2BIG);
-
-	if (overflows_type(size, obj->base.size))
-		return ERR_PTR(-E2BIG);
-
 	obj = i915_gem_object_alloc();
 	if (!obj)
 		return ERR_PTR(-ENOMEM);
 
-	ret = create_shmem(i915, &obj->base, size);
+	ret = __create_shmem(i915, &obj->base, size);
 	if (ret)
 		goto fail;
 
@@ -518,7 +515,7 @@ i915_gem_object_create_shmem(struct drm_i915_private *i915, u64 size)
 
 	i915_gem_object_set_cache_coherency(obj, cache_level);
 
-	trace_i915_gem_object_create(obj);
+	i915_gem_object_init_memory_region(obj, mem, 0);
 
 	return obj;
 
@@ -527,14 +524,22 @@ fail:
 	return ERR_PTR(ret);
 }
 
+struct drm_i915_gem_object *
+i915_gem_object_create_shmem(struct drm_i915_private *i915,
+			     resource_size_t size)
+{
+	return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_SMEM],
+					     size, 0);
+}
+
 /* Allocate a new GEM object and fill it with the supplied data */
 struct drm_i915_gem_object *
 i915_gem_object_create_shmem_from_data(struct drm_i915_private *dev_priv,
-				       const void *data, size_t size)
+				       const void *data, resource_size_t size)
 {
 	struct drm_i915_gem_object *obj;
 	struct file *file;
-	size_t offset;
+	resource_size_t offset;
 	int err;
 
 	obj = i915_gem_object_create_shmem(dev_priv, round_up(size, PAGE_SIZE));
@@ -577,3 +582,35 @@ fail:
 	i915_gem_object_put(obj);
 	return ERR_PTR(err);
 }
+
+static int init_shmem(struct intel_memory_region *mem)
+{
+	int err;
+
+	err = i915_gemfs_init(mem->i915);
+	if (err) {
+		DRM_NOTE("Unable to create a private tmpfs mount, hugepage support will be disabled(%d).\n",
+			 err);
+	}
+
+	return 0; /* Don't error, we can simply fallback to the kernel mnt */
+}
+
+static void release_shmem(struct intel_memory_region *mem)
+{
+	i915_gemfs_fini(mem->i915);
+}
+
+static const struct intel_memory_region_ops shmem_region_ops = {
+	.init = init_shmem,
+	.release = release_shmem,
+	.create_object = create_shmem,
+};
+
+struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915)
+{
+	return intel_memory_region_create(i915, 0,
+					  totalram_pages() << PAGE_SHIFT,
+					  PAGE_SIZE, 0,
+					  &shmem_region_ops);
+}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index faf645802710..db3c3a025a03 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1876,6 +1876,8 @@ void i915_gem_cleanup_early(struct drm_i915_private *dev_priv);
 int i915_gem_freeze(struct drm_i915_private *dev_priv);
 int i915_gem_freeze_late(struct drm_i915_private *dev_priv);
 
+struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915);
+
 static inline void i915_gem_drain_freed_objects(struct drm_i915_private *i915)
 {
 	/*
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index aef5cf2227dd..dd0a3271b4e2 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -45,7 +45,6 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_ioctls.h"
 #include "gem/i915_gem_pm.h"
-#include "gem/i915_gemfs.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
@@ -1432,16 +1431,10 @@ static void i915_gem_init__mm(struct drm_i915_private *i915)
 
 void i915_gem_init_early(struct drm_i915_private *dev_priv)
 {
-	int err;
-
 	i915_gem_init__mm(dev_priv);
 	i915_gem_init__pm(dev_priv);
 
 	spin_lock_init(&dev_priv->fb_tracking.lock);
-
-	err = i915_gemfs_init(dev_priv);
-	if (err)
-		DRM_NOTE("Unable to create a private tmpfs mount, hugepage support will be disabled(%d).\n", err);
 }
 
 void i915_gem_cleanup_early(struct drm_i915_private *dev_priv)
@@ -1450,8 +1443,6 @@ void i915_gem_cleanup_early(struct drm_i915_private *dev_priv)
 	GEM_BUG_ON(!llist_empty(&dev_priv->mm.free_list));
 	GEM_BUG_ON(atomic_read(&dev_priv->mm.free_count));
 	WARN_ON(dev_priv->mm.shrink_count);
-
-	i915_gemfs_fini(dev_priv);
 }
 
 int i915_gem_freeze(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 7b8e30c72f86..263f1cea0b64 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2773,14 +2773,29 @@ int i915_gem_init_memory_regions(struct drm_i915_private *i915)
 
 	for (i = 0; i < INTEL_REGION_UNKNOWN; i++) {
 		struct intel_memory_region *mem = ERR_PTR(-ENODEV);
+		u32 type;
 
 		if (!HAS_REGION(i915, BIT(i)))
 			continue;
 
+		type = MEMORY_TYPE_FROM_REGION(intel_region_map[i]);
+		switch (type) {
+		case INTEL_MEMORY_SYSTEM:
+			mem = i915_gem_shmem_setup(i915);
+			break;
+		}
+
 		if (IS_ERR(mem)) {
 			err = PTR_ERR(mem);
+			DRM_ERROR("Failed to setup region(%d) type=%d\n", err, type);
 			goto out_cleanup;
 		}
+
+		mem->id = intel_region_map[i];
+		mem->type = type;
+		mem->instance = MEMORY_INSTANCE_FROM_REGION(intel_region_map[i]);
+
+		i915->mm.regions[i] = mem;
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 1cbf3998b361..e55ab2724996 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -151,6 +151,9 @@
 #define GEN_DEFAULT_PAGE_SIZES \
 	.page_sizes = I915_GTT_PAGE_SIZE_4K
 
+#define GEN_DEFAULT_REGIONS \
+	.memory_regions = REGION_SMEM
+
 #define I830_FEATURES \
 	GEN(2), \
 	.is_mobile = 1, \
@@ -168,7 +171,8 @@
 	I9XX_PIPE_OFFSETS, \
 	I9XX_CURSOR_OFFSETS, \
 	I9XX_COLORS, \
-	GEN_DEFAULT_PAGE_SIZES
+	GEN_DEFAULT_PAGE_SIZES, \
+	GEN_DEFAULT_REGIONS
 
 #define I845_FEATURES \
 	GEN(2), \
@@ -185,7 +189,8 @@
 	I845_PIPE_OFFSETS, \
 	I845_CURSOR_OFFSETS, \
 	I9XX_COLORS, \
-	GEN_DEFAULT_PAGE_SIZES
+	GEN_DEFAULT_PAGE_SIZES, \
+	GEN_DEFAULT_REGIONS
 
 static const struct intel_device_info intel_i830_info = {
 	I830_FEATURES,
@@ -219,7 +224,8 @@ static const struct intel_device_info intel_i865g_info = {
 	I9XX_PIPE_OFFSETS, \
 	I9XX_CURSOR_OFFSETS, \
 	I9XX_COLORS, \
-	GEN_DEFAULT_PAGE_SIZES
+	GEN_DEFAULT_PAGE_SIZES, \
+	GEN_DEFAULT_REGIONS
 
 static const struct intel_device_info intel_i915g_info = {
 	GEN3_FEATURES,
@@ -304,7 +310,8 @@ static const struct intel_device_info intel_pineview_m_info = {
 	I9XX_PIPE_OFFSETS, \
 	I9XX_CURSOR_OFFSETS, \
 	I965_COLORS, \
-	GEN_DEFAULT_PAGE_SIZES
+	GEN_DEFAULT_PAGE_SIZES, \
+	GEN_DEFAULT_REGIONS
 
 static const struct intel_device_info intel_i965g_info = {
 	GEN4_FEATURES,
@@ -354,7 +361,8 @@ static const struct intel_device_info intel_gm45_info = {
 	I9XX_PIPE_OFFSETS, \
 	I9XX_CURSOR_OFFSETS, \
 	ILK_COLORS, \
-	GEN_DEFAULT_PAGE_SIZES
+	GEN_DEFAULT_PAGE_SIZES, \
+	GEN_DEFAULT_REGIONS
 
 static const struct intel_device_info intel_ironlake_d_info = {
 	GEN5_FEATURES,
@@ -384,7 +392,8 @@ static const struct intel_device_info intel_ironlake_m_info = {
 	I9XX_PIPE_OFFSETS, \
 	I9XX_CURSOR_OFFSETS, \
 	ILK_COLORS, \
-	GEN_DEFAULT_PAGE_SIZES
+	GEN_DEFAULT_PAGE_SIZES, \
+	GEN_DEFAULT_REGIONS
 
 #define SNB_D_PLATFORM \
 	GEN6_FEATURES, \
@@ -432,7 +441,8 @@ static const struct intel_device_info intel_sandybridge_m_gt2_info = {
 	IVB_PIPE_OFFSETS, \
 	IVB_CURSOR_OFFSETS, \
 	IVB_COLORS, \
-	GEN_DEFAULT_PAGE_SIZES
+	GEN_DEFAULT_PAGE_SIZES, \
+	GEN_DEFAULT_REGIONS
 
 #define IVB_D_PLATFORM \
 	GEN7_FEATURES, \
@@ -493,6 +503,7 @@ static const struct intel_device_info intel_valleyview_info = {
 	I9XX_CURSOR_OFFSETS,
 	I965_COLORS,
 	GEN_DEFAULT_PAGE_SIZES,
+	GEN_DEFAULT_REGIONS,
 };
 
 #define G75_FEATURES  \
@@ -587,6 +598,7 @@ static const struct intel_device_info intel_cherryview_info = {
 	CHV_CURSOR_OFFSETS,
 	CHV_COLORS,
 	GEN_DEFAULT_PAGE_SIZES,
+	GEN_DEFAULT_REGIONS,
 };
 
 #define GEN9_DEFAULT_PAGE_SIZES \
@@ -661,7 +673,8 @@ static const struct intel_device_info intel_skylake_gt4_info = {
 	HSW_PIPE_OFFSETS, \
 	IVB_CURSOR_OFFSETS, \
 	IVB_COLORS, \
-	GEN9_DEFAULT_PAGE_SIZES
+	GEN9_DEFAULT_PAGE_SIZES, \
+	GEN_DEFAULT_REGIONS
 
 static const struct intel_device_info intel_broxton_info = {
 	GEN9_LP_FEATURES,
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index c0299435d75e..72f98a111de1 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -6,6 +6,16 @@
 #include "intel_memory_region.h"
 #include "i915_drv.h"
 
+/* XXX: Hysterical raisins. BIT(inst) needs to just be (inst) at some point. */
+#define REGION_MAP(type, inst) \
+	BIT((type) + INTEL_MEMORY_TYPE_SHIFT) | BIT(inst)
+
+const u32 intel_region_map[] = {
+	[INTEL_REGION_SMEM] = REGION_MAP(INTEL_MEMORY_SYSTEM, 0),
+	[INTEL_REGION_LMEM] = REGION_MAP(INTEL_MEMORY_LOCAL, 0),
+	[INTEL_REGION_STOLEN] = REGION_MAP(INTEL_MEMORY_STOLEN, 0),
+};
+
 static u64
 intel_memory_region_free_pages(struct intel_memory_region *mem,
 			       struct list_head *blocks)
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index 2c165a7a5ab4..49b059a2be70 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -18,13 +18,39 @@ struct drm_i915_gem_object;
 struct intel_memory_region;
 struct sg_table;
 
+/**
+ *  Base memory type
+ */
+enum intel_memory_type {
+	INTEL_MEMORY_SYSTEM = 0,
+	INTEL_MEMORY_LOCAL,
+	INTEL_MEMORY_STOLEN,
+};
+
 enum intel_region_id {
-	INTEL_REGION_UNKNOWN = 0, /* Should be last */
+	INTEL_REGION_SMEM = 0,
+	INTEL_REGION_LMEM,
+	INTEL_REGION_STOLEN,
+	INTEL_REGION_UNKNOWN, /* Should be last */
 };
 
+#define REGION_SMEM     BIT(INTEL_REGION_SMEM)
+#define REGION_LMEM     BIT(INTEL_REGION_LMEM)
+#define REGION_STOLEN   BIT(INTEL_REGION_STOLEN)
+
+#define INTEL_MEMORY_TYPE_SHIFT 16
+
+#define MEMORY_TYPE_FROM_REGION(r) (ilog2((r) >> INTEL_MEMORY_TYPE_SHIFT))
+#define MEMORY_INSTANCE_FROM_REGION(r) (ilog2((r) & 0xffff))
+
 #define I915_ALLOC_MIN_PAGE_SIZE  BIT(0)
 #define I915_ALLOC_CONTIGUOUS     BIT(1)
 
+/**
+ * Memory regions encoded as type | instance
+ */
+extern const u32 intel_region_map[];
+
 struct intel_memory_region_ops {
 	unsigned int flags;
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index bc5e3c67409f..cb8c3a501cc7 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -72,8 +72,6 @@ static void mock_device_release(struct drm_device *dev)
 	mock_fini_ggtt(&i915->ggtt);
 	destroy_workqueue(i915->wq);
 
-	i915_gemfs_fini(i915);
-
 	i915_gem_cleanup_memory_regions(i915);
 
 	drm_mode_config_cleanup(&i915->drm);
@@ -165,7 +163,10 @@ struct drm_i915_private *mock_gem_device(void)
 		I915_GTT_PAGE_SIZE_64K |
 		I915_GTT_PAGE_SIZE_2M;
 
+	mkwrite_device_info(i915)->memory_regions = REGION_SMEM;
+
 	mock_uncore_init(&i915->uncore, i915);
+
 	i915_gem_init__mm(i915);
 	intel_gt_init_early(&i915->gt, i915);
 	atomic_inc(&i915->gt.wakeref.count); /* disable; no hw support */
@@ -196,8 +197,6 @@ struct drm_i915_private *mock_gem_device(void)
 
 	intel_engines_driver_register(i915);
 
-	WARN_ON(i915_gemfs_init(i915));
-
 	err = i915_gem_init_memory_regions(i915);
 	if (err)
 		goto err_context;
-- 
cgit v1.2.3


From 72405c3d7850c85dccbe4629720004ae933c2add Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 18 Oct 2019 10:07:51 +0100
Subject: drm/i915: treat stolen as a region

Convert stolen memory over to a region object. Still leaves open the
question with what to do with pre-allocated objects...

Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018090751.28295-3-matthew.auld@intel.com
---
 drivers/gpu/drm/i915/gem/i915_gem_stolen.c | 65 +++++++++++++++++++++++++-----
 drivers/gpu/drm/i915/gem/i915_gem_stolen.h |  3 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c        | 14 ++-----
 drivers/gpu/drm/i915/i915_pci.c            |  2 +-
 4 files changed, 61 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index c76260ce13e3..57cd8bc2657c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -10,6 +10,7 @@
 #include <drm/drm_mm.h>
 #include <drm/i915_drm.h>
 
+#include "gem/i915_gem_region.h"
 #include "i915_drv.h"
 #include "i915_gem_stolen.h"
 
@@ -150,7 +151,7 @@ static int i915_adjust_stolen(struct drm_i915_private *dev_priv,
 	return 0;
 }
 
-void i915_gem_cleanup_stolen(struct drm_i915_private *dev_priv)
+static void i915_gem_cleanup_stolen(struct drm_i915_private *dev_priv)
 {
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return;
@@ -355,7 +356,7 @@ static void icl_get_stolen_reserved(struct drm_i915_private *i915,
 	}
 }
 
-int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
+static int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 {
 	resource_size_t reserved_base, stolen_top;
 	resource_size_t reserved_total, reserved_size;
@@ -539,6 +540,9 @@ i915_gem_object_release_stolen(struct drm_i915_gem_object *obj)
 
 	i915_gem_stolen_remove_node(dev_priv, stolen);
 	kfree(stolen);
+
+	if (obj->mm.region)
+		i915_gem_object_release_memory_region(obj);
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_object_stolen_ops = {
@@ -548,8 +552,9 @@ static const struct drm_i915_gem_object_ops i915_gem_object_stolen_ops = {
 };
 
 static struct drm_i915_gem_object *
-_i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
-			       struct drm_mm_node *stolen)
+__i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
+				struct drm_mm_node *stolen,
+				struct intel_memory_region *mem)
 {
 	struct drm_i915_gem_object *obj;
 	unsigned int cache_level;
@@ -571,6 +576,9 @@ _i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
 	if (err)
 		goto cleanup;
 
+	if (mem)
+		i915_gem_object_init_memory_region(obj, mem, 0);
+
 	return obj;
 
 cleanup:
@@ -579,10 +587,12 @@ err:
 	return ERR_PTR(err);
 }
 
-struct drm_i915_gem_object *
-i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
-			      resource_size_t size)
+static struct drm_i915_gem_object *
+_i915_gem_object_create_stolen(struct intel_memory_region *mem,
+			       resource_size_t size,
+			       unsigned int flags)
 {
+	struct drm_i915_private *dev_priv = mem->i915;
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *stolen;
 	int ret;
@@ -603,7 +613,7 @@ i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
 		goto err_free;
 	}
 
-	obj = _i915_gem_object_create_stolen(dev_priv, stolen);
+	obj = __i915_gem_object_create_stolen(dev_priv, stolen, mem);
 	if (IS_ERR(obj))
 		goto err_remove;
 
@@ -616,6 +626,43 @@ err_free:
 	return obj;
 }
 
+struct drm_i915_gem_object *
+i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
+			      resource_size_t size)
+{
+	return i915_gem_object_create_region(dev_priv->mm.regions[INTEL_REGION_STOLEN],
+					     size, I915_BO_ALLOC_CONTIGUOUS);
+}
+
+static int init_stolen(struct intel_memory_region *mem)
+{
+	/*
+	 * Initialise stolen early so that we may reserve preallocated
+	 * objects for the BIOS to KMS transition.
+	 */
+	return i915_gem_init_stolen(mem->i915);
+}
+
+static void release_stolen(struct intel_memory_region *mem)
+{
+	i915_gem_cleanup_stolen(mem->i915);
+}
+
+static const struct intel_memory_region_ops i915_region_stolen_ops = {
+	.init = init_stolen,
+	.release = release_stolen,
+	.create_object = _i915_gem_object_create_stolen,
+};
+
+struct intel_memory_region *i915_gem_stolen_setup(struct drm_i915_private *i915)
+{
+	return intel_memory_region_create(i915,
+					  intel_graphics_stolen_res.start,
+					  resource_size(&intel_graphics_stolen_res),
+					  PAGE_SIZE, 0,
+					  &i915_region_stolen_ops);
+}
+
 struct drm_i915_gem_object *
 i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv,
 					       resource_size_t stolen_offset,
@@ -655,7 +702,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 		return ERR_PTR(ret);
 	}
 
-	obj = _i915_gem_object_create_stolen(dev_priv, stolen);
+	obj = __i915_gem_object_create_stolen(dev_priv, stolen, NULL);
 	if (IS_ERR(obj)) {
 		DRM_DEBUG_DRIVER("failed to allocate stolen object\n");
 		i915_gem_stolen_remove_node(dev_priv, stolen);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h
index 2289644d8604..c1040627fbf3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h
@@ -21,8 +21,7 @@ int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv,
 					 u64 end);
 void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv,
 				 struct drm_mm_node *node);
-int i915_gem_init_stolen(struct drm_i915_private *dev_priv);
-void i915_gem_cleanup_stolen(struct drm_i915_private *dev_priv);
+struct intel_memory_region *i915_gem_stolen_setup(struct drm_i915_private *i915);
 struct drm_i915_gem_object *
 i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
 			      resource_size_t size);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 263f1cea0b64..0df057838a24 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2748,8 +2748,6 @@ void i915_gem_cleanup_memory_regions(struct drm_i915_private *i915)
 {
 	int i;
 
-	i915_gem_cleanup_stolen(i915);
-
 	for (i = 0; i < INTEL_REGION_UNKNOWN; i++) {
 		struct intel_memory_region *region = i915->mm.regions[i];
 
@@ -2762,15 +2760,6 @@ int i915_gem_init_memory_regions(struct drm_i915_private *i915)
 {
 	int err, i;
 
-	/*
-	 * Initialise stolen early so that we may reserve preallocated
-	 * objects for the BIOS to KMS transition.
-	 */
-	/* XXX: stolen will become a region at some point */
-	err = i915_gem_init_stolen(i915);
-	if (err)
-		return err;
-
 	for (i = 0; i < INTEL_REGION_UNKNOWN; i++) {
 		struct intel_memory_region *mem = ERR_PTR(-ENODEV);
 		u32 type;
@@ -2783,6 +2772,9 @@ int i915_gem_init_memory_regions(struct drm_i915_private *i915)
 		case INTEL_MEMORY_SYSTEM:
 			mem = i915_gem_shmem_setup(i915);
 			break;
+		case INTEL_MEMORY_STOLEN:
+			mem = i915_gem_stolen_setup(i915);
+			break;
 		}
 
 		if (IS_ERR(mem)) {
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index e55ab2724996..f9a3bfe68689 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -152,7 +152,7 @@
 	.page_sizes = I915_GTT_PAGE_SIZE_4K
 
 #define GEN_DEFAULT_REGIONS \
-	.memory_regions = REGION_SMEM
+	.memory_regions = REGION_SMEM | REGION_STOLEN
 
 #define I830_FEATURES \
 	GEN(2), \
-- 
cgit v1.2.3


From bcce7d90d120cddc726d5c98aa46188daef141f3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 18 Oct 2019 14:07:03 +0100
Subject: drm/i915/selftests: Add the mock engine to the gt->engine[]

Remember to include the newly created mock engine in the list of
available engines inside the gt.

Fixes: a50134b1983b ("drm/i915: Make for_each_engine_masked work on intel_gt")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018130703.31125-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/mock_engine.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index 747f7c7790eb..123db2c3f956 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -253,6 +253,7 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	snprintf(engine->base.name, sizeof(engine->base.name), "%s", name);
 	engine->base.id = id;
 	engine->base.mask = BIT(id);
+	engine->base.legacy_idx = INVALID_ENGINE;
 	engine->base.instance = id;
 	engine->base.status_page.addr = (void *)(engine + 1);
 
@@ -267,6 +268,9 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	engine->base.reset.finish = mock_reset_finish;
 	engine->base.cancel_requests = mock_cancel_requests;
 
+	i915->gt.engine[id] = &engine->base;
+	i915->gt.engine_class[0][id] = &engine->base;
+
 	/* fake hw queue */
 	spin_lock_init(&engine->hw_lock);
 	timer_setup(&engine->hw_delay, hw_delay_complete, 0);
-- 
cgit v1.2.3


From c6e07ada8eaa3ff66868a8bd6b1b9cdfa6d9fe21 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 18 Oct 2019 12:53:31 +0100
Subject: drm/i915/gt: Convert the leftover for_each_engine(gt)

Use the local gt for iterating over the available set of engines.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018115331.8980-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gt/intel_rc6.c        | 12 ++++++------
 drivers/gpu/drm/i915/gt/intel_ringbuffer.c |  6 +++---
 drivers/gpu/drm/i915/i915_gem_gtt.c        |  2 +-
 drivers/gpu/drm/i915/i915_pmu.c            |  2 +-
 4 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index 71184aa72896..70f0e01a38b9 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -65,7 +65,7 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
 
 	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
 	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-	for_each_engine(engine, rc6_to_gt(rc6)->i915, id)
+	for_each_engine(engine, rc6_to_gt(rc6), id)
 		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
 
 	set(uncore, GUC_MAX_IDLE_COUNT, 0xA);
@@ -133,7 +133,7 @@ static void gen9_rc6_enable(struct intel_rc6 *rc6)
 
 	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
 	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-	for_each_engine(engine, rc6_to_gt(rc6)->i915, id)
+	for_each_engine(engine, rc6_to_gt(rc6), id)
 		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
 
 	set(uncore, GUC_MAX_IDLE_COUNT, 0xA);
@@ -192,7 +192,7 @@ static void gen8_rc6_enable(struct intel_rc6 *rc6)
 	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
 	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
 	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
-	for_each_engine(engine, rc6_to_gt(rc6)->i915, id)
+	for_each_engine(engine, rc6_to_gt(rc6), id)
 		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
 	set(uncore, GEN6_RC_SLEEP, 0);
 	set(uncore, GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */
@@ -219,7 +219,7 @@ static void gen6_rc6_enable(struct intel_rc6 *rc6)
 	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000);
 	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25);
 
-	for_each_engine(engine, i915, id)
+	for_each_engine(engine, rc6_to_gt(rc6), id)
 		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
 
 	set(uncore, GEN6_RC_SLEEP, 0);
@@ -344,7 +344,7 @@ static void chv_rc6_enable(struct intel_rc6 *rc6)
 	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
 	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
 
-	for_each_engine(engine, rc6_to_gt(rc6)->i915, id)
+	for_each_engine(engine, rc6_to_gt(rc6), id)
 		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
 	set(uncore, GEN6_RC_SLEEP, 0);
 
@@ -371,7 +371,7 @@ static void vlv_rc6_enable(struct intel_rc6 *rc6)
 	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000);
 	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25);
 
-	for_each_engine(engine, rc6_to_gt(rc6)->i915, id)
+	for_each_engine(engine, rc6_to_gt(rc6), id)
 		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
 
 	set(uncore, GEN6_RC6_THRESHOLD, 0x557);
diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
index 311fdc0a21bc..bf631f15aa78 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
@@ -1609,7 +1609,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 			struct intel_engine_cs *signaller;
 
 			*cs++ = MI_LOAD_REGISTER_IMM(num_engines);
-			for_each_engine(signaller, i915, id) {
+			for_each_engine(signaller, engine->gt, id) {
 				if (signaller == engine)
 					continue;
 
@@ -1663,7 +1663,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 			i915_reg_t last_reg = {}; /* keep gcc quiet */
 
 			*cs++ = MI_LOAD_REGISTER_IMM(num_engines);
-			for_each_engine(signaller, i915, id) {
+			for_each_engine(signaller, engine->gt, id) {
 				if (signaller == engine)
 					continue;
 
@@ -1676,7 +1676,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 			/* Insert a delay before the next switch! */
 			*cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
 			*cs++ = i915_mmio_reg_offset(last_reg);
-			*cs++ = intel_gt_scratch_offset(rq->engine->gt,
+			*cs++ = intel_gt_scratch_offset(engine->gt,
 							INTEL_GT_SCRATCH_FIELD_DEFAULT);
 			*cs++ = MI_NOOP;
 		}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 0df057838a24..3148d5946b63 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1569,7 +1569,7 @@ static void gen7_ppgtt_enable(struct intel_gt *gt)
 	}
 	intel_uncore_write(uncore, GAM_ECOCHK, ecochk);
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt, id) {
 		/* GFX_MODE is per-ring on gen7+ */
 		ENGINE_WRITE(engine,
 			     RING_MODE_GEN7,
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 144c32eed045..85912917c062 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -301,7 +301,7 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 	if ((i915->pmu.enable & ENGINE_SAMPLE_MASK) == 0)
 		return;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct intel_engine_pmu *pmu = &engine->pmu;
 		unsigned long flags;
 		bool busy;
-- 
cgit v1.2.3


From 30a027dcccc27051b3145ff9bb756d79038ad320 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 15 Oct 2019 18:27:57 +0300
Subject: drm/i915: Move the cursor rotation handling into
 intel_cursor_check_surface()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unlike other planes the cursor currently handles 180 degree rotation
adjustment during the hardware programming phase. Let's move that
stuff into intel_cursor_check_surface() to match how we do things
with other plane types.

And while at we'll plop in the final src x/y coordinates (which will
actually always be zero) into the src rect and color_plane[0].x/y,
just for some extra consistency.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015152757.12231-1-ville.syrjala@linux.intel.com
Reviewed-by: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 31 ++++++++++++++++++++--------
 1 file changed, 22 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 164ded862148..96de58281301 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -10530,15 +10530,7 @@ static u32 intel_cursor_base(const struct intel_plane_state *plane_state)
 	else
 		base = intel_plane_ggtt_offset(plane_state);
 
-	base += plane_state->color_plane[0].offset;
-
-	/* ILK+ do this automagically */
-	if (HAS_GMCH(dev_priv) &&
-	    plane_state->base.rotation & DRM_MODE_ROTATE_180)
-		base += (drm_rect_height(&plane_state->base.dst) *
-			 drm_rect_width(&plane_state->base.dst) - 1) * fb->format->cpp[0];
-
-	return base;
+	return base + plane_state->color_plane[0].offset;
 }
 
 static u32 intel_cursor_position(const struct intel_plane_state *plane_state)
@@ -10575,6 +10567,9 @@ static bool intel_cursor_size_ok(const struct intel_plane_state *plane_state)
 
 static int intel_cursor_check_surface(struct intel_plane_state *plane_state)
 {
+	struct drm_i915_private *dev_priv =
+		to_i915(plane_state->base.plane->dev);
+	unsigned int rotation = plane_state->base.rotation;
 	int src_x, src_y;
 	u32 offset;
 	int ret;
@@ -10598,7 +10593,25 @@ static int intel_cursor_check_surface(struct intel_plane_state *plane_state)
 		return -EINVAL;
 	}
 
+	/*
+	 * Put the final coordinates back so that the src
+	 * coordinate checks will see the right values.
+	 */
+	drm_rect_translate_to(&plane_state->base.src,
+			      src_x << 16, src_y << 16);
+
+	/* ILK+ do this automagically in hardware */
+	if (HAS_GMCH(dev_priv) && rotation & DRM_MODE_ROTATE_180) {
+		const struct drm_framebuffer *fb = plane_state->base.fb;
+		int src_w = drm_rect_width(&plane_state->base.src) >> 16;
+		int src_h = drm_rect_height(&plane_state->base.src) >> 16;
+
+		offset += (src_h * src_w - 1) * fb->format->cpp[0];
+	}
+
 	plane_state->color_plane[0].offset = offset;
+	plane_state->color_plane[0].x = src_x;
+	plane_state->color_plane[0].y = src_y;
 
 	return 0;
 }
-- 
cgit v1.2.3


From c08f995a284dc202a934530ee73cc7136665af38 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 2 Oct 2019 19:25:00 +0300
Subject: drm/i915: Polish possible_clones setup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace the hand rolled stuff with drm_encoder_mask() when populating
possible_clones, and rename the function to
intel_encoder_possible_clones() to make it clear what it's used for.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191002162505.30716-1-ville.syrjala@linux.intel.com
Reviewed-by: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 96de58281301..0233831f559a 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -15261,21 +15261,18 @@ int intel_get_pipe_from_crtc_id_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
-static int intel_encoder_clones(struct intel_encoder *encoder)
+static u32 intel_encoder_possible_clones(struct intel_encoder *encoder)
 {
 	struct drm_device *dev = encoder->base.dev;
 	struct intel_encoder *source_encoder;
-	int index_mask = 0;
-	int entry = 0;
+	u32 possible_clones = 0;
 
 	for_each_intel_encoder(dev, source_encoder) {
 		if (encoders_cloneable(encoder, source_encoder))
-			index_mask |= (1 << entry);
-
-		entry++;
+			possible_clones |= drm_encoder_mask(&source_encoder->base);
 	}
 
-	return index_mask;
+	return possible_clones;
 }
 
 static u32 intel_encoder_possible_crtcs(struct intel_encoder *encoder)
@@ -15595,7 +15592,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 		encoder->base.possible_crtcs =
 			intel_encoder_possible_crtcs(encoder);
 		encoder->base.possible_clones =
-			intel_encoder_clones(encoder);
+			intel_encoder_possible_clones(encoder);
 	}
 
 	intel_init_pch_refclk(dev_priv);
-- 
cgit v1.2.3


From 98c93394ba907e6b741c67dc6affea78c2a940a0 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 18 Jul 2019 17:43:39 +0300
Subject: drm/i915: Refuse modes with hdisplay==4096 on pre-HSW DP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The DP port/pipe goes wonky if we try to use timings with
hdisplay==4096 on pre-HSW platforms. The link fails to train
and the pipe may not signal vblank interrupts. On HDMI such at
mode works just fine (tested on ELK/SNB/CHV). So let's refuse
such modes on DP on older platforms.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190718144340.1114-1-ville.syrjala@linux.intel.com
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index c4c081c79dd9..3792d143bea9 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -591,6 +591,25 @@ static u8 intel_dp_dsc_get_slice_count(struct intel_dp *intel_dp,
 	return 0;
 }
 
+static bool intel_dp_hdisplay_bad(struct drm_i915_private *dev_priv,
+				  int hdisplay)
+{
+	/*
+	 * Older platforms don't like hdisplay==4096 with DP.
+	 *
+	 * On ILK/SNB/IVB the pipe seems to be somewhat running (scanline
+	 * and frame counter increment), but we don't get vblank interrupts,
+	 * and the pipe underruns immediately. The link also doesn't seem
+	 * to get trained properly.
+	 *
+	 * On CHV the vblank interrupts don't seem to disappear but
+	 * otherwise the symptoms are similar.
+	 *
+	 * TODO: confirm the behaviour on HSW+
+	 */
+	return hdisplay == 4096 && !HAS_DDI(dev_priv);
+}
+
 static enum drm_mode_status
 intel_dp_mode_valid(struct drm_connector *connector,
 		    struct drm_display_mode *mode)
@@ -626,6 +645,9 @@ intel_dp_mode_valid(struct drm_connector *connector,
 	max_rate = intel_dp_max_data_rate(max_link_clock, max_lanes);
 	mode_rate = intel_dp_link_required(target_clock, 18);
 
+	if (intel_dp_hdisplay_bad(dev_priv, mode->hdisplay))
+		return MODE_H_ILLEGAL;
+
 	/*
 	 * Output bpp is stored in 6.4 format so right shift by 4 to get the
 	 * integer value since we support only integer values of bpp.
@@ -2345,6 +2367,9 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
 		return -EINVAL;
 
+	if (intel_dp_hdisplay_bad(dev_priv, adjusted_mode->crtc_hdisplay))
+		return -EINVAL;
+
 	ret = intel_dp_compute_link_config(encoder, pipe_config, conn_state);
 	if (ret < 0)
 		return ret;
-- 
cgit v1.2.3


From d7a145849b680075ce94d8b341905104e2ee58d0 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 11 Oct 2019 23:09:42 +0300
Subject: drm/i915: Nuke the useless changed param from
 skl_ddb_add_affected_pipes()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

changed==true just means we have some crtcs in the state. All the
stuff following this only operates on crtcs in the state anyway so
there is no point in having this bool.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011200949.7839-2-ville.syrjala@linux.intel.com
Reviewed-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
---
 drivers/gpu/drm/i915/intel_pm.c | 30 ++++--------------------------
 1 file changed, 4 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index b306e2338f5a..49568270a89d 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5424,35 +5424,14 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 }
 
 static int
-skl_ddb_add_affected_pipes(struct intel_atomic_state *state, bool *changed)
+skl_ddb_add_affected_pipes(struct intel_atomic_state *state)
 {
 	struct drm_device *dev = state->base.dev;
 	const struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc;
 	struct intel_crtc_state *crtc_state;
 	u32 realloc_pipes = pipes_modified(state);
-	int ret, i;
-
-	/*
-	 * When we distrust bios wm we always need to recompute to set the
-	 * expected DDB allocations for each CRTC.
-	 */
-	if (dev_priv->wm.distrust_bios_wm)
-		(*changed) = true;
-
-	/*
-	 * If this transaction isn't actually touching any CRTC's, don't
-	 * bother with watermark calculation.  Note that if we pass this
-	 * test, we're guaranteed to hold at least one CRTC state mutex,
-	 * which means we can safely use values like dev_priv->active_pipes
-	 * since any racing commits that want to update them would need to
-	 * hold _all_ CRTC state mutexes.
-	 */
-	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i)
-		(*changed) = true;
-
-	if (!*changed)
-		return 0;
+	int ret;
 
 	/*
 	 * If this is our first atomic update following hardware readout,
@@ -5576,14 +5555,13 @@ skl_compute_wm(struct intel_atomic_state *state)
 	struct intel_crtc_state *new_crtc_state;
 	struct intel_crtc_state *old_crtc_state;
 	struct skl_ddb_values *results = &state->wm_results;
-	bool changed = false;
 	int ret, i;
 
 	/* Clear all dirty flags */
 	results->dirty_pipes = 0;
 
-	ret = skl_ddb_add_affected_pipes(state, &changed);
-	if (ret || !changed)
+	ret = skl_ddb_add_affected_pipes(state);
+	if (ret)
 		return ret;
 
 	/*
-- 
cgit v1.2.3


From 49e0ed3848d0e3ef22c3a458ded8847cbf08330e Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 11 Oct 2019 23:09:43 +0300
Subject: drm/i915: Nuke 'realloc_pipes'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The 'realloc_pipes' bitmask is pointless. It is either:
a) the set of pipes which are already part of the state,
   in which case adding them again is entirely redundant
b) the set of all pipes which we then add to the state

Also the fact that 'realloc_pipes' uses the crtc indexes is
going to bite is at some point so best get rid of it quick.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011200949.7839-3-ville.syrjala@linux.intel.com
Reviewed-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
---
 drivers/gpu/drm/i915/intel_pm.c | 50 +++++++++++++++++------------------------
 1 file changed, 21 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 49568270a89d..3536c2e975e7 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5235,19 +5235,6 @@ bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry *ddb,
 	return false;
 }
 
-static u32
-pipes_modified(struct intel_atomic_state *state)
-{
-	struct intel_crtc *crtc;
-	struct intel_crtc_state *crtc_state;
-	u32 i, ret = 0;
-
-	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i)
-		ret |= drm_crtc_mask(&crtc->base);
-
-	return ret;
-}
-
 static int
 skl_ddb_add_affected_planes(const struct intel_crtc_state *old_crtc_state,
 			    struct intel_crtc_state *new_crtc_state)
@@ -5423,14 +5410,26 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 	}
 }
 
+static int intel_add_all_pipes(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_crtc *crtc;
+
+	for_each_intel_crtc(&dev_priv->drm, crtc) {
+		struct intel_crtc_state *crtc_state;
+
+		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
+		if (IS_ERR(crtc_state))
+			return PTR_ERR(crtc_state);
+	}
+
+	return 0;
+}
+
 static int
 skl_ddb_add_affected_pipes(struct intel_atomic_state *state)
 {
-	struct drm_device *dev = state->base.dev;
-	const struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *crtc;
-	struct intel_crtc_state *crtc_state;
-	u32 realloc_pipes = pipes_modified(state);
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	int ret;
 
 	/*
@@ -5440,7 +5439,7 @@ skl_ddb_add_affected_pipes(struct intel_atomic_state *state)
 	 * ensure a full DDB recompute.
 	 */
 	if (dev_priv->wm.distrust_bios_wm) {
-		ret = drm_modeset_lock(&dev->mode_config.connection_mutex,
+		ret = drm_modeset_lock(&dev_priv->drm.mode_config.connection_mutex,
 				       state->base.acquire_ctx);
 		if (ret)
 			return ret;
@@ -5471,18 +5470,11 @@ skl_ddb_add_affected_pipes(struct intel_atomic_state *state)
 	 * to grab the lock on *all* CRTC's.
 	 */
 	if (state->active_pipe_changes || state->modeset) {
-		realloc_pipes = ~0;
 		state->wm_results.dirty_pipes = ~0;
-	}
 
-	/*
-	 * We're not recomputing for the pipes not included in the commit, so
-	 * make sure we start with the current state.
-	 */
-	for_each_intel_crtc_mask(dev, crtc, realloc_pipes) {
-		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
-		if (IS_ERR(crtc_state))
-			return PTR_ERR(crtc_state);
+		ret = intel_add_all_pipes(state);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 36b53a291b6a9213b7c053c7d72931bb89587440 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 11 Oct 2019 23:09:44 +0300
Subject: drm/i915: Make dirty_pipes refer to pipes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Despite the its name dirty_pipes refers to crtc indexes. Let's
change its behaviout to match the name.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011200949.7839-4-ville.syrjala@linux.intel.com
Reviewed-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c |  9 +++------
 drivers/gpu/drm/i915/intel_pm.c              | 13 ++++++-------
 2 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 0233831f559a..23450f16df66 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -13934,7 +13934,6 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 	struct intel_crtc_state *old_crtc_state, *new_crtc_state;
 	unsigned int updated = 0;
 	bool progress;
-	enum pipe pipe;
 	int i;
 	u8 hw_enabled_slices = dev_priv->wm.skl_hw.ddb.enabled_slices;
 	u8 required_slices = state->wm_results.ddb.enabled_slices;
@@ -13959,12 +13958,10 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 		progress = false;
 
 		for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
+			enum pipe pipe = crtc->pipe;
 			bool vbl_wait = false;
-			unsigned int cmask = drm_crtc_mask(&crtc->base);
-
-			pipe = crtc->pipe;
 
-			if (updated & cmask || !new_crtc_state->base.active)
+			if (updated & BIT(crtc->pipe) || !new_crtc_state->base.active)
 				continue;
 
 			if (skl_ddb_allocation_overlaps(&new_crtc_state->wm.skl.ddb,
@@ -13972,7 +13969,7 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 							INTEL_NUM_PIPES(dev_priv), i))
 				continue;
 
-			updated |= cmask;
+			updated |= BIT(pipe);
 			entries[i] = new_crtc_state->wm.skl.ddb;
 
 			/*
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 3536c2e975e7..2b71d52a4ede 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5575,7 +5575,7 @@ skl_compute_wm(struct intel_atomic_state *state)
 		if (!skl_pipe_wm_equals(crtc,
 					&old_crtc_state->wm.skl.optimal,
 					&new_crtc_state->wm.skl.optimal))
-			results->dirty_pipes |= drm_crtc_mask(&crtc->base);
+			results->dirty_pipes |= BIT(crtc->pipe);
 	}
 
 	ret = skl_compute_ddb(state);
@@ -5595,7 +5595,7 @@ static void skl_atomic_update_crtc_wm(struct intel_atomic_state *state,
 	struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal;
 	enum pipe pipe = crtc->pipe;
 
-	if (!(state->wm_results.dirty_pipes & drm_crtc_mask(&crtc->base)))
+	if ((state->wm_results.dirty_pipes & BIT(crtc->pipe)) == 0)
 		return;
 
 	I915_WRITE(PIPE_WM_LINETIME(pipe), pipe_wm->linetime);
@@ -5604,12 +5604,11 @@ static void skl_atomic_update_crtc_wm(struct intel_atomic_state *state,
 static void skl_initial_wm(struct intel_atomic_state *state,
 			   struct intel_crtc_state *crtc_state)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct drm_device *dev = intel_crtc->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct skl_ddb_values *results = &state->wm_results;
 
-	if ((results->dirty_pipes & drm_crtc_mask(&intel_crtc->base)) == 0)
+	if ((results->dirty_pipes & BIT(crtc->pipe)) == 0)
 		return;
 
 	mutex_lock(&dev_priv->wm.wm_mutex);
@@ -5758,7 +5757,7 @@ void skl_wm_get_hw_state(struct drm_i915_private *dev_priv)
 		skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal);
 
 		if (crtc->active)
-			hw->dirty_pipes |= drm_crtc_mask(&crtc->base);
+			hw->dirty_pipes |= BIT(crtc->pipe);
 	}
 
 	if (dev_priv->active_pipes) {
-- 
cgit v1.2.3


From 2edb3de9e599e79db4028335df2a64f3ad014b2a Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 10 Oct 2019 17:51:23 +0300
Subject: drm/i915: Shrink eDRAM ways/sets arrays
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make the ways/sets arrays static cosnt u8 to shrink things a bit.

    text	   data	    bss	    dec	    hex	filename
-  23935	    629	    128	  24692	   6074	i915_drv.o
+  23818	    629	    128	  24575	   5fff	i915_drv.o

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191010145127.7487-1-ville.syrjala@linux.intel.com
Reviewed-by: Ramalingam C <ramalingam.c@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index fd532b8cfdb8..b3a92951f671 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1073,8 +1073,8 @@ intel_get_dram_info(struct drm_i915_private *dev_priv)
 
 static u32 gen9_edram_size_mb(struct drm_i915_private *dev_priv, u32 cap)
 {
-	const unsigned int ways[8] = { 4, 8, 12, 16, 16, 16, 16, 16 };
-	const unsigned int sets[4] = { 1, 1, 2, 2 };
+	static const u8 ways[8] = { 4, 8, 12, 16, 16, 16, 16, 16 };
+	static const u8 sets[4] = { 1, 1, 2, 2 };
 
 	return EDRAM_NUM_BANKS(cap) *
 		ways[EDRAM_WAYS_IDX(cap)] *
-- 
cgit v1.2.3


From 67fdd8ea53195ee265cf4b8bf5498a549cebcd71 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 10 Oct 2019 17:51:24 +0300
Subject: drm/i915: s/hdcp2_hdmi_msg_data/hdcp2_hdmi_msg_timeout/
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The array is there only for timeout, "data" doesn't mean anything
so let's rename the thing to be more descriptive.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191010145127.7487-2-ville.syrjala@linux.intel.com
Reviewed-by: Ramalingam C <ramalingam.c@intel.com>
---
 drivers/gpu/drm/i915/display/intel_hdmi.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 92d1cbbbee2b..f779f60a1160 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -1535,13 +1535,13 @@ bool intel_hdmi_hdcp_check_link(struct intel_digital_port *intel_dig_port)
 	return true;
 }
 
-struct hdcp2_hdmi_msg_data {
+struct hdcp2_hdmi_msg_timeout {
 	u8 msg_id;
 	u32 timeout;
 	u32 timeout2;
 };
 
-static const struct hdcp2_hdmi_msg_data hdcp2_msg_data[] = {
+static const struct hdcp2_hdmi_msg_timeout hdcp2_msg_timeout[] = {
 	{ HDCP_2_2_AKE_INIT, 0, 0 },
 	{ HDCP_2_2_AKE_SEND_CERT, HDCP_2_2_CERT_TIMEOUT_MS, 0 },
 	{ HDCP_2_2_AKE_NO_STORED_KM, 0, 0 },
@@ -1572,12 +1572,12 @@ static int get_hdcp2_msg_timeout(u8 msg_id, bool is_paired)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(hdcp2_msg_data); i++)
-		if (hdcp2_msg_data[i].msg_id == msg_id &&
+	for (i = 0; i < ARRAY_SIZE(hdcp2_msg_timeout); i++)
+		if (hdcp2_msg_timeout[i].msg_id == msg_id &&
 		    (msg_id != HDCP_2_2_AKE_SEND_HPRIME || is_paired))
-			return hdcp2_msg_data[i].timeout;
-		else if (hdcp2_msg_data[i].msg_id == msg_id)
-			return hdcp2_msg_data[i].timeout2;
+			return hdcp2_msg_timeout[i].timeout;
+		else if (hdcp2_msg_timeout[i].msg_id == msg_id)
+			return hdcp2_msg_timeout[i].timeout2;
 
 	return -EINVAL;
 }
-- 
cgit v1.2.3


From a4f40484e7f1dff56bb9f286cc59ffa36e0259eb Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Fri, 18 Oct 2019 10:53:14 +0800
Subject: nvme-pci: Set the prp2 correctly when using more than 4k page

In the current code, the nvme is using a fixed 4k PRP entry size,
but if the kernel use a page size which is more than 4k, we should
consider the situation that the bv_offset may be larger than the
dev->ctrl.page_size. Otherwise we may miss setting the prp2 and then
cause the command can't be executed correctly.

Fixes: dff824b2aadb ("nvme-pci: optimize mapping of small single segment requests")
Cc: stable@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 4b181969c432..869f462e6b6e 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -773,7 +773,8 @@ static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev,
 		struct bio_vec *bv)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
-	unsigned int first_prp_len = dev->ctrl.page_size - bv->bv_offset;
+	unsigned int offset = bv->bv_offset & (dev->ctrl.page_size - 1);
+	unsigned int first_prp_len = dev->ctrl.page_size - offset;
 
 	iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0);
 	if (dma_mapping_error(dev->dev, iod->first_dma))
-- 
cgit v1.2.3


From 770ce5a07190e26b18f46037f357c1870ce29b30 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 10 Oct 2019 17:51:25 +0300
Subject: drm/i915: Remove dead weight from hdcp2_msg_timeout[]
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The .read_2_2() hooks is never called for any of the message
types with a zero timeout. So it's all just dead weight which
we can chuck.

    text	   data	    bss	    dec	    hex	filename
-  34701	    360	      0	  35061	   88f5	intel_hdmi.o
+  34633	    360	      0	  34993	   88b1	intel_hdmi.o

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191010145127.7487-3-ville.syrjala@linux.intel.com
Reviewed-by: Ramalingam C <ramalingam.c@intel.com>
---
 drivers/gpu/drm/i915/display/intel_hdmi.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index f779f60a1160..ef2c19470b92 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -1542,19 +1542,12 @@ struct hdcp2_hdmi_msg_timeout {
 };
 
 static const struct hdcp2_hdmi_msg_timeout hdcp2_msg_timeout[] = {
-	{ HDCP_2_2_AKE_INIT, 0, 0 },
 	{ HDCP_2_2_AKE_SEND_CERT, HDCP_2_2_CERT_TIMEOUT_MS, 0 },
-	{ HDCP_2_2_AKE_NO_STORED_KM, 0, 0 },
-	{ HDCP_2_2_AKE_STORED_KM, 0, 0 },
 	{ HDCP_2_2_AKE_SEND_HPRIME, HDCP_2_2_HPRIME_PAIRED_TIMEOUT_MS,
 	  HDCP_2_2_HPRIME_NO_PAIRED_TIMEOUT_MS },
 	{ HDCP_2_2_AKE_SEND_PAIRING_INFO, HDCP_2_2_PAIRING_TIMEOUT_MS, 0 },
-	{ HDCP_2_2_LC_INIT, 0, 0 },
 	{ HDCP_2_2_LC_SEND_LPRIME, HDCP_2_2_HDMI_LPRIME_TIMEOUT_MS, 0 },
-	{ HDCP_2_2_SKE_SEND_EKS, 0, 0 },
 	{ HDCP_2_2_REP_SEND_RECVID_LIST, HDCP_2_2_RECVID_LIST_TIMEOUT_MS, 0 },
-	{ HDCP_2_2_REP_SEND_ACK, 0, 0 },
-	{ HDCP_2_2_REP_STREAM_MANAGE, 0, 0 },
 	{ HDCP_2_2_REP_STREAM_READY, HDCP_2_2_STREAM_READY_TIMEOUT_MS, 0 },
 };
 
-- 
cgit v1.2.3


From eac03efdc85f062b16c72dae848b56aba261d566 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 10 Oct 2019 17:51:26 +0300
Subject: drm/i915: Remove hdcp2_hdmi_msg_timeout.timeout2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The only reason for the timeout2 value in the array is the
HDCP_2_2_AKE_SEND_HPRIME message. But that one still needs
special casing inside the loop, and so just ends up making
the code harder to read. Let's just remove this leaky
timeout2 abstraction and special case that one command
in a way that is easy to understand. We can then remove the
timeout2 member from struct entirely.

    text	   data	    bss	    dec	    hex	filename
-  34633	    360	      0	  34993	   88b1	intel_hdmi.o
+  34521	    360	      0	  34881	   8841	intel_hdmi.o

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191010145127.7487-4-ville.syrjala@linux.intel.com
Reviewed-by: Ramalingam C <ramalingam.c@intel.com>
---
 drivers/gpu/drm/i915/display/intel_hdmi.c | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index ef2c19470b92..3b88d7b0aac5 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -1538,17 +1538,14 @@ bool intel_hdmi_hdcp_check_link(struct intel_digital_port *intel_dig_port)
 struct hdcp2_hdmi_msg_timeout {
 	u8 msg_id;
 	u32 timeout;
-	u32 timeout2;
 };
 
 static const struct hdcp2_hdmi_msg_timeout hdcp2_msg_timeout[] = {
-	{ HDCP_2_2_AKE_SEND_CERT, HDCP_2_2_CERT_TIMEOUT_MS, 0 },
-	{ HDCP_2_2_AKE_SEND_HPRIME, HDCP_2_2_HPRIME_PAIRED_TIMEOUT_MS,
-	  HDCP_2_2_HPRIME_NO_PAIRED_TIMEOUT_MS },
-	{ HDCP_2_2_AKE_SEND_PAIRING_INFO, HDCP_2_2_PAIRING_TIMEOUT_MS, 0 },
-	{ HDCP_2_2_LC_SEND_LPRIME, HDCP_2_2_HDMI_LPRIME_TIMEOUT_MS, 0 },
-	{ HDCP_2_2_REP_SEND_RECVID_LIST, HDCP_2_2_RECVID_LIST_TIMEOUT_MS, 0 },
-	{ HDCP_2_2_REP_STREAM_READY, HDCP_2_2_STREAM_READY_TIMEOUT_MS, 0 },
+	{ HDCP_2_2_AKE_SEND_CERT, HDCP_2_2_CERT_TIMEOUT_MS, },
+	{ HDCP_2_2_AKE_SEND_PAIRING_INFO, HDCP_2_2_PAIRING_TIMEOUT_MS, },
+	{ HDCP_2_2_LC_SEND_LPRIME, HDCP_2_2_HDMI_LPRIME_TIMEOUT_MS, },
+	{ HDCP_2_2_REP_SEND_RECVID_LIST, HDCP_2_2_RECVID_LIST_TIMEOUT_MS, },
+	{ HDCP_2_2_REP_STREAM_READY, HDCP_2_2_STREAM_READY_TIMEOUT_MS, },
 };
 
 static
@@ -1565,12 +1562,17 @@ static int get_hdcp2_msg_timeout(u8 msg_id, bool is_paired)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(hdcp2_msg_timeout); i++)
-		if (hdcp2_msg_timeout[i].msg_id == msg_id &&
-		    (msg_id != HDCP_2_2_AKE_SEND_HPRIME || is_paired))
+	if (msg_id == HDCP_2_2_AKE_SEND_HPRIME) {
+		if (is_paired)
+			return HDCP_2_2_HPRIME_PAIRED_TIMEOUT_MS;
+		else
+			return HDCP_2_2_HPRIME_NO_PAIRED_TIMEOUT_MS;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(hdcp2_msg_timeout); i++) {
+		if (hdcp2_msg_timeout[i].msg_id == msg_id)
 			return hdcp2_msg_timeout[i].timeout;
-		else if (hdcp2_msg_timeout[i].msg_id == msg_id)
-			return hdcp2_msg_timeout[i].timeout2;
+	}
 
 	return -EINVAL;
 }
-- 
cgit v1.2.3


From 0b7b6966403d75472eb2dc6082a3d483c219b173 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 10 Oct 2019 17:51:27 +0300
Subject: drm/i915: Make hdcp2_msg_timeout.timeout u16
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All the timeout values fit in u16, so let's shrink the structure
a bit.

This ends up actually increasing the .text size a bit due to
some changes in instructions (constant imul+small jmps replaced
with mov+bigger jmpqs). Seems pretty arbitrary to me so I'll
just pretend I didn't see it.

    text	   data	    bss	    dec	    hex	filename
-  34521	    360	      0	  34881	   8841	intel_hdmi.o
+  34537	    360	      0	  34897	   8851	intel_hdmi.o

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191010145127.7487-5-ville.syrjala@linux.intel.com
Reviewed-by: Ramalingam C <ramalingam.c@intel.com>
---
 drivers/gpu/drm/i915/display/intel_hdmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 3b88d7b0aac5..b54ccbb5aad5 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -1537,7 +1537,7 @@ bool intel_hdmi_hdcp_check_link(struct intel_digital_port *intel_dig_port)
 
 struct hdcp2_hdmi_msg_timeout {
 	u8 msg_id;
-	u32 timeout;
+	u16 timeout;
 };
 
 static const struct hdcp2_hdmi_msg_timeout hdcp2_msg_timeout[] = {
-- 
cgit v1.2.3


From 46ac18c347b00be29b265c28209b0f3c38a1f142 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Fri, 18 Oct 2019 11:34:22 +0200
Subject: iommu/amd: Check PM_LEVEL_SIZE() condition in locked section

The increase_address_space() function has to check the PM_LEVEL_SIZE()
condition again under the domain->lock to avoid a false trigger of the
WARN_ON_ONCE() and to avoid that the address space is increase more
often than necessary.

Reported-by: Qian Cai <cai@lca.pw>
Fixes: 754265bcab78 ("iommu/amd: Fix race in increase_address_space()")
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd_iommu.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index bcd89ea50a8b..dd555078258c 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -1464,6 +1464,7 @@ static void free_pagetable(struct protection_domain *domain)
  * to 64 bits.
  */
 static bool increase_address_space(struct protection_domain *domain,
+				   unsigned long address,
 				   gfp_t gfp)
 {
 	unsigned long flags;
@@ -1472,8 +1473,8 @@ static bool increase_address_space(struct protection_domain *domain,
 
 	spin_lock_irqsave(&domain->lock, flags);
 
-	if (WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
-		/* address space already 64 bit large */
+	if (address <= PM_LEVEL_SIZE(domain->mode) ||
+	    WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
 		goto out;
 
 	pte = (void *)get_zeroed_page(gfp);
@@ -1506,7 +1507,7 @@ static u64 *alloc_pte(struct protection_domain *domain,
 	BUG_ON(!is_power_of_2(page_size));
 
 	while (address > PM_LEVEL_SIZE(domain->mode))
-		*updated = increase_address_space(domain, gfp) || *updated;
+		*updated = increase_address_space(domain, address, gfp) || *updated;
 
 	level   = domain->mode - 1;
 	pte     = &domain->pt_root[PM_LEVEL_INDEX(level, address)];
-- 
cgit v1.2.3


From e83c467358c1d99f235af8374c0eca0b0c91b329 Mon Sep 17 00:00:00 2001
From: Vivek Kasireddy <vivek.kasireddy@intel.com>
Date: Wed, 16 Oct 2019 11:35:14 -0700
Subject: drm/i915: Correct the PCH type in irq postinstall

JasperLake PCH (JSP) has DDI HPD pin mappings similar to TGP and not
MCC. Also add the correct HPD pin mappings for the MCC PCH.

Cc: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016183514.11128-1-vivek.kasireddy@intel.com
---
 drivers/gpu/drm/i915/i915_irq.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index ef09fbb36f37..e618f4621308 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3803,8 +3803,11 @@ static void icp_irq_postinstall(struct drm_i915_private *dev_priv)
 	if (HAS_PCH_TGP(dev_priv))
 		icp_hpd_detection_setup(dev_priv, TGP_DDI_HPD_ENABLE_MASK,
 					TGP_TC_HPD_ENABLE_MASK);
-	else if (HAS_PCH_MCC(dev_priv))
+	else if (HAS_PCH_JSP(dev_priv))
 		icp_hpd_detection_setup(dev_priv, TGP_DDI_HPD_ENABLE_MASK, 0);
+	else if (HAS_PCH_MCC(dev_priv))
+		icp_hpd_detection_setup(dev_priv, ICP_DDI_HPD_ENABLE_MASK,
+					ICP_TC_HPD_ENABLE(PORT_TC1));
 	else
 		icp_hpd_detection_setup(dev_priv, ICP_DDI_HPD_ENABLE_MASK,
 					ICP_TC_HPD_ENABLE_MASK);
-- 
cgit v1.2.3


From 7de48402faa32298c3551ea32c76ccb4f9d3025d Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Wed, 16 Oct 2019 16:06:29 -0700
Subject: net: bcmgenet: don't set phydev->link from MAC

When commit 28b2e0d2cd13 ("net: phy: remove parameter new_link from
phy_mac_interrupt()") removed the new_link parameter it set the
phydev->link state from the MAC before invoking phy_mac_interrupt().

However, once commit 88d6272acaaa ("net: phy: avoid unneeded MDIO
reads in genphy_read_status") was added this initialization prevents
the proper determination of the connection parameters by the function
genphy_read_status().

This commit removes that initialization to restore the proper
functionality.

Fixes: 88d6272acaaa ("net: phy: avoid unneeded MDIO reads in genphy_read_status")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 12cb77ef1081..10d68017ff6c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2612,10 +2612,8 @@ static void bcmgenet_irq_task(struct work_struct *work)
 	spin_unlock_irq(&priv->lock);
 
 	/* Link UP/DOWN event */
-	if (status & UMAC_IRQ_LINK_EVENT) {
-		priv->dev->phydev->link = !!(status & UMAC_IRQ_LINK_UP);
+	if (status & UMAC_IRQ_LINK_EVENT)
 		phy_mac_interrupt(priv->dev->phydev);
-	}
 }
 
 /* bcmgenet_isr1: handle Rx and Tx priority queues */
-- 
cgit v1.2.3


From fe586b823372a9f43f90e2c6aa0573992ce7ccb7 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Wed, 16 Oct 2019 16:06:30 -0700
Subject: net: phy: bcm7xxx: define soft_reset for 40nm EPHY

The internal 40nm EPHYs use a "Workaround for putting the PHY in
IDDQ mode." These PHYs require a soft reset to restore functionality
after they are powered back up.

This commit defines the soft_reset function to use genphy_soft_reset
during phy_init_hw to accommodate this.

Fixes: 6e2d85ec0559 ("net: phy: Stop with excessive soft reset")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm7xxx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 8fc33867e524..af8eabe7a6d4 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -572,6 +572,7 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev)
 	.name           = _name,					\
 	/* PHY_BASIC_FEATURES */					\
 	.flags          = PHY_IS_INTERNAL,				\
+	.soft_reset	= genphy_soft_reset,				\
 	.config_init    = bcm7xxx_config_init,				\
 	.suspend        = bcm7xxx_suspend,				\
 	.resume         = bcm7xxx_config_init,				\
-- 
cgit v1.2.3


From 1f515486275a08a17a2c806b844cca18f7de5b34 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Wed, 16 Oct 2019 16:06:31 -0700
Subject: net: bcmgenet: soft reset 40nm EPHYs before MAC init

It turns out that the "Workaround for putting the PHY in IDDQ mode"
used by the internal EPHYs on 40nm Set-Top Box chips when powering
down puts the interface to the GENET MAC in a state that can cause
subsequent MAC resets to be incomplete.

Rather than restore the forced soft reset when powering up internal
PHYs, this commit moves the invocation of phy_init_hw earlier in
the MAC initialization sequence to just before the MAC reset in the
open and resume functions. This allows the interface to be stable
and allows the MAC resets to be successful.

The bcmgenet_mii_probe() function is split in two to accommodate
this. The new function bcmgenet_mii_connect() handles the first
half of the functionality before the MAC initialization, and the
bcmgenet_mii_config() function is extended to provide the remaining
PHY configuration following the MAC initialization.

Fixes: 484bfa1507bf ("Revert "net: bcmgenet: Software reset EPHY after power on"")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c |  28 ++++---
 drivers/net/ethernet/broadcom/genet/bcmgenet.h |   2 +-
 drivers/net/ethernet/broadcom/genet/bcmmii.c   | 112 +++++++++++--------------
 3 files changed, 69 insertions(+), 73 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 10d68017ff6c..f0937c650e3c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2872,6 +2872,12 @@ static int bcmgenet_open(struct net_device *dev)
 	if (priv->internal_phy)
 		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
 
+	ret = bcmgenet_mii_connect(dev);
+	if (ret) {
+		netdev_err(dev, "failed to connect to PHY\n");
+		goto err_clk_disable;
+	}
+
 	/* take MAC out of reset */
 	bcmgenet_umac_reset(priv);
 
@@ -2881,6 +2887,12 @@ static int bcmgenet_open(struct net_device *dev)
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
 	priv->crc_fwd_en = !!(reg & CMD_CRC_FWD);
 
+	ret = bcmgenet_mii_config(dev, true);
+	if (ret) {
+		netdev_err(dev, "unsupported PHY\n");
+		goto err_disconnect_phy;
+	}
+
 	bcmgenet_set_hw_addr(priv, dev->dev_addr);
 
 	if (priv->internal_phy) {
@@ -2896,7 +2908,7 @@ static int bcmgenet_open(struct net_device *dev)
 	ret = bcmgenet_init_dma(priv);
 	if (ret) {
 		netdev_err(dev, "failed to initialize DMA\n");
-		goto err_clk_disable;
+		goto err_disconnect_phy;
 	}
 
 	/* Always enable ring 16 - descriptor ring */
@@ -2919,25 +2931,19 @@ static int bcmgenet_open(struct net_device *dev)
 		goto err_irq0;
 	}
 
-	ret = bcmgenet_mii_probe(dev);
-	if (ret) {
-		netdev_err(dev, "failed to connect to PHY\n");
-		goto err_irq1;
-	}
-
 	bcmgenet_netif_start(dev);
 
 	netif_tx_start_all_queues(dev);
 
 	return 0;
 
-err_irq1:
-	free_irq(priv->irq1, priv);
 err_irq0:
 	free_irq(priv->irq0, priv);
 err_fini_dma:
 	bcmgenet_dma_teardown(priv);
 	bcmgenet_fini_dma(priv);
+err_disconnect_phy:
+	phy_disconnect(dev->phydev);
 err_clk_disable:
 	if (priv->internal_phy)
 		bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
@@ -3618,6 +3624,8 @@ static int bcmgenet_resume(struct device *d)
 	if (priv->internal_phy)
 		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
 
+	phy_init_hw(dev->phydev);
+
 	bcmgenet_umac_reset(priv);
 
 	init_umac(priv);
@@ -3626,8 +3634,6 @@ static int bcmgenet_resume(struct device *d)
 	if (priv->wolopts)
 		clk_disable_unprepare(priv->clk_wol);
 
-	phy_init_hw(dev->phydev);
-
 	/* Speed settings must be restored */
 	bcmgenet_mii_config(priv->dev, false);
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index dbc69d8fa05f..7fbf573d8d52 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -720,8 +720,8 @@ GENET_IO_MACRO(rbuf, GENET_RBUF_OFF);
 
 /* MDIO routines */
 int bcmgenet_mii_init(struct net_device *dev);
+int bcmgenet_mii_connect(struct net_device *dev);
 int bcmgenet_mii_config(struct net_device *dev, bool init);
-int bcmgenet_mii_probe(struct net_device *dev);
 void bcmgenet_mii_exit(struct net_device *dev);
 void bcmgenet_phy_power_set(struct net_device *dev, bool enable);
 void bcmgenet_mii_setup(struct net_device *dev);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index e7c291bf4ed1..17bb8d60a157 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -173,6 +173,46 @@ static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 					  bcmgenet_fixed_phy_link_update);
 }
 
+int bcmgenet_mii_connect(struct net_device *dev)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct device_node *dn = priv->pdev->dev.of_node;
+	struct phy_device *phydev;
+	u32 phy_flags = 0;
+	int ret;
+
+	/* Communicate the integrated PHY revision */
+	if (priv->internal_phy)
+		phy_flags = priv->gphy_rev;
+
+	/* Initialize link state variables that bcmgenet_mii_setup() uses */
+	priv->old_link = -1;
+	priv->old_speed = -1;
+	priv->old_duplex = -1;
+	priv->old_pause = -1;
+
+	if (dn) {
+		phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup,
+					phy_flags, priv->phy_interface);
+		if (!phydev) {
+			pr_err("could not attach to PHY\n");
+			return -ENODEV;
+		}
+	} else {
+		phydev = dev->phydev;
+		phydev->dev_flags = phy_flags;
+
+		ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup,
+					 priv->phy_interface);
+		if (ret) {
+			pr_err("could not attach to PHY\n");
+			return -ENODEV;
+		}
+	}
+
+	return 0;
+}
+
 int bcmgenet_mii_config(struct net_device *dev, bool init)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
@@ -266,71 +306,21 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 		bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
 	}
 
-	if (init)
-		dev_info(kdev, "configuring instance for %s\n", phy_name);
-
-	return 0;
-}
+	if (init) {
+		linkmode_copy(phydev->advertising, phydev->supported);
 
-int bcmgenet_mii_probe(struct net_device *dev)
-{
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct device_node *dn = priv->pdev->dev.of_node;
-	struct phy_device *phydev;
-	u32 phy_flags = 0;
-	int ret;
-
-	/* Communicate the integrated PHY revision */
-	if (priv->internal_phy)
-		phy_flags = priv->gphy_rev;
-
-	/* Initialize link state variables that bcmgenet_mii_setup() uses */
-	priv->old_link = -1;
-	priv->old_speed = -1;
-	priv->old_duplex = -1;
-	priv->old_pause = -1;
-
-	if (dn) {
-		phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup,
-					phy_flags, priv->phy_interface);
-		if (!phydev) {
-			pr_err("could not attach to PHY\n");
-			return -ENODEV;
-		}
-	} else {
-		phydev = dev->phydev;
-		phydev->dev_flags = phy_flags;
-
-		ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup,
-					 priv->phy_interface);
-		if (ret) {
-			pr_err("could not attach to PHY\n");
-			return -ENODEV;
-		}
-	}
+		/* The internal PHY has its link interrupts routed to the
+		 * Ethernet MAC ISRs. On GENETv5 there is a hardware issue
+		 * that prevents the signaling of link UP interrupts when
+		 * the link operates at 10Mbps, so fallback to polling for
+		 * those versions of GENET.
+		 */
+		if (priv->internal_phy && !GENET_IS_V5(priv))
+			phydev->irq = PHY_IGNORE_INTERRUPT;
 
-	/* Configure port multiplexer based on what the probed PHY device since
-	 * reading the 'max-speed' property determines the maximum supported
-	 * PHY speed which is needed for bcmgenet_mii_config() to configure
-	 * things appropriately.
-	 */
-	ret = bcmgenet_mii_config(dev, true);
-	if (ret) {
-		phy_disconnect(dev->phydev);
-		return ret;
+		dev_info(kdev, "configuring instance for %s\n", phy_name);
 	}
 
-	linkmode_copy(phydev->advertising, phydev->supported);
-
-	/* The internal PHY has its link interrupts routed to the
-	 * Ethernet MAC ISRs. On GENETv5 there is a hardware issue
-	 * that prevents the signaling of link UP interrupts when
-	 * the link operates at 10Mbps, so fallback to polling for
-	 * those versions of GENET.
-	 */
-	if (priv->internal_phy && !GENET_IS_V5(priv))
-		dev->phydev->irq = PHY_IGNORE_INTERRUPT;
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From 25382b991d252aed961cd434176240f9de6bb15f Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Wed, 16 Oct 2019 16:06:32 -0700
Subject: net: bcmgenet: reset 40nm EPHY on energy detect

The EPHY integrated into the 40nm Set-Top Box devices can falsely
detect energy when connected to a disabled peer interface. When the
peer interface is enabled the EPHY will detect and report the link
as active, but on occasion may get into a state where it is not
able to exchange data with the connected GENET MAC. This issue has
not been observed when the link parameters are auto-negotiated;
however, it has been observed with a manually configured link.

It has been empirically determined that issuing a soft reset to the
EPHY when energy is detected prevents it from getting into this bad
state.

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file")
Signed-off-by: Doug Berger <opendmb@gmail.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index f0937c650e3c..0f138280315a 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2018,6 +2018,8 @@ static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
 	 */
 	if (priv->internal_phy) {
 		int0_enable |= UMAC_IRQ_LINK_EVENT;
+		if (GENET_IS_V1(priv) || GENET_IS_V2(priv) || GENET_IS_V3(priv))
+			int0_enable |= UMAC_IRQ_PHY_DET_R;
 	} else if (priv->ext_phy) {
 		int0_enable |= UMAC_IRQ_LINK_EVENT;
 	} else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
@@ -2611,9 +2613,14 @@ static void bcmgenet_irq_task(struct work_struct *work)
 	priv->irq0_stat = 0;
 	spin_unlock_irq(&priv->lock);
 
+	if (status & UMAC_IRQ_PHY_DET_R &&
+	    priv->dev->phydev->autoneg != AUTONEG_ENABLE)
+		phy_init_hw(priv->dev->phydev);
+
 	/* Link UP/DOWN event */
 	if (status & UMAC_IRQ_LINK_EVENT)
 		phy_mac_interrupt(priv->dev->phydev);
+
 }
 
 /* bcmgenet_isr1: handle Rx and Tx priority queues */
@@ -2708,7 +2715,7 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 	}
 
 	/* all other interested interrupts handled in bottom half */
-	status &= UMAC_IRQ_LINK_EVENT;
+	status &= (UMAC_IRQ_LINK_EVENT | UMAC_IRQ_PHY_DET_R);
 	if (status) {
 		/* Save irq status for bottom-half processing. */
 		spin_lock_irqsave(&priv->lock, flags);
-- 
cgit v1.2.3


From 9669fffc1415bb0c30e5d2ec98a8e1c3a418cb9c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 16 Oct 2019 18:00:56 -0700
Subject: net: ensure correct skb->tstamp in various fragmenters

Thomas found that some forwarded packets would be stuck
in FQ packet scheduler because their skb->tstamp contained
timestamps far in the future.

We thought we addressed this point in commit 8203e2d844d3
("net: clear skb->tstamp in forwarding paths") but there
is still an issue when/if a packet needs to be fragmented.

In order to meet EDT requirements, we have to make sure all
fragments get the original skb->tstamp.

Note that this original skb->tstamp should be zero in
forwarding path, but might have a non zero value in
output path if user decided so.

Fixes: fb420d5d91c1 ("tcp/fq: move back to CLOCK_MONOTONIC")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Thomas Bartschies <Thomas.Bartschies@cvk.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/netfilter/nf_conntrack_bridge.c | 3 +++
 net/ipv4/ip_output.c                       | 3 +++
 net/ipv6/ip6_output.c                      | 3 +++
 net/ipv6/netfilter.c                       | 3 +++
 4 files changed, 12 insertions(+)

diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 8842798c29e6..506d6141e44e 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -33,6 +33,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
 {
 	int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
 	unsigned int hlen, ll_rs, mtu;
+	ktime_t tstamp = skb->tstamp;
 	struct ip_frag_state state;
 	struct iphdr *iph;
 	int err;
@@ -80,6 +81,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk,
 			if (iter.frag)
 				ip_fraglist_prepare(skb, &iter);
 
+			skb->tstamp = tstamp;
 			err = output(net, sk, data, skb);
 			if (err || !iter.frag)
 				break;
@@ -104,6 +106,7 @@ slow_path:
 			goto blackhole;
 		}
 
+		skb2->tstamp = tstamp;
 		err = output(net, sk, data, skb2);
 		if (err)
 			goto blackhole;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 28fca408812c..814b9b8882a0 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -771,6 +771,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	struct rtable *rt = skb_rtable(skb);
 	unsigned int mtu, hlen, ll_rs;
 	struct ip_fraglist_iter iter;
+	ktime_t tstamp = skb->tstamp;
 	struct ip_frag_state state;
 	int err = 0;
 
@@ -846,6 +847,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				ip_fraglist_prepare(skb, &iter);
 			}
 
+			skb->tstamp = tstamp;
 			err = output(net, sk, skb);
 
 			if (!err)
@@ -900,6 +902,7 @@ slow_path:
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
+		skb2->tstamp = tstamp;
 		err = output(net, sk, skb2);
 		if (err)
 			goto fail;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index edadee4a7e76..71827b56c006 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -768,6 +768,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				inet6_sk(skb->sk) : NULL;
 	struct ip6_frag_state state;
 	unsigned int mtu, hlen, nexthdr_offset;
+	ktime_t tstamp = skb->tstamp;
 	int hroom, err = 0;
 	__be32 frag_id;
 	u8 *prevhdr, nexthdr = 0;
@@ -855,6 +856,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 			if (iter.frag)
 				ip6_fraglist_prepare(skb, &iter);
 
+			skb->tstamp = tstamp;
 			err = output(net, sk, skb);
 			if (!err)
 				IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
@@ -913,6 +915,7 @@ slow_path:
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
+		frag->tstamp = tstamp;
 		err = output(net, sk, frag);
 		if (err)
 			goto fail;
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index a9bff556d3b2..409e79b84a83 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -119,6 +119,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				  struct sk_buff *))
 {
 	int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
+	ktime_t tstamp = skb->tstamp;
 	struct ip6_frag_state state;
 	u8 *prevhdr, nexthdr = 0;
 	unsigned int mtu, hlen;
@@ -183,6 +184,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 			if (iter.frag)
 				ip6_fraglist_prepare(skb, &iter);
 
+			skb->tstamp = tstamp;
 			err = output(net, sk, data, skb);
 			if (err || !iter.frag)
 				break;
@@ -215,6 +217,7 @@ slow_path:
 			goto blackhole;
 		}
 
+		skb2->tstamp = tstamp;
 		err = output(net, sk, data, skb2);
 		if (err)
 			goto blackhole;
-- 
cgit v1.2.3


From 2e978795bb4c14293bf6ecf32621d32529706aef Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 17 Oct 2019 10:11:03 +0300
Subject: mlxsw: spectrum_trap: Push Ethernet header before reporting trap

devlink maintains packets and bytes statistics for each trap. Since
eth_type_trans() was called to set the skb's protocol, the data pointer
no longer points to the start of the packet and the bytes accounting is
off by 14 bytes.

Fix this by pushing the skb's data pointer to the start of the packet.

Fixes: b5ce611fd96e ("mlxsw: spectrum: Add devlink-trap support")
Reported-by: Alex Kushnarov <alexanderk@mellanox.com>
Tested-by: Alex Kushnarov <alexanderk@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 899450b28621..7c03b661ae7e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -99,6 +99,7 @@ static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port,
 	devlink = priv_to_devlink(mlxsw_sp->core);
 	in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core,
 							   local_port);
+	skb_push(skb, ETH_HLEN);
 	devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port);
 	consume_skb(skb);
 }
-- 
cgit v1.2.3


From ec3359b685db834c249953db6ac5717bf5cde425 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Thu, 17 Oct 2019 14:44:02 +0200
Subject: vsock/virtio: send a credit update when buffer size is changed

When the user application set a new buffer size value, we should
update the remote peer about this change, since it uses this
information to calculate the credit available.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport_common.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index a666ef8fc54e..db127a69f5c3 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -458,6 +458,9 @@ void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val)
 		vvs->buf_size_max = val;
 	vvs->buf_size = val;
 	vvs->buf_alloc = val;
+
+	virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM,
+					    NULL);
 }
 EXPORT_SYMBOL_GPL(virtio_transport_set_buffer_size);
 
-- 
cgit v1.2.3


From ae6fcfbf5f03de3407b809aaee319330d3dc7f8b Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Thu, 17 Oct 2019 14:44:03 +0200
Subject: vsock/virtio: discard packets if credit is not respected

If the remote peer doesn't respect the credit information
(buf_alloc, fwd_cnt), sending more data than it can send,
we should drop the packets to prevent a malicious peer
from using all of our memory.

This is patch follows the VIRTIO spec: "VIRTIO_VSOCK_OP_RW data
packets MUST only be transmitted when the peer has sufficient
free buffer space for the payload"

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/vmw_vsock/virtio_transport_common.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index db127a69f5c3..481f7f8a1655 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -204,10 +204,14 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
 	return virtio_transport_get_ops()->send_pkt(pkt);
 }
 
-static void virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs,
+static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs,
 					struct virtio_vsock_pkt *pkt)
 {
+	if (vvs->rx_bytes + pkt->len > vvs->buf_alloc)
+		return false;
+
 	vvs->rx_bytes += pkt->len;
+	return true;
 }
 
 static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs,
@@ -879,14 +883,18 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk,
 			      struct virtio_vsock_pkt *pkt)
 {
 	struct virtio_vsock_sock *vvs = vsk->trans;
-	bool free_pkt = false;
+	bool can_enqueue, free_pkt = false;
 
 	pkt->len = le32_to_cpu(pkt->hdr.len);
 	pkt->off = 0;
 
 	spin_lock_bh(&vvs->rx_lock);
 
-	virtio_transport_inc_rx_pkt(vvs, pkt);
+	can_enqueue = virtio_transport_inc_rx_pkt(vvs, pkt);
+	if (!can_enqueue) {
+		free_pkt = true;
+		goto out;
+	}
 
 	/* Try to copy small packets into the buffer of last packet queued,
 	 * to avoid wasting memory queueing the entire buffer with a small
-- 
cgit v1.2.3


From 38b4fe320119859c11b1dc06f6b4987a16344fa1 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 17 Oct 2019 21:29:26 +0200
Subject: net: usb: lan78xx: Connect PHY before registering MAC

As soon as the netdev is registers, the kernel can start using the
interface. If the driver connects the MAC to the PHY after the netdev
is registered, there is a race condition where the interface can be
opened without having the PHY connected.

Change the order to close this race condition.

Fixes: 92571a1aae40 ("lan78xx: Connect phy early")
Reported-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 58f5a219fb65..62948098191f 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -3782,10 +3782,14 @@ static int lan78xx_probe(struct usb_interface *intf,
 	/* driver requires remote-wakeup capability during autosuspend. */
 	intf->needs_remote_wakeup = 1;
 
+	ret = lan78xx_phy_init(dev);
+	if (ret < 0)
+		goto out4;
+
 	ret = register_netdev(netdev);
 	if (ret != 0) {
 		netif_err(dev, probe, netdev, "couldn't register the device\n");
-		goto out4;
+		goto out5;
 	}
 
 	usb_set_intfdata(intf, dev);
@@ -3798,14 +3802,10 @@ static int lan78xx_probe(struct usb_interface *intf,
 	pm_runtime_set_autosuspend_delay(&udev->dev,
 					 DEFAULT_AUTOSUSPEND_DELAY);
 
-	ret = lan78xx_phy_init(dev);
-	if (ret < 0)
-		goto out5;
-
 	return 0;
 
 out5:
-	unregister_netdev(netdev);
+	phy_disconnect(netdev->phydev);
 out4:
 	usb_free_urb(dev->urb_intr);
 out3:
-- 
cgit v1.2.3


From 789fa8746daf8561e8cd0870a66ba7a5bb05fbf7 Mon Sep 17 00:00:00 2001
From: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Date: Fri, 18 Oct 2019 12:07:10 +0200
Subject: drm/i915: Restore full symmetry in i915_driver_modeset_probe/remove

Commit 2d6f6f359fd8 ("drm/i915: add i915_driver_modeset_remove()")
claimed removal of asymmetry in probe() and remove() calls, however, it
didn't take care of calling intel_irq_uninstall() on driver remove.
That doesn't hurt as long as we still call it from
intel_modeset_driver_remove() but in order to have full symmetry we
should call it again from i915_driver_modeset_remove().

Note that it's safe to call intel_irq_uninstall() twice thanks to
commit b318b82455bd ("drm/i915: Nuke drm_driver irq vfuncs").  We may
only want to mention the case we are adding in a related FIXME comment
provided by that commit.  While being at it, update the name of
function mentioned as calling it out of sequence as that name has been
changed meanwhile by commit 78dae1ac35dd ("drm/i915: Propagate
"_remove" function name suffix down").

Suggested-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/6250061.7lZMOAyebC@jkrzyszt-desk.ger.corp.intel.com
---
 drivers/gpu/drm/i915/i915_drv.c | 2 ++
 drivers/gpu/drm/i915/i915_irq.c | 8 ++++----
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index b3a92951f671..157ed22052a2 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -354,6 +354,8 @@ static void i915_driver_modeset_remove(struct drm_i915_private *i915)
 {
 	intel_modeset_driver_remove(i915);
 
+	intel_irq_uninstall(i915);
+
 	intel_bios_driver_remove(i915);
 
 	i915_switcheroo_unregister(i915);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index e618f4621308..572a5c37cc61 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -4486,10 +4486,10 @@ void intel_irq_uninstall(struct drm_i915_private *dev_priv)
 	int irq = dev_priv->drm.pdev->irq;
 
 	/*
-	 * FIXME we can get called twice during driver load
-	 * error handling due to intel_modeset_cleanup()
-	 * calling us out of sequence. Would be nice if
-	 * it didn't do that...
+	 * FIXME we can get called twice during driver probe
+	 * error handling as well as during driver remove due to
+	 * intel_modeset_driver_remove() calling us out of sequence.
+	 * Would be nice if it didn't do that...
 	 */
 	if (!dev_priv->drm.irq_enabled)
 		return;
-- 
cgit v1.2.3


From b9959c7a347d6adbb558fba7e36e9fef3cba3b07 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 18 Oct 2019 18:41:16 -0400
Subject: filldir[64]: remove WARN_ON_ONCE() for bad directory entries

This was always meant to be a temporary thing, just for testing and to
see if it actually ever triggered.

The only thing that reported it was syzbot doing disk image fuzzing, and
then that warning is expected.  So let's just remove it before -rc4,
because the extra sanity testing should probably go to -stable, but we
don't want the warning to do so.

Reported-by: syzbot+3031f712c7ad5dd4d926@syzkaller.appspotmail.com
Fixes: 8a23eb804ca4 ("Make filldir[64]() verify the directory entry filename is valid")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/readdir.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/readdir.c b/fs/readdir.c
index 6e2623e57b2e..d26d5ea4de7b 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -105,9 +105,9 @@ EXPORT_SYMBOL(iterate_dir);
  */
 static int verify_dirent_name(const char *name, int len)
 {
-	if (WARN_ON_ONCE(!len))
+	if (!len)
 		return -EIO;
-	if (WARN_ON_ONCE(memchr(name, '/', len)))
+	if (memchr(name, '/', len))
 		return -EIO;
 	return 0;
 }
-- 
cgit v1.2.3


From bfb926e3238580a5b4c13509c6aa73d84643d75d Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Fri, 18 Oct 2019 10:27:20 -0700
Subject: drm/i915/display/icl: Save Master transcoder in slave's crtc_state
 for Transcoder Port Sync
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In case of tiled displays when the two tiles are sent across two CRTCs
over two separate DP SST connectors, we need a mechanism to synchronize
the two CRTCs and their corresponding transcoders.
So use the master-slave mode where there is one master corresponding
to last horizontal and vertical tile that needs to be genlocked with
all other slave tiles.
This patch identifies saves the master transcoder in all the slave
CRTC states. This is needed to select the master CRTC/transcoder
while configuring transcoder port sync for the corresponding slaves.

v6:
Rebase (manasi)
v5:
* Address Ville's comments
* Just pass crtc_state, no need to check GEN (Ville)
v4:
* Rebase
v3:
* Use master_tramscoder instead of master_crtc for valid
HW state readouts (Ville)
v2:
* Move this to intel_mode_set_pipe_config(Jani N, Ville)
* Use slave_bitmask to save associated slaves in master crtc state (Ville)

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018172725.1338-1-manasi.d.navare@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c       | 118 +++++++++++++++++++++
 drivers/gpu/drm/i915/display/intel_display.h       |   2 +
 drivers/gpu/drm/i915/display/intel_display_types.h |   6 ++
 3 files changed, 126 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 23450f16df66..a1595f50edf6 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -519,6 +519,20 @@ needs_modeset(const struct intel_crtc_state *state)
 	return drm_atomic_crtc_needs_modeset(&state->base);
 }
 
+bool
+is_trans_port_sync_mode(const struct intel_crtc_state *crtc_state)
+{
+	return (crtc_state->master_transcoder != INVALID_TRANSCODER ||
+		crtc_state->sync_mode_slaves_mask);
+}
+
+static bool
+is_trans_port_sync_master(const struct intel_crtc_state *crtc_state)
+{
+	return (crtc_state->master_transcoder == INVALID_TRANSCODER &&
+		crtc_state->sync_mode_slaves_mask);
+}
+
 /*
  * Platform specific helpers to calculate the port PLL loopback- (clock.m),
  * and post-divider (clock.p) values, pre- (clock.vco) and post-divided fast
@@ -11794,6 +11808,91 @@ static bool c8_planes_changed(const struct intel_crtc_state *new_crtc_state)
 	return !old_crtc_state->c8_planes != !new_crtc_state->c8_planes;
 }
 
+static int icl_add_sync_mode_crtcs(struct intel_crtc_state *crtc_state)
+{
+	struct drm_crtc *crtc = crtc_state->base.crtc;
+	struct intel_atomic_state *state = to_intel_atomic_state(crtc_state->base.state);
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	struct drm_connector *master_connector, *connector;
+	struct drm_connector_state *connector_state;
+	struct drm_connector_list_iter conn_iter;
+	struct drm_crtc *master_crtc = NULL;
+	struct drm_crtc_state *master_crtc_state;
+	struct intel_crtc_state *master_pipe_config;
+	int i, tile_group_id;
+
+	if (INTEL_GEN(dev_priv) < 11)
+		return 0;
+
+	/*
+	 * In case of tiled displays there could be one or more slaves but there is
+	 * only one master. Lets make the CRTC used by the connector corresponding
+	 * to the last horizonal and last vertical tile a master/genlock CRTC.
+	 * All the other CRTCs corresponding to other tiles of the same Tile group
+	 * are the slave CRTCs and hold a pointer to their genlock CRTC.
+	 */
+	for_each_new_connector_in_state(&state->base, connector, connector_state, i) {
+		if (connector_state->crtc != crtc)
+			continue;
+		if (!connector->has_tile)
+			continue;
+		if (crtc_state->base.mode.hdisplay != connector->tile_h_size ||
+		    crtc_state->base.mode.vdisplay != connector->tile_v_size)
+			return 0;
+		if (connector->tile_h_loc == connector->num_h_tile - 1 &&
+		    connector->tile_v_loc == connector->num_v_tile - 1)
+			continue;
+		crtc_state->sync_mode_slaves_mask = 0;
+		tile_group_id = connector->tile_group->id;
+		drm_connector_list_iter_begin(&dev_priv->drm, &conn_iter);
+		drm_for_each_connector_iter(master_connector, &conn_iter) {
+			struct drm_connector_state *master_conn_state = NULL;
+
+			if (!master_connector->has_tile)
+				continue;
+			if (master_connector->tile_h_loc != master_connector->num_h_tile - 1 ||
+			    master_connector->tile_v_loc != master_connector->num_v_tile - 1)
+				continue;
+			if (master_connector->tile_group->id != tile_group_id)
+				continue;
+
+			master_conn_state = drm_atomic_get_connector_state(&state->base,
+									   master_connector);
+			if (IS_ERR(master_conn_state)) {
+				drm_connector_list_iter_end(&conn_iter);
+				return PTR_ERR(master_conn_state);
+			}
+			if (master_conn_state->crtc) {
+				master_crtc = master_conn_state->crtc;
+				break;
+			}
+		}
+		drm_connector_list_iter_end(&conn_iter);
+
+		if (!master_crtc) {
+			DRM_DEBUG_KMS("Could not find Master CRTC for Slave CRTC %d\n",
+				      connector_state->crtc->base.id);
+			return -EINVAL;
+		}
+
+		master_crtc_state = drm_atomic_get_crtc_state(&state->base,
+							      master_crtc);
+		if (IS_ERR(master_crtc_state))
+			return PTR_ERR(master_crtc_state);
+
+		master_pipe_config = to_intel_crtc_state(master_crtc_state);
+		crtc_state->master_transcoder = master_pipe_config->cpu_transcoder;
+		master_pipe_config->sync_mode_slaves_mask |=
+			BIT(crtc_state->cpu_transcoder);
+		DRM_DEBUG_KMS("Master Transcoder = %s added for Slave CRTC = %d, slave transcoder bitmask = %d\n",
+			      transcoder_name(crtc_state->master_transcoder),
+			      crtc_state->base.crtc->base.id,
+			      master_pipe_config->sync_mode_slaves_mask);
+	}
+
+	return 0;
+}
+
 static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 				   struct intel_crtc *crtc)
 {
@@ -12292,6 +12391,13 @@ clear_intel_crtc_state(struct intel_crtc_state *crtc_state)
 	if (IS_G4X(dev_priv) ||
 	    IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 		saved_state->wm = crtc_state->wm;
+	/*
+	 * Save the slave bitmask which gets filled for master crtc state during
+	 * slave atomic check call.
+	 */
+	if (is_trans_port_sync_master(crtc_state))
+		saved_state->sync_mode_slaves_mask =
+			crtc_state->sync_mode_slaves_mask;
 
 	/* Keep base drm_crtc_state intact, only clear our extended struct */
 	BUILD_BUG_ON(offsetof(struct intel_crtc_state, base));
@@ -12385,6 +12491,15 @@ encoder_retry:
 	drm_mode_set_crtcinfo(&pipe_config->base.adjusted_mode,
 			      CRTC_STEREO_DOUBLE);
 
+	/* Set the crtc_state defaults for trans_port_sync */
+	pipe_config->master_transcoder = INVALID_TRANSCODER;
+	ret = icl_add_sync_mode_crtcs(pipe_config);
+	if (ret) {
+		DRM_DEBUG_KMS("Cannot assign Sync Mode CRTCs: %d\n",
+			      ret);
+		return ret;
+	}
+
 	/* Pass our mode to the connectors and the CRTC to give them a chance to
 	 * adjust it according to limitations or connector properties, and also
 	 * a chance to reject the mode entirely.
@@ -12900,6 +13015,9 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	PIPE_CONF_CHECK_INFOFRAME(hdmi);
 	PIPE_CONF_CHECK_INFOFRAME(drm);
 
+	PIPE_CONF_CHECK_I(sync_mode_slaves_mask);
+	PIPE_CONF_CHECK_I(master_transcoder);
+
 #undef PIPE_CONF_CHECK_X
 #undef PIPE_CONF_CHECK_I
 #undef PIPE_CONF_CHECK_BOOL
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 90807603987c..db149cb56ec5 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -93,6 +93,7 @@ enum pipe {
 #define pipe_name(p) ((p) + 'A')
 
 enum transcoder {
+	INVALID_TRANSCODER = -1,
 	/*
 	 * The following transcoders have a 1:1 transcoder -> pipe mapping,
 	 * keep their values fixed: the code assumes that TRANSCODER_A=0, the
@@ -462,6 +463,7 @@ enum drm_mode_status
 intel_mode_valid_max_plane_size(struct drm_i915_private *dev_priv,
 				const struct drm_display_mode *mode);
 enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port);
+bool is_trans_port_sync_mode(const struct intel_crtc_state *state);
 
 void intel_plane_destroy(struct drm_plane *plane);
 void i830_enable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe);
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 40390d855815..8358152e403e 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -991,6 +991,12 @@ struct intel_crtc_state {
 
 	/* Forward Error correction State */
 	bool fec_enable;
+
+	/* Pointer to master transcoder in case of tiled displays */
+	enum transcoder master_transcoder;
+
+	/* Bitmask to indicate slaves attached */
+	u8 sync_mode_slaves_mask;
 };
 
 struct intel_crtc {
-- 
cgit v1.2.3


From 705135bd734c949495f6c347dbfcca14cd2389b9 Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Fri, 18 Oct 2019 10:27:21 -0700
Subject: drm/i915/display/icl: Enable TRANSCODER PORT SYNC for tiled displays
 across separate ports
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In case of tiled displays where different tiles are displayed across
different ports, we need to synchronize the transcoders involved.
This patch implements the transcoder port sync feature for
synchronizing one master transcoder with one or more slave
transcoders. This is only enbaled in slave transcoder
and the master transcoder is unaware that it is operating
in this mode.
This has been tested with tiled display connected to ICL.

v7:
* Rebase on Maarten's patches
v6:
* Use master_trans +1 and address missing trans_edp case (Ville)
v5:
* Add TRANSCODER_D case and MISSING_CASE (Maarten)
v4:
Rebase
v3:
* Check of DP_MST moved to atomic_check (Maarten)
v2:
* Do not use RMW, just write to the register in commit (Jani N)

Cc: Daniel Vetter <daniel.vetter@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018172725.1338-2-manasi.d.navare@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 33 ++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index a1595f50edf6..4033e410b1df 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -4405,6 +4405,36 @@ static void icl_set_pipe_chicken(struct intel_crtc *crtc)
 	I915_WRITE(PIPE_CHICKEN(pipe), tmp);
 }
 
+static void icl_enable_trans_port_sync(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	u32 trans_ddi_func_ctl2_val;
+	u8 master_select;
+
+	/*
+	 * Configure the master select and enable Transcoder Port Sync for
+	 * Slave CRTCs transcoder.
+	 */
+	if (crtc_state->master_transcoder == INVALID_TRANSCODER)
+		return;
+
+	if (crtc_state->master_transcoder == TRANSCODER_EDP)
+		master_select = 0;
+	else
+		master_select = crtc_state->master_transcoder + 1;
+
+	/* Set the master select bits for Tranascoder Port Sync */
+	trans_ddi_func_ctl2_val = (PORT_SYNC_MODE_MASTER_SELECT(master_select) &
+				   PORT_SYNC_MODE_MASTER_SELECT_MASK) <<
+		PORT_SYNC_MODE_MASTER_SELECT_SHIFT;
+	/* Enable Transcoder Port Sync */
+	trans_ddi_func_ctl2_val |= PORT_SYNC_MODE_ENABLE;
+
+	I915_WRITE(TRANS_DDI_FUNC_CTL2(crtc_state->cpu_transcoder),
+		   trans_ddi_func_ctl2_val);
+}
+
 static void intel_fdi_normal_train(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
@@ -6429,6 +6459,9 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_set_pipe_timings(pipe_config);
 
+	if (INTEL_GEN(dev_priv) >= 11)
+		icl_enable_trans_port_sync(pipe_config);
+
 	intel_set_pipe_src_size(pipe_config);
 
 	if (cpu_transcoder != TRANSCODER_EDP &&
-- 
cgit v1.2.3


From ba5f1ae95d28cf3d5358fa7375578a1ad3b424e1 Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Fri, 18 Oct 2019 10:27:22 -0700
Subject: drm/i915/display/icl: HW state readout for transcoder port sync
 config
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After the state is committed, we readout the HW registers and compare
the HW state with the SW state that we just committed.
For Transcdoer port sync, we add master_transcoder and the
salves bitmask to the crtc_state, hence we need to read those during
the HW state readout to avoid pipe state mismatch.

v11:
* Move master trans init to get pipe_Config hooks (Ville)
v10:
* Initialize master_tarnscoder readout for all platforms (Ville)
v9:
* Initialize master_transcoder = INVALID at get config (Ville)
v8:
* Use master_select -1, address TRANS_EDP case (Ville)
* Rename master_transcoder to _readout (Lucas)
v7:
* NDont read HW state for DSI
v6:
* Go through both parts of HW readout (Maarten)
* Add a WARN if the same trans configured as
master and slave (Ville, Maarten)
v5:
* Add return INVALID in defaut case (Maarten)
v4:
* Get power domains in master loop for get_config (Ville)
v3:
* Add TRANSCODER_D (Maarten)
* v3 Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
v2:
* Add Transcoder_D and MISSING_CASE (Maarten)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018172725.1338-3-manasi.d.navare@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 61 ++++++++++++++++++++++++++++
 1 file changed, 61 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 4033e410b1df..30595d19d0f9 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -8798,6 +8798,7 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc,
 	pipe_config->output_format = INTEL_OUTPUT_FORMAT_RGB;
 	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = NULL;
+	pipe_config->master_transcoder = INVALID_TRANSCODER;
 
 	ret = false;
 
@@ -9987,6 +9988,7 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc,
 
 	pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe;
 	pipe_config->shared_dpll = NULL;
+	pipe_config->master_transcoder = INVALID_TRANSCODER;
 
 	ret = false;
 	tmp = I915_READ(PIPECONF(crtc->pipe));
@@ -10437,6 +10439,59 @@ static void haswell_get_ddi_port_state(struct intel_crtc *crtc,
 	}
 }
 
+static enum transcoder transcoder_master_readout(struct drm_i915_private *dev_priv,
+						 enum transcoder cpu_transcoder)
+{
+	u32 trans_port_sync, master_select;
+
+	trans_port_sync = I915_READ(TRANS_DDI_FUNC_CTL2(cpu_transcoder));
+
+	if ((trans_port_sync & PORT_SYNC_MODE_ENABLE) == 0)
+		return INVALID_TRANSCODER;
+
+	master_select = trans_port_sync &
+			PORT_SYNC_MODE_MASTER_SELECT_MASK;
+	if (master_select == 0)
+		return TRANSCODER_EDP;
+	else
+		return master_select - 1;
+}
+
+static void icelake_get_trans_port_sync_config(struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
+	u32 transcoders;
+	enum transcoder cpu_transcoder;
+
+	crtc_state->master_transcoder = transcoder_master_readout(dev_priv,
+								  crtc_state->cpu_transcoder);
+
+	transcoders = BIT(TRANSCODER_A) |
+		BIT(TRANSCODER_B) |
+		BIT(TRANSCODER_C) |
+		BIT(TRANSCODER_D);
+	for_each_cpu_transcoder_masked(dev_priv, cpu_transcoder, transcoders) {
+		enum intel_display_power_domain power_domain;
+		intel_wakeref_t trans_wakeref;
+
+		power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder);
+		trans_wakeref = intel_display_power_get_if_enabled(dev_priv,
+								   power_domain);
+
+		if (!trans_wakeref)
+			continue;
+
+		if (transcoder_master_readout(dev_priv, cpu_transcoder) ==
+		    crtc_state->cpu_transcoder)
+			crtc_state->sync_mode_slaves_mask |= BIT(cpu_transcoder);
+
+		intel_display_power_put(dev_priv, power_domain, trans_wakeref);
+	}
+
+	WARN_ON(crtc_state->master_transcoder != INVALID_TRANSCODER &&
+		crtc_state->sync_mode_slaves_mask);
+}
+
 static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 				    struct intel_crtc_state *pipe_config)
 {
@@ -10448,6 +10503,8 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 
 	intel_crtc_init_scalers(crtc, pipe_config);
 
+	pipe_config->master_transcoder = INVALID_TRANSCODER;
+
 	power_domain = POWER_DOMAIN_PIPE(crtc->pipe);
 	wf = intel_display_power_get_if_enabled(dev_priv, power_domain);
 	if (!wf)
@@ -10556,6 +10613,10 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc,
 		pipe_config->pixel_multiplier = 1;
 	}
 
+	if (INTEL_GEN(dev_priv) >= 11 &&
+	    !transcoder_is_dsi(pipe_config->cpu_transcoder))
+		icelake_get_trans_port_sync_config(pipe_config);
+
 out:
 	for_each_power_domain(power_domain, power_domain_mask)
 		intel_display_power_put(dev_priv,
-- 
cgit v1.2.3


From eadf6f9170d5e72ce571ce914638316863d512e7 Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Fri, 18 Oct 2019 10:27:23 -0700
Subject: drm/i915/display/icl: Enable master-slaves in trans port sync
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As per the display enable sequence, we need to follow the enable sequence
for slaves first with DP_TP_CTL set to Idle and configure the transcoder
port sync register to select the corersponding master, then follow the
enable sequence for master leaving DP_TP_CTL to idle.
At this point the transcoder port sync mode is configured and enabled
and the Vblanks of both ports are synchronized so then set DP_TP_CTL
for the slave and master to Normal and do post crtc enable updates.

v11:
* Rebase (Manasi)
v10:
* in trans sync mode, dont stop link train for tgl (Manasi)
v9:
Remove update_scanline_offset to rebase on Maarten's patch (Manasi)
v8:
* Rebase on Maarten's patches (Manasi)
v7:
* Use ffs(slaves) to get slave crtc (Ville)
v6:
* Modeset implies active_changed, remove one condition (Maarten)
v5:
* Fix checkpatch warning (Manasi)
v4:
* Reuse skl_commit_modeset_enables() hook (Maarten)
* Obtain slave crtc and states from master (Maarten)
v3:
* Rebase on drm-tip (Manasi)
v2:
* Create a icl_update_crtcs hook (Maarten, Danvet)
* This sequence only for CRTCs in trans port sync mode (Maarten)

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018172725.1338-4-manasi.d.navare@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c     |   6 +-
 drivers/gpu/drm/i915/display/intel_display.c | 136 ++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/display/intel_display.h |   2 +
 3 files changed, 139 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 4c81449ec144..46a7b2ca2782 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3500,7 +3500,8 @@ static void tgl_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	intel_dp_start_link_train(intel_dp);
 
 	/* 7.k */
-	intel_dp_stop_link_train(intel_dp);
+	if (!is_trans_port_sync_mode(crtc_state))
+		intel_dp_stop_link_train(intel_dp);
 
 	/*
 	 * TODO: enable clock gating
@@ -3574,7 +3575,8 @@ static void hsw_ddi_pre_enable_dp(struct intel_encoder *encoder,
 					      true);
 	intel_dp_sink_set_fec_ready(intel_dp, crtc_state);
 	intel_dp_start_link_train(intel_dp);
-	if (port != PORT_A || INTEL_GEN(dev_priv) >= 9)
+	if ((port != PORT_A || INTEL_GEN(dev_priv) >= 9) &&
+	    !is_trans_port_sync_mode(crtc_state))
 		intel_dp_stop_link_train(intel_dp);
 
 	intel_ddi_enable_fec(encoder, crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 30595d19d0f9..17c259d4922a 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -14061,6 +14061,18 @@ static void intel_update_crtc(struct intel_crtc *crtc,
 		intel_crtc_arm_fifo_underrun(crtc, new_crtc_state);
 }
 
+static struct intel_crtc *intel_get_slave_crtc(const struct intel_crtc_state *new_crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(new_crtc_state->base.crtc->dev);
+	enum transcoder slave_transcoder;
+
+	WARN_ON(!is_power_of_2(new_crtc_state->sync_mode_slaves_mask));
+
+	slave_transcoder = ffs(new_crtc_state->sync_mode_slaves_mask) - 1;
+	return intel_get_crtc_for_pipe(dev_priv,
+				       (enum pipe)slave_transcoder);
+}
+
 static void intel_old_crtc_state_disables(struct intel_atomic_state *state,
 					  struct intel_crtc_state *old_crtc_state,
 					  struct intel_crtc_state *new_crtc_state,
@@ -14139,6 +14151,113 @@ static void intel_commit_modeset_enables(struct intel_atomic_state *state)
 	}
 }
 
+static void intel_crtc_enable_trans_port_sync(struct intel_crtc *crtc,
+					      struct intel_atomic_state *state,
+					      struct intel_crtc_state *new_crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+
+	intel_crtc_update_active_timings(new_crtc_state);
+	dev_priv->display.crtc_enable(new_crtc_state, state);
+	intel_crtc_enable_pipe_crc(crtc);
+}
+
+static void intel_set_dp_tp_ctl_normal(struct intel_crtc *crtc,
+				       struct intel_atomic_state *state)
+{
+	struct drm_connector_state *conn_state;
+	struct drm_connector *conn;
+	struct intel_dp *intel_dp;
+	int i;
+
+	for_each_new_connector_in_state(&state->base, conn, conn_state, i) {
+		if (conn_state->crtc == &crtc->base)
+			break;
+	}
+	intel_dp = enc_to_intel_dp(&intel_attached_encoder(conn)->base);
+	intel_dp_stop_link_train(intel_dp);
+}
+
+static void intel_post_crtc_enable_updates(struct intel_crtc *crtc,
+					   struct intel_atomic_state *state)
+{
+	struct intel_crtc_state *new_crtc_state =
+		intel_atomic_get_new_crtc_state(state, crtc);
+	struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+	struct intel_plane_state *new_plane_state =
+		intel_atomic_get_new_plane_state(state,
+						 to_intel_plane(crtc->base.primary));
+	bool modeset = needs_modeset(new_crtc_state);
+
+	if (new_crtc_state->update_pipe && !new_crtc_state->enable_fbc)
+		intel_fbc_disable(crtc);
+	else if (new_plane_state)
+		intel_fbc_enable(crtc, new_crtc_state, new_plane_state);
+
+	/* Perform vblank evasion around commit operation */
+	intel_pipe_update_start(new_crtc_state);
+	commit_pipe_config(state, old_crtc_state, new_crtc_state);
+	skl_update_planes_on_crtc(state, crtc);
+	intel_pipe_update_end(new_crtc_state);
+
+	/*
+	 * We usually enable FIFO underrun interrupts as part of the
+	 * CRTC enable sequence during modesets.  But when we inherit a
+	 * valid pipe configuration from the BIOS we need to take care
+	 * of enabling them on the CRTC's first fastset.
+	 */
+	if (new_crtc_state->update_pipe && !modeset &&
+	    old_crtc_state->base.mode.private_flags & I915_MODE_FLAG_INHERITED)
+		intel_crtc_arm_fifo_underrun(crtc, new_crtc_state);
+}
+
+static void intel_update_trans_port_sync_crtcs(struct intel_crtc *crtc,
+					       struct intel_atomic_state *state,
+					       struct intel_crtc_state *old_crtc_state,
+					       struct intel_crtc_state *new_crtc_state)
+{
+	struct intel_crtc *slave_crtc = intel_get_slave_crtc(new_crtc_state);
+	struct intel_crtc_state *new_slave_crtc_state =
+		intel_atomic_get_new_crtc_state(state, slave_crtc);
+	struct intel_crtc_state *old_slave_crtc_state =
+		intel_atomic_get_old_crtc_state(state, slave_crtc);
+
+	WARN_ON(!slave_crtc || !new_slave_crtc_state ||
+		!old_slave_crtc_state);
+
+	DRM_DEBUG_KMS("Updating Transcoder Port Sync Master CRTC = %d %s and Slave CRTC %d %s\n",
+		      crtc->base.base.id, crtc->base.name, slave_crtc->base.base.id,
+		      slave_crtc->base.name);
+
+	/* Enable seq for slave with with DP_TP_CTL left Idle until the
+	 * master is ready
+	 */
+	intel_crtc_enable_trans_port_sync(slave_crtc,
+					  state,
+					  new_slave_crtc_state);
+
+	/* Enable seq for master with with DP_TP_CTL left Idle */
+	intel_crtc_enable_trans_port_sync(crtc,
+					  state,
+					  new_crtc_state);
+
+	/* Set Slave's DP_TP_CTL to Normal */
+	intel_set_dp_tp_ctl_normal(slave_crtc,
+				   state);
+
+	/* Set Master's DP_TP_CTL To Normal */
+	usleep_range(200, 400);
+	intel_set_dp_tp_ctl_normal(crtc,
+				   state);
+
+	/* Now do the post crtc enable for all master and slaves */
+	intel_post_crtc_enable_updates(slave_crtc,
+				       state);
+	intel_post_crtc_enable_updates(crtc,
+				       state);
+}
+
 static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
@@ -14172,6 +14291,7 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 		for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
 			enum pipe pipe = crtc->pipe;
 			bool vbl_wait = false;
+			bool modeset = needs_modeset(new_crtc_state);
 
 			if (updated & BIT(crtc->pipe) || !new_crtc_state->base.active)
 				continue;
@@ -14192,12 +14312,22 @@ static void skl_commit_modeset_enables(struct intel_atomic_state *state)
 			 */
 			if (!skl_ddb_entry_equal(&new_crtc_state->wm.skl.ddb,
 						 &old_crtc_state->wm.skl.ddb) &&
-			    !new_crtc_state->base.active_changed &&
+			    !modeset &&
 			    state->wm_results.dirty_pipes != updated)
 				vbl_wait = true;
 
-			intel_update_crtc(crtc, state, old_crtc_state,
-					  new_crtc_state);
+			if (modeset && is_trans_port_sync_mode(new_crtc_state)) {
+				if (is_trans_port_sync_master(new_crtc_state))
+					intel_update_trans_port_sync_crtcs(crtc,
+									   state,
+									   old_crtc_state,
+									   new_crtc_state);
+				else
+					continue;
+			} else {
+				intel_update_crtc(crtc, state, old_crtc_state,
+						  new_crtc_state);
+			}
 
 			if (vbl_wait)
 				intel_wait_for_vblank(dev_priv, pipe);
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index db149cb56ec5..7dcb176d91b0 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -27,6 +27,7 @@
 
 #include <drm/drm_util.h>
 #include <drm/i915_drm.h>
+#include "intel_dp_link_training.h"
 
 enum link_m_n_set;
 struct dpll;
@@ -54,6 +55,7 @@ struct intel_plane;
 struct intel_plane_state;
 struct intel_remapped_info;
 struct intel_rotation_info;
+struct intel_crtc_state;
 
 enum i915_gpio {
 	GPIOA,
-- 
cgit v1.2.3


From 51528afe7c5ed6fcd6ed4cfb046b74659d21738f Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Fri, 18 Oct 2019 10:27:24 -0700
Subject: drm/i915/display/icl: Disable transcoder port sync as part of
 crtc_disable() sequence
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This clears the transcoder port sync bits of the TRANS_DDI_FUNC_CTL2
register during crtc_disable().

v3:
* Rebase on maarten's patches
v2:
* Directly write the trans_port_sync reg value (Maarten)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018172725.1338-5-manasi.d.navare@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 17c259d4922a..1ea8f37448ba 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -4435,6 +4435,25 @@ static void icl_enable_trans_port_sync(const struct intel_crtc_state *crtc_state
 		   trans_ddi_func_ctl2_val);
 }
 
+static void icl_disable_transcoder_port_sync(const struct intel_crtc_state *old_crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	i915_reg_t reg;
+	u32 trans_ddi_func_ctl2_val;
+
+	if (old_crtc_state->master_transcoder == INVALID_TRANSCODER)
+		return;
+
+	DRM_DEBUG_KMS("Disabling Transcoder Port Sync on Slave Transcoder %s\n",
+		      transcoder_name(old_crtc_state->cpu_transcoder));
+
+	reg = TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder);
+	trans_ddi_func_ctl2_val = ~(PORT_SYNC_MODE_ENABLE |
+				    PORT_SYNC_MODE_MASTER_SELECT_MASK);
+	I915_WRITE(reg, trans_ddi_func_ctl2_val);
+}
+
 static void intel_fdi_normal_train(struct intel_crtc *crtc)
 {
 	struct drm_device *dev = crtc->base.dev;
@@ -6639,6 +6658,9 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	if (intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST))
 		intel_ddi_set_vc_payload_alloc(old_crtc_state, false);
 
+	if (INTEL_GEN(dev_priv) >= 11)
+		icl_disable_transcoder_port_sync(old_crtc_state);
+
 	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_ddi_disable_transcoder_func(old_crtc_state);
 
-- 
cgit v1.2.3


From a6c948f98239cbec1f5f0dc741b5841008c264ff Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Fri, 18 Oct 2019 10:27:25 -0700
Subject: drm/i915/display/icl: In port sync mode disable slaves first then
 master
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the transcoder port sync mode, the slave transcoders mask their vblanks
until master transcoder's vblank so while disabling them, make
sure slaves are disabled first and then the masters.

v5:
* Dont pass dev priv to get_slave_crtc (Ville)
v4:
* Obtain slave state from master (Maarten)
v3:
* Rebase
v2:
* Use the intel_old_crtc_state_disables() helper

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191018172725.1338-6-manasi.d.navare@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 58 +++++++++++++++++++++++++---
 1 file changed, 52 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 1ea8f37448ba..ff97423ea7ed 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -14130,6 +14130,37 @@ static void intel_old_crtc_state_disables(struct intel_atomic_state *state,
 						     new_crtc_state);
 }
 
+static void intel_trans_port_sync_modeset_disables(struct intel_atomic_state *state,
+						   struct intel_crtc *crtc,
+						   struct intel_crtc_state *old_crtc_state,
+						   struct intel_crtc_state *new_crtc_state)
+{
+	struct intel_crtc *slave_crtc = intel_get_slave_crtc(new_crtc_state);
+	struct intel_crtc_state *new_slave_crtc_state =
+		intel_atomic_get_new_crtc_state(state, slave_crtc);
+	struct intel_crtc_state *old_slave_crtc_state =
+		intel_atomic_get_old_crtc_state(state, slave_crtc);
+
+	WARN_ON(!slave_crtc || !new_slave_crtc_state ||
+		!old_slave_crtc_state);
+
+	/* Disable Slave first */
+	intel_pre_plane_update(old_slave_crtc_state, new_slave_crtc_state);
+	if (old_slave_crtc_state->base.active)
+		intel_old_crtc_state_disables(state,
+					      old_slave_crtc_state,
+					      new_slave_crtc_state,
+					      slave_crtc);
+
+	/* Disable Master */
+	intel_pre_plane_update(old_crtc_state, new_crtc_state);
+	if (old_crtc_state->base.active)
+		intel_old_crtc_state_disables(state,
+					      old_crtc_state,
+					      new_crtc_state,
+					      crtc);
+}
+
 static void intel_commit_modeset_disables(struct intel_atomic_state *state)
 {
 	struct intel_crtc_state *new_crtc_state, *old_crtc_state;
@@ -14148,13 +14179,28 @@ static void intel_commit_modeset_disables(struct intel_atomic_state *state)
 		if (!needs_modeset(new_crtc_state))
 			continue;
 
-		intel_pre_plane_update(old_crtc_state, new_crtc_state);
+		/* In case of Transcoder port Sync master slave CRTCs can be
+		 * assigned in any order and we need to make sure that
+		 * slave CRTCs are disabled first and then master CRTC since
+		 * Slave vblanks are masked till Master Vblanks.
+		 */
+		if (is_trans_port_sync_mode(new_crtc_state)) {
+			if (is_trans_port_sync_master(new_crtc_state))
+				intel_trans_port_sync_modeset_disables(state,
+								       crtc,
+								       old_crtc_state,
+								       new_crtc_state);
+			else
+				continue;
+		} else {
+			intel_pre_plane_update(old_crtc_state, new_crtc_state);
 
-		if (old_crtc_state->base.active)
-			intel_old_crtc_state_disables(state,
-						      old_crtc_state,
-						      new_crtc_state,
-						      crtc);
+			if (old_crtc_state->base.active)
+				intel_old_crtc_state_disables(state,
+							      old_crtc_state,
+							      new_crtc_state,
+							      crtc);
+		}
 	}
 }
 
-- 
cgit v1.2.3


From 327f8d8c336d2f7a037e26cdbd7f372d993a138f Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 10 Oct 2019 18:09:01 -0700
Subject: drm/i915: simplify setting of ddi_io_power_domain
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of the ever growing switch, just compute the ddi io power domain
based on the port number.

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011010907.103309-2-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 43 +++-----------------------------
 1 file changed, 3 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 46a7b2ca2782..9ba794cb9b4f 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -4758,46 +4758,9 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 		intel_encoder->update_complete = intel_ddi_update_complete;
 	}
 
-	switch (port) {
-	case PORT_A:
-		intel_dig_port->ddi_io_power_domain =
-			POWER_DOMAIN_PORT_DDI_A_IO;
-		break;
-	case PORT_B:
-		intel_dig_port->ddi_io_power_domain =
-			POWER_DOMAIN_PORT_DDI_B_IO;
-		break;
-	case PORT_C:
-		intel_dig_port->ddi_io_power_domain =
-			POWER_DOMAIN_PORT_DDI_C_IO;
-		break;
-	case PORT_D:
-		intel_dig_port->ddi_io_power_domain =
-			POWER_DOMAIN_PORT_DDI_D_IO;
-		break;
-	case PORT_E:
-		intel_dig_port->ddi_io_power_domain =
-			POWER_DOMAIN_PORT_DDI_E_IO;
-		break;
-	case PORT_F:
-		intel_dig_port->ddi_io_power_domain =
-			POWER_DOMAIN_PORT_DDI_F_IO;
-		break;
-	case PORT_G:
-		intel_dig_port->ddi_io_power_domain =
-			POWER_DOMAIN_PORT_DDI_G_IO;
-		break;
-	case PORT_H:
-		intel_dig_port->ddi_io_power_domain =
-			POWER_DOMAIN_PORT_DDI_H_IO;
-		break;
-	case PORT_I:
-		intel_dig_port->ddi_io_power_domain =
-			POWER_DOMAIN_PORT_DDI_I_IO;
-		break;
-	default:
-		MISSING_CASE(port);
-	}
+	WARN_ON(port > PORT_I);
+	intel_dig_port->ddi_io_power_domain = POWER_DOMAIN_PORT_DDI_A_IO +
+					      port - PORT_A;
 
 	if (init_dp) {
 		if (!intel_ddi_init_dp_connector(intel_dig_port))
-- 
cgit v1.2.3


From 10d987fd1b7baceaafa78d805e71427ab735b4e4 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 10 Oct 2019 18:09:03 -0700
Subject: drm/i915: fix port checks for MST support on gen >= 11
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Both Ice Lake and Elkhart Lake (gen 11) support MST on all external
connections except DDI A. Tiger Lake (gen 12) supports on all external
connections.

Move the check to happen inside intel_dp_mst_encoder_init() and add
specific platform checks.

v2: Replace != with == checks for ports on gen < 11 (Ville)

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015164029.18431-3-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c     |  7 ++-----
 drivers/gpu/drm/i915/display/intel_dp_mst.c | 22 ++++++++++++++++------
 2 files changed, 18 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 3792d143bea9..3696623ce443 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -7468,11 +7468,8 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 		intel_connector->get_hw_state = intel_connector_get_hw_state;
 
 	/* init MST on ports that can support it */
-	if (HAS_DP_MST(dev_priv) && !intel_dp_is_edp(intel_dp) &&
-	    (port == PORT_B || port == PORT_C ||
-	     port == PORT_D || port == PORT_F))
-		intel_dp_mst_encoder_init(intel_dig_port,
-					  intel_connector->base.base.id);
+	intel_dp_mst_encoder_init(intel_dig_port,
+				  intel_connector->base.base.id);
 
 	if (!intel_edp_init_connector(intel_dp, intel_connector)) {
 		intel_dp_aux_fini(intel_dp);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 2203be28ea01..bbcab27644dc 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -655,21 +655,31 @@ intel_dp_mst_encoder_active_links(struct intel_digital_port *intel_dig_port)
 int
 intel_dp_mst_encoder_init(struct intel_digital_port *intel_dig_port, int conn_base_id)
 {
+	struct drm_i915_private *i915 = to_i915(intel_dig_port->base.base.dev);
 	struct intel_dp *intel_dp = &intel_dig_port->dp;
-	struct drm_device *dev = intel_dig_port->base.base.dev;
+	enum port port = intel_dig_port->base.port;
 	int ret;
 
-	intel_dp->can_mst = true;
+	if (!HAS_DP_MST(i915) || intel_dp_is_edp(intel_dp))
+		return 0;
+
+	if (INTEL_GEN(i915) < 12 && port == PORT_A)
+		return 0;
+
+	if (INTEL_GEN(i915) < 11 && port == PORT_E)
+		return 0;
+
 	intel_dp->mst_mgr.cbs = &mst_cbs;
 
 	/* create encoders */
 	intel_dp_create_fake_mst_encoders(intel_dig_port);
-	ret = drm_dp_mst_topology_mgr_init(&intel_dp->mst_mgr, dev,
+	ret = drm_dp_mst_topology_mgr_init(&intel_dp->mst_mgr, &i915->drm,
 					   &intel_dp->aux, 16, 3, conn_base_id);
-	if (ret) {
-		intel_dp->can_mst = false;
+	if (ret)
 		return ret;
-	}
+
+	intel_dp->can_mst = true;
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From cbd9b9f2e7b1f2e34478e0b1d944d521063e430d Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 10 Oct 2019 18:09:04 -0700
Subject: drm/i915: remove extra new line on pipe_config mismatch
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The new line is already added by pipe_config_mismatch(), so the callers
shouldn't add it.

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011010907.103309-5-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index ff97423ea7ed..87e42faeed98 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -12817,7 +12817,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 #define PIPE_CONF_CHECK_X(name) do { \
 	if (current_config->name != pipe_config->name) { \
 		pipe_config_mismatch(fastset, __stringify(name), \
-				     "(expected 0x%08x, found 0x%08x)\n", \
+				     "(expected 0x%08x, found 0x%08x)", \
 				     current_config->name, \
 				     pipe_config->name); \
 		ret = false; \
@@ -12827,7 +12827,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 #define PIPE_CONF_CHECK_I(name) do { \
 	if (current_config->name != pipe_config->name) { \
 		pipe_config_mismatch(fastset, __stringify(name), \
-				     "(expected %i, found %i)\n", \
+				     "(expected %i, found %i)", \
 				     current_config->name, \
 				     pipe_config->name); \
 		ret = false; \
@@ -12837,7 +12837,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 #define PIPE_CONF_CHECK_BOOL(name) do { \
 	if (current_config->name != pipe_config->name) { \
 		pipe_config_mismatch(fastset, __stringify(name), \
-				     "(expected %s, found %s)\n", \
+				     "(expected %s, found %s)", \
 				     yesno(current_config->name), \
 				     yesno(pipe_config->name)); \
 		ret = false; \
@@ -12854,7 +12854,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 		PIPE_CONF_CHECK_BOOL(name); \
 	} else { \
 		pipe_config_mismatch(fastset, __stringify(name), \
-				     "unable to verify whether state matches exactly, forcing modeset (expected %s, found %s)\n", \
+				     "unable to verify whether state matches exactly, forcing modeset (expected %s, found %s)", \
 				     yesno(current_config->name), \
 				     yesno(pipe_config->name)); \
 		ret = false; \
@@ -12864,7 +12864,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 #define PIPE_CONF_CHECK_P(name) do { \
 	if (current_config->name != pipe_config->name) { \
 		pipe_config_mismatch(fastset, __stringify(name), \
-				     "(expected %p, found %p)\n", \
+				     "(expected %p, found %p)", \
 				     current_config->name, \
 				     pipe_config->name); \
 		ret = false; \
@@ -12877,7 +12877,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 				    !fastset)) { \
 		pipe_config_mismatch(fastset, __stringify(name), \
 				     "(expected tu %i gmch %i/%i link %i/%i, " \
-				     "found tu %i, gmch %i/%i link %i/%i)\n", \
+				     "found tu %i, gmch %i/%i link %i/%i)", \
 				     current_config->name.tu, \
 				     current_config->name.gmch_m, \
 				     current_config->name.gmch_n, \
@@ -12905,7 +12905,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 		pipe_config_mismatch(fastset, __stringify(name), \
 				     "(expected tu %i gmch %i/%i link %i/%i, " \
 				     "or tu %i gmch %i/%i link %i/%i, " \
-				     "found tu %i, gmch %i/%i link %i/%i)\n", \
+				     "found tu %i, gmch %i/%i link %i/%i)", \
 				     current_config->name.tu, \
 				     current_config->name.gmch_m, \
 				     current_config->name.gmch_n, \
@@ -12928,7 +12928,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 #define PIPE_CONF_CHECK_FLAGS(name, mask) do { \
 	if ((current_config->name ^ pipe_config->name) & (mask)) { \
 		pipe_config_mismatch(fastset, __stringify(name), \
-				     "(%x) (expected %i, found %i)\n", \
+				     "(%x) (expected %i, found %i)", \
 				     (mask), \
 				     current_config->name & (mask), \
 				     pipe_config->name & (mask)); \
@@ -12939,7 +12939,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 #define PIPE_CONF_CHECK_CLOCK_FUZZY(name) do { \
 	if (!intel_fuzzy_clock_check(current_config->name, pipe_config->name)) { \
 		pipe_config_mismatch(fastset, __stringify(name), \
-				     "(expected %i, found %i)\n", \
+				     "(expected %i, found %i)", \
 				     current_config->name, \
 				     pipe_config->name); \
 		ret = false; \
@@ -12959,7 +12959,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 #define PIPE_CONF_CHECK_COLOR_LUT(name1, name2, bit_precision) do { \
 	if (current_config->name1 != pipe_config->name1) { \
 		pipe_config_mismatch(fastset, __stringify(name1), \
-				"(expected %i, found %i, won't compare lut values)\n", \
+				"(expected %i, found %i, won't compare lut values)", \
 				current_config->name1, \
 				pipe_config->name1); \
 		ret = false;\
@@ -12968,7 +12968,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 					pipe_config->name2, pipe_config->name1, \
 					bit_precision)) { \
 			pipe_config_mismatch(fastset, __stringify(name2), \
-					"hw_state doesn't match sw_state\n"); \
+					"hw_state doesn't match sw_state"); \
 			ret = false; \
 		} \
 	} \
-- 
cgit v1.2.3


From 73cefd903de77ac084b278e152248d6923d400e5 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 10 Oct 2019 18:09:05 -0700
Subject: drm/i915: add pipe id/name to pipe mismatch logs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This way it's easier to figure out what didn't match when we have
multiple pipes enabled.

v2: pass drm_crtc and use the more common [CRTC:%d:%s] format
    (Ville)
v3: use struct intel_crtc type to pass crtc around (Ville)

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191015164029.18431-5-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/display/intel_display.c | 34 ++++++++++++++++------------
 1 file changed, 19 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 87e42faeed98..2912abd85148 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -12762,8 +12762,9 @@ pipe_config_infoframe_mismatch(struct drm_i915_private *dev_priv,
 	}
 }
 
-static void __printf(3, 4)
-pipe_config_mismatch(bool fastset, const char *name, const char *format, ...)
+static void __printf(4, 5)
+pipe_config_mismatch(bool fastset, const struct intel_crtc *crtc,
+		     const char *name, const char *format, ...)
 {
 	struct va_format vaf;
 	va_list args;
@@ -12773,9 +12774,11 @@ pipe_config_mismatch(bool fastset, const char *name, const char *format, ...)
 	vaf.va = &args;
 
 	if (fastset)
-		DRM_DEBUG_KMS("fastset mismatch in %s %pV\n", name, &vaf);
+		DRM_DEBUG_KMS("[CRTC:%d:%s] fastset mismatch in %s %pV\n",
+			      crtc->base.base.id, crtc->base.name, name, &vaf);
 	else
-		DRM_ERROR("mismatch in %s %pV\n", name, &vaf);
+		DRM_ERROR("[CRTC:%d:%s] mismatch in %s %pV\n",
+			  crtc->base.base.id, crtc->base.name, name, &vaf);
 
 	va_end(args);
 }
@@ -12803,6 +12806,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 			  bool fastset)
 {
 	struct drm_i915_private *dev_priv = to_i915(current_config->base.crtc->dev);
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
 	bool ret = true;
 	u32 bp_gamma = 0;
 	bool fixup_inherited = fastset &&
@@ -12816,7 +12820,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 #define PIPE_CONF_CHECK_X(name) do { \
 	if (current_config->name != pipe_config->name) { \
-		pipe_config_mismatch(fastset, __stringify(name), \
+		pipe_config_mismatch(fastset, crtc, __stringify(name), \
 				     "(expected 0x%08x, found 0x%08x)", \
 				     current_config->name, \
 				     pipe_config->name); \
@@ -12826,7 +12830,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 #define PIPE_CONF_CHECK_I(name) do { \
 	if (current_config->name != pipe_config->name) { \
-		pipe_config_mismatch(fastset, __stringify(name), \
+		pipe_config_mismatch(fastset, crtc, __stringify(name), \
 				     "(expected %i, found %i)", \
 				     current_config->name, \
 				     pipe_config->name); \
@@ -12836,7 +12840,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 #define PIPE_CONF_CHECK_BOOL(name) do { \
 	if (current_config->name != pipe_config->name) { \
-		pipe_config_mismatch(fastset, __stringify(name), \
+		pipe_config_mismatch(fastset, crtc,  __stringify(name), \
 				     "(expected %s, found %s)", \
 				     yesno(current_config->name), \
 				     yesno(pipe_config->name)); \
@@ -12853,7 +12857,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	if (!fixup_inherited || (!current_config->name && !pipe_config->name)) { \
 		PIPE_CONF_CHECK_BOOL(name); \
 	} else { \
-		pipe_config_mismatch(fastset, __stringify(name), \
+		pipe_config_mismatch(fastset, crtc, __stringify(name), \
 				     "unable to verify whether state matches exactly, forcing modeset (expected %s, found %s)", \
 				     yesno(current_config->name), \
 				     yesno(pipe_config->name)); \
@@ -12863,7 +12867,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 #define PIPE_CONF_CHECK_P(name) do { \
 	if (current_config->name != pipe_config->name) { \
-		pipe_config_mismatch(fastset, __stringify(name), \
+		pipe_config_mismatch(fastset, crtc, __stringify(name), \
 				     "(expected %p, found %p)", \
 				     current_config->name, \
 				     pipe_config->name); \
@@ -12875,7 +12879,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 	if (!intel_compare_link_m_n(&current_config->name, \
 				    &pipe_config->name,\
 				    !fastset)) { \
-		pipe_config_mismatch(fastset, __stringify(name), \
+		pipe_config_mismatch(fastset, crtc, __stringify(name), \
 				     "(expected tu %i gmch %i/%i link %i/%i, " \
 				     "found tu %i, gmch %i/%i link %i/%i)", \
 				     current_config->name.tu, \
@@ -12902,7 +12906,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 				    &pipe_config->name, !fastset) && \
 	    !intel_compare_link_m_n(&current_config->alt_name, \
 				    &pipe_config->name, !fastset)) { \
-		pipe_config_mismatch(fastset, __stringify(name), \
+		pipe_config_mismatch(fastset, crtc, __stringify(name), \
 				     "(expected tu %i gmch %i/%i link %i/%i, " \
 				     "or tu %i gmch %i/%i link %i/%i, " \
 				     "found tu %i, gmch %i/%i link %i/%i)", \
@@ -12927,7 +12931,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 #define PIPE_CONF_CHECK_FLAGS(name, mask) do { \
 	if ((current_config->name ^ pipe_config->name) & (mask)) { \
-		pipe_config_mismatch(fastset, __stringify(name), \
+		pipe_config_mismatch(fastset, crtc, __stringify(name), \
 				     "(%x) (expected %i, found %i)", \
 				     (mask), \
 				     current_config->name & (mask), \
@@ -12938,7 +12942,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 #define PIPE_CONF_CHECK_CLOCK_FUZZY(name) do { \
 	if (!intel_fuzzy_clock_check(current_config->name, pipe_config->name)) { \
-		pipe_config_mismatch(fastset, __stringify(name), \
+		pipe_config_mismatch(fastset, crtc, __stringify(name), \
 				     "(expected %i, found %i)", \
 				     current_config->name, \
 				     pipe_config->name); \
@@ -12958,7 +12962,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 
 #define PIPE_CONF_CHECK_COLOR_LUT(name1, name2, bit_precision) do { \
 	if (current_config->name1 != pipe_config->name1) { \
-		pipe_config_mismatch(fastset, __stringify(name1), \
+		pipe_config_mismatch(fastset, crtc, __stringify(name1), \
 				"(expected %i, found %i, won't compare lut values)", \
 				current_config->name1, \
 				pipe_config->name1); \
@@ -12967,7 +12971,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
 		if (!intel_color_lut_equal(current_config->name2, \
 					pipe_config->name2, pipe_config->name1, \
 					bit_precision)) { \
-			pipe_config_mismatch(fastset, __stringify(name2), \
+			pipe_config_mismatch(fastset, crtc, __stringify(name2), \
 					"hw_state doesn't match sw_state"); \
 			ret = false; \
 		} \
-- 
cgit v1.2.3


From 7acf6c9495d075a2f05e90915d03027227b0a1d5 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 10 Oct 2019 18:09:06 -0700
Subject: drm/i915: prettify MST debug message
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

s/?/:/ so it gets correctly colored by dmesg.

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191011010907.103309-7-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/display/intel_dp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 3696623ce443..5eeafa45831a 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -4478,7 +4478,7 @@ intel_dp_configure_mst(struct intel_dp *intel_dp)
 		&dp_to_dig_port(intel_dp)->base;
 	bool sink_can_mst = intel_dp_sink_can_mst(intel_dp);
 
-	DRM_DEBUG_KMS("[ENCODER:%d:%s] MST support? port: %s, sink: %s, modparam: %s\n",
+	DRM_DEBUG_KMS("[ENCODER:%d:%s] MST support: port: %s, sink: %s, modparam: %s\n",
 		      encoder->base.base.id, encoder->base.name,
 		      yesno(intel_dp->can_mst), yesno(sink_can_mst),
 		      yesno(i915_modparams.enable_dp_mst));
-- 
cgit v1.2.3


From 641fe2e9387a36f9ee01d7c69382d1fe147a5e98 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 18 Oct 2019 20:19:16 -0700
Subject: drivers/base/memory.c: don't access uninitialized memmaps in
 soft_offline_page_store()

Uninitialized memmaps contain garbage and in the worst case trigger kernel
BUGs, especially with CONFIG_PAGE_POISONING.  They should not get touched.

Right now, when trying to soft-offline a PFN that resides on a memory
block that was never onlined, one gets a misleading error with
CONFIG_PAGE_POISONING:

  :/# echo 5637144576 > /sys/devices/system/memory/soft_offline_page
  [   23.097167] soft offline: 0x150000 page already poisoned

But the actual result depends on the garbage in the memmap.

soft_offline_page() can only work with online pages, it returns -EIO in
case of ZONE_DEVICE.  Make sure to only forward pages that are online
(iow, managed by the buddy) and, therefore, have an initialized memmap.

Add a check against pfn_to_online_page() and similarly return -EIO.

Link: http://lkml.kernel.org/r/20191010141200.8985-1-david@redhat.com
Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online")	[visible after d0dc12e86b319]
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: <stable@vger.kernel.org>	[4.13+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/base/memory.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 6bea4f3f8040..55907c27075b 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -540,6 +540,9 @@ static ssize_t soft_offline_page_store(struct device *dev,
 	pfn >>= PAGE_SHIFT;
 	if (!pfn_valid(pfn))
 		return -ENXIO;
+	/* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */
+	if (!pfn_to_online_page(pfn))
+		return -EIO;
 	ret = soft_offline_page(pfn_to_page(pfn), 0);
 	return ret == 0 ? count : ret;
 }
-- 
cgit v1.2.3


From aad5f69bc161af489dbb5934868bd347282f0764 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 18 Oct 2019 20:19:20 -0700
Subject: fs/proc/page.c: don't access uninitialized memmaps in fs/proc/page.c

There are three places where we access uninitialized memmaps, namely:
- /proc/kpagecount
- /proc/kpageflags
- /proc/kpagecgroup

We have initialized memmaps either when the section is online or when the
page was initialized to the ZONE_DEVICE.  Uninitialized memmaps contain
garbage and in the worst case trigger kernel BUGs, especially with
CONFIG_PAGE_POISONING.

For example, not onlining a DIMM during boot and calling /proc/kpagecount
with CONFIG_PAGE_POISONING:

  :/# cat /proc/kpagecount > tmp.test
  BUG: unable to handle page fault for address: fffffffffffffffe
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 114616067 P4D 114616067 PUD 114618067 PMD 0
  Oops: 0000 [#1] SMP NOPTI
  CPU: 0 PID: 469 Comm: cat Not tainted 5.4.0-rc1-next-20191004+ #11
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.4
  RIP: 0010:kpagecount_read+0xce/0x1e0
  Code: e8 09 83 e0 3f 48 0f a3 02 73 2d 4c 89 e7 48 c1 e7 06 48 03 3d ab 51 01 01 74 1d 48 8b 57 08 480
  RSP: 0018:ffffa14e409b7e78 EFLAGS: 00010202
  RAX: fffffffffffffffe RBX: 0000000000020000 RCX: 0000000000000000
  RDX: 0000000000000001 RSI: 00007f76b5595000 RDI: fffff35645000000
  RBP: 00007f76b5595000 R08: 0000000000000001 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000140000
  R13: 0000000000020000 R14: 00007f76b5595000 R15: ffffa14e409b7f08
  FS:  00007f76b577d580(0000) GS:ffff8f41bd400000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: fffffffffffffffe CR3: 0000000078960000 CR4: 00000000000006f0
  Call Trace:
   proc_reg_read+0x3c/0x60
   vfs_read+0xc5/0x180
   ksys_read+0x68/0xe0
   do_syscall_64+0x5c/0xa0
   entry_SYSCALL_64_after_hwframe+0x49/0xbe

For now, let's drop support for ZONE_DEVICE from the three pseudo files
in order to fix this.  To distinguish offline memory (with garbage
memmap) from ZONE_DEVICE memory with properly initialized memmaps, we
would have to check get_dev_pagemap() and pfn_zone_device_reserved()
right now.  The usage of both (especially, special casing devmem) is
frowned upon and needs to be reworked.

The fundamental issue we have is:

	if (pfn_to_online_page(pfn)) {
		/* memmap initialized */
	} else if (pfn_valid(pfn)) {
		/*
		 * ???
		 * a) offline memory. memmap garbage.
		 * b) devmem: memmap initialized to ZONE_DEVICE.
		 * c) devmem: reserved for driver. memmap garbage.
		 * (d) devmem: memmap currently initializing - garbage)
		 */
	}

We'll leave the pfn_zone_device_reserved() check in stable_page_flags()
in place as that function is also used from memory failure.  We now no
longer dump information about pages that are not in use anymore -
offline.

Link: http://lkml.kernel.org/r/20191009142435.3975-2-david@redhat.com
Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online")	[visible after d0dc12e86b319]
Signed-off-by: David Hildenbrand <david@redhat.com>
Reported-by: Qian Cai <cai@lca.pw>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Toshiki Fukasawa <t-fukasawa@vx.jp.nec.com>
Cc: Pankaj gupta <pagupta@redhat.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Anthony Yznaga <anthony.yznaga@oracle.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: <stable@vger.kernel.org>	[4.13+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/page.c | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/fs/proc/page.c b/fs/proc/page.c
index 544d1ee15aee..7c952ee732e6 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -42,10 +42,12 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
 		return -EINVAL;
 
 	while (count > 0) {
-		if (pfn_valid(pfn))
-			ppage = pfn_to_page(pfn);
-		else
-			ppage = NULL;
+		/*
+		 * TODO: ZONE_DEVICE support requires to identify
+		 * memmaps that were actually initialized.
+		 */
+		ppage = pfn_to_online_page(pfn);
+
 		if (!ppage || PageSlab(ppage) || page_has_type(ppage))
 			pcount = 0;
 		else
@@ -216,10 +218,11 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf,
 		return -EINVAL;
 
 	while (count > 0) {
-		if (pfn_valid(pfn))
-			ppage = pfn_to_page(pfn);
-		else
-			ppage = NULL;
+		/*
+		 * TODO: ZONE_DEVICE support requires to identify
+		 * memmaps that were actually initialized.
+		 */
+		ppage = pfn_to_online_page(pfn);
 
 		if (put_user(stable_page_flags(ppage), out)) {
 			ret = -EFAULT;
@@ -261,10 +264,11 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
 		return -EINVAL;
 
 	while (count > 0) {
-		if (pfn_valid(pfn))
-			ppage = pfn_to_page(pfn);
-		else
-			ppage = NULL;
+		/*
+		 * TODO: ZONE_DEVICE support requires to identify
+		 * memmaps that were actually initialized.
+		 */
+		ppage = pfn_to_online_page(pfn);
 
 		if (ppage)
 			ino = page_cgroup_ino(ppage);
-- 
cgit v1.2.3


From 96c804a6ae8c59a9092b3d5dd581198472063184 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 18 Oct 2019 20:19:23 -0700
Subject: mm/memory-failure.c: don't access uninitialized memmaps in
 memory_failure()

We should check for pfn_to_online_page() to not access uninitialized
memmaps.  Reshuffle the code so we don't have to duplicate the error
message.

Link: http://lkml.kernel.org/r/20191009142435.3975-3-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online")	[visible after d0dc12e86b319]
Acked-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: <stable@vger.kernel.org>	[4.13+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memory-failure.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 0ae72b6acee7..3151c87dff73 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1257,17 +1257,19 @@ int memory_failure(unsigned long pfn, int flags)
 	if (!sysctl_memory_failure_recovery)
 		panic("Memory failure on page %lx", pfn);
 
-	if (!pfn_valid(pfn)) {
+	p = pfn_to_online_page(pfn);
+	if (!p) {
+		if (pfn_valid(pfn)) {
+			pgmap = get_dev_pagemap(pfn, NULL);
+			if (pgmap)
+				return memory_failure_dev_pagemap(pfn, flags,
+								  pgmap);
+		}
 		pr_err("Memory failure: %#lx: memory outside kernel control\n",
 			pfn);
 		return -ENXIO;
 	}
 
-	pgmap = get_dev_pagemap(pfn, NULL);
-	if (pgmap)
-		return memory_failure_dev_pagemap(pfn, flags, pgmap);
-
-	p = pfn_to_page(pfn);
 	if (PageHuge(p))
 		return memory_failure_hugetlb(pfn, flags);
 	if (TestSetPageHWPoison(p)) {
-- 
cgit v1.2.3


From ca210ba32ef7537b02731bfe255ed8eb1e4e2b59 Mon Sep 17 00:00:00 2001
From: Joel Colledge <joel.colledge@linbit.com>
Date: Fri, 18 Oct 2019 20:19:26 -0700
Subject: scripts/gdb: fix lx-dmesg when CONFIG_PRINTK_CALLER is set

When CONFIG_PRINTK_CALLER is set, struct printk_log contains an
additional member caller_id.  This affects the offset of the log text.
Account for this by using the type information from gdb to determine all
the offsets instead of using hardcoded values.

This fixes following error:

  (gdb) lx-dmesg
  Python Exception <class 'ValueError'> embedded null character:
  Error occurred in Python command: embedded null character

The read_u* utility functions now take an offset argument to make them
easier to use.

Link: http://lkml.kernel.org/r/20191011142500.2339-1-joel.colledge@linbit.com
Signed-off-by: Joel Colledge <joel.colledge@linbit.com>
Reviewed-by: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Kieran Bingham <kbingham@kernel.org>
Cc: Leonard Crestez <leonard.crestez@nxp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 scripts/gdb/linux/dmesg.py | 16 ++++++++++++----
 scripts/gdb/linux/utils.py | 25 +++++++++++++------------
 2 files changed, 25 insertions(+), 16 deletions(-)

diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py
index 6d2e09a2ad2f..2fa7bb83885f 100644
--- a/scripts/gdb/linux/dmesg.py
+++ b/scripts/gdb/linux/dmesg.py
@@ -16,6 +16,8 @@ import sys
 
 from linux import utils
 
+printk_log_type = utils.CachedType("struct printk_log")
+
 
 class LxDmesg(gdb.Command):
     """Print Linux kernel log buffer."""
@@ -42,9 +44,14 @@ class LxDmesg(gdb.Command):
             b = utils.read_memoryview(inf, log_buf_addr, log_next_idx)
             log_buf = a.tobytes() + b.tobytes()
 
+        length_offset = printk_log_type.get_type()['len'].bitpos // 8
+        text_len_offset = printk_log_type.get_type()['text_len'].bitpos // 8
+        time_stamp_offset = printk_log_type.get_type()['ts_nsec'].bitpos // 8
+        text_offset = printk_log_type.get_type().sizeof
+
         pos = 0
         while pos < log_buf.__len__():
-            length = utils.read_u16(log_buf[pos + 8:pos + 10])
+            length = utils.read_u16(log_buf, pos + length_offset)
             if length == 0:
                 if log_buf_2nd_half == -1:
                     gdb.write("Corrupted log buffer!\n")
@@ -52,10 +59,11 @@ class LxDmesg(gdb.Command):
                 pos = log_buf_2nd_half
                 continue
 
-            text_len = utils.read_u16(log_buf[pos + 10:pos + 12])
-            text = log_buf[pos + 16:pos + 16 + text_len].decode(
+            text_len = utils.read_u16(log_buf, pos + text_len_offset)
+            text_start = pos + text_offset
+            text = log_buf[text_start:text_start + text_len].decode(
                 encoding='utf8', errors='replace')
-            time_stamp = utils.read_u64(log_buf[pos:pos + 8])
+            time_stamp = utils.read_u64(log_buf, pos + time_stamp_offset)
 
             for line in text.splitlines():
                 msg = u"[{time:12.6f}] {line}\n".format(
diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py
index bc67126118c4..ea94221dbd39 100644
--- a/scripts/gdb/linux/utils.py
+++ b/scripts/gdb/linux/utils.py
@@ -92,15 +92,16 @@ def read_memoryview(inf, start, length):
     return memoryview(inf.read_memory(start, length))
 
 
-def read_u16(buffer):
+def read_u16(buffer, offset):
+    buffer_val = buffer[offset:offset + 2]
     value = [0, 0]
 
-    if type(buffer[0]) is str:
-        value[0] = ord(buffer[0])
-        value[1] = ord(buffer[1])
+    if type(buffer_val[0]) is str:
+        value[0] = ord(buffer_val[0])
+        value[1] = ord(buffer_val[1])
     else:
-        value[0] = buffer[0]
-        value[1] = buffer[1]
+        value[0] = buffer_val[0]
+        value[1] = buffer_val[1]
 
     if get_target_endianness() == LITTLE_ENDIAN:
         return value[0] + (value[1] << 8)
@@ -108,18 +109,18 @@ def read_u16(buffer):
         return value[1] + (value[0] << 8)
 
 
-def read_u32(buffer):
+def read_u32(buffer, offset):
     if get_target_endianness() == LITTLE_ENDIAN:
-        return read_u16(buffer[0:2]) + (read_u16(buffer[2:4]) << 16)
+        return read_u16(buffer, offset) + (read_u16(buffer, offset + 2) << 16)
     else:
-        return read_u16(buffer[2:4]) + (read_u16(buffer[0:2]) << 16)
+        return read_u16(buffer, offset + 2) + (read_u16(buffer, offset) << 16)
 
 
-def read_u64(buffer):
+def read_u64(buffer, offset):
     if get_target_endianness() == LITTLE_ENDIAN:
-        return read_u32(buffer[0:4]) + (read_u32(buffer[4:8]) << 32)
+        return read_u32(buffer, offset) + (read_u32(buffer, offset + 4) << 32)
     else:
-        return read_u32(buffer[4:8]) + (read_u32(buffer[0:4]) << 32)
+        return read_u32(buffer, offset + 4) + (read_u32(buffer, offset) << 32)
 
 
 target_arch = None
-- 
cgit v1.2.3


From a26ee565b6cd8dc2bf15ff6aa70bbb28f928b773 Mon Sep 17 00:00:00 2001
From: Qian Cai <cai@lca.pw>
Date: Fri, 18 Oct 2019 20:19:29 -0700
Subject: mm/page_owner: don't access uninitialized memmaps when reading
 /proc/pagetypeinfo

Uninitialized memmaps contain garbage and in the worst case trigger
kernel BUGs, especially with CONFIG_PAGE_POISONING.  They should not get
touched.

For example, when not onlining a memory block that is spanned by a zone
and reading /proc/pagetypeinfo with CONFIG_DEBUG_VM_PGFLAGS and
CONFIG_PAGE_POISONING, we can trigger a kernel BUG:

  :/# echo 1 > /sys/devices/system/memory/memory40/online
  :/# echo 1 > /sys/devices/system/memory/memory42/online
  :/# cat /proc/pagetypeinfo > test.file
   page:fffff2c585200000 is uninitialized and poisoned
   raw: ffffffffffffffff ffffffffffffffff ffffffffffffffff ffffffffffffffff
   raw: ffffffffffffffff ffffffffffffffff ffffffffffffffff ffffffffffffffff
   page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p))
   There is not page extension available.
   ------------[ cut here ]------------
   kernel BUG at include/linux/mm.h:1107!
   invalid opcode: 0000 [#1] SMP NOPTI

Please note that this change does not affect ZONE_DEVICE, because
pagetypeinfo_showmixedcount_print() is called from
mm/vmstat.c:pagetypeinfo_showmixedcount() only for populated zones, and
ZONE_DEVICE is never populated (zone->present_pages always 0).

[david@redhat.com: move check to outer loop, add comment, rephrase description]
Link: http://lkml.kernel.org/r/20191011140638.8160-1-david@redhat.com
Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online") # visible after d0dc12e86b319
Signed-off-by: Qian Cai <cai@lca.pw>
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc: Miles Chen <miles.chen@mediatek.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: <stable@vger.kernel.org>	[4.13+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_owner.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/mm/page_owner.c b/mm/page_owner.c
index e327bcd0380e..18ecde9f45b2 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -271,7 +271,8 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 	 * not matter as the mixed block count will still be correct
 	 */
 	for (; pfn < end_pfn; ) {
-		if (!pfn_valid(pfn)) {
+		page = pfn_to_online_page(pfn);
+		if (!page) {
 			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
 			continue;
 		}
@@ -279,13 +280,13 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 		block_end_pfn = min(block_end_pfn, end_pfn);
 
-		page = pfn_to_page(pfn);
 		pageblock_mt = get_pageblock_migratetype(page);
 
 		for (; pfn < block_end_pfn; pfn++) {
 			if (!pfn_valid_within(pfn))
 				continue;
 
+			/* The pageblock is online, no need to recheck. */
 			page = pfn_to_page(pfn);
 
 			if (page_zone(page) != zone)
-- 
cgit v1.2.3


From 00d6c019b5bc175cee3770e0e659f2b5f4804ea5 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 18 Oct 2019 20:19:33 -0700
Subject: mm/memory_hotplug: don't access uninitialized memmaps in
 shrink_pgdat_span()

We might use the nid of memmaps that were never initialized.  For
example, if the memmap was poisoned, we will crash the kernel in
pfn_to_nid() right now.  Let's use the calculated boundaries of the
separate zones instead.  This now also avoids having to iterate over a
whole bunch of subsections again, after shrinking one zone.

Before commit d0dc12e86b31 ("mm/memory_hotplug: optimize memory
hotplug"), the memmap was initialized to 0 and the node was set to the
right value.  After that commit, the node might be garbage.

We'll have to fix shrink_zone_span() next.

Link: http://lkml.kernel.org/r/20191006085646.5768-4-david@redhat.com
Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online")	[d0dc12e86b319]
Signed-off-by: David Hildenbrand <david@redhat.com>
Reported-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: David Hildenbrand <david@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Damian Tometzki <damian.tometzki@gmail.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Halil Pasic <pasic@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jun Yao <yaojun8558363@gmail.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Pankaj Gupta <pagupta@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pavel Tatashin <pavel.tatashin@microsoft.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qian Cai <cai@lca.pw>
Cc: Rich Felker <dalias@libc.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Steve Capper <steve.capper@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Yu Zhao <yuzhao@google.com>
Cc: <stable@vger.kernel.org>	[4.13+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memory_hotplug.c | 72 +++++++++++------------------------------------------
 1 file changed, 15 insertions(+), 57 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b1be791f772d..df570e5c71cc 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -436,67 +436,25 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 	zone_span_writeunlock(zone);
 }
 
-static void shrink_pgdat_span(struct pglist_data *pgdat,
-			      unsigned long start_pfn, unsigned long end_pfn)
+static void update_pgdat_span(struct pglist_data *pgdat)
 {
-	unsigned long pgdat_start_pfn = pgdat->node_start_pfn;
-	unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */
-	unsigned long pgdat_end_pfn = p;
-	unsigned long pfn;
-	int nid = pgdat->node_id;
-
-	if (pgdat_start_pfn == start_pfn) {
-		/*
-		 * If the section is smallest section in the pgdat, it need
-		 * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.
-		 * In this case, we find second smallest valid mem_section
-		 * for shrinking zone.
-		 */
-		pfn = find_smallest_section_pfn(nid, NULL, end_pfn,
-						pgdat_end_pfn);
-		if (pfn) {
-			pgdat->node_start_pfn = pfn;
-			pgdat->node_spanned_pages = pgdat_end_pfn - pfn;
-		}
-	} else if (pgdat_end_pfn == end_pfn) {
-		/*
-		 * If the section is biggest section in the pgdat, it need
-		 * shrink pgdat->node_spanned_pages.
-		 * In this case, we find second biggest valid mem_section for
-		 * shrinking zone.
-		 */
-		pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn,
-					       start_pfn);
-		if (pfn)
-			pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1;
-	}
-
-	/*
-	 * If the section is not biggest or smallest mem_section in the pgdat,
-	 * it only creates a hole in the pgdat. So in this case, we need not
-	 * change the pgdat.
-	 * But perhaps, the pgdat has only hole data. Thus it check the pgdat
-	 * has only hole or not.
-	 */
-	pfn = pgdat_start_pfn;
-	for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_valid(pfn)))
-			continue;
-
-		if (pfn_to_nid(pfn) != nid)
-			continue;
+	unsigned long node_start_pfn = 0, node_end_pfn = 0;
+	struct zone *zone;
 
-		/* Skip range to be removed */
-		if (pfn >= start_pfn && pfn < end_pfn)
-			continue;
+	for (zone = pgdat->node_zones;
+	     zone < pgdat->node_zones + MAX_NR_ZONES; zone++) {
+		unsigned long zone_end_pfn = zone->zone_start_pfn +
+					     zone->spanned_pages;
 
-		/* If we find valid section, we have nothing to do */
-		return;
+		/* No need to lock the zones, they can't change. */
+		if (zone_end_pfn > node_end_pfn)
+			node_end_pfn = zone_end_pfn;
+		if (zone->zone_start_pfn < node_start_pfn)
+			node_start_pfn = zone->zone_start_pfn;
 	}
 
-	/* The pgdat has no valid section */
-	pgdat->node_start_pfn = 0;
-	pgdat->node_spanned_pages = 0;
+	pgdat->node_start_pfn = node_start_pfn;
+	pgdat->node_spanned_pages = node_end_pfn - node_start_pfn;
 }
 
 static void __remove_zone(struct zone *zone, unsigned long start_pfn,
@@ -507,7 +465,7 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn,
 
 	pgdat_resize_lock(zone->zone_pgdat, &flags);
 	shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
-	shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages);
+	update_pgdat_span(pgdat);
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 }
 
-- 
cgit v1.2.3


From 77e080e7680e1e615587352f70c87b9e98126d03 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Date: Fri, 18 Oct 2019 20:19:39 -0700
Subject: mm/memunmap: don't access uninitialized memmap in memunmap_pages()

Patch series "mm/memory_hotplug: Shrink zones before removing memory",
v6.

This series fixes the access of uninitialized memmaps when shrinking
zones/nodes and when removing memory.  Also, it contains all fixes for
crashes that can be triggered when removing certain namespace using
memunmap_pages() - ZONE_DEVICE, reported by Aneesh.

We stop trying to shrink ZONE_DEVICE, as it's buggy, fixing it would be
more involved (we don't have SECTION_IS_ONLINE as an indicator), and
shrinking is only of limited use (set_zone_contiguous() cannot detect
the ZONE_DEVICE as contiguous).

We continue shrinking !ZONE_DEVICE zones, however, I reduced the amount
of code to a minimum.  Shrinking is especially necessary to keep
zone->contiguous set where possible, especially, on memory unplug of
DIMMs at zone boundaries.

--------------------------------------------------------------------------

Zones are now properly shrunk when offlining memory blocks or when
onlining failed.  This allows to properly shrink zones on memory unplug
even if the separate memory blocks of a DIMM were onlined to different
zones or re-onlined to a different zone after offlining.

Example:

  :/# cat /proc/zoneinfo
  Node 1, zone  Movable
          spanned  0
          present  0
          managed  0
  :/# echo "online_movable" > /sys/devices/system/memory/memory41/state
  :/# echo "online_movable" > /sys/devices/system/memory/memory43/state
  :/# cat /proc/zoneinfo
  Node 1, zone  Movable
          spanned  98304
          present  65536
          managed  65536
  :/# echo 0 > /sys/devices/system/memory/memory43/online
  :/# cat /proc/zoneinfo
  Node 1, zone  Movable
          spanned  32768
          present  32768
          managed  32768
  :/# echo 0 > /sys/devices/system/memory/memory41/online
  :/# cat /proc/zoneinfo
  Node 1, zone  Movable
          spanned  0
          present  0
          managed  0

This patch (of 10):

With an altmap, the memmap falling into the reserved altmap space are not
initialized and, therefore, contain a garbage NID and a garbage zone.
Make sure to read the NID/zone from a memmap that was initialized.

This fixes a kernel crash that is observed when destroying a namespace:

  kernel BUG at include/linux/mm.h:1107!
  cpu 0x1: Vector: 700 (Program Check) at [c000000274087890]
      pc: c0000000004b9728: memunmap_pages+0x238/0x340
      lr: c0000000004b9724: memunmap_pages+0x234/0x340
  ...
      pid   = 3669, comm = ndctl
  kernel BUG at include/linux/mm.h:1107!
    devm_action_release+0x30/0x50
    release_nodes+0x268/0x2d0
    device_release_driver_internal+0x174/0x240
    unbind_store+0x13c/0x190
    drv_attr_store+0x44/0x60
    sysfs_kf_write+0x70/0xa0
    kernfs_fop_write+0x1ac/0x290
    __vfs_write+0x3c/0x70
    vfs_write+0xe4/0x200
    ksys_write+0x7c/0x140
    system_call+0x5c/0x68

The "page_zone(pfn_to_page(pfn)" was introduced by 69324b8f4833 ("mm,
devm_memremap_pages: add MEMORY_DEVICE_PRIVATE support"), however, I
think we will never have driver reserved memory with
MEMORY_DEVICE_PRIVATE (no altmap AFAIKS).

[david@redhat.com: minimze code changes, rephrase description]
Link: http://lkml.kernel.org/r/20191006085646.5768-2-david@redhat.com
Fixes: 2c2a5af6fed2 ("mm, memory_hotplug: add nid parameter to arch_remove_memory")
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Damian Tometzki <damian.tometzki@gmail.com>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Halil Pasic <pasic@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jun Yao <yaojun8558363@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Pankaj Gupta <pagupta@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Pavel Tatashin <pavel.tatashin@microsoft.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qian Cai <cai@lca.pw>
Cc: Rich Felker <dalias@libc.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Steve Capper <steve.capper@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Yu Zhao <yuzhao@google.com>
Cc: <stable@vger.kernel.org>	[5.0+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memremap.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/mm/memremap.c b/mm/memremap.c
index 68204912cc0a..03ccbdfeb697 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -103,6 +103,7 @@ static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
 void memunmap_pages(struct dev_pagemap *pgmap)
 {
 	struct resource *res = &pgmap->res;
+	struct page *first_page;
 	unsigned long pfn;
 	int nid;
 
@@ -111,14 +112,16 @@ void memunmap_pages(struct dev_pagemap *pgmap)
 		put_page(pfn_to_page(pfn));
 	dev_pagemap_cleanup(pgmap);
 
+	/* make sure to access a memmap that was actually initialized */
+	first_page = pfn_to_page(pfn_first(pgmap));
+
 	/* pages are dead and unused, undo the arch mapping */
-	nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start)));
+	nid = page_to_nid(first_page);
 
 	mem_hotplug_begin();
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
-		pfn = PHYS_PFN(res->start);
-		__remove_pages(page_zone(pfn_to_page(pfn)), pfn,
-				 PHYS_PFN(resource_size(res)), NULL);
+		__remove_pages(page_zone(first_page), PHYS_PFN(res->start),
+			       PHYS_PFN(resource_size(res)), NULL);
 	} else {
 		arch_remove_memory(nid, res->start, resource_size(res),
 				pgmap_altmap(pgmap));
-- 
cgit v1.2.3


From b749ecfaf6c53ce79d6ab66afd2fc34189a073b1 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 18 Oct 2019 20:19:44 -0700
Subject: mm: memcg/slab: fix panic in __free_slab() caused by premature memcg
 pointer release
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Karsten reported the following panic in __free_slab() happening on a s390x
machine:

  Unable to handle kernel pointer dereference in virtual kernel address space
  Failing address: 0000000000000000 TEID: 0000000000000483
  Fault in home space mode while using kernel ASCE.
  AS:00000000017d4007 R3:000000007fbd0007 S:000000007fbff000 P:000000000000003d
  Oops: 0004 ilc:3 Ý#1¨ PREEMPT SMP
  Modules linked in: tcp_diag inet_diag xt_tcpudp ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 ipt_REJECT nf_reject_ipv4 xt_conntrack ip6table_nat ip6table_mangle ip6table_raw ip6table_security iptable_at nf_nat
  CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.3.0-05872-g6133e3e4bada-dirty #14
  Hardware name: IBM 2964 NC9 702 (z/VM 6.4.0)
  Krnl PSW : 0704d00180000000 00000000003cadb6 (__free_slab+0x686/0x6b0)
             R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:1 PM:0 RI:0 EA:3
  Krnl GPRS: 00000000f3a32928 0000000000000000 000000007fbf5d00 000000000117c4b8
             0000000000000000 000000009e3291c1 0000000000000000 0000000000000000
             0000000000000003 0000000000000008 000000002b478b00 000003d080a97600
             0000000000000003 0000000000000008 000000002b478b00 000003d080a97600
             000000000117ba00 000003e000057db0 00000000003cabcc 000003e000057c78
  Krnl Code: 00000000003cada6: e310a1400004        lg      %r1,320(%r10)
             00000000003cadac: c0e50046c286        brasl   %r14,ca32b8
            #00000000003cadb2: a7f4fe36            brc     15,3caa1e
            >00000000003cadb6: e32060800024        stg     %r2,128(%r6)
             00000000003cadbc: a7f4fd9e            brc     15,3ca8f8
             00000000003cadc0: c0e50046790c        brasl   %r14,c99fd8
             00000000003cadc6: a7f4fe2c            brc     15,3caa
             00000000003cadc6: a7f4fe2c            brc     15,3caa1e
             00000000003cadca: ecb1ffff00d9        aghik   %r11,%r1,-1
  Call Trace:
  (<00000000003cabcc> __free_slab+0x49c/0x6b0)
   <00000000001f5886> rcu_core+0x5a6/0x7e0
   <0000000000ca2dea> __do_softirq+0xf2/0x5c0
   <0000000000152644> irq_exit+0x104/0x130
   <000000000010d222> do_IRQ+0x9a/0xf0
   <0000000000ca2344> ext_int_handler+0x130/0x134
   <0000000000103648> enabled_wait+0x58/0x128
  (<0000000000103634> enabled_wait+0x44/0x128)
   <0000000000103b00> arch_cpu_idle+0x40/0x58
   <0000000000ca0544> default_idle_call+0x3c/0x68
   <000000000018eaa4> do_idle+0xec/0x1c0
   <000000000018ee0e> cpu_startup_entry+0x36/0x40
   <000000000122df34> arch_call_rest_init+0x5c/0x88
   <0000000000000000> 0x0
  INFO: lockdep is turned off.
  Last Breaking-Event-Address:
   <00000000003ca8f4> __free_slab+0x1c4/0x6b0
  Kernel panic - not syncing: Fatal exception in interrupt

The kernel panics on an attempt to dereference the NULL memcg pointer.
When shutdown_cache() is called from the kmem_cache_destroy() context, a
memcg kmem_cache might have empty slab pages in a partial list, which are
still charged to the memory cgroup.

These pages are released by free_partial() at the beginning of
shutdown_cache(): either directly or by scheduling a RCU-delayed work
(if the kmem_cache has the SLAB_TYPESAFE_BY_RCU flag).  The latter case
is when the reported panic can happen: memcg_unlink_cache() is called
immediately after shrinking partial lists, without waiting for scheduled
RCU works.  It sets the kmem_cache->memcg_params.memcg pointer to NULL,
and the following attempt to dereference it by __free_slab() from the
RCU work context causes the panic.

To fix the issue, let's postpone the release of the memcg pointer to
destroy_memcg_params().  It's called from a separate work context by
slab_caches_to_rcu_destroy_workfn(), which contains a full RCU barrier.
This guarantees that all scheduled page release RCU works will complete
before the memcg pointer will be zeroed.

Big thanks for Karsten for the perfect report containing all necessary
information, his help with the analysis of the problem and testing of the
fix.

Link: http://lkml.kernel.org/r/20191010160549.1584316-1-guro@fb.com
Fixes: fb2f2b0adb98 ("mm: memcg/slab: reparent memcg kmem_caches on cgroup removal")
Signed-off-by: Roman Gushchin <guro@fb.com>
Reported-by: Karsten Graul <kgraul@linux.ibm.com>
Tested-by: Karsten Graul <kgraul@linux.ibm.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Karsten Graul <kgraul@linux.ibm.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/slab_common.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/mm/slab_common.c b/mm/slab_common.c
index c29f03adca91..f9fb27b4c843 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -178,10 +178,13 @@ static int init_memcg_params(struct kmem_cache *s,
 
 static void destroy_memcg_params(struct kmem_cache *s)
 {
-	if (is_root_cache(s))
+	if (is_root_cache(s)) {
 		kvfree(rcu_access_pointer(s->memcg_params.memcg_caches));
-	else
+	} else {
+		mem_cgroup_put(s->memcg_params.memcg);
+		WRITE_ONCE(s->memcg_params.memcg, NULL);
 		percpu_ref_exit(&s->memcg_params.refcnt);
+	}
 }
 
 static void free_memcg_params(struct rcu_head *rcu)
@@ -253,8 +256,6 @@ static void memcg_unlink_cache(struct kmem_cache *s)
 	} else {
 		list_del(&s->memcg_params.children_node);
 		list_del(&s->memcg_params.kmem_caches_node);
-		mem_cgroup_put(s->memcg_params.memcg);
-		WRITE_ONCE(s->memcg_params.memcg, NULL);
 	}
 }
 #else
-- 
cgit v1.2.3


From ce750f43f5790de74c1644c39d78f684071658d1 Mon Sep 17 00:00:00 2001
From: Chengguang Xu <cgxu519@mykernel.net>
Date: Fri, 18 Oct 2019 20:19:47 -0700
Subject: ocfs2: fix error handling in ocfs2_setattr()

Should set transfer_to[USRQUOTA/GRPQUOTA] to NULL on error case before
jumping to do dqput().

Link: http://lkml.kernel.org/r/20191010082349.1134-1-cgxu519@mykernel.net
Signed-off-by: Chengguang Xu <cgxu519@mykernel.net>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Gang He <ghe@suse.com>
Cc: Jun Piao <piaojun@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ocfs2/file.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 2e982db3e1ae..53939bf9d7d2 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1230,6 +1230,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 			transfer_to[USRQUOTA] = dqget(sb, make_kqid_uid(attr->ia_uid));
 			if (IS_ERR(transfer_to[USRQUOTA])) {
 				status = PTR_ERR(transfer_to[USRQUOTA]);
+				transfer_to[USRQUOTA] = NULL;
 				goto bail_unlock;
 			}
 		}
@@ -1239,6 +1240,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 			transfer_to[GRPQUOTA] = dqget(sb, make_kqid_gid(attr->ia_gid));
 			if (IS_ERR(transfer_to[GRPQUOTA])) {
 				status = PTR_ERR(transfer_to[GRPQUOTA]);
+				transfer_to[GRPQUOTA] = NULL;
 				goto bail_unlock;
 			}
 		}
-- 
cgit v1.2.3


From 6f24c8d30d08f270b54f4c2cb9b08dfccbe59c57 Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Fri, 18 Oct 2019 20:19:50 -0700
Subject: mm/gup_benchmark: add a missing "w" to getopt string

Even though gup_benchmark.c has code to handle the -w command-line option,
the "w" is not part of the getopt string.  It looks as if it has been
missing the whole time.

On my machine, this leads naturally to the following predictable result:

  $ sudo ./gup_benchmark -w
  ./gup_benchmark: invalid option -- 'w'

...which is fixed with this commit.

Link: http://lkml.kernel.org/r/20191014184639.1512873-2-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: kbuild test robot <lkp@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 tools/testing/selftests/vm/gup_benchmark.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index c0534e298b51..cb3fc09645c4 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -37,7 +37,7 @@ int main(int argc, char **argv)
 	char *file = "/dev/zero";
 	char *p;
 
-	while ((opt = getopt(argc, argv, "m:r:n:f:tTLUSH")) != -1) {
+	while ((opt = getopt(argc, argv, "m:r:n:f:tTLUwSH")) != -1) {
 		switch (opt) {
 		case 'm':
 			size = atoi(optarg) * MB;
-- 
cgit v1.2.3


From 0cd22afdcea21fa16bb5b0d3e0508ca42072d0bd Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Fri, 18 Oct 2019 20:19:53 -0700
Subject: mm/gup: fix a misnamed "write" argument, and a related bug

In several routines, the "flags" argument is incorrectly named "write".
Change it to "flags".

Also, in one place, the misnaming led to an actual bug:
"flags & FOLL_WRITE" is required, rather than just "flags".
(That problem was flagged by krobot, in v1 of this patch.)

Also, change the flags argument from int, to unsigned int.

You can see that this was a simple oversight, because the
calling code passes "flags" to the fifth argument:

gup_pgd_range():
    ...
    if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
		    PGDIR_SHIFT, next, flags, pages, nr))

...which, until this patch, the callees referred to as "write".

Also, change two lines to avoid checkpatch line length
complaints, and another line to fix another oversight
that checkpatch called out: missing "int" on pdshift.

Link: http://lkml.kernel.org/r/20191014184639.1512873-3-jhubbard@nvidia.com
Fixes: b798bec4741b ("mm/gup: change write parameter to flags in fast walk")
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Reported-by: kbuild test robot <lkp@intel.com>
Suggested-by: Kirill A. Shutemov <kirill@shutemov.name>
Suggested-by: Ira Weiny <ira.weiny@intel.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/gup.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 23a9f9c9d377..8f236a335ae9 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1973,7 +1973,8 @@ static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 }
 
 static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
-		       unsigned long end, int write, struct page **pages, int *nr)
+		       unsigned long end, unsigned int flags,
+		       struct page **pages, int *nr)
 {
 	unsigned long pte_end;
 	struct page *head, *page;
@@ -1986,7 +1987,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 
 	pte = READ_ONCE(*ptep);
 
-	if (!pte_access_permitted(pte, write))
+	if (!pte_access_permitted(pte, flags & FOLL_WRITE))
 		return 0;
 
 	/* hugepages are never "special" */
@@ -2023,7 +2024,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 }
 
 static int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
-		unsigned int pdshift, unsigned long end, int write,
+		unsigned int pdshift, unsigned long end, unsigned int flags,
 		struct page **pages, int *nr)
 {
 	pte_t *ptep;
@@ -2033,7 +2034,7 @@ static int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
 	ptep = hugepte_offset(hugepd, addr, pdshift);
 	do {
 		next = hugepte_addr_end(addr, end, sz);
-		if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
+		if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr))
 			return 0;
 	} while (ptep++, addr = next, addr != end);
 
@@ -2041,7 +2042,7 @@ static int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
 }
 #else
 static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
-		unsigned pdshift, unsigned long end, int write,
+		unsigned int pdshift, unsigned long end, unsigned int flags,
 		struct page **pages, int *nr)
 {
 	return 0;
@@ -2049,7 +2050,8 @@ static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
 #endif /* CONFIG_ARCH_HAS_HUGEPD */
 
 static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages, int *nr)
+			unsigned long end, unsigned int flags,
+			struct page **pages, int *nr)
 {
 	struct page *head, *page;
 	int refs;
-- 
cgit v1.2.3


From b11edebbc967ebf5c55b8f9e1d5bb6d68ec3a7fd Mon Sep 17 00:00:00 2001
From: Honglei Wang <honglei.wang@oracle.com>
Date: Fri, 18 Oct 2019 20:19:58 -0700
Subject: mm: memcg: get number of pages on the LRU list in memcgroup base on
 lru_zone_size

Commit 1a61ab8038e72 ("mm: memcontrol: replace zone summing with
lruvec_page_state()") has made lruvec_page_state to use per-cpu counters
instead of calculating it directly from lru_zone_size with an idea that
this would be more effective.

Tim has reported that this is not really the case for their database
benchmark which is showing an opposite results where lruvec_page_state
is taking up a huge chunk of CPU cycles (about 25% of the system time
which is roughly 7% of total cpu cycles) on 5.3 kernels.  The workload
is running on a larger machine (96cpus), it has many cgroups (500) and
it is heavily direct reclaim bound.

Tim Chen said:

: The problem can also be reproduced by running simple multi-threaded
: pmbench benchmark with a fast Optane SSD swap (see profile below).
:
:
: 6.15%     3.08%  pmbench          [kernel.vmlinux]            [k] lruvec_lru_size
:             |
:             |--3.07%--lruvec_lru_size
:             |          |
:             |          |--2.11%--cpumask_next
:             |          |          |
:             |          |           --1.66%--find_next_bit
:             |          |
:             |           --0.57%--call_function_interrupt
:             |                     |
:             |                      --0.55%--smp_call_function_interrupt
:             |
:             |--1.59%--0x441f0fc3d009
:             |          _ops_rdtsc_init_base_freq
:             |          access_histogram
:             |          page_fault
:             |          __do_page_fault
:             |          handle_mm_fault
:             |          __handle_mm_fault
:             |          |
:             |           --1.54%--do_swap_page
:             |                     swapin_readahead
:             |                     swap_cluster_readahead
:             |                     |
:             |                      --1.53%--read_swap_cache_async
:             |                                __read_swap_cache_async
:             |                                alloc_pages_vma
:             |                                __alloc_pages_nodemask
:             |                                __alloc_pages_slowpath
:             |                                try_to_free_pages
:             |                                do_try_to_free_pages
:             |                                shrink_node
:             |                                shrink_node_memcg
:             |                                |
:             |                                |--0.77%--lruvec_lru_size
:             |                                |
:             |                                 --0.76%--inactive_list_is_low
:             |                                           |
:             |                                            --0.76%--lruvec_lru_size
:             |
:              --1.50%--measure_read
:                        page_fault
:                        __do_page_fault
:                        handle_mm_fault
:                        __handle_mm_fault
:                        do_swap_page
:                        swapin_readahead
:                        swap_cluster_readahead
:                        |
:                         --1.48%--read_swap_cache_async
:                                   __read_swap_cache_async
:                                   alloc_pages_vma
:                                   __alloc_pages_nodemask
:                                   __alloc_pages_slowpath
:                                   try_to_free_pages
:                                   do_try_to_free_pages
:                                   shrink_node
:                                   shrink_node_memcg
:                                   |
:                                   |--0.75%--inactive_list_is_low
:                                   |          |
:                                   |           --0.75%--lruvec_lru_size
:                                   |
:                                    --0.73%--lruvec_lru_size

The likely culprit is the cache traffic the lruvec_page_state_local
generates.  Dave Hansen says:

: I was thinking purely of the cache footprint.  If it's reading
: pn->lruvec_stat_local->count[idx] is three separate cachelines, so 192
: bytes of cache *96 CPUs = 18k of data, mostly read-only.  1 cgroup would
: be 18k of data for the whole system and the caching would be pretty
: efficient and all 18k would probably survive a tight page fault loop in
: the L1.  500 cgroups would be ~90k of data per CPU thread which doesn't
: fit in the L1 and probably wouldn't survive a tight page fault loop if
: both logical threads were banging on different cgroups.
:
: It's just a theory, but it's why I noted the number of cgroups when I
: initially saw this show up in profiles

Fix the regression by partially reverting the said commit and calculate
the lru size explicitly.

Link: http://lkml.kernel.org/r/20190905071034.16822-1-honglei.wang@oracle.com
Fixes: 1a61ab8038e72 ("mm: memcontrol: replace zone summing with lruvec_page_state()")
Signed-off-by: Honglei Wang <honglei.wang@oracle.com>
Reported-by: Tim Chen <tim.c.chen@linux.intel.com>
Acked-by: Tim Chen <tim.c.chen@linux.intel.com>
Tested-by: Tim Chen <tim.c.chen@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: <stable@vger.kernel.org>	[5.2+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/vmscan.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index c6659bb758a4..024b7e929752 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -351,12 +351,13 @@ unsigned long zone_reclaimable_pages(struct zone *zone)
  */
 unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx)
 {
-	unsigned long lru_size;
+	unsigned long lru_size = 0;
 	int zid;
 
-	if (!mem_cgroup_disabled())
-		lru_size = lruvec_page_state_local(lruvec, NR_LRU_BASE + lru);
-	else
+	if (!mem_cgroup_disabled()) {
+		for (zid = 0; zid < MAX_NR_ZONES; zid++)
+			lru_size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
+	} else
 		lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
 
 	for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) {
-- 
cgit v1.2.3


From f3057ad767542be7bbac44e548cb44017178a163 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Fri, 18 Oct 2019 20:20:01 -0700
Subject: mm: memblock: do not enforce current limit for memblock_phys* family

Until commit 92d12f9544b7 ("memblock: refactor internal allocation
functions") the maximal address for memblock allocations was forced to
memblock.current_limit only for the allocation functions returning
virtual address.  The changes introduced by that commit moved the limit
enforcement into the allocation core and as a result the allocation
functions returning physical address also started to limit allocations
to memblock.current_limit.

This caused breakage of etnaviv GPU driver:

  etnaviv etnaviv: bound 130000.gpu (ops gpu_ops)
  etnaviv etnaviv: bound 134000.gpu (ops gpu_ops)
  etnaviv etnaviv: bound 2204000.gpu (ops gpu_ops)
  etnaviv-gpu 130000.gpu: model: GC2000, revision: 5108
  etnaviv-gpu 130000.gpu: command buffer outside valid memory window
  etnaviv-gpu 134000.gpu: model: GC320, revision: 5007
  etnaviv-gpu 134000.gpu: command buffer outside valid memory window
  etnaviv-gpu 2204000.gpu: model: GC355, revision: 1215
  etnaviv-gpu 2204000.gpu: Ignoring GPU with VG and FE2.0

Restore the behaviour of memblock_phys* family so that these functions
will not enforce memblock.current_limit.

Link: http://lkml.kernel.org/r/1570915861-17633-1-git-send-email-rppt@kernel.org
Fixes: 92d12f9544b7 ("memblock: refactor internal allocation functions")
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Reported-by: Adam Ford <aford173@gmail.com>
Tested-by: Adam Ford <aford173@gmail.com>	[imx6q-logicpd]
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Fabio Estevam <festevam@gmail.com>
Cc: Lucas Stach <l.stach@pengutronix.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memblock.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/mm/memblock.c b/mm/memblock.c
index 7d4f61ae666a..c4b16cae2bc9 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1356,9 +1356,6 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
 		align = SMP_CACHE_BYTES;
 	}
 
-	if (end > memblock.current_limit)
-		end = memblock.current_limit;
-
 again:
 	found = memblock_find_in_range_node(size, align, start, end, nid,
 					    flags);
@@ -1469,6 +1466,9 @@ static void * __init memblock_alloc_internal(
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, nid);
 
+	if (max_addr > memblock.current_limit)
+		max_addr = memblock.current_limit;
+
 	alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid);
 
 	/* retry allocation without lower limit */
-- 
cgit v1.2.3


From f231fe4235e22e18d847e05cbe705deaca56580a Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 18 Oct 2019 20:20:05 -0700
Subject: hugetlbfs: don't access uninitialized memmaps in
 pfn_range_valid_gigantic()

Uninitialized memmaps contain garbage and in the worst case trigger
kernel BUGs, especially with CONFIG_PAGE_POISONING.  They should not get
touched.

Let's make sure that we only consider online memory (managed by the
buddy) that has initialized memmaps.  ZONE_DEVICE is not applicable.

page_zone() will call page_to_nid(), which will trigger
VM_BUG_ON_PGFLAGS(PagePoisoned(page), page) with CONFIG_PAGE_POISONING
and CONFIG_DEBUG_VM_PGFLAGS when called on uninitialized memmaps.  This
can be the case when an offline memory block (e.g., never onlined) is
spanned by a zone.

Note: As explained by Michal in [1], alloc_contig_range() will verify
the range.  So it boils down to the wrong access in this function.

[1] http://lkml.kernel.org/r/20180423000943.GO17484@dhcp22.suse.cz

Link: http://lkml.kernel.org/r/20191015120717.4858-1-david@redhat.com
Fixes: f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online")	[visible after d0dc12e86b319]
Signed-off-by: David Hildenbrand <david@redhat.com>
Reported-by: Michal Hocko <mhocko@kernel.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: <stable@vger.kernel.org>	[4.13+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/hugetlb.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ef37c85423a5..b45a95363a84 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1084,11 +1084,10 @@ static bool pfn_range_valid_gigantic(struct zone *z,
 	struct page *page;
 
 	for (i = start_pfn; i < end_pfn; i++) {
-		if (!pfn_valid(i))
+		page = pfn_to_online_page(i);
+		if (!page)
 			return false;
 
-		page = pfn_to_page(i);
-
 		if (page_zone(page) != z)
 			return false;
 
-- 
cgit v1.2.3


From b918c43021baaa3648de09e19a4a3dd555a45f40 Mon Sep 17 00:00:00 2001
From: Yi Li <yilikernel@gmail.com>
Date: Fri, 18 Oct 2019 20:20:08 -0700
Subject: ocfs2: fix panic due to ocfs2_wq is null

mount.ocfs2 failed when reading ocfs2 filesystem superblock encounters
an error.  ocfs2_initialize_super() returns before allocating ocfs2_wq.
ocfs2_dismount_volume() triggers the following panic.

  Oct 15 16:09:27 cnwarekv-205120 kernel: On-disk corruption discovered.Please run fsck.ocfs2 once the filesystem is unmounted.
  Oct 15 16:09:27 cnwarekv-205120 kernel: (mount.ocfs2,22804,44): ocfs2_read_locked_inode:537 ERROR: status = -30
  Oct 15 16:09:27 cnwarekv-205120 kernel: (mount.ocfs2,22804,44): ocfs2_init_global_system_inodes:458 ERROR: status = -30
  Oct 15 16:09:27 cnwarekv-205120 kernel: (mount.ocfs2,22804,44): ocfs2_init_global_system_inodes:491 ERROR: status = -30
  Oct 15 16:09:27 cnwarekv-205120 kernel: (mount.ocfs2,22804,44): ocfs2_initialize_super:2313 ERROR: status = -30
  Oct 15 16:09:27 cnwarekv-205120 kernel: (mount.ocfs2,22804,44): ocfs2_fill_super:1033 ERROR: status = -30
  ------------[ cut here ]------------
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 11753 Comm: mount.ocfs2 Tainted: G  E
        4.14.148-200.ckv.x86_64 #1
  Hardware name: Sugon H320-G30/35N16-US, BIOS 0SSDX017 12/21/2018
  task: ffff967af0520000 task.stack: ffffa5f05484000
  RIP: 0010:mutex_lock+0x19/0x20
  Call Trace:
    flush_workqueue+0x81/0x460
    ocfs2_shutdown_local_alloc+0x47/0x440 [ocfs2]
    ocfs2_dismount_volume+0x84/0x400 [ocfs2]
    ocfs2_fill_super+0xa4/0x1270 [ocfs2]
    ? ocfs2_initialize_super.isa.211+0xf20/0xf20 [ocfs2]
    mount_bdev+0x17f/0x1c0
    mount_fs+0x3a/0x160

Link: http://lkml.kernel.org/r/1571139611-24107-1-git-send-email-yili@winhong.com
Signed-off-by: Yi Li <yilikernel@gmail.com>
Reviewed-by: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Gang He <ghe@suse.com>
Cc: Jun Piao <piaojun@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ocfs2/journal.c    | 3 ++-
 fs/ocfs2/localalloc.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 930e3d388579..699a560efbb0 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -217,7 +217,8 @@ void ocfs2_recovery_exit(struct ocfs2_super *osb)
 	/* At this point, we know that no more recovery threads can be
 	 * launched, so wait for any recovery completion work to
 	 * complete. */
-	flush_workqueue(osb->ocfs2_wq);
+	if (osb->ocfs2_wq)
+		flush_workqueue(osb->ocfs2_wq);
 
 	/*
 	 * Now that recovery is shut down, and the osb is about to be
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 158e5af767fd..720e9f94957e 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -377,7 +377,8 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 	struct ocfs2_dinode *alloc = NULL;
 
 	cancel_delayed_work(&osb->la_enable_wq);
-	flush_workqueue(osb->ocfs2_wq);
+	if (osb->ocfs2_wq)
+		flush_workqueue(osb->ocfs2_wq);
 
 	if (osb->local_alloc_state == OCFS2_LA_UNUSED)
 		goto out;
-- 
cgit v1.2.3


From ae8af4388db002bbd1df78ecee7ca31cee78e964 Mon Sep 17 00:00:00 2001
From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Date: Fri, 18 Oct 2019 20:20:11 -0700
Subject: mm/memcontrol: update lruvec counters in mem_cgroup_move_account

Mapped, dirty and writeback pages are also counted in per-lruvec stats.
These counters needs update when page is moved between cgroups.

Currently is nobody *consuming* the lruvec versions of these counters and
that there is no user-visible effect.

Link: http://lkml.kernel.org/r/157112699975.7360.1062614888388489788.stgit@buzz
Fixes: 00f3ca2c2d66 ("mm: memcontrol: per-lruvec stats infrastructure")
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memcontrol.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index bdac56009a38..363106578876 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5420,6 +5420,8 @@ static int mem_cgroup_move_account(struct page *page,
 				   struct mem_cgroup *from,
 				   struct mem_cgroup *to)
 {
+	struct lruvec *from_vec, *to_vec;
+	struct pglist_data *pgdat;
 	unsigned long flags;
 	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;
 	int ret;
@@ -5443,11 +5445,15 @@ static int mem_cgroup_move_account(struct page *page,
 
 	anon = PageAnon(page);
 
+	pgdat = page_pgdat(page);
+	from_vec = mem_cgroup_lruvec(pgdat, from);
+	to_vec = mem_cgroup_lruvec(pgdat, to);
+
 	spin_lock_irqsave(&from->move_lock, flags);
 
 	if (!anon && page_mapped(page)) {
-		__mod_memcg_state(from, NR_FILE_MAPPED, -nr_pages);
-		__mod_memcg_state(to, NR_FILE_MAPPED, nr_pages);
+		__mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages);
+		__mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages);
 	}
 
 	/*
@@ -5459,14 +5465,14 @@ static int mem_cgroup_move_account(struct page *page,
 		struct address_space *mapping = page_mapping(page);
 
 		if (mapping_cap_account_dirty(mapping)) {
-			__mod_memcg_state(from, NR_FILE_DIRTY, -nr_pages);
-			__mod_memcg_state(to, NR_FILE_DIRTY, nr_pages);
+			__mod_lruvec_state(from_vec, NR_FILE_DIRTY, -nr_pages);
+			__mod_lruvec_state(to_vec, NR_FILE_DIRTY, nr_pages);
 		}
 	}
 
 	if (PageWriteback(page)) {
-		__mod_memcg_state(from, NR_WRITEBACK, -nr_pages);
-		__mod_memcg_state(to, NR_WRITEBACK, nr_pages);
+		__mod_lruvec_state(from_vec, NR_WRITEBACK, -nr_pages);
+		__mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages);
 	}
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-- 
cgit v1.2.3


From f7daefe4231e57381d92c2e2ad905a899c28e402 Mon Sep 17 00:00:00 2001
From: Chenwandun <chenwandun@huawei.com>
Date: Fri, 18 Oct 2019 20:20:14 -0700
Subject: zram: fix race between backing_dev_show and backing_dev_store

CPU0:				       CPU1:
backing_dev_show		       backing_dev_store
    ......				   ......
    file = zram->backing_dev;
    down_read(&zram->init_lock);	   down_read(&zram->init_init_lock)
    file_path(file, ...);		   zram->backing_dev = backing_dev;
    up_read(&zram->init_lock);		   up_read(&zram->init_lock);

gets the value of zram->backing_dev too early in backing_dev_show, which
resultin the value being NULL at the beginning, and not NULL later.

backtrace:
  d_path+0xcc/0x174
  file_path+0x10/0x18
  backing_dev_show+0x40/0xb4
  dev_attr_show+0x20/0x54
  sysfs_kf_seq_show+0x9c/0x10c
  kernfs_seq_show+0x28/0x30
  seq_read+0x184/0x488
  kernfs_fop_read+0x5c/0x1a4
  __vfs_read+0x44/0x128
  vfs_read+0xa0/0x138
  SyS_read+0x54/0xb4

Link: http://lkml.kernel.org/r/1571046839-16814-1-git-send-email-chenwandun@huawei.com
Signed-off-by: Chenwandun <chenwandun@huawei.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: <stable@vger.kernel.org>	[4.14+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/block/zram/zram_drv.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index d58a359a6622..4285e75e52c3 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -413,13 +413,14 @@ static void reset_bdev(struct zram *zram)
 static ssize_t backing_dev_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
+	struct file *file;
 	struct zram *zram = dev_to_zram(dev);
-	struct file *file = zram->backing_dev;
 	char *p;
 	ssize_t ret;
 
 	down_read(&zram->init_lock);
-	if (!zram->backing_dev) {
+	file = zram->backing_dev;
+	if (!file) {
 		memcpy(buf, "none\n", 5);
 		up_read(&zram->init_lock);
 		return 5;
-- 
cgit v1.2.3


From 444f84fd2ac7bae36f3dd3ce1d39d11211c2c72a Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Fri, 18 Oct 2019 20:20:17 -0700
Subject: mm: include <linux/huge_mm.h> for is_vma_temporary_stack

Include <linux/huge_mm.h> for the definition of is_vma_temporary_stack
to fix the following sparse warning:

  mm/rmap.c:1673:6: warning: symbol 'is_vma_temporary_stack' was not declared. Should it be static?

Link: http://lkml.kernel.org/r/20191009151155.27763-1-ben.dooks@codethink.co.uk
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Reviewed-by: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/rmap.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/rmap.c b/mm/rmap.c
index d9a23bb773bf..0c7b2a9400d4 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -61,6 +61,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/migrate.h>
 #include <linux/hugetlb.h>
+#include <linux/huge_mm.h>
 #include <linux/backing-dev.h>
 #include <linux/page_idle.h>
 #include <linux/memremap.h>
-- 
cgit v1.2.3


From d0e6a5821cdf08eea91d8597dce1ad695ebeb8bc Mon Sep 17 00:00:00 2001
From: Ben Dooks <ben.dooks@codethink.co.uk>
Date: Fri, 18 Oct 2019 20:20:20 -0700
Subject: mm/filemap.c: include <linux/ramfs.h> for generic_file_vm_ops
 definition

The generic_file_vm_ops is defined in <linux/ramfs.h> so include it to
fix the following warning:

  mm/filemap.c:2717:35: warning: symbol 'generic_file_vm_ops' was not declared. Should it be static?

Link: http://lkml.kernel.org/r/20191008102311.25432-1-ben.dooks@codethink.co.uk
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/filemap.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/filemap.c b/mm/filemap.c
index 1146fcfa3215..85b7d087eb45 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -40,6 +40,7 @@
 #include <linux/rmap.h>
 #include <linux/delayacct.h>
 #include <linux/psi.h>
+#include <linux/ramfs.h>
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
-- 
cgit v1.2.3


From a2ae8c0551050cbf3232fbb3d963a9bbe7b57268 Mon Sep 17 00:00:00 2001
From: "Ben Dooks (Codethink)" <ben.dooks@codethink.co.uk>
Date: Fri, 18 Oct 2019 20:20:24 -0700
Subject: mm/init-mm.c: include <linux/mman.h> for vm_committed_as_batch

mm_init.c needs to include <linux/mman.h> for the definition of
vm_committed_as_batch.  Fixes the following sparse warning:

  mm/mm_init.c:141:5: warning: symbol 'vm_committed_as_batch' was not declared. Should it be static?

Link: http://lkml.kernel.org/r/20191016091509.26708-1-ben.dooks@codethink.co.uk
Signed-off-by: Ben Dooks <ben.dooks@codethink.co.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/init-mm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/init-mm.c b/mm/init-mm.c
index fb1e15028ef0..19603302a77f 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -5,6 +5,7 @@
 #include <linux/spinlock.h>
 #include <linux/list.h>
 #include <linux/cpumask.h>
+#include <linux/mman.h>
 
 #include <linux/atomic.h>
 #include <linux/user_namespace.h>
-- 
cgit v1.2.3


From 2be5fbf9a91c417cd178a481538baddda3e2f38c Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Fri, 18 Oct 2019 20:20:27 -0700
Subject: proc/meminfo: fix output alignment

Patch series "Fixes for THP in page cache", v2.

This patch (of 5):

Add extra space for FileHugePages and FilePmdMapped, so the output is
aligned with other rows.

Link: http://lkml.kernel.org/r/20191017164223.2762148-2-songliubraving@fb.com
Fixes: 60fbf0ab5da1 ("mm,thp: stats for file backed THP")
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Tested-by: Song Liu <songliubraving@fb.com>
Acked-by: Yang Shi <yang.shi@linux.alibaba.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/meminfo.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index ac9247371871..8c1f1bb1a5ce 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -132,9 +132,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		    global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR);
 	show_val_kb(m, "ShmemPmdMapped: ",
 		    global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR);
-	show_val_kb(m, "FileHugePages: ",
+	show_val_kb(m, "FileHugePages:  ",
 		    global_node_page_state(NR_FILE_THPS) * HPAGE_PMD_NR);
-	show_val_kb(m, "FilePmdMapped: ",
+	show_val_kb(m, "FilePmdMapped:  ",
 		    global_node_page_state(NR_FILE_PMDMAPPED) * HPAGE_PMD_NR);
 #endif
 
-- 
cgit v1.2.3


From 06d3eff62d9dc6f21e7ebeb14399f2542a36cdf5 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Fri, 18 Oct 2019 20:20:30 -0700
Subject: mm/thp: fix node page state in split_huge_page_to_list()

Make sure split_huge_page_to_list() handles the state of shmem THP and
file THP properly.

Link: http://lkml.kernel.org/r/20191017164223.2762148-3-songliubraving@fb.com
Fixes: 60fbf0ab5da1 ("mm,thp: stats for file backed THP")
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Tested-by: Song Liu <songliubraving@fb.com>
Acked-by: Yang Shi <yang.shi@linux.alibaba.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/huge_memory.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c5cb6dcd6c69..13cc93785006 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2789,8 +2789,13 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 			ds_queue->split_queue_len--;
 			list_del(page_deferred_list(head));
 		}
-		if (mapping)
-			__dec_node_page_state(page, NR_SHMEM_THPS);
+		if (mapping) {
+			if (PageSwapBacked(page))
+				__dec_node_page_state(page, NR_SHMEM_THPS);
+			else
+				__dec_node_page_state(page, NR_FILE_THPS);
+		}
+
 		spin_unlock(&ds_queue->split_queue_lock);
 		__split_huge_page(page, list, end, flags);
 		if (PageSwapCache(head)) {
-- 
cgit v1.2.3


From 906d278d75e364f2bb85dc1e1ff6265ea46e7e43 Mon Sep 17 00:00:00 2001
From: William Kucharski <william.kucharski@oracle.com>
Date: Fri, 18 Oct 2019 20:20:33 -0700
Subject: mm/vmscan.c: support removing arbitrary sized pages from mapping

__remove_mapping() assumes that pages can only be either base pages or
HPAGE_PMD_SIZE.  Ask the page what size it is.

Link: http://lkml.kernel.org/r/20191017164223.2762148-4-songliubraving@fb.com
Fixes: 99cb0dbd47a1 ("mm,thp: add read-only THP support for (non-shmem) FS")
Signed-off-by: William Kucharski <william.kucharski@oracle.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Song Liu <songliubraving@fb.com>
Acked-by: Yang Shi <yang.shi@linux.alibaba.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/vmscan.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 024b7e929752..ee4eecc7e1c2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -933,10 +933,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 	 * Note that if SetPageDirty is always performed via set_page_dirty,
 	 * and thus under the i_pages lock, then this ordering is not required.
 	 */
-	if (unlikely(PageTransHuge(page)) && PageSwapCache(page))
-		refcount = 1 + HPAGE_PMD_NR;
-	else
-		refcount = 2;
+	refcount = 1 + compound_nr(page);
 	if (!page_ref_freeze(page, refcount))
 		goto cannot_free;
 	/* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */
-- 
cgit v1.2.3


From ef18a1ca847b01cb7296f11a728cb2f5ef671760 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Fri, 18 Oct 2019 20:20:36 -0700
Subject: mm/thp: allow dropping THP from page cache

Once a THP is added to the page cache, it cannot be dropped via
/proc/sys/vm/drop_caches.  Fix this issue with proper handling in
invalidate_mapping_pages().

Link: http://lkml.kernel.org/r/20191017164223.2762148-5-songliubraving@fb.com
Fixes: 99cb0dbd47a1 ("mm,thp: add read-only THP support for (non-shmem) FS")
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Song Liu <songliubraving@fb.com>
Tested-by: Song Liu <songliubraving@fb.com>
Acked-by: Yang Shi <yang.shi@linux.alibaba.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/truncate.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/mm/truncate.c b/mm/truncate.c
index 8563339041f6..dd9ebc1da356 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -592,6 +592,16 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 					unlock_page(page);
 					continue;
 				}
+
+				/* Take a pin outside pagevec */
+				get_page(page);
+
+				/*
+				 * Drop extra pins before trying to invalidate
+				 * the huge page.
+				 */
+				pagevec_remove_exceptionals(&pvec);
+				pagevec_release(&pvec);
 			}
 
 			ret = invalidate_inode_page(page);
@@ -602,6 +612,8 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 			 */
 			if (!ret)
 				deactivate_file_page(page);
+			if (PageTransHuge(page))
+				put_page(page);
 			count += ret;
 		}
 		pagevec_remove_exceptionals(&pvec);
-- 
cgit v1.2.3


From aa5de305c90c995321df452f274fe75b52bd8fcc Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Fri, 18 Oct 2019 20:20:40 -0700
Subject: kernel/events/uprobes.c: only do FOLL_SPLIT_PMD for uprobe register

Attaching uprobe to text section in THP splits the PMD mapped page table
into PTE mapped entries.  On uprobe detach, we would like to regroup PMD
mapped page table entry to regain performance benefit of THP.

However, the regroup is broken For perf_event based trace_uprobe.  This
is because perf_event based trace_uprobe calls uprobe_unregister twice
on close: first in TRACE_REG_PERF_CLOSE, then in
TRACE_REG_PERF_UNREGISTER.  The second call will split the PMD mapped
page table entry, which is not the desired behavior.

Fix this by only use FOLL_SPLIT_PMD for uprobe register case.

Add a WARN() to confirm uprobe unregister never work on huge pages, and
abort the operation when this WARN() triggers.

Link: http://lkml.kernel.org/r/20191017164223.2762148-6-songliubraving@fb.com
Fixes: 5a52c9df62b4 ("uprobe: use FOLL_SPLIT_PMD instead of FOLL_SPLIT")
Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: William Kucharski <william.kucharski@oracle.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/events/uprobes.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 94d38a39d72e..c74761004ee5 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -474,14 +474,17 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	struct vm_area_struct *vma;
 	int ret, is_register, ref_ctr_updated = 0;
 	bool orig_page_huge = false;
+	unsigned int gup_flags = FOLL_FORCE;
 
 	is_register = is_swbp_insn(&opcode);
 	uprobe = container_of(auprobe, struct uprobe, arch);
 
 retry:
+	if (is_register)
+		gup_flags |= FOLL_SPLIT_PMD;
 	/* Read the page with vaddr into memory */
-	ret = get_user_pages_remote(NULL, mm, vaddr, 1,
-			FOLL_FORCE | FOLL_SPLIT_PMD, &old_page, &vma, NULL);
+	ret = get_user_pages_remote(NULL, mm, vaddr, 1, gup_flags,
+				    &old_page, &vma, NULL);
 	if (ret <= 0)
 		return ret;
 
@@ -489,6 +492,12 @@ retry:
 	if (ret <= 0)
 		goto put_old;
 
+	if (WARN(!is_register && PageCompound(old_page),
+		 "uprobe unregister should never work on compound page\n")) {
+		ret = -EINVAL;
+		goto put_old;
+	}
+
 	/* We are going to replace instruction, update ref_ctr. */
 	if (!ref_ctr_updated && uprobe->ref_ctr_offset) {
 		ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1);
-- 
cgit v1.2.3


From 585d730d41120926e3f79a601edad3930fa28366 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Fri, 18 Oct 2019 20:20:43 -0700
Subject: scripts/gdb: fix debugging modules on s390

Currently lx-symbols assumes that module text is always located at
module->core_layout->base, but s390 uses the following layout:

  +------+  <- module->core_layout->base
  | GOT  |
  +------+  <- module->core_layout->base + module->arch->plt_offset
  | PLT  |
  +------+  <- module->core_layout->base + module->arch->plt_offset +
  | TEXT |     module->arch->plt_size
  +------+

Therefore, when trying to debug modules on s390, all the symbol
addresses are skewed by plt_offset + plt_size.

Fix by adding plt_offset + plt_size to module_addr in
load_module_symbols().

Link: http://lkml.kernel.org/r/20191017085917.81791-1-iii@linux.ibm.com
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Reviewed-by: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Kieran Bingham <kbingham@kernel.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 scripts/gdb/linux/symbols.py | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py
index 34e40e96dee2..7b7c2fafbc68 100644
--- a/scripts/gdb/linux/symbols.py
+++ b/scripts/gdb/linux/symbols.py
@@ -15,7 +15,7 @@ import gdb
 import os
 import re
 
-from linux import modules
+from linux import modules, utils
 
 
 if hasattr(gdb, 'Breakpoint'):
@@ -116,6 +116,12 @@ lx-symbols command."""
             module_file = self._get_module_file(module_name)
 
         if module_file:
+            if utils.is_target_arch('s390'):
+                # Module text is preceded by PLT stubs on s390.
+                module_arch = module['arch']
+                plt_offset = int(module_arch['plt_offset'])
+                plt_size = int(module_arch['plt_size'])
+                module_addr = hex(int(module_addr, 0) + plt_offset + plt_size)
             gdb.write("loading @{addr}: {filename}\n".format(
                 addr=module_addr, filename=module_file))
             cmdline = "add-symbol-file {filename} {addr}{sections}".format(
-- 
cgit v1.2.3


From 580a05f9d4ada3bfb689140d0efec1efdb8a48da Mon Sep 17 00:00:00 2001
From: Yonglong Liu <liuyonglong@huawei.com>
Date: Fri, 18 Oct 2019 11:42:59 +0800
Subject: net: hns3: fix mis-counting IRQ vector numbers issue

Currently, the num_msi_left means the vector numbers of NIC,
but if the PF supported RoCE, it contains the vector numbers
of NIC and RoCE(Not expected).

This may cause interrupts lost in some case, because of the
NIC module used the vector resources which belongs to RoCE.

This patch adds a new variable num_nic_msi to store the vector
numbers of NIC, and adjust the default TQP numbers and rss_size
according to the value of num_nic_msi.

Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support")
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  2 ++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 21 +++++++++++++++-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  1 +
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c  | 11 +++++++--
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 28 +++++++++++++++++++---
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  1 +
 6 files changed, 58 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index c4b7bf851a28..75ccc1e7076b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -32,6 +32,8 @@
 
 #define HNAE3_MOD_VERSION "1.0"
 
+#define HNAE3_MIN_VECTOR_NUM	2 /* first one for misc, another for IO */
+
 /* Device IDs */
 #define HNAE3_DEV_ID_GE				0xA220
 #define HNAE3_DEV_ID_25GE			0xA221
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index fd7f94372ff0..e02e01bd9eff 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -906,6 +906,9 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 		hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
 				HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
 
+		/* nic's msix numbers is always equals to the roce's. */
+		hdev->num_nic_msi = hdev->num_roce_msi;
+
 		/* PF should have NIC vectors and Roce vectors,
 		 * NIC vectors are queued before Roce vectors.
 		 */
@@ -915,6 +918,15 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 		hdev->num_msi =
 		hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
 				HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
+
+		hdev->num_nic_msi = hdev->num_msi;
+	}
+
+	if (hdev->num_nic_msi < HNAE3_MIN_VECTOR_NUM) {
+		dev_err(&hdev->pdev->dev,
+			"Just %u msi resources, not enough for pf(min:2).\n",
+			hdev->num_nic_msi);
+		return -EINVAL;
 	}
 
 	return 0;
@@ -1507,6 +1519,10 @@ static int  hclge_assign_tqp(struct hclge_vport *vport, u16 num_tqps)
 	kinfo->rss_size = min_t(u16, hdev->rss_size_max,
 				vport->alloc_tqps / hdev->tm_info.num_tc);
 
+	/* ensure one to one mapping between irq and queue at default */
+	kinfo->rss_size = min_t(u16, kinfo->rss_size,
+				(hdev->num_nic_msi - 1) / hdev->tm_info.num_tc);
+
 	return 0;
 }
 
@@ -2285,7 +2301,8 @@ static int hclge_init_msi(struct hclge_dev *hdev)
 	int vectors;
 	int i;
 
-	vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi,
+	vectors = pci_alloc_irq_vectors(pdev, HNAE3_MIN_VECTOR_NUM,
+					hdev->num_msi,
 					PCI_IRQ_MSI | PCI_IRQ_MSIX);
 	if (vectors < 0) {
 		dev_err(&pdev->dev,
@@ -2300,6 +2317,7 @@ static int hclge_init_msi(struct hclge_dev *hdev)
 
 	hdev->num_msi = vectors;
 	hdev->num_msi_left = vectors;
+
 	hdev->base_msi_vector = pdev->irq;
 	hdev->roce_base_vector = hdev->base_msi_vector +
 				hdev->roce_base_msix_offset;
@@ -3903,6 +3921,7 @@ static int hclge_get_vector(struct hnae3_handle *handle, u16 vector_num,
 	int alloc = 0;
 	int i, j;
 
+	vector_num = min_t(u16, hdev->num_nic_msi - 1, vector_num);
 	vector_num = min(hdev->num_msi_left, vector_num);
 
 	for (j = 0; j < vector_num; j++) {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 3e9574a9e22d..c3d56b872ed7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -763,6 +763,7 @@ struct hclge_dev {
 	u32 base_msi_vector;
 	u16 *vector_status;
 	int *vector_irq;
+	u16 num_nic_msi;	/* Num of nic vectors for this PF */
 	u16 num_roce_msi;	/* Num of roce vectors for this PF */
 	int roce_base_vector;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 9f0e35f27789..62399cc1c5a6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -537,9 +537,16 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport)
 		kinfo->rss_size = kinfo->req_rss_size;
 	} else if (kinfo->rss_size > max_rss_size ||
 		   (!kinfo->req_rss_size && kinfo->rss_size < max_rss_size)) {
+		/* if user not set rss, the rss_size should compare with the
+		 * valid msi numbers to ensure one to one map between tqp and
+		 * irq as default.
+		 */
+		if (!kinfo->req_rss_size)
+			max_rss_size = min_t(u16, max_rss_size,
+					     (hdev->num_nic_msi - 1) /
+					     kinfo->num_tc);
+
 		/* Set to the maximum specification value (max_rss_size). */
-		dev_info(&hdev->pdev->dev, "rss changes from %d to %d\n",
-			 kinfo->rss_size, max_rss_size);
 		kinfo->rss_size = max_rss_size;
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index e3090b3dab1d..7d7e712691b9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -411,6 +411,13 @@ static int hclgevf_knic_setup(struct hclgevf_dev *hdev)
 		kinfo->tqp[i] = &hdev->htqp[i].q;
 	}
 
+	/* after init the max rss_size and tqps, adjust the default tqp numbers
+	 * and rss size with the actual vector numbers
+	 */
+	kinfo->num_tqps = min_t(u16, hdev->num_nic_msix - 1, kinfo->num_tqps);
+	kinfo->rss_size = min_t(u16, kinfo->num_tqps / kinfo->num_tc,
+				kinfo->rss_size);
+
 	return 0;
 }
 
@@ -502,6 +509,7 @@ static int hclgevf_get_vector(struct hnae3_handle *handle, u16 vector_num,
 	int alloc = 0;
 	int i, j;
 
+	vector_num = min_t(u16, hdev->num_nic_msix - 1, vector_num);
 	vector_num = min(hdev->num_msi_left, vector_num);
 
 	for (j = 0; j < vector_num; j++) {
@@ -2246,13 +2254,14 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
 	int vectors;
 	int i;
 
-	if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B))
+	if (hnae3_dev_roce_supported(hdev))
 		vectors = pci_alloc_irq_vectors(pdev,
 						hdev->roce_base_msix_offset + 1,
 						hdev->num_msi,
 						PCI_IRQ_MSIX);
 	else
-		vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi,
+		vectors = pci_alloc_irq_vectors(pdev, HNAE3_MIN_VECTOR_NUM,
+						hdev->num_msi,
 						PCI_IRQ_MSI | PCI_IRQ_MSIX);
 
 	if (vectors < 0) {
@@ -2268,6 +2277,7 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
 
 	hdev->num_msi = vectors;
 	hdev->num_msi_left = vectors;
+
 	hdev->base_msi_vector = pdev->irq;
 	hdev->roce_base_vector = pdev->irq + hdev->roce_base_msix_offset;
 
@@ -2533,7 +2543,7 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
 
 	req = (struct hclgevf_query_res_cmd *)desc.data;
 
-	if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)) {
+	if (hnae3_dev_roce_supported(hdev)) {
 		hdev->roce_base_msix_offset =
 		hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee),
 				HCLGEVF_MSIX_OFT_ROCEE_M,
@@ -2542,6 +2552,9 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
 		hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number),
 				HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S);
 
+		/* nic's msix numbers is always equals to the roce's. */
+		hdev->num_nic_msix = hdev->num_roce_msix;
+
 		/* VF should have NIC vectors and Roce vectors, NIC vectors
 		 * are queued before Roce vectors. The offset is fixed to 64.
 		 */
@@ -2551,6 +2564,15 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
 		hdev->num_msi =
 		hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number),
 				HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S);
+
+		hdev->num_nic_msix = hdev->num_msi;
+	}
+
+	if (hdev->num_nic_msix < HNAE3_MIN_VECTOR_NUM) {
+		dev_err(&hdev->pdev->dev,
+			"Just %u msi resources, not enough for vf(min:2).\n",
+			hdev->num_nic_msix);
+		return -EINVAL;
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index bdde3afc286b..2b8d6bc6d224 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -270,6 +270,7 @@ struct hclgevf_dev {
 	u16 num_msi;
 	u16 num_msi_left;
 	u16 num_msi_used;
+	u16 num_nic_msix;	/* Num of nic vectors for this VF */
 	u16 num_roce_msix;	/* Num of roce vectors for this VF */
 	u16 roce_base_msix_offset;
 	int roce_base_vector;
-- 
cgit v1.2.3


From 3d5c1a037d37392a6859afbde49be5ba6a70a6b3 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Fri, 18 Oct 2019 09:45:49 +0200
Subject: xen/netback: fix error path of xenvif_connect_data()

xenvif_connect_data() calls module_put() in case of error. This is
wrong as there is no related module_get().

Remove the superfluous module_put().

Fixes: 279f438e36c0a7 ("xen-netback: Don't destroy the netdev until the vif is shut down")
Cc: <stable@vger.kernel.org> # 3.12
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Paul Durrant <paul@xen.org>
Reviewed-by: Wei Liu <wei.liu@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/interface.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 240f762b3749..103ed00775eb 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -719,7 +719,6 @@ err_unmap:
 	xenvif_unmap_frontend_data_rings(queue);
 	netif_napi_del(&queue->napi);
 err:
-	module_put(THIS_MODULE);
 	return err;
 }
 
-- 
cgit v1.2.3


From bd310aca442fcc72731b7acb65d32d05c956d56b Mon Sep 17 00:00:00 2001
From: Michael Tretter <m.tretter@pengutronix.de>
Date: Fri, 18 Oct 2019 16:11:43 +0200
Subject: macb: propagate errors when getting optional clocks

The tx_clk, rx_clk, and tsu_clk are optional. Currently the macb driver
marks clock as not available if it receives an error when trying to get
a clock. This is wrong, because a clock controller might return
-EPROBE_DEFER if a clock is not available, but will eventually become
available.

In these cases, the driver would probe successfully but will never be
able to adjust the clocks, because the clocks were not available during
probe, but became available later.

For example, the clock controller for the ZynqMP is implemented in the
PMU firmware and the clocks are only available after the firmware driver
has been probed.

Use devm_clk_get_optional() in instead of devm_clk_get() to get the
optional clock and propagate all errors to the calling function.

Signed-off-by: Michael Tretter <m.tretter@pengutronix.de>
Acked-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Tested-by: Nicolas Ferre <nicolas.ferre@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 8e8d557901a9..1e1b774e1953 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3405,17 +3405,17 @@ static int macb_clk_init(struct platform_device *pdev, struct clk **pclk,
 		return err;
 	}
 
-	*tx_clk = devm_clk_get(&pdev->dev, "tx_clk");
+	*tx_clk = devm_clk_get_optional(&pdev->dev, "tx_clk");
 	if (IS_ERR(*tx_clk))
-		*tx_clk = NULL;
+		return PTR_ERR(*tx_clk);
 
-	*rx_clk = devm_clk_get(&pdev->dev, "rx_clk");
+	*rx_clk = devm_clk_get_optional(&pdev->dev, "rx_clk");
 	if (IS_ERR(*rx_clk))
-		*rx_clk = NULL;
+		return PTR_ERR(*rx_clk);
 
-	*tsu_clk = devm_clk_get(&pdev->dev, "tsu_clk");
+	*tsu_clk = devm_clk_get_optional(&pdev->dev, "tsu_clk");
 	if (IS_ERR(*tsu_clk))
-		*tsu_clk = NULL;
+		return PTR_ERR(*tsu_clk);
 
 	err = clk_prepare_enable(*pclk);
 	if (err) {
-- 
cgit v1.2.3


From a7fa12d15855904aff1716e1fc723c03ba38c5cc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 18 Oct 2019 09:16:57 -0700
Subject: net: netem: fix error path for corrupted GSO frames

To corrupt a GSO frame we first perform segmentation.  We then
proceed using the first segment instead of the full GSO skb and
requeue the rest of the segments as separate packets.

If there are any issues with processing the first segment we
still want to process the rest, therefore we jump to the
finish_segs label.

Commit 177b8007463c ("net: netem: fix backlog accounting for
corrupted GSO frames") started using the pointer to the first
segment in the "rest of segments processing", but as mentioned
above the first segment may had already been freed at this point.

Backlog corrections for parent qdiscs have to be adjusted.

Fixes: 177b8007463c ("net: netem: fix backlog accounting for corrupted GSO frames")
Reported-by: kbuild test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Reported-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_netem.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 0e44039e729c..942eb17f413c 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -509,6 +509,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		if (skb->ip_summed == CHECKSUM_PARTIAL &&
 		    skb_checksum_help(skb)) {
 			qdisc_drop(skb, sch, to_free);
+			skb = NULL;
 			goto finish_segs;
 		}
 
@@ -593,9 +594,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 finish_segs:
 	if (segs) {
 		unsigned int len, last_len;
-		int nb = 0;
+		int nb;
 
-		len = skb->len;
+		len = skb ? skb->len : 0;
+		nb = skb ? 1 : 0;
 
 		while (segs) {
 			skb2 = segs->next;
@@ -612,7 +614,8 @@ finish_segs:
 			}
 			segs = skb2;
 		}
-		qdisc_tree_reduce_backlog(sch, -nb, prev_len - len);
+		/* Parent qdiscs accounted for 1 skb of size @prev_len */
+		qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len));
 	}
 	return NET_XMIT_SUCCESS;
 }
-- 
cgit v1.2.3


From e0ad032e144731a5928f2d75e91c2064ba1a764c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 18 Oct 2019 09:16:58 -0700
Subject: net: netem: correct the parent's backlog when corrupted packet was
 dropped

If packet corruption failed we jump to finish_segs and return
NET_XMIT_SUCCESS. Seeing success will make the parent qdisc
increment its backlog, that's incorrect - we need to return
NET_XMIT_DROP.

Fixes: 6071bd1aa13e ("netem: Segment GSO packets on enqueue")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_netem.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 942eb17f413c..42e557d48e4e 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -616,6 +616,8 @@ finish_segs:
 		}
 		/* Parent qdiscs accounted for 1 skb of size @prev_len */
 		qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len));
+	} else if (!skb) {
+		return NET_XMIT_DROP;
 	}
 	return NET_XMIT_SUCCESS;
 }
-- 
cgit v1.2.3


From 3d00cf2fbb61212f47a3cf838be51c921366c937 Mon Sep 17 00:00:00 2001
From: Chenwandun <chenwandun@huawei.com>
Date: Fri, 18 Oct 2019 18:20:37 +0800
Subject: net: aquantia: add an error handling in aq_nic_set_multicast_list

add an error handling in aq_nic_set_multicast_list, it may not
work when hw_multicast_list_set error; and at the same time
it will remove gcc Wunused-but-set-variable warning.

Signed-off-by: Chenwandun <chenwandun@huawei.com>
Reviewed-by: Igor Russkikh <igor.russkikh@aquantia.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 2a18439b36fb..137c1de4c6ec 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -664,6 +664,8 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev)
 		err = hw_ops->hw_multicast_list_set(self->aq_hw,
 						    self->mc_list.ar,
 						    self->mc_list.count);
+		if (err < 0)
+			return err;
 	}
 	return aq_nic_set_packet_filter(self, packet_filter);
 }
-- 
cgit v1.2.3


From 05908d72cc8fa39058cd9535db2833089cc3df6f Mon Sep 17 00:00:00 2001
From: Mans Rullgard <mans@mansr.com>
Date: Fri, 18 Oct 2019 17:56:58 +0100
Subject: net: ethernet: dwmac-sun8i: show message only when switching to
 promisc

Printing the info message every time more than the max number of mac
addresses are requested generates unnecessary log spam.  Showing it only
when the hw is not already in promiscous mode is equally informative
without being annoying.

Signed-off-by: Mans Rullgard <mans@mansr.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index f97a4096f8fc..ddcc191febdb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -651,7 +651,8 @@ static void sun8i_dwmac_set_filter(struct mac_device_info *hw,
 			}
 		}
 	} else {
-		netdev_info(dev, "Too many address, switching to promiscuous\n");
+		if (!(readl(ioaddr + EMAC_RX_FRM_FLT) & EMAC_FRM_FLT_RXALL))
+			netdev_info(dev, "Too many address, switching to promiscuous\n");
 		v = EMAC_FRM_FLT_RXALL;
 	}
 
-- 
cgit v1.2.3


From 50c7d2ba9de20f60a2d527ad6928209ef67e4cdd Mon Sep 17 00:00:00 2001
From: Vivien Didelot <vivien.didelot@gmail.com>
Date: Fri, 18 Oct 2019 17:02:46 -0400
Subject: net: dsa: fix switch tree list

If there are multiple switch trees on the device, only the last one
will be listed, because the arguments of list_add_tail are swapped.

Fixes: 83c0afaec7b7 ("net: dsa: Add new binding implementation")
Signed-off-by: Vivien Didelot <vivien.didelot@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dsa/dsa2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 73002022c9d8..716d265ba8ca 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -46,7 +46,7 @@ static struct dsa_switch_tree *dsa_tree_alloc(int index)
 	dst->index = index;
 
 	INIT_LIST_HEAD(&dst->list);
-	list_add_tail(&dsa_tree_list, &dst->list);
+	list_add_tail(&dst->list, &dsa_tree_list);
 
 	kref_init(&dst->refcount);
 
-- 
cgit v1.2.3


From 2a06b8982f8f2f40d03a3daf634676386bd84dbc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 18 Oct 2019 15:20:05 -0700
Subject: net: reorder 'struct net' fields to avoid false sharing

Intel test robot reported a ~7% regression on TCP_CRR tests
that they bisected to the cited commit.

Indeed, every time a new TCP socket is created or deleted,
the atomic counter net->count is touched (via get_net(net)
and put_net(net) calls)

So cpus might have to reload a contended cache line in
net_hash_mix(net) calls.

We need to reorder 'struct net' fields to move @hash_mix
in a read mostly cache line.

We move in the first cache line fields that can be
dirtied often.

We probably will have to address in a followup patch
the __randomize_layout that was added in linux-4.13,
since this might break our placement choices.

Fixes: 355b98553789 ("netns: provide pure entropy for net_hash_mix()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index f8712bbeb2e0..4c2cd9378699 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -52,6 +52,9 @@ struct bpf_prog;
 #define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
 
 struct net {
+	/* First cache line can be often dirtied.
+	 * Do not place here read-mostly fields.
+	 */
 	refcount_t		passive;	/* To decide when the network
 						 * namespace should be freed.
 						 */
@@ -60,7 +63,13 @@ struct net {
 						 */
 	spinlock_t		rules_mod_lock;
 
-	u32			hash_mix;
+	unsigned int		dev_unreg_count;
+
+	unsigned int		dev_base_seq;	/* protected by rtnl_mutex */
+	int			ifindex;
+
+	spinlock_t		nsid_lock;
+	atomic_t		fnhe_genid;
 
 	struct list_head	list;		/* list of network namespaces */
 	struct list_head	exit_list;	/* To linked to call pernet exit
@@ -76,11 +85,11 @@ struct net {
 #endif
 	struct user_namespace   *user_ns;	/* Owning user namespace */
 	struct ucounts		*ucounts;
-	spinlock_t		nsid_lock;
 	struct idr		netns_ids;
 
 	struct ns_common	ns;
 
+	struct list_head 	dev_base_head;
 	struct proc_dir_entry 	*proc_net;
 	struct proc_dir_entry 	*proc_net_stat;
 
@@ -93,17 +102,18 @@ struct net {
 
 	struct uevent_sock	*uevent_sock;		/* uevent socket */
 
-	struct list_head 	dev_base_head;
 	struct hlist_head 	*dev_name_head;
 	struct hlist_head	*dev_index_head;
-	unsigned int		dev_base_seq;	/* protected by rtnl_mutex */
-	int			ifindex;
-	unsigned int		dev_unreg_count;
+	/* Note that @hash_mix can be read millions times per second,
+	 * it is critical that it is on a read_mostly cache line.
+	 */
+	u32			hash_mix;
+
+	struct net_device       *loopback_dev;          /* The loopback */
 
 	/* core fib_rules */
 	struct list_head	rules_ops;
 
-	struct net_device       *loopback_dev;          /* The loopback */
 	struct netns_core	core;
 	struct netns_mib	mib;
 	struct netns_packet	packet;
@@ -171,7 +181,6 @@ struct net {
 	struct sock		*crypto_nlsk;
 #endif
 	struct sock		*diag_nlsk;
-	atomic_t		fnhe_genid;
 } __randomize_layout;
 
 #include <linux/seq_file_net.h>
-- 
cgit v1.2.3


From 8814c6d01f7e82e6be70ac04d8bca0fc90757418 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Sun, 20 Oct 2019 00:46:47 +0300
Subject: drm/i915/perf: fix oa config reconfiguration

The current logic just reapplies the same configuration already stored
into stream->oa_config instead of the newly selected one.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 7831e9a965ea ("drm/i915/perf: Allow dynamic reconfiguration of the OA stream")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191019214647.27866-1-lionel.g.landwerlin@intel.com
---
 drivers/gpu/drm/i915/i915_perf.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 54ec1c4190ac..d2ac51fe4f04 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1863,13 +1863,14 @@ out:
 }
 
 static int emit_oa_config(struct i915_perf_stream *stream,
+			  struct i915_oa_config *oa_config,
 			  struct intel_context *ce)
 {
 	struct i915_request *rq;
 	struct i915_vma *vma;
 	int err;
 
-	vma = get_oa_vma(stream, stream->oa_config);
+	vma = get_oa_vma(stream, oa_config);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
@@ -1927,7 +1928,7 @@ static int hsw_enable_metric_set(struct i915_perf_stream *stream)
 	intel_uncore_rmw(uncore, GEN6_UCGCTL1,
 			 0, GEN6_CSUNIT_CLOCK_GATE_DISABLE);
 
-	return emit_oa_config(stream, oa_context(stream));
+	return emit_oa_config(stream, stream->oa_config, oa_context(stream));
 }
 
 static void hsw_disable_metric_set(struct i915_perf_stream *stream)
@@ -2250,7 +2251,7 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
-	const struct i915_oa_config *oa_config = stream->oa_config;
+	struct i915_oa_config *oa_config = stream->oa_config;
 	int ret;
 
 	/*
@@ -2291,7 +2292,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	if (ret)
 		return ret;
 
-	return emit_oa_config(stream, oa_context(stream));
+	return emit_oa_config(stream, oa_config, oa_context(stream));
 }
 
 static void gen8_disable_metric_set(struct i915_perf_stream *stream)
@@ -2895,7 +2896,7 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
 		 * When set globally, we use a low priority kernel context,
 		 * so it will effectively take effect when idle.
 		 */
-		err = emit_oa_config(stream, oa_context(stream));
+		err = emit_oa_config(stream, config, oa_context(stream));
 		if (err == 0)
 			config = xchg(&stream->oa_config, config);
 		else
-- 
cgit v1.2.3


From 0dc3c562aa95e029f40779c5c9709c7c1bdeb415 Mon Sep 17 00:00:00 2001
From: Andi Shyti <andi.shyti@intel.com>
Date: Sun, 20 Oct 2019 19:41:39 +0100
Subject: drm/i915: Extract GT ring management

Although the ring management is much smaller compared to the other GT
power management functions, continue the theme of extracting it out of
the huge intel_pm.c for maintenance.

Based on a patch by Chris Wilson.

Signed-off-by: Andi Shyti <andi.shyti@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191020184139.9145-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/Makefile             |   1 +
 drivers/gpu/drm/i915/gt/intel_gt_types.h  |   2 +
 drivers/gpu/drm/i915/gt/intel_llc.c       | 161 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_llc.h       |  15 +++
 drivers/gpu/drm/i915/gt/intel_llc_types.h |  13 +++
 drivers/gpu/drm/i915/gt/selftest_gt_pm.c  |   9 ++
 drivers/gpu/drm/i915/gt/selftest_llc.c    |  77 ++++++++++++++
 drivers/gpu/drm/i915/gt/selftest_llc.h    |  14 +++
 drivers/gpu/drm/i915/i915_drv.h           |   5 -
 drivers/gpu/drm/i915/intel_pm.c           | 120 +---------------------
 10 files changed, 297 insertions(+), 120 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/gt/intel_llc.c
 create mode 100644 drivers/gpu/drm/i915/gt/intel_llc.h
 create mode 100644 drivers/gpu/drm/i915/gt/intel_llc_types.h
 create mode 100644 drivers/gpu/drm/i915/gt/selftest_llc.c
 create mode 100644 drivers/gpu/drm/i915/gt/selftest_llc.h

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index e791d9323b51..a16a2daef977 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -87,6 +87,7 @@ gt-y += \
 	gt/intel_gt_pm_irq.o \
 	gt/intel_gt_requests.o \
 	gt/intel_hangcheck.o \
+	gt/intel_llc.o \
 	gt/intel_lrc.o \
 	gt/intel_rc6.o \
 	gt/intel_renderstate.o \
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index be4b263621c8..ae4aaf75ac78 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -17,6 +17,7 @@
 
 #include "i915_vma.h"
 #include "intel_engine_types.h"
+#include "intel_llc_types.h"
 #include "intel_reset_types.h"
 #include "intel_rc6_types.h"
 #include "intel_wakeref.h"
@@ -79,6 +80,7 @@ struct intel_gt {
 	 */
 	intel_wakeref_t awake;
 
+	struct intel_llc llc;
 	struct intel_rc6 rc6;
 
 	struct blocking_notifier_head pm_notifications;
diff --git a/drivers/gpu/drm/i915/gt/intel_llc.c b/drivers/gpu/drm/i915/gt/intel_llc.c
new file mode 100644
index 000000000000..35093eb5f24e
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_llc.c
@@ -0,0 +1,161 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include <linux/cpufreq.h>
+
+#include "i915_drv.h"
+#include "intel_gt.h"
+#include "intel_llc.h"
+#include "intel_sideband.h"
+
+struct ia_constants {
+	unsigned int min_gpu_freq;
+	unsigned int max_gpu_freq;
+
+	unsigned int min_ring_freq;
+	unsigned int max_ia_freq;
+};
+
+static struct intel_gt *llc_to_gt(struct intel_llc *llc)
+{
+	return container_of(llc, struct intel_gt, llc);
+}
+
+static unsigned int cpu_max_MHz(void)
+{
+	struct cpufreq_policy *policy;
+	unsigned int max_khz;
+
+	policy = cpufreq_cpu_get(0);
+	if (policy) {
+		max_khz = policy->cpuinfo.max_freq;
+		cpufreq_cpu_put(policy);
+	} else {
+		/*
+		 * Default to measured freq if none found, PCU will ensure we
+		 * don't go over
+		 */
+		max_khz = tsc_khz;
+	}
+
+	return max_khz / 1000;
+}
+
+static bool get_ia_constants(struct intel_llc *llc,
+			     struct ia_constants *consts)
+{
+	struct drm_i915_private *i915 = llc_to_gt(llc)->i915;
+	struct intel_rps *rps = &i915->gt_pm.rps;
+
+	if (rps->max_freq <= rps->min_freq)
+		return false;
+
+	consts->max_ia_freq = cpu_max_MHz();
+
+	consts->min_ring_freq =
+		intel_uncore_read(llc_to_gt(llc)->uncore, DCLK) & 0xf;
+	/* convert DDR frequency from units of 266.6MHz to bandwidth */
+	consts->min_ring_freq = mult_frac(consts->min_ring_freq, 8, 3);
+
+	consts->min_gpu_freq = rps->min_freq;
+	consts->max_gpu_freq = rps->max_freq;
+	if (INTEL_GEN(i915) >= 9) {
+		/* Convert GT frequency to 50 HZ units */
+		consts->min_gpu_freq /= GEN9_FREQ_SCALER;
+		consts->max_gpu_freq /= GEN9_FREQ_SCALER;
+	}
+
+	return true;
+}
+
+static void calc_ia_freq(struct intel_llc *llc,
+			 unsigned int gpu_freq,
+			 const struct ia_constants *consts,
+			 unsigned int *out_ia_freq,
+			 unsigned int *out_ring_freq)
+{
+	struct drm_i915_private *i915 = llc_to_gt(llc)->i915;
+	const int diff = consts->max_gpu_freq - gpu_freq;
+	unsigned int ia_freq = 0, ring_freq = 0;
+
+	if (INTEL_GEN(i915) >= 9) {
+		/*
+		 * ring_freq = 2 * GT. ring_freq is in 100MHz units
+		 * No floor required for ring frequency on SKL.
+		 */
+		ring_freq = gpu_freq;
+	} else if (INTEL_GEN(i915) >= 8) {
+		/* max(2 * GT, DDR). NB: GT is 50MHz units */
+		ring_freq = max(consts->min_ring_freq, gpu_freq);
+	} else if (IS_HASWELL(i915)) {
+		ring_freq = mult_frac(gpu_freq, 5, 4);
+		ring_freq = max(consts->min_ring_freq, ring_freq);
+		/* leave ia_freq as the default, chosen by cpufreq */
+	} else {
+		const int min_freq = 15;
+		const int scale = 180;
+
+		/*
+		 * On older processors, there is no separate ring
+		 * clock domain, so in order to boost the bandwidth
+		 * of the ring, we need to upclock the CPU (ia_freq).
+		 *
+		 * For GPU frequencies less than 750MHz,
+		 * just use the lowest ring freq.
+		 */
+		if (gpu_freq < min_freq)
+			ia_freq = 800;
+		else
+			ia_freq = consts->max_ia_freq - diff * scale / 2;
+		ia_freq = DIV_ROUND_CLOSEST(ia_freq, 100);
+	}
+
+	*out_ia_freq = ia_freq;
+	*out_ring_freq = ring_freq;
+}
+
+static void gen6_update_ring_freq(struct intel_llc *llc)
+{
+	struct drm_i915_private *i915 = llc_to_gt(llc)->i915;
+	struct ia_constants consts;
+	unsigned int gpu_freq;
+
+	if (!get_ia_constants(llc, &consts))
+		return;
+
+	/*
+	 * For each potential GPU frequency, load a ring frequency we'd like
+	 * to use for memory access.  We do this by specifying the IA frequency
+	 * the PCU should use as a reference to determine the ring frequency.
+	 */
+	for (gpu_freq = consts.max_gpu_freq;
+	     gpu_freq >= consts.min_gpu_freq;
+	     gpu_freq--) {
+		unsigned int ia_freq, ring_freq;
+
+		calc_ia_freq(llc, gpu_freq, &consts, &ia_freq, &ring_freq);
+		sandybridge_pcode_write(i915,
+					GEN6_PCODE_WRITE_MIN_FREQ_TABLE,
+					ia_freq << GEN6_PCODE_FREQ_IA_RATIO_SHIFT |
+					ring_freq << GEN6_PCODE_FREQ_RING_RATIO_SHIFT |
+					gpu_freq);
+	}
+}
+
+void intel_llc_enable(struct intel_llc *llc)
+{
+	if (HAS_LLC(llc_to_gt(llc)->i915))
+		gen6_update_ring_freq(llc);
+}
+
+void intel_llc_disable(struct intel_llc *llc)
+{
+	/* Currently there is no HW configuration to be done to disable. */
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_llc.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_llc.h b/drivers/gpu/drm/i915/gt/intel_llc.h
new file mode 100644
index 000000000000..ef09a890d2b7
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_llc.h
@@ -0,0 +1,15 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_LLC_H
+#define INTEL_LLC_H
+
+struct intel_llc;
+
+void intel_llc_enable(struct intel_llc *llc);
+void intel_llc_disable(struct intel_llc *llc);
+
+#endif /* INTEL_LLC_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_llc_types.h b/drivers/gpu/drm/i915/gt/intel_llc_types.h
new file mode 100644
index 000000000000..ecad4687b930
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_llc_types.h
@@ -0,0 +1,13 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_LLC_TYPES_H
+#define INTEL_LLC_TYPES_H
+
+struct intel_llc {
+};
+
+#endif /* INTEL_LLC_TYPES_H */
diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
index 87985bd46423..5d429037cdad 100644
--- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
@@ -5,6 +5,8 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include "selftest_llc.h"
+
 static int live_gt_resume(void *arg)
 {
 	struct intel_gt *gt = arg;
@@ -32,6 +34,13 @@ static int live_gt_resume(void *arg)
 			err = -EINVAL;
 			break;
 		}
+
+		err = st_llc_verify(&gt->llc);
+		if (err) {
+			pr_err("llc state not restored upon resume!\n");
+			intel_gt_set_wedged_on_init(gt);
+			break;
+		}
 	} while (!__igt_timeout(end_time, NULL));
 
 	return err;
diff --git a/drivers/gpu/drm/i915/gt/selftest_llc.c b/drivers/gpu/drm/i915/gt/selftest_llc.c
new file mode 100644
index 000000000000..a7057785e420
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_llc.c
@@ -0,0 +1,77 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "intel_pm.h" /* intel_gpu_freq() */
+#include "selftest_llc.h"
+
+static int gen6_verify_ring_freq(struct intel_llc *llc)
+{
+	struct drm_i915_private *i915 = llc_to_gt(llc)->i915;
+	struct ia_constants consts;
+	intel_wakeref_t wakeref;
+	unsigned int gpu_freq;
+	int err = 0;
+
+	wakeref = intel_runtime_pm_get(llc_to_gt(llc)->uncore->rpm);
+
+	if (!get_ia_constants(llc, &consts)) {
+		err = -ENODEV;
+		goto out_rpm;
+	}
+
+	for (gpu_freq = consts.min_gpu_freq;
+	     gpu_freq <= consts.max_gpu_freq;
+	     gpu_freq++) {
+		unsigned int ia_freq, ring_freq, found;
+		u32 val;
+
+		calc_ia_freq(llc, gpu_freq, &consts, &ia_freq, &ring_freq);
+
+		val = gpu_freq;
+		if (sandybridge_pcode_read(i915,
+					   GEN6_PCODE_READ_MIN_FREQ_TABLE,
+					   &val, NULL)) {
+			pr_err("Failed to read freq table[%d], range [%d, %d]\n",
+			       gpu_freq, consts.min_gpu_freq, consts.max_gpu_freq);
+			err = -ENXIO;
+			break;
+		}
+
+		found = (val >> 0) & 0xff;
+		if (found != ia_freq) {
+			pr_err("Min freq table(%d/[%d, %d]):%dMHz did not match expected CPU freq, found %d, expected %d\n",
+			       gpu_freq, consts.min_gpu_freq, consts.max_gpu_freq,
+			       intel_gpu_freq(i915, gpu_freq * (INTEL_GEN(i915) >= 9 ? GEN9_FREQ_SCALER : 1)),
+			       found, ia_freq);
+			err = -EINVAL;
+			break;
+		}
+
+		found = (val >> 8) & 0xff;
+		if (found != ring_freq) {
+			pr_err("Min freq table(%d/[%d, %d]):%dMHz did not match expected ring freq, found %d, expected %d\n",
+			       gpu_freq, consts.min_gpu_freq, consts.max_gpu_freq,
+			       intel_gpu_freq(i915, gpu_freq * (INTEL_GEN(i915) >= 9 ? GEN9_FREQ_SCALER : 1)),
+			       found, ring_freq);
+			err = -EINVAL;
+			break;
+		}
+	}
+
+out_rpm:
+	intel_runtime_pm_put(llc_to_gt(llc)->uncore->rpm, wakeref);
+	return err;
+}
+
+int st_llc_verify(struct intel_llc *llc)
+{
+	int err = 0;
+
+	if (HAS_LLC(llc_to_gt(llc)->i915))
+		err = gen6_verify_ring_freq(llc);
+
+	return err;
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_llc.h b/drivers/gpu/drm/i915/gt/selftest_llc.h
new file mode 100644
index 000000000000..873f896e72f2
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_llc.h
@@ -0,0 +1,14 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef SELFTEST_LLC_H
+#define SELFTEST_LLC_H
+
+struct intel_llc;
+
+int st_llc_verify(struct intel_llc *llc);
+
+#endif /* SELFTEST_LLC_H */
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index db3c3a025a03..16b85c7f7f21 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -605,13 +605,8 @@ struct intel_rps {
 	struct intel_rps_ei ei;
 };
 
-struct intel_llc_pstate {
-	bool enabled;
-};
-
 struct intel_gen6_power_mgmt {
 	struct intel_rps rps;
-	struct intel_llc_pstate llc_pstate;
 };
 
 /* defined intel_pm.c */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 2b71d52a4ede..362234449087 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -25,7 +25,6 @@
  *
  */
 
-#include <linux/cpufreq.h>
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 
@@ -38,6 +37,8 @@
 #include "display/intel_fbc.h"
 #include "display/intel_sprite.h"
 
+#include "gt/intel_llc.h"
+
 #include "i915_drv.h"
 #include "i915_irq.h"
 #include "i915_trace.h"
@@ -7030,93 +7031,6 @@ static void gen6_enable_rps(struct drm_i915_private *dev_priv)
 	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
 }
 
-static void gen6_update_ring_freq(struct drm_i915_private *dev_priv)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	const int min_freq = 15;
-	const int scaling_factor = 180;
-	unsigned int gpu_freq;
-	unsigned int max_ia_freq, min_ring_freq;
-	unsigned int max_gpu_freq, min_gpu_freq;
-	struct cpufreq_policy *policy;
-
-	lockdep_assert_held(&rps->lock);
-
-	if (rps->max_freq <= rps->min_freq)
-		return;
-
-	policy = cpufreq_cpu_get(0);
-	if (policy) {
-		max_ia_freq = policy->cpuinfo.max_freq;
-		cpufreq_cpu_put(policy);
-	} else {
-		/*
-		 * Default to measured freq if none found, PCU will ensure we
-		 * don't go over
-		 */
-		max_ia_freq = tsc_khz;
-	}
-
-	/* Convert from kHz to MHz */
-	max_ia_freq /= 1000;
-
-	min_ring_freq = I915_READ(DCLK) & 0xf;
-	/* convert DDR frequency from units of 266.6MHz to bandwidth */
-	min_ring_freq = mult_frac(min_ring_freq, 8, 3);
-
-	min_gpu_freq = rps->min_freq;
-	max_gpu_freq = rps->max_freq;
-	if (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
-		/* Convert GT frequency to 50 HZ units */
-		min_gpu_freq /= GEN9_FREQ_SCALER;
-		max_gpu_freq /= GEN9_FREQ_SCALER;
-	}
-
-	/*
-	 * For each potential GPU frequency, load a ring frequency we'd like
-	 * to use for memory access.  We do this by specifying the IA frequency
-	 * the PCU should use as a reference to determine the ring frequency.
-	 */
-	for (gpu_freq = max_gpu_freq; gpu_freq >= min_gpu_freq; gpu_freq--) {
-		const int diff = max_gpu_freq - gpu_freq;
-		unsigned int ia_freq = 0, ring_freq = 0;
-
-		if (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
-			/*
-			 * ring_freq = 2 * GT. ring_freq is in 100MHz units
-			 * No floor required for ring frequency on SKL.
-			 */
-			ring_freq = gpu_freq;
-		} else if (INTEL_GEN(dev_priv) >= 8) {
-			/* max(2 * GT, DDR). NB: GT is 50MHz units */
-			ring_freq = max(min_ring_freq, gpu_freq);
-		} else if (IS_HASWELL(dev_priv)) {
-			ring_freq = mult_frac(gpu_freq, 5, 4);
-			ring_freq = max(min_ring_freq, ring_freq);
-			/* leave ia_freq as the default, chosen by cpufreq */
-		} else {
-			/* On older processors, there is no separate ring
-			 * clock domain, so in order to boost the bandwidth
-			 * of the ring, we need to upclock the CPU (ia_freq).
-			 *
-			 * For GPU frequencies less than 750MHz,
-			 * just use the lowest ring freq.
-			 */
-			if (gpu_freq < min_freq)
-				ia_freq = 800;
-			else
-				ia_freq = max_ia_freq - ((diff * scaling_factor) / 2);
-			ia_freq = DIV_ROUND_CLOSEST(ia_freq, 100);
-		}
-
-		sandybridge_pcode_write(dev_priv,
-					GEN6_PCODE_WRITE_MIN_FREQ_TABLE,
-					ia_freq << GEN6_PCODE_FREQ_IA_RATIO_SHIFT |
-					ring_freq << GEN6_PCODE_FREQ_RING_RATIO_SHIFT |
-					gpu_freq);
-	}
-}
-
 static int cherryview_rps_max_freq(struct drm_i915_private *dev_priv)
 {
 	u32 val, rp0;
@@ -7965,18 +7879,6 @@ void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv)
 		gen6_reset_rps_interrupts(dev_priv);
 }
 
-static inline void intel_disable_llc_pstate(struct drm_i915_private *i915)
-{
-	lockdep_assert_held(&i915->gt_pm.rps.lock);
-
-	if (!i915->gt_pm.llc_pstate.enabled)
-		return;
-
-	/* Currently there is no HW configuration to be done to disable. */
-
-	i915->gt_pm.llc_pstate.enabled = false;
-}
-
 static void intel_disable_rps(struct drm_i915_private *dev_priv)
 {
 	lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
@@ -8004,23 +7906,11 @@ void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
 
 	intel_disable_rps(dev_priv);
 	if (HAS_LLC(dev_priv))
-		intel_disable_llc_pstate(dev_priv);
+		intel_llc_disable(&dev_priv->gt.llc);
 
 	mutex_unlock(&dev_priv->gt_pm.rps.lock);
 }
 
-static inline void intel_enable_llc_pstate(struct drm_i915_private *i915)
-{
-	lockdep_assert_held(&i915->gt_pm.rps.lock);
-
-	if (i915->gt_pm.llc_pstate.enabled)
-		return;
-
-	gen6_update_ring_freq(i915);
-
-	i915->gt_pm.llc_pstate.enabled = true;
-}
-
 static void intel_enable_rps(struct drm_i915_private *dev_priv)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
@@ -8064,8 +7954,8 @@ void intel_enable_gt_powersave(struct drm_i915_private *dev_priv)
 
 	if (HAS_RPS(dev_priv))
 		intel_enable_rps(dev_priv);
-	if (HAS_LLC(dev_priv))
-		intel_enable_llc_pstate(dev_priv);
+
+	intel_llc_enable(&dev_priv->gt.llc);
 
 	mutex_unlock(&dev_priv->gt_pm.rps.lock);
 }
-- 
cgit v1.2.3


From 7d194c2100ad2a6dded545887d02754948ca5241 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 20 Oct 2019 15:56:22 -0400
Subject: Linux 5.4-rc4

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 19efe04b398c..5475cdb6d57d 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Nesting Opossum
 
 # *DOCUMENTATION*
-- 
cgit v1.2.3


From 952f89f098c75ae4147fc440aaa3b9a209240cea Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 Oct 2019 19:39:01 +0100
Subject: drm/i915/gvt: Wean off struct_mutex

Use the local vgpu_lock while preparing workloads to avoid taking the
obsolete i915->drm.struct_mutex

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191016183902.13614-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gvt/scheduler.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 9ebb2534558b..36bb7639e82f 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -415,10 +415,9 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	int ret;
 
-	lockdep_assert_held(&dev_priv->drm.struct_mutex);
+	lockdep_assert_held(&vgpu->vgpu_lock);
 
 	if (workload->shadow)
 		return 0;
@@ -580,8 +579,6 @@ static void update_vreg_in_ctx(struct intel_vgpu_workload *workload)
 
 static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 {
-	struct intel_vgpu *vgpu = workload->vgpu;
-	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	struct intel_vgpu_shadow_bb *bb, *pos;
 
 	if (list_empty(&workload->shadow_bb))
@@ -590,8 +587,6 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 	bb = list_first_entry(&workload->shadow_bb,
 			struct intel_vgpu_shadow_bb, list);
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
-
 	list_for_each_entry_safe(bb, pos, &workload->shadow_bb, list) {
 		if (bb->obj) {
 			if (bb->accessing)
@@ -609,8 +604,6 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 		list_del(&bb->list);
 		kfree(bb);
 	}
-
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 }
 
 static int prepare_workload(struct intel_vgpu_workload *workload)
@@ -685,7 +678,6 @@ err_unpin_mm:
 static int dispatch_workload(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
-	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	struct i915_request *rq;
 	int ring_id = workload->ring_id;
 	int ret;
@@ -694,7 +686,6 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
 		ring_id, workload);
 
 	mutex_lock(&vgpu->vgpu_lock);
-	mutex_lock(&dev_priv->drm.struct_mutex);
 
 	ret = intel_gvt_workload_req_alloc(workload);
 	if (ret)
@@ -729,7 +720,6 @@ out:
 err_req:
 	if (ret)
 		workload->status = ret;
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 	mutex_unlock(&vgpu->vgpu_lock);
 	return ret;
 }
@@ -1594,9 +1584,9 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id,
 	 */
 	if (list_empty(workload_q_head(vgpu, ring_id))) {
 		intel_runtime_pm_get(&dev_priv->runtime_pm);
-		mutex_lock(&dev_priv->drm.struct_mutex);
+		mutex_lock(&vgpu->vgpu_lock);
 		ret = intel_gvt_scan_and_shadow_workload(workload);
-		mutex_unlock(&dev_priv->drm.struct_mutex);
+		mutex_unlock(&vgpu->vgpu_lock);
 		intel_runtime_pm_put_unchecked(&dev_priv->runtime_pm);
 	}
 
-- 
cgit v1.2.3


From ce53908bba6fa6e905d8fe81da4591d3e7a65878 Mon Sep 17 00:00:00 2001
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Date: Mon, 21 Oct 2019 12:56:07 +0300
Subject: drm/i915: Update DRIVER_DATE to 20191021

Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 16b85c7f7f21..8882c0908c3b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -108,8 +108,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20191007"
-#define DRIVER_TIMESTAMP	1570451087
+#define DRIVER_DATE		"20191021"
+#define DRIVER_TIMESTAMP	1571651766
 
 struct drm_i915_gem_object;
 
-- 
cgit v1.2.3